Merge branch 'html5-parser-work'

148 files changed, 42470 insertions, 0 deletions

diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Big5.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5.java
new file mode 100644
index 000000000..00e5f7ca7
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5.java
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Big5 extends Encoding {
+
+    private static final String[] LABELS = {
+        "big5",
+        "big5-hkscs",
+        "cn-big5",
+        "csbig5",
+        "x-x-big5"
+    };
+    
+    private static final String NAME = "big5";
+    
+    static final Big5 INSTANCE = new Big5();
+    
+    private Big5() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new Big5Decoder(this);
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return new Big5Encoder(this);
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Data.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Data.java
new file mode 100644
index 000000000..9f35be341
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Data.java
@@ -0,0 +1,185 @@
+/*
+ * Copyright (c) 2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+final class Big5Data {
+
+    private static final String ASTRALNESS = "\uF829\u7A22\u1290\uC5C4\u0007\u0200\u7549\"\u0000\uA000\u3859\u0300\u002C\u573E\uF72B\u6EFC\u90F2\u3B7B\u83E9\uF049\u9DA6\uBBFC\uBEF7\uFDFE\u0C83\uABD1\u7BFF\u7FBF\u1804\u002C\u4840\u2046\u0408\u2A22\u4858\u091A\u5100\u3122\uC000\u5000\uC00D\u6110\uD44C\u9A24\u0180\u0004\u92B2\u0209\u8631\u1242\u8140\u0351\uAB48\u7460\uD5A2\u3E5C\uE361\u1083\u720B\u08A0\u51D6\uE00A\u8100\u1686\uC443\u1135\u6037\u7AE6\u056D\u7D0C\u0E66\u81E0\u7F88\u2420\u2406\u1D03\u340C\u4268\u454A\uF13F\u080D\u8084\uBB00\u0C4D\u6ED6\u97D7\u41DF\u5D3E\uDA68\u305C\uB800\u26E9\u80BC\u0151\uE078\u89A1\u59C0\u9679\u3BCC\u5EDE\uBC2C\uDF9B\u6C5D\u046D\u6043\u4A36\uD860\u073E\uC8C4\u6C69\uD8B1\u8302\u0F88\u0973\u806E\u3B6B\u5A17\uA503\u2D52\u3F40\u1120\u4101\u5024\uB903\u90EE\u1079\u5CAD\u1820\uDA0A\u8060\u9E26\u6E73\u1021\u080E\u4368\u6FB2\u161F\u8AFE\u76B6\u763A\u8262\u1894\u1801\uFE7D\u578D\u1327\u5BD2\u1937\uDB8C\u4862\u0024\u0000\u0010\u8000\u0000\u0000\u0038\u3800\uB9E2\uFD7D\u75F8\uDCF7\u6FF3\uBBF2\uFF4A\uAE3F\u9FC5\uEAFF\uBABA\uBC5D\u9F73\uD8FA\uDED6\u4B25\u975E\u2ADA\u6DB9\u06E6\u9D36\u53F9\u6FC5\uF98A\u49BF\uDB5D\uFFF8\u14A6\uE605\u96F7\u0A99\u00E5\u0800\u3D81\u5002\u0102\uBF49\u475E\u036F\u6280\uEECA\u4819\u6081\u205A\u24F7\u0000\u0004\u0000\u2804\u22C8\u0200\u0000\u2010\u5082\u3040\u0001\u0010\u1284\u0041\u0504\u2000\uC100\u3F7F\uB059\u8AC1\uAFAF\uAC05\u033F\u0204\u7280\u420A\u0426\u02D0\u0EC3\u0958\u0A80\u20B5\u9206\u8B77\u0560\u21C9\u4606\u6038\uC048\u24B4\u84DE\uC0E0\u3364\u3154\u300D\u688A\u5F2B\u0626\u8496\uB108\uE890\uA394\u734F\u50B8\u0D11\uDFA4\u4003\u5D20\u8480\u6160\u51CE\u800A\u58B7\u0050\uE862\u6750\u7220\u1228";
+
+    private static final String TABLE0 = "\u43F0\u4C32\u4603\u45A6\u4578\u7267\u4D77\u45B3\u7CB1\u4CE2\u7CC5\u3B95\u4736\u4744\u4C47\u4C40\u42BF\u3617\u7352\u6E8B\u70D2\u4C57\uA351\u474F\u45DA\u4C85\u7C6C\u4D07\u4AA4\u46A1\u6B23\u7225\u5A54\u1A63\u3E06\u3F61\u664D\u56FB\u0000\u7D95\u591D\u8BB9\u3DF4\u9734\u7BEF\u5BDB\u1D5E\u5AA4\u3625\u9EB0\u5AD1\u5BB7\u5CFC\u676E\u8593\u9945\u7461\u749D\u3875\u1D53\u369E\u6021\u3EEC\u58DE\u3AF5\u7AFC\u9F97\u4161\u890D\u31EA\u0A8A\u325E\u430A\u8484\u9F96\u942F\u4930\u8613\u5896\u974A\u9218\u79D0\u7A32\u6660\u6A29\u889D\u744C\u7BC5\u6782\u7A2C\u524F\u9046\u34E6\u73C4\u5DB9\u74C6\u9FC7\u57B3\u492F\u544C\u4131\u368E\u5818\u7A72\u7B65\u8B8F\u46AE\u6E88\u4181\u5D99\u7BAE\u24BC\u9FC8\u24C1\u24C9\u24CC\u9FC9\u8504\u35BB\u40B4\u9FCA\u44E1\uADFF\u62C1\u706E\u9FCB";
+
+    private static final String TABLE1 = "\u31C0\u31C1\u31C2\u31C3\u31C4\u010C\u31C5\u00D1\u00CD\u31C6\u31C7\u00CB\u1FE8\u31C8\u00CA\u31C9\u31CA\u31CB\u31CC\u010E\u31CD\u31CE\u0100\u00C1\u01CD\u00C0\u0112\u00C9\u011A\u00C8\u014C\u00D3\u01D1\u00D2\u0000\u1EBE\u0000\u1EC0\u00CA\u0101\u00E1\u01CE\u00E0\u0251\u0113\u00E9\u011B\u00E8\u012B\u00ED\u01D0\u00EC\u014D\u00F3\u01D2\u00F2\u016B\u00FA\u01D4\u00F9\u01D6\u01D8\u01DA\u01DC\u00FC\u0000\u1EBF\u0000\u1EC1\u00EA\u0261\u23DA\u23DB";
+
+    private static final String TABLE2 = "\uA3A9\u1145\u0000\u650A\u0000\u0000\u4E3D\u6EDD\u9D4E\u91DF\u0000\u0000\u7735\u6491\u4F1A\u4F28\u4FA8\u5156\u5174\u519C\u51E4\u52A1\u52A8\u533B\u534E\u53D1\u53D8\u56E2\u58F0\u5904\u5907\u5932\u5934\u5B66\u5B9E\u5B9F\u5C9A\u5E86\u603B\u6589\u67FE\u6804\u6865\u6D4E\u70BC\u7535\u7EA4\u7EAC\u7EBA\u7EC7\u7ECF\u7EDF\u7F06\u7F37\u827A\u82CF\u836F\u89C6\u8BBE\u8BE2\u8F66\u8F67\u8F6E\u7411\u7CFC\u7DCD\u6946\u7AC9\u5227\u0000\u0000\u0000\u0000\u918C\u78B8\u915E\u80BC\u0000\u8D0B\u80F6\u09E7\u0000\u0000\u809F\u9EC7\u4CCD\u9DC9\u9E0C\u4C3E\u9DF6\u700E\u9E0A\uA133\u35C1\u0000\u6E9A\u823E\u7519\u0000\u4911\u9A6C\u9A8F\u9F99\u7987\u846C\u1DCA\u05D0\u2AE6\u4E24\u4E81\u4E80\u4E87\u4EBF\u4EEB\u4F37\u344C\u4FBD\u3E48\u5003\u5088\u347D\u3493\u34A5\u5186\u5905\u51DB\u51FC\u5205\u4E89\u5279\u5290\u5327\u35C7\u53A9\u3551\u53B0\u3553\u53C2\u5423\u356D\u3572\u3681\u5493\u54A3\u54B4\u54B9\u54D0\u54EF\u5518\u5523\u5528\u3598\u553F\u35A5\u35BF\u55D7\u35C5\u7D84\u5525\u0000\u0C42\u0D15\u512B\u5590\u2CC6\u39EC\u0341\u8E46\u4DB8\u94E5\u4053\u80BE\u777A\u2C38\u3A34\u47D5\u815D\u69F2\u4DEA\u64DD\u0D7C\u0FB4\u0CD5\u10F4\u648D\u8E7E\u0E96\u0C0B\u0F64\u2CA9\u8256\u44D3\u0000\u0D46\u9A4D\u80E9\u47F4\u4EA7\u2CC2\u9AB2\u3A67\u95F4\u3FED\u3506\u52C7\u97D4\u78C8\u2D44\u9D6E\u9815\u0000\u43D9\u60A5\u64B4\u54E3\u2D4C\u2BCA\u1077\u39FB\u106F\u66DA\u6716\u79A0\u64EA\u5052\u0C43\u8E68\u21A1\u8B4C\u0731\u0000\u480B\u01A9\u3FFA\u5873\u2D8D\u0000\u45C8\u04FC\u6097\u0F4C\u0D96\u5579\u40BB\u43BA\u0000\u4AB4\u2A66\u109D\u81AA\u98F5\u0D9C\u6379\u39FE\u2775\u8DC0\u56A1\u647C\u3E43\u0000\uA601\u0E09\u2ACF\u2CC9\u0000\u10C8\u39C2\u3992\u3A06\u829B\u3578\u5E49\u20C7\u5652\u0F31\u2CB2\u9720\u34BC\u6C3D\u4E3B\u0000\u0000\u7574\u2E8B\u2208\uA65B\u8CCD\u0E7A\u0C34\u681C\u7F93\u10CF\u2803\u2939\u35FB\u51E3\u0E8C\u0F8D\u0EAA\u3F93\u0F30\u0D47\u114F\u0E4C\u0000\u0EAB\u0BA9\u0D48\u10C0\u113D\u3FF9\u2696\u6432\u0FAD\u33F4\u7639\u2BCE\u0D7E\u0D7F\u2C51\u2C55\u3A18\u0E98\u10C7\u0F2E\uA632\u6B50\u8CD2\u8D99\u8CCA\u95AA\u54CC\u82C4\u55B9\u0000\u9EC3\u9C26\u9AB6\u775E\u2DEE\u7140\u816D\u80EC\u5C1C\u6572\u8134\u3797\u535F\u80BD\u91B6\u0EFA\u0E0F\u0E77\u0EFB\u35DD\u4DEB\u3609\u0CD6\u56AF\u27B5\u10C9\u0E10\u0E78\u1078\u1148\u8207\u1455\u0E79\u4E50\u2DA4\u5A54\u101D\u101E\u10F5\u10F6\u579C\u0E11\u7694\u82CD\u0FB5\u0E7B\u517E\u3703\u0FB6\u1180\u52D8\uA2BD\u49DA\u183A\u4177\u827C\u5899\u5268\u361A\u573D\u7BB2\u5B68\u4800\u4B2C\u9F27\u49E7\u9C1F\u9B8D\u5B74\u313D\u55FB\u35F2\u5689\u4E28\u5902\u1BC1\uF878\u9751\u0086\u4E5B\u4EBB\u353E\u5C23\u5F51\u5FC4\u38FA\u624C\u6535\u6B7A\u6C35\u6C3A\u706C\u722B\u4E2C\u72AD\u48E9\u7F52\u793B\u7CF9\u7F53\u626A\u34C1\u0000\u634B\u8002\u8080\u6612\u6951\u535D\u8864\u89C1\u78B2\u8BA0\u8D1D\u9485\u9578\u957F\u95E8\u8E0F\u97E6\u9875\u98CE\u98DE\u9963\u9810\u9C7C\u9E1F\u9EC4\u6B6F\uF907\u4E37\u0087\u961D\u6237\u94A2\u0000\u503B\u6DFE\u9C73\u9FA6\u3DC9\u888F\u414E\u7077\u5CF5\u4B20\u51CD\u3559\u5D30\u6122\u8A32\u8FA7\u91F6\u7191\u6719\u73BA\u3281\uA107\u3C8B\u1980\u4B10\u78E4\u7402\u51AE\u870F\u4009\u6A63\uA2BA\u4223\u860F\u0A6F\u7A2A\u9947\u8AEA\u9755\u704D\u5324\u207E\u93F4\u76D9\u89E3\u9FA7\u77DD\u4EA3\u4FF0\u50BC\u4E2F\u4F17\u9FA8\u5434\u7D8B\u5892\u58D0\u1DB6\u5E92\u5E99\u5FC2\u2712\u658B\u33F9\u6919\u6A43\u3C63\u6CFF\u0000\u7200\u4505\u738C\u3EDB\u4A13\u5B15\u74B9\u8B83\u5CA4\u5695\u7A93\u7BEC\u7CC3\u7E6C\u82F8\u8597\u9FA9\u8890\u9FAA\u8EB9\u9FAB\u8FCF\u855F\u99E0\u9221\u9FAC\u8DB9\u143F\u4071\u42A2\u5A1A\u0000\u0000\u0000\u9868\u676B\u4276\u573D\u0000\u85D6\u497B\u82BF\u710D\u4C81\u6D74\u5D7B\u6B15\u6FBE\u9FAD\u9FAE\u5B96\u9FAF\u66E7\u7E5B\u6E57\u79CA\u3D88\u44C3\u3256\u2796\u439A\u4536\u0000\u5CD5\u3B1A\u8AF9\u5C78\u3D12\u3551\u5D78\u9FB2\u7157\u4558\u40EC\u1E23\u4C77\u3978\u344A\u01A4\u6C41\u8ACC\u4FB4\u0239\u59BF\u816C\u9856\u98FA\u5F3B\u0B9F\u0000\u21C1\u896D\u4102\u46BB\u9079\u3F07\u9FB3\uA1B5\u40F8\u37D6\u46F7\u6C46\u417C\u86B2\u73FF\u456D\u38D4\u549A\u4561\u451B\u4D89\u4C7B\u4D76\u45EA\u3FC8\u4B0F\u3661\u44DE\u44BD\u41ED\u5D3E\u5D48\u5D56\u3DFC\u380F\u5DA4\u5DB9\u3820\u3838\u5E42\u5EBD\u5F25\u5F83\u3908\u3914\u393F\u394D\u60D7\u613D\u5CE5\u3989\u61B7\u61B9\u61CF\u39B8\u622C\u6290\u62E5\u6318\u39F8\u56B1\u3A03\u63E2\u63FB\u6407\u645A\u3A4B\u64C0\u5D15\u5621\u9F9F\u3A97\u6586\u3ABD\u65FF\u6653\u3AF2\u6692\u3B22\u6716\u3B42\u67A4\u6800\u3B58\u684A\u6884\u3B72\u3B71\u3B7B\u6909\u6943\u725C\u6964\u699F\u6985\u3BBC\u69D6\u3BDD\u6A65\u6A74\u6A71\u6A82\u3BEC\u6A99\u3BF2\u6AAB\u6AB5\u6AD4\u6AF6\u6B81\u6BC1\u6BEA\u6C75\u6CAA\u3CCB\u6D02\u6D06\u6D26\u6D81\u3CEF\u6DA4\u6DB1\u6E15\u6E18\u6E29\u6E86\u89C0\u6EBB\u6EE2\u6EDA\u9F7F\u6EE8\u6EE9\u6F24\u6F34\u3D46\u3F41\u6F81\u6FBE\u3D6A\u3D75\u71B7\u5C99\u3D8A\u702C\u3D91\u7050\u7054\u706F\u707F\u7089\u0325\u43C1\u35F1\u0ED8\u3ED7\u57BE\u6ED3\u713E\u57E0\u364E\u69A2\u8BE9\u5B74\u7A49\u58E1\u94D9\u7A65\u7A7D\u59AC\u7ABB\u7AB0\u7AC2\u7AC3\u71D1\u648D\u41CA\u7ADA\u7ADD\u7AEA\u41EF\u54B2\u5C01\u7B0B\u7B55\u7B29\u530E\u5CFE\u7BA2\u7B6F\u839C\u5BB4\u6C7F\u7BD0\u8421\u7B92\u7BB8\u5D20\u3DAD\u5C65\u8492\u7BFA\u7C06\u7C35\u5CC1\u7C44\u7C83\u4882\u7CA6\u667D\u4578\u7CC9\u7CC7\u7CE6\u7C74\u7CF3\u7CF5\u7CCE\u7E67\u451D\u6E44\u7D5D\u6ED6\u748D\u7D89\u7DAB\u7135\u7DB3\u7DD2\u4057\u6029\u7DE4\u3D13\u7DF5\u17F9\u7DE5\u836D\u7E1D\u6121\u615A\u7E6E\u7E92\u432B\u946C\u7E27\u7F40\u7F41\u7F47\u7936\u62D0\u99E1\u7F97\u6351\u7FA3\u1661\u0068\u455C\u3766\u4503\u833A\u7FFA\u6489\u8005\u8008\u801D\u8028\u802F\uA087\u6CC3\u803B\u803C\u8061\u2714\u4989\u6626\u3DE3\u66E8\u6725\u80A7\u8A48\u8107\u811A\u58B0\u26F6\u6C7F\u6498\u4FB8\u64E7\u148A\u8218\u185E\u6A53\u4A65\u4A95\u447A\u8229\u0B0D\u6A52\u3D7E\u4FF9\u14FD\u84E2\u8362\u6B0A\u49A7\u3530\u1773\u3DF8\u82AA\u691B\uF994\u41DB\u854B\u82D0\u831A\u0E16\u17B4\u36C1\u317D\u355A\u827B\u82E2\u8318\u3E8B\u6DA3\u6B05\u6B97\u35CE\u3DBF\u831D\u55EC\u8385\u450B\u6DA5\u83AC\u83C1\u83D3\u347E\u6ED4\u6A57\u855A\u3496\u6E42\u2EEF\u8458\u5BE4\u8471\u3DD3\u44E4\u6AA7\u844A\u3CB5\u7958\u84A8\u6B96\u6E77\u6E43\u84DE\u840F\u8391\u44A0\u8493\u84E4\u5C91\u4240\u5CC0\u4543\u8534\u5AF2\u6E99\u4527\u8573\u4516\u67BF\u8616\u8625\u863B\u85C1\u7088\u8602\u1582\u70CD\uF9B2\u456A\u8628\u3648\u18A2\u53F7\u739A\u867E\u8771\uA0F8\u87EE\u2C27\u87B1\u87DA\u880F\u5661\u866C\u6856\u460F\u8845\u8846\u75E0\u3DB9\u75E4\u885E\u889C\u465B\u88B4\u88B5\u63C1\u88C5\u7777\u770F\u8987\u898A\u89A6\u89A9\u89A7\u89BC\u8A25\u89E7\u7924\u7ABD\u8A9C\u7793\u91FE\u8A90\u7A59\u7AE9\u7B3A\u3F8F\u4713\u7B38\u717C\u8B0C\u8B1F\u5430\u5565\u8B3F\u8B4C\u8B4D\u8AA9\u4A7A\u8B90\u8B9B\u8AAF\u16DF\u4615\u884F\u8C9B\u7D54\u7D8F\uF9D4\u3725\u7D53\u8CD6\u7D98\u7DBD\u8D12\u8D03\u1910\u8CDB\u705C\u8D11\u4CC9\u3ED0\u8D77\u8DA9\u8002\u1014\u498A\u3B7C\u81BC\u710C\u7AE7\u8EAD\u8EB6\u8EC3\u92D4\u8F19\u8F2D\u8365\u8412\u8FA5\u9303\uA29F\u0A50\u8FB3\u492A\u89DE\u853D\u3DBB\u5EF8\u3262\u8FF9\uA014\u86BC\u8501\u2325\u3980\u6ED7\u9037\u853C\u7ABE\u9061\u856C\u860B\u90A8\u8713\u90C4\u86E6\u90AE\u90FD\u9167\u3AF0\u91A9\u91C4\u7CAC\u8933\u1E89\u920E\u6C9F\u9241\u9262\u55B9\u92B9\u8AC6\u3C9B\u8B0C\u55DB\u0D31\u932C\u936B\u8AE1\u8BEB\u708F\u5AC3\u8AE2\u8AE5\u4965\u9244\u8BEC\u8C39\u8BFF\u9373\u945B\u8EBC\u9585\u95A6\u9426\u95A0\u6FF6\u42B9\u267A\u86D8\u127C\u3E2E\u49DF\u6C1C\u967B\u9696\u416C\u96A3\u6ED5\u61DA\u96B6\u78F5\u8AE0\u96BD\u53CC\u49A1\u6CB8\u0274\u6410\u90AF\u90E5\u4AD1\u1915\u330A\u9731\u8642\u9736\u4A0F\u453D\u4585\u4AE9\u7075\u5B41\u971B\u975C\u91D5\u9757\u5B4A\u91EB\u975F\u9425\u50D0\u30B7\u30BC\u9789\u979F\u97B1\u97BE\u97C0\u97D2\u97E0\u546C\u97EE\u741C\u9433\u97FF\u97F5\u941D\u797A\u4AD1\u9834\u9833\u984B\u9866\u3B0E\u7175\u3D51\u0630\u415C\u5706\u98CA\u98B7\u98C8\u98C7\u4AFF\u6D27\u16D3\u55B0\u98E1\u98E6\u98EC\u9378\u9939\u4A29\u4B72\u9857\u9905\u99F5\u9A0C\u9A3B\u9A10\u9A58\u5725\u36C4\u90B1\u9BD5\u9AE0\u9AE2\u9B05\u9AF4\u4C0E\u9B14\u9B2D\u8600\u5034\u9B34\u69A8\u38C3\u307D\u9B50\u9B40\u9D3E\u5A45\u1863\u9B8E\u424B\u9C02\u9BFF\u9C0C\u9E68\u9DD4\u9FB7\uA192\uA1AB\uA0E1\uA123\uA1DF\u9D7E\u9D83\uA134\u9E0E\u6888\u9DC4\u215B\uA193\uA220\u193B\uA233\u9D39\uA0B9\uA2B4\u9E90\u9E95\u9E9E\u9EA2\u4D34\u9EAA\u9EAF\u4364\u9EC1\u3B60\u39E5\u3D1D\u4F32\u37BE\u8C2B\u9F02\u9F08\u4B96\u9424\u6DA2\u9F17\u9F16\u9F39\u569F\u568A\u9F45\u99B8\u908B\u97F2\u847F\u9F62\u9F69\u7ADC\u9F8E\u7216\u4BBE\u4975\u49BB\u7177\u49F8\u4348\u4A51\u739E\u8BDA\u18FA\u799F\u897E\u8E36\u9369\u93F3\u8A44\u92EC\u9381\u93CB\u896C\u44B9\u7217\u3EEB\u7772\u7A43\u70D0\u4473\u43F8\u717E\u17EF\u70A3\u18BE\u3599\u3EC7\u1885\u542F\u17F8\u3722\u16FB\u1839\u36E1\u1774\u18D1\u5F4B\u3723\u16C0\u575B\u4A25\u13FE\u12A8\u13C6\u14B6\u8503\u36A6\u8503\u8455\u4994\u7165\u3E31\u555C\u3EFB\u7052\u44F4\u36EE\u999D\u6F26\u67F9\u3733\u3C15\u3DE7\u586C\u1922\u6810\u4057\u373F\u40E1\u408B\u410F\u6C21\u54CB\u569E\u66B1\u5692\u0FDF\u0BA8\u0E0D\u93C6\u8B13\u939C\u4EF8\u512B\u3819\u4436\u4EBC\u0465\u037F\u4F4B\u4F8A\u5651\u5A68\u01AB\u03CB\u3999\u030A\u0414\u3435\u4F29\u02C0\u8EB3\u0275\u8ADA\u020C\u4E98\u50CD\u510D\u4FA2\u4F03\u4A0E\u3E8A\u4F42\u502E\u506C\u5081\u4FCC\u4FE5\u5058\u50FC\u5159\u515B\u515D\u515E\u6E76\u3595\u3E39\u3EBF\u6D72\u1884\u3E89\u51A8\u51C3\u05E0\u44DD\u04A3\u0492\u0491\u8D7A\u8A9C\u070E\u5259\u52A4\u0873\u52E1\u936E\u467A\u718C\u438C\u0C20\u49AC\u10E4\u69D1\u0E1D\u7479\u3EDE\u7499\u7414\u7456\u7398\u4B8E\u4ABC\u408D\u53D0\u3584\u720F\u40C9\u55B4\u0345\u54CD\u0BC6\u571D\u925D\u96F4\u9366\u57DD\u578D\u577F\u363E\u58CB\u5A99\u8A46\u16FA\u176F\u1710\u5A2C\u59B8\u928F\u5A7E\u5ACF\u5A12\u5946\u19F3\u1861\u4295\u36F5\u6D05\u7443\u5A21\u5E83\u5A81\u8BD7\u0413\u93E0\u748C\u1303\u7105\u4972\u9408\u89FB\u93BD\u37A0\u5C1E\u5C9E\u5E5E\u5E48\u1996\u197C\u3AEE\u5ECD\u5B4F\u1903\u1904\u3701\u18A0\u36DD\u16FE\u36D3\u812A\u8A47\u1DBA\u3472\u89A8\u5F0C\u5F0E\u1927\u17AB\u5A6B\u173B\u5B44\u8614\u75FD\u8860\u607E\u2860\u262B\u5FDB\u3EB8\u25AF\u25BE\u9088\u6F73\u61C0\u003E\u0046\u261B\u6199\u6198\u6075\u2C9B\u2D07\u46D4\u914D\u6471\u4665\u2B6A\u3A29\u2B22\u3450\u98EA\u2E78\u6337\uA45B\u64B6\u6331\u63D1\u49E3\u2D67\u62A4\u2CA1\u643B\u656B\u6972\u3BF4\u308E\u32AD\u4989\u32AB\u550D\u32E0\u18D9\u943F\u66CE\u3289\u31B3\u3AE0\u4190\u5584\u8B22\u558F\u16FC\u555B\u5425\u78EE\u3103\u182A\u3234\u3464\u320F\u3182\u42C9\u668E\u6D24\u666B\u4B93\u6630\u7870\u1DEB\u6663\u32D2\u32E1\u661E\u5872\u38D1\u383A\u37BC\u3B99\u37A2\u33FE\u74D0\u3B96\u678F\u462A\u68B6\u681E\u3BC4\u6ABE\u3863\u37D5\u4487\u6A33\u6A52\u6AC9\u6B05\u1912\u6511\u6898\u6A4C\u3BD7\u6A7A\u6B57\u3FC0\u3C9A\u93A0\u92F2\u8BEA\u8ACB\u9289\u801E\u89DC\u9467\u6DA5\u6F0B\u49EC\u6D67\u3F7F\u3D8F\u6E04\u403C\u5A3D\u6E0A\u5847\u6D24\u7842\u713B\u431A\u4276\u70F1\u7250\u7287\u7294\u478F\u4725\u5179\u4AA4\u05EB\u747A\u3EF8\u365F\u4A4A\u4917\u5FE1\u3F06\u3EB1\u4ADF\u8C23\u3F35\u60A7\u3EF3\u74CC\u743C\u9387\u7437\u449F\u6DEA\u4551\u7583\u3F63\u4CD9\u4D06\u3F58\u7555\u7673\uA5C6\u3B19\u7468\u8ACC\u49AB\u498E\u3AFB\u3DCD\u4A4E\u3EFF\u49C5\u48F3\u91FA\u5732\u9342\u8AE3\u1864\u50DF\u5221\u51E7\u7778\u3232\u770E\u770F\u777B\u4697\u3781\u3A5E\u48F0\u7438\u749B\u3EBF\u4ABA\u4AC7\u40C8\u4A96\u61AE\u9307\u5581\u781E\u788D\u7888\u78D2\u73D0\u7959\u7741\u56E3\u410E\u799B\u8496\u79A5\u6A2D\u3EFA\u7A3A\u79F4\u416E\u16E6\u4132\u9235\u79F1\u0D4C\u498C\u0299\u3DBA\u176E\u3597\u556B\u3570\u36AA\u01D4\u0C0D\u7AE2\u5A59\u26F5\u5AAF\u5A9C\u5A0D\u025B\u78F0\u5A2A\u5BC6\u7AFE\u41F9\u7C5D\u7C6D\u4211\u5BB3\u5EBC\u5EA6\u7CCD\u49F9\u17B0\u7C8E\u7C7C\u7CAE\u6AB2\u7DDC\u7E07\u7DD3\u7F4E\u6261\u615C\u7B48\u7D97\u5E82\u426A\u6B75\u0916\u67D6\u004E\u35CF\u57C4\u6412\u63F8\u4962\u7FDD\u7B27\u082C\u5AE9\u5D43\u7B0C\u5E0E\u99E6\u8645\u9A63\u6A1C\u343F\u39E2\u49F7\u65AD\u9A1F\u65A0\u8480\u7127\u6CD1\u44EA\u8137\u4402\u80C6\u8109\u8142\u67B4\u98C3\u6A42\u8262\u8265\u6A51\u8453\u6DA7\u8610\u721B\u5A86\u417F\u1840\u5B2B\u18A1\u5AE4\u18D8\u86A0\uF9BC\u3D8F\u882D\u7422\u5A02\u886E\u4F45\u8887\u88BF\u88E6\u8965\u894D\u5683\u8954\u7785\u7784\u8BF5\u8BD9\u8B9C\u89F9\u3EAD\u84A3\u46F5\u46CF\u37F2\u8A3D\u8A1C\u9448\u5F4D\u922B\u4284\u65D4\u7129\u70C4\u1845\u9D6D\u8C9F\u8CE9\u7DDC\u599A\u77C3\u59F0\u436E\u36D4\u8E2A\u8EA7\u4C09\u8F30\u8F4A\u42F4\u6C58\u6FBB\u2321\u489B\u6F79\u6E8B\u17DA\u9BE9\u36B5\u492F\u90BB\u9097\u5571\u4906\u91BB\u9404\u8A4B\u4062\u8AFC\u9427\u8C1D\u8C3B\u84E5\u8A2B\u9599\u95A7\u9597\u9596\u8D34\u7445\u3EC2\u48FF\u4A42\u43EA\u3EE7\u3225\u968F\u8EE7\u8E66\u8E65\u3ECC\u49ED\u4A78\u3FEE\u7412\u746B\u3EFC\u9741\u90B0\u6847\u4A1D\u9093\u57DF\u975D\u9368\u8989\u8C26\u8B2F\u63BE\u92BA\u5B11\u8B69\u493C\u73F9\u421B\u979B\u9771\u9938\u0F26\u5DC1\u8BC5\u4AB2\u981F\u94DA\u92F6\u95D7\u91E5\u44C0\u8B50\u4A67\u8B64\u98DC\u8A45\u3F00\u922A\u4925\u8414\u993B\u994D\u7B06\u3DFD\u999B\u4B6F\u99AA\u9A5C\u8B65\u58C8\u6A8F\u9A21\u5AFE\u9A2F\u98F1\u4B90\u9948\u99BC\u4BBD\u4B97\u937D\u5872\u1302\u5822\u49B8\u14E8\u7844\u271F\u3DB8\u68C5\u3D7D\u9458\u3927\u6150\u2781\u296B\u6107\u9C4F\u9C53\u9C7B\u9C35\u9C10\u9B7F\u9BCF\u9E2D\u9B9F\uA1F5\uA0FE\u9D21\u4CAE\u4104\u9E18\u4CB0\u9D0C\uA1B4\uA0ED\uA0F3\u992F\u9DA5\u84BD\u6E12\u6FDF\u6B82\u85FC\u4533\u6DA4\u6E84\u6DF0\u8420\u85EE\u6E00\u37D7\u6064\u79E2\u359C\u3640\u492D\u49DE\u3D62\u93DB\u92BE\u9348\u02BF\u78B9\u9277\u944D\u4FE4\u3440\u9064\u555D\u783D\u7854\u78B6\u784B\u1757\u31C9\u4941\u369A\u4F72\u6FDA\u6FD9\u701E\u701E\u5414\u41B5\u57BB\u58F3\u578A\u9D16\u57D7\u7134\u34AF\u41AC\u71EB\u6C40\u4F97\u5B28\u17B5\u8A49\u610C\u5ACE\u5A0B\u42BC\u4488\u372C\u4B7B\u89FC\u93BB\u93B8\u18D6\u0F1D\u8472\u6CC0\u1413\u42FA\u2C26\u43C1\u5994\u3DB7\u6741\u7DA8\u615B\u60A4\u49B9\u498B\u89FA\u92E5\u73E2\u3EE9\u74B4\u8B63\u189F\u3EE1\u4AB3\u6AD8\u73F3\u73FB\u3ED6\u4A3E\u4A94\u17D9\u4A66\u03A7\u1424\u49E5\u7448\u4916\u70A5\u4976\u9284\u73E6\u935F\u04FE\u9331\u8ACE\u8A16\u9386\u8BE7\u55D5\u4935\u8A82\u716B\u4943\u0CFF\u56A4\u061A\u0BEB\u0CB8\u5502\u79C4\u17FA\u7DFE\u16C2\u4A50\u1852\u452E\u9401\u370A\u8AC0\u49AD\u59B0\u18BF\u1883\u7484\u5AA1\u36E2\u3D5B\u36B0\u925F\u5A79\u8A81\u1862\u9374\u3CCD\u0AB4\u4A96\u398A\u50F4\u3D69\u3D4C\u139C\u7175\u42FB\u8218\u6E0F\u90E4\u44EB\u6D57\u7E4F\u7067\u6CAF\u3CD6\u3FED\u3E2D\u6E02\u6F0C\u3D6F\u03F5\u7551\u36BC\u34C8\u4680\u3EDA\u4871\u59C4\u926E\u493E\u8F41\u8C1C\u6BC0\u5812\u57C8\u36D6\u1452\u70FE\u4362\u4A71\u2FE3\u12B0\u23BD\u68B9\u6967\u1398\u34E5\u7BF4\u36DF\u8A83\u37D6\u33FA\u4C9F\u6A1A\u36AD\u6CB7\u843E\u44DF\u44CE\u6D26\u6D51\u6C82\u6FDE\u6F17\u7109\u833D\u173A\u83ED\u6C80\u7053\u17DB\u5989\u5A82\u17B3\u5A61\u5A71\u1905\u41FC\u372D\u59EF\u173C\u36C7\u718E\u9390\u669A\u42A5\u5A6E\u5A2B\u4293\u6A2B\u3EF9\u7736\u445B\u42CA\u711D\u4259\u89E1\u4FB0\u6D28\u5CC2\u44CE\u7E4D\u43BD\u6A0C\u4256\u1304\u70A6\u7133\u43E9\u3DA5\u6CDF\uF825\u4A4F\u7E65\u59EB\u5D2F\u3DF3\u5F5C\u4A5D\u17DF\u7DA4\u8426\u5485\u3AFA\u3300\u0214\u577E\u08D5\u0619\u3FE5\u1F9E\uA2B6\u7003\u915B\u5D70\u738F\u7CD3\u8A59\u9420\u4FC8\u7FE7\u72CD\u7310\u7AF4\u7338\u7339\u56F6\u7341\u7348\u3EA9\u7B18\u906C\u71F5\u48F2\u73E1\u81F6\u3ECA\u770C\u3ED1\u6CA2\u56FD\u7419\u741E\u741F\u3EE2\u3EF0\u3EF4\u3EFA\u74D3\u3F0E\u3F53\u7542\u756D\u7572\u758D\u3F7C\u75C8\u75DC\u3FC0\u764D\u3FD7\u7674\u3FDC\u767A\u4F5C\u7188\u5623\u8980\u5869\u401D\u7743\u4039\u6761\u4045\u35DB\u7798\u406A\u406F\u5C5E\u77BE\u77CB\u58F2\u7818\u70B9\u781C\u40A8\u7839\u7847\u7851\u7866\u8448\u5535\u7933\u6803\u7932\u4103\u4109\u7991\u7999\u8FBB\u7A06\u8FBC\u4167\u7A91\u41B2\u7ABC\u8279\u41C4\u7ACF\u7ADB\u41CF\u4E21\u7B62\u7B6C\u7B7B\u7C12\u7C1B\u4260\u427A\u7C7B\u7C9C\u428C\u7CB8\u4294\u7CED\u8F93\u70C0\u0CCF\u7DCF\u7DD4\u7DD0\u7DFD\u7FAE\u7FB4\u729F\u4397\u8020\u8025\u7B39\u802E\u8031\u8054\u3DCC\u57B4\u70A0\u80B7\u80E9\u43ED\u810C\u732A\u810E\u8112\u7560\u8114\u4401\u3B39\u8156\u8159\u815A\u4413\u583A\u817C\u8184\u4425\u8193\u442D\u81A5\u57EF\u81C1\u81E4\u8254\u448F\u82A6\u8276\u82CA\u82D8\u82FF\u44B0\u8357\u9669\u698A\u8405\u70F5\u8464\u60E3\u8488\u4504\u84BE\u84E1\u84F8\u8510\u8538\u8552\u453B\u856F\u8570\u85E0\u4577\u8672\u8692\u86B2\u86EF\u9645\u878B\u4606\u4617\u88AE\u88FF\u8924\u8947\u8991\u7967\u8A29\u8A38\u8A94\u8AB4\u8C51\u8CD4\u8CF2\u8D1C\u4798\u585F\u8DC3\u47ED\u4EEE\u8E3A\u55D8\u5754\u8E71\u55F5\u8EB0\u4837\u8ECE\u8EE2\u8EE4\u8EED\u8EF2\u8FB7\u8FC1\u8FCA\u8FCC\u9033\u99C4\u48AD\u98E0\u9213\u491E\u9228\u9258\u926B\u92B1\u92AE\u92BF\u92E3\u92EB\u92F3\u92F4\u92FD\u9343\u9384\u93AD\u4945\u4951\u9EBF\u9417\u5301\u941D\u942D\u943E\u496A\u9454\u9479\u952D\u95A2\u49A7\u95F4\u9633\u49E5\u67A0\u4A24\u9740\u4A35\u97B2\u97C2\u5654\u4AE4\u60E8\u98B9\u4B19\u98F1\u5844\u990E\u9919\u51B4\u991C\u9937\u9942\u995D\u9962\u4B70\u99C5\u4B9D\u9A3C\u9B0F\u7A83\u9B69\u9B81\u9BDD\u9BF1\u9BF4\u4C6D\u9C20\u376F\u1BC2\u9D49\u9C3A\u9EFE\u5650\u9D93\u9DBD\u9DC0\u9DFC\u94F6\u8FB6\u9E7B\u9EAC\u9EB1\u9EBD\u9EC6\u94DC\u9EE2\u9EF1\u9EF8\u7AC8\u9F44\u0094\u02B7\u03A0\u691A\u94C3\u59AC\u04D7\u5840\u94C1\u37B9\u05D5\u0615\u0676\u16BA\u5757\u7173\u0AC2\u0ACD\u0BBF\u546A\uF83B\u0BCB\u549E\u0BFB\u0C3B\u0C53\u0C65\u0C7C\u60E7\u0C8D\u567A\u0CB5\u0CDD\u0CED\u0D6F\u0DB2\u0DC8\u6955\u9C2F\u87A5\u0E04\u0E0E\u0ED7\u0F90\u0F2D\u0E73\u5C20\u0FBC\u5E0B\u105C\u104F\u1076\u671E\u107B\u1088\u1096\u3647\u10BF\u10D3\u112F\u113B\u5364\u84AD\u12E3\u1375\u1336\u8B81\u1577\u1619\u17C3\u17C7\u4E78\u70BB\u182D\u196A\u1A2D\u1A45\u1C2A\u1C70\u1CAC\u1EC8\u62C3\u1ED5\u1F15\u7198\u6855\u2045\u69E9\u36C8\u227C\u23D7\u23FA\u272A\u2871\u294F\u82FD\u2967\u2993\u2AD5\u89A5\u2AE8\u8FA0\u2B0E\u97B8\u2B3F\u9847\u9ABD\u2C4C\u0000\u2C88\u2CB7\u5BE8\u2D08\u2D12\u2DB7\u2D95\u2E42\u2F74\u2FCC\u3033\u3066\u331F\u33DE\u5FB1\u6648\u66BF\u7A79\u3567\u35F3\u7201\u49BA\u77D7\u361A\u3716\u7E87\u0346\u58B5\u670E\u6918\u3AA7\u7657\u5FE2\u3E11\u3EB9\u75FE\u209A\u48D0\u4AB8\u4119\u8A9A\u42EE\u430D\u403B\u4334\u4396\u4A45\u05CA\u51D2\u0611\u599F\u1EA8\u3BBE\u3CFF\u4404\u44D6\u5788\u4674\u399B\u472F\u85E8\u99C9\u3762\u21C3\u8B5E\u8B4E\u99D6\u4812\u48FB\u4A15\u7209\u4AC0\u0C78\u5965\u4EA5\u4F86\u0779\u8EDA\u502C\u528F\u573F\u7171\u5299\u5419\u3F4A\u4AA7\u55BC\u5446\u546E\u6B52\u91D4\u3473\u553F\u7632\u555E\u4718\u5562\u5566\u57C7\u493F\u585D\u5066\u34FB\u33CC\u60DE\u5903\u477C\u8948\u5AAE\u5B89\u5C06\u1D90\u57A1\u7151\u6FB6\u6102\u7C12\u9056\u61B2\u4F9A\u8B62\u6402\u644A\u5D5B\u6BF7\u8F36\u6484\u191C\u8AEA\u49F6\u6488\u3FEF\u6512\u4BC0\u65BF\u66B5\u271B\u9465\u57E1\u6195\u5A27\uF8CD\u4FBB\u56B9\u4521\u66FC\u4E6A\u4934\u9656\u6D8F\u6CBD\u3618\u8977\u6799\u686E\u6411\u685E\u71DF\u68C7\u7B42\u90C0\u0A11\u6926\u9104\u6939\u7A45\u9DF0\u69FA\u9A26\u6A2D\u365F\u6469\u0021\u7983\u6A34\u6B5B\u5D2C\u3519\u83CF\u6B9D\u46D0\u6CA4\u753B\u8865\u6DAE\u58B6\u371C\u258D\u704B\u71CD\u3C54\u7280\u7285\u9281\u217A\u728B\u9330\u72E6\u49D0\u6C39\u949F\u7450\u0EF8\u8827\u88F5\u2926\u8473\u17B1\u6EB8\u4A2A\u1820\u39A4\u36B9\u5C10\u79E3\u453F\u66B6\u9CAD\u98A4\u8943\u77CC\u7858\u56D6\u40DF\u160A\u39A1\u372F\u80E8\u13C5\u71AD\u8366\u79DD\u91A8\u5A67\u4CB7\u70AF\u89AB\u79FD\u7A0A\u7B0B\u7D66\u417A\u7B43\u797E\u8009\u6FB5\uA2DF\u6A03\u8318\u53A2\u6E07\u93BF\u6836\u975D\u816F\u8023\u69B5\u13ED\u322F\u8048\u5D85\u8C30\u8083\u5715\u9823\u8949\u5DAB\u4988\u65BE\u69D5\u53D2\u4AA5\u3F81\u3C11\u6736\u8090\u80F4\u812E\u1FA1\u814F\u8189\u81AF\u821A\u8306\u832F\u838A\u35CA\u8468\u86AA\u48FA\u63E6\u8956\u7808\u9255\u89B8\u43F2\u89E7\u43DF\u89E8\u8B46\u8BD4\u59F8\u8C09\u8F0B\u8FC5\u90EC\u7B51\u9110\u913C\u3DF7\u915E\u4ACA\u8FD0\u728F\u568B\u94E7\u95E9\u95B0\u95B8\u9732\u98D1\u9949\u996A\u99C3\u9A28\u9B0E\u9D5A\u9D9B\u7E9F\u9EF8\u9F23\u4CA4\u9547\uA293\u71A2\uA2FF\u4D91\u9012\uA5CB\u4D9C\u0C9C\u8FBE\u55C1\u8FBA\u24B0\u8FB9\u4A93\u4509\u7E7F\u6F56\u6AB1\u4EEA\u34E4\u8B2C\u789D\u373A\u8E80\u17F5\u8024\u8B6C\u8B99\u7A3E\u66AF\u3DEB\u7655\u3CB7\u5635\u5956\u4E9A\u5E81\u6258\u56BF\u0E6D\u8E0E\u5B6D\u3E88\u4C9E\u63DE\u62D0\u17F6\u187B\u6530\u562D\u5C4A\u541A\u5311\u3DC6\u9D98\u4C7D\u5622\u561E\u7F49\u5ED8\u5975\u3D40\u8770\u4E1C\u0FEA\u0D49\u36BA\u8117\u9D5E\u8D18\u763B\u9C45\u764E\u77B9\u9345\u5432\u8148\u82F7\u5625\u8132\u8418\u80BD\u55EA\u7962\u5643\u5416\u0E9D\u35CE\u5605\u55F1\u66F1\u82E2\u362D\u7534\u55F0\u55BA\u5497\u5572\u0C41\u0C96\u5ED0\u5148\u0E76\u2C62\u0EA2\u9EAB\u7D5A\u55DE\u1075\u629D\u976D\u5494\u8CCD\u71F6\u9176\u63FC\u63B9\u63FE\u5569\u2B43\u9C72\u2EB3\u519A\u34DF\u0DA7\u51A7\u544D\u551E\u5513\u7666\u8E2D\u688A\u75B1\u80B6\u8804\u8786\u88C7\u81B6\u841C\u10C1\u44EC\u7304\u4706\u5B90\u830B\u6893\u567B\u26F4\u7D2F\u41A3\u7D73\u6ED0\u72B6\u9170\u11D9\u9208\u3CFC\uA6A9\u0EAC\u0EF9\u7266\u1CA2\u474E\u4FC2\u7FF9\u0FEB\u40FA\u9C5D\u651F\u2DA0\u48F3\u47E0\u9D7C\u0FEC\u0E0A\u6062\u75A3\u0FED\u0000\u6048\u1187\u71A3\u7E8E\u9D50\u4E1A\u4E04\u3577\u5B0D\u6CB2\u5367\u36AC\u39DC\u537D\u36A5\u4618\u589A\u4B6E\u822D\u544B\u57AA\u5A95\u0979\u0000\u3A52\u2465\u7374\u9EAC\u4D09\u9BED\u3CFE\u9F30\u4C5B\u4FA9\u959E\u9FDE\u845C\u3DB6\u72B2\u67B3\u3720\u632E\u7D25\u3EF7\u3E2C\u3A2A\u9008\u52CC\u3E74\u367A\u45E9\u048E\u7640\u5AF0\u0EB6\u787A\u7F2E\u58A7\u40BF\u567C\u9B8B\u5D74\u7654\uA434\u9E85\u4CE1\u75F9\u37FB\u6119\u30DA\u43F2\u0000\u565D\u12A9\u57A7\u4963\u9E06\u5234\u70AE\u35AD\u6C4A\u9D7C\u7C56\u9B39\u57DE\u176C\u5C53\u64D3\u94D0\u6335\u7164\u86AD\u0D28\u6D22\u4AE2\u0D71\u0000\u51FE\u1F0F\u5D8E\u9703\u1DD1\u9E81\u904C\u7B1F\u9B02\u5CD1\u7BA3\u6268\u6335\u9AFF\u7BCF\u9B2A\u7C7E\u9B2E\u7C42\u7C86\u9C15\u7BFC\u9B09\u9F17\u9C1B\u493E\u9F5A\u5573\u5BC3\u4FFD\u9E98\u4FF2\u5260\u3E06\u52D1\u5767\u5056\u59B7\u5E12\u97C8\u9DAB\u8F5C\u5469\u97B4\u9940\u97BA\u532C\u6130\u692C\u53DA\u9C0A\u9D02\u4C3B\u9641\u6980\u50A6\u7546\u176D\u99DA\u5273\u0000\u9159\u9681\u915C\u0000\u9151\u8E97\u637F\u6D23\u6ACA\u5611\u918E\u757A\u6285\u03FC\u734F\u7C70\u5C21\u3CFD\u0000\u4919\u76D6\u9B9D\u4E2A\u0CD4\u83BE\u8842\u0000\u5C4A\u69C0\u50ED\u577A\u521F\u5DF5\u4ECE\u6C31\u01F2\u4F39\u549C\u54DA\u529A\u8D82\u35FE\u5F0C\u35F3\u0000\u6B52\u917C\u9FA5\u9B97\u982E\u98B4\u9ABA\u9EA8\u9E84\u717A\u7B14\u0000\u6BFA\u8818\u7F78\u0000\u5620\uA64A\u8E77\u9F53\u0000\u8DD4\u8E4F\u9E1C\u8E01\u6282\u837D\u8E28\u8E75\u7AD3\u4A77\u7A3E\u78D8\u6CEA\u8A67\u7607\u8A5A\u9F26\u6CCE\u87D6\u75C3\uA2B2\u7853\uF840\u8D0C\u72E2\u7371\u8B2D\u7302\u74F1\u8CEB\u4ABB\u862F\u5FBA\u88A0\u44B7\u0000\u183B\u6E05\u0000\u8A7E\u251B\u0000\u60FD\u7667\u9AD7\u9D44\u936E\u9B8F\u87F5\u0000\u880F\u8CF7\u732C\u9721\u9BB0\u35D6\u72B2\u4C07\u7C51\u994A\u6159\u6159\u4C04\u9E96\u617D\u0000\u575F\u616F\u62A6\u6239\u62CE\u3A5C\u61E2\u53AA\u33F5\u6364\u6802\u35D2\u5D57\u8BC2\u8FDA\u8E39\u0000\u50D9\u1D46\u7906\u5332\u9638\u0F3B\u4065\u0000\u77FE\u0000\u7CC2\u5F1A\u7CDA\u7A2D\u8066\u8063\u7D4D\u7505\u74F2\u8994\u821A\u670C\u8062\u7486\u805B\u74F0\u8103\u7724\u8989\u67CC\u7553\u6ED1\u87A9\u87CE\u81C8\u878C\u8A49\u8CAD\u8B43\u772B\u74F8\u84DA\u3635\u69B2\u8DA6\u0000\u89A9\u7468\u6DB9\u87C1\u4011\u74E7\u3DDB\u7176\u60A4\u619C\u3CD1\u7162\u6077\u0000\u7F71\u8B2D\u7250\u60E9\u4B7E\u5220\u3C18\u3CC7\u5ED7\u7656\u5531\u1944\u12FE\u9903\u6DDC\u70AD\u5CC1\u61AD\u8A0F\u3677\u00EE\u6846\u4F0E\u4562\u5B1F\u634C\u9F50\u9EA6\u626B\u3000\uFF0C\u3001\u3002\uFF0E\u2027\uFF1B\uFF1A\uFF1F\uFF01\uFE30\u2026\u2025\uFE50\uFE51\uFE52\u00B7\uFE54\uFE55\uFE56\uFE57\uFF5C\u2013\uFE31\u2014\uFE33\u2574\uFE34\uFE4F\uFF08\uFF09\uFE35\uFE36\uFF5B\uFF5D\uFE37\uFE38\u3014\u3015\uFE39\uFE3A\u3010\u3011\uFE3B\uFE3C\u300A\u300B\uFE3D\uFE3E\u3008\u3009\uFE3F\uFE40\u300C\u300D\uFE41\uFE42\u300E\u300F\uFE43\uFE44\uFE59\uFE5A\uFE5B\uFE5C\uFE5D\uFE5E\u2018\u2019\u201C\u201D\u301D\u301E\u2035\u2032\uFF03\uFF06\uFF0A\u203B\u00A7\u3003\u25CB\u25CF\u25B3\u25B2\u25CE\u2606\u2605\u25C7\u25C6\u25A1\u25A0\u25BD\u25BC\u32A3\u2105\u00AF\uFFE3\uFF3F\u02CD\uFE49\uFE4A\uFE4D\uFE4E\uFE4B\uFE4C\uFE5F\uFE60\uFE61\uFF0B\uFF0D\u00D7\u00F7\u00B1\u221A\uFF1C\uFF1E\uFF1D\u2266\u2267\u2260\u221E\u2252\u2261\uFE62\uFE63\uFE64\uFE65\uFE66\uFF5E\u2229\u222A\u22A5\u2220\u221F\u22BF\u33D2\u33D1\u222B\u222E\u2235\u2234\u2640\u2642\u2295\u2299\u2191\u2193\u2190\u2192\u2196\u2197\u2199\u2198\u2225\u2223\uFF0F\uFF3C\u2215\uFE68\uFF04\uFFE5\u3012\uFFE0\uFFE1\uFF05\uFF20\u2103\u2109\uFE69\uFE6A\uFE6B\u33D5\u339C\u339D\u339E\u33CE\u33A1\u338E\u338F\u33C4\u00B0\u5159\u515B\u515E\u515D\u5161\u5163\u55E7\u74E9\u7CCE\u2581\u2582\u2583\u2584\u2585\u2586\u2587\u2588\u258F\u258E\u258D\u258C\u258B\u258A\u2589\u253C\u2534\u252C\u2524\u251C\u2594\u2500\u2502\u2595\u250C\u2510\u2514\u2518\u256D\u256E\u2570\u256F\u2550\u255E\u256A\u2561\u25E2\u25E3\u25E5\u25E4\u2571\u2572\u2573\uFF10\uFF11\uFF12\uFF13\uFF14\uFF15\uFF16\uFF17\uFF18\uFF19\u2160\u2161\u2162\u2163\u2164\u2165\u2166\u2167\u2168\u2169\u3021\u3022\u3023\u3024\u3025\u3026\u3027\u3028\u3029\u5341\u5344\u5345\uFF21\uFF22\uFF23\uFF24\uFF25\uFF26\uFF27\uFF28\uFF29\uFF2A\uFF2B\uFF2C\uFF2D\uFF2E\uFF2F\uFF30\uFF31\uFF32\uFF33\uFF34\uFF35\uFF36\uFF37\uFF38\uFF39\uFF3A\uFF41\uFF42\uFF43\uFF44\uFF45\uFF46\uFF47\uFF48\uFF49\uFF4A\uFF4B\uFF4C\uFF4D\uFF4E\uFF4F\uFF50\uFF51\uFF52\uFF53\uFF54\uFF55\uFF56\uFF57\uFF58\uFF59\uFF5A\u0391\u0392\u0393\u0394\u0395\u0396\u0397\u0398\u0399\u039A\u039B\u039C\u039D\u039E\u039F\u03A0\u03A1\u03A3\u03A4\u03A5\u03A6\u03A7\u03A8\u03A9\u03B1\u03B2\u03B3\u03B4\u03B5\u03B6\u03B7\u03B8\u03B9\u03BA\u03BB\u03BC\u03BD\u03BE\u03BF\u03C0\u03C1\u03C3\u03C4\u03C5\u03C6\u03C7\u03C8\u03C9\u3105\u3106\u3107\u3108\u3109\u310A\u310B\u310C\u310D\u310E\u310F\u3110\u3111\u3112\u3113\u3114\u3115\u3116\u3117\u3118\u3119\u311A\u311B\u311C\u311D\u311E\u311F\u3120\u3121\u3122\u3123\u3124\u3125\u3126\u3127\u3128\u3129\u02D9\u02C9\u02CA\u02C7\u02CB\u2400\u2401\u2402\u2403\u2404\u2405\u2406\u2407\u2408\u2409\u240A\u240B\u240C\u240D\u240E\u240F\u2410\u2411\u2412\u2413\u2414\u2415\u2416\u2417\u2418\u2419\u241A\u241B\u241C\u241D\u241E\u241F\u2421\u20AC";
+
+    private static final String TABLE3 = "\u4E00\u4E59\u4E01\u4E03\u4E43\u4E5D\u4E86\u4E8C\u4EBA\u513F\u5165\u516B\u51E0\u5200\u5201\u529B\u5315\u5341\u535C\u53C8\u4E09\u4E0B\u4E08\u4E0A\u4E2B\u4E38\u51E1\u4E45\u4E48\u4E5F\u4E5E\u4E8E\u4EA1\u5140\u5203\u52FA\u5343\u53C9\u53E3\u571F\u58EB\u5915\u5927\u5973\u5B50\u5B51\u5B53\u5BF8\u5C0F\u5C22\u5C38\u5C71\u5DDD\u5DE5\u5DF1\u5DF2\u5DF3\u5DFE\u5E72\u5EFE\u5F0B\u5F13\u624D\u4E11\u4E10\u4E0D\u4E2D\u4E30\u4E39\u4E4B\u5C39\u4E88\u4E91\u4E95\u4E92\u4E94\u4EA2\u4EC1\u4EC0\u4EC3\u4EC6\u4EC7\u4ECD\u4ECA\u4ECB\u4EC4\u5143\u5141\u5167\u516D\u516E\u516C\u5197\u51F6\u5206\u5207\u5208\u52FB\u52FE\u52FF\u5316\u5339\u5348\u5347\u5345\u535E\u5384\u53CB\u53CA\u53CD\u58EC\u5929\u592B\u592A\u592D\u5B54\u5C11\u5C24\u5C3A\u5C6F\u5DF4\u5E7B\u5EFF\u5F14\u5F15\u5FC3\u6208\u6236\u624B\u624E\u652F\u6587\u6597\u65A4\u65B9\u65E5\u66F0\u6708\u6728\u6B20\u6B62\u6B79\u6BCB\u6BD4\u6BDB\u6C0F\u6C34\u706B\u722A\u7236\u723B\u7247\u7259\u725B\u72AC\u738B\u4E19\u4E16\u4E15\u4E14\u4E18\u4E3B\u4E4D\u4E4F\u4E4E\u4EE5\u4ED8\u4ED4\u4ED5\u4ED6\u4ED7\u4EE3\u4EE4\u4ED9\u4EDE\u5145\u5144\u5189\u518A\u51AC\u51F9\u51FA\u51F8\u520A\u52A0\u529F\u5305\u5306\u5317\u531D\u4EDF\u534A\u5349\u5361\u5360\u536F\u536E\u53BB\u53EF\u53E4\u53F3\u53EC\u53EE\u53E9\u53E8\u53FC\u53F8\u53F5\u53EB\u53E6\u53EA\u53F2\u53F1\u53F0\u53E5\u53ED\u53FB\u56DB\u56DA\u5916\u592E\u5931\u5974\u5976\u5B55\u5B83\u5C3C\u5DE8\u5DE7\u5DE6\u5E02\u5E03\u5E73\u5E7C\u5F01\u5F18\u5F17\u5FC5\u620A\u6253\u6254\u6252\u6251\u65A5\u65E6\u672E\u672C\u672A\u672B\u672D\u6B63\u6BCD\u6C11\u6C10\u6C38\u6C41\u6C40\u6C3E\u72AF\u7384\u7389\u74DC\u74E6\u7518\u751F\u7528\u7529\u7530\u7531\u7532\u7533\u758B\u767D\u76AE\u76BF\u76EE\u77DB\u77E2\u77F3\u793A\u79BE\u7A74\u7ACB\u4E1E\u4E1F\u4E52\u4E53\u4E69\u4E99\u4EA4\u4EA6\u4EA5\u4EFF\u4F09\u4F19\u4F0A\u4F15\u4F0D\u4F10\u4F11\u4F0F\u4EF2\u4EF6\u4EFB\u4EF0\u4EF3\u4EFD\u4F01\u4F0B\u5149\u5147\u5146\u5148\u5168\u5171\u518D\u51B0\u5217\u5211\u5212\u520E\u5216\u52A3\u5308\u5321\u5320\u5370\u5371\u5409\u540F\u540C\u540A\u5410\u5401\u540B\u5404\u5411\u540D\u5408\u5403\u540E\u5406\u5412\u56E0\u56DE\u56DD\u5733\u5730\u5728\u572D\u572C\u572F\u5729\u5919\u591A\u5937\u5938\u5984\u5978\u5983\u597D\u5979\u5982\u5981\u5B57\u5B58\u5B87\u5B88\u5B85\u5B89\u5BFA\u5C16\u5C79\u5DDE\u5E06\u5E76\u5E74\u5F0F\u5F1B\u5FD9\u5FD6\u620E\u620C\u620D\u6210\u6263\u625B\u6258\u6536\u65E9\u65E8\u65EC\u65ED\u66F2\u66F3\u6709\u673D\u6734\u6731\u6735\u6B21\u6B64\u6B7B\u6C16\u6C5D\u6C57\u6C59\u6C5F\u6C60\u6C50\u6C55\u6C61\u6C5B\u6C4D\u6C4E\u7070\u725F\u725D\u767E\u7AF9\u7C73\u7CF8\u7F36\u7F8A\u7FBD\u8001\u8003\u800C\u8012\u8033\u807F\u8089\u808B\u808C\u81E3\u81EA\u81F3\u81FC\u820C\u821B\u821F\u826E\u8272\u827E\u866B\u8840\u884C\u8863\u897F\u9621\u4E32\u4EA8\u4F4D\u4F4F\u4F47\u4F57\u4F5E\u4F34\u4F5B\u4F55\u4F30\u4F50\u4F51\u4F3D\u4F3A\u4F38\u4F43\u4F54\u4F3C\u4F46\u4F63\u4F5C\u4F60\u4F2F\u4F4E\u4F36\u4F59\u4F5D\u4F48\u4F5A\u514C\u514B\u514D\u5175\u51B6\u51B7\u5225\u5224\u5229\u522A\u5228\u52AB\u52A9\u52AA\u52AC\u5323\u5373\u5375\u541D\u542D\u541E\u543E\u5426\u544E\u5427\u5446\u5443\u5433\u5448\u5442\u541B\u5429\u544A\u5439\u543B\u5438\u542E\u5435\u5436\u5420\u543C\u5440\u5431\u542B\u541F\u542C\u56EA\u56F0\u56E4\u56EB\u574A\u5751\u5740\u574D\u5747\u574E\u573E\u5750\u574F\u573B\u58EF\u593E\u599D\u5992\u59A8\u599E\u59A3\u5999\u5996\u598D\u59A4\u5993\u598A\u59A5\u5B5D\u5B5C\u5B5A\u5B5B\u5B8C\u5B8B\u5B8F\u5C2C\u5C40\u5C41\u5C3F\u5C3E\u5C90\u5C91\u5C94\u5C8C\u5DEB\u5E0C\u5E8F\u5E87\u5E8A\u5EF7\u5F04\u5F1F\u5F64\u5F62\u5F77\u5F79\u5FD8\u5FCC\u5FD7\u5FCD\u5FF1\u5FEB\u5FF8\u5FEA\u6212\u6211\u6284\u6297\u6296\u6280\u6276\u6289\u626D\u628A\u627C\u627E\u6279\u6273\u6292\u626F\u6298\u626E\u6295\u6293\u6291\u6286\u6539\u653B\u6538\u65F1\u66F4\u675F\u674E\u674F\u6750\u6751\u675C\u6756\u675E\u6749\u6746\u6760\u6753\u6757\u6B65\u6BCF\u6C42\u6C5E\u6C99\u6C81\u6C88\u6C89\u6C85\u6C9B\u6C6A\u6C7A\u6C90\u6C70\u6C8C\u6C68\u6C96\u6C92\u6C7D\u6C83\u6C72\u6C7E\u6C74\u6C86\u6C76\u6C8D\u6C94\u6C98\u6C82\u7076\u707C\u707D\u7078\u7262\u7261\u7260\u72C4\u72C2\u7396\u752C\u752B\u7537\u7538\u7682\u76EF\u77E3\u79C1\u79C0\u79BF\u7A76\u7CFB\u7F55\u8096\u8093\u809D\u8098\u809B\u809A\u80B2\u826F\u8292\u828B\u828D\u898B\u89D2\u8A00\u8C37\u8C46\u8C55\u8C9D\u8D64\u8D70\u8DB3\u8EAB\u8ECA\u8F9B\u8FB0\u8FC2\u8FC6\u8FC5\u8FC4\u5DE1\u9091\u90A2\u90AA\u90A6\u90A3\u9149\u91C6\u91CC\u9632\u962E\u9631\u962A\u962C\u4E26\u4E56\u4E73\u4E8B\u4E9B\u4E9E\u4EAB\u4EAC\u4F6F\u4F9D\u4F8D\u4F73\u4F7F\u4F6C\u4F9B\u4F8B\u4F86\u4F83\u4F70\u4F75\u4F88\u4F69\u4F7B\u4F96\u4F7E\u4F8F\u4F91\u4F7A\u5154\u5152\u5155\u5169\u5177\u5176\u5178\u51BD\u51FD\u523B\u5238\u5237\u523A\u5230\u522E\u5236\u5241\u52BE\u52BB\u5352\u5354\u5353\u5351\u5366\u5377\u5378\u5379\u53D6\u53D4\u53D7\u5473\u5475\u5496\u5478\u5495\u5480\u547B\u5477\u5484\u5492\u5486\u547C\u5490\u5471\u5476\u548C\u549A\u5462\u5468\u548B\u547D\u548E\u56FA\u5783\u5777\u576A\u5769\u5761\u5766\u5764\u577C\u591C\u5949\u5947\u5948\u5944\u5954\u59BE\u59BB\u59D4\u59B9\u59AE\u59D1\u59C6\u59D0\u59CD\u59CB\u59D3\u59CA\u59AF\u59B3\u59D2\u59C5\u5B5F\u5B64\u5B63\u5B97\u5B9A\u5B98\u5B9C\u5B99\u5B9B\u5C1A\u5C48\u5C45\u5C46\u5CB7\u5CA1\u5CB8\u5CA9\u5CAB\u5CB1\u5CB3\u5E18\u5E1A\u5E16\u5E15\u5E1B\u5E11\u5E78\u5E9A\u5E97\u5E9C\u5E95\u5E96\u5EF6\u5F26\u5F27\u5F29\u5F80\u5F81\u5F7F\u5F7C\u5FDD\u5FE0\u5FFD\u5FF5\u5FFF\u600F\u6014\u602F\u6035\u6016\u602A\u6015\u6021\u6027\u6029\u602B\u601B\u6216\u6215\u623F\u623E\u6240\u627F\u62C9\u62CC\u62C4\u62BF\u62C2\u62B9\u62D2\u62DB\u62AB\u62D3\u62D4\u62CB\u62C8\u62A8\u62BD\u62BC\u62D0\u62D9\u62C7\u62CD\u62B5\u62DA\u62B1\u62D8\u62D6\u62D7\u62C6\u62AC\u62CE\u653E\u65A7\u65BC\u65FA\u6614\u6613\u660C\u6606\u6602\u660E\u6600\u660F\u6615\u660A\u6607\u670D\u670B\u676D\u678B\u6795\u6771\u679C\u6773\u6777\u6787\u679D\u6797\u676F\u6770\u677F\u6789\u677E\u6790\u6775\u679A\u6793\u677C\u676A\u6772\u6B23\u6B66\u6B67\u6B7F\u6C13\u6C1B\u6CE3\u6CE8\u6CF3\u6CB1\u6CCC\u6CE5\u6CB3\u6CBD\u6CBE\u6CBC\u6CE2\u6CAB\u6CD5\u6CD3\u6CB8\u6CC4\u6CB9\u6CC1\u6CAE\u6CD7\u6CC5\u6CF1\u6CBF\u6CBB\u6CE1\u6CDB\u6CCA\u6CAC\u6CEF\u6CDC\u6CD6\u6CE0\u7095\u708E\u7092\u708A\u7099\u722C\u722D\u7238\u7248\u7267\u7269\u72C0\u72CE\u72D9\u72D7\u72D0\u73A9\u73A8\u739F\u73AB\u73A5\u753D\u759D\u7599\u759A\u7684\u76C2\u76F2\u76F4\u77E5\u77FD\u793E\u7940\u7941\u79C9\u79C8\u7A7A\u7A79\u7AFA\u7CFE\u7F54\u7F8C\u7F8B\u8005\u80BA\u80A5\u80A2\u80B1\u80A1\u80AB\u80A9\u80B4\u80AA\u80AF\u81E5\u81FE\u820D\u82B3\u829D\u8299\u82AD\u82BD\u829F\u82B9\u82B1\u82AC\u82A5\u82AF\u82B8\u82A3\u82B0\u82BE\u82B7\u864E\u8671\u521D\u8868\u8ECB\u8FCE\u8FD4\u8FD1\u90B5\u90B8\u90B1\u90B6\u91C7\u91D1\u9577\u9580\u961C\u9640\u963F\u963B\u9644\u9642\u96B9\u96E8\u9752\u975E\u4E9F\u4EAD\u4EAE\u4FE1\u4FB5\u4FAF\u4FBF\u4FE0\u4FD1\u4FCF\u4FDD\u4FC3\u4FB6\u4FD8\u4FDF\u4FCA\u4FD7\u4FAE\u4FD0\u4FC4\u4FC2\u4FDA\u4FCE\u4FDE\u4FB7\u5157\u5192\u5191\u51A0\u524E\u5243\u524A\u524D\u524C\u524B\u5247\u52C7\u52C9\u52C3\u52C1\u530D\u5357\u537B\u539A\u53DB\u54AC\u54C0\u54A8\u54CE\u54C9\u54B8\u54A6\u54B3\u54C7\u54C2\u54BD\u54AA\u54C1\u54C4\u54C8\u54AF\u54AB\u54B1\u54BB\u54A9\u54A7\u54BF\u56FF\u5782\u578B\u57A0\u57A3\u57A2\u57CE\u57AE\u5793\u5955\u5951\u594F\u594E\u5950\u59DC\u59D8\u59FF\u59E3\u59E8\u5A03\u59E5\u59EA\u59DA\u59E6\u5A01\u59FB\u5B69\u5BA3\u5BA6\u5BA4\u5BA2\u5BA5\u5C01\u5C4E\u5C4F\u5C4D\u5C4B\u5CD9\u5CD2\u5DF7\u5E1D\u5E25\u5E1F\u5E7D\u5EA0\u5EA6\u5EFA\u5F08\u5F2D\u5F65\u5F88\u5F85\u5F8A\u5F8B\u5F87\u5F8C\u5F89\u6012\u601D\u6020\u6025\u600E\u6028\u604D\u6070\u6068\u6062\u6046\u6043\u606C\u606B\u606A\u6064\u6241\u62DC\u6316\u6309\u62FC\u62ED\u6301\u62EE\u62FD\u6307\u62F1\u62F7\u62EF\u62EC\u62FE\u62F4\u6311\u6302\u653F\u6545\u65AB\u65BD\u65E2\u6625\u662D\u6620\u6627\u662F\u661F\u6628\u6631\u6624\u66F7\u67FF\u67D3\u67F1\u67D4\u67D0\u67EC\u67B6\u67AF\u67F5\u67E9\u67EF\u67C4\u67D1\u67B4\u67DA\u67E5\u67B8\u67CF\u67DE\u67F3\u67B0\u67D9\u67E2\u67DD\u67D2\u6B6A\u6B83\u6B86\u6BB5\u6BD2\u6BD7\u6C1F\u6CC9\u6D0B\u6D32\u6D2A\u6D41\u6D25\u6D0C\u6D31\u6D1E\u6D17\u6D3B\u6D3D\u6D3E\u6D36\u6D1B\u6CF5\u6D39\u6D27\u6D38\u6D29\u6D2E\u6D35\u6D0E\u6D2B\u70AB\u70BA\u70B3\u70AC\u70AF\u70AD\u70B8\u70AE\u70A4\u7230\u7272\u726F\u7274\u72E9\u72E0\u72E1\u73B7\u73CA\u73BB\u73B2\u73CD\u73C0\u73B3\u751A\u752D\u754F\u754C\u754E\u754B\u75AB\u75A4\u75A5\u75A2\u75A3\u7678\u7686\u7687\u7688\u76C8\u76C6\u76C3\u76C5\u7701\u76F9\u76F8\u7709\u770B\u76FE\u76FC\u7707\u77DC\u7802\u7814\u780C\u780D\u7946\u7949\u7948\u7947\u79B9\u79BA\u79D1\u79D2\u79CB\u7A7F\u7A81\u7AFF\u7AFD\u7C7D\u7D02\u7D05\u7D00\u7D09\u7D07\u7D04\u7D06\u7F38\u7F8E\u7FBF\u8004\u8010\u800D\u8011\u8036\u80D6\u80E5\u80DA\u80C3\u80C4\u80CC\u80E1\u80DB\u80CE\u80DE\u80E4\u80DD\u81F4\u8222\u82E7\u8303\u8305\u82E3\u82DB\u82E6\u8304\u82E5\u8302\u8309\u82D2\u82D7\u82F1\u8301\u82DC\u82D4\u82D1\u82DE\u82D3\u82DF\u82EF\u8306\u8650\u8679\u867B\u867A\u884D\u886B\u8981\u89D4\u8A08\u8A02\u8A03\u8C9E\u8CA0\u8D74\u8D73\u8DB4\u8ECD\u8ECC\u8FF0\u8FE6\u8FE2\u8FEA\u8FE5\u8FED\u8FEB\u8FE4\u8FE8\u90CA\u90CE\u90C1\u90C3\u914B\u914A\u91CD\u9582\u9650\u964B\u964C\u964D\u9762\u9769\u97CB\u97ED\u97F3\u9801\u98A8\u98DB\u98DF\u9996\u9999\u4E58\u4EB3\u500C\u500D\u5023\u4FEF\u5026\u5025\u4FF8\u5029\u5016\u5006\u503C\u501F\u501A\u5012\u5011\u4FFA\u5000\u5014\u5028\u4FF1\u5021\u500B\u5019\u5018\u4FF3\u4FEE\u502D\u502A\u4FFE\u502B\u5009\u517C\u51A4\u51A5\u51A2\u51CD\u51CC\u51C6\u51CB\u5256\u525C\u5254\u525B\u525D\u532A\u537F\u539F\u539D\u53DF\u54E8\u5510\u5501\u5537\u54FC\u54E5\u54F2\u5506\u54FA\u5514\u54E9\u54ED\u54E1\u5509\u54EE\u54EA\u54E6\u5527\u5507\u54FD\u550F\u5703\u5704\u57C2\u57D4\u57CB\u57C3\u5809\u590F\u5957\u5958\u595A\u5A11\u5A18\u5A1C\u5A1F\u5A1B\u5A13\u59EC\u5A20\u5A23\u5A29\u5A25\u5A0C\u5A09\u5B6B\u5C58\u5BB0\u5BB3\u5BB6\u5BB4\u5BAE\u5BB5\u5BB9\u5BB8\u5C04\u5C51\u5C55\u5C50\u5CED\u5CFD\u5CFB\u5CEA\u5CE8\u5CF0\u5CF6\u5D01\u5CF4\u5DEE\u5E2D\u5E2B\u5EAB\u5EAD\u5EA7\u5F31\u5F92\u5F91\u5F90\u6059\u6063\u6065\u6050\u6055\u606D\u6069\u606F\u6084\u609F\u609A\u608D\u6094\u608C\u6085\u6096\u6247\u62F3\u6308\u62FF\u634E\u633E\u632F\u6355\u6342\u6346\u634F\u6349\u633A\u6350\u633D\u632A\u632B\u6328\u634D\u634C\u6548\u6549\u6599\u65C1\u65C5\u6642\u6649\u664F\u6643\u6652\u664C\u6645\u6641\u66F8\u6714\u6715\u6717\u6821\u6838\u6848\u6846\u6853\u6839\u6842\u6854\u6829\u68B3\u6817\u684C\u6851\u683D\u67F4\u6850\u6840\u683C\u6843\u682A\u6845\u6813\u6818\u6841\u6B8A\u6B89\u6BB7\u6C23\u6C27\u6C28\u6C26\u6C24\u6CF0\u6D6A\u6D95\u6D88\u6D87\u6D66\u6D78\u6D77\u6D59\u6D93\u6D6C\u6D89\u6D6E\u6D5A\u6D74\u6D69\u6D8C\u6D8A\u6D79\u6D85\u6D65\u6D94\u70CA\u70D8\u70E4\u70D9\u70C8\u70CF\u7239\u7279\u72FC\u72F9\u72FD\u72F8\u72F7\u7386\u73ED\u7409\u73EE\u73E0\u73EA\u73DE\u7554\u755D\u755C\u755A\u7559\u75BE\u75C5\u75C7\u75B2\u75B3\u75BD\u75BC\u75B9\u75C2\u75B8\u768B\u76B0\u76CA\u76CD\u76CE\u7729\u771F\u7720\u7728\u77E9\u7830\u7827\u7838\u781D\u7834\u7837\u7825\u782D\u7820\u781F\u7832\u7955\u7950\u7960\u795F\u7956\u795E\u795D\u7957\u795A\u79E4\u79E3\u79E7\u79DF\u79E6\u79E9\u79D8\u7A84\u7A88\u7AD9\u7B06\u7B11\u7C89\u7D21\u7D17\u7D0B\u7D0A\u7D20\u7D22\u7D14\u7D10\u7D15\u7D1A\u7D1C\u7D0D\u7D19\u7D1B\u7F3A\u7F5F\u7F94\u7FC5\u7FC1\u8006\u8018\u8015\u8019\u8017\u803D\u803F\u80F1\u8102\u80F0\u8105\u80ED\u80F4\u8106\u80F8\u80F3\u8108\u80FD\u810A\u80FC\u80EF\u81ED\u81EC\u8200\u8210\u822A\u822B\u8228\u822C\u82BB\u832B\u8352\u8354\u834A\u8338\u8350\u8349\u8335\u8334\u834F\u8332\u8339\u8336\u8317\u8340\u8331\u8328\u8343\u8654\u868A\u86AA\u8693\u86A4\u86A9\u868C\u86A3\u869C\u8870\u8877\u8881\u8882\u887D\u8879\u8A18\u8A10\u8A0E\u8A0C\u8A15\u8A0A\u8A17\u8A13\u8A16\u8A0F\u8A11\u8C48\u8C7A\u8C79\u8CA1\u8CA2\u8D77\u8EAC\u8ED2\u8ED4\u8ECF\u8FB1\u9001\u9006\u8FF7\u9000\u8FFA\u8FF4\u9003\u8FFD\u9005\u8FF8\u9095\u90E1\u90DD\u90E2\u9152\u914D\u914C\u91D8\u91DD\u91D7\u91DC\u91D9\u9583\u9662\u9663\u9661\u965B\u965D\u9664\u9658\u965E\u96BB\u98E2\u99AC\u9AA8\u9AD8\u9B25\u9B32\u9B3C\u4E7E\u507A\u507D\u505C\u5047\u5043\u504C\u505A\u5049\u5065\u5076\u504E\u5055\u5075\u5074\u5077\u504F\u500F\u506F\u506D\u515C\u5195\u51F0\u526A\u526F\u52D2\u52D9\u52D8\u52D5\u5310\u530F\u5319\u533F\u5340\u533E\u53C3\u66FC\u5546\u556A\u5566\u5544\u555E\u5561\u5543\u554A\u5531\u5556\u554F\u5555\u552F\u5564\u5538\u552E\u555C\u552C\u5563\u5533\u5541\u5557\u5708\u570B\u5709\u57DF\u5805\u580A\u5806\u57E0\u57E4\u57FA\u5802\u5835\u57F7\u57F9\u5920\u5962\u5A36\u5A41\u5A49\u5A66\u5A6A\u5A40\u5A3C\u5A62\u5A5A\u5A46\u5A4A\u5B70\u5BC7\u5BC5\u5BC4\u5BC2\u5BBF\u5BC6\u5C09\u5C08\u5C07\u5C60\u5C5C\u5C5D\u5D07\u5D06\u5D0E\u5D1B\u5D16\u5D22\u5D11\u5D29\u5D14\u5D19\u5D24\u5D27\u5D17\u5DE2\u5E38\u5E36\u5E33\u5E37\u5EB7\u5EB8\u5EB6\u5EB5\u5EBE\u5F35\u5F37\u5F57\u5F6C\u5F69\u5F6B\u5F97\u5F99\u5F9E\u5F98\u5FA1\u5FA0\u5F9C\u607F\u60A3\u6089\u60A0\u60A8\u60CB\u60B4\u60E6\u60BD\u60C5\u60BB\u60B5\u60DC\u60BC\u60D8\u60D5\u60C6\u60DF\u60B8\u60DA\u60C7\u621A\u621B\u6248\u63A0\u63A7\u6372\u6396\u63A2\u63A5\u6377\u6367\u6398\u63AA\u6371\u63A9\u6389\u6383\u639B\u636B\u63A8\u6384\u6388\u6399\u63A1\u63AC\u6392\u638F\u6380\u637B\u6369\u6368\u637A\u655D\u6556\u6551\u6559\u6557\u555F\u654F\u6558\u6555\u6554\u659C\u659B\u65AC\u65CF\u65CB\u65CC\u65CE\u665D\u665A\u6664\u6668\u6666\u665E\u66F9\u52D7\u671B\u6881\u68AF\u68A2\u6893\u68B5\u687F\u6876\u68B1\u68A7\u6897\u68B0\u6883\u68C4\u68AD\u6886\u6885\u6894\u689D\u68A8\u689F\u68A1\u6882\u6B32\u6BBA\u6BEB\u6BEC\u6C2B\u6D8E\u6DBC\u6DF3\u6DD9\u6DB2\u6DE1\u6DCC\u6DE4\u6DFB\u6DFA\u6E05\u6DC7\u6DCB\u6DAF\u6DD1\u6DAE\u6DDE\u6DF9\u6DB8\u6DF7\u6DF5\u6DC5\u6DD2\u6E1A\u6DB5\u6DDA\u6DEB\u6DD8\u6DEA\u6DF1\u6DEE\u6DE8\u6DC6\u6DC4\u6DAA\u6DEC\u6DBF\u6DE6\u70F9\u7109\u710A\u70FD\u70EF\u723D\u727D\u7281\u731C\u731B\u7316\u7313\u7319\u7387\u7405\u740A\u7403\u7406\u73FE\u740D\u74E0\u74F6\u74F7\u751C\u7522\u7565\u7566\u7562\u7570\u758F\u75D4\u75D5\u75B5\u75CA\u75CD\u768E\u76D4\u76D2\u76DB\u7737\u773E\u773C\u7736\u7738\u773A\u786B\u7843\u784E\u7965\u7968\u796D\u79FB\u7A92\u7A95\u7B20\u7B28\u7B1B\u7B2C\u7B26\u7B19\u7B1E\u7B2E\u7C92\u7C97\u7C95\u7D46\u7D43\u7D71\u7D2E\u7D39\u7D3C\u7D40\u7D30\u7D33\u7D44\u7D2F\u7D42\u7D32\u7D31\u7F3D\u7F9E\u7F9A\u7FCC\u7FCE\u7FD2\u801C\u804A\u8046\u812F\u8116\u8123\u812B\u8129\u8130\u8124\u8202\u8235\u8237\u8236\u8239\u838E\u839E\u8398\u8378\u83A2\u8396\u83BD\u83AB\u8392\u838A\u8393\u8389\u83A0\u8377\u837B\u837C\u8386\u83A7\u8655\u5F6A\u86C7\u86C0\u86B6\u86C4\u86B5\u86C6\u86CB\u86B1\u86AF\u86C9\u8853\u889E\u8888\u88AB\u8892\u8896\u888D\u888B\u8993\u898F\u8A2A\u8A1D\u8A23\u8A25\u8A31\u8A2D\u8A1F\u8A1B\u8A22\u8C49\u8C5A\u8CA9\u8CAC\u8CAB\u8CA8\u8CAA\u8CA7\u8D67\u8D66\u8DBE\u8DBA\u8EDB\u8EDF\u9019\u900D\u901A\u9017\u9023\u901F\u901D\u9010\u9015\u901E\u9020\u900F\u9022\u9016\u901B\u9014\u90E8\u90ED\u90FD\u9157\u91CE\u91F5\u91E6\u91E3\u91E7\u91ED\u91E9\u9589\u966A\u9675\u9673\u9678\u9670\u9674\u9676\u9677\u966C\u96C0\u96EA\u96E9\u7AE0\u7ADF\u9802\u9803\u9B5A\u9CE5\u9E75\u9E7F\u9EA5\u9EBB\u50A2\u508D\u5085\u5099\u5091\u5080\u5096\u5098\u509A\u6700\u51F1\u5272\u5274\u5275\u5269\u52DE\u52DD\u52DB\u535A\u53A5\u557B\u5580\u55A7\u557C\u558A\u559D\u5598\u5582\u559C\u55AA\u5594\u5587\u558B\u5583\u55B3\u55AE\u559F\u553E\u55B2\u559A\u55BB\u55AC\u55B1\u557E\u5589\u55AB\u5599\u570D\u582F\u582A\u5834\u5824\u5830\u5831\u5821\u581D\u5820\u58F9\u58FA\u5960\u5A77\u5A9A\u5A7F\u5A92\u5A9B\u5AA7\u5B73\u5B71\u5BD2\u5BCC\u5BD3\u5BD0\u5C0A\u5C0B\u5C31\u5D4C\u5D50\u5D34\u5D47\u5DFD\u5E45\u5E3D\u5E40\u5E43\u5E7E\u5ECA\u5EC1\u5EC2\u5EC4\u5F3C\u5F6D\u5FA9\u5FAA\u5FA8\u60D1\u60E1\u60B2\u60B6\u60E0\u611C\u6123\u60FA\u6115\u60F0\u60FB\u60F4\u6168\u60F1\u610E\u60F6\u6109\u6100\u6112\u621F\u6249\u63A3\u638C\u63CF\u63C0\u63E9\u63C9\u63C6\u63CD\u63D2\u63E3\u63D0\u63E1\u63D6\u63ED\u63EE\u6376\u63F4\u63EA\u63DB\u6452\u63DA\u63F9\u655E\u6566\u6562\u6563\u6591\u6590\u65AF\u666E\u6670\u6674\u6676\u666F\u6691\u667A\u667E\u6677\u66FE\u66FF\u671F\u671D\u68FA\u68D5\u68E0\u68D8\u68D7\u6905\u68DF\u68F5\u68EE\u68E7\u68F9\u68D2\u68F2\u68E3\u68CB\u68CD\u690D\u6912\u690E\u68C9\u68DA\u696E\u68FB\u6B3E\u6B3A\u6B3D\u6B98\u6B96\u6BBC\u6BEF\u6C2E\u6C2F\u6C2C\u6E2F\u6E38\u6E54\u6E21\u6E32\u6E67\u6E4A\u6E20\u6E25\u6E23\u6E1B\u6E5B\u6E58\u6E24\u6E56\u6E6E\u6E2D\u6E26\u6E6F\u6E34\u6E4D\u6E3A\u6E2C\u6E43\u6E1D\u6E3E\u6ECB\u6E89\u6E19\u6E4E\u6E63\u6E44\u6E72\u6E69\u6E5F\u7119\u711A\u7126\u7130\u7121\u7136\u716E\u711C\u724C\u7284\u7280\u7336\u7325\u7334\u7329\u743A\u742A\u7433\u7422\u7425\u7435\u7436\u7434\u742F\u741B\u7426\u7428\u7525\u7526\u756B\u756A\u75E2\u75DB\u75E3\u75D9\u75D8\u75DE\u75E0\u767B\u767C\u7696\u7693\u76B4\u76DC\u774F\u77ED\u785D\u786C\u786F\u7A0D\u7A08\u7A0B\u7A05\u7A00\u7A98\u7A97\u7A96\u7AE5\u7AE3\u7B49\u7B56\u7B46\u7B50\u7B52\u7B54\u7B4D\u7B4B\u7B4F\u7B51\u7C9F\u7CA5\u7D5E\u7D50\u7D68\u7D55\u7D2B\u7D6E\u7D72\u7D61\u7D66\u7D62\u7D70\u7D73\u5584\u7FD4\u7FD5\u800B\u8052\u8085\u8155\u8154\u814B\u8151\u814E\u8139\u8146\u813E\u814C\u8153\u8174\u8212\u821C\u83E9\u8403\u83F8\u840D\u83E0\u83C5\u840B\u83C1\u83EF\u83F1\u83F4\u8457\u840A\u83F0\u840C\u83CC\u83FD\u83F2\u83CA\u8438\u840E\u8404\u83DC\u8407\u83D4\u83DF\u865B\u86DF\u86D9\u86ED\u86D4\u86DB\u86E4\u86D0\u86DE\u8857\u88C1\u88C2\u88B1\u8983\u8996\u8A3B\u8A60\u8A55\u8A5E\u8A3C\u8A41\u8A54\u8A5B\u8A50\u8A46\u8A34\u8A3A\u8A36\u8A56\u8C61\u8C82\u8CAF\u8CBC\u8CB3\u8CBD\u8CC1\u8CBB\u8CC0\u8CB4\u8CB7\u8CB6\u8CBF\u8CB8\u8D8A\u8D85\u8D81\u8DCE\u8DDD\u8DCB\u8DDA\u8DD1\u8DCC\u8DDB\u8DC6\u8EFB\u8EF8\u8EFC\u8F9C\u902E\u9035\u9031\u9038\u9032\u9036\u9102\u90F5\u9109\u90FE\u9163\u9165\u91CF\u9214\u9215\u9223\u9209\u921E\u920D\u9210\u9207\u9211\u9594\u958F\u958B\u9591\u9593\u9592\u958E\u968A\u968E\u968B\u967D\u9685\u9686\u968D\u9672\u9684\u96C1\u96C5\u96C4\u96C6\u96C7\u96EF\u96F2\u97CC\u9805\u9806\u9808\u98E7\u98EA\u98EF\u98E9\u98F2\u98ED\u99AE\u99AD\u9EC3\u9ECD\u9ED1\u4E82\u50AD\u50B5\u50B2\u50B3\u50C5\u50BE\u50AC\u50B7\u50BB\u50AF\u50C7\u527F\u5277\u527D\u52DF\u52E6\u52E4\u52E2\u52E3\u532F\u55DF\u55E8\u55D3\u55E6\u55CE\u55DC\u55C7\u55D1\u55E3\u55E4\u55EF\u55DA\u55E1\u55C5\u55C6\u55E5\u55C9\u5712\u5713\u585E\u5851\u5858\u5857\u585A\u5854\u586B\u584C\u586D\u584A\u5862\u5852\u584B\u5967\u5AC1\u5AC9\u5ACC\u5ABE\u5ABD\u5ABC\u5AB3\u5AC2\u5AB2\u5D69\u5D6F\u5E4C\u5E79\u5EC9\u5EC8\u5F12\u5F59\u5FAC\u5FAE\u611A\u610F\u6148\u611F\u60F3\u611B\u60F9\u6101\u6108\u614E\u614C\u6144\u614D\u613E\u6134\u6127\u610D\u6106\u6137\u6221\u6222\u6413\u643E\u641E\u642A\u642D\u643D\u642C\u640F\u641C\u6414\u640D\u6436\u6416\u6417\u6406\u656C\u659F\u65B0\u6697\u6689\u6687\u6688\u6696\u6684\u6698\u668D\u6703\u6994\u696D\u695A\u6977\u6960\u6954\u6975\u6930\u6982\u694A\u6968\u696B\u695E\u6953\u6979\u6986\u695D\u6963\u695B\u6B47\u6B72\u6BC0\u6BBF\u6BD3\u6BFD\u6EA2\u6EAF\u6ED3\u6EB6\u6EC2\u6E90\u6E9D\u6EC7\u6EC5\u6EA5\u6E98\u6EBC\u6EBA\u6EAB\u6ED1\u6E96\u6E9C\u6EC4\u6ED4\u6EAA\u6EA7\u6EB4\u714E\u7159\u7169\u7164\u7149\u7167\u715C\u716C\u7166\u714C\u7165\u715E\u7146\u7168\u7156\u723A\u7252\u7337\u7345\u733F\u733E\u746F\u745A\u7455\u745F\u745E\u7441\u743F\u7459\u745B\u745C\u7576\u7578\u7600\u75F0\u7601\u75F2\u75F1\u75FA\u75FF\u75F4\u75F3\u76DE\u76DF\u775B\u776B\u7766\u775E\u7763\u7779\u776A\u776C\u775C\u7765\u7768\u7762\u77EE\u788E\u78B0\u7897\u7898\u788C\u7889\u787C\u7891\u7893\u787F\u797A\u797F\u7981\u842C\u79BD\u7A1C\u7A1A\u7A20\u7A14\u7A1F\u7A1E\u7A9F\u7AA0\u7B77\u7BC0\u7B60\u7B6E\u7B67\u7CB1\u7CB3\u7CB5\u7D93\u7D79\u7D91\u7D81\u7D8F\u7D5B\u7F6E\u7F69\u7F6A\u7F72\u7FA9\u7FA8\u7FA4\u8056\u8058\u8086\u8084\u8171\u8170\u8178\u8165\u816E\u8173\u816B\u8179\u817A\u8166\u8205\u8247\u8482\u8477\u843D\u8431\u8475\u8466\u846B\u8449\u846C\u845B\u843C\u8435\u8461\u8463\u8469\u846D\u8446\u865E\u865C\u865F\u86F9\u8713\u8708\u8707\u8700\u86FE\u86FB\u8702\u8703\u8706\u870A\u8859\u88DF\u88D4\u88D9\u88DC\u88D8\u88DD\u88E1\u88CA\u88D5\u88D2\u899C\u89E3\u8A6B\u8A72\u8A73\u8A66\u8A69\u8A70\u8A87\u8A7C\u8A63\u8AA0\u8A71\u8A85\u8A6D\u8A62\u8A6E\u8A6C\u8A79\u8A7B\u8A3E\u8A68\u8C62\u8C8A\u8C89\u8CCA\u8CC7\u8CC8\u8CC4\u8CB2\u8CC3\u8CC2\u8CC5\u8DE1\u8DDF\u8DE8\u8DEF\u8DF3\u8DFA\u8DEA\u8DE4\u8DE6\u8EB2\u8F03\u8F09\u8EFE\u8F0A\u8F9F\u8FB2\u904B\u904A\u9053\u9042\u9054\u903C\u9055\u9050\u9047\u904F\u904E\u904D\u9051\u903E\u9041\u9112\u9117\u916C\u916A\u9169\u91C9\u9237\u9257\u9238\u923D\u9240\u923E\u925B\u924B\u9264\u9251\u9234\u9249\u924D\u9245\u9239\u923F\u925A\u9598\u9698\u9694\u9695\u96CD\u96CB\u96C9\u96CA\u96F7\u96FB\u96F9\u96F6\u9756\u9774\u9776\u9810\u9811\u9813\u980A\u9812\u980C\u98FC\u98F4\u98FD\u98FE\u99B3\u99B1\u99B4\u9AE1\u9CE9\u9E82\u9F0E\u9F13\u9F20\u50E7\u50EE\u50E5\u50D6\u50ED\u50DA\u50D5\u50CF\u50D1\u50F1\u50CE\u50E9\u5162\u51F3\u5283\u5282\u5331\u53AD\u55FE\u5600\u561B\u5617\u55FD\u5614\u5606\u5609\u560D\u560E\u55F7\u5616\u561F\u5608\u5610\u55F6\u5718\u5716\u5875\u587E\u5883\u5893\u588A\u5879\u5885\u587D\u58FD\u5925\u5922\u5924\u596A\u5969\u5AE1\u5AE6\u5AE9\u5AD7\u5AD6\u5AD8\u5AE3\u5B75\u5BDE\u5BE7\u5BE1\u5BE5\u5BE6\u5BE8\u5BE2\u5BE4\u5BDF\u5C0D\u5C62\u5D84\u5D87\u5E5B\u5E63\u5E55\u5E57\u5E54\u5ED3\u5ED6\u5F0A\u5F46\u5F70\u5FB9\u6147\u613F\u614B\u6177\u6162\u6163\u615F\u615A\u6158\u6175\u622A\u6487\u6458\u6454\u64A4\u6478\u645F\u647A\u6451\u6467\u6434\u646D\u647B\u6572\u65A1\u65D7\u65D6\u66A2\u66A8\u669D\u699C\u69A8\u6995\u69C1\u69AE\u69D3\u69CB\u699B\u69B7\u69BB\u69AB\u69B4\u69D0\u69CD\u69AD\u69CC\u69A6\u69C3\u69A3\u6B49\u6B4C\u6C33\u6F33\u6F14\u6EFE\u6F13\u6EF4\u6F29\u6F3E\u6F20\u6F2C\u6F0F\u6F02\u6F22\u6EFF\u6EEF\u6F06\u6F31\u6F38\u6F32\u6F23\u6F15\u6F2B\u6F2F\u6F88\u6F2A\u6EEC\u6F01\u6EF2\u6ECC\u6EF7\u7194\u7199\u717D\u718A\u7184\u7192\u723E\u7292\u7296\u7344\u7350\u7464\u7463\u746A\u7470\u746D\u7504\u7591\u7627\u760D\u760B\u7609\u7613\u76E1\u76E3\u7784\u777D\u777F\u7761\u78C1\u789F\u78A7\u78B3\u78A9\u78A3\u798E\u798F\u798D\u7A2E\u7A31\u7AAA\u7AA9\u7AED\u7AEF\u7BA1\u7B95\u7B8B\u7B75\u7B97\u7B9D\u7B94\u7B8F\u7BB8\u7B87\u7B84\u7CB9\u7CBD\u7CBE\u7DBB\u7DB0\u7D9C\u7DBD\u7DBE\u7DA0\u7DCA\u7DB4\u7DB2\u7DB1\u7DBA\u7DA2\u7DBF\u7DB5\u7DB8\u7DAD\u7DD2\u7DC7\u7DAC\u7F70\u7FE0\u7FE1\u7FDF\u805E\u805A\u8087\u8150\u8180\u818F\u8188\u818A\u817F\u8182\u81E7\u81FA\u8207\u8214\u821E\u824B\u84C9\u84BF\u84C6\u84C4\u8499\u849E\u84B2\u849C\u84CB\u84B8\u84C0\u84D3\u8490\u84BC\u84D1\u84CA\u873F\u871C\u873B\u8722\u8725\u8734\u8718\u8755\u8737\u8729\u88F3\u8902\u88F4\u88F9\u88F8\u88FD\u88E8\u891A\u88EF\u8AA6\u8A8C\u8A9E\u8AA3\u8A8D\u8AA1\u8A93\u8AA4\u8AAA\u8AA5\u8AA8\u8A98\u8A91\u8A9A\u8AA7\u8C6A\u8C8D\u8C8C\u8CD3\u8CD1\u8CD2\u8D6B\u8D99\u8D95\u8DFC\u8F14\u8F12\u8F15\u8F13\u8FA3\u9060\u9058\u905C\u9063\u9059\u905E\u9062\u905D\u905B\u9119\u9118\u911E\u9175\u9178\u9177\u9174\u9278\u9280\u9285\u9298\u9296\u927B\u9293\u929C\u92A8\u927C\u9291\u95A1\u95A8\u95A9\u95A3\u95A5\u95A4\u9699\u969C\u969B\u96CC\u96D2\u9700\u977C\u9785\u97F6\u9817\u9818\u98AF\u98B1\u9903\u9905\u990C\u9909\u99C1\u9AAF\u9AB0\u9AE6\u9B41\u9B42\u9CF4\u9CF6\u9CF3\u9EBC\u9F3B\u9F4A\u5104\u5100\u50FB\u50F5\u50F9\u5102\u5108\u5109\u5105\u51DC\u5287\u5288\u5289\u528D\u528A\u52F0\u53B2\u562E\u563B\u5639\u5632\u563F\u5634\u5629\u5653\u564E\u5657\u5674\u5636\u562F\u5630\u5880\u589F\u589E\u58B3\u589C\u58AE\u58A9\u58A6\u596D\u5B09\u5AFB\u5B0B\u5AF5\u5B0C\u5B08\u5BEE\u5BEC\u5BE9\u5BEB\u5C64\u5C65\u5D9D\u5D94\u5E62\u5E5F\u5E61\u5EE2\u5EDA\u5EDF\u5EDD\u5EE3\u5EE0\u5F48\u5F71\u5FB7\u5FB5\u6176\u6167\u616E\u615D\u6155\u6182\u617C\u6170\u616B\u617E\u61A7\u6190\u61AB\u618E\u61AC\u619A\u61A4\u6194\u61AE\u622E\u6469\u646F\u6479\u649E\u64B2\u6488\u6490\u64B0\u64A5\u6493\u6495\u64A9\u6492\u64AE\u64AD\u64AB\u649A\u64AC\u6499\u64A2\u64B3\u6575\u6577\u6578\u66AE\u66AB\u66B4\u66B1\u6A23\u6A1F\u69E8\u6A01\u6A1E\u6A19\u69FD\u6A21\u6A13\u6A0A\u69F3\u6A02\u6A05\u69ED\u6A11\u6B50\u6B4E\u6BA4\u6BC5\u6BC6\u6F3F\u6F7C\u6F84\u6F51\u6F66\u6F54\u6F86\u6F6D\u6F5B\u6F78\u6F6E\u6F8E\u6F7A\u6F70\u6F64\u6F97\u6F58\u6ED5\u6F6F\u6F60\u6F5F\u719F\u71AC\u71B1\u71A8\u7256\u729B\u734E\u7357\u7469\u748B\u7483\u747E\u7480\u757F\u7620\u7629\u761F\u7624\u7626\u7621\u7622\u769A\u76BA\u76E4\u778E\u7787\u778C\u7791\u778B\u78CB\u78C5\u78BA\u78CA\u78BE\u78D5\u78BC\u78D0\u7A3F\u7A3C\u7A40\u7A3D\u7A37\u7A3B\u7AAF\u7AAE\u7BAD\u7BB1\u7BC4\u7BB4\u7BC6\u7BC7\u7BC1\u7BA0\u7BCC\u7CCA\u7DE0\u7DF4\u7DEF\u7DFB\u7DD8\u7DEC\u7DDD\u7DE8\u7DE3\u7DDA\u7DDE\u7DE9\u7D9E\u7DD9\u7DF2\u7DF9\u7F75\u7F77\u7FAF\u7FE9\u8026\u819B\u819C\u819D\u81A0\u819A\u8198\u8517\u853D\u851A\u84EE\u852C\u852D\u8513\u8511\u8523\u8521\u8514\u84EC\u8525\u84FF\u8506\u8782\u8774\u8776\u8760\u8766\u8778\u8768\u8759\u8757\u874C\u8753\u885B\u885D\u8910\u8907\u8912\u8913\u8915\u890A\u8ABC\u8AD2\u8AC7\u8AC4\u8A95\u8ACB\u8AF8\u8AB2\u8AC9\u8AC2\u8ABF\u8AB0\u8AD6\u8ACD\u8AB6\u8AB9\u8ADB\u8C4C\u8C4E\u8C6C\u8CE0\u8CDE\u8CE6\u8CE4\u8CEC\u8CED\u8CE2\u8CE3\u8CDC\u8CEA\u8CE1\u8D6D\u8D9F\u8DA3\u8E2B\u8E10\u8E1D\u8E22\u8E0F\u8E29\u8E1F\u8E21\u8E1E\u8EBA\u8F1D\u8F1B\u8F1F\u8F29\u8F26\u8F2A\u8F1C\u8F1E\u8F25\u9069\u906E\u9068\u906D\u9077\u9130\u912D\u9127\u9131\u9187\u9189\u918B\u9183\u92C5\u92BB\u92B7\u92EA\u92AC\u92E4\u92C1\u92B3\u92BC\u92D2\u92C7\u92F0\u92B2\u95AD\u95B1\u9704\u9706\u9707\u9709\u9760\u978D\u978B\u978F\u9821\u982B\u981C\u98B3\u990A\u9913\u9912\u9918\u99DD\u99D0\u99DF\u99DB\u99D1\u99D5\u99D2\u99D9\u9AB7\u9AEE\u9AEF\u9B27\u9B45\u9B44\u9B77\u9B6F\u9D06\u9D09\u9D03\u9EA9\u9EBE\u9ECE\u58A8\u9F52\u5112\u5118\u5114\u5110\u5115\u5180\u51AA\u51DD\u5291\u5293\u52F3\u5659\u566B\u5679\u5669\u5664\u5678\u566A\u5668\u5665\u5671\u566F\u566C\u5662\u5676\u58C1\u58BE\u58C7\u58C5\u596E\u5B1D\u5B34\u5B78\u5BF0\u5C0E\u5F4A\u61B2\u6191\u61A9\u618A\u61CD\u61B6\u61BE\u61CA\u61C8\u6230\u64C5\u64C1\u64CB\u64BB\u64BC\u64DA\u64C4\u64C7\u64C2\u64CD\u64BF\u64D2\u64D4\u64BE\u6574\u66C6\u66C9\u66B9\u66C4\u66C7\u66B8\u6A3D\u6A38\u6A3A\u6A59\u6A6B\u6A58\u6A39\u6A44\u6A62\u6A61\u6A4B\u6A47\u6A35\u6A5F\u6A48\u6B59\u6B77\u6C05\u6FC2\u6FB1\u6FA1\u6FC3\u6FA4\u6FC1\u6FA7\u6FB3\u6FC0\u6FB9\u6FB6\u6FA6\u6FA0\u6FB4\u71BE\u71C9\u71D0\u71D2\u71C8\u71D5\u71B9\u71CE\u71D9\u71DC\u71C3\u71C4\u7368\u749C\u74A3\u7498\u749F\u749E\u74E2\u750C\u750D\u7634\u7638\u763A\u76E7\u76E5\u77A0\u779E\u779F\u77A5\u78E8\u78DA\u78EC\u78E7\u79A6\u7A4D\u7A4E\u7A46\u7A4C\u7A4B\u7ABA\u7BD9\u7C11\u7BC9\u7BE4\u7BDB\u7BE1\u7BE9\u7BE6\u7CD5\u7CD6\u7E0A\u7E11\u7E08\u7E1B\u7E23\u7E1E\u7E1D\u7E09\u7E10\u7F79\u7FB2\u7FF0\u7FF1\u7FEE\u8028\u81B3\u81A9\u81A8\u81FB\u8208\u8258\u8259\u854A\u8559\u8548\u8568\u8569\u8543\u8549\u856D\u856A\u855E\u8783\u879F\u879E\u87A2\u878D\u8861\u892A\u8932\u8925\u892B\u8921\u89AA\u89A6\u8AE6\u8AFA\u8AEB\u8AF1\u8B00\u8ADC\u8AE7\u8AEE\u8AFE\u8B01\u8B02\u8AF7\u8AED\u8AF3\u8AF6\u8AFC\u8C6B\u8C6D\u8C93\u8CF4\u8E44\u8E31\u8E34\u8E42\u8E39\u8E35\u8F3B\u8F2F\u8F38\u8F33\u8FA8\u8FA6\u9075\u9074\u9078\u9072\u907C\u907A\u9134\u9192\u9320\u9336\u92F8\u9333\u932F\u9322\u92FC\u932B\u9304\u931A\u9310\u9326\u9321\u9315\u932E\u9319\u95BB\u96A7\u96A8\u96AA\u96D5\u970E\u9711\u9716\u970D\u9713\u970F\u975B\u975C\u9766\u9798\u9830\u9838\u983B\u9837\u982D\u9839\u9824\u9910\u9928\u991E\u991B\u9921\u991A\u99ED\u99E2\u99F1\u9AB8\u9ABC\u9AFB\u9AED\u9B28\u9B91\u9D15\u9D23\u9D26\u9D28\u9D12\u9D1B\u9ED8\u9ED4\u9F8D\u9F9C\u512A\u511F\u5121\u5132\u52F5\u568E\u5680\u5690\u5685\u5687\u568F\u58D5\u58D3\u58D1\u58CE\u5B30\u5B2A\u5B24\u5B7A\u5C37\u5C68\u5DBC\u5DBA\u5DBD\u5DB8\u5E6B\u5F4C\u5FBD\u61C9\u61C2\u61C7\u61E6\u61CB\u6232\u6234\u64CE\u64CA\u64D8\u64E0\u64F0\u64E6\u64EC\u64F1\u64E2\u64ED\u6582\u6583\u66D9\u66D6\u6A80\u6A94\u6A84\u6AA2\u6A9C\u6ADB\u6AA3\u6A7E\u6A97\u6A90\u6AA0\u6B5C\u6BAE\u6BDA\u6C08\u6FD8\u6FF1\u6FDF\u6FE0\u6FDB\u6FE4\u6FEB\u6FEF\u6F80\u6FEC\u6FE1\u6FE9\u6FD5\u6FEE\u6FF0\u71E7\u71DF\u71EE\u71E6\u71E5\u71ED\u71EC\u71F4\u71E0\u7235\u7246\u7370\u7372\u74A9\u74B0\u74A6\u74A8\u7646\u7642\u764C\u76EA\u77B3\u77AA\u77B0\u77AC\u77A7\u77AD\u77EF\u78F7\u78FA\u78F4\u78EF\u7901\u79A7\u79AA\u7A57\u7ABF\u7C07\u7C0D\u7BFE\u7BF7\u7C0C\u7BE0\u7CE0\u7CDC\u7CDE\u7CE2\u7CDF\u7CD9\u7CDD\u7E2E\u7E3E\u7E46\u7E37\u7E32\u7E43\u7E2B\u7E3D\u7E31\u7E45\u7E41\u7E34\u7E39\u7E48\u7E35\u7E3F\u7E2F\u7F44\u7FF3\u7FFC\u8071\u8072\u8070\u806F\u8073\u81C6\u81C3\u81BA\u81C2\u81C0\u81BF\u81BD\u81C9\u81BE\u81E8\u8209\u8271\u85AA\u8584\u857E\u859C\u8591\u8594\u85AF\u859B\u8587\u85A8\u858A\u8667\u87C0\u87D1\u87B3\u87D2\u87C6\u87AB\u87BB\u87BA\u87C8\u87CB\u893B\u8936\u8944\u8938\u893D\u89AC\u8B0E\u8B17\u8B19\u8B1B\u8B0A\u8B20\u8B1D\u8B04\u8B10\u8C41\u8C3F\u8C73\u8CFA\u8CFD\u8CFC\u8CF8\u8CFB\u8DA8\u8E49\u8E4B\u8E48\u8E4A\u8F44\u8F3E\u8F42\u8F45\u8F3F\u907F\u907D\u9084\u9081\u9082\u9080\u9139\u91A3\u919E\u919C\u934D\u9382\u9328\u9375\u934A\u9365\u934B\u9318\u937E\u936C\u935B\u9370\u935A\u9354\u95CA\u95CB\u95CC\u95C8\u95C6\u96B1\u96B8\u96D6\u971C\u971E\u97A0\u97D3\u9846\u98B6\u9935\u9A01\u99FF\u9BAE\u9BAB\u9BAA\u9BAD\u9D3B\u9D3F\u9E8B\u9ECF\u9EDE\u9EDC\u9EDD\u9EDB\u9F3E\u9F4B\u53E2\u5695\u56AE\u58D9\u58D8\u5B38\u5F5D\u61E3\u6233\u64F4\u64F2\u64FE\u6506\u64FA\u64FB\u64F7\u65B7\u66DC\u6726\u6AB3\u6AAC\u6AC3\u6ABB\u6AB8\u6AC2\u6AAE\u6AAF\u6B5F\u6B78\u6BAF\u7009\u700B\u6FFE\u7006\u6FFA\u7011\u700F\u71FB\u71FC\u71FE\u71F8\u7377\u7375\u74A7\u74BF\u7515\u7656\u7658\u7652\u77BD\u77BF\u77BB\u77BC\u790E\u79AE\u7A61\u7A62\u7A60\u7AC4\u7AC5\u7C2B\u7C27\u7C2A\u7C1E\u7C23\u7C21\u7CE7\u7E54\u7E55\u7E5E\u7E5A\u7E61\u7E52\u7E59\u7F48\u7FF9\u7FFB\u8077\u8076\u81CD\u81CF\u820A\u85CF\u85A9\u85CD\u85D0\u85C9\u85B0\u85BA\u85B9\u85A6\u87EF\u87EC\u87F2\u87E0\u8986\u89B2\u89F4\u8B28\u8B39\u8B2C\u8B2B\u8C50\u8D05\u8E59\u8E63\u8E66\u8E64\u8E5F\u8E55\u8EC0\u8F49\u8F4D\u9087\u9083\u9088\u91AB\u91AC\u91D0\u9394\u938A\u9396\u93A2\u93B3\u93AE\u93AC\u93B0\u9398\u939A\u9397\u95D4\u95D6\u95D0\u95D5\u96E2\u96DC\u96D9\u96DB\u96DE\u9724\u97A3\u97A6\u97AD\u97F9\u984D\u984F\u984C\u984E\u9853\u98BA\u993E\u993F\u993D\u992E\u99A5\u9A0E\u9AC1\u9B03\u9B06\u9B4F\u9B4E\u9B4D\u9BCA\u9BC9\u9BFD\u9BC8\u9BC0\u9D51\u9D5D\u9D60\u9EE0\u9F15\u9F2C\u5133\u56A5\u58DE\u58DF\u58E2\u5BF5\u9F90\u5EEC\u61F2\u61F7\u61F6\u61F5\u6500\u650F\u66E0\u66DD\u6AE5\u6ADD\u6ADA\u6AD3\u701B\u701F\u7028\u701A\u701D\u7015\u7018\u7206\u720D\u7258\u72A2\u7378\u737A\u74BD\u74CA\u74E3\u7587\u7586\u765F\u7661\u77C7\u7919\u79B1\u7A6B\u7A69\u7C3E\u7C3F\u7C38\u7C3D\u7C37\u7C40\u7E6B\u7E6D\u7E79\u7E69\u7E6A\u7F85\u7E73\u7FB6\u7FB9\u7FB8\u81D8\u85E9\u85DD\u85EA\u85D5\u85E4\u85E5\u85F7\u87FB\u8805\u880D\u87F9\u87FE\u8960\u895F\u8956\u895E\u8B41\u8B5C\u8B58\u8B49\u8B5A\u8B4E\u8B4F\u8B46\u8B59\u8D08\u8D0A\u8E7C\u8E72\u8E87\u8E76\u8E6C\u8E7A\u8E74\u8F54\u8F4E\u8FAD\u908A\u908B\u91B1\u91AE\u93E1\u93D1\u93DF\u93C3\u93C8\u93DC\u93DD\u93D6\u93E2\u93CD\u93D8\u93E4\u93D7\u93E8\u95DC\u96B4\u96E3\u972A\u9727\u9761\u97DC\u97FB\u985E\u9858\u985B\u98BC\u9945\u9949\u9A16\u9A19\u9B0D\u9BE8\u9BE7\u9BD6\u9BDB\u9D89\u9D61\u9D72\u9D6A\u9D6C\u9E92\u9E97\u9E93\u9EB4\u52F8\u56A8\u56B7\u56B6\u56B4\u56BC\u58E4\u5B40\u5B43\u5B7D\u5BF6\u5DC9\u61F8\u61FA\u6518\u6514\u6519\u66E6\u6727\u6AEC\u703E\u7030\u7032\u7210\u737B\u74CF\u7662\u7665\u7926\u792A\u792C\u792B\u7AC7\u7AF6\u7C4C\u7C43\u7C4D\u7CEF\u7CF0\u8FAE\u7E7D\u7E7C\u7E82\u7F4C\u8000\u81DA\u8266\u85FB\u85F9\u8611\u85FA\u8606\u860B\u8607\u860A\u8814\u8815\u8964\u89BA\u89F8\u8B70\u8B6C\u8B66\u8B6F\u8B5F\u8B6B\u8D0F\u8D0D\u8E89\u8E81\u8E85\u8E82\u91B4\u91CB\u9418\u9403\u93FD\u95E1\u9730\u98C4\u9952\u9951\u99A8\u9A2B\u9A30\u9A37\u9A35\u9C13\u9C0D\u9E79\u9EB5\u9EE8\u9F2F\u9F5F\u9F63\u9F61\u5137\u5138\u56C1\u56C0\u56C2\u5914\u5C6C\u5DCD\u61FC\u61FE\u651D\u651C\u6595\u66E9\u6AFB\u6B04\u6AFA\u6BB2\u704C\u721B\u72A7\u74D6\u74D4\u7669\u77D3\u7C50\u7E8F\u7E8C\u7FBC\u8617\u862D\u861A\u8823\u8822\u8821\u881F\u896A\u896C\u89BD\u8B74\u8B77\u8B7D\u8D13\u8E8A\u8E8D\u8E8B\u8F5F\u8FAF\u91BA\u942E\u9433\u9435\u943A\u9438\u9432\u942B\u95E2\u9738\u9739\u9732\u97FF\u9867\u9865\u9957\u9A45\u9A43\u9A40\u9A3E\u9ACF\u9B54\u9B51\u9C2D\u9C25\u9DAF\u9DB4\u9DC2\u9DB8\u9E9D\u9EEF\u9F19\u9F5C\u9F66\u9F67\u513C\u513B\u56C8\u56CA\u56C9\u5B7F\u5DD4\u5DD2\u5F4E\u61FF\u6524\u6B0A\u6B61\u7051\u7058\u7380\u74E4\u758A\u766E\u766C\u79B3\u7C60\u7C5F\u807E\u807D\u81DF\u8972\u896F\u89FC\u8B80\u8D16\u8D17\u8E91\u8E93\u8F61\u9148\u9444\u9451\u9452\u973D\u973E\u97C3\u97C1\u986B\u9955\u9A55\u9A4D\u9AD2\u9B1A\u9C49\u9C31\u9C3E\u9C3B\u9DD3\u9DD7\u9F34\u9F6C\u9F6A\u9F94\u56CC\u5DD6\u6200\u6523\u652B\u652A\u66EC\u6B10\u74DA\u7ACA\u7C64\u7C63\u7C65\u7E93\u7E96\u7E94\u81E2\u8638\u863F\u8831\u8B8A\u9090\u908F\u9463\u9460\u9464\u9768\u986F\u995C\u9A5A\u9A5B\u9A57\u9AD3\u9AD4\u9AD1\u9C54\u9C57\u9C56\u9DE5\u9E9F\u9EF4\u56D1\u58E9\u652C\u705E\u7671\u7672\u77D7\u7F50\u7F88\u8836\u8839\u8862\u8B93\u8B92\u8B96\u8277\u8D1B\u91C0\u946A\u9742\u9748\u9744\u97C6\u9870\u9A5F\u9B22\u9B58\u9C5F\u9DF9\u9DFA\u9E7C\u9E7D\u9F07\u9F77\u9F72\u5EF3\u6B16\u7063\u7C6C\u7C6E\u883B\u89C0\u8EA1\u91C1\u9472\u9470\u9871\u995E\u9AD6\u9B23\u9ECC\u7064\u77DA\u8B9A\u9477\u97C9\u9A62\u9A65\u7E9C\u8B9C\u8EAA\u91C5\u947D\u947E\u947C\u9C77\u9C78\u9EF7\u8C54\u947F\u9E1A\u7228\u9A6A\u9B31\u9E1B\u9E1E\u7C72\u2460\u2461\u2462\u2463\u2464\u2465\u2466\u2467\u2468\u2469\u2474\u2475\u2476\u2477\u2478\u2479\u247A\u247B\u247C\u247D\u2170\u2171\u2172\u2173\u2174\u2175\u2176\u2177\u2178\u2179\u4E36\u4E3F\u4E85\u4EA0\u5182\u5196\u51AB\u52F9\u5338\u5369\u53B6\u590A\u5B80\u5DDB\u2F33\u5E7F\u5EF4\u5F50\u5F61\u6534\u65E0\u7592\u7676\u8FB5\u96B6\u00A8\u02C6\u30FD\u30FE\u309D\u309E\u3003\u4EDD\u3005\u3006\u3007\u30FC\uFF3B\uFF3D\u273D\u3041\u3042\u3043\u3044\u3045\u3046\u3047\u3048\u3049\u304A\u304B\u304C\u304D\u304E\u304F\u3050\u3051\u3052\u3053\u3054\u3055\u3056\u3057\u3058\u3059\u305A\u305B\u305C\u305D\u305E\u305F\u3060\u3061\u3062\u3063\u3064\u3065\u3066\u3067\u3068\u3069\u306A\u306B\u306C\u306D\u306E\u306F\u3070\u3071\u3072\u3073\u3074\u3075\u3076\u3077\u3078\u3079\u307A\u307B\u307C\u307D\u307E\u307F\u3080\u3081\u3082\u3083\u3084\u3085\u3086\u3087\u3088\u3089\u308A\u308B\u308C\u308D\u308E\u308F\u3090\u3091\u3092\u3093\u30A1\u30A2\u30A3\u30A4\u30A5\u30A6\u30A7\u30A8\u30A9\u30AA\u30AB\u30AC\u30AD\u30AE\u30AF\u30B0\u30B1\u30B2\u30B3\u30B4\u30B5\u30B6\u30B7\u30B8\u30B9\u30BA\u30BB\u30BC\u30BD\u30BE\u30BF\u30C0\u30C1\u30C2\u30C3\u30C4\u30C5\u30C6\u30C7\u30C8\u30C9\u30CA\u30CB\u30CC\u30CD\u30CE\u30CF\u30D0\u30D1\u30D2\u30D3\u30D4\u30D5\u30D6\u30D7\u30D8\u30D9\u30DA\u30DB\u30DC\u30DD\u30DE\u30DF\u30E0\u30E1\u30E2\u30E3\u30E4\u30E5\u30E6\u30E7\u30E8\u30E9\u30EA\u30EB\u30EC\u30ED\u30EE\u30EF\u30F0\u30F1\u30F2\u30F3\u30F4\u30F5\u30F6\u0410\u0411\u0412\u0413\u0414\u0415\u0401\u0416\u0417\u0418\u0419\u041A\u041B\u041C\u041D\u041E\u041F\u0420\u0421\u0422\u0423\u0424\u0425\u0426\u0427\u0428\u0429\u042A\u042B\u042C\u042D\u042E\u042F\u0430\u0431\u0432\u0433\u0434\u0435\u0451\u0436\u0437\u0438\u0439\u043A\u043B\u043C\u043D\u043E\u043F\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044A\u044B\u044C\u044D\u044E\u044F\u21E7\u21B8\u21B9\u31CF\u00CC\u4E5A\u008A\u5202\u4491\u9FB0\u5188\u9FB1\u7607";
+
+    private static final String TABLE4 = "\uFFE2\uFFE4\uFF07\uFF02\u3231\u2116\u2121\u309B\u309C\u2E80\u2E84\u2E86\u2E87\u2E88\u2E8A\u2E8C\u2E8D\u2E95\u2E9C\u2E9D\u2EA5\u2EA7\u2EAA\u2EAC\u2EAE\u2EB6\u2EBC\u2EBE\u2EC6\u2ECA\u2ECC\u2ECD\u2ECF\u2ED6\u2ED7\u2EDE\u2EE3\u0000\u0000\u0000\u0283\u0250\u025B\u0254\u0275\u0153\u00F8\u014B\u028A\u026A\u4E42\u4E5C\u51F5\u531A\u5382\u4E07\u4E0C\u4E47\u4E8D\u56D7\uFA0C\u5C6E\u5F73\u4E0F\u5187\u4E0E\u4E2E\u4E93\u4EC2\u4EC9\u4EC8\u5198\u52FC\u536C\u53B9\u5720\u5903\u592C\u5C10\u5DFF\u65E1\u6BB3\u6BCC\u6C14\u723F\u4E31\u4E3C\u4EE8\u4EDC\u4EE9\u4EE1\u4EDD\u4EDA\u520C\u531C\u534C\u5722\u5723\u5917\u592F\u5B81\u5B84\u5C12\u5C3B\u5C74\u5C73\u5E04\u5E80\u5E82\u5FC9\u6209\u6250\u6C15\u6C36\u6C43\u6C3F\u6C3B\u72AE\u72B0\u738A\u79B8\u808A\u961E\u4F0E\u4F18\u4F2C\u4EF5\u4F14\u4EF1\u4F00\u4EF7\u4F08\u4F1D\u4F02\u4F05\u4F22\u4F13\u4F04\u4EF4\u4F12\u51B1\u5213\u5209\u5210\u52A6\u5322\u531F\u534D\u538A\u5407\u56E1\u56DF\u572E\u572A\u5734\u593C\u5980\u597C\u5985\u597B\u597E\u5977\u597F\u5B56\u5C15\u5C25\u5C7C\u5C7A\u5C7B\u5C7E\u5DDF\u5E75\u5E84\u5F02\u5F1A\u5F74\u5FD5\u5FD4\u5FCF\u625C\u625E\u6264\u6261\u6266\u6262\u6259\u6260\u625A\u6265\u65EF\u65EE\u673E\u6739\u6738\u673B\u673A\u673F\u673C\u6733\u6C18\u6C46\u6C52\u6C5C\u6C4F\u6C4A\u6C54\u6C4B\u6C4C\u7071\u725E\u72B4\u72B5\u738E\u752A\u767F\u7A75\u7F51\u8278\u827C\u8280\u827D\u827F\u864D\u897E\u9099\u9097\u9098\u909B\u9094\u9622\u9624\u9620\u9623\u4F56\u4F3B\u4F62\u4F49\u4F53\u4F64\u4F3E\u4F67\u4F52\u4F5F\u4F41\u4F58\u4F2D\u4F33\u4F3F\u4F61\u518F\u51B9\u521C\u521E\u5221\u52AD\u52AE\u5309\u5363\u5372\u538E\u538F\u5430\u5437\u542A\u5454\u5445\u5419\u541C\u5425\u5418\u543D\u544F\u5441\u5428\u5424\u5447\u56EE\u56E7\u56E5\u5741\u5745\u574C\u5749\u574B\u5752\u5906\u5940\u59A6\u5998\u59A0\u5997\u598E\u59A2\u5990\u598F\u59A7\u59A1\u5B8E\u5B92\u5C28\u5C2A\u5C8D\u5C8F\u5C88\u5C8B\u5C89\u5C92\u5C8A\u5C86\u5C93\u5C95\u5DE0\u5E0A\u5E0E\u5E8B\u5E89\u5E8C\u5E88\u5E8D\u5F05\u5F1D\u5F78\u5F76\u5FD2\u5FD1\u5FD0\u5FED\u5FE8\u5FEE\u5FF3\u5FE1\u5FE4\u5FE3\u5FFA\u5FEF\u5FF7\u5FFB\u6000\u5FF4\u623A\u6283\u628C\u628E\u628F\u6294\u6287\u6271\u627B\u627A\u6270\u6281\u6288\u6277\u627D\u6272\u6274\u6537\u65F0\u65F4\u65F3\u65F2\u65F5\u6745\u6747\u6759\u6755\u674C\u6748\u675D\u674D\u675A\u674B\u6BD0\u6C19\u6C1A\u6C78\u6C67\u6C6B\u6C84\u6C8B\u6C8F\u6C71\u6C6F\u6C69\u6C9A\u6C6D\u6C87\u6C95\u6C9C\u6C66\u6C73\u6C65\u6C7B\u6C8E\u7074\u707A\u7263\u72BF\u72BD\u72C3\u72C6\u72C1\u72BA\u72C5\u7395\u7397\u7393\u7394\u7392\u753A\u7539\u7594\u7595\u7681\u793D\u8034\u8095\u8099\u8090\u8092\u809C\u8290\u828F\u8285\u828E\u8291\u8293\u828A\u8283\u8284\u8C78\u8FC9\u8FBF\u909F\u90A1\u90A5\u909E\u90A7\u90A0\u9630\u9628\u962F\u962D\u4E33\u4F98\u4F7C\u4F85\u4F7D\u4F80\u4F87\u4F76\u4F74\u4F89\u4F84\u4F77\u4F4C\u4F97\u4F6A\u4F9A\u4F79\u4F81\u4F78\u4F90\u4F9C\u4F94\u4F9E\u4F92\u4F82\u4F95\u4F6B\u4F6E\u519E\u51BC\u51BE\u5235\u5232\u5233\u5246\u5231\u52BC\u530A\u530B\u533C\u5392\u5394\u5487\u547F\u5481\u5491\u5482\u5488\u546B\u547A\u547E\u5465\u546C\u5474\u5466\u548D\u546F\u5461\u5460\u5498\u5463\u5467\u5464\u56F7\u56F9\u576F\u5772\u576D\u576B\u5771\u5770\u5776\u5780\u5775\u577B\u5773\u5774\u5762\u5768\u577D\u590C\u5945\u59B5\u59BA\u59CF\u59CE\u59B2\u59CC\u59C1\u59B6\u59BC\u59C3\u59D6\u59B1\u59BD\u59C0\u59C8\u59B4\u59C7\u5B62\u5B65\u5B93\u5B95\u5C44\u5C47\u5CAE\u5CA4\u5CA0\u5CB5\u5CAF\u5CA8\u5CAC\u5C9F\u5CA3\u5CAD\u5CA2\u5CAA\u5CA7\u5C9D\u5CA5\u5CB6\u5CB0\u5CA6\u5E17\u5E14\u5E19\u5F28\u5F22\u5F23\u5F24\u5F54\u5F82\u5F7E\u5F7D\u5FDE\u5FE5\u602D\u6026\u6019\u6032\u600B\u6034\u600A\u6017\u6033\u601A\u601E\u602C\u6022\u600D\u6010\u602E\u6013\u6011\u600C\u6009\u601C\u6214\u623D\u62AD\u62B4\u62D1\u62BE\u62AA\u62B6\u62CA\u62AE\u62B3\u62AF\u62BB\u62A9\u62B0\u62B8\u653D\u65A8\u65BB\u6609\u65FC\u6604\u6612\u6608\u65FB\u6603\u660B\u660D\u6605\u65FD\u6611\u6610\u66F6\u670A\u6785\u676C\u678E\u6792\u6776\u677B\u6798\u6786\u6784\u6774\u678D\u678C\u677A\u679F\u6791\u6799\u6783\u677D\u6781\u6778\u6779\u6794\u6B25\u6B80\u6B7E\u6BDE\u6C1D\u6C93\u6CEC\u6CEB\u6CEE\u6CD9\u6CB6\u6CD4\u6CAD\u6CE7\u6CB7\u6CD0\u6CC2\u6CBA\u6CC3\u6CC6\u6CED\u6CF2\u6CD2\u6CDD\u6CB4\u6C8A\u6C9D\u6C80\u6CDE\u6CC0\u6D30\u6CCD\u6CC7\u6CB0\u6CF9\u6CCF\u6CE9\u6CD1\u7094\u7098\u7085\u7093\u7086\u7084\u7091\u7096\u7082\u709A\u7083\u726A\u72D6\u72CB\u72D8\u72C9\u72DC\u72D2\u72D4\u72DA\u72CC\u72D1\u73A4\u73A1\u73AD\u73A6\u73A2\u73A0\u73AC\u739D\u74DD\u74E8\u753F\u7540\u753E\u758C\u7598\u76AF\u76F3\u76F1\u76F0\u76F5\u77F8\u77FC\u77F9\u77FB\u77FA\u77F7\u7942\u793F\u79C5\u7A78\u7A7B\u7AFB\u7C75\u7CFD\u8035\u808F\u80AE\u80A3\u80B8\u80B5\u80AD\u8220\u82A0\u82C0\u82AB\u829A\u8298\u829B\u82B5\u82A7\u82AE\u82BC\u829E\u82BA\u82B4\u82A8\u82A1\u82A9\u82C2\u82A4\u82C3\u82B6\u82A2\u8670\u866F\u866D\u866E\u8C56\u8FD2\u8FCB\u8FD3\u8FCD\u8FD6\u8FD5\u8FD7\u90B2\u90B4\u90AF\u90B3\u90B0\u9639\u963D\u963C\u963A\u9643\u4FCD\u4FC5\u4FD3\u4FB2\u4FC9\u4FCB\u4FC1\u4FD4\u4FDC\u4FD9\u4FBB\u4FB3\u4FDB\u4FC7\u4FD6\u4FBA\u4FC0\u4FB9\u4FEC\u5244\u5249\u52C0\u52C2\u533D\u537C\u5397\u5396\u5399\u5398\u54BA\u54A1\u54AD\u54A5\u54CF\u54C3\u830D\u54B7\u54AE\u54D6\u54B6\u54C5\u54C6\u54A0\u5470\u54BC\u54A2\u54BE\u5472\u54DE\u54B0\u57B5\u579E\u579F\u57A4\u578C\u5797\u579D\u579B\u5794\u5798\u578F\u5799\u57A5\u579A\u5795\u58F4\u590D\u5953\u59E1\u59DE\u59EE\u5A00\u59F1\u59DD\u59FA\u59FD\u59FC\u59F6\u59E4\u59F2\u59F7\u59DB\u59E9\u59F3\u59F5\u59E0\u59FE\u59F4\u59ED\u5BA8\u5C4C\u5CD0\u5CD8\u5CCC\u5CD7\u5CCB\u5CDB\u5CDE\u5CDA\u5CC9\u5CC7\u5CCA\u5CD6\u5CD3\u5CD4\u5CCF\u5CC8\u5CC6\u5CCE\u5CDF\u5CF8\u5DF9\u5E21\u5E22\u5E23\u5E20\u5E24\u5EB0\u5EA4\u5EA2\u5E9B\u5EA3\u5EA5\u5F07\u5F2E\u5F56\u5F86\u6037\u6039\u6054\u6072\u605E\u6045\u6053\u6047\u6049\u605B\u604C\u6040\u6042\u605F\u6024\u6044\u6058\u6066\u606E\u6242\u6243\u62CF\u630D\u630B\u62F5\u630E\u6303\u62EB\u62F9\u630F\u630C\u62F8\u62F6\u6300\u6313\u6314\u62FA\u6315\u62FB\u62F0\u6541\u6543\u65AA\u65BF\u6636\u6621\u6632\u6635\u661C\u6626\u6622\u6633\u662B\u663A\u661D\u6634\u6639\u662E\u670F\u6710\u67C1\u67F2\u67C8\u67BA\u67DC\u67BB\u67F8\u67D8\u67C0\u67B7\u67C5\u67EB\u67E4\u67DF\u67B5\u67CD\u67B3\u67F7\u67F6\u67EE\u67E3\u67C2\u67B9\u67CE\u67E7\u67F0\u67B2\u67FC\u67C6\u67ED\u67CC\u67AE\u67E6\u67DB\u67FA\u67C9\u67CA\u67C3\u67EA\u67CB\u6B28\u6B82\u6B84\u6BB6\u6BD6\u6BD8\u6BE0\u6C20\u6C21\u6D28\u6D34\u6D2D\u6D1F\u6D3C\u6D3F\u6D12\u6D0A\u6CDA\u6D33\u6D04\u6D19\u6D3A\u6D1A\u6D11\u6D00\u6D1D\u6D42\u6D01\u6D18\u6D37\u6D03\u6D0F\u6D40\u6D07\u6D20\u6D2C\u6D08\u6D22\u6D09\u6D10\u70B7\u709F\u70BE\u70B1\u70B0\u70A1\u70B4\u70B5\u70A9\u7241\u7249\u724A\u726C\u7270\u7273\u726E\u72CA\u72E4\u72E8\u72EB\u72DF\u72EA\u72E6\u72E3\u7385\u73CC\u73C2\u73C8\u73C5\u73B9\u73B6\u73B5\u73B4\u73EB\u73BF\u73C7\u73BE\u73C3\u73C6\u73B8\u73CB\u74EC\u74EE\u752E\u7547\u7548\u75A7\u75AA\u7679\u76C4\u7708\u7703\u7704\u7705\u770A\u76F7\u76FB\u76FA\u77E7\u77E8\u7806\u7811\u7812\u7805\u7810\u780F\u780E\u7809\u7803\u7813\u794A\u794C\u794B\u7945\u7944\u79D5\u79CD\u79CF\u79D6\u79CE\u7A80\u7A7E\u7AD1\u7B00\u7B01\u7C7A\u7C78\u7C79\u7C7F\u7C80\u7C81\u7D03\u7D08\u7D01\u7F58\u7F91\u7F8D\u7FBE\u8007\u800E\u800F\u8014\u8037\u80D8\u80C7\u80E0\u80D1\u80C8\u80C2\u80D0\u80C5\u80E3\u80D9\u80DC\u80CA\u80D5\u80C9\u80CF\u80D7\u80E6\u80CD\u81FF\u8221\u8294\u82D9\u82FE\u82F9\u8307\u82E8\u8300\u82D5\u833A\u82EB\u82D6\u82F4\u82EC\u82E1\u82F2\u82F5\u830C\u82FB\u82F6\u82F0\u82EA\u82E4\u82E0\u82FA\u82F3\u82ED\u8677\u8674\u867C\u8673\u8841\u884E\u8867\u886A\u8869\u89D3\u8A04\u8A07\u8D72\u8FE3\u8FE1\u8FEE\u8FE0\u90F1\u90BD\u90BF\u90D5\u90C5\u90BE\u90C7\u90CB\u90C8\u91D4\u91D3\u9654\u964F\u9651\u9653\u964A\u964E\u501E\u5005\u5007\u5013\u5022\u5030\u501B\u4FF5\u4FF4\u5033\u5037\u502C\u4FF6\u4FF7\u5017\u501C\u5020\u5027\u5035\u502F\u5031\u500E\u515A\u5194\u5193\u51CA\u51C4\u51C5\u51C8\u51CE\u5261\u525A\u5252\u525E\u525F\u5255\u5262\u52CD\u530E\u539E\u5526\u54E2\u5517\u5512\u54E7\u54F3\u54E4\u551A\u54FF\u5504\u5508\u54EB\u5511\u5505\u54F1\u550A\u54FB\u54F7\u54F8\u54E0\u550E\u5503\u550B\u5701\u5702\u57CC\u5832\u57D5\u57D2\u57BA\u57C6\u57BD\u57BC\u57B8\u57B6\u57BF\u57C7\u57D0\u57B9\u57C1\u590E\u594A\u5A19\u5A16\u5A2D\u5A2E\u5A15\u5A0F\u5A17\u5A0A\u5A1E\u5A33\u5B6C\u5BA7\u5BAD\u5BAC\u5C03\u5C56\u5C54\u5CEC\u5CFF\u5CEE\u5CF1\u5CF7\u5D00\u5CF9\u5E29\u5E28\u5EA8\u5EAE\u5EAA\u5EAC\u5F33\u5F30\u5F67\u605D\u605A\u6067\u6041\u60A2\u6088\u6080\u6092\u6081\u609D\u6083\u6095\u609B\u6097\u6087\u609C\u608E\u6219\u6246\u62F2\u6310\u6356\u632C\u6344\u6345\u6336\u6343\u63E4\u6339\u634B\u634A\u633C\u6329\u6341\u6334\u6358\u6354\u6359\u632D\u6347\u6333\u635A\u6351\u6338\u6357\u6340\u6348\u654A\u6546\u65C6\u65C3\u65C4\u65C2\u664A\u665F\u6647\u6651\u6712\u6713\u681F\u681A\u6849\u6832\u6833\u683B\u684B\u684F\u6816\u6831\u681C\u6835\u682B\u682D\u682F\u684E\u6844\u6834\u681D\u6812\u6814\u6826\u6828\u682E\u684D\u683A\u6825\u6820\u6B2C\u6B2F\u6B2D\u6B31\u6B34\u6B6D\u8082\u6B88\u6BE6\u6BE4\u6BE8\u6BE3\u6BE2\u6BE7\u6C25\u6D7A\u6D63\u6D64\u6D76\u6D0D\u6D61\u6D92\u6D58\u6D62\u6D6D\u6D6F\u6D91\u6D8D\u6DEF\u6D7F\u6D86\u6D5E\u6D67\u6D60\u6D97\u6D70\u6D7C\u6D5F\u6D82\u6D98\u6D2F\u6D68\u6D8B\u6D7E\u6D80\u6D84\u6D16\u6D83\u6D7B\u6D7D\u6D75\u6D90\u70DC\u70D3\u70D1\u70DD\u70CB\u7F39\u70E2\u70D7\u70D2\u70DE\u70E0\u70D4\u70CD\u70C5\u70C6\u70C7\u70DA\u70CE\u70E1\u7242\u7278\u7277\u7276\u7300\u72FA\u72F4\u72FE\u72F6\u72F3\u72FB\u7301\u73D3\u73D9\u73E5\u73D6\u73BC\u73E7\u73E3\u73E9\u73DC\u73D2\u73DB\u73D4\u73DD\u73DA\u73D7\u73D8\u73E8\u74DE\u74DF\u74F4\u74F5\u7521\u755B\u755F\u75B0\u75C1\u75BB\u75C4\u75C0\u75BF\u75B6\u75BA\u768A\u76C9\u771D\u771B\u7710\u7713\u7712\u7723\u7711\u7715\u7719\u771A\u7722\u7727\u7823\u782C\u7822\u7835\u782F\u7828\u782E\u782B\u7821\u7829\u7833\u782A\u7831\u7954\u795B\u794F\u795C\u7953\u7952\u7951\u79EB\u79EC\u79E0\u79EE\u79ED\u79EA\u79DC\u79DE\u79DD\u7A86\u7A89\u7A85\u7A8B\u7A8C\u7A8A\u7A87\u7AD8\u7B10\u7B04\u7B13\u7B05\u7B0F\u7B08\u7B0A\u7B0E\u7B09\u7B12\u7C84\u7C91\u7C8A\u7C8C\u7C88\u7C8D\u7C85\u7D1E\u7D1D\u7D11\u7D0E\u7D18\u7D16\u7D13\u7D1F\u7D12\u7D0F\u7D0C\u7F5C\u7F61\u7F5E\u7F60\u7F5D\u7F5B\u7F96\u7F92\u7FC3\u7FC2\u7FC0\u8016\u803E\u8039\u80FA\u80F2\u80F9\u80F5\u8101\u80FB\u8100\u8201\u822F\u8225\u8333\u832D\u8344\u8319\u8351\u8325\u8356\u833F\u8341\u8326\u831C\u8322\u8342\u834E\u831B\u832A\u8308\u833C\u834D\u8316\u8324\u8320\u8337\u832F\u8329\u8347\u8345\u834C\u8353\u831E\u832C\u834B\u8327\u8348\u8653\u8652\u86A2\u86A8\u8696\u868D\u8691\u869E\u8687\u8697\u8686\u868B\u869A\u8685\u86A5\u8699\u86A1\u86A7\u8695\u8698\u868E\u869D\u8690\u8694\u8843\u8844\u886D\u8875\u8876\u8872\u8880\u8871\u887F\u886F\u8883\u887E\u8874\u887C\u8A12\u8C47\u8C57\u8C7B\u8CA4\u8CA3\u8D76\u8D78\u8DB5\u8DB7\u8DB6\u8ED1\u8ED3\u8FFE\u8FF5\u9002\u8FFF\u8FFB\u9004\u8FFC\u8FF6\u90D6\u90E0\u90D9\u90DA\u90E3\u90DF\u90E5\u90D8\u90DB\u90D7\u90DC\u90E4\u9150\u914E\u914F\u91D5\u91E2\u91DA\u965C\u965F\u96BC\u98E3\u9ADF\u9B2F\u4E7F\u5070\u506A\u5061\u505E\u5060\u5053\u504B\u505D\u5072\u5048\u504D\u5041\u505B\u504A\u5062\u5015\u5045\u505F\u5069\u506B\u5063\u5064\u5046\u5040\u506E\u5073\u5057\u5051\u51D0\u526B\u526D\u526C\u526E\u52D6\u52D3\u532D\u539C\u5575\u5576\u553C\u554D\u5550\u5534\u552A\u5551\u5562\u5536\u5535\u5530\u5552\u5545\u550C\u5532\u5565\u554E\u5539\u5548\u552D\u553B\u5540\u554B\u570A\u5707\u57FB\u5814\u57E2\u57F6\u57DC\u57F4\u5800\u57ED\u57FD\u5808\u57F8\u580B\u57F3\u57CF\u5807\u57EE\u57E3\u57F2\u57E5\u57EC\u57E1\u580E\u57FC\u5810\u57E7\u5801\u580C\u57F1\u57E9\u57F0\u580D\u5804\u595C\u5A60\u5A58\u5A55\u5A67\u5A5E\u5A38\u5A35\u5A6D\u5A50\u5A5F\u5A65\u5A6C\u5A53\u5A64\u5A57\u5A43\u5A5D\u5A52\u5A44\u5A5B\u5A48\u5A8E\u5A3E\u5A4D\u5A39\u5A4C\u5A70\u5A69\u5A47\u5A51\u5A56\u5A42\u5A5C\u5B72\u5B6E\u5BC1\u5BC0\u5C59\u5D1E\u5D0B\u5D1D\u5D1A\u5D20\u5D0C\u5D28\u5D0D\u5D26\u5D25\u5D0F\u5D30\u5D12\u5D23\u5D1F\u5D2E\u5E3E\u5E34\u5EB1\u5EB4\u5EB9\u5EB2\u5EB3\u5F36\u5F38\u5F9B\u5F96\u5F9F\u608A\u6090\u6086\u60BE\u60B0\u60BA\u60D3\u60D4\u60CF\u60E4\u60D9\u60DD\u60C8\u60B1\u60DB\u60B7\u60CA\u60BF\u60C3\u60CD\u60C0\u6332\u6365\u638A\u6382\u637D\u63BD\u639E\u63AD\u639D\u6397\u63AB\u638E\u636F\u6387\u6390\u636E\u63AF\u6375\u639C\u636D\u63AE\u637C\u63A4\u633B\u639F\u6378\u6385\u6381\u6391\u638D\u6370\u6553\u65CD\u6665\u6661\u665B\u6659\u665C\u6662\u6718\u6879\u6887\u6890\u689C\u686D\u686E\u68AE\u68AB\u6956\u686F\u68A3\u68AC\u68A9\u6875\u6874\u68B2\u688F\u6877\u6892\u687C\u686B\u6872\u68AA\u6880\u6871\u687E\u689B\u6896\u688B\u68A0\u6889\u68A4\u6878\u687B\u6891\u688C\u688A\u687D\u6B36\u6B33\u6B37\u6B38\u6B91\u6B8F\u6B8D\u6B8E\u6B8C\u6C2A\u6DC0\u6DAB\u6DB4\u6DB3\u6E74\u6DAC\u6DE9\u6DE2\u6DB7\u6DF6\u6DD4\u6E00\u6DC8\u6DE0\u6DDF\u6DD6\u6DBE\u6DE5\u6DDC\u6DDD\u6DDB\u6DF4\u6DCA\u6DBD\u6DED\u6DF0\u6DBA\u6DD5\u6DC2\u6DCF\u6DC9\u6DD0\u6DF2\u6DD3\u6DFD\u6DD7\u6DCD\u6DE3\u6DBB\u70FA\u710D\u70F7\u7117\u70F4\u710C\u70F0\u7104\u70F3\u7110\u70FC\u70FF\u7106\u7113\u7100\u70F8\u70F6\u710B\u7102\u710E\u727E\u727B\u727C\u727F\u731D\u7317\u7307\u7311\u7318\u730A\u7308\u72FF\u730F\u731E\u7388\u73F6\u73F8\u73F5\u7404\u7401\u73FD\u7407\u7400\u73FA\u73FC\u73FF\u740C\u740B\u73F4\u7408\u7564\u7563\u75CE\u75D2\u75CF\u75CB\u75CC\u75D1\u75D0\u768F\u7689\u76D3\u7739\u772F\u772D\u7731\u7732\u7734\u7733\u773D\u7725\u773B\u7735\u7848\u7852\u7849\u784D\u784A\u784C\u7826\u7845\u7850\u7964\u7967\u7969\u796A\u7963\u796B\u7961\u79BB\u79FA\u79F8\u79F6\u79F7\u7A8F\u7A94\u7A90\u7B35\u7B47\u7B34\u7B25\u7B30\u7B22\u7B24\u7B33\u7B18\u7B2A\u7B1D\u7B31\u7B2B\u7B2D\u7B2F\u7B32\u7B38\u7B1A\u7B23\u7C94\u7C98\u7C96\u7CA3\u7D35\u7D3D\u7D38\u7D36\u7D3A\u7D45\u7D2C\u7D29\u7D41\u7D47\u7D3E\u7D3F\u7D4A\u7D3B\u7D28\u7F63\u7F95\u7F9C\u7F9D\u7F9B\u7FCA\u7FCB\u7FCD\u7FD0\u7FD1\u7FC7\u7FCF\u7FC9\u801F\u801E\u801B\u8047\u8043\u8048\u8118\u8125\u8119\u811B\u812D\u811F\u812C\u811E\u8121\u8115\u8127\u811D\u8122\u8211\u8238\u8233\u823A\u8234\u8232\u8274\u8390\u83A3\u83A8\u838D\u837A\u8373\u83A4\u8374\u838F\u8381\u8395\u8399\u8375\u8394\u83A9\u837D\u8383\u838C\u839D\u839B\u83AA\u838B\u837E\u83A5\u83AF\u8388\u8397\u83B0\u837F\u83A6\u8387\u83AE\u8376\u839A\u8659\u8656\u86BF\u86B7\u86C2\u86C1\u86C5\u86BA\u86B0\u86C8\u86B9\u86B3\u86B8\u86CC\u86B4\u86BB\u86BC\u86C3\u86BD\u86BE\u8852\u8889\u8895\u88A8\u88A2\u88AA\u889A\u8891\u88A1\u889F\u8898\u88A7\u8899\u889B\u8897\u88A4\u88AC\u888C\u8893\u888E\u8982\u89D6\u89D9\u89D5\u8A30\u8A27\u8A2C\u8A1E\u8C39\u8C3B\u8C5C\u8C5D\u8C7D\u8CA5\u8D7D\u8D7B\u8D79\u8DBC\u8DC2\u8DB9\u8DBF\u8DC1\u8ED8\u8EDE\u8EDD\u8EDC\u8ED7\u8EE0\u8EE1\u9024\u900B\u9011\u901C\u900C\u9021\u90EF\u90EA\u90F0\u90F4\u90F2\u90F3\u90D4\u90EB\u90EC\u90E9\u9156\u9158\u915A\u9153\u9155\u91EC\u91F4\u91F1\u91F3\u91F8\u91E4\u91F9\u91EA\u91EB\u91F7\u91E8\u91EE\u957A\u9586\u9588\u967C\u966D\u966B\u9671\u966F\u96BF\u976A\u9804\u98E5\u9997\u509B\u5095\u5094\u509E\u508B\u50A3\u5083\u508C\u508E\u509D\u5068\u509C\u5092\u5082\u5087\u515F\u51D4\u5312\u5311\u53A4\u53A7\u5591\u55A8\u55A5\u55AD\u5577\u5645\u55A2\u5593\u5588\u558F\u55B5\u5581\u55A3\u5592\u55A4\u557D\u558C\u55A6\u557F\u5595\u55A1\u558E\u570C\u5829\u5837\u5819\u581E\u5827\u5823\u5828\u57F5\u5848\u5825\u581C\u581B\u5833\u583F\u5836\u582E\u5839\u5838\u582D\u582C\u583B\u5961\u5AAF\u5A94\u5A9F\u5A7A\u5AA2\u5A9E\u5A78\u5AA6\u5A7C\u5AA5\u5AAC\u5A95\u5AAE\u5A37\u5A84\u5A8A\u5A97\u5A83\u5A8B\u5AA9\u5A7B\u5A7D\u5A8C\u5A9C\u5A8F\u5A93\u5A9D\u5BEA\u5BCD\u5BCB\u5BD4\u5BD1\u5BCA\u5BCE\u5C0C\u5C30\u5D37\u5D43\u5D6B\u5D41\u5D4B\u5D3F\u5D35\u5D51\u5D4E\u5D55\u5D33\u5D3A\u5D52\u5D3D\u5D31\u5D59\u5D42\u5D39\u5D49\u5D38\u5D3C\u5D32\u5D36\u5D40\u5D45\u5E44\u5E41\u5F58\u5FA6\u5FA5\u5FAB\u60C9\u60B9\u60CC\u60E2\u60CE\u60C4\u6114\u60F2\u610A\u6116\u6105\u60F5\u6113\u60F8\u60FC\u60FE\u60C1\u6103\u6118\u611D\u6110\u60FF\u6104\u610B\u624A\u6394\u63B1\u63B0\u63CE\u63E5\u63E8\u63EF\u63C3\u649D\u63F3\u63CA\u63E0\u63F6\u63D5\u63F2\u63F5\u6461\u63DF\u63BE\u63DD\u63DC\u63C4\u63D8\u63D3\u63C2\u63C7\u63CC\u63CB\u63C8\u63F0\u63D7\u63D9\u6532\u6567\u656A\u6564\u655C\u6568\u6565\u658C\u659D\u659E\u65AE\u65D0\u65D2\u667C\u666C\u667B\u6680\u6671\u6679\u666A\u6672\u6701\u690C\u68D3\u6904\u68DC\u692A\u68EC\u68EA\u68F1\u690F\u68D6\u68F7\u68EB\u68E4\u68F6\u6913\u6910\u68F3\u68E1\u6907\u68CC\u6908\u6970\u68B4\u6911\u68EF\u68C6\u6914\u68F8\u68D0\u68FD\u68FC\u68E8\u690B\u690A\u6917\u68CE\u68C8\u68DD\u68DE\u68E6\u68F4\u68D1\u6906\u68D4\u68E9\u6915\u6925\u68C7\u6B39\u6B3B\u6B3F\u6B3C\u6B94\u6B97\u6B99\u6B95\u6BBD\u6BF0\u6BF2\u6BF3\u6C30\u6DFC\u6E46\u6E47\u6E1F\u6E49\u6E88\u6E3C\u6E3D\u6E45\u6E62\u6E2B\u6E3F\u6E41\u6E5D\u6E73\u6E1C\u6E33\u6E4B\u6E40\u6E51\u6E3B\u6E03\u6E2E\u6E5E\u6E68\u6E5C\u6E61\u6E31\u6E28\u6E60\u6E71\u6E6B\u6E39\u6E22\u6E30\u6E53\u6E65\u6E27\u6E78\u6E64\u6E77\u6E55\u6E79\u6E52\u6E66\u6E35\u6E36\u6E5A\u7120\u711E\u712F\u70FB\u712E\u7131\u7123\u7125\u7122\u7132\u711F\u7128\u713A\u711B\u724B\u725A\u7288\u7289\u7286\u7285\u728B\u7312\u730B\u7330\u7322\u7331\u7333\u7327\u7332\u732D\u7326\u7323\u7335\u730C\u742E\u742C\u7430\u742B\u7416\u741A\u7421\u742D\u7431\u7424\u7423\u741D\u7429\u7420\u7432\u74FB\u752F\u756F\u756C\u75E7\u75DA\u75E1\u75E6\u75DD\u75DF\u75E4\u75D7\u7695\u7692\u76DA\u7746\u7747\u7744\u774D\u7745\u774A\u774E\u774B\u774C\u77DE\u77EC\u7860\u7864\u7865\u785C\u786D\u7871\u786A\u786E\u7870\u7869\u7868\u785E\u7862\u7974\u7973\u7972\u7970\u7A02\u7A0A\u7A03\u7A0C\u7A04\u7A99\u7AE6\u7AE4\u7B4A\u7B3B\u7B44\u7B48\u7B4C\u7B4E\u7B40\u7B58\u7B45\u7CA2\u7C9E\u7CA8\u7CA1\u7D58\u7D6F\u7D63\u7D53\u7D56\u7D67\u7D6A\u7D4F\u7D6D\u7D5C\u7D6B\u7D52\u7D54\u7D69\u7D51\u7D5F\u7D4E\u7F3E\u7F3F\u7F65\u7F66\u7FA2\u7FA0\u7FA1\u7FD7\u8051\u804F\u8050\u80FE\u80D4\u8143\u814A\u8152\u814F\u8147\u813D\u814D\u813A\u81E6\u81EE\u81F7\u81F8\u81F9\u8204\u823C\u823D\u823F\u8275\u833B\u83CF\u83F9\u8423\u83C0\u83E8\u8412\u83E7\u83E4\u83FC\u83F6\u8410\u83C6\u83C8\u83EB\u83E3\u83BF\u8401\u83DD\u83E5\u83D8\u83FF\u83E1\u83CB\u83CE\u83D6\u83F5\u83C9\u8409\u840F\u83DE\u8411\u8406\u83C2\u83F3\u83D5\u83FA\u83C7\u83D1\u83EA\u8413\u83C3\u83EC\u83EE\u83C4\u83FB\u83D7\u83E2\u841B\u83DB\u83FE\u86D8\u86E2\u86E6\u86D3\u86E3\u86DA\u86EA\u86DD\u86EB\u86DC\u86EC\u86E9\u86D7\u86E8\u86D1\u8848\u8856\u8855\u88BA\u88D7\u88B9\u88B8\u88C0\u88BE\u88B6\u88BC\u88B7\u88BD\u88B2\u8901\u88C9\u8995\u8998\u8997\u89DD\u89DA\u89DB\u8A4E\u8A4D\u8A39\u8A59\u8A40\u8A57\u8A58\u8A44\u8A45\u8A52\u8A48\u8A51\u8A4A\u8A4C\u8A4F\u8C5F\u8C81\u8C80\u8CBA\u8CBE\u8CB0\u8CB9\u8CB5\u8D84\u8D80\u8D89\u8DD8\u8DD3\u8DCD\u8DC7\u8DD6\u8DDC\u8DCF\u8DD5\u8DD9\u8DC8\u8DD7\u8DC5\u8EEF\u8EF7\u8EFA\u8EF9\u8EE6\u8EEE\u8EE5\u8EF5\u8EE7\u8EE8\u8EF6\u8EEB\u8EF1\u8EEC\u8EF4\u8EE9\u902D\u9034\u902F\u9106\u912C\u9104\u90FF\u90FC\u9108\u90F9\u90FB\u9101\u9100\u9107\u9105\u9103\u9161\u9164\u915F\u9162\u9160\u9201\u920A\u9225\u9203\u921A\u9226\u920F\u920C\u9200\u9212\u91FF\u91FD\u9206\u9204\u9227\u9202\u921C\u9224\u9219\u9217\u9205\u9216\u957B\u958D\u958C\u9590\u9687\u967E\u9688\u9689\u9683\u9680\u96C2\u96C8\u96C3\u96F1\u96F0\u976C\u9770\u976E\u9807\u98A9\u98EB\u9CE6\u9EF9\u4E83\u4E84\u4EB6\u50BD\u50BF\u50C6\u50AE\u50C4\u50CA\u50B4\u50C8\u50C2\u50B0\u50C1\u50BA\u50B1\u50CB\u50C9\u50B6\u50B8\u51D7\u527A\u5278\u527B\u527C\u55C3\u55DB\u55CC\u55D0\u55CB\u55CA\u55DD\u55C0\u55D4\u55C4\u55E9\u55BF\u55D2\u558D\u55CF\u55D5\u55E2\u55D6\u55C8\u55F2\u55CD\u55D9\u55C2\u5714\u5853\u5868\u5864\u584F\u584D\u5849\u586F\u5855\u584E\u585D\u5859\u5865\u585B\u583D\u5863\u5871\u58FC\u5AC7\u5AC4\u5ACB\u5ABA\u5AB8\u5AB1\u5AB5\u5AB0\u5ABF\u5AC8\u5ABB\u5AC6\u5AB7\u5AC0\u5ACA\u5AB4\u5AB6\u5ACD\u5AB9\u5A90\u5BD6\u5BD8\u5BD9\u5C1F\u5C33\u5D71\u5D63\u5D4A\u5D65\u5D72\u5D6C\u5D5E\u5D68\u5D67\u5D62\u5DF0\u5E4F\u5E4E\u5E4A\u5E4D\u5E4B\u5EC5\u5ECC\u5EC6\u5ECB\u5EC7\u5F40\u5FAF\u5FAD\u60F7\u6149\u614A\u612B\u6145\u6136\u6132\u612E\u6146\u612F\u614F\u6129\u6140\u6220\u9168\u6223\u6225\u6224\u63C5\u63F1\u63EB\u6410\u6412\u6409\u6420\u6424\u6433\u6443\u641F\u6415\u6418\u6439\u6437\u6422\u6423\u640C\u6426\u6430\u6428\u6441\u6435\u642F\u640A\u641A\u6440\u6425\u6427\u640B\u63E7\u641B\u642E\u6421\u640E\u656F\u6592\u65D3\u6686\u668C\u6695\u6690\u668B\u668A\u6699\u6694\u6678\u6720\u6966\u695F\u6938\u694E\u6962\u6971\u693F\u6945\u696A\u6939\u6942\u6957\u6959\u697A\u6948\u6949\u6935\u696C\u6933\u693D\u6965\u68F0\u6978\u6934\u6969\u6940\u696F\u6944\u6976\u6958\u6941\u6974\u694C\u693B\u694B\u6937\u695C\u694F\u6951\u6932\u6952\u692F\u697B\u693C\u6B46\u6B45\u6B43\u6B42\u6B48\u6B41\u6B9B\uFA0D\u6BFB\u6BFC\u6BF9\u6BF7\u6BF8\u6E9B\u6ED6\u6EC8\u6E8F\u6EC0\u6E9F\u6E93\u6E94\u6EA0\u6EB1\u6EB9\u6EC6\u6ED2\u6EBD\u6EC1\u6E9E\u6EC9\u6EB7\u6EB0\u6ECD\u6EA6\u6ECF\u6EB2\u6EBE\u6EC3\u6EDC\u6ED8\u6E99\u6E92\u6E8E\u6E8D\u6EA4\u6EA1\u6EBF\u6EB3\u6ED0\u6ECA\u6E97\u6EAE\u6EA3\u7147\u7154\u7152\u7163\u7160\u7141\u715D\u7162\u7172\u7178\u716A\u7161\u7142\u7158\u7143\u714B\u7170\u715F\u7150\u7153\u7144\u714D\u715A\u724F\u728D\u728C\u7291\u7290\u728E\u733C\u7342\u733B\u733A\u7340\u734A\u7349\u7444\u744A\u744B\u7452\u7451\u7457\u7440\u744F\u7450\u744E\u7442\u7446\u744D\u7454\u74E1\u74FF\u74FE\u74FD\u751D\u7579\u7577\u6983\u75EF\u760F\u7603\u75F7\u75FE\u75FC\u75F9\u75F8\u7610\u75FB\u75F6\u75ED\u75F5\u75FD\u7699\u76B5\u76DD\u7755\u775F\u7760\u7752\u7756\u775A\u7769\u7767\u7754\u7759\u776D\u77E0\u7887\u789A\u7894\u788F\u7884\u7895\u7885\u7886\u78A1\u7883\u7879\u7899\u7880\u7896\u787B\u797C\u7982\u797D\u7979\u7A11\u7A18\u7A19\u7A12\u7A17\u7A15\u7A22\u7A13\u7A1B\u7A10\u7AA3\u7AA2\u7A9E\u7AEB\u7B66\u7B64\u7B6D\u7B74\u7B69\u7B72\u7B65\u7B73\u7B71\u7B70\u7B61\u7B78\u7B76\u7B63\u7CB2\u7CB4\u7CAF\u7D88\u7D86\u7D80\u7D8D\u7D7F\u7D85\u7D7A\u7D8E\u7D7B\u7D83\u7D7C\u7D8C\u7D94\u7D84\u7D7D\u7D92\u7F6D\u7F6B\u7F67\u7F68\u7F6C\u7FA6\u7FA5\u7FA7\u7FDB\u7FDC\u8021\u8164\u8160\u8177\u815C\u8169\u815B\u8162\u8172\u6721\u815E\u8176\u8167\u816F\u8144\u8161\u821D\u8249\u8244\u8240\u8242\u8245\u84F1\u843F\u8456\u8476\u8479\u848F\u848D\u8465\u8451\u8440\u8486\u8467\u8430\u844D\u847D\u845A\u8459\u8474\u8473\u845D\u8507\u845E\u8437\u843A\u8434\u847A\u8443\u8478\u8432\u8445\u8429\u83D9\u844B\u842F\u8442\u842D\u845F\u8470\u8439\u844E\u844C\u8452\u846F\u84C5\u848E\u843B\u8447\u8436\u8433\u8468\u847E\u8444\u842B\u8460\u8454\u846E\u8450\u870B\u8704\u86F7\u870C\u86FA\u86D6\u86F5\u874D\u86F8\u870E\u8709\u8701\u86F6\u870D\u8705\u88D6\u88CB\u88CD\u88CE\u88DE\u88DB\u88DA\u88CC\u88D0\u8985\u899B\u89DF\u89E5\u89E4\u89E1\u89E0\u89E2\u89DC\u89E6\u8A76\u8A86\u8A7F\u8A61\u8A3F\u8A77\u8A82\u8A84\u8A75\u8A83\u8A81\u8A74\u8A7A\u8C3C\u8C4B\u8C4A\u8C65\u8C64\u8C66\u8C86\u8C84\u8C85\u8CCC\u8D68\u8D69\u8D91\u8D8C\u8D8E\u8D8F\u8D8D\u8D93\u8D94\u8D90\u8D92\u8DF0\u8DE0\u8DEC\u8DF1\u8DEE\u8DD0\u8DE9\u8DE3\u8DE2\u8DE7\u8DF2\u8DEB\u8DF4\u8F06\u8EFF\u8F01\u8F00\u8F05\u8F07\u8F08\u8F02\u8F0B\u9052\u903F\u9044\u9049\u903D\u9110\u910D\u910F\u9111\u9116\u9114\u910B\u910E\u916E\u916F\u9248\u9252\u9230\u923A\u9266\u9233\u9265\u925E\u9283\u922E\u924A\u9246\u926D\u926C\u924F\u9260\u9267\u926F\u9236\u9261\u9270\u9231\u9254\u9263\u9250\u9272\u924E\u9253\u924C\u9256\u9232\u959F\u959C\u959E\u959B\u9692\u9693\u9691\u9697\u96CE\u96FA\u96FD\u96F8\u96F5\u9773\u9777\u9778\u9772\u980F\u980D\u980E\u98AC\u98F6\u98F9\u99AF\u99B2\u99B0\u99B5\u9AAD\u9AAB\u9B5B\u9CEA\u9CED\u9CE7\u9E80\u9EFD\u50E6\u50D4\u50D7\u50E8\u50F3\u50DB\u50EA\u50DD\u50E4\u50D3\u50EC\u50F0\u50EF\u50E3\u50E0\u51D8\u5280\u5281\u52E9\u52EB\u5330\u53AC\u5627\u5615\u560C\u5612\u55FC\u560F\u561C\u5601\u5613\u5602\u55FA\u561D\u5604\u55FF\u55F9\u5889\u587C\u5890\u5898\u5886\u5881\u587F\u5874\u588B\u587A\u5887\u5891\u588E\u5876\u5882\u5888\u587B\u5894\u588F\u58FE\u596B\u5ADC\u5AEE\u5AE5\u5AD5\u5AEA\u5ADA\u5AED\u5AEB\u5AF3\u5AE2\u5AE0\u5ADB\u5AEC\u5ADE\u5ADD\u5AD9\u5AE8\u5ADF\u5B77\u5BE0\u5BE3\u5C63\u5D82\u5D80\u5D7D\u5D86\u5D7A\u5D81\u5D77\u5D8A\u5D89\u5D88\u5D7E\u5D7C\u5D8D\u5D79\u5D7F\u5E58\u5E59\u5E53\u5ED8\u5ED1\u5ED7\u5ECE\u5EDC\u5ED5\u5ED9\u5ED2\u5ED4\u5F44\u5F43\u5F6F\u5FB6\u612C\u6128\u6141\u615E\u6171\u6173\u6152\u6153\u6172\u616C\u6180\u6174\u6154\u617A\u615B\u6165\u613B\u616A\u6161\u6156\u6229\u6227\u622B\u642B\u644D\u645B\u645D\u6474\u6476\u6472\u6473\u647D\u6475\u6466\u64A6\u644E\u6482\u645E\u645C\u644B\u6453\u6460\u6450\u647F\u643F\u646C\u646B\u6459\u6465\u6477\u6573\u65A0\u66A1\u66A0\u669F\u6705\u6704\u6722\u69B1\u69B6\u69C9\u69A0\u69CE\u6996\u69B0\u69AC\u69BC\u6991\u6999\u698E\u69A7\u698D\u69A9\u69BE\u69AF\u69BF\u69C4\u69BD\u69A4\u69D4\u69B9\u69CA\u699A\u69CF\u69B3\u6993\u69AA\u69A1\u699E\u69D9\u6997\u6990\u69C2\u69B5\u69A5\u69C6\u6B4A\u6B4D\u6B4B\u6B9E\u6B9F\u6BA0\u6BC3\u6BC4\u6BFE\u6ECE\u6EF5\u6EF1\u6F03\u6F25\u6EF8\u6F37\u6EFB\u6F2E\u6F09\u6F4E\u6F19\u6F1A\u6F27\u6F18\u6F3B\u6F12\u6EED\u6F0A\u6F36\u6F73\u6EF9\u6EEE\u6F2D\u6F40\u6F30\u6F3C\u6F35\u6EEB\u6F07\u6F0E\u6F43\u6F05\u6EFD\u6EF6\u6F39\u6F1C\u6EFC\u6F3A\u6F1F\u6F0D\u6F1E\u6F08\u6F21\u7187\u7190\u7189\u7180\u7185\u7182\u718F\u717B\u7186\u7181\u7197\u7244\u7253\u7297\u7295\u7293\u7343\u734D\u7351\u734C\u7462\u7473\u7471\u7475\u7472\u7467\u746E\u7500\u7502\u7503\u757D\u7590\u7616\u7608\u760C\u7615\u7611\u760A\u7614\u76B8\u7781\u777C\u7785\u7782\u776E\u7780\u776F\u777E\u7783\u78B2\u78AA\u78B4\u78AD\u78A8\u787E\u78AB\u789E\u78A5\u78A0\u78AC\u78A2\u78A4\u7998\u798A\u798B\u7996\u7995\u7994\u7993\u7997\u7988\u7992\u7990\u7A2B\u7A4A\u7A30\u7A2F\u7A28\u7A26\u7AA8\u7AAB\u7AAC\u7AEE\u7B88\u7B9C\u7B8A\u7B91\u7B90\u7B96\u7B8D\u7B8C\u7B9B\u7B8E\u7B85\u7B98\u5284\u7B99\u7BA4\u7B82\u7CBB\u7CBF\u7CBC\u7CBA\u7DA7\u7DB7\u7DC2\u7DA3\u7DAA\u7DC1\u7DC0\u7DC5\u7D9D\u7DCE\u7DC4\u7DC6\u7DCB\u7DCC\u7DAF\u7DB9\u7D96\u7DBC\u7D9F\u7DA6\u7DAE\u7DA9\u7DA1\u7DC9\u7F73\u7FE2\u7FE3\u7FE5\u7FDE\u8024\u805D\u805C\u8189\u8186\u8183\u8187\u818D\u818C\u818B\u8215\u8497\u84A4\u84A1\u849F\u84BA\u84CE\u84C2\u84AC\u84AE\u84AB\u84B9\u84B4\u84C1\u84CD\u84AA\u849A\u84B1\u84D0\u849D\u84A7\u84BB\u84A2\u8494\u84C7\u84CC\u849B\u84A9\u84AF\u84A8\u84D6\u8498\u84B6\u84CF\u84A0\u84D7\u84D4\u84D2\u84DB\u84B0\u8491\u8661\u8733\u8723\u8728\u876B\u8740\u872E\u871E\u8721\u8719\u871B\u8743\u872C\u8741\u873E\u8746\u8720\u8732\u872A\u872D\u873C\u8712\u873A\u8731\u8735\u8742\u8726\u8727\u8738\u8724\u871A\u8730\u8711\u88F7\u88E7\u88F1\u88F2\u88FA\u88FE\u88EE\u88FC\u88F6\u88FB\u88F0\u88EC\u88EB\u899D\u89A1\u899F\u899E\u89E9\u89EB\u89E8\u8AAB\u8A99\u8A8B\u8A92\u8A8F\u8A96\u8C3D\u8C68\u8C69\u8CD5\u8CCF\u8CD7\u8D96\u8E09\u8E02\u8DFF\u8E0D\u8DFD\u8E0A\u8E03\u8E07\u8E06\u8E05\u8DFE\u8E00\u8E04\u8F10\u8F11\u8F0E\u8F0D\u9123\u911C\u9120\u9122\u911F\u911D\u911A\u9124\u9121\u911B\u917A\u9172\u9179\u9173\u92A5\u92A4\u9276\u929B\u927A\u92A0\u9294\u92AA\u928D\u92A6\u929A\u92AB\u9279\u9297\u927F\u92A3\u92EE\u928E\u9282\u9295\u92A2\u927D\u9288\u92A1\u928A\u9286\u928C\u9299\u92A7\u927E\u9287\u92A9\u929D\u928B\u922D\u969E\u96A1\u96FF\u9758\u977D\u977A\u977E\u9783\u9780\u9782\u977B\u9784\u9781\u977F\u97CE\u97CD\u9816\u98AD\u98AE\u9902\u9900\u9907\u999D\u999C\u99C3\u99B9\u99BB\u99BA\u99C2\u99BD\u99C7\u9AB1\u9AE3\u9AE7\u9B3E\u9B3F\u9B60\u9B61\u9B5F\u9CF1\u9CF2\u9CF5\u9EA7\u50FF\u5103\u5130\u50F8\u5106\u5107\u50F6\u50FE\u510B\u510C\u50FD\u510A\u528B\u528C\u52F1\u52EF\u5648\u5642\u564C\u5635\u5641\u564A\u5649\u5646\u5658\u565A\u5640\u5633\u563D\u562C\u563E\u5638\u562A\u563A\u571A\u58AB\u589D\u58B1\u58A0\u58A3\u58AF\u58AC\u58A5\u58A1\u58FF\u5AFF\u5AF4\u5AFD\u5AF7\u5AF6\u5B03\u5AF8\u5B02\u5AF9\u5B01\u5B07\u5B05\u5B0F\u5C67\u5D99\u5D97\u5D9F\u5D92\u5DA2\u5D93\u5D95\u5DA0\u5D9C\u5DA1\u5D9A\u5D9E\u5E69\u5E5D\u5E60\u5E5C\u7DF3\u5EDB\u5EDE\u5EE1\u5F49\u5FB2\u618B\u6183\u6179\u61B1\u61B0\u61A2\u6189\u619B\u6193\u61AF\u61AD\u619F\u6192\u61AA\u61A1\u618D\u6166\u61B3\u622D\u646E\u6470\u6496\u64A0\u6485\u6497\u649C\u648F\u648B\u648A\u648C\u64A3\u649F\u6468\u64B1\u6498\u6576\u657A\u6579\u657B\u65B2\u65B3\u66B5\u66B0\u66A9\u66B2\u66B7\u66AA\u66AF\u6A00\u6A06\u6A17\u69E5\u69F8\u6A15\u69F1\u69E4\u6A20\u69FF\u69EC\u69E2\u6A1B\u6A1D\u69FE\u6A27\u69F2\u69EE\u6A14\u69F7\u69E7\u6A40\u6A08\u69E6\u69FB\u6A0D\u69FC\u69EB\u6A09\u6A04\u6A18\u6A25\u6A0F\u69F6\u6A26\u6A07\u69F4\u6A16\u6B51\u6BA5\u6BA3\u6BA2\u6BA6\u6C01\u6C00\u6BFF\u6C02\u6F41\u6F26\u6F7E\u6F87\u6FC6\u6F92\u6F8D\u6F89\u6F8C\u6F62\u6F4F\u6F85\u6F5A\u6F96\u6F76\u6F6C\u6F82\u6F55\u6F72\u6F52\u6F50\u6F57\u6F94\u6F93\u6F5D\u6F00\u6F61\u6F6B\u6F7D\u6F67\u6F90\u6F53\u6F8B\u6F69\u6F7F\u6F95\u6F63\u6F77\u6F6A\u6F7B\u71B2\u71AF\u719B\u71B0\u71A0\u719A\u71A9\u71B5\u719D\u71A5\u719E\u71A4\u71A1\u71AA\u719C\u71A7\u71B3\u7298\u729A\u7358\u7352\u735E\u735F\u7360\u735D\u735B\u7361\u735A\u7359\u7362\u7487\u7489\u748A\u7486\u7481\u747D\u7485\u7488\u747C\u7479\u7508\u7507\u757E\u7625\u761E\u7619\u761D\u761C\u7623\u761A\u7628\u761B\u769C\u769D\u769E\u769B\u778D\u778F\u7789\u7788\u78CD\u78BB\u78CF\u78CC\u78D1\u78CE\u78D4\u78C8\u78C3\u78C4\u78C9\u799A\u79A1\u79A0\u799C\u79A2\u799B\u6B76\u7A39\u7AB2\u7AB4\u7AB3\u7BB7\u7BCB\u7BBE\u7BAC\u7BCE\u7BAF\u7BB9\u7BCA\u7BB5\u7CC5\u7CC8\u7CCC\u7CCB\u7DF7\u7DDB\u7DEA\u7DE7\u7DD7\u7DE1\u7E03\u7DFA\u7DE6\u7DF6\u7DF1\u7DF0\u7DEE\u7DDF\u7F76\u7FAC\u7FB0\u7FAD\u7FED\u7FEB\u7FEA\u7FEC\u7FE6\u7FE8\u8064\u8067\u81A3\u819F\u819E\u8195\u81A2\u8199\u8197\u8216\u824F\u8253\u8252\u8250\u824E\u8251\u8524\u853B\u850F\u8500\u8529\u850E\u8509\u850D\u851F\u850A\u8527\u851C\u84FB\u852B\u84FA\u8508\u850C\u84F4\u852A\u84F2\u8515\u84F7\u84EB\u84F3\u84FC\u8512\u84EA\u84E9\u8516\u84FE\u8528\u851D\u852E\u8502\u84FD\u851E\u84F6\u8531\u8526\u84E7\u84E8\u84F0\u84EF\u84F9\u8518\u8520\u8530\u850B\u8519\u852F\u8662\u8756\u8763\u8764\u8777\u87E1\u8773\u8758\u8754\u875B\u8752\u8761\u875A\u8751\u875E\u876D\u876A\u8750\u874E\u875F\u875D\u876F\u876C\u877A\u876E\u875C\u8765\u874F\u877B\u8775\u8762\u8767\u8769\u885A\u8905\u890C\u8914\u890B\u8917\u8918\u8919\u8906\u8916\u8911\u890E\u8909\u89A2\u89A4\u89A3\u89ED\u89F0\u89EC\u8ACF\u8AC6\u8AB8\u8AD3\u8AD1\u8AD4\u8AD5\u8ABB\u8AD7\u8ABE\u8AC0\u8AC5\u8AD8\u8AC3\u8ABA\u8ABD\u8AD9\u8C3E\u8C4D\u8C8F\u8CE5\u8CDF\u8CD9\u8CE8\u8CDA\u8CDD\u8CE7\u8DA0\u8D9C\u8DA1\u8D9B\u8E20\u8E23\u8E25\u8E24\u8E2E\u8E15\u8E1B\u8E16\u8E11\u8E19\u8E26\u8E27\u8E14\u8E12\u8E18\u8E13\u8E1C\u8E17\u8E1A\u8F2C\u8F24\u8F18\u8F1A\u8F20\u8F23\u8F16\u8F17\u9073\u9070\u906F\u9067\u906B\u912F\u912B\u9129\u912A\u9132\u9126\u912E\u9185\u9186\u918A\u9181\u9182\u9184\u9180\u92D0\u92C3\u92C4\u92C0\u92D9\u92B6\u92CF\u92F1\u92DF\u92D8\u92E9\u92D7\u92DD\u92CC\u92EF\u92C2\u92E8\u92CA\u92C8\u92CE\u92E6\u92CD\u92D5\u92C9\u92E0\u92DE\u92E7\u92D1\u92D3\u92B5\u92E1\u92C6\u92B4\u957C\u95AC\u95AB\u95AE\u95B0\u96A4\u96A2\u96D3\u9705\u9708\u9702\u975A\u978A\u978E\u9788\u97D0\u97CF\u981E\u981D\u9826\u9829\u9828\u9820\u981B\u9827\u98B2\u9908\u98FA\u9911\u9914\u9916\u9917\u9915\u99DC\u99CD\u99CF\u99D3\u99D4\u99CE\u99C9\u99D6\u99D8\u99CB\u99D7\u99CC\u9AB3\u9AEC\u9AEB\u9AF3\u9AF2\u9AF1\u9B46\u9B43\u9B67\u9B74\u9B71\u9B66\u9B76\u9B75\u9B70\u9B68\u9B64\u9B6C\u9CFC\u9CFA\u9CFD\u9CFF\u9CF7\u9D07\u9D00\u9CF9\u9CFB\u9D08\u9D05\u9D04\u9E83\u9ED3\u9F0F\u9F10\u511C\u5113\u5117\u511A\u5111\u51DE\u5334\u53E1\u5670\u5660\u566E\u5673\u5666\u5663\u566D\u5672\u565E\u5677\u571C\u571B\u58C8\u58BD\u58C9\u58BF\u58BA\u58C2\u58BC\u58C6\u5B17\u5B19\u5B1B\u5B21\u5B14\u5B13\u5B10\u5B16\u5B28\u5B1A\u5B20\u5B1E\u5BEF\u5DAC\u5DB1\u5DA9\u5DA7\u5DB5\u5DB0\u5DAE\u5DAA\u5DA8\u5DB2\u5DAD\u5DAF\u5DB4\u5E67\u5E68\u5E66\u5E6F\u5EE9\u5EE7\u5EE6\u5EE8\u5EE5\u5F4B\u5FBC\u619D\u61A8\u6196\u61C5\u61B4\u61C6\u61C1\u61CC\u61BA\u61BF\u61B8\u618C\u64D7\u64D6\u64D0\u64CF\u64C9\u64BD\u6489\u64C3\u64DB\u64F3\u64D9\u6533\u657F\u657C\u65A2\u66C8\u66BE\u66C0\u66CA\u66CB\u66CF\u66BD\u66BB\u66BA\u66CC\u6723\u6A34\u6A66\u6A49\u6A67\u6A32\u6A68\u6A3E\u6A5D\u6A6D\u6A76\u6A5B\u6A51\u6A28\u6A5A\u6A3B\u6A3F\u6A41\u6A6A\u6A64\u6A50\u6A4F\u6A54\u6A6F\u6A69\u6A60\u6A3C\u6A5E\u6A56\u6A55\u6A4D\u6A4E\u6A46\u6B55\u6B54\u6B56\u6BA7\u6BAA\u6BAB\u6BC8\u6BC7\u6C04\u6C03\u6C06\u6FAD\u6FCB\u6FA3\u6FC7\u6FBC\u6FCE\u6FC8\u6F5E\u6FC4\u6FBD\u6F9E\u6FCA\u6FA8\u7004\u6FA5\u6FAE\u6FBA\u6FAC\u6FAA\u6FCF\u6FBF\u6FB8\u6FA2\u6FC9\u6FAB\u6FCD\u6FAF\u6FB2\u6FB0\u71C5\u71C2\u71BF\u71B8\u71D6\u71C0\u71C1\u71CB\u71D4\u71CA\u71C7\u71CF\u71BD\u71D8\u71BC\u71C6\u71DA\u71DB\u729D\u729E\u7369\u7366\u7367\u736C\u7365\u736B\u736A\u747F\u749A\u74A0\u7494\u7492\u7495\u74A1\u750B\u7580\u762F\u762D\u7631\u763D\u7633\u763C\u7635\u7632\u7630\u76BB\u76E6\u779A\u779D\u77A1\u779C\u779B\u77A2\u77A3\u7795\u7799\u7797\u78DD\u78E9\u78E5\u78EA\u78DE\u78E3\u78DB\u78E1\u78E2\u78ED\u78DF\u78E0\u79A4\u7A44\u7A48\u7A47\u7AB6\u7AB8\u7AB5\u7AB1\u7AB7\u7BDE\u7BE3\u7BE7\u7BDD\u7BD5\u7BE5\u7BDA\u7BE8\u7BF9\u7BD4\u7BEA\u7BE2\u7BDC\u7BEB\u7BD8\u7BDF\u7CD2\u7CD4\u7CD7\u7CD0\u7CD1\u7E12\u7E21\u7E17\u7E0C\u7E1F\u7E20\u7E13\u7E0E\u7E1C\u7E15\u7E1A\u7E22\u7E0B\u7E0F\u7E16\u7E0D\u7E14\u7E25\u7E24\u7F43\u7F7B\u7F7C\u7F7A\u7FB1\u7FEF\u802A\u8029\u806C\u81B1\u81A6\u81AE\u81B9\u81B5\u81AB\u81B0\u81AC\u81B4\u81B2\u81B7\u81A7\u81F2\u8255\u8256\u8257\u8556\u8545\u856B\u854D\u8553\u8561\u8558\u8540\u8546\u8564\u8541\u8562\u8544\u8551\u8547\u8563\u853E\u855B\u8571\u854E\u856E\u8575\u8555\u8567\u8560\u858C\u8566\u855D\u8554\u8565\u856C\u8663\u8665\u8664\u879B\u878F\u8797\u8793\u8792\u8788\u8781\u8796\u8798\u8779\u8787\u87A3\u8785\u8790\u8791\u879D\u8784\u8794\u879C\u879A\u8789\u891E\u8926\u8930\u892D\u892E\u8927\u8931\u8922\u8929\u8923\u892F\u892C\u891F\u89F1\u8AE0\u8AE2\u8AF2\u8AF4\u8AF5\u8ADD\u8B14\u8AE4\u8ADF\u8AF0\u8AC8\u8ADE\u8AE1\u8AE8\u8AFF\u8AEF\u8AFB\u8C91\u8C92\u8C90\u8CF5\u8CEE\u8CF1\u8CF0\u8CF3\u8D6C\u8D6E\u8DA5\u8DA7\u8E33\u8E3E\u8E38\u8E40\u8E45\u8E36\u8E3C\u8E3D\u8E41\u8E30\u8E3F\u8EBD\u8F36\u8F2E\u8F35\u8F32\u8F39\u8F37\u8F34\u9076\u9079\u907B\u9086\u90FA\u9133\u9135\u9136\u9193\u9190\u9191\u918D\u918F\u9327\u931E\u9308\u931F\u9306\u930F\u937A\u9338\u933C\u931B\u9323\u9312\u9301\u9346\u932D\u930E\u930D\u92CB\u931D\u92FA\u9325\u9313\u92F9\u92F7\u9334\u9302\u9324\u92FF\u9329\u9339\u9335\u932A\u9314\u930C\u930B\u92FE\u9309\u9300\u92FB\u9316\u95BC\u95CD\u95BE\u95B9\u95BA\u95B6\u95BF\u95B5\u95BD\u96A9\u96D4\u970B\u9712\u9710\u9799\u9797\u9794\u97F0\u97F8\u9835\u982F\u9832\u9924\u991F\u9927\u9929\u999E\u99EE\u99EC\u99E5\u99E4\u99F0\u99E3\u99EA\u99E9\u99E7\u9AB9\u9ABF\u9AB4\u9ABB\u9AF6\u9AFA\u9AF9\u9AF7\u9B33\u9B80\u9B85\u9B87\u9B7C\u9B7E\u9B7B\u9B82\u9B93\u9B92\u9B90\u9B7A\u9B95\u9B7D\u9B88\u9D25\u9D17\u9D20\u9D1E\u9D14\u9D29\u9D1D\u9D18\u9D22\u9D10\u9D19\u9D1F\u9E88\u9E86\u9E87\u9EAE\u9EAD\u9ED5\u9ED6\u9EFA\u9F12\u9F3D\u5126\u5125\u5122\u5124\u5120\u5129\u52F4\u5693\u568C\u568D\u5686\u5684\u5683\u567E\u5682\u567F\u5681\u58D6\u58D4\u58CF\u58D2\u5B2D\u5B25\u5B32\u5B23\u5B2C\u5B27\u5B26\u5B2F\u5B2E\u5B7B\u5BF1\u5BF2\u5DB7\u5E6C\u5E6A\u5FBE\u5FBB\u61C3\u61B5\u61BC\u61E7\u61E0\u61E5\u61E4\u61E8\u61DE\u64EF\u64E9\u64E3\u64EB\u64E4\u64E8\u6581\u6580\u65B6\u65DA\u66D2\u6A8D\u6A96\u6A81\u6AA5\u6A89\u6A9F\u6A9B\u6AA1\u6A9E\u6A87\u6A93\u6A8E\u6A95\u6A83\u6AA8\u6AA4\u6A91\u6A7F\u6AA6\u6A9A\u6A85\u6A8C\u6A92\u6B5B\u6BAD\u6C09\u6FCC\u6FA9\u6FF4\u6FD4\u6FE3\u6FDC\u6FED\u6FE7\u6FE6\u6FDE\u6FF2\u6FDD\u6FE2\u6FE8\u71E1\u71F1\u71E8\u71F2\u71E4\u71F0\u71E2\u7373\u736E\u736F\u7497\u74B2\u74AB\u7490\u74AA\u74AD\u74B1\u74A5\u74AF\u7510\u7511\u7512\u750F\u7584\u7643\u7648\u7649\u7647\u76A4\u76E9\u77B5\u77AB\u77B2\u77B7\u77B6\u77B4\u77B1\u77A8\u77F0\u78F3\u78FD\u7902\u78FB\u78FC\u78F2\u7905\u78F9\u78FE\u7904\u79AB\u79A8\u7A5C\u7A5B\u7A56\u7A58\u7A54\u7A5A\u7ABE\u7AC0\u7AC1\u7C05\u7C0F\u7BF2\u7C00\u7BFF\u7BFB\u7C0E\u7BF4\u7C0B\u7BF3\u7C02\u7C09\u7C03\u7C01\u7BF8\u7BFD\u7C06\u7BF0\u7BF1\u7C10\u7C0A\u7CE8\u7E2D\u7E3C\u7E42\u7E33\u9848\u7E38\u7E2A\u7E49\u7E40\u7E47\u7E29\u7E4C\u7E30\u7E3B\u7E36\u7E44\u7E3A\u7F45\u7F7F\u7F7E\u7F7D\u7FF4\u7FF2\u802C\u81BB\u81C4\u81CC\u81CA\u81C5\u81C7\u81BC\u81E9\u825B\u825A\u825C\u8583\u8580\u858F\u85A7\u8595\u85A0\u858B\u85A3\u857B\u85A4\u859A\u859E\u8577\u857C\u8589\u85A1\u857A\u8578\u8557\u858E\u8596\u8586\u858D\u8599\u859D\u8581\u85A2\u8582\u8588\u8585\u8579\u8576\u8598\u8590\u859F\u8668\u87BE\u87AA\u87AD\u87C5\u87B0\u87AC\u87B9\u87B5\u87BC\u87AE\u87C9\u87C3\u87C2\u87CC\u87B7\u87AF\u87C4\u87CA\u87B4\u87B6\u87BF\u87B8\u87BD\u87DE\u87B2\u8935\u8933\u893C\u893E\u8941\u8952\u8937\u8942\u89AD\u89AF\u89AE\u89F2\u89F3\u8B1E\u8B18\u8B16\u8B11\u8B05\u8B0B\u8B22\u8B0F\u8B12\u8B15\u8B07\u8B0D\u8B08\u8B06\u8B1C\u8B13\u8B1A\u8C4F\u8C70\u8C72\u8C71\u8C6F\u8C95\u8C94\u8CF9\u8D6F\u8E4E\u8E4D\u8E53\u8E50\u8E4C\u8E47\u8F43\u8F40\u9085\u907E\u9138\u919A\u91A2\u919B\u9199\u919F\u91A1\u919D\u91A0\u93A1\u9383\u93AF\u9364\u9356\u9347\u937C\u9358\u935C\u9376\u9349\u9350\u9351\u9360\u936D\u938F\u934C\u936A\u9379\u9357\u9355\u9352\u934F\u9371\u9377\u937B\u9361\u935E\u9363\u9367\u9380\u934E\u9359\u95C7\u95C0\u95C9\u95C3\u95C5\u95B7\u96AE\u96B0\u96AC\u9720\u971F\u9718\u971D\u9719\u979A\u97A1\u979C\u979E\u979D\u97D5\u97D4\u97F1\u9841\u9844\u984A\u9849\u9845\u9843\u9925\u992B\u992C\u992A\u9933\u9932\u992F\u992D\u9931\u9930\u9998\u99A3\u99A1\u9A02\u99FA\u99F4\u99F7\u99F9\u99F8\u99F6\u99FB\u99FD\u99FE\u99FC\u9A03\u9ABE\u9AFE\u9AFD\u9B01\u9AFC\u9B48\u9B9A\u9BA8\u9B9E\u9B9B\u9BA6\u9BA1\u9BA5\u9BA4\u9B86\u9BA2\u9BA0\u9BAF\u9D33\u9D41\u9D67\u9D36\u9D2E\u9D2F\u9D31\u9D38\u9D30\u9D45\u9D42\u9D43\u9D3E\u9D37\u9D40\u9D3D\u7FF5\u9D2D\u9E8A\u9E89\u9E8D\u9EB0\u9EC8\u9EDA\u9EFB\u9EFF\u9F24\u9F23\u9F22\u9F54\u9FA0\u5131\u512D\u512E\u5698\u569C\u5697\u569A\u569D\u5699\u5970\u5B3C\u5C69\u5C6A\u5DC0\u5E6D\u5E6E\u61D8\u61DF\u61ED\u61EE\u61F1\u61EA\u61F0\u61EB\u61D6\u61E9\u64FF\u6504\u64FD\u64F8\u6501\u6503\u64FC\u6594\u65DB\u66DA\u66DB\u66D8\u6AC5\u6AB9\u6ABD\u6AE1\u6AC6\u6ABA\u6AB6\u6AB7\u6AC7\u6AB4\u6AAD\u6B5E\u6BC9\u6C0B\u7007\u700C\u700D\u7001\u7005\u7014\u700E\u6FFF\u7000\u6FFB\u7026\u6FFC\u6FF7\u700A\u7201\u71FF\u71F9\u7203\u71FD\u7376\u74B8\u74C0\u74B5\u74C1\u74BE\u74B6\u74BB\u74C2\u7514\u7513\u765C\u7664\u7659\u7650\u7653\u7657\u765A\u76A6\u76BD\u76EC\u77C2\u77BA\u78FF\u790C\u7913\u7914\u7909\u7910\u7912\u7911\u79AD\u79AC\u7A5F\u7C1C\u7C29\u7C19\u7C20\u7C1F\u7C2D\u7C1D\u7C26\u7C28\u7C22\u7C25\u7C30\u7E5C\u7E50\u7E56\u7E63\u7E58\u7E62\u7E5F\u7E51\u7E60\u7E57\u7E53\u7FB5\u7FB3\u7FF7\u7FF8\u8075\u81D1\u81D2\u81D0\u825F\u825E\u85B4\u85C6\u85C0\u85C3\u85C2\u85B3\u85B5\u85BD\u85C7\u85C4\u85BF\u85CB\u85CE\u85C8\u85C5\u85B1\u85B6\u85D2\u8624\u85B8\u85B7\u85BE\u8669\u87E7\u87E6\u87E2\u87DB\u87EB\u87EA\u87E5\u87DF\u87F3\u87E4\u87D4\u87DC\u87D3\u87ED\u87D8\u87E3\u87A4\u87D7\u87D9\u8801\u87F4\u87E8\u87DD\u8953\u894B\u894F\u894C\u8946\u8950\u8951\u8949\u8B2A\u8B27\u8B23\u8B33\u8B30\u8B35\u8B47\u8B2F\u8B3C\u8B3E\u8B31\u8B25\u8B37\u8B26\u8B36\u8B2E\u8B24\u8B3B\u8B3D\u8B3A\u8C42\u8C75\u8C99\u8C98\u8C97\u8CFE\u8D04\u8D02\u8D00\u8E5C\u8E62\u8E60\u8E57\u8E56\u8E5E\u8E65\u8E67\u8E5B\u8E5A\u8E61\u8E5D\u8E69\u8E54\u8F46\u8F47\u8F48\u8F4B\u9128\u913A\u913B\u913E\u91A8\u91A5\u91A7\u91AF\u91AA\u93B5\u938C\u9392\u93B7\u939B\u939D\u9389\u93A7\u938E\u93AA\u939E\u93A6\u9395\u9388\u9399\u939F\u938D\u93B1\u9391\u93B2\u93A4\u93A8\u93B4\u93A3\u93A5\u95D2\u95D3\u95D1\u96B3\u96D7\u96DA\u5DC2\u96DF\u96D8\u96DD\u9723\u9722\u9725\u97AC\u97AE\u97A8\u97AB\u97A4\u97AA\u97A2\u97A5\u97D7\u97D9\u97D6\u97D8\u97FA\u9850\u9851\u9852\u98B8\u9941\u993C\u993A\u9A0F\u9A0B\u9A09\u9A0D\u9A04\u9A11\u9A0A\u9A05\u9A07\u9A06\u9AC0\u9ADC\u9B08\u9B04\u9B05\u9B29\u9B35\u9B4A\u9B4C\u9B4B\u9BC7\u9BC6\u9BC3\u9BBF\u9BC1\u9BB5\u9BB8\u9BD3\u9BB6\u9BC4\u9BB9\u9BBD\u9D5C\u9D53\u9D4F\u9D4A\u9D5B\u9D4B\u9D59\u9D56\u9D4C\u9D57\u9D52\u9D54\u9D5F\u9D58\u9D5A\u9E8E\u9E8C\u9EDF\u9F01\u9F00\u9F16\u9F25\u9F2B\u9F2A\u9F29\u9F28\u9F4C\u9F55\u5134\u5135\u5296\u52F7\u53B4\u56AB\u56AD\u56A6\u56A7\u56AA\u56AC\u58DA\u58DD\u58DB\u5912\u5B3D\u5B3E\u5B3F\u5DC3\u5E70\u5FBF\u61FB\u6507\u6510\u650D\u6509\u650C\u650E\u6584\u65DE\u65DD\u66DE\u6AE7\u6AE0\u6ACC\u6AD1\u6AD9\u6ACB\u6ADF\u6ADC\u6AD0\u6AEB\u6ACF\u6ACD\u6ADE\u6B60\u6BB0\u6C0C\u7019\u7027\u7020\u7016\u702B\u7021\u7022\u7023\u7029\u7017\u7024\u701C\u702A\u720C\u720A\u7207\u7202\u7205\u72A5\u72A6\u72A4\u72A3\u72A1\u74CB\u74C5\u74B7\u74C3\u7516\u7660\u77C9\u77CA\u77C4\u77F1\u791D\u791B\u7921\u791C\u7917\u791E\u79B0\u7A67\u7A68\u7C33\u7C3C\u7C39\u7C2C\u7C3B\u7CEC\u7CEA\u7E76\u7E75\u7E78\u7E70\u7E77\u7E6F\u7E7A\u7E72\u7E74\u7E68\u7F4B\u7F4A\u7F83\u7F86\u7FB7\u7FFD\u7FFE\u8078\u81D7\u81D5\u8264\u8261\u8263\u85EB\u85F1\u85ED\u85D9\u85E1\u85E8\u85DA\u85D7\u85EC\u85F2\u85F8\u85D8\u85DF\u85E3\u85DC\u85D1\u85F0\u85E6\u85EF\u85DE\u85E2\u8800\u87FA\u8803\u87F6\u87F7\u8809\u880C\u880B\u8806\u87FC\u8808\u87FF\u880A\u8802\u8962\u895A\u895B\u8957\u8961\u895C\u8958\u895D\u8959\u8988\u89B7\u89B6\u89F6\u8B50\u8B48\u8B4A\u8B40\u8B53\u8B56\u8B54\u8B4B\u8B55\u8B51\u8B42\u8B52\u8B57\u8C43\u8C77\u8C76\u8C9A\u8D06\u8D07\u8D09\u8DAC\u8DAA\u8DAD\u8DAB\u8E6D\u8E78\u8E73\u8E6A\u8E6F\u8E7B\u8EC2\u8F52\u8F51\u8F4F\u8F50\u8F53\u8FB4\u9140\u913F\u91B0\u91AD\u93DE\u93C7\u93CF\u93C2\u93DA\u93D0\u93F9\u93EC\u93CC\u93D9\u93A9\u93E6\u93CA\u93D4\u93EE\u93E3\u93D5\u93C4\u93CE\u93C0\u93D2\u93E7\u957D\u95DA\u95DB\u96E1\u9729\u972B\u972C\u9728\u9726\u97B3\u97B7\u97B6\u97DD\u97DE\u97DF\u985C\u9859\u985D\u9857\u98BF\u98BD\u98BB\u98BE\u9948\u9947\u9943\u99A6\u99A7\u9A1A\u9A15\u9A25\u9A1D\u9A24\u9A1B\u9A22\u9A20\u9A27\u9A23\u9A1E\u9A1C\u9A14\u9AC2\u9B0B\u9B0A\u9B0E\u9B0C\u9B37\u9BEA\u9BEB\u9BE0\u9BDE\u9BE4\u9BE6\u9BE2\u9BF0\u9BD4\u9BD7\u9BEC\u9BDC\u9BD9\u9BE5\u9BD5\u9BE1\u9BDA\u9D77\u9D81\u9D8A\u9D84\u9D88\u9D71\u9D80\u9D78\u9D86\u9D8B\u9D8C\u9D7D\u9D6B\u9D74\u9D75\u9D70\u9D69\u9D85\u9D73\u9D7B\u9D82\u9D6F\u9D79\u9D7F\u9D87\u9D68\u9E94\u9E91\u9EC0\u9EFC\u9F2D\u9F40\u9F41\u9F4D\u9F56\u9F57\u9F58\u5337\u56B2\u56B5\u56B3\u58E3\u5B45\u5DC6\u5DC7\u5EEE\u5EEF\u5FC0\u5FC1\u61F9\u6517\u6516\u6515\u6513\u65DF\u66E8\u66E3\u66E4\u6AF3\u6AF0\u6AEA\u6AE8\u6AF9\u6AF1\u6AEE\u6AEF\u703C\u7035\u702F\u7037\u7034\u7031\u7042\u7038\u703F\u703A\u7039\u7040\u703B\u7033\u7041\u7213\u7214\u72A8\u737D\u737C\u74BA\u76AB\u76AA\u76BE\u76ED\u77CC\u77CE\u77CF\u77CD\u77F2\u7925\u7923\u7927\u7928\u7924\u7929\u79B2\u7A6E\u7A6C\u7A6D\u7AF7\u7C49\u7C48\u7C4A\u7C47\u7C45\u7CEE\u7E7B\u7E7E\u7E81\u7E80\u7FBA\u7FFF\u8079\u81DB\u81D9\u820B\u8268\u8269\u8622\u85FF\u8601\u85FE\u861B\u8600\u85F6\u8604\u8609\u8605\u860C\u85FD\u8819\u8810\u8811\u8817\u8813\u8816\u8963\u8966\u89B9\u89F7\u8B60\u8B6A\u8B5D\u8B68\u8B63\u8B65\u8B67\u8B6D\u8DAE\u8E86\u8E88\u8E84\u8F59\u8F56\u8F57\u8F55\u8F58\u8F5A\u908D\u9143\u9141\u91B7\u91B5\u91B2\u91B3\u940B\u9413\u93FB\u9420\u940F\u9414\u93FE\u9415\u9410\u9428\u9419\u940D\u93F5\u9400\u93F7\u9407\u940E\u9416\u9412\u93FA\u9409\u93F8\u940A\u93FF\u93FC\u940C\u93F6\u9411\u9406\u95DE\u95E0\u95DF\u972E\u972F\u97B9\u97BB\u97FD\u97FE\u9860\u9862\u9863\u985F\u98C1\u98C2\u9950\u994E\u9959\u994C\u994B\u9953\u9A32\u9A34\u9A31\u9A2C\u9A2A\u9A36\u9A29\u9A2E\u9A38\u9A2D\u9AC7\u9ACA\u9AC6\u9B10\u9B12\u9B11\u9C0B\u9C08\u9BF7\u9C05\u9C12\u9BF8\u9C40\u9C07\u9C0E\u9C06\u9C17\u9C14\u9C09\u9D9F\u9D99\u9DA4\u9D9D\u9D92\u9D98\u9D90\u9D9B\u9DA0\u9D94\u9D9C\u9DAA\u9D97\u9DA1\u9D9A\u9DA2\u9DA8\u9D9E\u9DA3\u9DBF\u9DA9\u9D96\u9DA6\u9DA7\u9E99\u9E9B\u9E9A\u9EE5\u9EE4\u9EE7\u9EE6\u9F30\u9F2E\u9F5B\u9F60\u9F5E\u9F5D\u9F59\u9F91\u513A\u5139\u5298\u5297\u56C3\u56BD\u56BE\u5B48\u5B47\u5DCB\u5DCF\u5EF1\u61FD\u651B\u6B02\u6AFC\u6B03\u6AF8\u6B00\u7043\u7044\u704A\u7048\u7049\u7045\u7046\u721D\u721A\u7219\u737E\u7517\u766A\u77D0\u792D\u7931\u792F\u7C54\u7C53\u7CF2\u7E8A\u7E87\u7E88\u7E8B\u7E86\u7E8D\u7F4D\u7FBB\u8030\u81DD\u8618\u862A\u8626\u861F\u8623\u861C\u8619\u8627\u862E\u8621\u8620\u8629\u861E\u8625\u8829\u881D\u881B\u8820\u8824\u881C\u882B\u884A\u896D\u8969\u896E\u896B\u89FA\u8B79\u8B78\u8B45\u8B7A\u8B7B\u8D10\u8D14\u8DAF\u8E8E\u8E8C\u8F5E\u8F5B\u8F5D\u9146\u9144\u9145\u91B9\u943F\u943B\u9436\u9429\u943D\u943C\u9430\u9439\u942A\u9437\u942C\u9440\u9431\u95E5\u95E4\u95E3\u9735\u973A\u97BF\u97E1\u9864\u98C9\u98C6\u98C0\u9958\u9956\u9A39\u9A3D\u9A46\u9A44\u9A42\u9A41\u9A3A\u9A3F\u9ACD\u9B15\u9B17\u9B18\u9B16\u9B3A\u9B52\u9C2B\u9C1D\u9C1C\u9C2C\u9C23\u9C28\u9C29\u9C24\u9C21\u9DB7\u9DB6\u9DBC\u9DC1\u9DC7\u9DCA\u9DCF\u9DBE\u9DC5\u9DC3\u9DBB\u9DB5\u9DCE\u9DB9\u9DBA\u9DAC\u9DC8\u9DB1\u9DAD\u9DCC\u9DB3\u9DCD\u9DB2\u9E7A\u9E9C\u9EEB\u9EEE\u9EED\u9F1B\u9F18\u9F1A\u9F31\u9F4E\u9F65\u9F64\u9F92\u4EB9\u56C6\u56C5\u56CB\u5971\u5B4B\u5B4C\u5DD5\u5DD1\u5EF2\u6521\u6520\u6526\u6522\u6B0B\u6B08\u6B09\u6C0D\u7055\u7056\u7057\u7052\u721E\u721F\u72A9\u737F\u74D8\u74D5\u74D9\u74D7\u766D\u76AD\u7935\u79B4\u7A70\u7A71\u7C57\u7C5C\u7C59\u7C5B\u7C5A\u7CF4\u7CF1\u7E91\u7F4F\u7F87\u81DE\u826B\u8634\u8635\u8633\u862C\u8632\u8636\u882C\u8828\u8826\u882A\u8825\u8971\u89BF\u89BE\u89FB\u8B7E\u8B84\u8B82\u8B86\u8B85\u8B7F\u8D15\u8E95\u8E94\u8E9A\u8E92\u8E90\u8E96\u8E97\u8F60\u8F62\u9147\u944C\u9450\u944A\u944B\u944F\u9447\u9445\u9448\u9449\u9446\u973F\u97E3\u986A\u9869\u98CB\u9954\u995B\u9A4E\u9A53\u9A54\u9A4C\u9A4F\u9A48\u9A4A\u9A49\u9A52\u9A50\u9AD0\u9B19\u9B2B\u9B3B\u9B56\u9B55\u9C46\u9C48\u9C3F\u9C44\u9C39\u9C33\u9C41\u9C3C\u9C37\u9C34\u9C32\u9C3D\u9C36\u9DDB\u9DD2\u9DDE\u9DDA\u9DCB\u9DD0\u9DDC\u9DD1\u9DDF\u9DE9\u9DD9\u9DD8\u9DD6\u9DF5\u9DD5\u9DDD\u9EB6\u9EF0\u9F35\u9F33\u9F32\u9F42\u9F6B\u9F95\u9FA2\u513D\u5299\u58E8\u58E7\u5972\u5B4D\u5DD8\u882F\u5F4F\u6201\u6203\u6204\u6529\u6525\u6596\u66EB\u6B11\u6B12\u6B0F\u6BCA\u705B\u705A\u7222\u7382\u7381\u7383\u7670\u77D4\u7C67\u7C66\u7E95\u826C\u863A\u8640\u8639\u863C\u8631\u863B\u863E\u8830\u8832\u882E\u8833\u8976\u8974\u8973\u89FE\u8B8C\u8B8E\u8B8B\u8B88\u8C45\u8D19\u8E98\u8F64\u8F63\u91BC\u9462\u9455\u945D\u9457\u945E\u97C4\u97C5\u9800\u9A56\u9A59\u9B1E\u9B1F\u9B20\u9C52\u9C58\u9C50\u9C4A\u9C4D\u9C4B\u9C55\u9C59\u9C4C\u9C4E\u9DFB\u9DF7\u9DEF\u9DE3\u9DEB\u9DF8\u9DE4\u9DF6\u9DE1\u9DEE\u9DE6\u9DF2\u9DF0\u9DE2\u9DEC\u9DF4\u9DF3\u9DE8\u9DED\u9EC2\u9ED0\u9EF2\u9EF3\u9F06\u9F1C\u9F38\u9F37\u9F36\u9F43\u9F4F\u9F71\u9F70\u9F6E\u9F6F\u56D3\u56CD\u5B4E\u5C6D\u652D\u66ED\u66EE\u6B13\u705F\u7061\u705D\u7060\u7223\u74DB\u74E5\u77D5\u7938\u79B7\u79B6\u7C6A\u7E97\u7F89\u826D\u8643\u8838\u8837\u8835\u884B\u8B94\u8B95\u8E9E\u8E9F\u8EA0\u8E9D\u91BE\u91BD\u91C2\u946B\u9468\u9469\u96E5\u9746\u9743\u9747\u97C7\u97E5\u9A5E\u9AD5\u9B59\u9C63\u9C67\u9C66\u9C62\u9C5E\u9C60\u9E02\u9DFE\u9E07\u9E03\u9E06\u9E05\u9E00\u9E01\u9E09\u9DFF\u9DFD\u9E04\u9EA0\u9F1E\u9F46\u9F74\u9F75\u9F76\u56D4\u652E\u65B8\u6B18\u6B19\u6B17\u6B1A\u7062\u7226\u72AA\u77D8\u77D9\u7939\u7C69\u7C6B\u7CF6\u7E9A\u7E98\u7E9B\u7E99\u81E0\u81E1\u8646\u8647\u8648\u8979\u897A\u897C\u897B\u89FF\u8B98\u8B99\u8EA5\u8EA4\u8EA3\u946E\u946D\u946F\u9471\u9473\u9749\u9872\u995F\u9C68\u9C6E\u9C6D\u9E0B\u9E0D\u9E10\u9E0F\u9E12\u9E11\u9EA1\u9EF5\u9F09\u9F47\u9F78\u9F7B\u9F7A\u9F79\u571E\u7066\u7C6F\u883C\u8DB2\u8EA6\u91C3\u9474\u9478\u9476\u9475\u9A60\u9C74\u9C73\u9C71\u9C75\u9E14\u9E13\u9EF6\u9F0A\u9FA4\u7068\u7065\u7CF7\u866A\u883E\u883D\u883F\u8B9E\u8C9C\u8EA9\u8EC9\u974B\u9873\u9874\u98CC\u9961\u99AB\u9A64\u9A66\u9A67\u9B24\u9E15\u9E17\u9F48\u6207\u6B1E\u7227\u864C\u8EA8\u9482\u9480\u9481\u9A69\u9A68\u9B2E\u9E19\u7229\u864B\u8B9F\u9483\u9C79\u9EB7\u7675\u9A6B\u9C7A\u9E1D\u7069\u706A\u9EA4\u9F7E\u9F49\u9F98\u7881\u92B9\u88CF\u58BB\u6052\u7CA7\u5AFA\u2554\u2566\u2557\u2560\u256C\u2563\u255A\u2569\u255D\u2552\u2564\u2555\u255E\u256A\u2561\u2558\u2567\u255B\u2553\u2565\u2556\u255F\u256B\u2562\u2559\u2568\u255C\u2551\u2550\u256D\u256E\u2570\u256F\uFFED\u0547\u92DB\u05DF\u3FC5\u854C\u42B5\u73EF\u51B5\u3649\u4942\u89E4\u9344\u19DB\u82EE\u3CC8\u783C\u6744\u62DF\u4933\u89AA\u02A0\u6BB3\u1305\u4FAB\u24ED\u5008\u6D29\u7A84\u3600\u4AB1\u2513\u5029\u037E\u5FA4\u0380\u0347\u6EDB\u041F\u507D\u5101\u347A\u510E\u986C\u3743\u8416\u49A4\u0487\u5160\u33B4\u516A\u0BFF\u20FC\u02E5\u2530\u058E\u3233\u1983\u5B82\u877D\u05B3\u3C99\u51B2\u51B8\u9D34\u51C9\u51CF\u51D1\u3CDC\u51D3\u4AA6\u51B3\u51E2\u5342\u51ED\u83CD\u693E\u372D\u5F7B\u520B\u5226\u523C\u52B5\u5257\u5294\u52B9\u52C5\u7C15\u8542\u52E0\u860D\u6B13\u5305\u8ADE\u5549\u6ED9\u3F80\u0954\u3FEC\u5333\u5344\u0BE2\u6CCB\u1726\u681B\u73D5\u604A\u3EAA\u38CC\u16E8\u71DD\u44A2\u536D\u5374\u86AB\u537E\u537F\u1596\u1613\u77E6\u5393\u8A9B\u53A0\u53AB\u53AE\u73A7\u5772\u3F59\u739C\u53C1\u53C5\u6C49\u4E49\u57FE\u53D9\u3AAB\u0B8F\u53E0\u3FEB\u2DA3\u53F6\u0C77\u5413\u7079\u552B\u6657\u6D5B\u546D\u6B53\u0D74\u555D\u548F\u54A4\u47A6\u170D\u0EDD\u3DB4\u0D4D\u89BC\u2698\u5547\u4CED\u542F\u7417\u5586\u55A9\u5605\u18D7\u403A\u4552\u4435\u66B3\u10B4\u5637\u66CD\u328A\u66A4\u66AD\u564D\u564F\u78F1\u56F1\u9787\u53FE\u5700\u56EF\u56ED\u8B66\u3623\u124F\u5746\u41A5\u6C6E\u708B\u5742\u36B1\u6C7E\u57E6\u1416\u5803\u1454\u4363\u5826\u4BF5\u585C\u58AA\u3561\u58E0\u58DC\u123C\u58FB\u5BFF\u5743\uA150\u4278\u93D3\u35A1\u591F\u68A6\u36C3\u6E59\u163E\u5A24\u5553\u1692\u8505\u59C9\u0D4E\u6C81\u6D2A\u17DC\u59D9\u17FB\u17B2\u6DA6\u6D71\u1828\u16D5\u59F9\u6E45\u5AAB\u5A63\u36E6\u49A9\u5A77\u3708\u5A96\u7465\u5AD3\u6FA1\u2554\u3D85\u1911\u3732\u16B8\u5E83\u52D0\u5B76\u6588\u5B7C\u7A0E\u4004\u485D\u0204\u5BD5\u6160\u1A34\u59CC\u05A5\u5BF3\u5B9D\u4D10\u5C05\u1B44\u5C13\u73CE\u5C14\u1CA5\u6B28\u5C49\u48DD\u5C85\u5CE9\u5CEF\u5D8B\u1DF9\u1E37\u5D10\u5D18\u5D46\u1EA4\u5CBA\u5DD7\u82FC\u382D\u4901\u2049\u2173\u8287\u3836\u3BC2\u5E2E\u6A8A\u5E75\u5E7A\u44BC\u0CD3\u53A6\u4EB7\u5ED0\u53A8\u1771\u5E09\u5EF4\u8482\u5EF9\u5EFB\u38A0\u5EFC\u683E\u941B\u5F0D\u01C1\uF894\u3ADE\u48AE\u133A\u5F3A\u6888\u23D0\u5F58\u2471\u5F63\u97BD\u6E6E\u5F72\u9340\u8A36\u5FA7\u5DB6\u3D5F\u5250\u1F6A\u70F8\u2668\u91D6\u029E\u8A29\u6031\u6685\u1877\u3963\u3DC7\u3639\u5790\u27B4\u7971\u3E40\u609E\u60A4\u60B3\u4982\u498F\u7A53\u74A4\u50E1\u5AA0\u6164\u8424\u6142\uF8A6\u6ED2\u6181\u51F4\u0656\u6187\u5BAA\u3FB7\u285F\u61D3\u8B9D\u995D\u61D0\u3932\u2980\u28C1\u6023\u615C\u651E\u638B\u0118\u62C5\u1770\u62D5\u2E0D\u636C\u49DF\u3A17\u6438\u63F8\u138E\u17FC\u6490\u6F8A\u2E36\u9814\u408C\u571D\u64E1\u64E5\u947B\u3A66\u643A\u3A57\u654D\u6F16\u4A28\u4A23\u6585\u656D\u655F\u307E\u65B5\u4940\u4B37\u65D1\u40D8\u1829\u65E0\u65E3\u5FDF\u3400\u6618\u31F7\u31F8\u6644\u31A4\u31A5\u664B\u0E75\u6667\u51E6\u6673\u6674\u1E3D\u3231\u85F4\u31C8\u5313\u77C5\u28F7\u99A4\u6702\u439C\u4A21\u3B2B\u69FA\u37C2\u675E\u6767\u6762\u41CD\u90ED\u67D7\u44E9\u6822\u6E50\u923C\u6801\u33E6\u6DA0\u685D\u346F\u69E1\u6A0B\u8ADF\u6973\u68C3\u35CD\u6901\u6900\u3D32\u3A01\u363C\u3B80\u67AC\u6961\u8A4A\u42FC\u6936\u6998\u3BA1\u03C9\u8363\u5090\u69F9\u3659\u212A\u6A45\u3703\u6A9D\u3BF3\u67B1\u6AC8\u919C\u3C0D\u6B1D\u0923\u60DE\u6B35\u6B74\u27CD\u6EB5\u3ADB\u03B5\u1958\u3740\u5421\u3B5A\u6BE1\u3EFC\u6BDC\u6C37\u248B\u48F1\u6B51\u6C5A\u8226\u6C79\u3DBC\u44C5\u3DBD\u41A4\u490C\u4900\u3CC9\u36E5\u3CEB\u0D32\u9B83\u31F9\u2491\u7F8F\u6837\u6D25\u6DA1\u6DEB\u6D96\u6D5C\u6E7C\u6F04\u497F\u4085\u6E72\u8533\u6F74\u51C7\u6C9C\u6E1D\u842E\u8B21\u6E2F\u3E2F\u7453\u3F82\u79CC\u6E4F\u5A91\u304B\u6FF8\u370D\u6F9D\u3E30\u6EFA\u1497\u403D\u4555\u93F0\u6F44\u6F5C\u3D4E\u6F74\u9170\u3D3B\u6F9F\u4144\u6FD3\u4091\u4155\u4039\u3FF0\u3FB4\u413F\u51DF\u4156\u4157\u4140\u61DD\u704B\u707E\u70A7\u7081\u70CC\u70D5\u70D6\u70DF\u4104\u3DE8\u71B4\u7196\u4277\u712B\u7145\u5A88\u714A\u716E\u5C9C\u4365\u714F\u9362\u42C1\u712C\u445A\u4A27\u4A22\u71BA\u8BE8\u70BD\u720E\u9442\u7215\u5911\u9443\u7224\u9341\u5605\u722E\u7240\u4974\u68BD\u7255\u7257\u3E55\u3044\u680D\u6F3D\u7282\u732A\u732B\u4823\u882B\u48ED\u8804\u7328\u732E\u73CF\u73AA\u0C3A\u6A2E\u73C9\u7449\u41E2\u16E7\u4A24\u6623\u36C5\u49B7\u498D\u49FB\u73F7\u7415\u6903\u4A26\u7439\u05C3\u3ED7\u745C\u28AD\u7460\u8EB2\u7447\u73E4\u7476\u83B9\u746C\u3730\u7474\u93F1\u6A2C\u7482\u4953\u4A8C\u415F\u4A79\u8B8F\u5B46\u8C03\u189E\u74C8\u1988\u750E\u74E9\u751E\u8ED9\u1A4B\u5BD7\u8EAC\u9385\u754D\u754A\u7567\u756E\u4F82\u3F04\u4D13\u758E\u745D\u759E\u75B4\u7602\u762C\u7651\u764F\u766F\u7676\u63F5\u7690\u81EF\u37F8\u6911\u690E\u76A1\u76A5\u76B7\u76CC\u6F9F\u8462\u509D\u517D\u1E1C\u771E\u7726\u7740\u64AF\u5220\u7758\u32AC\u77AF\u8964\u8968\u16C1\u77F4\u7809\u1376\u4A12\u68CA\u78AF\u78C7\u78D3\u96A5\u792E\u55E0\u78D7\u7934\u78B1\u760C\u8FB8\u8884\u8B2B\u6083\u261C\u7986\u8900\u6902\u7980\u5857\u799D\u7B39\u793C\u79A9\u6E2A\u7126\u3EA8\u79C6\u910D\u79D4";
+
+    private static boolean readBit(int i) {
+        return (ASTRALNESS.charAt(i >> 4) & (1 << (i & 0xF))) != 0;
+    }
+
+    static char lowBits(int pointer) {
+        if (pointer < 942) {
+            return '\u0000';
+        }
+        if (pointer < 1068) {
+            return TABLE0.charAt(pointer - 942);
+        }
+        if (pointer < 1099) {
+            return '\u0000';
+        }
+        if (pointer < 1172) {
+            return TABLE1.charAt(pointer - 1099);
+        }
+        if (pointer < 1256) {
+            return '\u0000';
+        }
+        if (pointer < 5466) {
+            return TABLE2.charAt(pointer - 1256);
+        }
+        if (pointer < 5495) {
+            return '\u0000';
+        }
+        if (pointer < 11214) {
+            return TABLE3.charAt(pointer - 5495);
+        }
+        if (pointer < 11254) {
+            return '\u0000';
+        }
+        if (pointer < 19782) {
+            return TABLE4.charAt(pointer - 11254);
+        }
+        return '\u0000';
+    }
+
+    static boolean isAstral(int pointer) {
+        if (pointer < 947) {
+            return false;
+        }
+        if (pointer < 1119) {
+            return readBit(0 + (pointer - 947));
+        }
+        if (pointer < 1256) {
+            return false;
+        }
+        if (pointer < 1269) {
+            return readBit(172 + (pointer - 1256));
+        }
+        if (pointer < 1336) {
+            return false;
+        }
+        if (pointer < 1364) {
+            return readBit(185 + (pointer - 1336));
+        }
+        if (pointer < 1413) {
+            return false;
+        }
+        if (pointer < 1912) {
+            return readBit(213 + (pointer - 1413));
+        }
+        if (pointer < 2012) {
+            return false;
+        }
+        if (pointer < 3800) {
+            return readBit(712 + (pointer - 2012));
+        }
+        if (pointer < 3883) {
+            return false;
+        }
+        if (pointer == 3883) {
+            return true;
+        }
+        if (pointer < 3985) {
+            return false;
+        }
+        if (pointer < 5024) {
+            return readBit(2501 + (pointer - 3985));
+        }
+        if (pointer < 11205) {
+            return false;
+        }
+        if (pointer < 11214) {
+            return readBit(3540 + (pointer - 11205));
+        }
+        if (pointer < 18997) {
+            return false;
+        }
+        if (pointer < 19782) {
+            return readBit(3549 + (pointer - 18997));
+        }
+        return false;
+    }
+
+    public static int findPointer(char lowBits, boolean isAstral) {
+        if (!isAstral) {
+            switch (lowBits) {
+                case 0x2550:
+                    return 18991;
+                case 0x255E:
+                    return 18975;
+                case 0x2561:
+                    return 18977;
+                case 0x256A:
+                    return 18976;
+                case 0x5341:
+                    return 5512;
+                case 0x5345:
+                    return 5599;
+                default:
+                    break;
+            }
+        }
+        for (int i = 3768; i < TABLE2.length(); i++) {
+            if (TABLE2.charAt(i) == lowBits) {
+                int pointer = i + 1256;
+                if (isAstral == isAstral(pointer)) {
+                    return pointer;
+                }
+            }
+        }
+        for (int i = 0; i < TABLE3.length(); i++) {
+            if (TABLE3.charAt(i) == lowBits) {
+                int pointer = i + 5495;
+                if (isAstral == isAstral(pointer)) {
+                    return pointer;
+                }
+            }
+        }
+        for (int i = 0; i < TABLE4.length(); i++) {
+            if (TABLE4.charAt(i) == lowBits) {
+                int pointer = i + 11254;
+                if (isAstral == isAstral(pointer)) {
+                    return pointer;
+                }
+            }
+        }
+        return 0;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Decoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Decoder.java
new file mode 100644
index 000000000..cc56b892f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Decoder.java
@@ -0,0 +1,184 @@
+/*
+ * Copyright (c) 2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.Charset;
+import java.nio.charset.CoderResult;
+
+public class Big5Decoder extends Decoder {
+   
+    private int big5Lead = 0;
+    
+    private char pendingTrail = '\u0000';
+    
+    protected Big5Decoder(Charset cs) {
+        super(cs, 0.5f, 1.0f);
+    }
+
+    @Override protected CoderResult decodeLoop(ByteBuffer in, CharBuffer out) {
+        assert !(this.report && (big5Lead != 0)):
+            "When reporting, this method should never return with big5Lead set.";
+        if (pendingTrail != '\u0000') {
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            out.put(pendingTrail);
+            pendingTrail = '\u0000';
+        }
+        for (;;) {
+            if (!in.hasRemaining()) {
+                return CoderResult.UNDERFLOW;
+            }
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            int b = ((int) in.get() & 0xFF);
+            if (big5Lead == 0) {
+                if (b <= 0x7F) {
+                    out.put((char) b);
+                    continue;
+                }
+                if (b >= 0x81 && b <= 0xFE) {
+                    if (this.report && !in.hasRemaining()) {
+                        // The Java API is badly documented. Need to do this
+                        // crazy thing and hope the caller knows about the
+                        // undocumented aspects of the API!
+                        in.position(in.position() - 1);
+                        return CoderResult.UNDERFLOW;
+                    }
+                    big5Lead = b;
+                    continue;
+                }
+                if (this.report) {
+                    in.position(in.position() - 1);
+                    return CoderResult.malformedForLength(1);
+                }
+                out.put('\uFFFD');
+                continue;
+            }
+            int lead = big5Lead;
+            big5Lead = 0;
+            int offset = (b < 0x7F) ? 0x40 : 0x62;
+            if ((b >= 0x40 && b <= 0x7E) || (b >= 0xA1 && b <= 0xFE)) {
+                int pointer = (lead - 0x81) * 157 + (b - offset);
+                char outTrail;
+                switch (pointer) {
+                    case 1133:
+                        out.put('\u00CA');
+                        outTrail = '\u0304';
+                        break;
+                    case 1135:
+                        out.put('\u00CA');
+                        outTrail = '\u030C';
+                        break;
+                    case 1164:
+                        out.put('\u00EA');
+                        outTrail = '\u0304';
+                        break;
+                    case 1166:
+                        out.put('\u00EA');
+                        outTrail = '\u030C';
+                        break;
+                    default:
+                        char lowBits = Big5Data.lowBits(pointer);
+                        if (lowBits == '\u0000') {
+                            // The following |if| block fixes
+                            // https://github.com/whatwg/encoding/issues/5
+                            if (b <= 0x7F) {
+                                // prepend byte to stream
+                                // Always legal, since we've always just read a byte
+                                // if we come here.
+                                in.position(in.position() - 1);
+                            }
+                            if (this.report) {
+                                // This can go past the start of the buffer
+                                // if the caller does not conform to the
+                                // undocumented aspects of the API.
+                                in.position(in.position() - 1);
+                                return CoderResult.malformedForLength(b <= 0x7F ? 1 : 2);
+                            }
+                            out.put('\uFFFD');
+                            continue;
+                        }
+                        if (Big5Data.isAstral(pointer)) {
+                            int codePoint = lowBits | 0x20000;
+                            out.put((char) (0xD7C0 + (codePoint >> 10)));
+                            outTrail = (char) (0xDC00 + (codePoint & 0x3FF));
+                            break;
+                        }
+                        out.put(lowBits);
+                        continue;
+                }
+                if (!out.hasRemaining()) {
+                    pendingTrail = outTrail;
+                    return CoderResult.OVERFLOW;
+                }
+                out.put(outTrail);
+                continue;
+            }
+            // pointer is null
+            if (b <= 0x7F) {
+                // prepend byte to stream
+                // Always legal, since we've always just read a byte
+                // if we come here.
+                in.position(in.position() - 1);
+            }
+            if (this.report) {
+                // if position() == 0, the caller is not using the
+                // undocumented part of the API right and the line
+                // below will throw!
+                in.position(in.position() - 1);
+                return CoderResult.malformedForLength(b <= 0x7F ? 1 : 2);
+            }
+            out.put('\uFFFD');
+            continue;
+        }
+    }
+
+    @Override protected CoderResult implFlush(CharBuffer out) {
+        if (pendingTrail != '\u0000') {
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            out.put(pendingTrail);
+            pendingTrail = '\u0000';
+        }
+        if (big5Lead != 0) {
+            assert !this.report: "How come big5Lead got to be non-zero when decodeLoop() returned in the reporting mode?";
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            out.put('\uFFFD');
+            big5Lead = 0;            
+        }
+        return CoderResult.UNDERFLOW;
+    }
+
+    @Override protected void implReset() {
+        big5Lead = 0;
+        pendingTrail = '\u0000';
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Encoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Encoder.java
new file mode 100644
index 000000000..de5132151
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Big5Encoder.java
@@ -0,0 +1,185 @@
+/*
+ * Copyright (c) 2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.Charset;
+import java.nio.charset.CoderResult;
+
+public class Big5Encoder extends Encoder {
+
+    private char utf16Lead = '\u0000';
+
+    private byte pendingTrail = 0;
+
+    protected Big5Encoder(Charset cs) {
+        super(cs, 1.5f, 2.0f);
+    }
+
+    @Override protected CoderResult encodeLoop(CharBuffer in, ByteBuffer out) {
+        assert !((this.reportMalformed || this.reportUnmappable) && (utf16Lead != '\u0000')):
+            "When reporting, this method should never return with utf16Lead set.";
+        if (pendingTrail != 0) {
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            out.put(pendingTrail);
+            pendingTrail = 0;
+        }
+        for (;;) {
+            if (!in.hasRemaining()) {
+                return CoderResult.UNDERFLOW;
+            }
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            boolean isAstral; // true means Plane 2, false means BMP
+            char lowBits; // The low 16 bits of the code point
+            char codeUnit = in.get();
+            int highBits = (codeUnit & 0xFC00);
+            if (highBits == 0xD800) {
+                // high surrogate
+                if (utf16Lead != '\u0000') {
+                    // High surrogate follows another high surrogate. The
+                    // *previous* code unit is in error.
+                    if (this.reportMalformed) {
+                        // The caller had better adhere to the API contract.
+                        // Otherwise, this may throw.
+                        in.position(in.position() - 2);
+                        utf16Lead = '\u0000';
+                        return CoderResult.malformedForLength(1);
+                    }
+                    out.put((byte) '?');
+                }
+                utf16Lead = codeUnit;
+                continue;
+            }
+            if (highBits == 0xDC00) {
+                // low surrogate
+                if (utf16Lead == '\u0000') {
+                    // Got low surrogate without a previous high surrogate
+                    if (this.reportMalformed) {
+                        in.position(in.position() - 1);
+                        return CoderResult.malformedForLength(1);
+                    }
+                    out.put((byte) '?');
+                    continue;
+                }
+                int codePoint = (utf16Lead << 10) + codeUnit - 56613888;
+                utf16Lead = '\u0000';
+                // Plane 2 is the only astral plane that has potentially
+                // Big5-encodable characters.
+                if ((0xFF0000 & codePoint) != 0x20000) {
+                    if (this.reportUnmappable) {
+                        in.position(in.position() - 2);
+                        return CoderResult.unmappableForLength(2);
+                    }
+                    out.put((byte) '?');
+                    continue;
+                }
+                isAstral = true;
+                lowBits = (char)(codePoint & 0xFFFF);
+            } else {
+                // not a surrogate
+                if (utf16Lead != '\u0000') {
+                    // Non-surrogate follows a high surrogate. The *previous*
+                    // code unit is in error.
+                    utf16Lead = '\u0000';
+                    if (this.reportMalformed) {
+                        // The caller had better adhere to the API contract.
+                        // Otherwise, this may throw.
+                        in.position(in.position() - 2);
+                        return CoderResult.malformedForLength(1);
+                    }
+                    out.put((byte) '?');
+                    // Let's unconsume this code unit and reloop in order to
+                    // re-check if the output buffer still has space.
+                    in.position(in.position() - 1);
+                    continue;
+                }
+                isAstral = false;
+                lowBits = codeUnit;
+            }
+            // isAstral now tells us if we have a Plane 2 or a BMP character.
+            // lowBits tells us the low 16 bits.
+            // After all the above setup to deal with UTF-16, we are now
+            // finally ready to follow the spec.
+            if (!isAstral && lowBits <= 0x7F) {
+                out.put((byte)lowBits);
+                continue;
+            }
+            int pointer = Big5Data.findPointer(lowBits, isAstral);
+            if (pointer == 0) {
+                if (this.reportUnmappable) {
+                    if (isAstral) {
+                        in.position(in.position() - 2);
+                        return CoderResult.unmappableForLength(2);
+                    }
+                    in.position(in.position() - 1);
+                    return CoderResult.unmappableForLength(1);
+                }
+                out.put((byte)'?');
+                continue;
+            }
+            int lead = pointer / 157 + 0x81;
+            int trail = pointer % 157;
+            if (trail < 0x3F) {
+                trail += 0x40;
+            } else {
+                trail += 0x62;
+            }
+            out.put((byte)lead);
+            if (!out.hasRemaining()) {
+                pendingTrail = (byte)trail;
+                return CoderResult.OVERFLOW;
+            }
+            out.put((byte)trail);
+            continue;
+        }
+    }
+
+    @Override protected CoderResult implFlush(ByteBuffer out) {
+        if (pendingTrail != 0) {
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            out.put(pendingTrail);
+            pendingTrail = 0;
+        }
+        if (utf16Lead != '\u0000') {
+            assert !this.reportMalformed: "How come utf16Lead got to be non-zero when decodeLoop() returned in the reporting mode?";
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            out.put((byte)'?');
+            utf16Lead = '\u0000';
+        }
+        return CoderResult.UNDERFLOW;
+    }
+
+    @Override protected void implReset() {
+        utf16Lead = '\u0000';
+        pendingTrail = 0;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Decoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Decoder.java
new file mode 100644
index 000000000..41e06c63a
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Decoder.java
@@ -0,0 +1,80 @@
+/*
+ * Copyright (c) 2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CodingErrorAction;
+
+public abstract class Decoder extends CharsetDecoder {
+
+    protected boolean report = true;
+    
+    protected Decoder(Charset cs, float averageCharsPerByte, float maxCharsPerByte) {
+        super(cs, averageCharsPerByte, maxCharsPerByte);
+    }
+
+    @Override protected final void implOnMalformedInput(CodingErrorAction newAction) {
+        if (newAction == null) {
+            throw new IllegalArgumentException("The argument must not be null.");
+        }
+        if (newAction == CodingErrorAction.IGNORE) {
+            throw new IllegalArgumentException("The Encoding Standard does not allow errors to be ignored.");
+        }
+        if (newAction == CodingErrorAction.REPLACE) {
+            this.report = false;
+            return;
+        }
+        if (newAction == CodingErrorAction.REPORT) {
+            this.report = true;
+            return;
+        }
+        assert false: "Unreachable.";
+        throw new IllegalArgumentException("Unknown CodingErrorAction.");
+    }
+
+    @Override protected final void implOnUnmappableCharacter(
+            CodingErrorAction newAction) {
+        if (newAction == null) {
+            throw new IllegalArgumentException("The argument must not be null.");
+        }
+        if (newAction == CodingErrorAction.IGNORE) {
+            throw new IllegalArgumentException("The Encoding Standard does not allow errors to be ignored.");
+        }
+        if (newAction == CodingErrorAction.REPLACE) {
+            return; // We don't actually care, since there are no unmappables.
+        }
+        if (newAction == CodingErrorAction.REPORT) {
+            return; // We don't actually care, since there are no unmappables.
+        }
+        assert false: "Unreachable.";
+        throw new IllegalArgumentException("Unknown CodingErrorAction.");
+    }
+
+    @Override protected final void implReplaceWith(String newReplacement) {
+        if (!"\uFFFD".equals(newReplacement)) {
+            throw new IllegalArgumentException("Only U+FFFD is allowed as the replacement.");
+        }
+    }
+    
+    // TODO: Check if the JDK decoders reset the reporting state on reset()
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Encoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Encoder.java
new file mode 100644
index 000000000..6fc011ed2
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Encoder.java
@@ -0,0 +1,95 @@
+/*
+ * Copyright (c) 2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetEncoder;
+import java.nio.charset.CodingErrorAction;
+
+public abstract class Encoder extends CharsetEncoder {
+
+    boolean reportMalformed = true;
+
+    boolean reportUnmappable = true;
+
+    protected Encoder(Charset cs, float averageBytesPerChar,
+            float maxBytesPerChar) {
+        super(cs, averageBytesPerChar, maxBytesPerChar);
+    }
+
+    @Override protected final void implOnMalformedInput(CodingErrorAction newAction) {
+        if (newAction == null) {
+            throw new IllegalArgumentException("The argument must not be null.");
+        }
+        if (newAction == CodingErrorAction.IGNORE) {
+            throw new IllegalArgumentException("The Encoding Standard does not allow errors to be ignored.");
+        }
+        if (newAction == CodingErrorAction.REPLACE) {
+            this.reportMalformed = false;
+            return;
+        }
+        if (newAction == CodingErrorAction.REPORT) {
+            this.reportUnmappable = true;
+            return;
+        }
+        assert false: "Unreachable.";
+        throw new IllegalArgumentException("Unknown CodingErrorAction.");
+    }
+
+    @Override protected final void implOnUnmappableCharacter(
+            CodingErrorAction newAction) {
+        if (newAction == null) {
+            throw new IllegalArgumentException("The argument must not be null.");
+        }
+        if (newAction == CodingErrorAction.IGNORE) {
+            throw new IllegalArgumentException("The Encoding Standard does not allow errors to be ignored.");
+        }
+        if (newAction == CodingErrorAction.REPLACE) {
+            this.reportUnmappable = false;
+            return;
+        }
+        if (newAction == CodingErrorAction.REPORT) {
+            this.reportMalformed = true;
+            return;
+        }
+        assert false: "Unreachable.";
+        throw new IllegalArgumentException("Unknown CodingErrorAction.");
+    }
+
+    @Override public boolean isLegalReplacement(byte[] repl) {
+        if (repl == null) {
+            return false;
+        }
+        if (repl.length != 1) {
+            return false;
+        }
+        if (repl[0] != '?') {
+            return false;
+        }
+        return true;
+    }
+
+    @Override protected final void implReplaceWith(byte[] newReplacement) {
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Encoding.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Encoding.java
new file mode 100644
index 000000000..6e59ef7c7
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Encoding.java
@@ -0,0 +1,886 @@
+/*
+ * Copyright (c) 2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetEncoder;
+import java.nio.charset.IllegalCharsetNameException;
+import java.nio.charset.UnsupportedCharsetException;
+import java.nio.charset.spi.CharsetProvider;
+import java.util.Arrays;
+import java.util.Collections;
+import java.util.SortedMap;
+import java.util.TreeMap;
+
+/**
+ * Represents an <a href="https://encoding.spec.whatwg.org/#encoding">encoding</a>
+ * as defined in the <a href="https://encoding.spec.whatwg.org/">Encoding
+ * Standard</a>, provides access to each encoding defined in the Encoding
+ * Standard via a static constant and provides the 
+ * "<a href="https://encoding.spec.whatwg.org/#concept-encoding-get">get an 
+ * encoding</a>" algorithm defined in the Encoding Standard.
+ * 
+ * <p>This class inherits from {@link Charset} to allow the Encoding 
+ * Standard-compliant encodings to be used in contexts that support
+ * <code>Charset</code> instances. However, by design, the Encoding 
+ * Standard-compliant encodings are not supplied via a {@link CharsetProvider}
+ * and, therefore, are not available via and do not interfere with the static
+ * methods provided by <code>Charset</code>. (This class provides methods of
+ * the same name to hide each static method of <code>Charset</code> to help
+ * avoid accidental calls to the static methods of the superclass when working
+ * with Encoding Standard-compliant encodings.)
+ * 
+ * <p>When an application needs to use a particular encoding, such as utf-8
+ * or windows-1252, the corresponding constant, i.e.
+ * {@link #UTF_8 Encoding.UTF_8} and {@link #WINDOWS_1252 Encoding.WINDOWS_1252}
+ * respectively, should be used. However, when the application receives an
+ * encoding label from external input, the method {@link #forName(String) 
+ * forName()} should be used to obtain the object representing the encoding 
+ * identified by the label. In contexts where labels that map to the 
+ * <a href="https://encoding.spec.whatwg.org/#replacement">replacement
+ * encoding</a> should be treated as unknown, the method {@link
+ * #forNameNoReplacement(String) forNameNoReplacement()} should be used instead.
+ * 
+ * 
+ * @author hsivonen
+ */
+public abstract class Encoding extends Charset {
+
+    private static final String[] LABELS = {
+        "866",
+        "ansi_x3.4-1968",
+        "arabic",
+        "ascii",
+        "asmo-708",
+        "big5",
+        "big5-hkscs",
+        "chinese",
+        "cn-big5",
+        "cp1250",
+        "cp1251",
+        "cp1252",
+        "cp1253",
+        "cp1254",
+        "cp1255",
+        "cp1256",
+        "cp1257",
+        "cp1258",
+        "cp819",
+        "cp866",
+        "csbig5",
+        "cseuckr",
+        "cseucpkdfmtjapanese",
+        "csgb2312",
+        "csibm866",
+        "csiso2022jp",
+        "csiso2022kr",
+        "csiso58gb231280",
+        "csiso88596e",
+        "csiso88596i",
+        "csiso88598e",
+        "csiso88598i",
+        "csisolatin1",
+        "csisolatin2",
+        "csisolatin3",
+        "csisolatin4",
+        "csisolatin5",
+        "csisolatin6",
+        "csisolatin9",
+        "csisolatinarabic",
+        "csisolatincyrillic",
+        "csisolatingreek",
+        "csisolatinhebrew",
+        "cskoi8r",
+        "csksc56011987",
+        "csmacintosh",
+        "csshiftjis",
+        "cyrillic",
+        "dos-874",
+        "ecma-114",
+        "ecma-118",
+        "elot_928",
+        "euc-jp",
+        "euc-kr",
+        "gb18030",
+        "gb2312",
+        "gb_2312",
+        "gb_2312-80",
+        "gbk",
+        "greek",
+        "greek8",
+        "hebrew",
+        "hz-gb-2312",
+        "ibm819",
+        "ibm866",
+        "iso-2022-cn",
+        "iso-2022-cn-ext",
+        "iso-2022-jp",
+        "iso-2022-kr",
+        "iso-8859-1",
+        "iso-8859-10",
+        "iso-8859-11",
+        "iso-8859-13",
+        "iso-8859-14",
+        "iso-8859-15",
+        "iso-8859-16",
+        "iso-8859-2",
+        "iso-8859-3",
+        "iso-8859-4",
+        "iso-8859-5",
+        "iso-8859-6",
+        "iso-8859-6-e",
+        "iso-8859-6-i",
+        "iso-8859-7",
+        "iso-8859-8",
+        "iso-8859-8-e",
+        "iso-8859-8-i",
+        "iso-8859-9",
+        "iso-ir-100",
+        "iso-ir-101",
+        "iso-ir-109",
+        "iso-ir-110",
+        "iso-ir-126",
+        "iso-ir-127",
+        "iso-ir-138",
+        "iso-ir-144",
+        "iso-ir-148",
+        "iso-ir-149",
+        "iso-ir-157",
+        "iso-ir-58",
+        "iso8859-1",
+        "iso8859-10",
+        "iso8859-11",
+        "iso8859-13",
+        "iso8859-14",
+        "iso8859-15",
+        "iso8859-2",
+        "iso8859-3",
+        "iso8859-4",
+        "iso8859-5",
+        "iso8859-6",
+        "iso8859-7",
+        "iso8859-8",
+        "iso8859-9",
+        "iso88591",
+        "iso885910",
+        "iso885911",
+        "iso885913",
+        "iso885914",
+        "iso885915",
+        "iso88592",
+        "iso88593",
+        "iso88594",
+        "iso88595",
+        "iso88596",
+        "iso88597",
+        "iso88598",
+        "iso88599",
+        "iso_8859-1",
+        "iso_8859-15",
+        "iso_8859-1:1987",
+        "iso_8859-2",
+        "iso_8859-2:1987",
+        "iso_8859-3",
+        "iso_8859-3:1988",
+        "iso_8859-4",
+        "iso_8859-4:1988",
+        "iso_8859-5",
+        "iso_8859-5:1988",
+        "iso_8859-6",
+        "iso_8859-6:1987",
+        "iso_8859-7",
+        "iso_8859-7:1987",
+        "iso_8859-8",
+        "iso_8859-8:1988",
+        "iso_8859-9",
+        "iso_8859-9:1989",
+        "koi",
+        "koi8",
+        "koi8-r",
+        "koi8-ru",
+        "koi8-u",
+        "koi8_r",
+        "korean",
+        "ks_c_5601-1987",
+        "ks_c_5601-1989",
+        "ksc5601",
+        "ksc_5601",
+        "l1",
+        "l2",
+        "l3",
+        "l4",
+        "l5",
+        "l6",
+        "l9",
+        "latin1",
+        "latin2",
+        "latin3",
+        "latin4",
+        "latin5",
+        "latin6",
+        "logical",
+        "mac",
+        "macintosh",
+        "ms932",
+        "ms_kanji",
+        "shift-jis",
+        "shift_jis",
+        "sjis",
+        "sun_eu_greek",
+        "tis-620",
+        "unicode-1-1-utf-8",
+        "us-ascii",
+        "utf-16",
+        "utf-16be",
+        "utf-16le",
+        "utf-8",
+        "utf8",
+        "visual",
+        "windows-1250",
+        "windows-1251",
+        "windows-1252",
+        "windows-1253",
+        "windows-1254",
+        "windows-1255",
+        "windows-1256",
+        "windows-1257",
+        "windows-1258",
+        "windows-31j",
+        "windows-874",
+        "windows-949",
+        "x-cp1250",
+        "x-cp1251",
+        "x-cp1252",
+        "x-cp1253",
+        "x-cp1254",
+        "x-cp1255",
+        "x-cp1256",
+        "x-cp1257",
+        "x-cp1258",
+        "x-euc-jp",
+        "x-gbk",
+        "x-mac-cyrillic",
+        "x-mac-roman",
+        "x-mac-ukrainian",
+        "x-sjis",
+        "x-user-defined",
+        "x-x-big5",
+    };
+    
+    private static final Encoding[] ENCODINGS_FOR_LABELS = {
+        Ibm866.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso6.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso6.INSTANCE,
+        Big5.INSTANCE,
+        Big5.INSTANCE,
+        Gbk.INSTANCE,
+        Big5.INSTANCE,
+        Windows1250.INSTANCE,
+        Windows1251.INSTANCE,
+        Windows1252.INSTANCE,
+        Windows1253.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1255.INSTANCE,
+        Windows1256.INSTANCE,
+        Windows1257.INSTANCE,
+        Windows1258.INSTANCE,
+        Windows1252.INSTANCE,
+        Ibm866.INSTANCE,
+        Big5.INSTANCE,
+        EucKr.INSTANCE,
+        EucJp.INSTANCE,
+        Gbk.INSTANCE,
+        Ibm866.INSTANCE,
+        Iso2022Jp.INSTANCE,
+        Replacement.INSTANCE,
+        Gbk.INSTANCE,
+        Iso6.INSTANCE,
+        Iso6.INSTANCE,
+        Iso8.INSTANCE,
+        Iso8I.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Windows1254.INSTANCE,
+        Iso10.INSTANCE,
+        Iso15.INSTANCE,
+        Iso6.INSTANCE,
+        Iso5.INSTANCE,
+        Iso7.INSTANCE,
+        Iso8.INSTANCE,
+        Koi8R.INSTANCE,
+        EucKr.INSTANCE,
+        Macintosh.INSTANCE,
+        ShiftJis.INSTANCE,
+        Iso5.INSTANCE,
+        Windows874.INSTANCE,
+        Iso6.INSTANCE,
+        Iso7.INSTANCE,
+        Iso7.INSTANCE,
+        EucJp.INSTANCE,
+        EucKr.INSTANCE,
+        Gb18030.INSTANCE,
+        Gbk.INSTANCE,
+        Gbk.INSTANCE,
+        Gbk.INSTANCE,
+        Gbk.INSTANCE,
+        Iso7.INSTANCE,
+        Iso7.INSTANCE,
+        Iso8.INSTANCE,
+        Replacement.INSTANCE,
+        Windows1252.INSTANCE,
+        Ibm866.INSTANCE,
+        Replacement.INSTANCE,
+        Replacement.INSTANCE,
+        Iso2022Jp.INSTANCE,
+        Replacement.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso10.INSTANCE,
+        Windows874.INSTANCE,
+        Iso13.INSTANCE,
+        Iso14.INSTANCE,
+        Iso15.INSTANCE,
+        Iso16.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Iso5.INSTANCE,
+        Iso6.INSTANCE,
+        Iso6.INSTANCE,
+        Iso6.INSTANCE,
+        Iso7.INSTANCE,
+        Iso8.INSTANCE,
+        Iso8.INSTANCE,
+        Iso8I.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Iso7.INSTANCE,
+        Iso6.INSTANCE,
+        Iso8.INSTANCE,
+        Iso5.INSTANCE,
+        Windows1254.INSTANCE,
+        EucKr.INSTANCE,
+        Iso10.INSTANCE,
+        Gbk.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso10.INSTANCE,
+        Windows874.INSTANCE,
+        Iso13.INSTANCE,
+        Iso14.INSTANCE,
+        Iso15.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Iso5.INSTANCE,
+        Iso6.INSTANCE,
+        Iso7.INSTANCE,
+        Iso8.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso10.INSTANCE,
+        Windows874.INSTANCE,
+        Iso13.INSTANCE,
+        Iso14.INSTANCE,
+        Iso15.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Iso5.INSTANCE,
+        Iso6.INSTANCE,
+        Iso7.INSTANCE,
+        Iso8.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso15.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso2.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Iso4.INSTANCE,
+        Iso5.INSTANCE,
+        Iso5.INSTANCE,
+        Iso6.INSTANCE,
+        Iso6.INSTANCE,
+        Iso7.INSTANCE,
+        Iso7.INSTANCE,
+        Iso8.INSTANCE,
+        Iso8.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1254.INSTANCE,
+        Koi8R.INSTANCE,
+        Koi8R.INSTANCE,
+        Koi8R.INSTANCE,
+        Koi8U.INSTANCE,
+        Koi8U.INSTANCE,
+        Koi8R.INSTANCE,
+        EucKr.INSTANCE,
+        EucKr.INSTANCE,
+        EucKr.INSTANCE,
+        EucKr.INSTANCE,
+        EucKr.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Windows1254.INSTANCE,
+        Iso10.INSTANCE,
+        Iso15.INSTANCE,
+        Windows1252.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Windows1254.INSTANCE,
+        Iso10.INSTANCE,
+        Iso8I.INSTANCE,
+        Macintosh.INSTANCE,
+        Macintosh.INSTANCE,
+        ShiftJis.INSTANCE,
+        ShiftJis.INSTANCE,
+        ShiftJis.INSTANCE,
+        ShiftJis.INSTANCE,
+        ShiftJis.INSTANCE,
+        Iso7.INSTANCE,
+        Windows874.INSTANCE,
+        Utf8.INSTANCE,
+        Windows1252.INSTANCE,
+        Utf16Le.INSTANCE,
+        Utf16Be.INSTANCE,
+        Utf16Le.INSTANCE,
+        Utf8.INSTANCE,
+        Utf8.INSTANCE,
+        Iso8.INSTANCE,
+        Windows1250.INSTANCE,
+        Windows1251.INSTANCE,
+        Windows1252.INSTANCE,
+        Windows1253.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1255.INSTANCE,
+        Windows1256.INSTANCE,
+        Windows1257.INSTANCE,
+        Windows1258.INSTANCE,
+        ShiftJis.INSTANCE,
+        Windows874.INSTANCE,
+        EucKr.INSTANCE,
+        Windows1250.INSTANCE,
+        Windows1251.INSTANCE,
+        Windows1252.INSTANCE,
+        Windows1253.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1255.INSTANCE,
+        Windows1256.INSTANCE,
+        Windows1257.INSTANCE,
+        Windows1258.INSTANCE,
+        EucJp.INSTANCE,
+        Gbk.INSTANCE,
+        MacCyrillic.INSTANCE,
+        Macintosh.INSTANCE,
+        MacCyrillic.INSTANCE,
+        ShiftJis.INSTANCE,
+        UserDefined.INSTANCE,
+        Big5.INSTANCE,
+    };
+
+    private static final Encoding[] ENCODINGS = {
+        Big5.INSTANCE,
+        EucJp.INSTANCE,
+        EucKr.INSTANCE,
+        Gb18030.INSTANCE,
+        Gbk.INSTANCE,
+        Ibm866.INSTANCE,
+        Iso2022Jp.INSTANCE,
+        Iso10.INSTANCE,
+        Iso13.INSTANCE,
+        Iso14.INSTANCE,
+        Iso15.INSTANCE,
+        Iso16.INSTANCE,
+        Iso2.INSTANCE,
+        Iso3.INSTANCE,
+        Iso4.INSTANCE,
+        Iso5.INSTANCE,
+        Iso6.INSTANCE,
+        Iso7.INSTANCE,
+        Iso8.INSTANCE,
+        Iso8I.INSTANCE,
+        Koi8R.INSTANCE,
+        Koi8U.INSTANCE,
+        Macintosh.INSTANCE,
+        Replacement.INSTANCE,
+        ShiftJis.INSTANCE,
+        Utf16Be.INSTANCE,
+        Utf16Le.INSTANCE,
+        Utf8.INSTANCE,
+        Windows1250.INSTANCE,
+        Windows1251.INSTANCE,
+        Windows1252.INSTANCE,
+        Windows1253.INSTANCE,
+        Windows1254.INSTANCE,
+        Windows1255.INSTANCE,
+        Windows1256.INSTANCE,
+        Windows1257.INSTANCE,
+        Windows1258.INSTANCE,
+        Windows874.INSTANCE,
+        MacCyrillic.INSTANCE,
+        UserDefined.INSTANCE,
+    };
+
+    /**
+     * The big5 encoding.
+     */
+    public static final Encoding BIG5 = Big5.INSTANCE;
+
+    /**
+     * The euc-jp encoding.
+     */
+    public static final Encoding EUC_JP = EucJp.INSTANCE;
+
+    /**
+     * The euc-kr encoding.
+     */
+    public static final Encoding EUC_KR = EucKr.INSTANCE;
+
+    /**
+     * The gb18030 encoding.
+     */
+    public static final Encoding GB18030 = Gb18030.INSTANCE;
+
+    /**
+     * The gbk encoding.
+     */
+    public static final Encoding GBK = Gbk.INSTANCE;
+
+    /**
+     * The ibm866 encoding.
+     */
+    public static final Encoding IBM866 = Ibm866.INSTANCE;
+
+    /**
+     * The iso-2022-jp encoding.
+     */
+    public static final Encoding ISO_2022_JP = Iso2022Jp.INSTANCE;
+
+    /**
+     * The iso-8859-10 encoding.
+     */
+    public static final Encoding ISO_8859_10 = Iso10.INSTANCE;
+
+    /**
+     * The iso-8859-13 encoding.
+     */
+    public static final Encoding ISO_8859_13 = Iso13.INSTANCE;
+
+    /**
+     * The iso-8859-14 encoding.
+     */
+    public static final Encoding ISO_8859_14 = Iso14.INSTANCE;
+
+    /**
+     * The iso-8859-15 encoding.
+     */
+    public static final Encoding ISO_8859_15 = Iso15.INSTANCE;
+
+    /**
+     * The iso-8859-16 encoding.
+     */
+    public static final Encoding ISO_8859_16 = Iso16.INSTANCE;
+
+    /**
+     * The iso-8859-2 encoding.
+     */
+    public static final Encoding ISO_8859_2 = Iso2.INSTANCE;
+
+    /**
+     * The iso-8859-3 encoding.
+     */
+    public static final Encoding ISO_8859_3 = Iso3.INSTANCE;
+
+    /**
+     * The iso-8859-4 encoding.
+     */
+    public static final Encoding ISO_8859_4 = Iso4.INSTANCE;
+
+    /**
+     * The iso-8859-5 encoding.
+     */
+    public static final Encoding ISO_8859_5 = Iso5.INSTANCE;
+
+    /**
+     * The iso-8859-6 encoding.
+     */
+    public static final Encoding ISO_8859_6 = Iso6.INSTANCE;
+
+    /**
+     * The iso-8859-7 encoding.
+     */
+    public static final Encoding ISO_8859_7 = Iso7.INSTANCE;
+
+    /**
+     * The iso-8859-8 encoding.
+     */
+    public static final Encoding ISO_8859_8 = Iso8.INSTANCE;
+
+    /**
+     * The iso-8859-8-i encoding.
+     */
+    public static final Encoding ISO_8859_8_I = Iso8I.INSTANCE;
+
+    /**
+     * The koi8-r encoding.
+     */
+    public static final Encoding KOI8_R = Koi8R.INSTANCE;
+
+    /**
+     * The koi8-u encoding.
+     */
+    public static final Encoding KOI8_U = Koi8U.INSTANCE;
+
+    /**
+     * The macintosh encoding.
+     */
+    public static final Encoding MACINTOSH = Macintosh.INSTANCE;
+
+    /**
+     * The replacement encoding.
+     */
+    public static final Encoding REPLACEMENT = Replacement.INSTANCE;
+
+    /**
+     * The shift_jis encoding.
+     */
+    public static final Encoding SHIFT_JIS = ShiftJis.INSTANCE;
+
+    /**
+     * The utf-16be encoding.
+     */
+    public static final Encoding UTF_16BE = Utf16Be.INSTANCE;
+
+    /**
+     * The utf-16le encoding.
+     */
+    public static final Encoding UTF_16LE = Utf16Le.INSTANCE;
+
+    /**
+     * The utf-8 encoding.
+     */
+    public static final Encoding UTF_8 = Utf8.INSTANCE;
+
+    /**
+     * The windows-1250 encoding.
+     */
+    public static final Encoding WINDOWS_1250 = Windows1250.INSTANCE;
+
+    /**
+     * The windows-1251 encoding.
+     */
+    public static final Encoding WINDOWS_1251 = Windows1251.INSTANCE;
+
+    /**
+     * The windows-1252 encoding.
+     */
+    public static final Encoding WINDOWS_1252 = Windows1252.INSTANCE;
+
+    /**
+     * The windows-1253 encoding.
+     */
+    public static final Encoding WINDOWS_1253 = Windows1253.INSTANCE;
+
+    /**
+     * The windows-1254 encoding.
+     */
+    public static final Encoding WINDOWS_1254 = Windows1254.INSTANCE;
+
+    /**
+     * The windows-1255 encoding.
+     */
+    public static final Encoding WINDOWS_1255 = Windows1255.INSTANCE;
+
+    /**
+     * The windows-1256 encoding.
+     */
+    public static final Encoding WINDOWS_1256 = Windows1256.INSTANCE;
+
+    /**
+     * The windows-1257 encoding.
+     */
+    public static final Encoding WINDOWS_1257 = Windows1257.INSTANCE;
+
+    /**
+     * The windows-1258 encoding.
+     */
+    public static final Encoding WINDOWS_1258 = Windows1258.INSTANCE;
+
+    /**
+     * The windows-874 encoding.
+     */
+    public static final Encoding WINDOWS_874 = Windows874.INSTANCE;
+
+    /**
+     * The x-mac-cyrillic encoding.
+     */
+    public static final Encoding X_MAC_CYRILLIC = MacCyrillic.INSTANCE;
+
+    /**
+     * The x-user-defined encoding.
+     */
+    public static final Encoding X_USER_DEFINED = UserDefined.INSTANCE;
+
+
+private static SortedMap<String, Charset> encodings = null;
+
+    protected Encoding(String canonicalName, String[] aliases) {
+        super(canonicalName, aliases);
+    }
+
+    private enum State {
+        HEAD, LABEL, TAIL
+    };
+
+    public static Encoding forName(String label) {
+        if (label == null) {
+            throw new IllegalArgumentException("Label must not be null.");
+        }
+        if (label.length() == 0) {
+            throw new IllegalCharsetNameException(label);
+        }
+        // First try the fast path
+        int index = Arrays.binarySearch(LABELS, label);
+        if (index >= 0) {
+            return ENCODINGS_FOR_LABELS[index];
+        }
+        // Else, slow path
+        StringBuilder sb = new StringBuilder();
+        State state = State.HEAD;
+        for (int i = 0; i < label.length(); i++) {
+            char c = label.charAt(i);
+            if ((c == ' ') || (c == '\n') || (c == '\r') || (c == '\t')
+                    || (c == '\u000C')) {
+                if (state == State.LABEL) {
+                    state = State.TAIL;
+                }
+                continue;
+            }
+            if ((c >= 'a' && c <= 'z') || (c >= '0' && c <= '9')) {
+                switch (state) {
+                    case HEAD:
+                        state = State.LABEL;
+                        // Fall through
+                    case LABEL:
+                        sb.append(c);
+                        continue;
+                    case TAIL:
+                        throw new IllegalCharsetNameException(label);
+                }
+            }
+            if (c >= 'A' && c <= 'Z') {
+                c += 0x20;
+                switch (state) {
+                    case HEAD:
+                        state = State.LABEL;
+                        // Fall through
+                    case LABEL:
+                        sb.append(c);
+                        continue;
+                    case TAIL:
+                        throw new IllegalCharsetNameException(label);
+                }
+            }
+            if ((c == '-') || (c == '+') || (c == '.') || (c == ':')
+                    || (c == '_')) {
+                switch (state) {
+                    case LABEL:
+                        sb.append(c);
+                        continue;
+                    case HEAD:
+                    case TAIL:
+                        throw new IllegalCharsetNameException(label);
+                }
+            }
+            throw new IllegalCharsetNameException(label);
+        }
+        index = Arrays.binarySearch(LABELS, sb.toString());
+        if (index >= 0) {
+            return ENCODINGS_FOR_LABELS[index];
+        }
+        throw new UnsupportedCharsetException(label);
+    }
+
+    public static Encoding forNameNoReplacement(String label) {
+        Encoding encoding = Encoding.forName(label);
+        if (encoding == Encoding.REPLACEMENT) {
+            throw new UnsupportedCharsetException(label);            
+        }
+        return encoding;
+    }
+
+    public static boolean isSupported(String label) {
+        try {
+            Encoding.forName(label);
+        } catch (UnsupportedCharsetException e) {
+            return false;
+        }
+        return true;
+    }
+
+    public static boolean isSupportedNoReplacement(String label) {
+        try {
+            Encoding.forNameNoReplacement(label);
+        } catch (UnsupportedCharsetException e) {
+            return false;
+        }
+        return true;
+    }
+
+    public static SortedMap<String, Charset> availableCharsets() {
+        if (encodings == null) {
+            TreeMap<String, Charset> map = new TreeMap<String, Charset>();
+            for (Encoding encoding : ENCODINGS) {
+                map.put(encoding.name(), encoding);
+            }
+            encodings = Collections.unmodifiableSortedMap(map);
+        }
+        return encodings;
+    }
+
+    public static Encoding defaultCharset() {
+        return WINDOWS_1252;
+    }
+
+    @Override public boolean canEncode() {
+        return false;
+    }
+
+    @Override public boolean contains(Charset cs) {
+        return false;
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        throw new UnsupportedOperationException("Encoder not implemented.");
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/EucJp.java b/parser/html/java/htmlparser/src/nu/validator/encoding/EucJp.java
new file mode 100644
index 000000000..05fbef810
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/EucJp.java
@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class EucJp extends Encoding {
+
+    private static final String[] LABELS = {
+        "cseucpkdfmtjapanese",
+        "euc-jp",
+        "x-euc-jp"
+    };
+    
+    private static final String NAME = "euc-jp";
+    
+    static final EucJp INSTANCE = new EucJp();
+    
+    private EucJp() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/EucKr.java b/parser/html/java/htmlparser/src/nu/validator/encoding/EucKr.java
new file mode 100644
index 000000000..a3923e224
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/EucKr.java
@@ -0,0 +1,64 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class EucKr extends Encoding {
+
+    private static final String[] LABELS = {
+        "cseuckr",
+        "csksc56011987",
+        "euc-kr",
+        "iso-ir-149",
+        "korean",
+        "ks_c_5601-1987",
+        "ks_c_5601-1989",
+        "ksc5601",
+        "ksc_5601",
+        "windows-949"
+    };
+    
+    private static final String NAME = "euc-kr";
+    
+    static final EucKr INSTANCE = new EucKr();
+    
+    private EucKr() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/FallibleSingleByteDecoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/FallibleSingleByteDecoder.java
new file mode 100644
index 000000000..34a1f36b5
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/FallibleSingleByteDecoder.java
@@ -0,0 +1,61 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.CoderResult;
+
+public final class FallibleSingleByteDecoder extends InfallibleSingleByteDecoder {
+
+    public FallibleSingleByteDecoder(Encoding cs, char[] upperHalf) {
+        super(cs, upperHalf);
+    }
+
+    @Override protected CoderResult decodeLoop(ByteBuffer in, CharBuffer out) {
+        if (!this.report) {
+            return super.decodeLoop(in, out);
+        } else {
+            for (;;) {
+                if (!in.hasRemaining()) {
+                    return CoderResult.UNDERFLOW;
+                }
+                if (!out.hasRemaining()) {
+                    return CoderResult.OVERFLOW;
+                }
+                int b = (int) in.get();
+                if (b >= 0) {
+                    out.put((char) b);
+                } else {
+                    char mapped = this.upperHalf[b + 128];
+                    if (mapped == '\uFFFD') {
+                        in.position(in.position() - 1);
+                        return CoderResult.malformedForLength(1);
+                    }
+                    out.put(mapped);
+                }
+            }
+        }
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Gb18030.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Gb18030.java
new file mode 100644
index 000000000..fcb090dde
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Gb18030.java
@@ -0,0 +1,55 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Gb18030 extends Encoding {
+
+    private static final String[] LABELS = {
+        "gb18030"
+    };
+    
+    private static final String NAME = "gb18030";
+    
+    static final Gb18030 INSTANCE = new Gb18030();
+    
+    private Gb18030() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Gbk.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Gbk.java
new file mode 100644
index 000000000..2dc3694ed
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Gbk.java
@@ -0,0 +1,63 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Gbk extends Encoding {
+
+    private static final String[] LABELS = {
+        "chinese",
+        "csgb2312",
+        "csiso58gb231280",
+        "gb2312",
+        "gb_2312",
+        "gb_2312-80",
+        "gbk",
+        "iso-ir-58",
+        "x-gbk"
+    };
+    
+    private static final String NAME = "gbk";
+    
+    static final Gbk INSTANCE = new Gbk();
+    
+    private Gbk() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName("gb18030").newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Ibm866.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Ibm866.java
new file mode 100644
index 000000000..037e62835
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Ibm866.java
@@ -0,0 +1,184 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Ibm866 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0410',
+        '\u0411',
+        '\u0412',
+        '\u0413',
+        '\u0414',
+        '\u0415',
+        '\u0416',
+        '\u0417',
+        '\u0418',
+        '\u0419',
+        '\u041a',
+        '\u041b',
+        '\u041c',
+        '\u041d',
+        '\u041e',
+        '\u041f',
+        '\u0420',
+        '\u0421',
+        '\u0422',
+        '\u0423',
+        '\u0424',
+        '\u0425',
+        '\u0426',
+        '\u0427',
+        '\u0428',
+        '\u0429',
+        '\u042a',
+        '\u042b',
+        '\u042c',
+        '\u042d',
+        '\u042e',
+        '\u042f',
+        '\u0430',
+        '\u0431',
+        '\u0432',
+        '\u0433',
+        '\u0434',
+        '\u0435',
+        '\u0436',
+        '\u0437',
+        '\u0438',
+        '\u0439',
+        '\u043a',
+        '\u043b',
+        '\u043c',
+        '\u043d',
+        '\u043e',
+        '\u043f',
+        '\u2591',
+        '\u2592',
+        '\u2593',
+        '\u2502',
+        '\u2524',
+        '\u2561',
+        '\u2562',
+        '\u2556',
+        '\u2555',
+        '\u2563',
+        '\u2551',
+        '\u2557',
+        '\u255d',
+        '\u255c',
+        '\u255b',
+        '\u2510',
+        '\u2514',
+        '\u2534',
+        '\u252c',
+        '\u251c',
+        '\u2500',
+        '\u253c',
+        '\u255e',
+        '\u255f',
+        '\u255a',
+        '\u2554',
+        '\u2569',
+        '\u2566',
+        '\u2560',
+        '\u2550',
+        '\u256c',
+        '\u2567',
+        '\u2568',
+        '\u2564',
+        '\u2565',
+        '\u2559',
+        '\u2558',
+        '\u2552',
+        '\u2553',
+        '\u256b',
+        '\u256a',
+        '\u2518',
+        '\u250c',
+        '\u2588',
+        '\u2584',
+        '\u258c',
+        '\u2590',
+        '\u2580',
+        '\u0440',
+        '\u0441',
+        '\u0442',
+        '\u0443',
+        '\u0444',
+        '\u0445',
+        '\u0446',
+        '\u0447',
+        '\u0448',
+        '\u0449',
+        '\u044a',
+        '\u044b',
+        '\u044c',
+        '\u044d',
+        '\u044e',
+        '\u044f',
+        '\u0401',
+        '\u0451',
+        '\u0404',
+        '\u0454',
+        '\u0407',
+        '\u0457',
+        '\u040e',
+        '\u045e',
+        '\u00b0',
+        '\u2219',
+        '\u00b7',
+        '\u221a',
+        '\u2116',
+        '\u00a4',
+        '\u25a0',
+        '\u00a0'
+    };
+    
+    private static final String[] LABELS = {
+        "866",
+        "cp866",
+        "csibm866",
+        "ibm866"
+    };
+    
+    private static final String NAME = "ibm866";
+    
+    static final Encoding INSTANCE = new Ibm866();
+    
+    private Ibm866() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/InfallibleSingleByteDecoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/InfallibleSingleByteDecoder.java
new file mode 100644
index 000000000..7cc63072c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/InfallibleSingleByteDecoder.java
@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.CoderResult;
+
+public class InfallibleSingleByteDecoder extends Decoder {
+
+    protected final char[] upperHalf;
+    
+    protected InfallibleSingleByteDecoder(Encoding cs, char[] upperHalf) {
+        super(cs, 1.0f, 1.0f);
+        this.upperHalf = upperHalf;
+    }
+
+    @Override protected CoderResult decodeLoop(ByteBuffer in, CharBuffer out) {
+        // TODO figure out if it's worthwhile to optimize the case where both
+        // buffers are array-backed.
+        for (;;) {
+            if (!in.hasRemaining()) {
+                return CoderResult.UNDERFLOW;
+            }
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            int b = (int) in.get();
+            if (b >= 0) {
+                out.put((char) b);
+            } else {
+                out.put(this.upperHalf[b + 128]);
+            }
+        }
+    }
+    
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso10.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso10.java
new file mode 100644
index 000000000..895cb5eed
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso10.java
@@ -0,0 +1,187 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso10 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0104',
+        '\u0112',
+        '\u0122',
+        '\u012a',
+        '\u0128',
+        '\u0136',
+        '\u00a7',
+        '\u013b',
+        '\u0110',
+        '\u0160',
+        '\u0166',
+        '\u017d',
+        '\u00ad',
+        '\u016a',
+        '\u014a',
+        '\u00b0',
+        '\u0105',
+        '\u0113',
+        '\u0123',
+        '\u012b',
+        '\u0129',
+        '\u0137',
+        '\u00b7',
+        '\u013c',
+        '\u0111',
+        '\u0161',
+        '\u0167',
+        '\u017e',
+        '\u2015',
+        '\u016b',
+        '\u014b',
+        '\u0100',
+        '\u00c1',
+        '\u00c2',
+        '\u00c3',
+        '\u00c4',
+        '\u00c5',
+        '\u00c6',
+        '\u012e',
+        '\u010c',
+        '\u00c9',
+        '\u0118',
+        '\u00cb',
+        '\u0116',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u00d0',
+        '\u0145',
+        '\u014c',
+        '\u00d3',
+        '\u00d4',
+        '\u00d5',
+        '\u00d6',
+        '\u0168',
+        '\u00d8',
+        '\u0172',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u00dd',
+        '\u00de',
+        '\u00df',
+        '\u0101',
+        '\u00e1',
+        '\u00e2',
+        '\u00e3',
+        '\u00e4',
+        '\u00e5',
+        '\u00e6',
+        '\u012f',
+        '\u010d',
+        '\u00e9',
+        '\u0119',
+        '\u00eb',
+        '\u0117',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\u00f0',
+        '\u0146',
+        '\u014d',
+        '\u00f3',
+        '\u00f4',
+        '\u00f5',
+        '\u00f6',
+        '\u0169',
+        '\u00f8',
+        '\u0173',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u00fd',
+        '\u00fe',
+        '\u0138'
+    };
+    
+    private static final String[] LABELS = {
+        "csisolatin6",
+        "iso-8859-10",
+        "iso-ir-157",
+        "iso8859-10",
+        "iso885910",
+        "l6",
+        "latin6"
+    };
+    
+    private static final String NAME = "iso-8859-10";
+    
+    static final Encoding INSTANCE = new Iso10();
+    
+    private Iso10() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso13.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso13.java
new file mode 100644
index 000000000..60e6f5339
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso13.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso13 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u201d',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\u201e',
+        '\u00a6',
+        '\u00a7',
+        '\u00d8',
+        '\u00a9',
+        '\u0156',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00c6',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u201c',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00f8',
+        '\u00b9',
+        '\u0157',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\u00e6',
+        '\u0104',
+        '\u012e',
+        '\u0100',
+        '\u0106',
+        '\u00c4',
+        '\u00c5',
+        '\u0118',
+        '\u0112',
+        '\u010c',
+        '\u00c9',
+        '\u0179',
+        '\u0116',
+        '\u0122',
+        '\u0136',
+        '\u012a',
+        '\u013b',
+        '\u0160',
+        '\u0143',
+        '\u0145',
+        '\u00d3',
+        '\u014c',
+        '\u00d5',
+        '\u00d6',
+        '\u00d7',
+        '\u0172',
+        '\u0141',
+        '\u015a',
+        '\u016a',
+        '\u00dc',
+        '\u017b',
+        '\u017d',
+        '\u00df',
+        '\u0105',
+        '\u012f',
+        '\u0101',
+        '\u0107',
+        '\u00e4',
+        '\u00e5',
+        '\u0119',
+        '\u0113',
+        '\u010d',
+        '\u00e9',
+        '\u017a',
+        '\u0117',
+        '\u0123',
+        '\u0137',
+        '\u012b',
+        '\u013c',
+        '\u0161',
+        '\u0144',
+        '\u0146',
+        '\u00f3',
+        '\u014d',
+        '\u00f5',
+        '\u00f6',
+        '\u00f7',
+        '\u0173',
+        '\u0142',
+        '\u015b',
+        '\u016b',
+        '\u00fc',
+        '\u017c',
+        '\u017e',
+        '\u2019'
+    };
+    
+    private static final String[] LABELS = {
+        "iso-8859-13",
+        "iso8859-13",
+        "iso885913"
+    };
+    
+    private static final String NAME = "iso-8859-13";
+    
+    static final Encoding INSTANCE = new Iso13();
+    
+    private Iso13() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso14.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso14.java
new file mode 100644
index 000000000..d4a180e6e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso14.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso14 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u1e02',
+        '\u1e03',
+        '\u00a3',
+        '\u010a',
+        '\u010b',
+        '\u1e0a',
+        '\u00a7',
+        '\u1e80',
+        '\u00a9',
+        '\u1e82',
+        '\u1e0b',
+        '\u1ef2',
+        '\u00ad',
+        '\u00ae',
+        '\u0178',
+        '\u1e1e',
+        '\u1e1f',
+        '\u0120',
+        '\u0121',
+        '\u1e40',
+        '\u1e41',
+        '\u00b6',
+        '\u1e56',
+        '\u1e81',
+        '\u1e57',
+        '\u1e83',
+        '\u1e60',
+        '\u1ef3',
+        '\u1e84',
+        '\u1e85',
+        '\u1e61',
+        '\u00c0',
+        '\u00c1',
+        '\u00c2',
+        '\u00c3',
+        '\u00c4',
+        '\u00c5',
+        '\u00c6',
+        '\u00c7',
+        '\u00c8',
+        '\u00c9',
+        '\u00ca',
+        '\u00cb',
+        '\u00cc',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u0174',
+        '\u00d1',
+        '\u00d2',
+        '\u00d3',
+        '\u00d4',
+        '\u00d5',
+        '\u00d6',
+        '\u1e6a',
+        '\u00d8',
+        '\u00d9',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u00dd',
+        '\u0176',
+        '\u00df',
+        '\u00e0',
+        '\u00e1',
+        '\u00e2',
+        '\u00e3',
+        '\u00e4',
+        '\u00e5',
+        '\u00e6',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u00ec',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\u0175',
+        '\u00f1',
+        '\u00f2',
+        '\u00f3',
+        '\u00f4',
+        '\u00f5',
+        '\u00f6',
+        '\u1e6b',
+        '\u00f8',
+        '\u00f9',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u00fd',
+        '\u0177',
+        '\u00ff'
+    };
+    
+    private static final String[] LABELS = {
+        "iso-8859-14",
+        "iso8859-14",
+        "iso885914"
+    };
+    
+    private static final String NAME = "iso-8859-14";
+    
+    static final Encoding INSTANCE = new Iso14();
+    
+    private Iso14() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso15.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso15.java
new file mode 100644
index 000000000..a60e4b6ef
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso15.java
@@ -0,0 +1,186 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso15 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u00a1',
+        '\u00a2',
+        '\u00a3',
+        '\u20ac',
+        '\u00a5',
+        '\u0160',
+        '\u00a7',
+        '\u0161',
+        '\u00a9',
+        '\u00aa',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u017d',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u017e',
+        '\u00b9',
+        '\u00ba',
+        '\u00bb',
+        '\u0152',
+        '\u0153',
+        '\u0178',
+        '\u00bf',
+        '\u00c0',
+        '\u00c1',
+        '\u00c2',
+        '\u00c3',
+        '\u00c4',
+        '\u00c5',
+        '\u00c6',
+        '\u00c7',
+        '\u00c8',
+        '\u00c9',
+        '\u00ca',
+        '\u00cb',
+        '\u00cc',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u00d0',
+        '\u00d1',
+        '\u00d2',
+        '\u00d3',
+        '\u00d4',
+        '\u00d5',
+        '\u00d6',
+        '\u00d7',
+        '\u00d8',
+        '\u00d9',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u00dd',
+        '\u00de',
+        '\u00df',
+        '\u00e0',
+        '\u00e1',
+        '\u00e2',
+        '\u00e3',
+        '\u00e4',
+        '\u00e5',
+        '\u00e6',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u00ec',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\u00f0',
+        '\u00f1',
+        '\u00f2',
+        '\u00f3',
+        '\u00f4',
+        '\u00f5',
+        '\u00f6',
+        '\u00f7',
+        '\u00f8',
+        '\u00f9',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u00fd',
+        '\u00fe',
+        '\u00ff'
+    };
+    
+    private static final String[] LABELS = {
+        "csisolatin9",
+        "iso-8859-15",
+        "iso8859-15",
+        "iso885915",
+        "iso_8859-15",
+        "l9"
+    };
+    
+    private static final String NAME = "iso-8859-15";
+    
+    static final Encoding INSTANCE = new Iso15();
+    
+    private Iso15() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso16.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso16.java
new file mode 100644
index 000000000..5eb1926db
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso16.java
@@ -0,0 +1,181 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso16 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0104',
+        '\u0105',
+        '\u0141',
+        '\u20ac',
+        '\u201e',
+        '\u0160',
+        '\u00a7',
+        '\u0161',
+        '\u00a9',
+        '\u0218',
+        '\u00ab',
+        '\u0179',
+        '\u00ad',
+        '\u017a',
+        '\u017b',
+        '\u00b0',
+        '\u00b1',
+        '\u010c',
+        '\u0142',
+        '\u017d',
+        '\u201d',
+        '\u00b6',
+        '\u00b7',
+        '\u017e',
+        '\u010d',
+        '\u0219',
+        '\u00bb',
+        '\u0152',
+        '\u0153',
+        '\u0178',
+        '\u017c',
+        '\u00c0',
+        '\u00c1',
+        '\u00c2',
+        '\u0102',
+        '\u00c4',
+        '\u0106',
+        '\u00c6',
+        '\u00c7',
+        '\u00c8',
+        '\u00c9',
+        '\u00ca',
+        '\u00cb',
+        '\u00cc',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u0110',
+        '\u0143',
+        '\u00d2',
+        '\u00d3',
+        '\u00d4',
+        '\u0150',
+        '\u00d6',
+        '\u015a',
+        '\u0170',
+        '\u00d9',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u0118',
+        '\u021a',
+        '\u00df',
+        '\u00e0',
+        '\u00e1',
+        '\u00e2',
+        '\u0103',
+        '\u00e4',
+        '\u0107',
+        '\u00e6',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u00ec',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\u0111',
+        '\u0144',
+        '\u00f2',
+        '\u00f3',
+        '\u00f4',
+        '\u0151',
+        '\u00f6',
+        '\u015b',
+        '\u0171',
+        '\u00f9',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u0119',
+        '\u021b',
+        '\u00ff'
+    };
+    
+    private static final String[] LABELS = {
+        "iso-8859-16"
+    };
+    
+    private static final String NAME = "iso-8859-16";
+    
+    static final Encoding INSTANCE = new Iso16();
+    
+    private Iso16() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso2.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso2.java
new file mode 100644
index 000000000..7a5f6322a
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso2.java
@@ -0,0 +1,189 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso2 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0104',
+        '\u02d8',
+        '\u0141',
+        '\u00a4',
+        '\u013d',
+        '\u015a',
+        '\u00a7',
+        '\u00a8',
+        '\u0160',
+        '\u015e',
+        '\u0164',
+        '\u0179',
+        '\u00ad',
+        '\u017d',
+        '\u017b',
+        '\u00b0',
+        '\u0105',
+        '\u02db',
+        '\u0142',
+        '\u00b4',
+        '\u013e',
+        '\u015b',
+        '\u02c7',
+        '\u00b8',
+        '\u0161',
+        '\u015f',
+        '\u0165',
+        '\u017a',
+        '\u02dd',
+        '\u017e',
+        '\u017c',
+        '\u0154',
+        '\u00c1',
+        '\u00c2',
+        '\u0102',
+        '\u00c4',
+        '\u0139',
+        '\u0106',
+        '\u00c7',
+        '\u010c',
+        '\u00c9',
+        '\u0118',
+        '\u00cb',
+        '\u011a',
+        '\u00cd',
+        '\u00ce',
+        '\u010e',
+        '\u0110',
+        '\u0143',
+        '\u0147',
+        '\u00d3',
+        '\u00d4',
+        '\u0150',
+        '\u00d6',
+        '\u00d7',
+        '\u0158',
+        '\u016e',
+        '\u00da',
+        '\u0170',
+        '\u00dc',
+        '\u00dd',
+        '\u0162',
+        '\u00df',
+        '\u0155',
+        '\u00e1',
+        '\u00e2',
+        '\u0103',
+        '\u00e4',
+        '\u013a',
+        '\u0107',
+        '\u00e7',
+        '\u010d',
+        '\u00e9',
+        '\u0119',
+        '\u00eb',
+        '\u011b',
+        '\u00ed',
+        '\u00ee',
+        '\u010f',
+        '\u0111',
+        '\u0144',
+        '\u0148',
+        '\u00f3',
+        '\u00f4',
+        '\u0151',
+        '\u00f6',
+        '\u00f7',
+        '\u0159',
+        '\u016f',
+        '\u00fa',
+        '\u0171',
+        '\u00fc',
+        '\u00fd',
+        '\u0163',
+        '\u02d9'
+    };
+    
+    private static final String[] LABELS = {
+        "csisolatin2",
+        "iso-8859-2",
+        "iso-ir-101",
+        "iso8859-2",
+        "iso88592",
+        "iso_8859-2",
+        "iso_8859-2:1987",
+        "l2",
+        "latin2"
+    };
+    
+    private static final String NAME = "iso-8859-2";
+    
+    static final Encoding INSTANCE = new Iso2();
+    
+    private Iso2() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso2022Jp.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso2022Jp.java
new file mode 100644
index 000000000..6ebadc947
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso2022Jp.java
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Iso2022Jp extends Encoding {
+
+    private static final String[] LABELS = {
+        "csiso2022jp",
+        "iso-2022-jp"
+    };
+    
+    private static final String NAME = "iso-2022-jp";
+    
+    static final Iso2022Jp INSTANCE = new Iso2022Jp();
+    
+    private Iso2022Jp() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso3.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso3.java
new file mode 100644
index 000000000..0667a160c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso3.java
@@ -0,0 +1,189 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso3 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0126',
+        '\u02d8',
+        '\u00a3',
+        '\u00a4',
+        '\ufffd',
+        '\u0124',
+        '\u00a7',
+        '\u00a8',
+        '\u0130',
+        '\u015e',
+        '\u011e',
+        '\u0134',
+        '\u00ad',
+        '\ufffd',
+        '\u017b',
+        '\u00b0',
+        '\u0127',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u0125',
+        '\u00b7',
+        '\u00b8',
+        '\u0131',
+        '\u015f',
+        '\u011f',
+        '\u0135',
+        '\u00bd',
+        '\ufffd',
+        '\u017c',
+        '\u00c0',
+        '\u00c1',
+        '\u00c2',
+        '\ufffd',
+        '\u00c4',
+        '\u010a',
+        '\u0108',
+        '\u00c7',
+        '\u00c8',
+        '\u00c9',
+        '\u00ca',
+        '\u00cb',
+        '\u00cc',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\ufffd',
+        '\u00d1',
+        '\u00d2',
+        '\u00d3',
+        '\u00d4',
+        '\u0120',
+        '\u00d6',
+        '\u00d7',
+        '\u011c',
+        '\u00d9',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u016c',
+        '\u015c',
+        '\u00df',
+        '\u00e0',
+        '\u00e1',
+        '\u00e2',
+        '\ufffd',
+        '\u00e4',
+        '\u010b',
+        '\u0109',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u00ec',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\ufffd',
+        '\u00f1',
+        '\u00f2',
+        '\u00f3',
+        '\u00f4',
+        '\u0121',
+        '\u00f6',
+        '\u00f7',
+        '\u011d',
+        '\u00f9',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u016d',
+        '\u015d',
+        '\u02d9'
+    };
+    
+    private static final String[] LABELS = {
+        "csisolatin3",
+        "iso-8859-3",
+        "iso-ir-109",
+        "iso8859-3",
+        "iso88593",
+        "iso_8859-3",
+        "iso_8859-3:1988",
+        "l3",
+        "latin3"
+    };
+    
+    private static final String NAME = "iso-8859-3";
+    
+    static final Encoding INSTANCE = new Iso3();
+    
+    private Iso3() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso4.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso4.java
new file mode 100644
index 000000000..b954869ab
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso4.java
@@ -0,0 +1,189 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso4 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0104',
+        '\u0138',
+        '\u0156',
+        '\u00a4',
+        '\u0128',
+        '\u013b',
+        '\u00a7',
+        '\u00a8',
+        '\u0160',
+        '\u0112',
+        '\u0122',
+        '\u0166',
+        '\u00ad',
+        '\u017d',
+        '\u00af',
+        '\u00b0',
+        '\u0105',
+        '\u02db',
+        '\u0157',
+        '\u00b4',
+        '\u0129',
+        '\u013c',
+        '\u02c7',
+        '\u00b8',
+        '\u0161',
+        '\u0113',
+        '\u0123',
+        '\u0167',
+        '\u014a',
+        '\u017e',
+        '\u014b',
+        '\u0100',
+        '\u00c1',
+        '\u00c2',
+        '\u00c3',
+        '\u00c4',
+        '\u00c5',
+        '\u00c6',
+        '\u012e',
+        '\u010c',
+        '\u00c9',
+        '\u0118',
+        '\u00cb',
+        '\u0116',
+        '\u00cd',
+        '\u00ce',
+        '\u012a',
+        '\u0110',
+        '\u0145',
+        '\u014c',
+        '\u0136',
+        '\u00d4',
+        '\u00d5',
+        '\u00d6',
+        '\u00d7',
+        '\u00d8',
+        '\u0172',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u0168',
+        '\u016a',
+        '\u00df',
+        '\u0101',
+        '\u00e1',
+        '\u00e2',
+        '\u00e3',
+        '\u00e4',
+        '\u00e5',
+        '\u00e6',
+        '\u012f',
+        '\u010d',
+        '\u00e9',
+        '\u0119',
+        '\u00eb',
+        '\u0117',
+        '\u00ed',
+        '\u00ee',
+        '\u012b',
+        '\u0111',
+        '\u0146',
+        '\u014d',
+        '\u0137',
+        '\u00f4',
+        '\u00f5',
+        '\u00f6',
+        '\u00f7',
+        '\u00f8',
+        '\u0173',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u0169',
+        '\u016b',
+        '\u02d9'
+    };
+    
+    private static final String[] LABELS = {
+        "csisolatin4",
+        "iso-8859-4",
+        "iso-ir-110",
+        "iso8859-4",
+        "iso88594",
+        "iso_8859-4",
+        "iso_8859-4:1988",
+        "l4",
+        "latin4"
+    };
+    
+    private static final String NAME = "iso-8859-4";
+    
+    static final Encoding INSTANCE = new Iso4();
+    
+    private Iso4() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso5.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso5.java
new file mode 100644
index 000000000..13946cdbb
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso5.java
@@ -0,0 +1,188 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso5 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0401',
+        '\u0402',
+        '\u0403',
+        '\u0404',
+        '\u0405',
+        '\u0406',
+        '\u0407',
+        '\u0408',
+        '\u0409',
+        '\u040a',
+        '\u040b',
+        '\u040c',
+        '\u00ad',
+        '\u040e',
+        '\u040f',
+        '\u0410',
+        '\u0411',
+        '\u0412',
+        '\u0413',
+        '\u0414',
+        '\u0415',
+        '\u0416',
+        '\u0417',
+        '\u0418',
+        '\u0419',
+        '\u041a',
+        '\u041b',
+        '\u041c',
+        '\u041d',
+        '\u041e',
+        '\u041f',
+        '\u0420',
+        '\u0421',
+        '\u0422',
+        '\u0423',
+        '\u0424',
+        '\u0425',
+        '\u0426',
+        '\u0427',
+        '\u0428',
+        '\u0429',
+        '\u042a',
+        '\u042b',
+        '\u042c',
+        '\u042d',
+        '\u042e',
+        '\u042f',
+        '\u0430',
+        '\u0431',
+        '\u0432',
+        '\u0433',
+        '\u0434',
+        '\u0435',
+        '\u0436',
+        '\u0437',
+        '\u0438',
+        '\u0439',
+        '\u043a',
+        '\u043b',
+        '\u043c',
+        '\u043d',
+        '\u043e',
+        '\u043f',
+        '\u0440',
+        '\u0441',
+        '\u0442',
+        '\u0443',
+        '\u0444',
+        '\u0445',
+        '\u0446',
+        '\u0447',
+        '\u0448',
+        '\u0449',
+        '\u044a',
+        '\u044b',
+        '\u044c',
+        '\u044d',
+        '\u044e',
+        '\u044f',
+        '\u2116',
+        '\u0451',
+        '\u0452',
+        '\u0453',
+        '\u0454',
+        '\u0455',
+        '\u0456',
+        '\u0457',
+        '\u0458',
+        '\u0459',
+        '\u045a',
+        '\u045b',
+        '\u045c',
+        '\u00a7',
+        '\u045e',
+        '\u045f'
+    };
+    
+    private static final String[] LABELS = {
+        "csisolatincyrillic",
+        "cyrillic",
+        "iso-8859-5",
+        "iso-ir-144",
+        "iso8859-5",
+        "iso88595",
+        "iso_8859-5",
+        "iso_8859-5:1988"
+    };
+    
+    private static final String NAME = "iso-8859-5";
+    
+    static final Encoding INSTANCE = new Iso5();
+    
+    private Iso5() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso6.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso6.java
new file mode 100644
index 000000000..02e6df8ba
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso6.java
@@ -0,0 +1,194 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso6 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u00a4',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u060c',
+        '\u00ad',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u061b',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u061f',
+        '\ufffd',
+        '\u0621',
+        '\u0622',
+        '\u0623',
+        '\u0624',
+        '\u0625',
+        '\u0626',
+        '\u0627',
+        '\u0628',
+        '\u0629',
+        '\u062a',
+        '\u062b',
+        '\u062c',
+        '\u062d',
+        '\u062e',
+        '\u062f',
+        '\u0630',
+        '\u0631',
+        '\u0632',
+        '\u0633',
+        '\u0634',
+        '\u0635',
+        '\u0636',
+        '\u0637',
+        '\u0638',
+        '\u0639',
+        '\u063a',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u0640',
+        '\u0641',
+        '\u0642',
+        '\u0643',
+        '\u0644',
+        '\u0645',
+        '\u0646',
+        '\u0647',
+        '\u0648',
+        '\u0649',
+        '\u064a',
+        '\u064b',
+        '\u064c',
+        '\u064d',
+        '\u064e',
+        '\u064f',
+        '\u0650',
+        '\u0651',
+        '\u0652',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd'
+    };
+    
+    private static final String[] LABELS = {
+        "arabic",
+        "asmo-708",
+        "csiso88596e",
+        "csiso88596i",
+        "csisolatinarabic",
+        "ecma-114",
+        "iso-8859-6",
+        "iso-8859-6-e",
+        "iso-8859-6-i",
+        "iso-ir-127",
+        "iso8859-6",
+        "iso88596",
+        "iso_8859-6",
+        "iso_8859-6:1987"
+    };
+    
+    private static final String NAME = "iso-8859-6";
+    
+    static final Encoding INSTANCE = new Iso6();
+    
+    private Iso6() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso7.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso7.java
new file mode 100644
index 000000000..630e702de
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso7.java
@@ -0,0 +1,192 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso7 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u2018',
+        '\u2019',
+        '\u00a3',
+        '\u20ac',
+        '\u20af',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u037a',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\ufffd',
+        '\u2015',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u0384',
+        '\u0385',
+        '\u0386',
+        '\u00b7',
+        '\u0388',
+        '\u0389',
+        '\u038a',
+        '\u00bb',
+        '\u038c',
+        '\u00bd',
+        '\u038e',
+        '\u038f',
+        '\u0390',
+        '\u0391',
+        '\u0392',
+        '\u0393',
+        '\u0394',
+        '\u0395',
+        '\u0396',
+        '\u0397',
+        '\u0398',
+        '\u0399',
+        '\u039a',
+        '\u039b',
+        '\u039c',
+        '\u039d',
+        '\u039e',
+        '\u039f',
+        '\u03a0',
+        '\u03a1',
+        '\ufffd',
+        '\u03a3',
+        '\u03a4',
+        '\u03a5',
+        '\u03a6',
+        '\u03a7',
+        '\u03a8',
+        '\u03a9',
+        '\u03aa',
+        '\u03ab',
+        '\u03ac',
+        '\u03ad',
+        '\u03ae',
+        '\u03af',
+        '\u03b0',
+        '\u03b1',
+        '\u03b2',
+        '\u03b3',
+        '\u03b4',
+        '\u03b5',
+        '\u03b6',
+        '\u03b7',
+        '\u03b8',
+        '\u03b9',
+        '\u03ba',
+        '\u03bb',
+        '\u03bc',
+        '\u03bd',
+        '\u03be',
+        '\u03bf',
+        '\u03c0',
+        '\u03c1',
+        '\u03c2',
+        '\u03c3',
+        '\u03c4',
+        '\u03c5',
+        '\u03c6',
+        '\u03c7',
+        '\u03c8',
+        '\u03c9',
+        '\u03ca',
+        '\u03cb',
+        '\u03cc',
+        '\u03cd',
+        '\u03ce',
+        '\ufffd'
+    };
+    
+    private static final String[] LABELS = {
+        "csisolatingreek",
+        "ecma-118",
+        "elot_928",
+        "greek",
+        "greek8",
+        "iso-8859-7",
+        "iso-ir-126",
+        "iso8859-7",
+        "iso88597",
+        "iso_8859-7",
+        "iso_8859-7:1987",
+        "sun_eu_greek"
+    };
+    
+    private static final String NAME = "iso-8859-7";
+    
+    static final Encoding INSTANCE = new Iso7();
+    
+    private Iso7() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso8.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso8.java
new file mode 100644
index 000000000..10ee33486
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso8.java
@@ -0,0 +1,191 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso8 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\ufffd',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u00d7',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u00b9',
+        '\u00f7',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u2017',
+        '\u05d0',
+        '\u05d1',
+        '\u05d2',
+        '\u05d3',
+        '\u05d4',
+        '\u05d5',
+        '\u05d6',
+        '\u05d7',
+        '\u05d8',
+        '\u05d9',
+        '\u05da',
+        '\u05db',
+        '\u05dc',
+        '\u05dd',
+        '\u05de',
+        '\u05df',
+        '\u05e0',
+        '\u05e1',
+        '\u05e2',
+        '\u05e3',
+        '\u05e4',
+        '\u05e5',
+        '\u05e6',
+        '\u05e7',
+        '\u05e8',
+        '\u05e9',
+        '\u05ea',
+        '\ufffd',
+        '\ufffd',
+        '\u200e',
+        '\u200f',
+        '\ufffd'
+    };
+    
+    private static final String[] LABELS = {
+        "csiso88598e",
+        "csisolatinhebrew",
+        "hebrew",
+        "iso-8859-8",
+        "iso-8859-8-e",
+        "iso-ir-138",
+        "iso8859-8",
+        "iso88598",
+        "iso_8859-8",
+        "iso_8859-8:1988",
+        "visual"
+    };
+    
+    private static final String NAME = "iso-8859-8";
+    
+    static final Encoding INSTANCE = new Iso8();
+    
+    private Iso8() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Iso8I.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso8I.java
new file mode 100644
index 000000000..732e1c952
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Iso8I.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Iso8I extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0080',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u0085',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u0091',
+        '\u0092',
+        '\u0093',
+        '\u0094',
+        '\u0095',
+        '\u0096',
+        '\u0097',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\ufffd',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u00d7',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u00b9',
+        '\u00f7',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u2017',
+        '\u05d0',
+        '\u05d1',
+        '\u05d2',
+        '\u05d3',
+        '\u05d4',
+        '\u05d5',
+        '\u05d6',
+        '\u05d7',
+        '\u05d8',
+        '\u05d9',
+        '\u05da',
+        '\u05db',
+        '\u05dc',
+        '\u05dd',
+        '\u05de',
+        '\u05df',
+        '\u05e0',
+        '\u05e1',
+        '\u05e2',
+        '\u05e3',
+        '\u05e4',
+        '\u05e5',
+        '\u05e6',
+        '\u05e7',
+        '\u05e8',
+        '\u05e9',
+        '\u05ea',
+        '\ufffd',
+        '\ufffd',
+        '\u200e',
+        '\u200f',
+        '\ufffd'
+    };
+    
+    private static final String[] LABELS = {
+        "csiso88598i",
+        "iso-8859-8-i",
+        "logical"
+    };
+    
+    private static final String NAME = "iso-8859-8-i";
+    
+    static final Encoding INSTANCE = new Iso8I();
+    
+    private Iso8I() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Koi8R.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Koi8R.java
new file mode 100644
index 000000000..b6157bd8e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Koi8R.java
@@ -0,0 +1,185 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Koi8R extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u2500',
+        '\u2502',
+        '\u250c',
+        '\u2510',
+        '\u2514',
+        '\u2518',
+        '\u251c',
+        '\u2524',
+        '\u252c',
+        '\u2534',
+        '\u253c',
+        '\u2580',
+        '\u2584',
+        '\u2588',
+        '\u258c',
+        '\u2590',
+        '\u2591',
+        '\u2592',
+        '\u2593',
+        '\u2320',
+        '\u25a0',
+        '\u2219',
+        '\u221a',
+        '\u2248',
+        '\u2264',
+        '\u2265',
+        '\u00a0',
+        '\u2321',
+        '\u00b0',
+        '\u00b2',
+        '\u00b7',
+        '\u00f7',
+        '\u2550',
+        '\u2551',
+        '\u2552',
+        '\u0451',
+        '\u2553',
+        '\u2554',
+        '\u2555',
+        '\u2556',
+        '\u2557',
+        '\u2558',
+        '\u2559',
+        '\u255a',
+        '\u255b',
+        '\u255c',
+        '\u255d',
+        '\u255e',
+        '\u255f',
+        '\u2560',
+        '\u2561',
+        '\u0401',
+        '\u2562',
+        '\u2563',
+        '\u2564',
+        '\u2565',
+        '\u2566',
+        '\u2567',
+        '\u2568',
+        '\u2569',
+        '\u256a',
+        '\u256b',
+        '\u256c',
+        '\u00a9',
+        '\u044e',
+        '\u0430',
+        '\u0431',
+        '\u0446',
+        '\u0434',
+        '\u0435',
+        '\u0444',
+        '\u0433',
+        '\u0445',
+        '\u0438',
+        '\u0439',
+        '\u043a',
+        '\u043b',
+        '\u043c',
+        '\u043d',
+        '\u043e',
+        '\u043f',
+        '\u044f',
+        '\u0440',
+        '\u0441',
+        '\u0442',
+        '\u0443',
+        '\u0436',
+        '\u0432',
+        '\u044c',
+        '\u044b',
+        '\u0437',
+        '\u0448',
+        '\u044d',
+        '\u0449',
+        '\u0447',
+        '\u044a',
+        '\u042e',
+        '\u0410',
+        '\u0411',
+        '\u0426',
+        '\u0414',
+        '\u0415',
+        '\u0424',
+        '\u0413',
+        '\u0425',
+        '\u0418',
+        '\u0419',
+        '\u041a',
+        '\u041b',
+        '\u041c',
+        '\u041d',
+        '\u041e',
+        '\u041f',
+        '\u042f',
+        '\u0420',
+        '\u0421',
+        '\u0422',
+        '\u0423',
+        '\u0416',
+        '\u0412',
+        '\u042c',
+        '\u042b',
+        '\u0417',
+        '\u0428',
+        '\u042d',
+        '\u0429',
+        '\u0427',
+        '\u042a'
+    };
+    
+    private static final String[] LABELS = {
+        "cskoi8r",
+        "koi",
+        "koi8",
+        "koi8-r",
+        "koi8_r"
+    };
+    
+    private static final String NAME = "koi8-r";
+    
+    static final Encoding INSTANCE = new Koi8R();
+    
+    private Koi8R() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Koi8U.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Koi8U.java
new file mode 100644
index 000000000..8150838d3
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Koi8U.java
@@ -0,0 +1,182 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Koi8U extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u2500',
+        '\u2502',
+        '\u250c',
+        '\u2510',
+        '\u2514',
+        '\u2518',
+        '\u251c',
+        '\u2524',
+        '\u252c',
+        '\u2534',
+        '\u253c',
+        '\u2580',
+        '\u2584',
+        '\u2588',
+        '\u258c',
+        '\u2590',
+        '\u2591',
+        '\u2592',
+        '\u2593',
+        '\u2320',
+        '\u25a0',
+        '\u2219',
+        '\u221a',
+        '\u2248',
+        '\u2264',
+        '\u2265',
+        '\u00a0',
+        '\u2321',
+        '\u00b0',
+        '\u00b2',
+        '\u00b7',
+        '\u00f7',
+        '\u2550',
+        '\u2551',
+        '\u2552',
+        '\u0451',
+        '\u0454',
+        '\u2554',
+        '\u0456',
+        '\u0457',
+        '\u2557',
+        '\u2558',
+        '\u2559',
+        '\u255a',
+        '\u255b',
+        '\u0491',
+        '\u045e',
+        '\u255e',
+        '\u255f',
+        '\u2560',
+        '\u2561',
+        '\u0401',
+        '\u0404',
+        '\u2563',
+        '\u0406',
+        '\u0407',
+        '\u2566',
+        '\u2567',
+        '\u2568',
+        '\u2569',
+        '\u256a',
+        '\u0490',
+        '\u040e',
+        '\u00a9',
+        '\u044e',
+        '\u0430',
+        '\u0431',
+        '\u0446',
+        '\u0434',
+        '\u0435',
+        '\u0444',
+        '\u0433',
+        '\u0445',
+        '\u0438',
+        '\u0439',
+        '\u043a',
+        '\u043b',
+        '\u043c',
+        '\u043d',
+        '\u043e',
+        '\u043f',
+        '\u044f',
+        '\u0440',
+        '\u0441',
+        '\u0442',
+        '\u0443',
+        '\u0436',
+        '\u0432',
+        '\u044c',
+        '\u044b',
+        '\u0437',
+        '\u0448',
+        '\u044d',
+        '\u0449',
+        '\u0447',
+        '\u044a',
+        '\u042e',
+        '\u0410',
+        '\u0411',
+        '\u0426',
+        '\u0414',
+        '\u0415',
+        '\u0424',
+        '\u0413',
+        '\u0425',
+        '\u0418',
+        '\u0419',
+        '\u041a',
+        '\u041b',
+        '\u041c',
+        '\u041d',
+        '\u041e',
+        '\u041f',
+        '\u042f',
+        '\u0420',
+        '\u0421',
+        '\u0422',
+        '\u0423',
+        '\u0416',
+        '\u0412',
+        '\u042c',
+        '\u042b',
+        '\u0417',
+        '\u0428',
+        '\u042d',
+        '\u0429',
+        '\u0427',
+        '\u042a'
+    };
+    
+    private static final String[] LABELS = {
+        "koi8-ru",
+        "koi8-u"
+    };
+    
+    private static final String NAME = "koi8-u";
+    
+    static final Encoding INSTANCE = new Koi8U();
+    
+    private Koi8U() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/MacCyrillic.java b/parser/html/java/htmlparser/src/nu/validator/encoding/MacCyrillic.java
new file mode 100644
index 000000000..f46546ce2
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/MacCyrillic.java
@@ -0,0 +1,182 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class MacCyrillic extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0410',
+        '\u0411',
+        '\u0412',
+        '\u0413',
+        '\u0414',
+        '\u0415',
+        '\u0416',
+        '\u0417',
+        '\u0418',
+        '\u0419',
+        '\u041a',
+        '\u041b',
+        '\u041c',
+        '\u041d',
+        '\u041e',
+        '\u041f',
+        '\u0420',
+        '\u0421',
+        '\u0422',
+        '\u0423',
+        '\u0424',
+        '\u0425',
+        '\u0426',
+        '\u0427',
+        '\u0428',
+        '\u0429',
+        '\u042a',
+        '\u042b',
+        '\u042c',
+        '\u042d',
+        '\u042e',
+        '\u042f',
+        '\u2020',
+        '\u00b0',
+        '\u0490',
+        '\u00a3',
+        '\u00a7',
+        '\u2022',
+        '\u00b6',
+        '\u0406',
+        '\u00ae',
+        '\u00a9',
+        '\u2122',
+        '\u0402',
+        '\u0452',
+        '\u2260',
+        '\u0403',
+        '\u0453',
+        '\u221e',
+        '\u00b1',
+        '\u2264',
+        '\u2265',
+        '\u0456',
+        '\u00b5',
+        '\u0491',
+        '\u0408',
+        '\u0404',
+        '\u0454',
+        '\u0407',
+        '\u0457',
+        '\u0409',
+        '\u0459',
+        '\u040a',
+        '\u045a',
+        '\u0458',
+        '\u0405',
+        '\u00ac',
+        '\u221a',
+        '\u0192',
+        '\u2248',
+        '\u2206',
+        '\u00ab',
+        '\u00bb',
+        '\u2026',
+        '\u00a0',
+        '\u040b',
+        '\u045b',
+        '\u040c',
+        '\u045c',
+        '\u0455',
+        '\u2013',
+        '\u2014',
+        '\u201c',
+        '\u201d',
+        '\u2018',
+        '\u2019',
+        '\u00f7',
+        '\u201e',
+        '\u040e',
+        '\u045e',
+        '\u040f',
+        '\u045f',
+        '\u2116',
+        '\u0401',
+        '\u0451',
+        '\u044f',
+        '\u0430',
+        '\u0431',
+        '\u0432',
+        '\u0433',
+        '\u0434',
+        '\u0435',
+        '\u0436',
+        '\u0437',
+        '\u0438',
+        '\u0439',
+        '\u043a',
+        '\u043b',
+        '\u043c',
+        '\u043d',
+        '\u043e',
+        '\u043f',
+        '\u0440',
+        '\u0441',
+        '\u0442',
+        '\u0443',
+        '\u0444',
+        '\u0445',
+        '\u0446',
+        '\u0447',
+        '\u0448',
+        '\u0449',
+        '\u044a',
+        '\u044b',
+        '\u044c',
+        '\u044d',
+        '\u044e',
+        '\u20ac'
+    };
+    
+    private static final String[] LABELS = {
+        "x-mac-cyrillic",
+        "x-mac-ukrainian"
+    };
+    
+    private static final String NAME = "x-mac-cyrillic";
+    
+    static final Encoding INSTANCE = new MacCyrillic();
+    
+    private MacCyrillic() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Macintosh.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Macintosh.java
new file mode 100644
index 000000000..70e356f23
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Macintosh.java
@@ -0,0 +1,184 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Macintosh extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u00c4',
+        '\u00c5',
+        '\u00c7',
+        '\u00c9',
+        '\u00d1',
+        '\u00d6',
+        '\u00dc',
+        '\u00e1',
+        '\u00e0',
+        '\u00e2',
+        '\u00e4',
+        '\u00e3',
+        '\u00e5',
+        '\u00e7',
+        '\u00e9',
+        '\u00e8',
+        '\u00ea',
+        '\u00eb',
+        '\u00ed',
+        '\u00ec',
+        '\u00ee',
+        '\u00ef',
+        '\u00f1',
+        '\u00f3',
+        '\u00f2',
+        '\u00f4',
+        '\u00f6',
+        '\u00f5',
+        '\u00fa',
+        '\u00f9',
+        '\u00fb',
+        '\u00fc',
+        '\u2020',
+        '\u00b0',
+        '\u00a2',
+        '\u00a3',
+        '\u00a7',
+        '\u2022',
+        '\u00b6',
+        '\u00df',
+        '\u00ae',
+        '\u00a9',
+        '\u2122',
+        '\u00b4',
+        '\u00a8',
+        '\u2260',
+        '\u00c6',
+        '\u00d8',
+        '\u221e',
+        '\u00b1',
+        '\u2264',
+        '\u2265',
+        '\u00a5',
+        '\u00b5',
+        '\u2202',
+        '\u2211',
+        '\u220f',
+        '\u03c0',
+        '\u222b',
+        '\u00aa',
+        '\u00ba',
+        '\u03a9',
+        '\u00e6',
+        '\u00f8',
+        '\u00bf',
+        '\u00a1',
+        '\u00ac',
+        '\u221a',
+        '\u0192',
+        '\u2248',
+        '\u2206',
+        '\u00ab',
+        '\u00bb',
+        '\u2026',
+        '\u00a0',
+        '\u00c0',
+        '\u00c3',
+        '\u00d5',
+        '\u0152',
+        '\u0153',
+        '\u2013',
+        '\u2014',
+        '\u201c',
+        '\u201d',
+        '\u2018',
+        '\u2019',
+        '\u00f7',
+        '\u25ca',
+        '\u00ff',
+        '\u0178',
+        '\u2044',
+        '\u20ac',
+        '\u2039',
+        '\u203a',
+        '\ufb01',
+        '\ufb02',
+        '\u2021',
+        '\u00b7',
+        '\u201a',
+        '\u201e',
+        '\u2030',
+        '\u00c2',
+        '\u00ca',
+        '\u00c1',
+        '\u00cb',
+        '\u00c8',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u00cc',
+        '\u00d3',
+        '\u00d4',
+        '\uf8ff',
+        '\u00d2',
+        '\u00da',
+        '\u00db',
+        '\u00d9',
+        '\u0131',
+        '\u02c6',
+        '\u02dc',
+        '\u00af',
+        '\u02d8',
+        '\u02d9',
+        '\u02da',
+        '\u00b8',
+        '\u02dd',
+        '\u02db',
+        '\u02c7'
+    };
+    
+    private static final String[] LABELS = {
+        "csmacintosh",
+        "mac",
+        "macintosh",
+        "x-mac-roman"
+    };
+    
+    private static final String NAME = "macintosh";
+    
+    static final Encoding INSTANCE = new Macintosh();
+    
+    private Macintosh() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Replacement.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Replacement.java
new file mode 100644
index 000000000..abb6e24e7
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Replacement.java
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Replacement extends Encoding {
+
+    private static final String[] LABELS = {
+        "csiso2022kr",
+        "hz-gb-2312",
+        "iso-2022-cn",
+        "iso-2022-cn-ext",
+        "iso-2022-kr"
+    };
+    
+    private static final String NAME = "replacement";
+    
+    static final Replacement INSTANCE = new Replacement();
+    
+    private Replacement() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new ReplacementDecoder(this);
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/ReplacementDecoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/ReplacementDecoder.java
new file mode 100644
index 000000000..f6f2448f6
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/ReplacementDecoder.java
@@ -0,0 +1,75 @@
+/*
+ * Copyright (c) 2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.Charset;
+import java.nio.charset.CoderResult;
+
+class ReplacementDecoder extends Decoder {
+
+    private boolean haveEmitted = false;
+    
+    ReplacementDecoder(Charset cs) {
+        super(cs, 1.0f, 1.0f);
+    }
+
+    @Override protected CoderResult decodeLoop(ByteBuffer in, CharBuffer out) {
+        for (;;) {
+            if (!in.hasRemaining()) {
+                return CoderResult.UNDERFLOW;
+            }
+            if (haveEmitted) {
+                in.position(in.limit());
+                return CoderResult.UNDERFLOW;                
+            }
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            in.position(in.limit());
+            haveEmitted = true;
+            if (this.report) {
+                return CoderResult.malformedForLength(1);
+            }
+            out.put('\uFFFD');           
+        }
+    }
+
+    /**
+     * @see java.nio.charset.CharsetDecoder#implFlush(java.nio.CharBuffer)
+     */
+    @Override protected CoderResult implFlush(CharBuffer out) {
+        // TODO Auto-generated method stub
+        return super.implFlush(out);
+    }
+
+    /**
+     * @see java.nio.charset.CharsetDecoder#implReset()
+     */
+    @Override protected void implReset() {
+        // TODO Auto-generated method stub
+        super.implReset();
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/ShiftJis.java b/parser/html/java/htmlparser/src/nu/validator/encoding/ShiftJis.java
new file mode 100644
index 000000000..6638eab39
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/ShiftJis.java
@@ -0,0 +1,62 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class ShiftJis extends Encoding {
+
+    private static final String[] LABELS = {
+        "csshiftjis",
+        "ms932",
+        "ms_kanji",
+        "shift-jis",
+        "shift_jis",
+        "sjis",
+        "windows-31j",
+        "x-sjis"
+    };
+    
+    private static final String NAME = "shift_jis";
+    
+    static final ShiftJis INSTANCE = new ShiftJis();
+    
+    private ShiftJis() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/UserDefined.java b/parser/html/java/htmlparser/src/nu/validator/encoding/UserDefined.java
new file mode 100644
index 000000000..61534cb28
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/UserDefined.java
@@ -0,0 +1,55 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class UserDefined extends Encoding {
+
+    private static final String[] LABELS = {
+        "x-user-defined"
+    };
+    
+    private static final String NAME = "x-user-defined";
+    
+    static final UserDefined INSTANCE = new UserDefined();
+    
+    private UserDefined() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new UserDefinedDecoder(this);
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/UserDefinedDecoder.java b/parser/html/java/htmlparser/src/nu/validator/encoding/UserDefinedDecoder.java
new file mode 100644
index 000000000..c14ca8627
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/UserDefinedDecoder.java
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.encoding;
+
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CoderResult;
+
+class UserDefinedDecoder extends Decoder {
+
+    UserDefinedDecoder(Charset cs) {
+        super(cs, 1.0f, 1.0f);
+    }
+
+    @Override protected CoderResult decodeLoop(ByteBuffer in, CharBuffer out) {
+        // TODO figure out if it's worthwhile to optimize the case where both
+        // buffers are array-backed.
+        for (;;) {
+            if (!in.hasRemaining()) {
+                return CoderResult.UNDERFLOW;
+            }
+            if (!out.hasRemaining()) {
+                return CoderResult.OVERFLOW;
+            }
+            int b = (int)in.get();
+            if (b >= 0) {
+                out.put((char)b);
+            } else {
+                out.put((char)(b + 128 + 0xF780));
+            }
+        }
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Utf16Be.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Utf16Be.java
new file mode 100644
index 000000000..16c0d2fd5
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Utf16Be.java
@@ -0,0 +1,55 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Utf16Be extends Encoding {
+
+    private static final String[] LABELS = {
+        "utf-16be"
+    };
+    
+    private static final String NAME = "utf-16be";
+    
+    static final Utf16Be INSTANCE = new Utf16Be();
+    
+    private Utf16Be() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Utf16Le.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Utf16Le.java
new file mode 100644
index 000000000..7381235b5
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Utf16Le.java
@@ -0,0 +1,56 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Utf16Le extends Encoding {
+
+    private static final String[] LABELS = {
+        "utf-16",
+        "utf-16le"
+    };
+    
+    private static final String NAME = "utf-16le";
+    
+    static final Utf16Le INSTANCE = new Utf16Le();
+    
+    private Utf16Le() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Utf8.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Utf8.java
new file mode 100644
index 000000000..d6ea7b514
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Utf8.java
@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+
+class Utf8 extends Encoding {
+
+    private static final String[] LABELS = {
+        "unicode-1-1-utf-8",
+        "utf-8",
+        "utf8"
+    };
+    
+    private static final String NAME = "utf-8";
+    
+    static final Utf8 INSTANCE = new Utf8();
+    
+    private Utf8() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return Charset.forName(NAME).newDecoder();
+    }
+
+    @Override public CharsetEncoder newEncoder() {
+        return Charset.forName(NAME).newEncoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1250.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1250.java
new file mode 100644
index 000000000..0b3f50875
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1250.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1250 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u201a',
+        '\u0083',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u0088',
+        '\u2030',
+        '\u0160',
+        '\u2039',
+        '\u015a',
+        '\u0164',
+        '\u017d',
+        '\u0179',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u0098',
+        '\u2122',
+        '\u0161',
+        '\u203a',
+        '\u015b',
+        '\u0165',
+        '\u017e',
+        '\u017a',
+        '\u00a0',
+        '\u02c7',
+        '\u02d8',
+        '\u0141',
+        '\u00a4',
+        '\u0104',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u015e',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u017b',
+        '\u00b0',
+        '\u00b1',
+        '\u02db',
+        '\u0142',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u0105',
+        '\u015f',
+        '\u00bb',
+        '\u013d',
+        '\u02dd',
+        '\u013e',
+        '\u017c',
+        '\u0154',
+        '\u00c1',
+        '\u00c2',
+        '\u0102',
+        '\u00c4',
+        '\u0139',
+        '\u0106',
+        '\u00c7',
+        '\u010c',
+        '\u00c9',
+        '\u0118',
+        '\u00cb',
+        '\u011a',
+        '\u00cd',
+        '\u00ce',
+        '\u010e',
+        '\u0110',
+        '\u0143',
+        '\u0147',
+        '\u00d3',
+        '\u00d4',
+        '\u0150',
+        '\u00d6',
+        '\u00d7',
+        '\u0158',
+        '\u016e',
+        '\u00da',
+        '\u0170',
+        '\u00dc',
+        '\u00dd',
+        '\u0162',
+        '\u00df',
+        '\u0155',
+        '\u00e1',
+        '\u00e2',
+        '\u0103',
+        '\u00e4',
+        '\u013a',
+        '\u0107',
+        '\u00e7',
+        '\u010d',
+        '\u00e9',
+        '\u0119',
+        '\u00eb',
+        '\u011b',
+        '\u00ed',
+        '\u00ee',
+        '\u010f',
+        '\u0111',
+        '\u0144',
+        '\u0148',
+        '\u00f3',
+        '\u00f4',
+        '\u0151',
+        '\u00f6',
+        '\u00f7',
+        '\u0159',
+        '\u016f',
+        '\u00fa',
+        '\u0171',
+        '\u00fc',
+        '\u00fd',
+        '\u0163',
+        '\u02d9'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1250",
+        "windows-1250",
+        "x-cp1250"
+    };
+    
+    private static final String NAME = "windows-1250";
+    
+    static final Encoding INSTANCE = new Windows1250();
+    
+    private Windows1250() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1251.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1251.java
new file mode 100644
index 000000000..def5cf11e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1251.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1251 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u0402',
+        '\u0403',
+        '\u201a',
+        '\u0453',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u20ac',
+        '\u2030',
+        '\u0409',
+        '\u2039',
+        '\u040a',
+        '\u040c',
+        '\u040b',
+        '\u040f',
+        '\u0452',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u0098',
+        '\u2122',
+        '\u0459',
+        '\u203a',
+        '\u045a',
+        '\u045c',
+        '\u045b',
+        '\u045f',
+        '\u00a0',
+        '\u040e',
+        '\u045e',
+        '\u0408',
+        '\u00a4',
+        '\u0490',
+        '\u00a6',
+        '\u00a7',
+        '\u0401',
+        '\u00a9',
+        '\u0404',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u0407',
+        '\u00b0',
+        '\u00b1',
+        '\u0406',
+        '\u0456',
+        '\u0491',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u0451',
+        '\u2116',
+        '\u0454',
+        '\u00bb',
+        '\u0458',
+        '\u0405',
+        '\u0455',
+        '\u0457',
+        '\u0410',
+        '\u0411',
+        '\u0412',
+        '\u0413',
+        '\u0414',
+        '\u0415',
+        '\u0416',
+        '\u0417',
+        '\u0418',
+        '\u0419',
+        '\u041a',
+        '\u041b',
+        '\u041c',
+        '\u041d',
+        '\u041e',
+        '\u041f',
+        '\u0420',
+        '\u0421',
+        '\u0422',
+        '\u0423',
+        '\u0424',
+        '\u0425',
+        '\u0426',
+        '\u0427',
+        '\u0428',
+        '\u0429',
+        '\u042a',
+        '\u042b',
+        '\u042c',
+        '\u042d',
+        '\u042e',
+        '\u042f',
+        '\u0430',
+        '\u0431',
+        '\u0432',
+        '\u0433',
+        '\u0434',
+        '\u0435',
+        '\u0436',
+        '\u0437',
+        '\u0438',
+        '\u0439',
+        '\u043a',
+        '\u043b',
+        '\u043c',
+        '\u043d',
+        '\u043e',
+        '\u043f',
+        '\u0440',
+        '\u0441',
+        '\u0442',
+        '\u0443',
+        '\u0444',
+        '\u0445',
+        '\u0446',
+        '\u0447',
+        '\u0448',
+        '\u0449',
+        '\u044a',
+        '\u044b',
+        '\u044c',
+        '\u044d',
+        '\u044e',
+        '\u044f'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1251",
+        "windows-1251",
+        "x-cp1251"
+    };
+    
+    private static final String NAME = "windows-1251";
+    
+    static final Encoding INSTANCE = new Windows1251();
+    
+    private Windows1251() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1252.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1252.java
new file mode 100644
index 000000000..4b3fa1ffa
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1252.java
@@ -0,0 +1,197 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1252 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u201a',
+        '\u0192',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u02c6',
+        '\u2030',
+        '\u0160',
+        '\u2039',
+        '\u0152',
+        '\u008d',
+        '\u017d',
+        '\u008f',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u02dc',
+        '\u2122',
+        '\u0161',
+        '\u203a',
+        '\u0153',
+        '\u009d',
+        '\u017e',
+        '\u0178',
+        '\u00a0',
+        '\u00a1',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u00aa',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u00b9',
+        '\u00ba',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\u00bf',
+        '\u00c0',
+        '\u00c1',
+        '\u00c2',
+        '\u00c3',
+        '\u00c4',
+        '\u00c5',
+        '\u00c6',
+        '\u00c7',
+        '\u00c8',
+        '\u00c9',
+        '\u00ca',
+        '\u00cb',
+        '\u00cc',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u00d0',
+        '\u00d1',
+        '\u00d2',
+        '\u00d3',
+        '\u00d4',
+        '\u00d5',
+        '\u00d6',
+        '\u00d7',
+        '\u00d8',
+        '\u00d9',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u00dd',
+        '\u00de',
+        '\u00df',
+        '\u00e0',
+        '\u00e1',
+        '\u00e2',
+        '\u00e3',
+        '\u00e4',
+        '\u00e5',
+        '\u00e6',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u00ec',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\u00f0',
+        '\u00f1',
+        '\u00f2',
+        '\u00f3',
+        '\u00f4',
+        '\u00f5',
+        '\u00f6',
+        '\u00f7',
+        '\u00f8',
+        '\u00f9',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u00fd',
+        '\u00fe',
+        '\u00ff'
+    };
+    
+    private static final String[] LABELS = {
+        "ansi_x3.4-1968",
+        "ascii",
+        "cp1252",
+        "cp819",
+        "csisolatin1",
+        "ibm819",
+        "iso-8859-1",
+        "iso-ir-100",
+        "iso8859-1",
+        "iso88591",
+        "iso_8859-1",
+        "iso_8859-1:1987",
+        "l1",
+        "latin1",
+        "us-ascii",
+        "windows-1252",
+        "x-cp1252"
+    };
+    
+    private static final String NAME = "windows-1252";
+    
+    static final Encoding INSTANCE = new Windows1252();
+    
+    private Windows1252() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1253.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1253.java
new file mode 100644
index 000000000..c96e8630c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1253.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1253 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u201a',
+        '\u0192',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u0088',
+        '\u2030',
+        '\u008a',
+        '\u2039',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u0098',
+        '\u2122',
+        '\u009a',
+        '\u203a',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0385',
+        '\u0386',
+        '\u00a3',
+        '\u00a4',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\ufffd',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u2015',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u0384',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u0388',
+        '\u0389',
+        '\u038a',
+        '\u00bb',
+        '\u038c',
+        '\u00bd',
+        '\u038e',
+        '\u038f',
+        '\u0390',
+        '\u0391',
+        '\u0392',
+        '\u0393',
+        '\u0394',
+        '\u0395',
+        '\u0396',
+        '\u0397',
+        '\u0398',
+        '\u0399',
+        '\u039a',
+        '\u039b',
+        '\u039c',
+        '\u039d',
+        '\u039e',
+        '\u039f',
+        '\u03a0',
+        '\u03a1',
+        '\ufffd',
+        '\u03a3',
+        '\u03a4',
+        '\u03a5',
+        '\u03a6',
+        '\u03a7',
+        '\u03a8',
+        '\u03a9',
+        '\u03aa',
+        '\u03ab',
+        '\u03ac',
+        '\u03ad',
+        '\u03ae',
+        '\u03af',
+        '\u03b0',
+        '\u03b1',
+        '\u03b2',
+        '\u03b3',
+        '\u03b4',
+        '\u03b5',
+        '\u03b6',
+        '\u03b7',
+        '\u03b8',
+        '\u03b9',
+        '\u03ba',
+        '\u03bb',
+        '\u03bc',
+        '\u03bd',
+        '\u03be',
+        '\u03bf',
+        '\u03c0',
+        '\u03c1',
+        '\u03c2',
+        '\u03c3',
+        '\u03c4',
+        '\u03c5',
+        '\u03c6',
+        '\u03c7',
+        '\u03c8',
+        '\u03c9',
+        '\u03ca',
+        '\u03cb',
+        '\u03cc',
+        '\u03cd',
+        '\u03ce',
+        '\ufffd'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1253",
+        "windows-1253",
+        "x-cp1253"
+    };
+    
+    private static final String NAME = "windows-1253";
+    
+    static final Encoding INSTANCE = new Windows1253();
+    
+    private Windows1253() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1254.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1254.java
new file mode 100644
index 000000000..fc3aa9839
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1254.java
@@ -0,0 +1,192 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1254 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u201a',
+        '\u0192',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u02c6',
+        '\u2030',
+        '\u0160',
+        '\u2039',
+        '\u0152',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u02dc',
+        '\u2122',
+        '\u0161',
+        '\u203a',
+        '\u0153',
+        '\u009d',
+        '\u009e',
+        '\u0178',
+        '\u00a0',
+        '\u00a1',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u00aa',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u00b9',
+        '\u00ba',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\u00bf',
+        '\u00c0',
+        '\u00c1',
+        '\u00c2',
+        '\u00c3',
+        '\u00c4',
+        '\u00c5',
+        '\u00c6',
+        '\u00c7',
+        '\u00c8',
+        '\u00c9',
+        '\u00ca',
+        '\u00cb',
+        '\u00cc',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u011e',
+        '\u00d1',
+        '\u00d2',
+        '\u00d3',
+        '\u00d4',
+        '\u00d5',
+        '\u00d6',
+        '\u00d7',
+        '\u00d8',
+        '\u00d9',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u0130',
+        '\u015e',
+        '\u00df',
+        '\u00e0',
+        '\u00e1',
+        '\u00e2',
+        '\u00e3',
+        '\u00e4',
+        '\u00e5',
+        '\u00e6',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u00ec',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\u011f',
+        '\u00f1',
+        '\u00f2',
+        '\u00f3',
+        '\u00f4',
+        '\u00f5',
+        '\u00f6',
+        '\u00f7',
+        '\u00f8',
+        '\u00f9',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u0131',
+        '\u015f',
+        '\u00ff'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1254",
+        "csisolatin5",
+        "iso-8859-9",
+        "iso-ir-148",
+        "iso8859-9",
+        "iso88599",
+        "iso_8859-9",
+        "iso_8859-9:1989",
+        "l5",
+        "latin5",
+        "windows-1254",
+        "x-cp1254"
+    };
+    
+    private static final String NAME = "windows-1254";
+    
+    static final Encoding INSTANCE = new Windows1254();
+    
+    private Windows1254() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1255.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1255.java
new file mode 100644
index 000000000..957203d80
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1255.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1255 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u201a',
+        '\u0192',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u02c6',
+        '\u2030',
+        '\u008a',
+        '\u2039',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u02dc',
+        '\u2122',
+        '\u009a',
+        '\u203a',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u00a1',
+        '\u00a2',
+        '\u00a3',
+        '\u20aa',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u00d7',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u00b9',
+        '\u00f7',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\u00bf',
+        '\u05b0',
+        '\u05b1',
+        '\u05b2',
+        '\u05b3',
+        '\u05b4',
+        '\u05b5',
+        '\u05b6',
+        '\u05b7',
+        '\u05b8',
+        '\u05b9',
+        '\ufffd',
+        '\u05bb',
+        '\u05bc',
+        '\u05bd',
+        '\u05be',
+        '\u05bf',
+        '\u05c0',
+        '\u05c1',
+        '\u05c2',
+        '\u05c3',
+        '\u05f0',
+        '\u05f1',
+        '\u05f2',
+        '\u05f3',
+        '\u05f4',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u05d0',
+        '\u05d1',
+        '\u05d2',
+        '\u05d3',
+        '\u05d4',
+        '\u05d5',
+        '\u05d6',
+        '\u05d7',
+        '\u05d8',
+        '\u05d9',
+        '\u05da',
+        '\u05db',
+        '\u05dc',
+        '\u05dd',
+        '\u05de',
+        '\u05df',
+        '\u05e0',
+        '\u05e1',
+        '\u05e2',
+        '\u05e3',
+        '\u05e4',
+        '\u05e5',
+        '\u05e6',
+        '\u05e7',
+        '\u05e8',
+        '\u05e9',
+        '\u05ea',
+        '\ufffd',
+        '\ufffd',
+        '\u200e',
+        '\u200f',
+        '\ufffd'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1255",
+        "windows-1255",
+        "x-cp1255"
+    };
+    
+    private static final String NAME = "windows-1255";
+    
+    static final Encoding INSTANCE = new Windows1255();
+    
+    private Windows1255() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1256.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1256.java
new file mode 100644
index 000000000..87d805e1e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1256.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1256 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u067e',
+        '\u201a',
+        '\u0192',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u02c6',
+        '\u2030',
+        '\u0679',
+        '\u2039',
+        '\u0152',
+        '\u0686',
+        '\u0698',
+        '\u0688',
+        '\u06af',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u06a9',
+        '\u2122',
+        '\u0691',
+        '\u203a',
+        '\u0153',
+        '\u200c',
+        '\u200d',
+        '\u06ba',
+        '\u00a0',
+        '\u060c',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u06be',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u00b9',
+        '\u061b',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\u061f',
+        '\u06c1',
+        '\u0621',
+        '\u0622',
+        '\u0623',
+        '\u0624',
+        '\u0625',
+        '\u0626',
+        '\u0627',
+        '\u0628',
+        '\u0629',
+        '\u062a',
+        '\u062b',
+        '\u062c',
+        '\u062d',
+        '\u062e',
+        '\u062f',
+        '\u0630',
+        '\u0631',
+        '\u0632',
+        '\u0633',
+        '\u0634',
+        '\u0635',
+        '\u0636',
+        '\u00d7',
+        '\u0637',
+        '\u0638',
+        '\u0639',
+        '\u063a',
+        '\u0640',
+        '\u0641',
+        '\u0642',
+        '\u0643',
+        '\u00e0',
+        '\u0644',
+        '\u00e2',
+        '\u0645',
+        '\u0646',
+        '\u0647',
+        '\u0648',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u0649',
+        '\u064a',
+        '\u00ee',
+        '\u00ef',
+        '\u064b',
+        '\u064c',
+        '\u064d',
+        '\u064e',
+        '\u00f4',
+        '\u064f',
+        '\u0650',
+        '\u00f7',
+        '\u0651',
+        '\u00f9',
+        '\u0652',
+        '\u00fb',
+        '\u00fc',
+        '\u200e',
+        '\u200f',
+        '\u06d2'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1256",
+        "windows-1256",
+        "x-cp1256"
+    };
+    
+    private static final String NAME = "windows-1256";
+    
+    static final Encoding INSTANCE = new Windows1256();
+    
+    private Windows1256() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1257.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1257.java
new file mode 100644
index 000000000..140e9b458
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1257.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1257 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u201a',
+        '\u0083',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u0088',
+        '\u2030',
+        '\u008a',
+        '\u2039',
+        '\u008c',
+        '\u00a8',
+        '\u02c7',
+        '\u00b8',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u0098',
+        '\u2122',
+        '\u009a',
+        '\u203a',
+        '\u009c',
+        '\u00af',
+        '\u02db',
+        '\u009f',
+        '\u00a0',
+        '\ufffd',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\ufffd',
+        '\u00a6',
+        '\u00a7',
+        '\u00d8',
+        '\u00a9',
+        '\u0156',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00c6',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00f8',
+        '\u00b9',
+        '\u0157',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\u00e6',
+        '\u0104',
+        '\u012e',
+        '\u0100',
+        '\u0106',
+        '\u00c4',
+        '\u00c5',
+        '\u0118',
+        '\u0112',
+        '\u010c',
+        '\u00c9',
+        '\u0179',
+        '\u0116',
+        '\u0122',
+        '\u0136',
+        '\u012a',
+        '\u013b',
+        '\u0160',
+        '\u0143',
+        '\u0145',
+        '\u00d3',
+        '\u014c',
+        '\u00d5',
+        '\u00d6',
+        '\u00d7',
+        '\u0172',
+        '\u0141',
+        '\u015a',
+        '\u016a',
+        '\u00dc',
+        '\u017b',
+        '\u017d',
+        '\u00df',
+        '\u0105',
+        '\u012f',
+        '\u0101',
+        '\u0107',
+        '\u00e4',
+        '\u00e5',
+        '\u0119',
+        '\u0113',
+        '\u010d',
+        '\u00e9',
+        '\u017a',
+        '\u0117',
+        '\u0123',
+        '\u0137',
+        '\u012b',
+        '\u013c',
+        '\u0161',
+        '\u0144',
+        '\u0146',
+        '\u00f3',
+        '\u014d',
+        '\u00f5',
+        '\u00f6',
+        '\u00f7',
+        '\u0173',
+        '\u0142',
+        '\u015b',
+        '\u016b',
+        '\u00fc',
+        '\u017c',
+        '\u017e',
+        '\u02d9'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1257",
+        "windows-1257",
+        "x-cp1257"
+    };
+    
+    private static final String NAME = "windows-1257";
+    
+    static final Encoding INSTANCE = new Windows1257();
+    
+    private Windows1257() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1258.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1258.java
new file mode 100644
index 000000000..130107789
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows1258.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows1258 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u201a',
+        '\u0192',
+        '\u201e',
+        '\u2026',
+        '\u2020',
+        '\u2021',
+        '\u02c6',
+        '\u2030',
+        '\u008a',
+        '\u2039',
+        '\u0152',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u02dc',
+        '\u2122',
+        '\u009a',
+        '\u203a',
+        '\u0153',
+        '\u009d',
+        '\u009e',
+        '\u0178',
+        '\u00a0',
+        '\u00a1',
+        '\u00a2',
+        '\u00a3',
+        '\u00a4',
+        '\u00a5',
+        '\u00a6',
+        '\u00a7',
+        '\u00a8',
+        '\u00a9',
+        '\u00aa',
+        '\u00ab',
+        '\u00ac',
+        '\u00ad',
+        '\u00ae',
+        '\u00af',
+        '\u00b0',
+        '\u00b1',
+        '\u00b2',
+        '\u00b3',
+        '\u00b4',
+        '\u00b5',
+        '\u00b6',
+        '\u00b7',
+        '\u00b8',
+        '\u00b9',
+        '\u00ba',
+        '\u00bb',
+        '\u00bc',
+        '\u00bd',
+        '\u00be',
+        '\u00bf',
+        '\u00c0',
+        '\u00c1',
+        '\u00c2',
+        '\u0102',
+        '\u00c4',
+        '\u00c5',
+        '\u00c6',
+        '\u00c7',
+        '\u00c8',
+        '\u00c9',
+        '\u00ca',
+        '\u00cb',
+        '\u0300',
+        '\u00cd',
+        '\u00ce',
+        '\u00cf',
+        '\u0110',
+        '\u00d1',
+        '\u0309',
+        '\u00d3',
+        '\u00d4',
+        '\u01a0',
+        '\u00d6',
+        '\u00d7',
+        '\u00d8',
+        '\u00d9',
+        '\u00da',
+        '\u00db',
+        '\u00dc',
+        '\u01af',
+        '\u0303',
+        '\u00df',
+        '\u00e0',
+        '\u00e1',
+        '\u00e2',
+        '\u0103',
+        '\u00e4',
+        '\u00e5',
+        '\u00e6',
+        '\u00e7',
+        '\u00e8',
+        '\u00e9',
+        '\u00ea',
+        '\u00eb',
+        '\u0301',
+        '\u00ed',
+        '\u00ee',
+        '\u00ef',
+        '\u0111',
+        '\u00f1',
+        '\u0323',
+        '\u00f3',
+        '\u00f4',
+        '\u01a1',
+        '\u00f6',
+        '\u00f7',
+        '\u00f8',
+        '\u00f9',
+        '\u00fa',
+        '\u00fb',
+        '\u00fc',
+        '\u01b0',
+        '\u20ab',
+        '\u00ff'
+    };
+    
+    private static final String[] LABELS = {
+        "cp1258",
+        "windows-1258",
+        "x-cp1258"
+    };
+    
+    private static final String NAME = "windows-1258";
+    
+    static final Encoding INSTANCE = new Windows1258();
+    
+    private Windows1258() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new InfallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/encoding/Windows874.java b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows874.java
new file mode 100644
index 000000000..f93be0175
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/encoding/Windows874.java
@@ -0,0 +1,186 @@
+/*
+ * Copyright (c) 2013-2015 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * THIS IS A GENERATED FILE. PLEASE DO NOT EDIT.
+ * Instead, please regenerate using generate-encoding-data.py
+ */
+
+package nu.validator.encoding;
+
+import java.nio.charset.CharsetDecoder;
+
+class Windows874 extends Encoding {
+
+    private static final char[] TABLE = {
+        '\u20ac',
+        '\u0081',
+        '\u0082',
+        '\u0083',
+        '\u0084',
+        '\u2026',
+        '\u0086',
+        '\u0087',
+        '\u0088',
+        '\u0089',
+        '\u008a',
+        '\u008b',
+        '\u008c',
+        '\u008d',
+        '\u008e',
+        '\u008f',
+        '\u0090',
+        '\u2018',
+        '\u2019',
+        '\u201c',
+        '\u201d',
+        '\u2022',
+        '\u2013',
+        '\u2014',
+        '\u0098',
+        '\u0099',
+        '\u009a',
+        '\u009b',
+        '\u009c',
+        '\u009d',
+        '\u009e',
+        '\u009f',
+        '\u00a0',
+        '\u0e01',
+        '\u0e02',
+        '\u0e03',
+        '\u0e04',
+        '\u0e05',
+        '\u0e06',
+        '\u0e07',
+        '\u0e08',
+        '\u0e09',
+        '\u0e0a',
+        '\u0e0b',
+        '\u0e0c',
+        '\u0e0d',
+        '\u0e0e',
+        '\u0e0f',
+        '\u0e10',
+        '\u0e11',
+        '\u0e12',
+        '\u0e13',
+        '\u0e14',
+        '\u0e15',
+        '\u0e16',
+        '\u0e17',
+        '\u0e18',
+        '\u0e19',
+        '\u0e1a',
+        '\u0e1b',
+        '\u0e1c',
+        '\u0e1d',
+        '\u0e1e',
+        '\u0e1f',
+        '\u0e20',
+        '\u0e21',
+        '\u0e22',
+        '\u0e23',
+        '\u0e24',
+        '\u0e25',
+        '\u0e26',
+        '\u0e27',
+        '\u0e28',
+        '\u0e29',
+        '\u0e2a',
+        '\u0e2b',
+        '\u0e2c',
+        '\u0e2d',
+        '\u0e2e',
+        '\u0e2f',
+        '\u0e30',
+        '\u0e31',
+        '\u0e32',
+        '\u0e33',
+        '\u0e34',
+        '\u0e35',
+        '\u0e36',
+        '\u0e37',
+        '\u0e38',
+        '\u0e39',
+        '\u0e3a',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\u0e3f',
+        '\u0e40',
+        '\u0e41',
+        '\u0e42',
+        '\u0e43',
+        '\u0e44',
+        '\u0e45',
+        '\u0e46',
+        '\u0e47',
+        '\u0e48',
+        '\u0e49',
+        '\u0e4a',
+        '\u0e4b',
+        '\u0e4c',
+        '\u0e4d',
+        '\u0e4e',
+        '\u0e4f',
+        '\u0e50',
+        '\u0e51',
+        '\u0e52',
+        '\u0e53',
+        '\u0e54',
+        '\u0e55',
+        '\u0e56',
+        '\u0e57',
+        '\u0e58',
+        '\u0e59',
+        '\u0e5a',
+        '\u0e5b',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd',
+        '\ufffd'
+    };
+    
+    private static final String[] LABELS = {
+        "dos-874",
+        "iso-8859-11",
+        "iso8859-11",
+        "iso885911",
+        "tis-620",
+        "windows-874"
+    };
+    
+    private static final String NAME = "windows-874";
+    
+    static final Encoding INSTANCE = new Windows874();
+    
+    private Windows874() {
+        super(NAME, LABELS);
+    }
+
+    @Override public CharsetDecoder newDecoder() {
+        return new FallibleSingleByteDecoder(this, TABLE);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Auto.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Auto.java
new file mode 100644
index 000000000..0967a5814
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Auto.java
@@ -0,0 +1,27 @@
+/*
+ * Copyright (c) 2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+public @interface Auto {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/CharacterName.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/CharacterName.java
new file mode 100644
index 000000000..bcb8a2b00
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/CharacterName.java
@@ -0,0 +1,27 @@
+/*
+ * Copyright (c) 2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+public @interface CharacterName {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Const.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Const.java
new file mode 100644
index 000000000..2ba7f418a
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Const.java
@@ -0,0 +1,34 @@
+/*
+ * Copyright (c) 2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * Marker for translating into the C++ const keyword on the declaration in 
+ * question.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface Const {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/IdType.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/IdType.java
new file mode 100644
index 000000000..117da8d3c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/IdType.java
@@ -0,0 +1,34 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * The type for attribute IDness. (In Java, an interned string
+ * <code>"CDATA"</code> or <code>"ID"</code>.)
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface IdType {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Inline.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Inline.java
new file mode 100644
index 000000000..cc0728b1b
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Inline.java
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2009-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * Translates into the C++ inline keyword.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface Inline {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Literal.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Literal.java
new file mode 100644
index 000000000..44444d525
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Literal.java
@@ -0,0 +1,34 @@
+/*
+ * Copyright (c) 2009-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * Marks a string type as being the literal string type (typically const char*)
+ * in C++.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface Literal {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Local.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Local.java
new file mode 100644
index 000000000..1f91ba93b
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Local.java
@@ -0,0 +1,34 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * The local name of an element or attribute. Must be comparable with
+ * <code>==</code> (interned <code>String</code> in Java).
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface Local {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/NoLength.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/NoLength.java
new file mode 100644
index 000000000..cf011d33e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/NoLength.java
@@ -0,0 +1,34 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * The array type marked with this annotation won't have its
+ * <code>.length</code> read.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface NoLength {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/NsUri.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/NsUri.java
new file mode 100644
index 000000000..03baa75f5
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/NsUri.java
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * The namespace URI type. (In Java, an interned <code>String</code>.)
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface NsUri {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Prefix.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Prefix.java
new file mode 100644
index 000000000..268e531a3
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Prefix.java
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * The type for namespace prefixes. (In Java, an interned <code>String</code>.)
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface Prefix {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/QName.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/QName.java
new file mode 100644
index 000000000..e6d4807b6
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/QName.java
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * The type for qualified names. (In Java, an interned <code>String</code>.)
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface QName {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Virtual.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Virtual.java
new file mode 100644
index 000000000..e293e1af5
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/Virtual.java
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.annotation;
+
+/**
+ * Marks a method as virtualy in C++.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public @interface Virtual {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/package.html b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/package.html
new file mode 100644
index 000000000..af15d3827
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/annotation/package.html
@@ -0,0 +1,30 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
+<html>
+<head><title>Package Overview</title>
+<!--
+ Copyright (c) 2008 Mozilla Foundation
+
+ Permission is hereby granted, free of charge, to any person obtaining a 
+ copy of this software and associated documentation files (the "Software"), 
+ to deal in the Software without restriction, including without limitation 
+ the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ and/or sell copies of the Software, and to permit persons to whom the 
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in 
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ DEALINGS IN THE SOFTWARE.
+-->
+</head>
+<body bgcolor="white">
+<p>This package provides annotations for facilitating automated translation 
+of the source code into other programming languages.</p>
+</body>
+</html>
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/ByteReadable.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/ByteReadable.java
new file mode 100644
index 000000000..f3b3e74ca
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/ByteReadable.java
@@ -0,0 +1,44 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+import java.io.IOException;
+
+/**
+ * An interface for providing a method for reading a stream of bytes one byte at
+ * a time.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface ByteReadable {
+    /**
+     * Returns the value of the next byte as an integer from 0 to 0xFF or -1 if
+     * the stream has ended.
+     * 
+     * @return integer from 0 to 0xFF or -1 on EOF
+     * @throws IOException
+     */
+    public int readByte() throws IOException;
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/CharacterHandler.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/CharacterHandler.java
new file mode 100644
index 000000000..4a5769f54
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/CharacterHandler.java
@@ -0,0 +1,59 @@
+/*
+ * Copyright (c) 2007-2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+import org.xml.sax.SAXException;
+
+/**
+ * An interface for receiving notifications of UTF-16 code units read from a character stream.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface CharacterHandler {
+
+    /**
+     * Receive notification of a run of UTF-16 code units.
+     * @param ch the buffer
+     * @param start start index in the buffer
+     * @param length the number of characters to process starting from <code>start</code>
+     * @throws SAXException if things go wrong
+     */
+    public void characters(char[] ch, int start, int length)
+            throws SAXException;
+
+    /**
+     * Signals the end of the stream. Can be used for cleanup. Doesn't mean that the stream ended successfully.
+     * 
+     * @throws SAXException if things go wrong
+     */
+    public void end() throws SAXException;
+
+    /**
+     * Signals the start of the stream. Can be used for setup.
+     * 
+     * @throws SAXException if things go wrong
+     */
+    public void start() throws SAXException;
+
+}
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DoctypeExpectation.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DoctypeExpectation.java
new file mode 100644
index 000000000..a34af51fa
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DoctypeExpectation.java
@@ -0,0 +1,65 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+/**
+ * Used for indicating desired behavior with legacy doctypes.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public enum DoctypeExpectation {
+    /**
+     * Be a pure HTML5 parser.
+     */
+    HTML,
+    
+    /**
+     * Require the HTML 4.01 Transitional public id. Turn on HTML4-specific
+     * additional errors regardless of doctype.
+     */
+    HTML401_TRANSITIONAL,
+    
+    /**
+     * Require the HTML 4.01 Transitional public id and a system id. Turn on
+     * HTML4-specific additional errors regardless of doctype.
+     */
+    HTML401_STRICT,
+    
+    /**
+     * Treat the doctype required by HTML 5, doctypes with the HTML 4.01 Strict 
+     * public id and doctypes with the HTML 4.01 Transitional public id and a 
+     * system id as non-errors. Turn on HTML4-specific additional errors if the 
+     * public id is the HTML 4.01 Strict or Transitional public id.
+     */
+    AUTO,
+    
+    /**
+     * Never enable HTML4-specific error checks. Never report any doctype 
+     * condition as an error. (Doctype tokens in wrong places will be 
+     * reported as errors, though.) The application may decide what to log 
+     * in response to calls to <code>DocumentModeHanler</code>. This mode 
+     * in meant for doing surveys on existing content.
+     */
+    NO_DOCTYPE_ERRORS
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DocumentMode.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DocumentMode.java
new file mode 100644
index 000000000..e30eddd87
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DocumentMode.java
@@ -0,0 +1,47 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+/**
+ * Represents the HTML document compatibility mode.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public enum DocumentMode {
+    /**
+     * The Standards Mode
+     */
+    STANDARDS_MODE,
+
+    /**
+     * The Limited Quirks Mode aka. The Almost Standards Mode
+     */
+    ALMOST_STANDARDS_MODE,
+
+    /**
+     * The Quirks Mode
+     */
+    QUIRKS_MODE
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DocumentModeHandler.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DocumentModeHandler.java
new file mode 100644
index 000000000..55377e0e4
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/DocumentModeHandler.java
@@ -0,0 +1,46 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+
+import org.xml.sax.SAXException;
+
+/**
+ * A callback interface for receiving notification about the document mode.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface DocumentModeHandler {
+    
+    /**
+     * Receive notification of the document mode.
+     * 
+     * @param mode the document mode
+     * @param publicIdentifier the public id of the doctype or <code>null</code> if unavailable
+     * @param systemIdentifier the system id of the doctype or <code>null</code> if unavailable
+     * @param html4SpecificAdditionalErrorChecks <code>true</code> if HTML 4-specific checks were enabled, <code>false</code> otherwise
+     * @throws SAXException if things go wrong
+     */
+    public void documentMode(DocumentMode mode, String publicIdentifier, String systemIdentifier, boolean html4SpecificAdditionalErrorChecks) throws SAXException;
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/EncodingDeclarationHandler.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/EncodingDeclarationHandler.java
new file mode 100644
index 000000000..6f185aeaf
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/EncodingDeclarationHandler.java
@@ -0,0 +1,58 @@
+/*
+ * Copyright (c) 2008-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+import org.xml.sax.SAXException;
+
+/**
+ * An interface for communicating about character encoding names with the
+ * environment of the parser.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface EncodingDeclarationHandler {
+
+    /**
+     * Indicates that the parser has found an internal encoding declaration with
+     * the charset value <code>charset</code>.
+     * 
+     * @param charset
+     *            the charset name found.
+     * @return <code>true</code> if the value of <code>charset</code> was an 
+     * encoding name for a supported ASCII-superset encoding.
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public boolean internalEncodingDeclaration(String charset) throws SAXException;
+
+    /**
+     * Queries the environment for the encoding in use (for error reporting).
+     * 
+     * @return the encoding in use
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public String getCharacterEncoding() throws SAXException;
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/Heuristics.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/Heuristics.java
new file mode 100644
index 000000000..40f15ce7d
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/Heuristics.java
@@ -0,0 +1,52 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+/**
+ * Indicates a request for character encoding sniffer choice.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public enum Heuristics {
+    
+    /**
+     * Perform no heuristic sniffing.
+     */
+    NONE,
+    
+    /**
+     * Use both jchardet and ICU4J.
+     */
+    ALL,
+    
+    /**
+     * Use jchardet only.
+     */
+    CHARDET,
+    
+    /**
+     * Use ICU4J only.
+     */
+    ICU
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/Interner.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/Interner.java
new file mode 100644
index 000000000..deab4c60f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/Interner.java
@@ -0,0 +1,35 @@
+/*
+ * Copyright (c) 2009-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+/**
+ * A placeholder type that translates into the type of the C++ class that
+ * implements an interning service for local names (<code>@Local</code> in
+ * Java).
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface Interner {
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/TokenHandler.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/TokenHandler.java
new file mode 100644
index 000000000..18f49e99d
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/TokenHandler.java
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+import nu.validator.htmlparser.annotation.Const;
+import nu.validator.htmlparser.annotation.NoLength;
+import nu.validator.htmlparser.impl.ElementName;
+import nu.validator.htmlparser.impl.HtmlAttributes;
+import nu.validator.htmlparser.impl.Tokenizer;
+
+import org.xml.sax.SAXException;
+
+/**
+ * <code>Tokenizer</code> reports tokens through this interface.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface TokenHandler {
+
+    /**
+     * This method is called at the start of tokenization before any other
+     * methods on this interface are called. Implementations should hold the
+     * reference to the <code>Tokenizer</code> in order to set the content
+     * model flag and in order to be able to query for <code>Locator</code>
+     * data.
+     * 
+     * @param self
+     *            the <code>Tokenizer</code>.
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void startTokenization(Tokenizer self) throws SAXException;
+
+    /**
+     * If this handler implementation cares about comments, return
+     * <code>true</code>. If not, return <code>false</code>.
+     * 
+     * @return whether this handler wants comments
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public boolean wantsComments() throws SAXException;
+
+    /**
+     * Receive a doctype token.
+     * 
+     * @param name
+     *            the name
+     * @param publicIdentifier
+     *            the public id
+     * @param systemIdentifier
+     *            the system id
+     * @param forceQuirks
+     *            whether the token is correct
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void doctype(String name, String publicIdentifier,
+            String systemIdentifier, boolean forceQuirks) throws SAXException;
+
+    /**
+     * Receive a start tag token.
+     * 
+     * @param eltName
+     *            the tag name
+     * @param attributes
+     *            the attributes
+     * @param selfClosing
+     *            TODO
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void startTag(ElementName eltName, HtmlAttributes attributes,
+            boolean selfClosing) throws SAXException;
+
+    /**
+     * Receive an end tag token.
+     * 
+     * @param eltName
+     *            the tag name
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void endTag(ElementName eltName) throws SAXException;
+
+    /**
+     * Receive a comment token. The data is junk if the
+     * <code>wantsComments()</code> returned <code>false</code>.
+     * 
+     * @param buf
+     *            a buffer holding the data
+     * @param start the offset into the buffer
+     * @param length
+     *            the number of code units to read
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void comment(@NoLength char[] buf, int start, int length) throws SAXException;
+
+    /**
+     * Receive character tokens. This method has the same semantics as the SAX
+     * method of the same name.
+     * 
+     * @param buf
+     *            a buffer holding the data
+     * @param start
+     *            offset into the buffer
+     * @param length
+     *            the number of code units to read
+     * @throws SAXException
+     *             if something went wrong
+     * @see org.xml.sax.ContentHandler#characters(char[], int, int)
+     */
+    public void characters(@Const @NoLength char[] buf, int start, int length)
+            throws SAXException;
+
+    /**
+     * Reports a U+0000 that's being turned into a U+FFFD.
+     * 
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void zeroOriginatingReplacementCharacter() throws SAXException;
+    
+    /**
+     * The end-of-file token.
+     * 
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void eof() throws SAXException;
+
+    /**
+     * The perform final cleanup.
+     * 
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public void endTokenization() throws SAXException;
+
+    /**
+     * Checks if the CDATA sections are allowed.
+     * 
+     * @return <code>true</code> if CDATA sections are allowed
+     * @throws SAXException
+     *             if something went wrong
+     */
+    public boolean cdataSectionAllowed() throws SAXException;
+
+    /**
+     * Notifies the token handler of the worst case amount of data to be
+     * reported via <code>characters()</code> and
+     * <code>zeroOriginatingReplacementCharacter()</code>.
+     *
+     * @param inputLength the maximum number of chars that can be reported
+     * via <code>characters()</code> and
+     * <code>zeroOriginatingReplacementCharacter()</code> before a new call to
+     * this method.
+     */
+    public void ensureBufferSpace(int inputLength) throws SAXException;
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/TransitionHandler.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/TransitionHandler.java
new file mode 100644
index 000000000..eec23c71c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/TransitionHandler.java
@@ -0,0 +1,53 @@
+/*
+ * Copyright (c) 2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+import org.xml.sax.SAXException;
+
+/**
+ * An interface for intercepting information about the state transitions that
+ * the tokenizer is making.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface TransitionHandler {
+
+    /**
+     * This method is called for every tokenizer state transition.
+     * 
+     * @param from
+     *            the state the tokenizer is transitioning from
+     * @param to
+     *            the state being transitioned to
+     * @param reconsume
+     *            <code>true</code> if the current input character is going to
+     *            be reconsumed in the new state
+     * @param pos
+     *            the current index into the input stream
+     * @throws SAXException
+     *             if something went wrong
+     */
+    void transition(int from, int to, boolean reconsume, int pos)
+            throws SAXException;
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/XmlViolationPolicy.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/XmlViolationPolicy.java
new file mode 100644
index 000000000..c959df655
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/XmlViolationPolicy.java
@@ -0,0 +1,48 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.common;
+
+/**
+ * Policy for XML 1.0 violations.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public enum XmlViolationPolicy {
+    /**
+     * Conform to HTML 5, allow XML 1.0 to be violated.
+     */
+    ALLOW,
+    
+    /**
+     * Halt when something cannot be mapped to XML 1.0.
+     */
+    FATAL,
+    
+    /**
+     * Be non-conforming and alter the infoset to fit 
+     * XML 1.0 when something would otherwise not be 
+     * mappable to XML 1.0.
+     */
+    ALTER_INFOSET
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/package.html b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/package.html
new file mode 100644
index 000000000..43f141cd8
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/common/package.html
@@ -0,0 +1,29 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
+<html>
+<head><title>Package Overview</title>
+<!--
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a 
+ copy of this software and associated documentation files (the "Software"), 
+ to deal in the Software without restriction, including without limitation 
+ the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ and/or sell copies of the Software, and to permit persons to whom the 
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in 
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ DEALINGS IN THE SOFTWARE.
+-->
+</head>
+<body bgcolor="white">
+<p>This package provides common interfaces and enumerations.</p>
+</body>
+</html>
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/DOMTreeBuilder.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/DOMTreeBuilder.java
new file mode 100644
index 000000000..2b8eff230
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/DOMTreeBuilder.java
@@ -0,0 +1,357 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.dom;
+
+import nu.validator.htmlparser.common.DocumentMode;
+import nu.validator.htmlparser.impl.CoalescingTreeBuilder;
+import nu.validator.htmlparser.impl.HtmlAttributes;
+
+import org.w3c.dom.DOMException;
+import org.w3c.dom.DOMImplementation;
+import org.w3c.dom.Document;
+import org.w3c.dom.DocumentFragment;
+import org.w3c.dom.Element;
+import org.w3c.dom.Node;
+import org.w3c.dom.Text;
+import org.xml.sax.SAXException;
+
+/**
+ * The tree builder glue for building a tree through the public DOM APIs.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+class DOMTreeBuilder extends CoalescingTreeBuilder<Element> {
+
+    /**
+     * The DOM impl.
+     */
+    private DOMImplementation implementation;
+
+    /**
+     * The current doc.
+     */
+    private Document document;
+
+    /**
+     * The constructor.
+     * 
+     * @param implementation
+     *            the DOM impl.
+     */
+    protected DOMTreeBuilder(DOMImplementation implementation) {
+        super();
+        this.implementation = implementation;
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#addAttributesToElement(java.lang.Object,
+     *      nu.validator.htmlparser.impl.HtmlAttributes)
+     */
+    @Override protected void addAttributesToElement(Element element,
+            HtmlAttributes attributes) throws SAXException {
+        try {
+            for (int i = 0; i < attributes.getLength(); i++) {
+                String localName = attributes.getLocalNameNoBoundsCheck(i);
+                String uri = attributes.getURINoBoundsCheck(i);
+                if (!element.hasAttributeNS(uri, localName)) {
+                    element.setAttributeNS(uri, localName,
+                            attributes.getValueNoBoundsCheck(i));
+                }
+            }
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.CoalescingTreeBuilder#appendCharacters(java.lang.Object,
+     *      java.lang.String)
+     */
+    @Override protected void appendCharacters(Element parent, String text)
+            throws SAXException {
+        try {
+            Node lastChild = parent.getLastChild();
+            if (lastChild != null && lastChild.getNodeType() == Node.TEXT_NODE) {
+                Text lastAsText = (Text) lastChild;
+                lastAsText.setData(lastAsText.getData() + text);
+                return;
+            }
+            parent.appendChild(document.createTextNode(text));
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendChildrenToNewParent(java.lang.Object,
+     *      java.lang.Object)
+     */
+    @Override protected void appendChildrenToNewParent(Element oldParent,
+            Element newParent) throws SAXException {
+        try {
+            while (oldParent.hasChildNodes()) {
+                newParent.appendChild(oldParent.getFirstChild());
+            }
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.CoalescingTreeBuilder#appendComment(java.lang.Object,
+     *      java.lang.String)
+     */
+    @Override protected void appendComment(Element parent, String comment)
+            throws SAXException {
+        try {
+            parent.appendChild(document.createComment(comment));
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.CoalescingTreeBuilder#appendCommentToDocument(java.lang.String)
+     */
+    @Override protected void appendCommentToDocument(String comment)
+            throws SAXException {
+        try {
+            document.appendChild(document.createComment(comment));
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#createElement(String, String, nu.validator.htmlparser.impl.HtmlAttributes, Object)
+     */
+    @Override protected Element createElement(String ns, String name,
+            HtmlAttributes attributes, Element intendedParent) throws SAXException {
+        try {
+            Element rv = document.createElementNS(ns, name);
+            for (int i = 0; i < attributes.getLength(); i++) {
+                rv.setAttributeNS(attributes.getURINoBoundsCheck(i),
+                        attributes.getLocalNameNoBoundsCheck(i),
+                        attributes.getValueNoBoundsCheck(i));
+                if (attributes.getTypeNoBoundsCheck(i) == "ID") {
+                    rv.setIdAttributeNS(null, attributes.getLocalName(i), true);
+                }
+            }
+            return rv;
+        } catch (DOMException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#createHtmlElementSetAsRoot(nu.validator.htmlparser.impl.HtmlAttributes)
+     */
+    @Override protected Element createHtmlElementSetAsRoot(
+            HtmlAttributes attributes) throws SAXException {
+        try {
+            Element rv = document.createElementNS(
+                    "http://www.w3.org/1999/xhtml", "html");
+            for (int i = 0; i < attributes.getLength(); i++) {
+                rv.setAttributeNS(attributes.getURINoBoundsCheck(i),
+                        attributes.getLocalNameNoBoundsCheck(i),
+                        attributes.getValueNoBoundsCheck(i));
+            }
+            document.appendChild(rv);
+            return rv;
+        } catch (DOMException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendElement(java.lang.Object,
+     *      java.lang.Object)
+     */
+    @Override protected void appendElement(Element child, Element newParent)
+            throws SAXException {
+        try {
+            newParent.appendChild(child);
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#hasChildren(java.lang.Object)
+     */
+    @Override protected boolean hasChildren(Element element)
+            throws SAXException {
+        try {
+            return element.hasChildNodes();
+        } catch (DOMException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#createElement(String,
+     *      java.lang.String, org.xml.sax.Attributes, java.lang.Object)
+     */
+    @Override protected Element createElement(String ns, String name,
+            HtmlAttributes attributes, Element form, Element intendedParent) throws SAXException {
+        try {
+            Element rv = createElement(ns, name, attributes, intendedParent);
+            rv.setUserData("nu.validator.form-pointer", form, null);
+            return rv;
+        } catch (DOMException e) {
+            fatal(e);
+            return null;
+        }
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#start()
+     */
+    @Override protected void start(boolean fragment) throws SAXException {
+        document = implementation.createDocument(null, null, null);
+    }
+
+    /**
+     * 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#documentMode(nu.validator.htmlparser.common.DocumentMode,
+     *      java.lang.String, java.lang.String, boolean)
+     */
+    protected void documentMode(DocumentMode mode, String publicIdentifier,
+            String systemIdentifier, boolean html4SpecificAdditionalErrorChecks)
+            throws SAXException {
+        document.setUserData("nu.validator.document-mode", mode, null);
+    }
+
+    /**
+     * Returns the document.
+     * 
+     * @return the document
+     */
+    Document getDocument() {
+        Document rv = document;
+        document = null;
+        return rv;
+    }
+
+    /**
+     * Return the document fragment.
+     * 
+     * @return the document fragment
+     */
+    DocumentFragment getDocumentFragment() {
+        DocumentFragment rv = document.createDocumentFragment();
+        Node rootElt = document.getFirstChild();
+        while (rootElt.hasChildNodes()) {
+            rv.appendChild(rootElt.getFirstChild());
+        }
+        document = null;
+        return rv;
+    }
+
+    @Override
+    protected Element createAndInsertFosterParentedElement(String ns, String name,
+            HtmlAttributes attributes, Element table, Element stackParent) throws SAXException {
+        try {
+            Node parent = table.getParentNode();
+            Element child = createElement(ns, name, attributes, parent != null ? (Element) parent : stackParent);
+
+            if (parent != null) { // always an element if not null
+                parent.insertBefore(child, table);
+            } else {
+                stackParent.appendChild(child);
+            }
+
+            return child;
+        } catch (DOMException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    @Override protected void insertFosterParentedCharacters(String text,
+            Element table, Element stackParent) throws SAXException {
+        try {
+            Node parent = table.getParentNode();
+            if (parent != null) { // always an element if not null
+                Node previousSibling = table.getPreviousSibling();
+                if (previousSibling != null
+                        && previousSibling.getNodeType() == Node.TEXT_NODE) {
+                    Text lastAsText = (Text) previousSibling;
+                    lastAsText.setData(lastAsText.getData() + text);
+                    return;
+                }
+                parent.insertBefore(document.createTextNode(text), table);
+                return;
+            }
+            Node lastChild = stackParent.getLastChild();
+            if (lastChild != null && lastChild.getNodeType() == Node.TEXT_NODE) {
+                Text lastAsText = (Text) lastChild;
+                lastAsText.setData(lastAsText.getData() + text);
+                return;
+            }
+            stackParent.appendChild(document.createTextNode(text));
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    @Override protected void insertFosterParentedChild(Element child,
+            Element table, Element stackParent) throws SAXException {
+        try {
+            Node parent = table.getParentNode();
+            if (parent != null) { // always an element if not null
+                parent.insertBefore(child, table);
+            } else {
+                stackParent.appendChild(child);
+            }
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+
+    @Override protected void detachFromParent(Element element)
+            throws SAXException {
+        try {
+            Node parent = element.getParentNode();
+            if (parent != null) {
+                parent.removeChild(element);
+            }
+        } catch (DOMException e) {
+            fatal(e);
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/Dom2Sax.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/Dom2Sax.java
new file mode 100644
index 000000000..5e366be7b
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/Dom2Sax.java
@@ -0,0 +1,259 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.dom;
+
+import org.w3c.dom.DocumentType;
+import org.w3c.dom.NamedNodeMap;
+import org.w3c.dom.Node;
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.SAXException;
+import org.xml.sax.ext.LexicalHandler;
+
+public class Dom2Sax {
+
+    private static String emptyIfNull(String namespaceURI) {
+        return namespaceURI == null ? "" : namespaceURI;
+    }
+    
+    private final NamedNodeMapAttributes attributes = new NamedNodeMapAttributes();
+
+    private final ContentHandler contentHandler;
+
+    private final LexicalHandler lexicalHandler;
+
+    /**
+     * @param contentHandler
+     * @param lexicalHandler
+     */
+    public Dom2Sax(ContentHandler contentHandler, LexicalHandler lexicalHandler) {
+        if (contentHandler == null) {
+            throw new IllegalArgumentException("ContentHandler must not be null.");
+        }
+        this.contentHandler = contentHandler;
+        this.lexicalHandler = lexicalHandler;
+    }
+
+    public void parse(Node node) throws SAXException {
+        Node current = node;
+        Node next;
+        char[] buf;
+        for (;;) {
+            switch (current.getNodeType()) {
+                case Node.ELEMENT_NODE:
+                    attributes.setNamedNodeMap(current.getAttributes());
+                    // To work around severe bogosity in the default DOM
+                    // impl, use the node name if local name is null.
+                    String localName = current.getLocalName();
+                    contentHandler.startElement(
+                            emptyIfNull(current.getNamespaceURI()),
+                            localName == null ? current.getNodeName()
+                                    : localName, null, attributes);
+                    attributes.clear();
+                    break;
+                case Node.TEXT_NODE:
+                    buf = current.getNodeValue().toCharArray();
+                    contentHandler.characters(buf, 0, buf.length);
+                    break;
+                case Node.CDATA_SECTION_NODE:
+                    if (lexicalHandler != null) {
+                        lexicalHandler.startCDATA();
+                    }
+                    buf = current.getNodeValue().toCharArray();
+                    contentHandler.characters(buf, 0, buf.length);
+                    if (lexicalHandler != null) {
+                        lexicalHandler.endCDATA();
+                    }
+                    break;
+                case Node.COMMENT_NODE:
+                    if (lexicalHandler != null) {
+                        buf = current.getNodeValue().toCharArray();
+                        lexicalHandler.comment(buf, 0, buf.length);
+                    }
+                    break;
+                case Node.DOCUMENT_NODE:
+                    contentHandler.startDocument();
+                    break;
+                case Node.DOCUMENT_TYPE_NODE:
+                    if (lexicalHandler != null) {
+                        DocumentType doctype = (DocumentType) current;
+                        lexicalHandler.startDTD(doctype.getName(),
+                                doctype.getPublicId(), doctype.getSystemId());
+                        lexicalHandler.endDTD();
+                    }
+                    break;
+                case Node.PROCESSING_INSTRUCTION_NODE:
+                    contentHandler.processingInstruction(current.getNodeName(), current.getNodeValue());
+                    break;
+                case Node.ENTITY_REFERENCE_NODE:
+                    contentHandler.skippedEntity(current.getNodeName());
+                    break;
+            }
+            if ((next = current.getFirstChild()) != null) {
+                current = next;
+                continue;
+            }
+            for (;;) {
+                switch (current.getNodeType()) {
+                    case Node.ELEMENT_NODE:
+                        // To work around severe bogosity in the default DOM
+                        // impl, use the node name if local name is null.
+                        String localName = current.getLocalName();
+                        contentHandler.endElement(
+                                emptyIfNull(current.getNamespaceURI()),
+                                localName == null ? current.getNodeName()
+                                        : localName, null);
+                        break;
+                    case Node.DOCUMENT_NODE:
+                        contentHandler.endDocument();
+                        break;
+                }
+                if (current == node) {
+                    return;
+                }
+                if ((next = current.getNextSibling()) != null) {
+                    current = next;
+                    break;
+                }
+                current = current.getParentNode();
+            }
+        }
+    }
+
+    private class NamedNodeMapAttributes implements Attributes {
+
+        private NamedNodeMap map;
+        
+        private int length;
+        
+        public void setNamedNodeMap(NamedNodeMap attributes) {
+            this.map = attributes;
+            this.length = attributes.getLength();
+        }
+        
+        public void clear() {
+            this.map = null;
+        }
+
+        public int getIndex(String qName) {
+            for (int i = 0; i < length; i++) {
+                Node n = map.item(i);
+                if (n.getNodeName().equals(qName)) {
+                    return i;
+                }
+            }
+            return -1;
+        }
+
+        public int getIndex(String uri, String localName) {
+            for (int i = 0; i < length; i++) {
+                Node n = map.item(i);
+                if (n.getLocalName().equals(localName) && emptyIfNull(n.getNamespaceURI()).equals(uri)) {
+                    return i;
+                }
+            }
+            return -1;
+        }
+
+        public int getLength() {
+            return length;
+        }
+
+        public String getLocalName(int index) {
+            if (index < length && index >= 0) {
+                return map.item(index).getLocalName();
+            } else {
+                return null;
+            }
+        }
+
+        public String getQName(int index) {
+            if (index < length && index >= 0) {
+                return map.item(index).getNodeName();
+            } else {
+                return null;
+            }
+        }
+
+        public String getType(int index) {
+            if (index < length && index >= 0) {
+                return "id".equals(map.item(index).getLocalName()) ? "ID" : "CDATA";
+            } else {
+                return null;
+            }
+        }
+
+        public String getType(String qName) {
+            int index = getIndex(qName);
+            if (index == -1) {
+                return null;
+            } else {
+                return getType(index);
+            }
+        }
+
+        public String getType(String uri, String localName) {
+            int index = getIndex(uri, localName);
+            if (index == -1) {
+                return null;
+            } else {
+                return getType(index);
+            }
+        }
+
+        public String getURI(int index) {
+            if (index < length && index >= 0) {
+                return emptyIfNull(map.item(index).getNamespaceURI());
+            } else {
+                return null;
+            }
+        }
+
+        public String getValue(int index) {
+            if (index < length && index >= 0) {
+                return map.item(index).getNodeValue();
+            } else {
+                return null;
+            }
+        }
+
+        public String getValue(String qName) {
+            int index = getIndex(qName);
+            if (index == -1) {
+                return null;
+            } else {
+                return getValue(index);
+            }
+        }
+
+        public String getValue(String uri, String localName) {
+            int index = getIndex(uri, localName);
+            if (index == -1) {
+                return null;
+            } else {
+                return getValue(index);
+            }
+        }
+
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java
new file mode 100644
index 000000000..f4a307c9f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java
@@ -0,0 +1,736 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2007-2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.dom;
+
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.LinkedList;
+import java.util.List;
+
+import javax.xml.parsers.DocumentBuilder;
+import javax.xml.parsers.DocumentBuilderFactory;
+import javax.xml.parsers.ParserConfigurationException;
+
+import nu.validator.htmlparser.common.CharacterHandler;
+import nu.validator.htmlparser.common.DoctypeExpectation;
+import nu.validator.htmlparser.common.DocumentModeHandler;
+import nu.validator.htmlparser.common.Heuristics;
+import nu.validator.htmlparser.common.TokenHandler;
+import nu.validator.htmlparser.common.TransitionHandler;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+import nu.validator.htmlparser.impl.ErrorReportingTokenizer;
+import nu.validator.htmlparser.impl.Tokenizer;
+import nu.validator.htmlparser.io.Driver;
+
+import org.w3c.dom.DOMImplementation;
+import org.w3c.dom.Document;
+import org.w3c.dom.DocumentFragment;
+import org.xml.sax.EntityResolver;
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.InputSource;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * This class implements an HTML5 parser that exposes data through the DOM 
+ * interface. 
+ * 
+ * <p>By default, when using the constructor without arguments, the 
+ * this parser coerces XML 1.0-incompatible infosets into XML 1.0-compatible
+ * infosets. This corresponds to <code>ALTER_INFOSET</code> as the general 
+ * XML violation policy. To make the parser support non-conforming HTML fully 
+ * per the HTML 5 spec while on the other hand potentially violating the SAX2 
+ * API contract, set the general XML violation policy to <code>ALLOW</code>. 
+ * This does not work with a standard DOM implementation.
+ * It is possible to treat XML 1.0 infoset violations as fatal by setting 
+ * the general XML violation policy to <code>FATAL</code>. 
+ * 
+ * <p>The doctype is not represented in the tree.
+ * 
+ * <p>The document mode is represented as user data <code>DocumentMode</code> 
+ * object with the key <code>nu.validator.document-mode</code> on the document 
+ * node. 
+ * 
+ * <p>The form pointer is also stored as user data with the key 
+ * <code>nu.validator.form-pointer</code>.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public class HtmlDocumentBuilder extends DocumentBuilder {
+
+    /**
+     * Returns the JAXP DOM implementation.
+     * 
+     * @return the JAXP DOM implementation
+     */
+    private static DOMImplementation jaxpDOMImplementation() {
+        DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
+        factory.setNamespaceAware(true);
+        DocumentBuilder builder;
+        try {
+            builder = factory.newDocumentBuilder();
+        } catch (ParserConfigurationException e) {
+            throw new RuntimeException(e);
+        }
+        return builder.getDOMImplementation();
+    }
+
+    /**
+     * The tokenizer.
+     */
+    private Driver driver;
+
+    /**
+     * The tree builder.
+     */
+    private final DOMTreeBuilder treeBuilder;
+
+    /**
+     * The DOM impl.
+     */
+    private final DOMImplementation implementation;
+
+    /**
+     * The entity resolver.
+     */
+    private EntityResolver entityResolver;
+
+    private ErrorHandler errorHandler = null;
+    
+    private DocumentModeHandler documentModeHandler = null;
+
+    private DoctypeExpectation doctypeExpectation = DoctypeExpectation.HTML;
+
+    private boolean checkingNormalization = false;
+
+    private boolean scriptingEnabled = false;
+
+    private final List<CharacterHandler> characterHandlers = new LinkedList<CharacterHandler>();
+    
+    private XmlViolationPolicy contentSpacePolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy contentNonXmlCharPolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy commentPolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy namePolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy streamabilityViolationPolicy = XmlViolationPolicy.ALLOW;
+    
+    private boolean html4ModeCompatibleWithXhtml1Schemata = false;
+
+    private boolean mappingLangToXmlLang = false;
+
+    private XmlViolationPolicy xmlnsPolicy = XmlViolationPolicy.FATAL;
+    
+    private boolean reportingDoctype = true;
+
+    private ErrorHandler treeBuilderErrorHandler = null;
+
+    private Heuristics heuristics = Heuristics.NONE;
+
+    private TransitionHandler transitionHandler = null;
+
+    /**
+     * Instantiates the document builder with a specific DOM 
+     * implementation and XML violation policy.
+     * 
+     * @param implementation
+     *            the DOM implementation
+     *            @param xmlPolicy the policy
+     */
+    public HtmlDocumentBuilder(DOMImplementation implementation,
+            XmlViolationPolicy xmlPolicy) {
+        this.implementation = implementation;
+        this.treeBuilder = new DOMTreeBuilder(implementation);
+        this.driver = null;
+        setXmlPolicy(xmlPolicy);
+    }
+
+    /**
+     * Instantiates the document builder with a specific DOM implementation 
+     * and the infoset-altering XML violation policy.
+     * 
+     * @param implementation
+     *            the DOM implementation
+     */
+    public HtmlDocumentBuilder(DOMImplementation implementation) {
+        this(implementation, XmlViolationPolicy.ALTER_INFOSET);
+    }
+
+    /**
+     * Instantiates the document builder with the JAXP DOM implementation 
+     * and the infoset-altering XML violation policy.
+     */
+    public HtmlDocumentBuilder() {
+        this(XmlViolationPolicy.ALTER_INFOSET);
+    }
+
+    /**
+     * Instantiates the document builder with the JAXP DOM implementation 
+     * and a specific XML violation policy.
+     *            @param xmlPolicy the policy
+     */
+    public HtmlDocumentBuilder(XmlViolationPolicy xmlPolicy) {
+        this(jaxpDOMImplementation(), xmlPolicy);
+    }
+
+
+    private Tokenizer newTokenizer(TokenHandler handler,
+            boolean newAttributesEachTime) {
+        if (errorHandler == null && transitionHandler == null
+                && contentNonXmlCharPolicy == XmlViolationPolicy.ALLOW) {
+            return new Tokenizer(handler, newAttributesEachTime);
+        } else {
+            return new ErrorReportingTokenizer(handler, newAttributesEachTime);
+        }
+    }
+    
+    /**
+     * This class wraps different tree builders depending on configuration. This 
+     * method does the work of hiding this from the user of the class.
+     */
+    private void lazyInit() {
+        if (driver == null) {
+            this.driver = new Driver(newTokenizer(treeBuilder, false));
+            this.driver.setErrorHandler(errorHandler);
+            this.driver.setTransitionHandler(transitionHandler);
+            this.treeBuilder.setErrorHandler(treeBuilderErrorHandler);
+            this.driver.setCheckingNormalization(checkingNormalization);
+            this.driver.setCommentPolicy(commentPolicy);
+            this.driver.setContentNonXmlCharPolicy(contentNonXmlCharPolicy);
+            this.driver.setContentSpacePolicy(contentSpacePolicy);
+            this.driver.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata);
+            this.driver.setMappingLangToXmlLang(mappingLangToXmlLang);
+            this.driver.setXmlnsPolicy(xmlnsPolicy);
+            this.driver.setHeuristics(heuristics);
+            for (CharacterHandler characterHandler : characterHandlers) {
+                this.driver.addCharacterHandler(characterHandler);
+            }
+            this.treeBuilder.setDoctypeExpectation(doctypeExpectation);
+            this.treeBuilder.setDocumentModeHandler(documentModeHandler);
+            this.treeBuilder.setScriptingEnabled(scriptingEnabled);
+            this.treeBuilder.setReportingDoctype(reportingDoctype);
+            this.treeBuilder.setNamePolicy(namePolicy);
+        }
+    }
+    
+    /**
+     * Tokenizes the input source.
+     * 
+     * @param is the source
+     * @throws SAXException if stuff goes wrong
+     * @throws IOException if IO goes wrong
+     * @throws MalformedURLException if the system ID is malformed and the entity resolver is <code>null</code>
+     */
+    private void tokenize(InputSource is) throws SAXException, IOException,
+            MalformedURLException {
+        if (is == null) {
+            throw new IllegalArgumentException("Null input.");
+        }
+        if (is.getByteStream() == null && is.getCharacterStream() == null) {
+            String systemId = is.getSystemId();
+            if (systemId == null) {
+                throw new IllegalArgumentException(
+                        "No byte stream, no character stream nor URI.");
+            }
+            if (entityResolver != null) {
+                is = entityResolver.resolveEntity(is.getPublicId(), systemId);
+            }
+            if (is.getByteStream() == null || is.getCharacterStream() == null) {
+                is = new InputSource();
+                is.setSystemId(systemId);
+                is.setByteStream(new URL(systemId).openStream());
+            }
+        }
+        if (driver == null) lazyInit();
+        driver.tokenize(is);
+    }
+    
+    /**
+     * Returns the DOM implementation
+     * @return the DOM implementation
+     * @see javax.xml.parsers.DocumentBuilder#getDOMImplementation()
+     */
+    @Override public DOMImplementation getDOMImplementation() {
+        return implementation;
+    }
+
+    /**
+     * Returns <code>true</code>.
+     * @return <code>true</code>
+     * @see javax.xml.parsers.DocumentBuilder#isNamespaceAware()
+     */
+    @Override public boolean isNamespaceAware() {
+        return true;
+    }
+
+    /**
+     * Returns <code>false</code>
+     * @return <code>false</code>
+     * @see javax.xml.parsers.DocumentBuilder#isValidating()
+     */
+    @Override public boolean isValidating() {
+        return false;
+    }
+
+    /**
+     * For API compatibility.
+     * @see javax.xml.parsers.DocumentBuilder#newDocument()
+     */
+    @Override public Document newDocument() {
+        return implementation.createDocument(null, null, null);
+    }
+
+    /**
+     * Parses a document from a SAX <code>InputSource</code>.
+     * @param is the source
+     * @return the doc
+     * @throws SAXException if stuff goes wrong
+     * @throws IOException if IO goes wrong
+     * @see javax.xml.parsers.DocumentBuilder#parse(org.xml.sax.InputSource)
+     */
+    @Override public Document parse(InputSource is) throws SAXException,
+            IOException {
+        treeBuilder.setFragmentContext(null);
+        tokenize(is);
+        return treeBuilder.getDocument();
+    }
+
+    /**
+     * Parses a document fragment from a SAX <code>InputSource</code> with 
+     * an HTML element as the fragment context.
+     * @param is the source
+     * @param context the context element name (HTML namespace assumed)
+     * @return the document fragment
+     * @throws SAXException if stuff goes wrong
+     * @throws IOException if IO goes wrong
+     */
+    public DocumentFragment parseFragment(InputSource is, String context)
+            throws IOException, SAXException {
+        treeBuilder.setFragmentContext(context.intern());
+        tokenize(is);
+        return treeBuilder.getDocumentFragment();
+    }
+
+    /**
+     * Parses a document fragment from a SAX <code>InputSource</code>.
+     * @param is the source
+     * @param contextLocal the local name of the context element
+     * @param contextNamespace the namespace of the context element
+     * @return the document fragment
+     * @throws SAXException if stuff goes wrong
+     * @throws IOException if IO goes wrong
+     */
+    public DocumentFragment parseFragment(InputSource is, String contextLocal,
+            String contextNamespace) throws IOException, SAXException {
+        treeBuilder.setFragmentContext(contextLocal.intern(),
+                contextNamespace.intern(), null, false);
+        tokenize(is);
+        return treeBuilder.getDocumentFragment();
+    }
+
+    /**
+     * Sets the entity resolver for URI-only inputs.
+     * @param resolver the resolver
+     * @see javax.xml.parsers.DocumentBuilder#setEntityResolver(org.xml.sax.EntityResolver)
+     */
+    @Override public void setEntityResolver(EntityResolver resolver) {
+        this.entityResolver = resolver;
+    }
+
+    /**
+     * Sets the error handler.
+     * @param errorHandler the handler
+     * @see javax.xml.parsers.DocumentBuilder#setErrorHandler(org.xml.sax.ErrorHandler)
+     */
+    @Override public void setErrorHandler(ErrorHandler errorHandler) {
+        treeBuilder.setErrorHandler(errorHandler);
+        if (driver != null) {
+            driver.setErrorHandler(errorHandler);
+        }
+    }
+
+    public void setTransitionHander(TransitionHandler handler) {
+        transitionHandler = handler;
+        driver = null;
+    }
+    
+    /**
+     * Indicates whether NFC normalization of source is being checked.
+     * @return <code>true</code> if NFC normalization of source is being checked.
+     * @see nu.validator.htmlparser.impl.Tokenizer#isCheckingNormalization()
+     */
+    public boolean isCheckingNormalization() {
+        return checkingNormalization;
+    }
+
+    /**
+     * Toggles the checking of the NFC normalization of source.
+     * @param enable <code>true</code> to check normalization
+     * @see nu.validator.htmlparser.impl.Tokenizer#setCheckingNormalization(boolean)
+     */
+    public void setCheckingNormalization(boolean enable) {
+        this.checkingNormalization = enable;
+        if (driver != null) {
+            driver.setCheckingNormalization(checkingNormalization);
+        }
+    }
+
+    /**
+     * Sets the policy for consecutive hyphens in comments.
+     * @param commentPolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setCommentPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setCommentPolicy(XmlViolationPolicy commentPolicy) {
+        this.commentPolicy = commentPolicy;
+        if (driver != null) {
+            driver.setCommentPolicy(commentPolicy);
+        }
+    }
+
+    /**
+     * Sets the policy for non-XML characters except white space.
+     * @param contentNonXmlCharPolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentNonXmlCharPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentNonXmlCharPolicy(
+            XmlViolationPolicy contentNonXmlCharPolicy) {
+        this.contentNonXmlCharPolicy = contentNonXmlCharPolicy;
+        driver = null;
+    }
+
+    /**
+     * Sets the policy for non-XML white space.
+     * @param contentSpacePolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentSpacePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentSpacePolicy(XmlViolationPolicy contentSpacePolicy) {
+        this.contentSpacePolicy = contentSpacePolicy;
+        if (driver != null) {
+            driver.setContentSpacePolicy(contentSpacePolicy);
+        }
+    }
+
+    /**
+     * Whether the parser considers scripting to be enabled for noscript treatment.
+     * 
+     * @return <code>true</code> if enabled
+     * @see nu.validator.htmlparser.impl.TreeBuilder#isScriptingEnabled()
+     */
+    public boolean isScriptingEnabled() {
+        return scriptingEnabled;
+    }
+
+    /**
+     * Sets whether the parser considers scripting to be enabled for noscript treatment.
+     * @param scriptingEnabled <code>true</code> to enable
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setScriptingEnabled(boolean)
+     */
+    public void setScriptingEnabled(boolean scriptingEnabled) {
+        this.scriptingEnabled = scriptingEnabled;
+        if (treeBuilder != null) {
+            treeBuilder.setScriptingEnabled(scriptingEnabled);
+        }
+    }
+
+    /**
+     * Returns the doctype expectation.
+     * 
+     * @return the doctypeExpectation
+     */
+    public DoctypeExpectation getDoctypeExpectation() {
+        return doctypeExpectation;
+    }
+
+    /**
+     * Sets the doctype expectation.
+     * 
+     * @param doctypeExpectation
+     *            the doctypeExpectation to set
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setDoctypeExpectation(nu.validator.htmlparser.common.DoctypeExpectation)
+     */
+    public void setDoctypeExpectation(DoctypeExpectation doctypeExpectation) {
+        this.doctypeExpectation = doctypeExpectation;
+        if (treeBuilder != null) {
+            treeBuilder.setDoctypeExpectation(doctypeExpectation);
+        }
+    }
+
+    /**
+     * Returns the document mode handler.
+     * 
+     * @return the documentModeHandler
+     */
+    public DocumentModeHandler getDocumentModeHandler() {
+        return documentModeHandler;
+    }
+
+    /**
+     * Sets the document mode handler.
+     * 
+     * @param documentModeHandler
+     *            the documentModeHandler to set
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setDocumentModeHandler(nu.validator.htmlparser.common.DocumentModeHandler)
+     */
+    public void setDocumentModeHandler(DocumentModeHandler documentModeHandler) {
+        this.documentModeHandler = documentModeHandler;
+    }
+
+    /**
+     * Returns the streamabilityViolationPolicy.
+     * 
+     * @return the streamabilityViolationPolicy
+     */
+    public XmlViolationPolicy getStreamabilityViolationPolicy() {
+        return streamabilityViolationPolicy;
+    }
+
+    /**
+     * Sets the streamabilityViolationPolicy.
+     * 
+     * @param streamabilityViolationPolicy
+     *            the streamabilityViolationPolicy to set
+     */
+    public void setStreamabilityViolationPolicy(
+            XmlViolationPolicy streamabilityViolationPolicy) {
+        this.streamabilityViolationPolicy = streamabilityViolationPolicy;
+        driver = null;
+    }
+
+    /**
+     * Whether the HTML 4 mode reports boolean attributes in a way that repeats
+     * the name in the value.
+     * @param html4ModeCompatibleWithXhtml1Schemata
+     */
+    public void setHtml4ModeCompatibleWithXhtml1Schemata(
+            boolean html4ModeCompatibleWithXhtml1Schemata) {
+        this.html4ModeCompatibleWithXhtml1Schemata = html4ModeCompatibleWithXhtml1Schemata;
+        if (driver != null) {
+            driver.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata);
+        }
+    }
+
+    /**
+     * Returns the <code>Locator</code> during parse.
+     * @return the <code>Locator</code>
+     */
+    public Locator getDocumentLocator() {
+        return driver.getDocumentLocator();
+    }
+
+    /**
+     * Whether the HTML 4 mode reports boolean attributes in a way that repeats
+     * the name in the value.
+     * 
+     * @return the html4ModeCompatibleWithXhtml1Schemata
+     */
+    public boolean isHtml4ModeCompatibleWithXhtml1Schemata() {
+        return html4ModeCompatibleWithXhtml1Schemata;
+    }
+
+    /**
+     * Whether <code>lang</code> is mapped to <code>xml:lang</code>.
+     * @param mappingLangToXmlLang
+     * @see nu.validator.htmlparser.impl.Tokenizer#setMappingLangToXmlLang(boolean)
+     */
+    public void setMappingLangToXmlLang(boolean mappingLangToXmlLang) {
+        this.mappingLangToXmlLang = mappingLangToXmlLang;
+        if (driver != null) {
+            driver.setMappingLangToXmlLang(mappingLangToXmlLang);
+        }
+    }
+
+    /**
+     * Whether <code>lang</code> is mapped to <code>xml:lang</code>.
+     * 
+     * @return the mappingLangToXmlLang
+     */
+    public boolean isMappingLangToXmlLang() {
+        return mappingLangToXmlLang;
+    }
+
+    /**
+     * Whether the <code>xmlns</code> attribute on the root element is 
+     * passed to through. (FATAL not allowed.)
+     * @param xmlnsPolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setXmlnsPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setXmlnsPolicy(XmlViolationPolicy xmlnsPolicy) {
+        if (xmlnsPolicy == XmlViolationPolicy.FATAL) {
+            throw new IllegalArgumentException("Can't use FATAL here.");
+        }
+        this.xmlnsPolicy = xmlnsPolicy;
+        if (driver != null) {
+            driver.setXmlnsPolicy(xmlnsPolicy);
+        }
+    }
+
+    /**
+     * Returns the xmlnsPolicy.
+     * 
+     * @return the xmlnsPolicy
+     */
+    public XmlViolationPolicy getXmlnsPolicy() {
+        return xmlnsPolicy;
+    }
+
+    /**
+     * Returns the commentPolicy.
+     * 
+     * @return the commentPolicy
+     */
+    public XmlViolationPolicy getCommentPolicy() {
+        return commentPolicy;
+    }
+
+    /**
+     * Returns the contentNonXmlCharPolicy.
+     * 
+     * @return the contentNonXmlCharPolicy
+     */
+    public XmlViolationPolicy getContentNonXmlCharPolicy() {
+        return contentNonXmlCharPolicy;
+    }
+
+    /**
+     * Returns the contentSpacePolicy.
+     * 
+     * @return the contentSpacePolicy
+     */
+    public XmlViolationPolicy getContentSpacePolicy() {
+        return contentSpacePolicy;
+    }
+
+    /**
+     * @param reportingDoctype
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setReportingDoctype(boolean)
+     */
+    public void setReportingDoctype(boolean reportingDoctype) {
+        this.reportingDoctype = reportingDoctype;
+        if (treeBuilder != null) {
+            treeBuilder.setReportingDoctype(reportingDoctype);
+        }
+    }
+
+    /**
+     * Returns the reportingDoctype.
+     * 
+     * @return the reportingDoctype
+     */
+    public boolean isReportingDoctype() {
+        return reportingDoctype;
+    }
+
+    /**
+     * The policy for non-NCName element and attribute names.
+     * @param namePolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setNamePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setNamePolicy(XmlViolationPolicy namePolicy) {
+        this.namePolicy = namePolicy;
+        if (driver != null) {
+            driver.setNamePolicy(namePolicy);
+            treeBuilder.setNamePolicy(namePolicy);
+        }
+    }
+    
+    /**
+     * Sets the encoding sniffing heuristics.
+     * 
+     * @param heuristics the heuristics to set
+     * @see nu.validator.htmlparser.impl.Tokenizer#setHeuristics(nu.validator.htmlparser.common.Heuristics)
+     */
+    public void setHeuristics(Heuristics heuristics) {
+        this.heuristics = heuristics;
+        if (driver != null) {
+            driver.setHeuristics(heuristics);
+        }
+    }
+    
+    public Heuristics getHeuristics() {
+        return this.heuristics;
+    }
+
+    /**
+     * This is a catch-all convenience method for setting name, xmlns, content space, 
+     * content non-XML char and comment policies in one go. This does not affect the 
+     * streamability policy or doctype reporting.
+     * 
+     * @param xmlPolicy
+     */
+    public void setXmlPolicy(XmlViolationPolicy xmlPolicy) {
+        setNamePolicy(xmlPolicy);
+        setXmlnsPolicy(xmlPolicy == XmlViolationPolicy.FATAL ? XmlViolationPolicy.ALTER_INFOSET : xmlPolicy);
+        setContentSpacePolicy(xmlPolicy);
+        setContentNonXmlCharPolicy(xmlPolicy);
+        setCommentPolicy(xmlPolicy);
+    }
+
+    /**
+     * The policy for non-NCName element and attribute names.
+     * 
+     * @return the namePolicy
+     */
+    public XmlViolationPolicy getNamePolicy() {
+        return namePolicy;
+    }
+
+    /**
+     * Does nothing.
+     * @deprecated
+     */
+    public void setBogusXmlnsPolicy(
+            XmlViolationPolicy bogusXmlnsPolicy) {
+    }
+
+    /**
+     * Returns <code>XmlViolationPolicy.ALTER_INFOSET</code>.
+     * @deprecated
+     * @return <code>XmlViolationPolicy.ALTER_INFOSET</code>
+     */
+    public XmlViolationPolicy getBogusXmlnsPolicy() {
+        return XmlViolationPolicy.ALTER_INFOSET;
+    }
+    
+    public void addCharacterHandler(CharacterHandler characterHandler) {
+        this.characterHandlers.add(characterHandler);
+        if (driver != null) {
+            driver.addCharacterHandler(characterHandler);
+        }
+    }
+
+    
+    /**
+     * Sets whether comment nodes appear in the tree.
+     * @param ignoreComments <code>true</code> to ignore comments
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setIgnoringComments(boolean)
+     */
+    public void setIgnoringComments(boolean ignoreComments) {
+        treeBuilder.setIgnoringComments(ignoreComments);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/package.html b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/package.html
new file mode 100644
index 000000000..d793bcf86
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/dom/package.html
@@ -0,0 +1,29 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
+<html>
+<head><title>Package Overview</title>
+<!--
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a 
+ copy of this software and associated documentation files (the "Software"), 
+ to deal in the Software without restriction, including without limitation 
+ the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ and/or sell copies of the Software, and to permit persons to whom the 
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in 
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ DEALINGS IN THE SOFTWARE.
+-->
+</head>
+<body bgcolor="white">
+<p>This package provides an HTML5 parser that exposes the document using the DOM API.</p>
+</body>
+</html>
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/ChardetSniffer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/ChardetSniffer.java
new file mode 100644
index 000000000..a75750398
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/ChardetSniffer.java
@@ -0,0 +1,84 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.extra;
+
+import java.io.IOException;
+import java.nio.charset.UnsupportedCharsetException;
+
+import nu.validator.htmlparser.io.Encoding;
+
+import org.mozilla.intl.chardet.nsDetector;
+import org.mozilla.intl.chardet.nsICharsetDetectionObserver;
+import org.mozilla.intl.chardet.nsPSMDetector;
+
+import com.ibm.icu.text.CharsetDetector;
+
+public class ChardetSniffer implements nsICharsetDetectionObserver {
+
+    private final byte[] source;
+
+    private final int length;
+    
+    private Encoding returnValue = null;
+    
+    /**
+     * @param source
+     */
+    public ChardetSniffer(final byte[] source, final int length) {
+        this.source = source;
+        this.length = length;
+    }
+    
+    public Encoding sniff() throws IOException {
+        nsDetector detector = new nsDetector(nsPSMDetector.ALL);
+        detector.Init(this);
+        detector.DoIt(source, length, false);
+        detector.DataEnd();
+        if (returnValue != null && returnValue != Encoding.WINDOWS1252 && returnValue.isAsciiSuperset()) {
+            return returnValue;
+        } else {
+            return null;
+        }
+    }
+    
+    public static void main(String[] args) {
+        String[] detectable = CharsetDetector.getAllDetectableCharsets();
+        for (int i = 0; i < detectable.length; i++) {
+            String charset = detectable[i];
+            System.out.println(charset);
+        }
+    }
+
+    public void Notify(String charsetName) {
+        try {
+            Encoding enc = Encoding.forName(charsetName);
+            Encoding actual = enc.getActualHtmlEncoding();
+            if (actual != null) {
+                enc = actual;
+            }
+            returnValue = enc;
+        } catch (UnsupportedCharsetException e) {
+            returnValue = null;
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/IcuDetectorSniffer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/IcuDetectorSniffer.java
new file mode 100644
index 000000000..f3caab5c4
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/IcuDetectorSniffer.java
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.extra;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+import nu.validator.htmlparser.common.ByteReadable;
+import nu.validator.htmlparser.io.Encoding;
+
+import com.ibm.icu.text.CharsetDetector;
+import com.ibm.icu.text.CharsetMatch;
+
+public class IcuDetectorSniffer extends InputStream {
+
+    private final ByteReadable source;
+
+    /**
+     * @param source
+     */
+    public IcuDetectorSniffer(final ByteReadable source) {
+        this.source = source;
+    }
+    
+    @Override
+    public int read() throws IOException {
+        return source.readByte();
+    }
+    
+    public Encoding sniff() throws IOException {
+        try {
+            CharsetDetector detector = new CharsetDetector();
+            detector.setText(this);
+            CharsetMatch match = detector.detect();
+            Encoding enc = Encoding.forName(match.getName());
+            Encoding actual = enc.getActualHtmlEncoding();
+            if (actual != null) {
+                enc = actual;
+            }
+            if (enc != Encoding.WINDOWS1252 && enc.isAsciiSuperset()) {
+                return enc;
+            } else {
+                return null;
+            }
+        } catch (Exception e) {
+            return null;
+        }
+    }
+    
+    public static void main(String[] args) {
+        String[] detectable = CharsetDetector.getAllDetectableCharsets();
+        for (int i = 0; i < detectable.length; i++) {
+            String charset = detectable[i];
+            System.out.println(charset);
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/NormalizationChecker.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/NormalizationChecker.java
new file mode 100644
index 000000000..45df62fb7
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/extra/NormalizationChecker.java
@@ -0,0 +1,268 @@
+/*
+ * Copyright (c) 2006, 2007 Henri Sivonen
+ * Copyright (c) 2007 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.extra;
+
+import nu.validator.htmlparser.common.CharacterHandler;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+import com.ibm.icu.lang.UCharacter;
+import com.ibm.icu.text.Normalizer;
+import com.ibm.icu.text.UnicodeSet;
+
+/**
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class NormalizationChecker implements CharacterHandler {
+
+    private ErrorHandler errorHandler;
+
+    private Locator locator;
+
+    /**
+     * A thread-safe set of composing characters as per Charmod Norm.
+     */
+    @SuppressWarnings("deprecation")
+    private static final UnicodeSet COMPOSING_CHARACTERS = (UnicodeSet) new UnicodeSet(
+            "[[:nfc_qc=maybe:][:^ccc=0:]]").freeze();
+
+    // see http://sourceforge.net/mailarchive/message.php?msg_id=37279908
+
+    /**
+     * A buffer for holding sequences overlap the SAX buffer boundary.
+     */
+    private char[] buf = new char[128];
+
+    /**
+     * A holder for the original buffer (for the memory leak prevention 
+     * mechanism).
+     */
+    private char[] bufHolder = null;
+
+    /**
+     * The current used length of the buffer, i.e. the index of the first slot 
+     * that does not hold current data.
+     */
+    private int pos;
+
+    /**
+     * Indicates whether the checker the next call to <code>characters()</code> 
+     * is the first call in a run.
+     */
+    private boolean atStartOfRun;
+
+    /**
+     * Indicates whether the current run has already caused an error.
+     */
+    private boolean alreadyComplainedAboutThisRun;
+
+    /**
+     * Emit an error. The locator is used.
+     * 
+     * @param message the error message
+     * @throws SAXException if something goes wrong
+     */
+    public void err(String message) throws SAXException {
+        if (errorHandler != null) {
+            SAXParseException spe = new SAXParseException(message, locator);
+            errorHandler.error(spe);
+        }
+    }
+
+    /**
+     * Returns <code>true</code> if the argument is a composing BMP character 
+     * or a surrogate and <code>false</code> otherwise.
+     * 
+     * @param c a UTF-16 code unit
+     * @return <code>true</code> if the argument is a composing BMP character 
+     * or a surrogate and <code>false</code> otherwise
+     */
+    private static boolean isComposingCharOrSurrogate(char c) {
+        if (UCharacter.isHighSurrogate(c) || UCharacter.isLowSurrogate(c)) {
+            return true;
+        }
+        return isComposingChar(c);
+    }
+
+    /**
+     * Returns <code>true</code> if the argument is a composing character 
+     * and <code>false</code> otherwise.
+     * 
+     * @param c a Unicode code point
+     * @return <code>true</code> if the argument is a composing character 
+     * <code>false</code> otherwise
+     */
+    private static boolean isComposingChar(int c) {
+        return COMPOSING_CHARACTERS.contains(c);
+    }
+
+    /**
+     * Constructor with mode selection.
+     * 
+     * @param sourceTextMode whether the source text-related messages 
+     * should be enabled.
+     */
+    public NormalizationChecker(Locator locator) {
+        super();
+        start();
+    }
+
+    /**
+     * @see nu.validator.htmlparser.common.CharacterHandler#start()
+     */
+    public void start() {
+        atStartOfRun = true;
+        alreadyComplainedAboutThisRun = false;
+        pos = 0;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.common.CharacterHandler#characters(char[], int, int)
+     */
+    public void characters(char[] ch, int start, int length)
+            throws SAXException {
+        if (alreadyComplainedAboutThisRun) {
+            return;
+        }
+        if (atStartOfRun) {
+            char c = ch[start];
+            if (pos == 1) {
+                // there's a single high surrogate in buf
+                if (isComposingChar(UCharacter.getCodePoint(buf[0], c))) {
+                    err("Text run starts with a composing character.");
+                }
+                atStartOfRun = false;
+            } else {
+                if (length == 1 && UCharacter.isHighSurrogate(c)) {
+                    buf[0] = c;
+                    pos = 1;
+                    return;
+                } else {
+                    if (UCharacter.isHighSurrogate(c)) {
+                        if (isComposingChar(UCharacter.getCodePoint(c,
+                                ch[start + 1]))) {
+                            err("Text run starts with a composing character.");
+                        }
+                    } else {
+                        if (isComposingCharOrSurrogate(c)) {
+                            err("Text run starts with a composing character.");
+                        }
+                    }
+                    atStartOfRun = false;
+                }
+            }
+        }
+        int i = start;
+        int stop = start + length;
+        if (pos > 0) {
+            // there's stuff in buf
+            while (i < stop && isComposingCharOrSurrogate(ch[i])) {
+                i++;
+            }
+            appendToBuf(ch, start, i);
+            if (i == stop) {
+                return;
+            } else {
+                if (!Normalizer.isNormalized(buf, 0, pos, Normalizer.NFC, 0)) {
+                    errAboutTextRun();
+                }
+                pos = 0;
+            }
+        }
+        if (i < stop) {
+            start = i;
+            i = stop - 1;
+            while (i > start && isComposingCharOrSurrogate(ch[i])) {
+                i--;
+            }
+            if (i > start) {
+                if (!Normalizer.isNormalized(ch, start, i, Normalizer.NFC, 0)) {
+                    errAboutTextRun();
+                }
+            }
+            appendToBuf(ch, i, stop);
+        }
+    }
+
+    /**
+     * Emits an error stating that the current text run or the source 
+     * text is not in NFC.
+     * 
+     * @throws SAXException if the <code>ErrorHandler</code> throws
+     */
+    private void errAboutTextRun() throws SAXException {
+        err("Source text is not in Unicode Normalization Form C.");
+        alreadyComplainedAboutThisRun = true;
+    }
+
+    /**
+     * Appends a slice of an UTF-16 code unit array to the internal 
+     * buffer.
+     * 
+     * @param ch the array from which to copy
+     * @param start the index of the first element that is copied
+     * @param end the index of the first element that is not copied
+     */
+    private void appendToBuf(char[] ch, int start, int end) {
+        if (start == end) {
+            return;
+        }
+        int neededBufLen = pos + (end - start);
+        if (neededBufLen > buf.length) {
+            char[] newBuf = new char[neededBufLen];
+            System.arraycopy(buf, 0, newBuf, 0, pos);
+            if (bufHolder == null) {
+                bufHolder = buf; // keep the original around
+            }
+            buf = newBuf;
+        }
+        System.arraycopy(ch, start, buf, pos, end - start);
+        pos += (end - start);
+    }
+
+    /**
+     * @see nu.validator.htmlparser.common.CharacterHandler#end()
+     */
+    public void end() throws SAXException {
+        if (!alreadyComplainedAboutThisRun
+                && !Normalizer.isNormalized(buf, 0, pos, Normalizer.NFC, 0)) {
+            errAboutTextRun();
+        }
+        if (bufHolder != null) {
+            // restore the original small buffer to avoid leaking
+            // memory if this checker is recycled
+            buf = bufHolder;
+            bufHolder = null;
+        }
+    }
+
+    public void setErrorHandler(ErrorHandler errorHandler) {
+        this.errorHandler = errorHandler;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/AttributeName.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/AttributeName.java
new file mode 100644
index 000000000..48d82036c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/AttributeName.java
@@ -0,0 +1,2475 @@
+/*
+ * Copyright (c) 2008-2011 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import java.util.Arrays;
+
+import nu.validator.htmlparser.annotation.Local;
+import nu.validator.htmlparser.annotation.NoLength;
+import nu.validator.htmlparser.annotation.NsUri;
+import nu.validator.htmlparser.annotation.Prefix;
+import nu.validator.htmlparser.annotation.QName;
+import nu.validator.htmlparser.annotation.Virtual;
+import nu.validator.htmlparser.common.Interner;
+
+public final class AttributeName
+// Uncomment to regenerate
+// implements Comparable<AttributeName>
+{
+    // [NOCPP[
+
+    public static final int NCNAME_HTML = 1;
+
+    public static final int NCNAME_FOREIGN = (1 << 1) | (1 << 2);
+
+    public static final int NCNAME_LANG = (1 << 3);
+
+    public static final int IS_XMLNS = (1 << 4);
+
+    public static final int CASE_FOLDED = (1 << 5);
+
+    public static final int BOOLEAN = (1 << 6);
+
+    // ]NOCPP]
+    
+    /**
+     * An array representing no namespace regardless of namespace mode (HTML,
+     * SVG, MathML, lang-mapping HTML) used.
+     */
+    static final @NoLength @NsUri String[] ALL_NO_NS = { "", "", "",
+    // [NOCPP[
+            ""
+    // ]NOCPP]
+    };
+
+    /**
+     * An array that has no namespace for the HTML mode but the XMLNS namespace
+     * for the SVG and MathML modes.
+     */
+    private static final @NoLength @NsUri String[] XMLNS_NS = { "",
+            "http://www.w3.org/2000/xmlns/", "http://www.w3.org/2000/xmlns/",
+            // [NOCPP[
+            ""
+    // ]NOCPP]
+    };
+
+    /**
+     * An array that has no namespace for the HTML mode but the XML namespace
+     * for the SVG and MathML modes.
+     */
+    private static final @NoLength @NsUri String[] XML_NS = { "",
+            "http://www.w3.org/XML/1998/namespace",
+            "http://www.w3.org/XML/1998/namespace",
+            // [NOCPP[
+            ""
+    // ]NOCPP]
+    };
+
+    /**
+     * An array that has no namespace for the HTML mode but the XLink namespace
+     * for the SVG and MathML modes.
+     */
+    private static final @NoLength @NsUri String[] XLINK_NS = { "",
+            "http://www.w3.org/1999/xlink", "http://www.w3.org/1999/xlink",
+            // [NOCPP[
+            ""
+    // ]NOCPP]
+    };
+
+    // [NOCPP[
+    /**
+     * An array that has no namespace for the HTML, SVG and MathML modes but has
+     * the XML namespace for the lang-mapping HTML mode.
+     */
+    private static final @NoLength @NsUri String[] LANG_NS = { "", "", "",
+            "http://www.w3.org/XML/1998/namespace" };
+
+    // ]NOCPP]
+
+    /**
+     * An array for no prefixes in any mode.
+     */
+    static final @NoLength @Prefix String[] ALL_NO_PREFIX = { null, null, null,
+    // [NOCPP[
+            null
+    // ]NOCPP]
+    };
+
+    /**
+     * An array for no prefixe in the HTML mode and the <code>xmlns</code>
+     * prefix in the SVG and MathML modes.
+     */
+    private static final @NoLength @Prefix String[] XMLNS_PREFIX = { null,
+            "xmlns", "xmlns",
+            // [NOCPP[
+            null
+    // ]NOCPP]
+    };
+
+    /**
+     * An array for no prefixe in the HTML mode and the <code>xlink</code>
+     * prefix in the SVG and MathML modes.
+     */
+    private static final @NoLength @Prefix String[] XLINK_PREFIX = { null,
+            "xlink", "xlink",
+            // [NOCPP[
+            null
+    // ]NOCPP]
+    };
+
+    /**
+     * An array for no prefixe in the HTML mode and the <code>xml</code> prefix
+     * in the SVG and MathML modes.
+     */
+    private static final @NoLength @Prefix String[] XML_PREFIX = { null, "xml",
+            "xml",
+            // [NOCPP[
+            null
+    // ]NOCPP]
+    };
+
+    // [NOCPP[
+
+    private static final @NoLength @Prefix String[] LANG_PREFIX = { null, null,
+            null, "xml" };
+
+    private static @QName String[] COMPUTE_QNAME(String[] local, String[] prefix) {
+        @QName String[] arr = new String[4];
+        for (int i = 0; i < arr.length; i++) {
+            if (prefix[i] == null) {
+                arr[i] = local[i];
+            } else {
+                arr[i] = (prefix[i] + ':' + local[i]).intern();
+            }
+        }
+        return arr;
+    }
+
+    // ]NOCPP]
+
+    /**
+     * An initialization helper for having a one name in the SVG mode and
+     * another name in the other modes.
+     * 
+     * @param name
+     *            the name for the non-SVG modes
+     * @param camel
+     *            the name for the SVG mode
+     * @return the initialized name array
+     */
+    private static @NoLength @Local String[] SVG_DIFFERENT(@Local String name,
+            @Local String camel) {
+        @NoLength @Local String[] arr = new String[4];
+        arr[0] = name;
+        arr[1] = name;
+        arr[2] = camel;
+        // [NOCPP[
+        arr[3] = name;
+        // ]NOCPP]
+        return arr;
+    }
+
+    /**
+     * An initialization helper for having a one name in the MathML mode and
+     * another name in the other modes.
+     * 
+     * @param name
+     *            the name for the non-MathML modes
+     * @param camel
+     *            the name for the MathML mode
+     * @return the initialized name array
+     */
+    private static @NoLength @Local String[] MATH_DIFFERENT(@Local String name,
+            @Local String camel) {
+        @NoLength @Local String[] arr = new String[4];
+        arr[0] = name;
+        arr[1] = camel;
+        arr[2] = name;
+        // [NOCPP[
+        arr[3] = name;
+        // ]NOCPP]
+        return arr;
+    }
+
+    /**
+     * An initialization helper for having a different local name in the HTML
+     * mode and the SVG and MathML modes.
+     * 
+     * @param name
+     *            the name for the HTML mode
+     * @param suffix
+     *            the name for the SVG and MathML modes
+     * @return the initialized name array
+     */
+    private static @NoLength @Local String[] COLONIFIED_LOCAL(
+            @Local String name, @Local String suffix) {
+        @NoLength @Local String[] arr = new String[4];
+        arr[0] = name;
+        arr[1] = suffix;
+        arr[2] = suffix;
+        // [NOCPP[
+        arr[3] = name;
+        // ]NOCPP]
+        return arr;
+    }
+
+    /**
+     * An initialization helper for having the same local name in all modes.
+     * 
+     * @param name
+     *            the name
+     * @return the initialized name array
+     */
+    static @NoLength @Local String[] SAME_LOCAL(@Local String name) {
+        @NoLength @Local String[] arr = new String[4];
+        arr[0] = name;
+        arr[1] = name;
+        arr[2] = name;
+        // [NOCPP[
+        arr[3] = name;
+        // ]NOCPP]
+        return arr;
+    }
+
+    /**
+     * Returns an attribute name by buffer.
+     * 
+     * <p>
+     * C++ ownership: The return value is either released by the caller if the
+     * attribute is a duplicate or the ownership is transferred to
+     * HtmlAttributes and released upon clearing or destroying that object.
+     * 
+     * @param buf
+     *            the buffer
+     * @param offset
+     *            ignored
+     * @param length
+     *            length of data
+     * @param checkNcName
+     *            whether to check ncnameness
+     * @return an <code>AttributeName</code> corresponding to the argument data
+     */
+    static AttributeName nameByBuffer(@NoLength char[] buf, int offset,
+            int length
+            // [NOCPP[
+            , boolean checkNcName
+            // ]NOCPP]
+            , Interner interner) {
+        // XXX deal with offset
+        int hash = AttributeName.bufToHash(buf, length);
+        int index = Arrays.binarySearch(AttributeName.ATTRIBUTE_HASHES, hash);
+        if (index < 0) {
+            return AttributeName.createAttributeName(
+                    Portability.newLocalNameFromBuffer(buf, offset, length,
+                            interner)
+                    // [NOCPP[
+                    , checkNcName
+            // ]NOCPP]
+            );
+        } else {
+            AttributeName attributeName = AttributeName.ATTRIBUTE_NAMES[index];
+            @Local String name = attributeName.getLocal(AttributeName.HTML);
+            if (!Portability.localEqualsBuffer(name, buf, offset, length)) {
+                return AttributeName.createAttributeName(
+                        Portability.newLocalNameFromBuffer(buf, offset, length,
+                                interner)
+                        // [NOCPP[
+                        , checkNcName
+                // ]NOCPP]
+                );
+            }
+            return attributeName;
+        }
+    }
+
+    /**
+     * This method has to return a unique integer for each well-known
+     * lower-cased attribute name.
+     * 
+     * @param buf
+     * @param len
+     * @return
+     */
+    private static int bufToHash(@NoLength char[] buf, int len) {
+        int hash2 = 0;
+        int hash = len;
+        hash <<= 5;
+        hash += buf[0] - 0x60;
+        int j = len;
+        for (int i = 0; i < 4 && j > 0; i++) {
+            j--;
+            hash <<= 5;
+            hash += buf[j] - 0x60;
+            hash2 <<= 6;
+            hash2 += buf[i] - 0x5F;
+        }
+        return hash ^ hash2;
+    }
+
+    /**
+     * The mode value for HTML.
+     */
+    public static final int HTML = 0;
+
+    /**
+     * The mode value for MathML.
+     */
+    public static final int MATHML = 1;
+
+    /**
+     * The mode value for SVG.
+     */
+    public static final int SVG = 2;
+
+    // [NOCPP[
+
+    /**
+     * The mode value for lang-mapping HTML.
+     */
+    public static final int HTML_LANG = 3;
+
+    // ]NOCPP]
+
+    /**
+     * The namespaces indexable by mode.
+     */
+    private final @NsUri @NoLength String[] uri;
+
+    /**
+     * The local names indexable by mode.
+     */
+    private final @Local @NoLength String[] local;
+
+    /**
+     * The prefixes indexably by mode.
+     */
+    private final @Prefix @NoLength String[] prefix;
+
+    // [NOCPP[
+
+    private final int flags;
+
+    /**
+     * The qnames indexable by mode.
+     */
+    private final @QName @NoLength String[] qName;
+
+    // ]NOCPP]
+
+    /**
+     * The startup-time constructor.
+     * 
+     * @param uri
+     *            the namespace
+     * @param local
+     *            the local name
+     * @param prefix
+     *            the prefix
+     * @param ncname
+     *            the ncnameness
+     * @param xmlns
+     *            whether this is an xmlns attribute
+     */
+    protected AttributeName(@NsUri @NoLength String[] uri,
+            @Local @NoLength String[] local, @Prefix @NoLength String[] prefix
+            // [NOCPP[
+            , int flags
+    // ]NOCPP]        
+    ) {
+        this.uri = uri;
+        this.local = local;
+        this.prefix = prefix;
+        // [NOCPP[
+        this.qName = COMPUTE_QNAME(local, prefix);
+        this.flags = flags;
+        // ]NOCPP]
+    }
+
+    /**
+     * Creates an <code>AttributeName</code> for a local name.
+     * 
+     * @param name
+     *            the name
+     * @param checkNcName
+     *            whether to check ncnameness
+     * @return an <code>AttributeName</code>
+     */
+    private static AttributeName createAttributeName(@Local String name
+    // [NOCPP[
+            , boolean checkNcName
+    // ]NOCPP]
+    ) {
+        // [NOCPP[
+        int flags = NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG;
+        if (name.startsWith("xmlns:")) {
+            flags = IS_XMLNS;
+        } else if (checkNcName && !NCName.isNCName(name)) {
+            flags = 0;
+        }
+        // ]NOCPP]
+        return new AttributeName(AttributeName.ALL_NO_NS,
+                AttributeName.SAME_LOCAL(name), ALL_NO_PREFIX, flags);
+    }
+
+    /**
+     * Deletes runtime-allocated instances in C++.
+     */
+    @Virtual void release() {
+        // No-op in Java.
+        // Implement as |delete this;| in subclass.
+    }
+
+    /**
+     * The C++ destructor.
+     */
+    @SuppressWarnings("unused") @Virtual private void destructor() {
+        Portability.deleteArray(local);
+    }
+
+    /**
+     * Clones the attribute using an interner. Returns <code>this</code> in Java
+     * and for non-dynamic instances in C++.
+     * 
+     * @param interner
+     *            an interner
+     * @return a clone
+     */
+    @Virtual public AttributeName cloneAttributeName(Interner interner) {
+        return this;
+    }
+
+    // [NOCPP[
+    /**
+     * Creator for use when the XML violation policy requires an attribute name
+     * to be changed.
+     * 
+     * @param name
+     *            the name of the attribute to create
+     */
+    static AttributeName create(@Local String name) {
+        return new AttributeName(AttributeName.ALL_NO_NS,
+                AttributeName.SAME_LOCAL(name), ALL_NO_PREFIX,
+                NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    }
+
+    /**
+     * Queries whether this name is an XML 1.0 4th ed. NCName.
+     * 
+     * @param mode
+     *            the SVG/MathML/HTML mode
+     * @return <code>true</code> if this is an NCName in the given mode
+     */
+    public boolean isNcName(int mode) {
+        return (flags & (1 << mode)) != 0;
+    }
+
+    /**
+     * Queries whether this is an <code>xmlns</code> attribute.
+     * 
+     * @return <code>true</code> if this is an <code>xmlns</code> attribute
+     */
+    public boolean isXmlns() {
+        return (flags & IS_XMLNS) != 0;
+    }
+        
+    /**
+     * Queries whether this attribute has a case-folded value in the HTML4 mode
+     * of the parser.
+     * 
+     * @return <code>true</code> if the value is case-folded
+     */
+    boolean isCaseFolded() {
+        return (flags & CASE_FOLDED) != 0;
+    }
+
+    boolean isBoolean() {
+        return (flags & BOOLEAN) != 0;
+    }
+
+    public @QName String getQName(int mode) {
+        return qName[mode];
+    }
+
+    // ]NOCPP]
+
+    public @NsUri String getUri(int mode) {
+        return uri[mode];
+    }
+
+    public @Local String getLocal(int mode) {
+        return local[mode];
+    }
+
+    public @Prefix String getPrefix(int mode) {
+        return prefix[mode];
+    }
+
+    boolean equalsAnother(AttributeName another) {
+        return this.getLocal(AttributeName.HTML) == another.getLocal(AttributeName.HTML);
+    }
+
+    // START CODE ONLY USED FOR GENERATING CODE uncomment to regenerate
+
+//    /**
+//     * @see java.lang.Object#toString()
+//     */
+//    @Override public String toString() {
+//        return "(" + formatNs() + ", " + formatLocal() + ", " + formatPrefix()
+//                + ", " + formatFlags() + ")";
+//    }
+//
+//    private String formatFlags() {
+//        StringBuilder builder = new StringBuilder();
+//        if ((flags & NCNAME_HTML) != 0) {
+//            if (builder.length() != 0) {
+//                builder.append(" | ");
+//            }
+//            builder.append("NCNAME_HTML");
+//        }
+//        if ((flags & NCNAME_FOREIGN) != 0) {
+//            if (builder.length() != 0) {
+//                builder.append(" | ");
+//            }
+//            builder.append("NCNAME_FOREIGN");
+//        }
+//        if ((flags & NCNAME_LANG) != 0) {
+//            if (builder.length() != 0) {
+//                builder.append(" | ");
+//            }
+//            builder.append("NCNAME_LANG");
+//        }
+//        if (isXmlns()) {
+//            if (builder.length() != 0) {
+//                builder.append(" | ");
+//            }
+//            builder.append("IS_XMLNS");
+//        }
+//        if (isCaseFolded()) {
+//            if (builder.length() != 0) {
+//                builder.append(" | ");
+//            }
+//            builder.append("CASE_FOLDED");
+//        }
+//        if (isBoolean()) {
+//            if (builder.length() != 0) {
+//                builder.append(" | ");
+//            }
+//            builder.append("BOOLEAN");
+//        }
+//        if (builder.length() == 0) {
+//            return "0";
+//        }
+//        return builder.toString();
+//    }
+//
+//    public int compareTo(AttributeName other) {
+//        int thisHash = this.hash();
+//        int otherHash = other.hash();
+//        if (thisHash < otherHash) {
+//            return -1;
+//        } else if (thisHash == otherHash) {
+//            return 0;
+//        } else {
+//            return 1;
+//        }
+//    }
+//
+//    private String formatPrefix() {
+//        if (prefix[0] == null && prefix[1] == null && prefix[2] == null
+//                && prefix[3] == null) {
+//            return "ALL_NO_PREFIX";
+//        } else if (prefix[0] == null && prefix[1] == prefix[2]
+//                && prefix[3] == null) {
+//            if ("xmlns".equals(prefix[1])) {
+//                return "XMLNS_PREFIX";
+//            } else if ("xml".equals(prefix[1])) {
+//                return "XML_PREFIX";
+//            } else if ("xlink".equals(prefix[1])) {
+//                return "XLINK_PREFIX";
+//            } else {
+//                throw new IllegalStateException();
+//            }
+//        } else if (prefix[0] == null && prefix[1] == null && prefix[2] == null
+//                && prefix[3] == "xml") {
+//            return "LANG_PREFIX";
+//        } else {
+//            throw new IllegalStateException();
+//        }
+//    }
+//
+//    private String formatLocal() {
+//        if (local[0] == local[1] && local[0] == local[3]
+//                && local[0] != local[2]) {
+//            return "SVG_DIFFERENT(\"" + local[0] + "\", \"" + local[2] + "\")";
+//        }
+//        if (local[0] == local[2] && local[0] == local[3]
+//                && local[0] != local[1]) {
+//            return "MATH_DIFFERENT(\"" + local[0] + "\", \"" + local[1] + "\")";
+//        }
+//        if (local[0] == local[3] && local[1] == local[2]
+//                && local[0] != local[1]) {
+//            return "COLONIFIED_LOCAL(\"" + local[0] + "\", \"" + local[1]
+//                    + "\")";
+//        }
+//        for (int i = 1; i < local.length; i++) {
+//            if (local[0] != local[i]) {
+//                throw new IllegalStateException();
+//            }
+//        }
+//        return "SAME_LOCAL(\"" + local[0] + "\")";
+//    }
+//
+//    private String formatNs() {
+//        if (uri[0] == "" && uri[1] == "" && uri[2] == "" && uri[3] == "") {
+//            return "ALL_NO_NS";
+//        } else if (uri[0] == "" && uri[1] == uri[2] && uri[3] == "") {
+//            if ("http://www.w3.org/2000/xmlns/".equals(uri[1])) {
+//                return "XMLNS_NS";
+//            } else if ("http://www.w3.org/XML/1998/namespace".equals(uri[1])) {
+//                return "XML_NS";
+//            } else if ("http://www.w3.org/1999/xlink".equals(uri[1])) {
+//                return "XLINK_NS";
+//            } else {
+//                throw new IllegalStateException();
+//            }
+//        } else if (uri[0] == "" && uri[1] == "" && uri[2] == ""
+//                && uri[3] == "http://www.w3.org/XML/1998/namespace") {
+//            return "LANG_NS";
+//        } else {
+//            throw new IllegalStateException();
+//        }
+//    }
+//
+//    private String constName() {
+//        String name = getLocal(HTML);
+//        char[] buf = new char[name.length()];
+//        for (int i = 0; i < name.length(); i++) {
+//            char c = name.charAt(i);
+//            if (c == '-' || c == ':') {
+//                buf[i] = '_';
+//            } else if (c >= 'a' && c <= 'z') {
+//                buf[i] = (char) (c - 0x20);
+//            } else {
+//                buf[i] = c;
+//            }
+//        }
+//        return new String(buf);
+//    }
+//
+//    private int hash() {
+//        String name = getLocal(HTML);
+//        return bufToHash(name.toCharArray(), name.length());
+//    }
+//
+//    /**
+//     * Regenerate self
+//     *
+//     * @param args
+//     */
+//    public static void main(String[] args) {
+//        Arrays.sort(ATTRIBUTE_NAMES);
+//        for (int i = 1; i < ATTRIBUTE_NAMES.length; i++) {
+//            if (ATTRIBUTE_NAMES[i].hash() == ATTRIBUTE_NAMES[i - 1].hash()) {
+//                System.err.println("Hash collision: "
+//                        + ATTRIBUTE_NAMES[i].getLocal(HTML) + ", "
+//                        + ATTRIBUTE_NAMES[i - 1].getLocal(HTML));
+//                return;
+//            }
+//        }
+//        for (int i = 0; i < ATTRIBUTE_NAMES.length; i++) {
+//            AttributeName att = ATTRIBUTE_NAMES[i];
+//            System.out.println("public static final AttributeName "
+//                    + att.constName() + " = new AttributeName" + att.toString()
+//                    + ";");
+//        }
+//        System.out.println("private final static @NoLength AttributeName[] ATTRIBUTE_NAMES = {");
+//        for (int i = 0; i < ATTRIBUTE_NAMES.length; i++) {
+//            AttributeName att = ATTRIBUTE_NAMES[i];
+//            System.out.println(att.constName() + ",");
+//        }
+//        System.out.println("};");
+//        System.out.println("private final static int[] ATTRIBUTE_HASHES = {");
+//        for (int i = 0; i < ATTRIBUTE_NAMES.length; i++) {
+//            AttributeName att = ATTRIBUTE_NAMES[i];
+//            System.out.println(Integer.toString(att.hash()) + ",");
+//        }
+//        System.out.println("};");
+//    }
+
+    // START GENERATED CODE
+    public static final AttributeName D = new AttributeName(ALL_NO_NS, SAME_LOCAL("d"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName K = new AttributeName(ALL_NO_NS, SAME_LOCAL("k"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName R = new AttributeName(ALL_NO_NS, SAME_LOCAL("r"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName X = new AttributeName(ALL_NO_NS, SAME_LOCAL("x"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName Y = new AttributeName(ALL_NO_NS, SAME_LOCAL("y"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName Z = new AttributeName(ALL_NO_NS, SAME_LOCAL("z"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BY = new AttributeName(ALL_NO_NS, SAME_LOCAL("by"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CX = new AttributeName(ALL_NO_NS, SAME_LOCAL("cx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CY = new AttributeName(ALL_NO_NS, SAME_LOCAL("cy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DX = new AttributeName(ALL_NO_NS, SAME_LOCAL("dx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DY = new AttributeName(ALL_NO_NS, SAME_LOCAL("dy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName G2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("g2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName G1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("g1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FX = new AttributeName(ALL_NO_NS, SAME_LOCAL("fx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FY = new AttributeName(ALL_NO_NS, SAME_LOCAL("fy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName K4 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k4"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName K2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName K3 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k3"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName K1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("k1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ID = new AttributeName(ALL_NO_NS, SAME_LOCAL("id"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName IN = new AttributeName(ALL_NO_NS, SAME_LOCAL("in"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName U2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("u2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName U1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("u1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RT = new AttributeName(ALL_NO_NS, SAME_LOCAL("rt"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RX = new AttributeName(ALL_NO_NS, SAME_LOCAL("rx"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RY = new AttributeName(ALL_NO_NS, SAME_LOCAL("ry"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TO = new AttributeName(ALL_NO_NS, SAME_LOCAL("to"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName Y2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("y2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName Y1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("y1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName X1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("x1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName X2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("x2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ALT = new AttributeName(ALL_NO_NS, SAME_LOCAL("alt"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DIR = new AttributeName(ALL_NO_NS, SAME_LOCAL("dir"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName DUR = new AttributeName(ALL_NO_NS, SAME_LOCAL("dur"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName END = new AttributeName(ALL_NO_NS, SAME_LOCAL("end"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("for"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName IN2 = new AttributeName(ALL_NO_NS, SAME_LOCAL("in2"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MAX = new AttributeName(ALL_NO_NS, SAME_LOCAL("max"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("min"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LOW = new AttributeName(ALL_NO_NS, SAME_LOCAL("low"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REL = new AttributeName(ALL_NO_NS, SAME_LOCAL("rel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REV = new AttributeName(ALL_NO_NS, SAME_LOCAL("rev"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SRC = new AttributeName(ALL_NO_NS, SAME_LOCAL("src"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName AXIS = new AttributeName(ALL_NO_NS, SAME_LOCAL("axis"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ABBR = new AttributeName(ALL_NO_NS, SAME_LOCAL("abbr"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BBOX = new AttributeName(ALL_NO_NS, SAME_LOCAL("bbox"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CITE = new AttributeName(ALL_NO_NS, SAME_LOCAL("cite"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("code"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BIAS = new AttributeName(ALL_NO_NS, SAME_LOCAL("bias"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLS = new AttributeName(ALL_NO_NS, SAME_LOCAL("cols"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CLIP = new AttributeName(ALL_NO_NS, SAME_LOCAL("clip"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CHAR = new AttributeName(ALL_NO_NS, SAME_LOCAL("char"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BASE = new AttributeName(ALL_NO_NS, SAME_LOCAL("base"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName EDGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("edge"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DATA = new AttributeName(ALL_NO_NS, SAME_LOCAL("data"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FILL = new AttributeName(ALL_NO_NS, SAME_LOCAL("fill"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FROM = new AttributeName(ALL_NO_NS, SAME_LOCAL("from"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FORM = new AttributeName(ALL_NO_NS, SAME_LOCAL("form"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("face"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HIGH = new AttributeName(ALL_NO_NS, SAME_LOCAL("high"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HREF = new AttributeName(ALL_NO_NS, SAME_LOCAL("href"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OPEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("open"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ICON = new AttributeName(ALL_NO_NS, SAME_LOCAL("icon"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName NAME = new AttributeName(ALL_NO_NS, SAME_LOCAL("name"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("mode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MASK = new AttributeName(ALL_NO_NS, SAME_LOCAL("mask"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LINK = new AttributeName(ALL_NO_NS, SAME_LOCAL("link"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LANG = new AttributeName(LANG_NS, SAME_LOCAL("lang"), LANG_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LOOP = new AttributeName(ALL_NO_NS, SAME_LOCAL("loop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LIST = new AttributeName(ALL_NO_NS, SAME_LOCAL("list"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("type"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName WHEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("when"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName WRAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("wrap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TEXT = new AttributeName(ALL_NO_NS, SAME_LOCAL("text"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PATH = new AttributeName(ALL_NO_NS, SAME_LOCAL("path"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PING = new AttributeName(ALL_NO_NS, SAME_LOCAL("ping"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REFX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("refx", "refX"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REFY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("refy", "refY"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("size"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SEED = new AttributeName(ALL_NO_NS, SAME_LOCAL("seed"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ROWS = new AttributeName(ALL_NO_NS, SAME_LOCAL("rows"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("span"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STEP = new AttributeName(ALL_NO_NS, SAME_LOCAL("step"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName ROLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("role"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName XREF = new AttributeName(ALL_NO_NS, SAME_LOCAL("xref"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ASYNC = new AttributeName(ALL_NO_NS, SAME_LOCAL("async"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName ALINK = new AttributeName(ALL_NO_NS, SAME_LOCAL("alink"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("align"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName CLOSE = new AttributeName(ALL_NO_NS, SAME_LOCAL("close"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CLASS = new AttributeName(ALL_NO_NS, SAME_LOCAL("class"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CLEAR = new AttributeName(ALL_NO_NS, SAME_LOCAL("clear"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName BEGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("begin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DEPTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("depth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DEFER = new AttributeName(ALL_NO_NS, SAME_LOCAL("defer"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName FENCE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fence"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FRAME = new AttributeName(ALL_NO_NS, SAME_LOCAL("frame"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName ISMAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("ismap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName ONEND = new AttributeName(ALL_NO_NS, SAME_LOCAL("onend"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName INDEX = new AttributeName(ALL_NO_NS, SAME_LOCAL("index"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ORDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("order"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OTHER = new AttributeName(ALL_NO_NS, SAME_LOCAL("other"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONCUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncut"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName NARGS = new AttributeName(ALL_NO_NS, SAME_LOCAL("nargs"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MEDIA = new AttributeName(ALL_NO_NS, SAME_LOCAL("media"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LABEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("label"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LOCAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("local"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName WIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("width"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TITLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("title"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VLINK = new AttributeName(ALL_NO_NS, SAME_LOCAL("vlink"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VALUE = new AttributeName(ALL_NO_NS, SAME_LOCAL("value"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SLOPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("slope"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SHAPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("shape"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName SCOPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("scope"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName SCALE = new AttributeName(ALL_NO_NS, SAME_LOCAL("scale"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SPEED = new AttributeName(ALL_NO_NS, SAME_LOCAL("speed"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("style"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RULES = new AttributeName(ALL_NO_NS, SAME_LOCAL("rules"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName STEMH = new AttributeName(ALL_NO_NS, SAME_LOCAL("stemh"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SIZES = new AttributeName(ALL_NO_NS, SAME_LOCAL("sizes"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STEMV = new AttributeName(ALL_NO_NS, SAME_LOCAL("stemv"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName START = new AttributeName(ALL_NO_NS, SAME_LOCAL("start"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName XMLNS = new AttributeName(XMLNS_NS, SAME_LOCAL("xmlns"), ALL_NO_PREFIX, IS_XMLNS);
+    public static final AttributeName ACCEPT = new AttributeName(ALL_NO_NS, SAME_LOCAL("accept"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ACCENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("accent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ASCENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("ascent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ACTIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("active"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName ALTIMG = new AttributeName(ALL_NO_NS, SAME_LOCAL("altimg"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ACTION = new AttributeName(ALL_NO_NS, SAME_LOCAL("action"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BORDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("border"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CURSOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("cursor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COORDS = new AttributeName(ALL_NO_NS, SAME_LOCAL("coords"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FILTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("filter"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FORMAT = new AttributeName(ALL_NO_NS, SAME_LOCAL("format"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HIDDEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("hidden"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("hspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("height"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmove"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONLOAD = new AttributeName(ALL_NO_NS, SAME_LOCAL("onload"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDRAG = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondrag"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ORIGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("origin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONZOOM = new AttributeName(ALL_NO_NS, SAME_LOCAL("onzoom"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONHELP = new AttributeName(ALL_NO_NS, SAME_LOCAL("onhelp"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONSTOP = new AttributeName(ALL_NO_NS, SAME_LOCAL("onstop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDROP = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondrop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBLUR = new AttributeName(ALL_NO_NS, SAME_LOCAL("onblur"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OBJECT = new AttributeName(ALL_NO_NS, SAME_LOCAL("object"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OFFSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("offset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ORIENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("orient"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONCOPY = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncopy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName NOWRAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("nowrap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName NOHREF = new AttributeName(ALL_NO_NS, SAME_LOCAL("nohref"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName MACROS = new AttributeName(ALL_NO_NS, SAME_LOCAL("macros"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName METHOD = new AttributeName(ALL_NO_NS, SAME_LOCAL("method"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName LOWSRC = new AttributeName(ALL_NO_NS, SAME_LOCAL("lowsrc"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("lspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LQUOTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("lquote"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName USEMAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("usemap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName WIDTHS = new AttributeName(ALL_NO_NS, SAME_LOCAL("widths"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TARGET = new AttributeName(ALL_NO_NS, SAME_LOCAL("target"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VALUES = new AttributeName(ALL_NO_NS, SAME_LOCAL("values"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("valign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName VSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("vspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName POSTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("poster"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName POINTS = new AttributeName(ALL_NO_NS, SAME_LOCAL("points"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PROMPT = new AttributeName(ALL_NO_NS, SAME_LOCAL("prompt"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SRCDOC = new AttributeName(ALL_NO_NS, SAME_LOCAL("srcdoc"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SCOPED = new AttributeName(ALL_NO_NS, SAME_LOCAL("scoped"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STRING = new AttributeName(ALL_NO_NS, SAME_LOCAL("string"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SCHEME = new AttributeName(ALL_NO_NS, SAME_LOCAL("scheme"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RADIUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("radius"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RESULT = new AttributeName(ALL_NO_NS, SAME_LOCAL("result"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REPEAT = new AttributeName(ALL_NO_NS, SAME_LOCAL("repeat"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SRCSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("srcset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("rspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ROTATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("rotate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RQUOTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("rquote"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ALTTEXT = new AttributeName(ALL_NO_NS, SAME_LOCAL("alttext"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARCHIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("archive"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName AZIMUTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("azimuth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CLOSURE = new AttributeName(ALL_NO_NS, SAME_LOCAL("closure"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CHECKED = new AttributeName(ALL_NO_NS, SAME_LOCAL("checked"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName CLASSID = new AttributeName(ALL_NO_NS, SAME_LOCAL("classid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CHAROFF = new AttributeName(ALL_NO_NS, SAME_LOCAL("charoff"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BGCOLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("bgcolor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLSPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("colspan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CHARSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("charset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COMPACT = new AttributeName(ALL_NO_NS, SAME_LOCAL("compact"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName CONTENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("content"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ENCTYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("enctype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName DATASRC = new AttributeName(ALL_NO_NS, SAME_LOCAL("datasrc"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DATAFLD = new AttributeName(ALL_NO_NS, SAME_LOCAL("datafld"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DECLARE = new AttributeName(ALL_NO_NS, SAME_LOCAL("declare"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName DISPLAY = new AttributeName(ALL_NO_NS, SAME_LOCAL("display"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DIVISOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("divisor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DEFAULT = new AttributeName(ALL_NO_NS, SAME_LOCAL("default"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName DESCENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("descent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName KERNING = new AttributeName(ALL_NO_NS, SAME_LOCAL("kerning"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HANGING = new AttributeName(ALL_NO_NS, SAME_LOCAL("hanging"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HEADERS = new AttributeName(ALL_NO_NS, SAME_LOCAL("headers"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONPASTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onpaste"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONCLICK = new AttributeName(ALL_NO_NS, SAME_LOCAL("onclick"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OPTIMUM = new AttributeName(ALL_NO_NS, SAME_LOCAL("optimum"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbegin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONKEYUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("onkeyup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONFOCUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfocus"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONERROR = new AttributeName(ALL_NO_NS, SAME_LOCAL("onerror"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONINPUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("oninput"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONABORT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onabort"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONSTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("onstart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONRESET = new AttributeName(ALL_NO_NS, SAME_LOCAL("onreset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName NOSHADE = new AttributeName(ALL_NO_NS, SAME_LOCAL("noshade"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName MINSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("minsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MAXSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("maxsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LARGEOP = new AttributeName(ALL_NO_NS, SAME_LOCAL("largeop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName UNICODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("unicode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TARGETX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("targetx", "targetX"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TARGETY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("targety", "targetY"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VIEWBOX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("viewbox", "viewBox"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERSION = new AttributeName(ALL_NO_NS, SAME_LOCAL("version"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PATTERN = new AttributeName(ALL_NO_NS, SAME_LOCAL("pattern"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PROFILE = new AttributeName(ALL_NO_NS, SAME_LOCAL("profile"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("spacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RESTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("restart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ROWSPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowspan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SANDBOX = new AttributeName(ALL_NO_NS, SAME_LOCAL("sandbox"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SUMMARY = new AttributeName(ALL_NO_NS, SAME_LOCAL("summary"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STANDBY = new AttributeName(ALL_NO_NS, SAME_LOCAL("standby"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REPLACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("replace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName AUTOPLAY = new AttributeName(ALL_NO_NS, SAME_LOCAL("autoplay"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ADDITIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("additive"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CALCMODE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("calcmode", "calcMode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CODETYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("codetype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CODEBASE = new AttributeName(ALL_NO_NS, SAME_LOCAL("codebase"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CONTROLS = new AttributeName(ALL_NO_NS, SAME_LOCAL("controls"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BEVELLED = new AttributeName(ALL_NO_NS, SAME_LOCAL("bevelled"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BASELINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("baseline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName EXPONENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("exponent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName EDGEMODE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("edgemode", "edgeMode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ENCODING = new AttributeName(ALL_NO_NS, SAME_LOCAL("encoding"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName GLYPHREF = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("glyphref", "glyphRef"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DATETIME = new AttributeName(ALL_NO_NS, SAME_LOCAL("datetime"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DISABLED = new AttributeName(ALL_NO_NS, SAME_LOCAL("disabled"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName FONTSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName KEYTIMES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("keytimes", "keyTimes"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PANOSE_1 = new AttributeName(ALL_NO_NS, SAME_LOCAL("panose-1"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HREFLANG = new AttributeName(ALL_NO_NS, SAME_LOCAL("hreflang"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONRESIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onresize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONCHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onchange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBOUNCE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbounce"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONUNLOAD = new AttributeName(ALL_NO_NS, SAME_LOCAL("onunload"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONFINISH = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfinish"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONSCROLL = new AttributeName(ALL_NO_NS, SAME_LOCAL("onscroll"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OPERATOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("operator"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OVERFLOW = new AttributeName(ALL_NO_NS, SAME_LOCAL("overflow"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONSUBMIT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onsubmit"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONREPEAT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onrepeat"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONSELECT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onselect"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName NOTATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("notation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName NORESIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("noresize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName MANIFEST = new AttributeName(ALL_NO_NS, SAME_LOCAL("manifest"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MATHSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MULTIPLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("multiple"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName LONGDESC = new AttributeName(ALL_NO_NS, SAME_LOCAL("longdesc"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LANGUAGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("language"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TEMPLATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("template"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TABINDEX = new AttributeName(ALL_NO_NS, SAME_LOCAL("tabindex"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PROPERTY = new AttributeName(ALL_NO_NS, SAME_LOCAL("property"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName READONLY = new AttributeName(ALL_NO_NS, SAME_LOCAL("readonly"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName SELECTED = new AttributeName(ALL_NO_NS, SAME_LOCAL("selected"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName ROWLINES = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowlines"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SEAMLESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("seamless"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ROWALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowalign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STRETCHY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stretchy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REQUIRED = new AttributeName(ALL_NO_NS, SAME_LOCAL("required"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName XML_BASE = new AttributeName(XML_NS, COLONIFIED_LOCAL("xml:base", "base"), XML_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName XML_LANG = new AttributeName(XML_NS, COLONIFIED_LOCAL("xml:lang", "lang"), XML_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName X_HEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("x-height"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_OWNS = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-owns"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName AUTOFOCUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("autofocus"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName ARIA_SORT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-sort"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ACCESSKEY = new AttributeName(ALL_NO_NS, SAME_LOCAL("accesskey"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_BUSY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-busy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_GRAB = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-grab"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName AMPLITUDE = new AttributeName(ALL_NO_NS, SAME_LOCAL("amplitude"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_LIVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-live"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CLIP_RULE = new AttributeName(ALL_NO_NS, SAME_LOCAL("clip-rule"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CLIP_PATH = new AttributeName(ALL_NO_NS, SAME_LOCAL("clip-path"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName EQUALROWS = new AttributeName(ALL_NO_NS, SAME_LOCAL("equalrows"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ELEVATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("elevation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DIRECTION = new AttributeName(ALL_NO_NS, SAME_LOCAL("direction"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DRAGGABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("draggable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FILL_RULE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fill-rule"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONTSTYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontstyle"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONT_SIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-size"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName KEYSYSTEM = new AttributeName(ALL_NO_NS, SAME_LOCAL("keysystem"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName KEYPOINTS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("keypoints", "keyPoints"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HIDEFOCUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("hidefocus"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMESSAGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmessage"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName INTERCEPT = new AttributeName(ALL_NO_NS, SAME_LOCAL("intercept"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDRAGEND = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragend"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOVEEND = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmoveend"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONINVALID = new AttributeName(ALL_NO_NS, SAME_LOCAL("oninvalid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName INTEGRITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("integrity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONKEYDOWN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onkeydown"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONFOCUSIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfocusin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSEUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName INPUTMODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("inputmode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONROWEXIT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onrowexit"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MATHCOLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathcolor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MASKUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("maskunits", "maskUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MAXLENGTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("maxlength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LINEBREAK = new AttributeName(ALL_NO_NS, SAME_LOCAL("linebreak"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TRANSFORM = new AttributeName(ALL_NO_NS, SAME_LOCAL("transform"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName V_HANGING = new AttributeName(ALL_NO_NS, SAME_LOCAL("v-hanging"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VALUETYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("valuetype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName POINTSATZ = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pointsatz", "pointsAtZ"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName POINTSATX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pointsatx", "pointsAtX"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName POINTSATY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pointsaty", "pointsAtY"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SYMMETRIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("symmetric"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SCROLLING = new AttributeName(ALL_NO_NS, SAME_LOCAL("scrolling"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName REPEATDUR = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("repeatdur", "repeatDur"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SELECTION = new AttributeName(ALL_NO_NS, SAME_LOCAL("selection"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SEPARATOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("separator"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName XML_SPACE = new AttributeName(XML_NS, COLONIFIED_LOCAL("xml:space", "space"), XML_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName AUTOSUBMIT = new AttributeName(ALL_NO_NS, SAME_LOCAL("autosubmit"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED | BOOLEAN);
+    public static final AttributeName ALPHABETIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("alphabetic"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ACTIONTYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("actiontype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ACCUMULATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("accumulate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_LEVEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-level"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLUMNSPAN = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnspan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CAP_HEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("cap-height"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BACKGROUND = new AttributeName(ALL_NO_NS, SAME_LOCAL("background"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName GLYPH_NAME = new AttributeName(ALL_NO_NS, SAME_LOCAL("glyph-name"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName GROUPALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("groupalign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONTFAMILY = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontfamily"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONTWEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("fontweight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONT_STYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-style"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName KEYSPLINES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("keysplines", "keySplines"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HTTP_EQUIV = new AttributeName(ALL_NO_NS, SAME_LOCAL("http-equiv"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONACTIVATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onactivate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OCCURRENCE = new AttributeName(ALL_NO_NS, SAME_LOCAL("occurrence"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName IRRELEVANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("irrelevant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDBLCLICK = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondblclick"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDRAGDROP = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragdrop"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONKEYPRESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("onkeypress"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONROWENTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("onrowenter"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDRAGOVER = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragover"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONFOCUSOUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfocusout"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSEOUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseout"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName NUMOCTAVES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("numoctaves", "numOctaves"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARKER_MID = new AttributeName(ALL_NO_NS, SAME_LOCAL("marker-mid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARKER_END = new AttributeName(ALL_NO_NS, SAME_LOCAL("marker-end"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TEXTLENGTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("textlength", "textLength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VISIBILITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("visibility"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VIEWTARGET = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("viewtarget", "viewTarget"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERT_ADV_Y = new AttributeName(ALL_NO_NS, SAME_LOCAL("vert-adv-y"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PATHLENGTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("pathlength", "pathLength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REPEAT_MAX = new AttributeName(ALL_NO_NS, SAME_LOCAL("repeat-max"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RADIOGROUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("radiogroup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STOP_COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("stop-color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SEPARATORS = new AttributeName(ALL_NO_NS, SAME_LOCAL("separators"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REPEAT_MIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("repeat-min"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ROWSPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("rowspacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ZOOMANDPAN = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("zoomandpan", "zoomAndPan"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName XLINK_TYPE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:type", "type"), XLINK_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName XLINK_ROLE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:role", "role"), XLINK_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName XLINK_HREF = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:href", "href"), XLINK_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName XLINK_SHOW = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:show", "show"), XLINK_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName ACCENTUNDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("accentunder"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_SECRET = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-secret"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_ATOMIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-atomic"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_HIDDEN = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-hidden"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_FLOWTO = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-flowto"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARABIC_FORM = new AttributeName(ALL_NO_NS, SAME_LOCAL("arabic-form"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CELLPADDING = new AttributeName(ALL_NO_NS, SAME_LOCAL("cellpadding"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CELLSPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("cellspacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLUMNWIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnwidth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CROSSORIGIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("crossorigin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLUMNALIGN = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnalign"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLUMNLINES = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnlines"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CONTEXTMENU = new AttributeName(ALL_NO_NS, SAME_LOCAL("contextmenu"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BASEPROFILE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("baseprofile", "baseProfile"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONT_FAMILY = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-family"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FRAMEBORDER = new AttributeName(ALL_NO_NS, SAME_LOCAL("frameborder"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FILTERUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("filterunits", "filterUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FLOOD_COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("flood-color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONT_WEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-weight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HORIZ_ADV_X = new AttributeName(ALL_NO_NS, SAME_LOCAL("horiz-adv-x"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDRAGLEAVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragleave"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSEMOVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmousemove"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ORIENTATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("orientation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSEDOWN = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmousedown"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSEOVER = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseover"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDRAGENTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragenter"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName IDEOGRAPHIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("ideographic"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFORECUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforecut"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONFORMINPUT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onforminput"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDRAGSTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondragstart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOVESTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmovestart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARKERUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("markerunits", "markerUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MATHVARIANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathvariant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARGINWIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("marginwidth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARKERWIDTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("markerwidth", "markerWidth"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TEXT_ANCHOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("text-anchor"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TABLEVALUES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("tablevalues", "tableValues"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SCRIPTLEVEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("scriptlevel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REPEATCOUNT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("repeatcount", "repeatCount"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STITCHTILES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("stitchtiles", "stitchTiles"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STARTOFFSET = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("startoffset", "startOffset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SCROLLDELAY = new AttributeName(ALL_NO_NS, SAME_LOCAL("scrolldelay"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName XMLNS_XLINK = new AttributeName(XMLNS_NS, COLONIFIED_LOCAL("xmlns:xlink", "xlink"), XMLNS_PREFIX, IS_XMLNS);
+    public static final AttributeName XLINK_TITLE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:title", "title"), XLINK_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName ARIA_INVALID = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-invalid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_PRESSED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-pressed"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_CHECKED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-checked"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName AUTOCOMPLETE = new AttributeName(ALL_NO_NS, SAME_LOCAL("autocomplete"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName ARIA_SETSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-setsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_CHANNEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-channel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName EQUALCOLUMNS = new AttributeName(ALL_NO_NS, SAME_LOCAL("equalcolumns"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DISPLAYSTYLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("displaystyle"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DATAFORMATAS = new AttributeName(ALL_NO_NS, SAME_LOCAL("dataformatas"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG | CASE_FOLDED);
+    public static final AttributeName FILL_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("fill-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONT_VARIANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-variant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONT_STRETCH = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-stretch"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FRAMESPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("framespacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName KERNELMATRIX = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("kernelmatrix", "kernelMatrix"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDEACTIVATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondeactivate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONROWSDELETE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onrowsdelete"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSELEAVE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseleave"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONFORMCHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onformchange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONCELLCHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncellchange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSEWHEEL = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmousewheel"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONMOUSEENTER = new AttributeName(ALL_NO_NS, SAME_LOCAL("onmouseenter"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONAFTERPRINT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onafterprint"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFORECOPY = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforecopy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARGINHEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("marginheight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARKERHEIGHT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("markerheight", "markerHeight"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MARKER_START = new AttributeName(ALL_NO_NS, SAME_LOCAL("marker-start"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MATHEMATICAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathematical"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LENGTHADJUST = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("lengthadjust", "lengthAdjust"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName UNSELECTABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("unselectable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName UNICODE_BIDI = new AttributeName(ALL_NO_NS, SAME_LOCAL("unicode-bidi"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName UNITS_PER_EM = new AttributeName(ALL_NO_NS, SAME_LOCAL("units-per-em"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName WORD_SPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("word-spacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName WRITING_MODE = new AttributeName(ALL_NO_NS, SAME_LOCAL("writing-mode"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName V_ALPHABETIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("v-alphabetic"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PATTERNUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("patternunits", "patternUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SPREADMETHOD = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("spreadmethod", "spreadMethod"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SURFACESCALE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("surfacescale", "surfaceScale"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE_WIDTH = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-width"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REPEAT_START = new AttributeName(ALL_NO_NS, SAME_LOCAL("repeat-start"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STDDEVIATION = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("stddeviation", "stdDeviation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STOP_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stop-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_CONTROLS = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-controls"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_HASPOPUP = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-haspopup"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ACCENT_HEIGHT = new AttributeName(ALL_NO_NS, SAME_LOCAL("accent-height"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_VALUENOW = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-valuenow"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_RELEVANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-relevant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_POSINSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-posinset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_VALUEMAX = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-valuemax"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_READONLY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-readonly"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_SELECTED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-selected"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_REQUIRED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-required"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_EXPANDED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-expanded"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_DISABLED = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-disabled"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ATTRIBUTETYPE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("attributetype", "attributeType"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ATTRIBUTENAME = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("attributename", "attributeName"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_DATATYPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-datatype"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_VALUEMIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-valuemin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BASEFREQUENCY = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("basefrequency", "baseFrequency"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLUMNSPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("columnspacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLOR_PROFILE = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-profile"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CLIPPATHUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("clippathunits", "clipPathUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DEFINITIONURL = new AttributeName(ALL_NO_NS, MATH_DIFFERENT("definitionurl", "definitionURL"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName GRADIENTUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("gradientunits", "gradientUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FLOOD_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("flood-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONAFTERUPDATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onafterupdate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONERRORUPDATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onerrorupdate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFOREPASTE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforepaste"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONLOSECAPTURE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onlosecapture"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONCONTEXTMENU = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncontextmenu"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONSELECTSTART = new AttributeName(ALL_NO_NS, SAME_LOCAL("onselectstart"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFOREPRINT = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforeprint"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MOVABLELIMITS = new AttributeName(ALL_NO_NS, SAME_LOCAL("movablelimits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LINETHICKNESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("linethickness"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName UNICODE_RANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("unicode-range"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName THINMATHSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("thinmathspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERT_ORIGIN_X = new AttributeName(ALL_NO_NS, SAME_LOCAL("vert-origin-x"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERT_ORIGIN_Y = new AttributeName(ALL_NO_NS, SAME_LOCAL("vert-origin-y"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName V_IDEOGRAPHIC = new AttributeName(ALL_NO_NS, SAME_LOCAL("v-ideographic"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PRESERVEALPHA = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("preservealpha", "preserveAlpha"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SCRIPTMINSIZE = new AttributeName(ALL_NO_NS, SAME_LOCAL("scriptminsize"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SPECIFICATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("specification"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName XLINK_ACTUATE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:actuate", "actuate"), XLINK_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName XLINK_ARCROLE = new AttributeName(XLINK_NS, COLONIFIED_LOCAL("xlink:arcrole", "arcrole"), XLINK_PREFIX, NCNAME_FOREIGN);
+    public static final AttributeName ACCEPT_CHARSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("accept-charset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ALIGNMENTSCOPE = new AttributeName(ALL_NO_NS, SAME_LOCAL("alignmentscope"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_MULTILINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-multiline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName BASELINE_SHIFT = new AttributeName(ALL_NO_NS, SAME_LOCAL("baseline-shift"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HORIZ_ORIGIN_X = new AttributeName(ALL_NO_NS, SAME_LOCAL("horiz-origin-x"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName HORIZ_ORIGIN_Y = new AttributeName(ALL_NO_NS, SAME_LOCAL("horiz-origin-y"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFOREUPDATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforeupdate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONFILTERCHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onfilterchange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONROWSINSERTED = new AttributeName(ALL_NO_NS, SAME_LOCAL("onrowsinserted"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFOREUNLOAD = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforeunload"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MATHBACKGROUND = new AttributeName(ALL_NO_NS, SAME_LOCAL("mathbackground"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LETTER_SPACING = new AttributeName(ALL_NO_NS, SAME_LOCAL("letter-spacing"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LIGHTING_COLOR = new AttributeName(ALL_NO_NS, SAME_LOCAL("lighting-color"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName THICKMATHSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("thickmathspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TEXT_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("text-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName V_MATHEMATICAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("v-mathematical"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName POINTER_EVENTS = new AttributeName(ALL_NO_NS, SAME_LOCAL("pointer-events"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PRIMITIVEUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("primitiveunits", "primitiveUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REFERRERPOLICY = new AttributeName(ALL_NO_NS, SAME_LOCAL("referrerpolicy"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SYSTEMLANGUAGE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("systemlanguage", "systemLanguage"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE_LINECAP = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-linecap"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SUBSCRIPTSHIFT = new AttributeName(ALL_NO_NS, SAME_LOCAL("subscriptshift"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE_OPACITY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-opacity"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_DROPEFFECT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-dropeffect"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_LABELLEDBY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-labelledby"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_TEMPLATEID = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-templateid"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLOR_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName CONTENTEDITABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("contenteditable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DIFFUSECONSTANT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("diffuseconstant", "diffuseConstant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDATAAVAILABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondataavailable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONCONTROLSELECT = new AttributeName(ALL_NO_NS, SAME_LOCAL("oncontrolselect"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName IMAGE_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("image-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MEDIUMMATHSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("mediummathspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName TEXT_DECORATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("text-decoration"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SHAPE_RENDERING = new AttributeName(ALL_NO_NS, SAME_LOCAL("shape-rendering"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE_LINEJOIN = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-linejoin"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REPEAT_TEMPLATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("repeat-template"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_DESCRIBEDBY = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-describedby"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName FONT_SIZE_ADJUST = new AttributeName(ALL_NO_NS, SAME_LOCAL("font-size-adjust"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName KERNELUNITLENGTH = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("kernelunitlength", "kernelUnitLength"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFOREACTIVATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforeactivate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONPROPERTYCHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onpropertychange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDATASETCHANGED = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondatasetchanged"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName MASKCONTENTUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("maskcontentunits", "maskContentUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PATTERNTRANSFORM = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("patterntransform", "patternTransform"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REQUIREDFEATURES = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("requiredfeatures", "requiredFeatures"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName RENDERING_INTENT = new AttributeName(ALL_NO_NS, SAME_LOCAL("rendering-intent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SPECULAREXPONENT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("specularexponent", "specularExponent"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SPECULARCONSTANT = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("specularconstant", "specularConstant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SUPERSCRIPTSHIFT = new AttributeName(ALL_NO_NS, SAME_LOCAL("superscriptshift"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE_DASHARRAY = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-dasharray"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName XCHANNELSELECTOR = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("xchannelselector", "xChannelSelector"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName YCHANNELSELECTOR = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("ychannelselector", "yChannelSelector"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_AUTOCOMPLETE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-autocomplete"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ENABLE_BACKGROUND = new AttributeName(ALL_NO_NS, SAME_LOCAL("enable-background"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName DOMINANT_BASELINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("dominant-baseline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName GRADIENTTRANSFORM = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("gradienttransform", "gradientTransform"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFORDEACTIVATE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbefordeactivate"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONDATASETCOMPLETE = new AttributeName(ALL_NO_NS, SAME_LOCAL("ondatasetcomplete"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OVERLINE_POSITION = new AttributeName(ALL_NO_NS, SAME_LOCAL("overline-position"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONBEFOREEDITFOCUS = new AttributeName(ALL_NO_NS, SAME_LOCAL("onbeforeeditfocus"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName LIMITINGCONEANGLE = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("limitingconeangle", "limitingConeAngle"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERYTHINMATHSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("verythinmathspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE_DASHOFFSET = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-dashoffset"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STROKE_MITERLIMIT = new AttributeName(ALL_NO_NS, SAME_LOCAL("stroke-miterlimit"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ALIGNMENT_BASELINE = new AttributeName(ALL_NO_NS, SAME_LOCAL("alignment-baseline"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ONREADYSTATECHANGE = new AttributeName(ALL_NO_NS, SAME_LOCAL("onreadystatechange"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName OVERLINE_THICKNESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("overline-thickness"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName UNDERLINE_POSITION = new AttributeName(ALL_NO_NS, SAME_LOCAL("underline-position"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERYTHICKMATHSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("verythickmathspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName REQUIREDEXTENSIONS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("requiredextensions", "requiredExtensions"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLOR_INTERPOLATION = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-interpolation"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName UNDERLINE_THICKNESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("underline-thickness"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PRESERVEASPECTRATIO = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("preserveaspectratio", "preserveAspectRatio"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName PATTERNCONTENTUNITS = new AttributeName(ALL_NO_NS, SVG_DIFFERENT("patterncontentunits", "patternContentUnits"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_MULTISELECTABLE = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-multiselectable"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName SCRIPTSIZEMULTIPLIER = new AttributeName(ALL_NO_NS, SAME_LOCAL("scriptsizemultiplier"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName ARIA_ACTIVEDESCENDANT = new AttributeName(ALL_NO_NS, SAME_LOCAL("aria-activedescendant"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERYVERYTHINMATHSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("veryverythinmathspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName VERYVERYTHICKMATHSPACE = new AttributeName(ALL_NO_NS, SAME_LOCAL("veryverythickmathspace"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STRIKETHROUGH_POSITION = new AttributeName(ALL_NO_NS, SAME_LOCAL("strikethrough-position"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName STRIKETHROUGH_THICKNESS = new AttributeName(ALL_NO_NS, SAME_LOCAL("strikethrough-thickness"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName GLYPH_ORIENTATION_VERTICAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("glyph-orientation-vertical"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName COLOR_INTERPOLATION_FILTERS = new AttributeName(ALL_NO_NS, SAME_LOCAL("color-interpolation-filters"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    public static final AttributeName GLYPH_ORIENTATION_HORIZONTAL = new AttributeName(ALL_NO_NS, SAME_LOCAL("glyph-orientation-horizontal"), ALL_NO_PREFIX, NCNAME_HTML | NCNAME_FOREIGN | NCNAME_LANG);
+    private final static @NoLength AttributeName[] ATTRIBUTE_NAMES = {
+    D,
+    K,
+    R,
+    X,
+    Y,
+    Z,
+    BY,
+    CX,
+    CY,
+    DX,
+    DY,
+    G2,
+    G1,
+    FX,
+    FY,
+    K4,
+    K2,
+    K3,
+    K1,
+    ID,
+    IN,
+    U2,
+    U1,
+    RT,
+    RX,
+    RY,
+    TO,
+    Y2,
+    Y1,
+    X1,
+    X2,
+    ALT,
+    DIR,
+    DUR,
+    END,
+    FOR,
+    IN2,
+    MAX,
+    MIN,
+    LOW,
+    REL,
+    REV,
+    SRC,
+    AXIS,
+    ABBR,
+    BBOX,
+    CITE,
+    CODE,
+    BIAS,
+    COLS,
+    CLIP,
+    CHAR,
+    BASE,
+    EDGE,
+    DATA,
+    FILL,
+    FROM,
+    FORM,
+    FACE,
+    HIGH,
+    HREF,
+    OPEN,
+    ICON,
+    NAME,
+    MODE,
+    MASK,
+    LINK,
+    LANG,
+    LOOP,
+    LIST,
+    TYPE,
+    WHEN,
+    WRAP,
+    TEXT,
+    PATH,
+    PING,
+    REFX,
+    REFY,
+    SIZE,
+    SEED,
+    ROWS,
+    SPAN,
+    STEP,
+    ROLE,
+    XREF,
+    ASYNC,
+    ALINK,
+    ALIGN,
+    CLOSE,
+    COLOR,
+    CLASS,
+    CLEAR,
+    BEGIN,
+    DEPTH,
+    DEFER,
+    FENCE,
+    FRAME,
+    ISMAP,
+    ONEND,
+    INDEX,
+    ORDER,
+    OTHER,
+    ONCUT,
+    NARGS,
+    MEDIA,
+    LABEL,
+    LOCAL,
+    WIDTH,
+    TITLE,
+    VLINK,
+    VALUE,
+    SLOPE,
+    SHAPE,
+    SCOPE,
+    SCALE,
+    SPEED,
+    STYLE,
+    RULES,
+    STEMH,
+    SIZES,
+    STEMV,
+    START,
+    XMLNS,
+    ACCEPT,
+    ACCENT,
+    ASCENT,
+    ACTIVE,
+    ALTIMG,
+    ACTION,
+    BORDER,
+    CURSOR,
+    COORDS,
+    FILTER,
+    FORMAT,
+    HIDDEN,
+    HSPACE,
+    HEIGHT,
+    ONMOVE,
+    ONLOAD,
+    ONDRAG,
+    ORIGIN,
+    ONZOOM,
+    ONHELP,
+    ONSTOP,
+    ONDROP,
+    ONBLUR,
+    OBJECT,
+    OFFSET,
+    ORIENT,
+    ONCOPY,
+    NOWRAP,
+    NOHREF,
+    MACROS,
+    METHOD,
+    LOWSRC,
+    LSPACE,
+    LQUOTE,
+    USEMAP,
+    WIDTHS,
+    TARGET,
+    VALUES,
+    VALIGN,
+    VSPACE,
+    POSTER,
+    POINTS,
+    PROMPT,
+    SRCDOC,
+    SCOPED,
+    STRING,
+    SCHEME,
+    STROKE,
+    RADIUS,
+    RESULT,
+    REPEAT,
+    SRCSET,
+    RSPACE,
+    ROTATE,
+    RQUOTE,
+    ALTTEXT,
+    ARCHIVE,
+    AZIMUTH,
+    CLOSURE,
+    CHECKED,
+    CLASSID,
+    CHAROFF,
+    BGCOLOR,
+    COLSPAN,
+    CHARSET,
+    COMPACT,
+    CONTENT,
+    ENCTYPE,
+    DATASRC,
+    DATAFLD,
+    DECLARE,
+    DISPLAY,
+    DIVISOR,
+    DEFAULT,
+    DESCENT,
+    KERNING,
+    HANGING,
+    HEADERS,
+    ONPASTE,
+    ONCLICK,
+    OPTIMUM,
+    ONBEGIN,
+    ONKEYUP,
+    ONFOCUS,
+    ONERROR,
+    ONINPUT,
+    ONABORT,
+    ONSTART,
+    ONRESET,
+    OPACITY,
+    NOSHADE,
+    MINSIZE,
+    MAXSIZE,
+    LARGEOP,
+    UNICODE,
+    TARGETX,
+    TARGETY,
+    VIEWBOX,
+    VERSION,
+    PATTERN,
+    PROFILE,
+    SPACING,
+    RESTART,
+    ROWSPAN,
+    SANDBOX,
+    SUMMARY,
+    STANDBY,
+    REPLACE,
+    AUTOPLAY,
+    ADDITIVE,
+    CALCMODE,
+    CODETYPE,
+    CODEBASE,
+    CONTROLS,
+    BEVELLED,
+    BASELINE,
+    EXPONENT,
+    EDGEMODE,
+    ENCODING,
+    GLYPHREF,
+    DATETIME,
+    DISABLED,
+    FONTSIZE,
+    KEYTIMES,
+    PANOSE_1,
+    HREFLANG,
+    ONRESIZE,
+    ONCHANGE,
+    ONBOUNCE,
+    ONUNLOAD,
+    ONFINISH,
+    ONSCROLL,
+    OPERATOR,
+    OVERFLOW,
+    ONSUBMIT,
+    ONREPEAT,
+    ONSELECT,
+    NOTATION,
+    NORESIZE,
+    MANIFEST,
+    MATHSIZE,
+    MULTIPLE,
+    LONGDESC,
+    LANGUAGE,
+    TEMPLATE,
+    TABINDEX,
+    PROPERTY,
+    READONLY,
+    SELECTED,
+    ROWLINES,
+    SEAMLESS,
+    ROWALIGN,
+    STRETCHY,
+    REQUIRED,
+    XML_BASE,
+    XML_LANG,
+    X_HEIGHT,
+    ARIA_OWNS,
+    AUTOFOCUS,
+    ARIA_SORT,
+    ACCESSKEY,
+    ARIA_BUSY,
+    ARIA_GRAB,
+    AMPLITUDE,
+    ARIA_LIVE,
+    CLIP_RULE,
+    CLIP_PATH,
+    EQUALROWS,
+    ELEVATION,
+    DIRECTION,
+    DRAGGABLE,
+    FILL_RULE,
+    FONTSTYLE,
+    FONT_SIZE,
+    KEYSYSTEM,
+    KEYPOINTS,
+    HIDEFOCUS,
+    ONMESSAGE,
+    INTERCEPT,
+    ONDRAGEND,
+    ONMOVEEND,
+    ONINVALID,
+    INTEGRITY,
+    ONKEYDOWN,
+    ONFOCUSIN,
+    ONMOUSEUP,
+    INPUTMODE,
+    ONROWEXIT,
+    MATHCOLOR,
+    MASKUNITS,
+    MAXLENGTH,
+    LINEBREAK,
+    TRANSFORM,
+    V_HANGING,
+    VALUETYPE,
+    POINTSATZ,
+    POINTSATX,
+    POINTSATY,
+    SYMMETRIC,
+    SCROLLING,
+    REPEATDUR,
+    SELECTION,
+    SEPARATOR,
+    XML_SPACE,
+    AUTOSUBMIT,
+    ALPHABETIC,
+    ACTIONTYPE,
+    ACCUMULATE,
+    ARIA_LEVEL,
+    COLUMNSPAN,
+    CAP_HEIGHT,
+    BACKGROUND,
+    GLYPH_NAME,
+    GROUPALIGN,
+    FONTFAMILY,
+    FONTWEIGHT,
+    FONT_STYLE,
+    KEYSPLINES,
+    HTTP_EQUIV,
+    ONACTIVATE,
+    OCCURRENCE,
+    IRRELEVANT,
+    ONDBLCLICK,
+    ONDRAGDROP,
+    ONKEYPRESS,
+    ONROWENTER,
+    ONDRAGOVER,
+    ONFOCUSOUT,
+    ONMOUSEOUT,
+    NUMOCTAVES,
+    MARKER_MID,
+    MARKER_END,
+    TEXTLENGTH,
+    VISIBILITY,
+    VIEWTARGET,
+    VERT_ADV_Y,
+    PATHLENGTH,
+    REPEAT_MAX,
+    RADIOGROUP,
+    STOP_COLOR,
+    SEPARATORS,
+    REPEAT_MIN,
+    ROWSPACING,
+    ZOOMANDPAN,
+    XLINK_TYPE,
+    XLINK_ROLE,
+    XLINK_HREF,
+    XLINK_SHOW,
+    ACCENTUNDER,
+    ARIA_SECRET,
+    ARIA_ATOMIC,
+    ARIA_HIDDEN,
+    ARIA_FLOWTO,
+    ARABIC_FORM,
+    CELLPADDING,
+    CELLSPACING,
+    COLUMNWIDTH,
+    CROSSORIGIN,
+    COLUMNALIGN,
+    COLUMNLINES,
+    CONTEXTMENU,
+    BASEPROFILE,
+    FONT_FAMILY,
+    FRAMEBORDER,
+    FILTERUNITS,
+    FLOOD_COLOR,
+    FONT_WEIGHT,
+    HORIZ_ADV_X,
+    ONDRAGLEAVE,
+    ONMOUSEMOVE,
+    ORIENTATION,
+    ONMOUSEDOWN,
+    ONMOUSEOVER,
+    ONDRAGENTER,
+    IDEOGRAPHIC,
+    ONBEFORECUT,
+    ONFORMINPUT,
+    ONDRAGSTART,
+    ONMOVESTART,
+    MARKERUNITS,
+    MATHVARIANT,
+    MARGINWIDTH,
+    MARKERWIDTH,
+    TEXT_ANCHOR,
+    TABLEVALUES,
+    SCRIPTLEVEL,
+    REPEATCOUNT,
+    STITCHTILES,
+    STARTOFFSET,
+    SCROLLDELAY,
+    XMLNS_XLINK,
+    XLINK_TITLE,
+    ARIA_INVALID,
+    ARIA_PRESSED,
+    ARIA_CHECKED,
+    AUTOCOMPLETE,
+    ARIA_SETSIZE,
+    ARIA_CHANNEL,
+    EQUALCOLUMNS,
+    DISPLAYSTYLE,
+    DATAFORMATAS,
+    FILL_OPACITY,
+    FONT_VARIANT,
+    FONT_STRETCH,
+    FRAMESPACING,
+    KERNELMATRIX,
+    ONDEACTIVATE,
+    ONROWSDELETE,
+    ONMOUSELEAVE,
+    ONFORMCHANGE,
+    ONCELLCHANGE,
+    ONMOUSEWHEEL,
+    ONMOUSEENTER,
+    ONAFTERPRINT,
+    ONBEFORECOPY,
+    MARGINHEIGHT,
+    MARKERHEIGHT,
+    MARKER_START,
+    MATHEMATICAL,
+    LENGTHADJUST,
+    UNSELECTABLE,
+    UNICODE_BIDI,
+    UNITS_PER_EM,
+    WORD_SPACING,
+    WRITING_MODE,
+    V_ALPHABETIC,
+    PATTERNUNITS,
+    SPREADMETHOD,
+    SURFACESCALE,
+    STROKE_WIDTH,
+    REPEAT_START,
+    STDDEVIATION,
+    STOP_OPACITY,
+    ARIA_CONTROLS,
+    ARIA_HASPOPUP,
+    ACCENT_HEIGHT,
+    ARIA_VALUENOW,
+    ARIA_RELEVANT,
+    ARIA_POSINSET,
+    ARIA_VALUEMAX,
+    ARIA_READONLY,
+    ARIA_SELECTED,
+    ARIA_REQUIRED,
+    ARIA_EXPANDED,
+    ARIA_DISABLED,
+    ATTRIBUTETYPE,
+    ATTRIBUTENAME,
+    ARIA_DATATYPE,
+    ARIA_VALUEMIN,
+    BASEFREQUENCY,
+    COLUMNSPACING,
+    COLOR_PROFILE,
+    CLIPPATHUNITS,
+    DEFINITIONURL,
+    GRADIENTUNITS,
+    FLOOD_OPACITY,
+    ONAFTERUPDATE,
+    ONERRORUPDATE,
+    ONBEFOREPASTE,
+    ONLOSECAPTURE,
+    ONCONTEXTMENU,
+    ONSELECTSTART,
+    ONBEFOREPRINT,
+    MOVABLELIMITS,
+    LINETHICKNESS,
+    UNICODE_RANGE,
+    THINMATHSPACE,
+    VERT_ORIGIN_X,
+    VERT_ORIGIN_Y,
+    V_IDEOGRAPHIC,
+    PRESERVEALPHA,
+    SCRIPTMINSIZE,
+    SPECIFICATION,
+    XLINK_ACTUATE,
+    XLINK_ARCROLE,
+    ACCEPT_CHARSET,
+    ALIGNMENTSCOPE,
+    ARIA_MULTILINE,
+    BASELINE_SHIFT,
+    HORIZ_ORIGIN_X,
+    HORIZ_ORIGIN_Y,
+    ONBEFOREUPDATE,
+    ONFILTERCHANGE,
+    ONROWSINSERTED,
+    ONBEFOREUNLOAD,
+    MATHBACKGROUND,
+    LETTER_SPACING,
+    LIGHTING_COLOR,
+    THICKMATHSPACE,
+    TEXT_RENDERING,
+    V_MATHEMATICAL,
+    POINTER_EVENTS,
+    PRIMITIVEUNITS,
+    REFERRERPOLICY,
+    SYSTEMLANGUAGE,
+    STROKE_LINECAP,
+    SUBSCRIPTSHIFT,
+    STROKE_OPACITY,
+    ARIA_DROPEFFECT,
+    ARIA_LABELLEDBY,
+    ARIA_TEMPLATEID,
+    COLOR_RENDERING,
+    CONTENTEDITABLE,
+    DIFFUSECONSTANT,
+    ONDATAAVAILABLE,
+    ONCONTROLSELECT,
+    IMAGE_RENDERING,
+    MEDIUMMATHSPACE,
+    TEXT_DECORATION,
+    SHAPE_RENDERING,
+    STROKE_LINEJOIN,
+    REPEAT_TEMPLATE,
+    ARIA_DESCRIBEDBY,
+    FONT_SIZE_ADJUST,
+    KERNELUNITLENGTH,
+    ONBEFOREACTIVATE,
+    ONPROPERTYCHANGE,
+    ONDATASETCHANGED,
+    MASKCONTENTUNITS,
+    PATTERNTRANSFORM,
+    REQUIREDFEATURES,
+    RENDERING_INTENT,
+    SPECULAREXPONENT,
+    SPECULARCONSTANT,
+    SUPERSCRIPTSHIFT,
+    STROKE_DASHARRAY,
+    XCHANNELSELECTOR,
+    YCHANNELSELECTOR,
+    ARIA_AUTOCOMPLETE,
+    ENABLE_BACKGROUND,
+    DOMINANT_BASELINE,
+    GRADIENTTRANSFORM,
+    ONBEFORDEACTIVATE,
+    ONDATASETCOMPLETE,
+    OVERLINE_POSITION,
+    ONBEFOREEDITFOCUS,
+    LIMITINGCONEANGLE,
+    VERYTHINMATHSPACE,
+    STROKE_DASHOFFSET,
+    STROKE_MITERLIMIT,
+    ALIGNMENT_BASELINE,
+    ONREADYSTATECHANGE,
+    OVERLINE_THICKNESS,
+    UNDERLINE_POSITION,
+    VERYTHICKMATHSPACE,
+    REQUIREDEXTENSIONS,
+    COLOR_INTERPOLATION,
+    UNDERLINE_THICKNESS,
+    PRESERVEASPECTRATIO,
+    PATTERNCONTENTUNITS,
+    ARIA_MULTISELECTABLE,
+    SCRIPTSIZEMULTIPLIER,
+    ARIA_ACTIVEDESCENDANT,
+    VERYVERYTHINMATHSPACE,
+    VERYVERYTHICKMATHSPACE,
+    STRIKETHROUGH_POSITION,
+    STRIKETHROUGH_THICKNESS,
+    GLYPH_ORIENTATION_VERTICAL,
+    COLOR_INTERPOLATION_FILTERS,
+    GLYPH_ORIENTATION_HORIZONTAL,
+    };
+    private final static int[] ATTRIBUTE_HASHES = {
+    1153,
+    1383,
+    1601,
+    1793,
+    1827,
+    1857,
+    68600,
+    69146,
+    69177,
+    70237,
+    70270,
+    71572,
+    71669,
+    72415,
+    72444,
+    74846,
+    74904,
+    74943,
+    75001,
+    75276,
+    75590,
+    84742,
+    84839,
+    85575,
+    85963,
+    85992,
+    87204,
+    88074,
+    88171,
+    89130,
+    89163,
+    3207892,
+    3283895,
+    3284791,
+    3338752,
+    3358197,
+    3369562,
+    3539124,
+    3562402,
+    3574260,
+    3670335,
+    3696933,
+    3721879,
+    135280021,
+    135346322,
+    136317019,
+    136475749,
+    136548517,
+    136652214,
+    136884919,
+    136902418,
+    136942992,
+    137292068,
+    139120259,
+    139785574,
+    142250603,
+    142314056,
+    142331176,
+    142519584,
+    144752417,
+    145106895,
+    146147200,
+    146765926,
+    148805544,
+    149655723,
+    149809441,
+    150018784,
+    150445028,
+    150813181,
+    150923321,
+    152528754,
+    152536216,
+    152647366,
+    152962785,
+    155219321,
+    155654904,
+    157317483,
+    157350248,
+    157437941,
+    157447478,
+    157604838,
+    157685404,
+    157894402,
+    158315188,
+    166078431,
+    169409980,
+    169700259,
+    169856932,
+    170007032,
+    170409695,
+    170466488,
+    170513710,
+    170608367,
+    173028944,
+    173896963,
+    176090625,
+    176129212,
+    179390001,
+    179489057,
+    179627464,
+    179840468,
+    179849042,
+    180004216,
+    181779081,
+    183027151,
+    183645319,
+    183698797,
+    185922012,
+    185997252,
+    188312483,
+    188675799,
+    190977533,
+    190992569,
+    191006194,
+    191033518,
+    191038774,
+    191096249,
+    191166163,
+    191194426,
+    191443343,
+    191522106,
+    191568039,
+    200104642,
+    202506661,
+    202537381,
+    202602917,
+    203070590,
+    203120766,
+    203389054,
+    203690071,
+    203971238,
+    203986524,
+    209040857,
+    209125756,
+    212055489,
+    212322418,
+    212746849,
+    213002877,
+    213055164,
+    213088023,
+    213259873,
+    213273386,
+    213435118,
+    213437318,
+    213438231,
+    213493071,
+    213532268,
+    213542834,
+    213584431,
+    213659891,
+    215285828,
+    215880731,
+    216112976,
+    216684637,
+    217369699,
+    217565298,
+    217576549,
+    218186795,
+    219743185,
+    220082234,
+    221623802,
+    221986406,
+    222283890,
+    223089542,
+    223138630,
+    223311265,
+    224431494,
+    224547358,
+    224587256,
+    224589550,
+    224655650,
+    224785518,
+    224810917,
+    224813302,
+    225126263,
+    225429618,
+    225432950,
+    225440869,
+    236107233,
+    236709921,
+    236838947,
+    237117095,
+    237143271,
+    237172455,
+    237209953,
+    237354143,
+    237372743,
+    237668065,
+    237703073,
+    237714273,
+    239743521,
+    240512803,
+    240522627,
+    240560417,
+    240656513,
+    241015715,
+    241062755,
+    241065383,
+    243523041,
+    245865199,
+    246261793,
+    246556195,
+    246774817,
+    246923491,
+    246928419,
+    246981667,
+    247014847,
+    247058369,
+    247112833,
+    247118177,
+    247119137,
+    247128739,
+    247316903,
+    249533729,
+    250235623,
+    250269543,
+    251402351,
+    252339047,
+    253260911,
+    253293679,
+    254844367,
+    255547879,
+    256077281,
+    256345377,
+    258124199,
+    258354465,
+    258605063,
+    258744193,
+    258845603,
+    258856961,
+    258926689,
+    269869248,
+    270174334,
+    270709417,
+    270778994,
+    270781796,
+    271102503,
+    271478858,
+    271490090,
+    272870654,
+    273335275,
+    273369140,
+    273924313,
+    274108530,
+    274116736,
+    276818662,
+    277476156,
+    279156579,
+    279349675,
+    280108533,
+    280128712,
+    280132869,
+    280162403,
+    280280292,
+    280413430,
+    280506130,
+    280677397,
+    280678580,
+    280686710,
+    280689066,
+    282736758,
+    283110901,
+    283275116,
+    283823226,
+    283890012,
+    284479340,
+    284606461,
+    286700477,
+    286798916,
+    290055764,
+    291557706,
+    291665349,
+    291804100,
+    292138018,
+    292166446,
+    292418738,
+    292451039,
+    300298041,
+    300374839,
+    300597935,
+    303073389,
+    303083839,
+    303266673,
+    303354997,
+    303430688,
+    303576261,
+    303724281,
+    303819694,
+    304242723,
+    304382625,
+    306247792,
+    307227811,
+    307468786,
+    307724489,
+    310252031,
+    310358241,
+    310373094,
+    310833159,
+    311015256,
+    313357609,
+    313683893,
+    313701861,
+    313706996,
+    313707317,
+    313710350,
+    313795700,
+    314027746,
+    314038181,
+    314091299,
+    314205627,
+    314233813,
+    316741830,
+    316797986,
+    317486755,
+    317794164,
+    320076137,
+    322657125,
+    322887778,
+    323506876,
+    323572412,
+    323605180,
+    325060058,
+    325320188,
+    325398738,
+    325541490,
+    325671619,
+    333868843,
+    336806130,
+    337212108,
+    337282686,
+    337285434,
+    337585223,
+    338036037,
+    338298087,
+    338566051,
+    340943551,
+    341190970,
+    342995704,
+    343352124,
+    343912673,
+    344585053,
+    346977248,
+    347218098,
+    347262163,
+    347278576,
+    347438191,
+    347655959,
+    347684788,
+    347726430,
+    347727772,
+    347776035,
+    347776629,
+    349500753,
+    350880161,
+    350887073,
+    353384123,
+    355496998,
+    355906922,
+    355979793,
+    356545959,
+    358637867,
+    358905016,
+    359164318,
+    359247286,
+    359350571,
+    359579447,
+    365560330,
+    367399355,
+    367420285,
+    367510727,
+    368013212,
+    370234760,
+    370353345,
+    370710317,
+    371074566,
+    371122285,
+    371194213,
+    371448425,
+    371448430,
+    371545055,
+    371593469,
+    371596922,
+    371758751,
+    371964792,
+    372151328,
+    376550136,
+    376710172,
+    376795771,
+    376826271,
+    376906556,
+    380514830,
+    380774774,
+    380775037,
+    381030322,
+    381136500,
+    381281631,
+    381282269,
+    381285504,
+    381330595,
+    381331422,
+    381335911,
+    381336484,
+    383907298,
+    383917408,
+    384595009,
+    384595013,
+    387799894,
+    387823201,
+    392581647,
+    392584937,
+    392742684,
+    392906485,
+    393003349,
+    400644707,
+    400973830,
+    404428547,
+    404432113,
+    404432865,
+    404469244,
+    404478897,
+    404694860,
+    406887479,
+    408294949,
+    408789955,
+    410022510,
+    410467324,
+    410586448,
+    410945965,
+    411845275,
+    414327152,
+    414327932,
+    414329781,
+    414346257,
+    414346439,
+    414639928,
+    414835998,
+    414894517,
+    414986533,
+    417465377,
+    417465381,
+    417492216,
+    418259232,
+    419310946,
+    420103495,
+    420242342,
+    420380455,
+    420658662,
+    420717432,
+    423183880,
+    424539259,
+    425929170,
+    425972964,
+    426050649,
+    426126450,
+    426142833,
+    426607922,
+    437289840,
+    437347469,
+    437412335,
+    437423943,
+    437455540,
+    437462252,
+    437597991,
+    437617485,
+    437986305,
+    437986507,
+    437986828,
+    437987072,
+    438015591,
+    438034813,
+    438038966,
+    438179623,
+    438347971,
+    438483573,
+    438547062,
+    438895551,
+    441592676,
+    442032555,
+    443548979,
+    447881379,
+    447881655,
+    447881895,
+    447887844,
+    448416189,
+    448445746,
+    448449012,
+    450942191,
+    452816744,
+    453668677,
+    454434495,
+    456610076,
+    456642844,
+    456738709,
+    457544600,
+    459451897,
+    459680944,
+    468058810,
+    468083581,
+    470964084,
+    471470955,
+    471567278,
+    472267822,
+    481177859,
+    481210627,
+    481435874,
+    481455115,
+    481485378,
+    481490218,
+    485105638,
+    486005878,
+    486383494,
+    487988916,
+    488103783,
+    490661867,
+    491574090,
+    491578272,
+    492891370,
+    493041952,
+    493441205,
+    493582844,
+    493716979,
+    504577572,
+    504740359,
+    505091638,
+    505592418,
+    505656212,
+    509516275,
+    514998531,
+    515571132,
+    515594682,
+    518712698,
+    521362273,
+    526592419,
+    526807354,
+    527348842,
+    538294791,
+    544689535,
+    545535009,
+    548544752,
+    548563346,
+    548595116,
+    551679010,
+    558034099,
+    560329411,
+    560356209,
+    560671018,
+    560671152,
+    560692590,
+    560845442,
+    569212097,
+    569474241,
+    572252718,
+    575326764,
+    576174758,
+    576190819,
+    582099184,
+    582099438,
+    582372519,
+    582558889,
+    586552164,
+    591325418,
+    594231990,
+    594243961,
+    605711268,
+    615672071,
+    616086845,
+    621792370,
+    624879850,
+    627432831,
+    640040548,
+    654392808,
+    658675477,
+    659420283,
+    672891587,
+    694768102,
+    705890982,
+    725543146,
+    759097578,
+    761686526,
+    795383908,
+    878105336,
+    908643300,
+    945213471,
+    };
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/CoalescingTreeBuilder.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/CoalescingTreeBuilder.java
new file mode 100644
index 000000000..01d76d700
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/CoalescingTreeBuilder.java
@@ -0,0 +1,90 @@
+/*
+ * Copyright (c) 2008-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.NoLength;
+
+import org.xml.sax.SAXException;
+
+/**
+ * A common superclass for tree builders that coalesce their text nodes.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public abstract class CoalescingTreeBuilder<T> extends TreeBuilder<T> {
+
+    protected final void accumulateCharacters(@NoLength char[] buf, int start,
+            int length) throws SAXException {
+        System.arraycopy(buf, start, charBuffer, charBufferLen, length);
+        charBufferLen += length;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendCharacters(java.lang.Object, char[], int, int)
+     */
+    @Override protected final void appendCharacters(T parent, char[] buf, int start,
+            int length) throws SAXException {
+        appendCharacters(parent, new String(buf, start, length));
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendIsindexPrompt(java.lang.Object)
+     */
+    @Override protected void appendIsindexPrompt(T parent) throws SAXException {
+        appendCharacters(parent, "This is a searchable index. Enter search keywords: ");
+    }
+
+    protected abstract void appendCharacters(T parent, String text) throws SAXException;
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendComment(java.lang.Object, char[], int, int)
+     */
+    @Override final protected void appendComment(T parent, char[] buf, int start,
+            int length) throws SAXException {
+        appendComment(parent, new String(buf, start, length));
+    }
+
+    protected abstract void appendComment(T parent, String comment) throws SAXException;
+    
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendCommentToDocument(char[], int, int)
+     */
+    @Override protected final void appendCommentToDocument(char[] buf, int start,
+            int length) throws SAXException {
+        // TODO Auto-generated method stub
+        appendCommentToDocument(new String(buf, start, length));
+    }
+
+    protected abstract void appendCommentToDocument(String comment) throws SAXException;
+    
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#insertFosterParentedCharacters(char[], int, int, java.lang.Object, java.lang.Object)
+     */
+    @Override protected final void insertFosterParentedCharacters(char[] buf, int start,
+            int length, T table, T stackParent) throws SAXException {
+        insertFosterParentedCharacters(new String(buf, start, length), table, stackParent);
+    }
+    
+    protected abstract void insertFosterParentedCharacters(String text, T table, T stackParent) throws SAXException;
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/ElementName.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/ElementName.java
new file mode 100644
index 000000000..ee0493318
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/ElementName.java
@@ -0,0 +1,1614 @@
+/*
+ * Copyright (c) 2008-2016 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import java.util.Arrays;
+
+import nu.validator.htmlparser.annotation.Inline;
+import nu.validator.htmlparser.annotation.Local;
+import nu.validator.htmlparser.annotation.NoLength;
+import nu.validator.htmlparser.annotation.Virtual;
+import nu.validator.htmlparser.common.Interner;
+
+public final class ElementName
+// uncomment when regenerating self
+//        implements Comparable<ElementName>
+{
+
+    /**
+     * The mask for extracting the dispatch group.
+     */
+    public static final int GROUP_MASK = 127;
+
+    /**
+     * Indicates that the element is not a pre-interned element. Forbidden
+     * on preinterned elements.
+     */
+    public static final int CUSTOM = (1 << 30);
+
+    /**
+     * Indicates that the element is in the "special" category. This bit
+     * should not be pre-set on MathML or SVG specials--only on HTML specials.
+     */
+    public static final int SPECIAL = (1 << 29);
+
+    /**
+     * The element is foster-parenting. This bit should be pre-set on elements
+     * that are foster-parenting as HTML.
+     */
+    public static final int FOSTER_PARENTING = (1 << 28);
+
+    /**
+     * The element is scoping. This bit should be pre-set on elements
+     * that are scoping as HTML.
+     */
+    public static final int SCOPING = (1 << 27);
+
+    /**
+     * The element is scoping as SVG.
+     */
+    public static final int SCOPING_AS_SVG = (1 << 26);
+
+    /**
+     * The element is scoping as MathML.
+     */
+    public static final int SCOPING_AS_MATHML = (1 << 25);
+
+    /**
+     * The element is an HTML integration point.
+     */
+    public static final int HTML_INTEGRATION_POINT = (1 << 24);
+
+    /**
+     * The element has an optional end tag.
+     */
+    public static final int OPTIONAL_END_TAG = (1 << 23);
+
+    public static final ElementName NULL_ELEMENT_NAME = new ElementName(null);
+
+    public final @Local String name;
+
+    public final @Local String camelCaseName;
+
+    /**
+     * The lowest 7 bits are the dispatch group. The high bits are flags.
+     */
+    public final int flags;
+
+    @Inline public int getFlags() {
+        return flags;
+    }
+
+    public int getGroup() {
+        return flags & GROUP_MASK;
+    }
+
+    public boolean isCustom() {
+        return (flags & CUSTOM) != 0;
+    }
+
+    static ElementName elementNameByBuffer(@NoLength char[] buf, int offset, int length, Interner interner) {
+        int hash = ElementName.bufToHash(buf, length);
+        int index = Arrays.binarySearch(ElementName.ELEMENT_HASHES, hash);
+        if (index < 0) {
+            return new ElementName(Portability.newLocalNameFromBuffer(buf, offset, length, interner));
+        } else {
+            ElementName elementName = ElementName.ELEMENT_NAMES[index];
+            @Local String name = elementName.name;
+            if (!Portability.localEqualsBuffer(name, buf, offset, length)) {
+                return new ElementName(Portability.newLocalNameFromBuffer(buf,
+                        offset, length, interner));
+            }
+            return elementName;
+        }
+    }
+
+    /**
+     * This method has to return a unique integer for each well-known
+     * lower-cased element name.
+     *
+     * @param buf
+     * @param len
+     * @return
+     */
+    private static int bufToHash(@NoLength char[] buf, int len) {
+        int hash = len;
+        hash <<= 5;
+        hash += buf[0] - 0x60;
+        int j = len;
+        for (int i = 0; i < 4 && j > 0; i++) {
+            j--;
+            hash <<= 5;
+            hash += buf[j] - 0x60;
+        }
+        return hash;
+    }
+
+    private ElementName(@Local String name, @Local String camelCaseName,
+            int flags) {
+        this.name = name;
+        this.camelCaseName = camelCaseName;
+        this.flags = flags;
+    }
+
+    protected ElementName(@Local String name) {
+        this.name = name;
+        this.camelCaseName = name;
+        this.flags = TreeBuilder.OTHER | CUSTOM;
+    }
+
+    @Virtual void release() {
+        // No-op in Java.
+        // Implement as delete this in subclass.
+        // Be sure to release the local name
+    }
+
+    @SuppressWarnings("unused") @Virtual private void destructor() {
+    }
+
+    @Virtual public ElementName cloneElementName(Interner interner) {
+        return this;
+    }
+
+    // START CODE ONLY USED FOR GENERATING CODE uncomment and run to regenerate
+
+//    /**
+//     * @see java.lang.Object#toString()
+//     */
+//    @Override public String toString() {
+//        return "(\"" + name + "\", \"" + camelCaseName + "\", " + decomposedFlags() + ")";
+//    }
+//
+//    private String decomposedFlags() {
+//        StringBuilder buf = new StringBuilder("TreeBuilder.");
+//        buf.append(treeBuilderGroupToName());
+//        if ((flags & SPECIAL) != 0) {
+//            buf.append(" | SPECIAL");
+//        }
+//        if ((flags & FOSTER_PARENTING) != 0) {
+//            buf.append(" | FOSTER_PARENTING");
+//        }
+//        if ((flags & SCOPING) != 0) {
+//            buf.append(" | SCOPING");
+//        }
+//        if ((flags & SCOPING_AS_MATHML) != 0) {
+//            buf.append(" | SCOPING_AS_MATHML");
+//        }
+//        if ((flags & SCOPING_AS_SVG) != 0) {
+//            buf.append(" | SCOPING_AS_SVG");
+//        }
+//        if ((flags & OPTIONAL_END_TAG) != 0) {
+//            buf.append(" | OPTIONAL_END_TAG");
+//        }
+//        return buf.toString();
+//    }
+//
+//    private String constName() {
+//        char[] buf = new char[name.length()];
+//        for (int i = 0; i < name.length(); i++) {
+//            char c = name.charAt(i);
+//            if (c == '-') {
+//                buf[i] = '_';
+//            } else if (c >= '0' && c <= '9') {
+//                buf[i] = c;
+//            } else {
+//                buf[i] = (char) (c - 0x20);
+//            }
+//        }
+//        return new String(buf);
+//    }
+//
+//    private int hash() {
+//        return bufToHash(name.toCharArray(), name.length());
+//    }
+//
+//    public int compareTo(ElementName other) {
+//        int thisHash = this.hash();
+//        int otherHash = other.hash();
+//        if (thisHash < otherHash) {
+//            return -1;
+//        } else if (thisHash == otherHash) {
+//            return 0;
+//        } else {
+//            return 1;
+//        }
+//    }
+//
+//    private String treeBuilderGroupToName() {
+//        switch (getGroup()) {
+//            case TreeBuilder.OTHER:
+//                return "OTHER";
+//            case TreeBuilder.A:
+//                return "A";
+//            case TreeBuilder.BASE:
+//                return "BASE";
+//            case TreeBuilder.BODY:
+//                return "BODY";
+//            case TreeBuilder.BR:
+//                return "BR";
+//            case TreeBuilder.BUTTON:
+//                return "BUTTON";
+//            case TreeBuilder.CAPTION:
+//                return "CAPTION";
+//            case TreeBuilder.COL:
+//                return "COL";
+//            case TreeBuilder.COLGROUP:
+//                return "COLGROUP";
+//            case TreeBuilder.FONT:
+//                return "FONT";
+//            case TreeBuilder.FORM:
+//                return "FORM";
+//            case TreeBuilder.FRAME:
+//                return "FRAME";
+//            case TreeBuilder.FRAMESET:
+//                return "FRAMESET";
+//            case TreeBuilder.IMAGE:
+//                return "IMAGE";
+//            case TreeBuilder.INPUT:
+//                return "INPUT";
+//            case TreeBuilder.ISINDEX:
+//                return "ISINDEX";
+//            case TreeBuilder.LI:
+//                return "LI";
+//            case TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND:
+//                return "LINK_OR_BASEFONT_OR_BGSOUND";
+//            case TreeBuilder.MATH:
+//                return "MATH";
+//            case TreeBuilder.META:
+//                return "META";
+//            case TreeBuilder.SVG:
+//                return "SVG";
+//            case TreeBuilder.HEAD:
+//                return "HEAD";
+//            case TreeBuilder.HR:
+//                return "HR";
+//            case TreeBuilder.HTML:
+//                return "HTML";
+//            case TreeBuilder.KEYGEN:
+//                return "KEYGEN";
+//            case TreeBuilder.NOBR:
+//                return "NOBR";
+//            case TreeBuilder.NOFRAMES:
+//                return "NOFRAMES";
+//            case TreeBuilder.NOSCRIPT:
+//                return "NOSCRIPT";
+//            case TreeBuilder.OPTGROUP:
+//                return "OPTGROUP";
+//            case TreeBuilder.OPTION:
+//                return "OPTION";
+//            case TreeBuilder.P:
+//                return "P";
+//            case TreeBuilder.PLAINTEXT:
+//                return "PLAINTEXT";
+//            case TreeBuilder.SCRIPT:
+//                return "SCRIPT";
+//            case TreeBuilder.SELECT:
+//                return "SELECT";
+//            case TreeBuilder.STYLE:
+//                return "STYLE";
+//            case TreeBuilder.TABLE:
+//                return "TABLE";
+//            case TreeBuilder.TEXTAREA:
+//                return "TEXTAREA";
+//            case TreeBuilder.TITLE:
+//                return "TITLE";
+//            case TreeBuilder.TEMPLATE:
+//                return "TEMPLATE";
+//            case TreeBuilder.TR:
+//                return "TR";
+//            case TreeBuilder.XMP:
+//                return "XMP";
+//            case TreeBuilder.TBODY_OR_THEAD_OR_TFOOT:
+//                return "TBODY_OR_THEAD_OR_TFOOT";
+//            case TreeBuilder.TD_OR_TH:
+//                return "TD_OR_TH";
+//            case TreeBuilder.DD_OR_DT:
+//                return "DD_OR_DT";
+//            case TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6:
+//                return "H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6";
+//            case TreeBuilder.OBJECT:
+//                return "OBJECT";
+//            case TreeBuilder.OUTPUT:
+//                return "OUTPUT";
+//            case TreeBuilder.MARQUEE_OR_APPLET:
+//                return "MARQUEE_OR_APPLET";
+//            case TreeBuilder.PRE_OR_LISTING:
+//                return "PRE_OR_LISTING";
+//            case TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U:
+//                return "B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U";
+//            case TreeBuilder.UL_OR_OL_OR_DL:
+//                return "UL_OR_OL_OR_DL";
+//            case TreeBuilder.IFRAME:
+//                return "IFRAME";
+//            case TreeBuilder.NOEMBED:
+//                return "NOEMBED";
+//            case TreeBuilder.EMBED:
+//                return "EMBED";
+//            case TreeBuilder.IMG:
+//                return "IMG";
+//            case TreeBuilder.AREA_OR_WBR:
+//                return "AREA_OR_WBR";
+//            case TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU:
+//                return "DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU";
+//            case TreeBuilder.FIELDSET:
+//                return "FIELDSET";
+//            case TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY:
+//                return "ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY";
+//            case TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR:
+//                return "RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR";
+//            case TreeBuilder.RB_OR_RTC:
+//                return "RB_OR_RTC";
+//            case TreeBuilder.RT_OR_RP:
+//                return "RT_OR_RP";
+//            case TreeBuilder.PARAM_OR_SOURCE_OR_TRACK:
+//                return "PARAM_OR_SOURCE_OR_TRACK";
+//            case TreeBuilder.MGLYPH_OR_MALIGNMARK:
+//                return "MGLYPH_OR_MALIGNMARK";
+//            case TreeBuilder.MI_MO_MN_MS_MTEXT:
+//                return "MI_MO_MN_MS_MTEXT";
+//            case TreeBuilder.ANNOTATION_XML:
+//                return "ANNOTATION_XML";
+//            case TreeBuilder.FOREIGNOBJECT_OR_DESC:
+//                return "FOREIGNOBJECT_OR_DESC";
+//            case TreeBuilder.MENUITEM:
+//                return "MENUITEM";
+//        }
+//        return null;
+//    }
+//
+//    /**
+//     * Regenerate self
+//     *
+//     * @param args
+//     */
+//    public static void main(String[] args) {
+//        Arrays.sort(ELEMENT_NAMES);
+//        for (int i = 1; i < ELEMENT_NAMES.length; i++) {
+//            if (ELEMENT_NAMES[i].hash() == ELEMENT_NAMES[i - 1].hash()) {
+//                System.err.println("Hash collision: " + ELEMENT_NAMES[i].name
+//                        + ", " + ELEMENT_NAMES[i - 1].name);
+//                return;
+//            }
+//        }
+//        for (int i = 0; i < ELEMENT_NAMES.length; i++) {
+//            ElementName el = ELEMENT_NAMES[i];
+//            System.out.println("public static final ElementName "
+//                    + el.constName() + " = new ElementName" + el.toString()
+//                    + ";");
+//        }
+//        System.out.println("private final static @NoLength ElementName[] ELEMENT_NAMES = {");
+//        for (int i = 0; i < ELEMENT_NAMES.length; i++) {
+//            ElementName el = ELEMENT_NAMES[i];
+//            System.out.println(el.constName() + ",");
+//        }
+//        System.out.println("};");
+//        System.out.println("private final static int[] ELEMENT_HASHES = {");
+//        for (int i = 0; i < ELEMENT_NAMES.length; i++) {
+//            ElementName el = ELEMENT_NAMES[i];
+//            System.out.println(Integer.toString(el.hash()) + ",");
+//        }
+//        System.out.println("};");
+//    }
+
+    // START GENERATED CODE
+    public static final ElementName A = new ElementName("a", "a", TreeBuilder.A);
+    public static final ElementName B = new ElementName("b", "b", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName G = new ElementName("g", "g", TreeBuilder.OTHER);
+    public static final ElementName I = new ElementName("i", "i", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName P = new ElementName("p", "p", TreeBuilder.P | SPECIAL | OPTIONAL_END_TAG);
+    public static final ElementName Q = new ElementName("q", "q", TreeBuilder.OTHER);
+    public static final ElementName S = new ElementName("s", "s", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName U = new ElementName("u", "u", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName BR = new ElementName("br", "br", TreeBuilder.BR | SPECIAL);
+    public static final ElementName CI = new ElementName("ci", "ci", TreeBuilder.OTHER);
+    public static final ElementName CN = new ElementName("cn", "cn", TreeBuilder.OTHER);
+    public static final ElementName DD = new ElementName("dd", "dd", TreeBuilder.DD_OR_DT | SPECIAL | OPTIONAL_END_TAG);
+    public static final ElementName DL = new ElementName("dl", "dl", TreeBuilder.UL_OR_OL_OR_DL | SPECIAL);
+    public static final ElementName DT = new ElementName("dt", "dt", TreeBuilder.DD_OR_DT | SPECIAL | OPTIONAL_END_TAG);
+    public static final ElementName EM = new ElementName("em", "em", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName EQ = new ElementName("eq", "eq", TreeBuilder.OTHER);
+    public static final ElementName FN = new ElementName("fn", "fn", TreeBuilder.OTHER);
+    public static final ElementName H1 = new ElementName("h1", "h1", TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL);
+    public static final ElementName H2 = new ElementName("h2", "h2", TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL);
+    public static final ElementName H3 = new ElementName("h3", "h3", TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL);
+    public static final ElementName H4 = new ElementName("h4", "h4", TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL);
+    public static final ElementName H5 = new ElementName("h5", "h5", TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL);
+    public static final ElementName H6 = new ElementName("h6", "h6", TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 | SPECIAL);
+    public static final ElementName GT = new ElementName("gt", "gt", TreeBuilder.OTHER);
+    public static final ElementName HR = new ElementName("hr", "hr", TreeBuilder.HR | SPECIAL);
+    public static final ElementName IN = new ElementName("in", "in", TreeBuilder.OTHER);
+    public static final ElementName LI = new ElementName("li", "li", TreeBuilder.LI | SPECIAL | OPTIONAL_END_TAG);
+    public static final ElementName LN = new ElementName("ln", "ln", TreeBuilder.OTHER);
+    public static final ElementName LT = new ElementName("lt", "lt", TreeBuilder.OTHER);
+    public static final ElementName MI = new ElementName("mi", "mi", TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML);
+    public static final ElementName MN = new ElementName("mn", "mn", TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML);
+    public static final ElementName MO = new ElementName("mo", "mo", TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML);
+    public static final ElementName MS = new ElementName("ms", "ms", TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML);
+    public static final ElementName OL = new ElementName("ol", "ol", TreeBuilder.UL_OR_OL_OR_DL | SPECIAL);
+    public static final ElementName OR = new ElementName("or", "or", TreeBuilder.OTHER);
+    public static final ElementName PI = new ElementName("pi", "pi", TreeBuilder.OTHER);
+    public static final ElementName RB = new ElementName("rb", "rb", TreeBuilder.RB_OR_RTC | OPTIONAL_END_TAG);
+    public static final ElementName RP = new ElementName("rp", "rp", TreeBuilder.RT_OR_RP | OPTIONAL_END_TAG);
+    public static final ElementName RT = new ElementName("rt", "rt", TreeBuilder.RT_OR_RP | OPTIONAL_END_TAG);
+    public static final ElementName TD = new ElementName("td", "td", TreeBuilder.TD_OR_TH | SPECIAL | SCOPING | OPTIONAL_END_TAG);
+    public static final ElementName TH = new ElementName("th", "th", TreeBuilder.TD_OR_TH | SPECIAL | SCOPING | OPTIONAL_END_TAG);
+    public static final ElementName TR = new ElementName("tr", "tr", TreeBuilder.TR | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG);
+    public static final ElementName TT = new ElementName("tt", "tt", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName UL = new ElementName("ul", "ul", TreeBuilder.UL_OR_OL_OR_DL | SPECIAL);
+    public static final ElementName AND = new ElementName("and", "and", TreeBuilder.OTHER);
+    public static final ElementName ARG = new ElementName("arg", "arg", TreeBuilder.OTHER);
+    public static final ElementName ABS = new ElementName("abs", "abs", TreeBuilder.OTHER);
+    public static final ElementName BIG = new ElementName("big", "big", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName BDO = new ElementName("bdo", "bdo", TreeBuilder.OTHER);
+    public static final ElementName CSC = new ElementName("csc", "csc", TreeBuilder.OTHER);
+    public static final ElementName COL = new ElementName("col", "col", TreeBuilder.COL | SPECIAL);
+    public static final ElementName COS = new ElementName("cos", "cos", TreeBuilder.OTHER);
+    public static final ElementName COT = new ElementName("cot", "cot", TreeBuilder.OTHER);
+    public static final ElementName DEL = new ElementName("del", "del", TreeBuilder.OTHER);
+    public static final ElementName DFN = new ElementName("dfn", "dfn", TreeBuilder.OTHER);
+    public static final ElementName DIR = new ElementName("dir", "dir", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName DIV = new ElementName("div", "div", TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL);
+    public static final ElementName EXP = new ElementName("exp", "exp", TreeBuilder.OTHER);
+    public static final ElementName GCD = new ElementName("gcd", "gcd", TreeBuilder.OTHER);
+    public static final ElementName GEQ = new ElementName("geq", "geq", TreeBuilder.OTHER);
+    public static final ElementName IMG = new ElementName("img", "img", TreeBuilder.IMG | SPECIAL);
+    public static final ElementName INS = new ElementName("ins", "ins", TreeBuilder.OTHER);
+    public static final ElementName INT = new ElementName("int", "int", TreeBuilder.OTHER);
+    public static final ElementName KBD = new ElementName("kbd", "kbd", TreeBuilder.OTHER);
+    public static final ElementName LOG = new ElementName("log", "log", TreeBuilder.OTHER);
+    public static final ElementName LCM = new ElementName("lcm", "lcm", TreeBuilder.OTHER);
+    public static final ElementName LEQ = new ElementName("leq", "leq", TreeBuilder.OTHER);
+    public static final ElementName MTD = new ElementName("mtd", "mtd", TreeBuilder.OTHER);
+    public static final ElementName MIN = new ElementName("min", "min", TreeBuilder.OTHER);
+    public static final ElementName MAP = new ElementName("map", "map", TreeBuilder.OTHER);
+    public static final ElementName MTR = new ElementName("mtr", "mtr", TreeBuilder.OTHER);
+    public static final ElementName MAX = new ElementName("max", "max", TreeBuilder.OTHER);
+    public static final ElementName NEQ = new ElementName("neq", "neq", TreeBuilder.OTHER);
+    public static final ElementName NOT = new ElementName("not", "not", TreeBuilder.OTHER);
+    public static final ElementName NAV = new ElementName("nav", "nav", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName PRE = new ElementName("pre", "pre", TreeBuilder.PRE_OR_LISTING | SPECIAL);
+    public static final ElementName RTC = new ElementName("rtc", "rtc", TreeBuilder.RB_OR_RTC | OPTIONAL_END_TAG);
+    public static final ElementName REM = new ElementName("rem", "rem", TreeBuilder.OTHER);
+    public static final ElementName SUB = new ElementName("sub", "sub", TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR);
+    public static final ElementName SEC = new ElementName("sec", "sec", TreeBuilder.OTHER);
+    public static final ElementName SVG = new ElementName("svg", "svg", TreeBuilder.SVG);
+    public static final ElementName SUM = new ElementName("sum", "sum", TreeBuilder.OTHER);
+    public static final ElementName SIN = new ElementName("sin", "sin", TreeBuilder.OTHER);
+    public static final ElementName SEP = new ElementName("sep", "sep", TreeBuilder.OTHER);
+    public static final ElementName SUP = new ElementName("sup", "sup", TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR);
+    public static final ElementName SET = new ElementName("set", "set", TreeBuilder.OTHER);
+    public static final ElementName TAN = new ElementName("tan", "tan", TreeBuilder.OTHER);
+    public static final ElementName USE = new ElementName("use", "use", TreeBuilder.OTHER);
+    public static final ElementName VAR = new ElementName("var", "var", TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR);
+    public static final ElementName WBR = new ElementName("wbr", "wbr", TreeBuilder.AREA_OR_WBR | SPECIAL);
+    public static final ElementName XMP = new ElementName("xmp", "xmp", TreeBuilder.XMP | SPECIAL);
+    public static final ElementName XOR = new ElementName("xor", "xor", TreeBuilder.OTHER);
+    public static final ElementName AREA = new ElementName("area", "area", TreeBuilder.AREA_OR_WBR | SPECIAL);
+    public static final ElementName ABBR = new ElementName("abbr", "abbr", TreeBuilder.OTHER);
+    public static final ElementName BASE = new ElementName("base", "base", TreeBuilder.BASE | SPECIAL);
+    public static final ElementName BVAR = new ElementName("bvar", "bvar", TreeBuilder.OTHER);
+    public static final ElementName BODY = new ElementName("body", "body", TreeBuilder.BODY | SPECIAL | OPTIONAL_END_TAG);
+    public static final ElementName CARD = new ElementName("card", "card", TreeBuilder.OTHER);
+    public static final ElementName CODE = new ElementName("code", "code", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName CITE = new ElementName("cite", "cite", TreeBuilder.OTHER);
+    public static final ElementName CSCH = new ElementName("csch", "csch", TreeBuilder.OTHER);
+    public static final ElementName COSH = new ElementName("cosh", "cosh", TreeBuilder.OTHER);
+    public static final ElementName COTH = new ElementName("coth", "coth", TreeBuilder.OTHER);
+    public static final ElementName CURL = new ElementName("curl", "curl", TreeBuilder.OTHER);
+    public static final ElementName DESC = new ElementName("desc", "desc", TreeBuilder.FOREIGNOBJECT_OR_DESC | SCOPING_AS_SVG);
+    public static final ElementName DIFF = new ElementName("diff", "diff", TreeBuilder.OTHER);
+    public static final ElementName DEFS = new ElementName("defs", "defs", TreeBuilder.OTHER);
+    public static final ElementName FORM = new ElementName("form", "form", TreeBuilder.FORM | SPECIAL);
+    public static final ElementName FONT = new ElementName("font", "font", TreeBuilder.FONT);
+    public static final ElementName GRAD = new ElementName("grad", "grad", TreeBuilder.OTHER);
+    public static final ElementName HEAD = new ElementName("head", "head", TreeBuilder.HEAD | SPECIAL | OPTIONAL_END_TAG);
+    public static final ElementName HTML = new ElementName("html", "html", TreeBuilder.HTML | SPECIAL | SCOPING | OPTIONAL_END_TAG);
+    public static final ElementName LINE = new ElementName("line", "line", TreeBuilder.OTHER);
+    public static final ElementName LINK = new ElementName("link", "link", TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND | SPECIAL);
+    public static final ElementName LIST = new ElementName("list", "list", TreeBuilder.OTHER);
+    public static final ElementName META = new ElementName("meta", "meta", TreeBuilder.META | SPECIAL);
+    public static final ElementName MSUB = new ElementName("msub", "msub", TreeBuilder.OTHER);
+    public static final ElementName MODE = new ElementName("mode", "mode", TreeBuilder.OTHER);
+    public static final ElementName MATH = new ElementName("math", "math", TreeBuilder.MATH);
+    public static final ElementName MARK = new ElementName("mark", "mark", TreeBuilder.OTHER);
+    public static final ElementName MASK = new ElementName("mask", "mask", TreeBuilder.OTHER);
+    public static final ElementName MEAN = new ElementName("mean", "mean", TreeBuilder.OTHER);
+    public static final ElementName MAIN = new ElementName("main", "main", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName MSUP = new ElementName("msup", "msup", TreeBuilder.OTHER);
+    public static final ElementName MENU = new ElementName("menu", "menu", TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL);
+    public static final ElementName MROW = new ElementName("mrow", "mrow", TreeBuilder.OTHER);
+    public static final ElementName NONE = new ElementName("none", "none", TreeBuilder.OTHER);
+    public static final ElementName NOBR = new ElementName("nobr", "nobr", TreeBuilder.NOBR);
+    public static final ElementName NEST = new ElementName("nest", "nest", TreeBuilder.OTHER);
+    public static final ElementName PATH = new ElementName("path", "path", TreeBuilder.OTHER);
+    public static final ElementName PLUS = new ElementName("plus", "plus", TreeBuilder.OTHER);
+    public static final ElementName RULE = new ElementName("rule", "rule", TreeBuilder.OTHER);
+    public static final ElementName REAL = new ElementName("real", "real", TreeBuilder.OTHER);
+    public static final ElementName RELN = new ElementName("reln", "reln", TreeBuilder.OTHER);
+    public static final ElementName RECT = new ElementName("rect", "rect", TreeBuilder.OTHER);
+    public static final ElementName ROOT = new ElementName("root", "root", TreeBuilder.OTHER);
+    public static final ElementName RUBY = new ElementName("ruby", "ruby", TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR);
+    public static final ElementName SECH = new ElementName("sech", "sech", TreeBuilder.OTHER);
+    public static final ElementName SINH = new ElementName("sinh", "sinh", TreeBuilder.OTHER);
+    public static final ElementName SPAN = new ElementName("span", "span", TreeBuilder.RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR);
+    public static final ElementName SAMP = new ElementName("samp", "samp", TreeBuilder.OTHER);
+    public static final ElementName STOP = new ElementName("stop", "stop", TreeBuilder.OTHER);
+    public static final ElementName SDEV = new ElementName("sdev", "sdev", TreeBuilder.OTHER);
+    public static final ElementName TIME = new ElementName("time", "time", TreeBuilder.OTHER);
+    public static final ElementName TRUE = new ElementName("true", "true", TreeBuilder.OTHER);
+    public static final ElementName TREF = new ElementName("tref", "tref", TreeBuilder.OTHER);
+    public static final ElementName TANH = new ElementName("tanh", "tanh", TreeBuilder.OTHER);
+    public static final ElementName TEXT = new ElementName("text", "text", TreeBuilder.OTHER);
+    public static final ElementName VIEW = new ElementName("view", "view", TreeBuilder.OTHER);
+    public static final ElementName ASIDE = new ElementName("aside", "aside", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName AUDIO = new ElementName("audio", "audio", TreeBuilder.OTHER);
+    public static final ElementName APPLY = new ElementName("apply", "apply", TreeBuilder.OTHER);
+    public static final ElementName EMBED = new ElementName("embed", "embed", TreeBuilder.EMBED | SPECIAL);
+    public static final ElementName FRAME = new ElementName("frame", "frame", TreeBuilder.FRAME | SPECIAL);
+    public static final ElementName FALSE = new ElementName("false", "false", TreeBuilder.OTHER);
+    public static final ElementName FLOOR = new ElementName("floor", "floor", TreeBuilder.OTHER);
+    public static final ElementName GLYPH = new ElementName("glyph", "glyph", TreeBuilder.OTHER);
+    public static final ElementName HKERN = new ElementName("hkern", "hkern", TreeBuilder.OTHER);
+    public static final ElementName IMAGE = new ElementName("image", "image", TreeBuilder.IMAGE);
+    public static final ElementName IDENT = new ElementName("ident", "ident", TreeBuilder.OTHER);
+    public static final ElementName INPUT = new ElementName("input", "input", TreeBuilder.INPUT | SPECIAL);
+    public static final ElementName LABEL = new ElementName("label", "label", TreeBuilder.OTHER);
+    public static final ElementName LIMIT = new ElementName("limit", "limit", TreeBuilder.OTHER);
+    public static final ElementName MFRAC = new ElementName("mfrac", "mfrac", TreeBuilder.OTHER);
+    public static final ElementName MPATH = new ElementName("mpath", "mpath", TreeBuilder.OTHER);
+    public static final ElementName METER = new ElementName("meter", "meter", TreeBuilder.OTHER);
+    public static final ElementName MOVER = new ElementName("mover", "mover", TreeBuilder.OTHER);
+    public static final ElementName MINUS = new ElementName("minus", "minus", TreeBuilder.OTHER);
+    public static final ElementName MROOT = new ElementName("mroot", "mroot", TreeBuilder.OTHER);
+    public static final ElementName MSQRT = new ElementName("msqrt", "msqrt", TreeBuilder.OTHER);
+    public static final ElementName MTEXT = new ElementName("mtext", "mtext", TreeBuilder.MI_MO_MN_MS_MTEXT | SCOPING_AS_MATHML);
+    public static final ElementName NOTIN = new ElementName("notin", "notin", TreeBuilder.OTHER);
+    public static final ElementName PIECE = new ElementName("piece", "piece", TreeBuilder.OTHER);
+    public static final ElementName PARAM = new ElementName("param", "param", TreeBuilder.PARAM_OR_SOURCE_OR_TRACK | SPECIAL);
+    public static final ElementName POWER = new ElementName("power", "power", TreeBuilder.OTHER);
+    public static final ElementName REALS = new ElementName("reals", "reals", TreeBuilder.OTHER);
+    public static final ElementName STYLE = new ElementName("style", "style", TreeBuilder.STYLE | SPECIAL);
+    public static final ElementName SMALL = new ElementName("small", "small", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName THEAD = new ElementName("thead", "thead", TreeBuilder.TBODY_OR_THEAD_OR_TFOOT | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG);
+    public static final ElementName TABLE = new ElementName("table", "table", TreeBuilder.TABLE | SPECIAL | FOSTER_PARENTING | SCOPING);
+    public static final ElementName TITLE = new ElementName("title", "title", TreeBuilder.TITLE | SPECIAL | SCOPING_AS_SVG);
+    public static final ElementName TRACK = new ElementName("track", "track", TreeBuilder.PARAM_OR_SOURCE_OR_TRACK | SPECIAL);
+    public static final ElementName TSPAN = new ElementName("tspan", "tspan", TreeBuilder.OTHER);
+    public static final ElementName TIMES = new ElementName("times", "times", TreeBuilder.OTHER);
+    public static final ElementName TFOOT = new ElementName("tfoot", "tfoot", TreeBuilder.TBODY_OR_THEAD_OR_TFOOT | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG);
+    public static final ElementName TBODY = new ElementName("tbody", "tbody", TreeBuilder.TBODY_OR_THEAD_OR_TFOOT | SPECIAL | FOSTER_PARENTING | OPTIONAL_END_TAG);
+    public static final ElementName UNION = new ElementName("union", "union", TreeBuilder.OTHER);
+    public static final ElementName VKERN = new ElementName("vkern", "vkern", TreeBuilder.OTHER);
+    public static final ElementName VIDEO = new ElementName("video", "video", TreeBuilder.OTHER);
+    public static final ElementName ARCSEC = new ElementName("arcsec", "arcsec", TreeBuilder.OTHER);
+    public static final ElementName ARCCSC = new ElementName("arccsc", "arccsc", TreeBuilder.OTHER);
+    public static final ElementName ARCTAN = new ElementName("arctan", "arctan", TreeBuilder.OTHER);
+    public static final ElementName ARCSIN = new ElementName("arcsin", "arcsin", TreeBuilder.OTHER);
+    public static final ElementName ARCCOS = new ElementName("arccos", "arccos", TreeBuilder.OTHER);
+    public static final ElementName APPLET = new ElementName("applet", "applet", TreeBuilder.MARQUEE_OR_APPLET | SPECIAL | SCOPING);
+    public static final ElementName ARCCOT = new ElementName("arccot", "arccot", TreeBuilder.OTHER);
+    public static final ElementName APPROX = new ElementName("approx", "approx", TreeBuilder.OTHER);
+    public static final ElementName BUTTON = new ElementName("button", "button", TreeBuilder.BUTTON | SPECIAL);
+    public static final ElementName CIRCLE = new ElementName("circle", "circle", TreeBuilder.OTHER);
+    public static final ElementName CENTER = new ElementName("center", "center", TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL);
+    public static final ElementName CURSOR = new ElementName("cursor", "cursor", TreeBuilder.OTHER);
+    public static final ElementName CANVAS = new ElementName("canvas", "canvas", TreeBuilder.OTHER);
+    public static final ElementName DIVIDE = new ElementName("divide", "divide", TreeBuilder.OTHER);
+    public static final ElementName DEGREE = new ElementName("degree", "degree", TreeBuilder.OTHER);
+    public static final ElementName DIALOG = new ElementName("dialog", "dialog", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName DOMAIN = new ElementName("domain", "domain", TreeBuilder.OTHER);
+    public static final ElementName EXISTS = new ElementName("exists", "exists", TreeBuilder.OTHER);
+    public static final ElementName FETILE = new ElementName("fetile", "feTile", TreeBuilder.OTHER);
+    public static final ElementName FIGURE = new ElementName("figure", "figure", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName FORALL = new ElementName("forall", "forall", TreeBuilder.OTHER);
+    public static final ElementName FILTER = new ElementName("filter", "filter", TreeBuilder.OTHER);
+    public static final ElementName FOOTER = new ElementName("footer", "footer", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName HGROUP = new ElementName("hgroup", "hgroup", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName HEADER = new ElementName("header", "header", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName IFRAME = new ElementName("iframe", "iframe", TreeBuilder.IFRAME | SPECIAL);
+    public static final ElementName KEYGEN = new ElementName("keygen", "keygen", TreeBuilder.KEYGEN);
+    public static final ElementName LAMBDA = new ElementName("lambda", "lambda", TreeBuilder.OTHER);
+    public static final ElementName LEGEND = new ElementName("legend", "legend", TreeBuilder.OTHER);
+    public static final ElementName MSPACE = new ElementName("mspace", "mspace", TreeBuilder.OTHER);
+    public static final ElementName MTABLE = new ElementName("mtable", "mtable", TreeBuilder.OTHER);
+    public static final ElementName MSTYLE = new ElementName("mstyle", "mstyle", TreeBuilder.OTHER);
+    public static final ElementName MGLYPH = new ElementName("mglyph", "mglyph", TreeBuilder.MGLYPH_OR_MALIGNMARK);
+    public static final ElementName MEDIAN = new ElementName("median", "median", TreeBuilder.OTHER);
+    public static final ElementName MUNDER = new ElementName("munder", "munder", TreeBuilder.OTHER);
+    public static final ElementName MARKER = new ElementName("marker", "marker", TreeBuilder.OTHER);
+    public static final ElementName MERROR = new ElementName("merror", "merror", TreeBuilder.OTHER);
+    public static final ElementName MOMENT = new ElementName("moment", "moment", TreeBuilder.OTHER);
+    public static final ElementName MATRIX = new ElementName("matrix", "matrix", TreeBuilder.OTHER);
+    public static final ElementName OPTION = new ElementName("option", "option", TreeBuilder.OPTION | OPTIONAL_END_TAG);
+    public static final ElementName OBJECT = new ElementName("object", "object", TreeBuilder.OBJECT | SPECIAL | SCOPING);
+    public static final ElementName OUTPUT = new ElementName("output", "output", TreeBuilder.OUTPUT);
+    public static final ElementName PRIMES = new ElementName("primes", "primes", TreeBuilder.OTHER);
+    public static final ElementName SOURCE = new ElementName("source", "source", TreeBuilder.PARAM_OR_SOURCE_OR_TRACK);
+    public static final ElementName STRIKE = new ElementName("strike", "strike", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName STRONG = new ElementName("strong", "strong", TreeBuilder.B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U);
+    public static final ElementName SWITCH = new ElementName("switch", "switch", TreeBuilder.OTHER);
+    public static final ElementName SYMBOL = new ElementName("symbol", "symbol", TreeBuilder.OTHER);
+    public static final ElementName SELECT = new ElementName("select", "select", TreeBuilder.SELECT | SPECIAL);
+    public static final ElementName SUBSET = new ElementName("subset", "subset", TreeBuilder.OTHER);
+    public static final ElementName SCRIPT = new ElementName("script", "script", TreeBuilder.SCRIPT | SPECIAL);
+    public static final ElementName TBREAK = new ElementName("tbreak", "tbreak", TreeBuilder.OTHER);
+    public static final ElementName VECTOR = new ElementName("vector", "vector", TreeBuilder.OTHER);
+    public static final ElementName ARTICLE = new ElementName("article", "article", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName ANIMATE = new ElementName("animate", "animate", TreeBuilder.OTHER);
+    public static final ElementName ARCSECH = new ElementName("arcsech", "arcsech", TreeBuilder.OTHER);
+    public static final ElementName ARCCSCH = new ElementName("arccsch", "arccsch", TreeBuilder.OTHER);
+    public static final ElementName ARCTANH = new ElementName("arctanh", "arctanh", TreeBuilder.OTHER);
+    public static final ElementName ARCSINH = new ElementName("arcsinh", "arcsinh", TreeBuilder.OTHER);
+    public static final ElementName ARCCOSH = new ElementName("arccosh", "arccosh", TreeBuilder.OTHER);
+    public static final ElementName ARCCOTH = new ElementName("arccoth", "arccoth", TreeBuilder.OTHER);
+    public static final ElementName ACRONYM = new ElementName("acronym", "acronym", TreeBuilder.OTHER);
+    public static final ElementName ADDRESS = new ElementName("address", "address", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName BGSOUND = new ElementName("bgsound", "bgsound", TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND | SPECIAL);
+    public static final ElementName COMPOSE = new ElementName("compose", "compose", TreeBuilder.OTHER);
+    public static final ElementName CEILING = new ElementName("ceiling", "ceiling", TreeBuilder.OTHER);
+    public static final ElementName CSYMBOL = new ElementName("csymbol", "csymbol", TreeBuilder.OTHER);
+    public static final ElementName CAPTION = new ElementName("caption", "caption", TreeBuilder.CAPTION | SPECIAL | SCOPING);
+    public static final ElementName DISCARD = new ElementName("discard", "discard", TreeBuilder.OTHER);
+    public static final ElementName DECLARE = new ElementName("declare", "declare", TreeBuilder.OTHER);
+    public static final ElementName DETAILS = new ElementName("details", "details", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName ELLIPSE = new ElementName("ellipse", "ellipse", TreeBuilder.OTHER);
+    public static final ElementName FEFUNCA = new ElementName("fefunca", "feFuncA", TreeBuilder.OTHER);
+    public static final ElementName FEFUNCB = new ElementName("fefuncb", "feFuncB", TreeBuilder.OTHER);
+    public static final ElementName FEBLEND = new ElementName("feblend", "feBlend", TreeBuilder.OTHER);
+    public static final ElementName FEFLOOD = new ElementName("feflood", "feFlood", TreeBuilder.OTHER);
+    public static final ElementName FEIMAGE = new ElementName("feimage", "feImage", TreeBuilder.OTHER);
+    public static final ElementName FEMERGE = new ElementName("femerge", "feMerge", TreeBuilder.OTHER);
+    public static final ElementName FEFUNCG = new ElementName("fefuncg", "feFuncG", TreeBuilder.OTHER);
+    public static final ElementName FEFUNCR = new ElementName("fefuncr", "feFuncR", TreeBuilder.OTHER);
+    public static final ElementName HANDLER = new ElementName("handler", "handler", TreeBuilder.OTHER);
+    public static final ElementName INVERSE = new ElementName("inverse", "inverse", TreeBuilder.OTHER);
+    public static final ElementName IMPLIES = new ElementName("implies", "implies", TreeBuilder.OTHER);
+    public static final ElementName ISINDEX = new ElementName("isindex", "isindex", TreeBuilder.ISINDEX | SPECIAL);
+    public static final ElementName LOGBASE = new ElementName("logbase", "logbase", TreeBuilder.OTHER);
+    public static final ElementName LISTING = new ElementName("listing", "listing", TreeBuilder.PRE_OR_LISTING | SPECIAL);
+    public static final ElementName MFENCED = new ElementName("mfenced", "mfenced", TreeBuilder.OTHER);
+    public static final ElementName MPADDED = new ElementName("mpadded", "mpadded", TreeBuilder.OTHER);
+    public static final ElementName MARQUEE = new ElementName("marquee", "marquee", TreeBuilder.MARQUEE_OR_APPLET | SPECIAL | SCOPING);
+    public static final ElementName MACTION = new ElementName("maction", "maction", TreeBuilder.OTHER);
+    public static final ElementName MSUBSUP = new ElementName("msubsup", "msubsup", TreeBuilder.OTHER);
+    public static final ElementName NOEMBED = new ElementName("noembed", "noembed", TreeBuilder.NOEMBED | SPECIAL);
+    public static final ElementName PICTURE = new ElementName("picture", "picture", TreeBuilder.OTHER);
+    public static final ElementName POLYGON = new ElementName("polygon", "polygon", TreeBuilder.OTHER);
+    public static final ElementName PATTERN = new ElementName("pattern", "pattern", TreeBuilder.OTHER);
+    public static final ElementName PRODUCT = new ElementName("product", "product", TreeBuilder.OTHER);
+    public static final ElementName SETDIFF = new ElementName("setdiff", "setdiff", TreeBuilder.OTHER);
+    public static final ElementName SECTION = new ElementName("section", "section", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName SUMMARY = new ElementName("summary", "summary", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName TENDSTO = new ElementName("tendsto", "tendsto", TreeBuilder.OTHER);
+    public static final ElementName UPLIMIT = new ElementName("uplimit", "uplimit", TreeBuilder.OTHER);
+    public static final ElementName ALTGLYPH = new ElementName("altglyph", "altGlyph", TreeBuilder.OTHER);
+    public static final ElementName BASEFONT = new ElementName("basefont", "basefont", TreeBuilder.LINK_OR_BASEFONT_OR_BGSOUND | SPECIAL);
+    public static final ElementName CLIPPATH = new ElementName("clippath", "clipPath", TreeBuilder.OTHER);
+    public static final ElementName CODOMAIN = new ElementName("codomain", "codomain", TreeBuilder.OTHER);
+    public static final ElementName COLGROUP = new ElementName("colgroup", "colgroup", TreeBuilder.COLGROUP | SPECIAL | OPTIONAL_END_TAG);
+    public static final ElementName EMPTYSET = new ElementName("emptyset", "emptyset", TreeBuilder.OTHER);
+    public static final ElementName FACTOROF = new ElementName("factorof", "factorof", TreeBuilder.OTHER);
+    public static final ElementName FIELDSET = new ElementName("fieldset", "fieldset", TreeBuilder.FIELDSET | SPECIAL);
+    public static final ElementName FRAMESET = new ElementName("frameset", "frameset", TreeBuilder.FRAMESET | SPECIAL);
+    public static final ElementName FEOFFSET = new ElementName("feoffset", "feOffset", TreeBuilder.OTHER);
+    public static final ElementName GLYPHREF = new ElementName("glyphref", "glyphRef", TreeBuilder.OTHER);
+    public static final ElementName INTERVAL = new ElementName("interval", "interval", TreeBuilder.OTHER);
+    public static final ElementName INTEGERS = new ElementName("integers", "integers", TreeBuilder.OTHER);
+    public static final ElementName INFINITY = new ElementName("infinity", "infinity", TreeBuilder.OTHER);
+    public static final ElementName LISTENER = new ElementName("listener", "listener", TreeBuilder.OTHER);
+    public static final ElementName LOWLIMIT = new ElementName("lowlimit", "lowlimit", TreeBuilder.OTHER);
+    public static final ElementName METADATA = new ElementName("metadata", "metadata", TreeBuilder.OTHER);
+    public static final ElementName MENCLOSE = new ElementName("menclose", "menclose", TreeBuilder.OTHER);
+    public static final ElementName MENUITEM = new ElementName("menuitem", "menuitem", TreeBuilder.MENUITEM);
+    public static final ElementName MPHANTOM = new ElementName("mphantom", "mphantom", TreeBuilder.OTHER);
+    public static final ElementName NOFRAMES = new ElementName("noframes", "noframes", TreeBuilder.NOFRAMES | SPECIAL);
+    public static final ElementName NOSCRIPT = new ElementName("noscript", "noscript", TreeBuilder.NOSCRIPT | SPECIAL);
+    public static final ElementName OPTGROUP = new ElementName("optgroup", "optgroup", TreeBuilder.OPTGROUP | OPTIONAL_END_TAG);
+    public static final ElementName POLYLINE = new ElementName("polyline", "polyline", TreeBuilder.OTHER);
+    public static final ElementName PREFETCH = new ElementName("prefetch", "prefetch", TreeBuilder.OTHER);
+    public static final ElementName PROGRESS = new ElementName("progress", "progress", TreeBuilder.OTHER);
+    public static final ElementName PRSUBSET = new ElementName("prsubset", "prsubset", TreeBuilder.OTHER);
+    public static final ElementName QUOTIENT = new ElementName("quotient", "quotient", TreeBuilder.OTHER);
+    public static final ElementName SELECTOR = new ElementName("selector", "selector", TreeBuilder.OTHER);
+    public static final ElementName TEXTAREA = new ElementName("textarea", "textarea", TreeBuilder.TEXTAREA | SPECIAL);
+    public static final ElementName TEMPLATE = new ElementName("template", "template", TreeBuilder.TEMPLATE | SPECIAL | SCOPING);
+    public static final ElementName TEXTPATH = new ElementName("textpath", "textPath", TreeBuilder.OTHER);
+    public static final ElementName VARIANCE = new ElementName("variance", "variance", TreeBuilder.OTHER);
+    public static final ElementName ANIMATION = new ElementName("animation", "animation", TreeBuilder.OTHER);
+    public static final ElementName CONJUGATE = new ElementName("conjugate", "conjugate", TreeBuilder.OTHER);
+    public static final ElementName CONDITION = new ElementName("condition", "condition", TreeBuilder.OTHER);
+    public static final ElementName COMPLEXES = new ElementName("complexes", "complexes", TreeBuilder.OTHER);
+    public static final ElementName FONT_FACE = new ElementName("font-face", "font-face", TreeBuilder.OTHER);
+    public static final ElementName FACTORIAL = new ElementName("factorial", "factorial", TreeBuilder.OTHER);
+    public static final ElementName INTERSECT = new ElementName("intersect", "intersect", TreeBuilder.OTHER);
+    public static final ElementName IMAGINARY = new ElementName("imaginary", "imaginary", TreeBuilder.OTHER);
+    public static final ElementName LAPLACIAN = new ElementName("laplacian", "laplacian", TreeBuilder.OTHER);
+    public static final ElementName MATRIXROW = new ElementName("matrixrow", "matrixrow", TreeBuilder.OTHER);
+    public static final ElementName NOTSUBSET = new ElementName("notsubset", "notsubset", TreeBuilder.OTHER);
+    public static final ElementName OTHERWISE = new ElementName("otherwise", "otherwise", TreeBuilder.OTHER);
+    public static final ElementName PIECEWISE = new ElementName("piecewise", "piecewise", TreeBuilder.OTHER);
+    public static final ElementName PLAINTEXT = new ElementName("plaintext", "plaintext", TreeBuilder.PLAINTEXT | SPECIAL);
+    public static final ElementName RATIONALS = new ElementName("rationals", "rationals", TreeBuilder.OTHER);
+    public static final ElementName SEMANTICS = new ElementName("semantics", "semantics", TreeBuilder.OTHER);
+    public static final ElementName TRANSPOSE = new ElementName("transpose", "transpose", TreeBuilder.OTHER);
+    public static final ElementName ANNOTATION = new ElementName("annotation", "annotation", TreeBuilder.OTHER);
+    public static final ElementName BLOCKQUOTE = new ElementName("blockquote", "blockquote", TreeBuilder.DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU | SPECIAL);
+    public static final ElementName DIVERGENCE = new ElementName("divergence", "divergence", TreeBuilder.OTHER);
+    public static final ElementName EULERGAMMA = new ElementName("eulergamma", "eulergamma", TreeBuilder.OTHER);
+    public static final ElementName EQUIVALENT = new ElementName("equivalent", "equivalent", TreeBuilder.OTHER);
+    public static final ElementName FIGCAPTION = new ElementName("figcaption", "figcaption", TreeBuilder.ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY | SPECIAL);
+    public static final ElementName IMAGINARYI = new ElementName("imaginaryi", "imaginaryi", TreeBuilder.OTHER);
+    public static final ElementName MALIGNMARK = new ElementName("malignmark", "malignmark", TreeBuilder.MGLYPH_OR_MALIGNMARK);
+    public static final ElementName MUNDEROVER = new ElementName("munderover", "munderover", TreeBuilder.OTHER);
+    public static final ElementName MLABELEDTR = new ElementName("mlabeledtr", "mlabeledtr", TreeBuilder.OTHER);
+    public static final ElementName NOTANUMBER = new ElementName("notanumber", "notanumber", TreeBuilder.OTHER);
+    public static final ElementName SOLIDCOLOR = new ElementName("solidcolor", "solidcolor", TreeBuilder.OTHER);
+    public static final ElementName ALTGLYPHDEF = new ElementName("altglyphdef", "altGlyphDef", TreeBuilder.OTHER);
+    public static final ElementName DETERMINANT = new ElementName("determinant", "determinant", TreeBuilder.OTHER);
+    public static final ElementName FEMERGENODE = new ElementName("femergenode", "feMergeNode", TreeBuilder.OTHER);
+    public static final ElementName FECOMPOSITE = new ElementName("fecomposite", "feComposite", TreeBuilder.OTHER);
+    public static final ElementName FESPOTLIGHT = new ElementName("fespotlight", "feSpotLight", TreeBuilder.OTHER);
+    public static final ElementName MALIGNGROUP = new ElementName("maligngroup", "maligngroup", TreeBuilder.OTHER);
+    public static final ElementName MPRESCRIPTS = new ElementName("mprescripts", "mprescripts", TreeBuilder.OTHER);
+    public static final ElementName MOMENTABOUT = new ElementName("momentabout", "momentabout", TreeBuilder.OTHER);
+    public static final ElementName NOTPRSUBSET = new ElementName("notprsubset", "notprsubset", TreeBuilder.OTHER);
+    public static final ElementName PARTIALDIFF = new ElementName("partialdiff", "partialdiff", TreeBuilder.OTHER);
+    public static final ElementName ALTGLYPHITEM = new ElementName("altglyphitem", "altGlyphItem", TreeBuilder.OTHER);
+    public static final ElementName ANIMATECOLOR = new ElementName("animatecolor", "animateColor", TreeBuilder.OTHER);
+    public static final ElementName DATATEMPLATE = new ElementName("datatemplate", "datatemplate", TreeBuilder.OTHER);
+    public static final ElementName EXPONENTIALE = new ElementName("exponentiale", "exponentiale", TreeBuilder.OTHER);
+    public static final ElementName FETURBULENCE = new ElementName("feturbulence", "feTurbulence", TreeBuilder.OTHER);
+    public static final ElementName FEPOINTLIGHT = new ElementName("fepointlight", "fePointLight", TreeBuilder.OTHER);
+    public static final ElementName FEDROPSHADOW = new ElementName("fedropshadow", "feDropShadow", TreeBuilder.OTHER);
+    public static final ElementName FEMORPHOLOGY = new ElementName("femorphology", "feMorphology", TreeBuilder.OTHER);
+    public static final ElementName OUTERPRODUCT = new ElementName("outerproduct", "outerproduct", TreeBuilder.OTHER);
+    public static final ElementName ANIMATEMOTION = new ElementName("animatemotion", "animateMotion", TreeBuilder.OTHER);
+    public static final ElementName COLOR_PROFILE = new ElementName("color-profile", "color-profile", TreeBuilder.OTHER);
+    public static final ElementName FONT_FACE_SRC = new ElementName("font-face-src", "font-face-src", TreeBuilder.OTHER);
+    public static final ElementName FONT_FACE_URI = new ElementName("font-face-uri", "font-face-uri", TreeBuilder.OTHER);
+    public static final ElementName FOREIGNOBJECT = new ElementName("foreignobject", "foreignObject", TreeBuilder.FOREIGNOBJECT_OR_DESC | SCOPING_AS_SVG);
+    public static final ElementName FECOLORMATRIX = new ElementName("fecolormatrix", "feColorMatrix", TreeBuilder.OTHER);
+    public static final ElementName MISSING_GLYPH = new ElementName("missing-glyph", "missing-glyph", TreeBuilder.OTHER);
+    public static final ElementName MMULTISCRIPTS = new ElementName("mmultiscripts", "mmultiscripts", TreeBuilder.OTHER);
+    public static final ElementName SCALARPRODUCT = new ElementName("scalarproduct", "scalarproduct", TreeBuilder.OTHER);
+    public static final ElementName VECTORPRODUCT = new ElementName("vectorproduct", "vectorproduct", TreeBuilder.OTHER);
+    public static final ElementName ANNOTATION_XML = new ElementName("annotation-xml", "annotation-xml", TreeBuilder.ANNOTATION_XML | SCOPING_AS_MATHML);
+    public static final ElementName DEFINITION_SRC = new ElementName("definition-src", "definition-src", TreeBuilder.OTHER);
+    public static final ElementName FONT_FACE_NAME = new ElementName("font-face-name", "font-face-name", TreeBuilder.OTHER);
+    public static final ElementName FEGAUSSIANBLUR = new ElementName("fegaussianblur", "feGaussianBlur", TreeBuilder.OTHER);
+    public static final ElementName FEDISTANTLIGHT = new ElementName("fedistantlight", "feDistantLight", TreeBuilder.OTHER);
+    public static final ElementName LINEARGRADIENT = new ElementName("lineargradient", "linearGradient", TreeBuilder.OTHER);
+    public static final ElementName NATURALNUMBERS = new ElementName("naturalnumbers", "naturalnumbers", TreeBuilder.OTHER);
+    public static final ElementName RADIALGRADIENT = new ElementName("radialgradient", "radialGradient", TreeBuilder.OTHER);
+    public static final ElementName ANIMATETRANSFORM = new ElementName("animatetransform", "animateTransform", TreeBuilder.OTHER);
+    public static final ElementName CARTESIANPRODUCT = new ElementName("cartesianproduct", "cartesianproduct", TreeBuilder.OTHER);
+    public static final ElementName FONT_FACE_FORMAT = new ElementName("font-face-format", "font-face-format", TreeBuilder.OTHER);
+    public static final ElementName FECONVOLVEMATRIX = new ElementName("feconvolvematrix", "feConvolveMatrix", TreeBuilder.OTHER);
+    public static final ElementName FEDIFFUSELIGHTING = new ElementName("fediffuselighting", "feDiffuseLighting", TreeBuilder.OTHER);
+    public static final ElementName FEDISPLACEMENTMAP = new ElementName("fedisplacementmap", "feDisplacementMap", TreeBuilder.OTHER);
+    public static final ElementName FESPECULARLIGHTING = new ElementName("fespecularlighting", "feSpecularLighting", TreeBuilder.OTHER);
+    public static final ElementName DOMAINOFAPPLICATION = new ElementName("domainofapplication", "domainofapplication", TreeBuilder.OTHER);
+    public static final ElementName FECOMPONENTTRANSFER = new ElementName("fecomponenttransfer", "feComponentTransfer", TreeBuilder.OTHER);
+    private final static @NoLength ElementName[] ELEMENT_NAMES = {
+    A,
+    B,
+    G,
+    I,
+    P,
+    Q,
+    S,
+    U,
+    BR,
+    CI,
+    CN,
+    DD,
+    DL,
+    DT,
+    EM,
+    EQ,
+    FN,
+    H1,
+    H2,
+    H3,
+    H4,
+    H5,
+    H6,
+    GT,
+    HR,
+    IN,
+    LI,
+    LN,
+    LT,
+    MI,
+    MN,
+    MO,
+    MS,
+    OL,
+    OR,
+    PI,
+    RB,
+    RP,
+    RT,
+    TD,
+    TH,
+    TR,
+    TT,
+    UL,
+    AND,
+    ARG,
+    ABS,
+    BIG,
+    BDO,
+    CSC,
+    COL,
+    COS,
+    COT,
+    DEL,
+    DFN,
+    DIR,
+    DIV,
+    EXP,
+    GCD,
+    GEQ,
+    IMG,
+    INS,
+    INT,
+    KBD,
+    LOG,
+    LCM,
+    LEQ,
+    MTD,
+    MIN,
+    MAP,
+    MTR,
+    MAX,
+    NEQ,
+    NOT,
+    NAV,
+    PRE,
+    RTC,
+    REM,
+    SUB,
+    SEC,
+    SVG,
+    SUM,
+    SIN,
+    SEP,
+    SUP,
+    SET,
+    TAN,
+    USE,
+    VAR,
+    WBR,
+    XMP,
+    XOR,
+    AREA,
+    ABBR,
+    BASE,
+    BVAR,
+    BODY,
+    CARD,
+    CODE,
+    CITE,
+    CSCH,
+    COSH,
+    COTH,
+    CURL,
+    DESC,
+    DIFF,
+    DEFS,
+    FORM,
+    FONT,
+    GRAD,
+    HEAD,
+    HTML,
+    LINE,
+    LINK,
+    LIST,
+    META,
+    MSUB,
+    MODE,
+    MATH,
+    MARK,
+    MASK,
+    MEAN,
+    MAIN,
+    MSUP,
+    MENU,
+    MROW,
+    NONE,
+    NOBR,
+    NEST,
+    PATH,
+    PLUS,
+    RULE,
+    REAL,
+    RELN,
+    RECT,
+    ROOT,
+    RUBY,
+    SECH,
+    SINH,
+    SPAN,
+    SAMP,
+    STOP,
+    SDEV,
+    TIME,
+    TRUE,
+    TREF,
+    TANH,
+    TEXT,
+    VIEW,
+    ASIDE,
+    AUDIO,
+    APPLY,
+    EMBED,
+    FRAME,
+    FALSE,
+    FLOOR,
+    GLYPH,
+    HKERN,
+    IMAGE,
+    IDENT,
+    INPUT,
+    LABEL,
+    LIMIT,
+    MFRAC,
+    MPATH,
+    METER,
+    MOVER,
+    MINUS,
+    MROOT,
+    MSQRT,
+    MTEXT,
+    NOTIN,
+    PIECE,
+    PARAM,
+    POWER,
+    REALS,
+    STYLE,
+    SMALL,
+    THEAD,
+    TABLE,
+    TITLE,
+    TRACK,
+    TSPAN,
+    TIMES,
+    TFOOT,
+    TBODY,
+    UNION,
+    VKERN,
+    VIDEO,
+    ARCSEC,
+    ARCCSC,
+    ARCTAN,
+    ARCSIN,
+    ARCCOS,
+    APPLET,
+    ARCCOT,
+    APPROX,
+    BUTTON,
+    CIRCLE,
+    CENTER,
+    CURSOR,
+    CANVAS,
+    DIVIDE,
+    DEGREE,
+    DIALOG,
+    DOMAIN,
+    EXISTS,
+    FETILE,
+    FIGURE,
+    FORALL,
+    FILTER,
+    FOOTER,
+    HGROUP,
+    HEADER,
+    IFRAME,
+    KEYGEN,
+    LAMBDA,
+    LEGEND,
+    MSPACE,
+    MTABLE,
+    MSTYLE,
+    MGLYPH,
+    MEDIAN,
+    MUNDER,
+    MARKER,
+    MERROR,
+    MOMENT,
+    MATRIX,
+    OPTION,
+    OBJECT,
+    OUTPUT,
+    PRIMES,
+    SOURCE,
+    STRIKE,
+    STRONG,
+    SWITCH,
+    SYMBOL,
+    SELECT,
+    SUBSET,
+    SCRIPT,
+    TBREAK,
+    VECTOR,
+    ARTICLE,
+    ANIMATE,
+    ARCSECH,
+    ARCCSCH,
+    ARCTANH,
+    ARCSINH,
+    ARCCOSH,
+    ARCCOTH,
+    ACRONYM,
+    ADDRESS,
+    BGSOUND,
+    COMPOSE,
+    CEILING,
+    CSYMBOL,
+    CAPTION,
+    DISCARD,
+    DECLARE,
+    DETAILS,
+    ELLIPSE,
+    FEFUNCA,
+    FEFUNCB,
+    FEBLEND,
+    FEFLOOD,
+    FEIMAGE,
+    FEMERGE,
+    FEFUNCG,
+    FEFUNCR,
+    HANDLER,
+    INVERSE,
+    IMPLIES,
+    ISINDEX,
+    LOGBASE,
+    LISTING,
+    MFENCED,
+    MPADDED,
+    MARQUEE,
+    MACTION,
+    MSUBSUP,
+    NOEMBED,
+    PICTURE,
+    POLYGON,
+    PATTERN,
+    PRODUCT,
+    SETDIFF,
+    SECTION,
+    SUMMARY,
+    TENDSTO,
+    UPLIMIT,
+    ALTGLYPH,
+    BASEFONT,
+    CLIPPATH,
+    CODOMAIN,
+    COLGROUP,
+    EMPTYSET,
+    FACTOROF,
+    FIELDSET,
+    FRAMESET,
+    FEOFFSET,
+    GLYPHREF,
+    INTERVAL,
+    INTEGERS,
+    INFINITY,
+    LISTENER,
+    LOWLIMIT,
+    METADATA,
+    MENCLOSE,
+    MENUITEM,
+    MPHANTOM,
+    NOFRAMES,
+    NOSCRIPT,
+    OPTGROUP,
+    POLYLINE,
+    PREFETCH,
+    PROGRESS,
+    PRSUBSET,
+    QUOTIENT,
+    SELECTOR,
+    TEXTAREA,
+    TEMPLATE,
+    TEXTPATH,
+    VARIANCE,
+    ANIMATION,
+    CONJUGATE,
+    CONDITION,
+    COMPLEXES,
+    FONT_FACE,
+    FACTORIAL,
+    INTERSECT,
+    IMAGINARY,
+    LAPLACIAN,
+    MATRIXROW,
+    NOTSUBSET,
+    OTHERWISE,
+    PIECEWISE,
+    PLAINTEXT,
+    RATIONALS,
+    SEMANTICS,
+    TRANSPOSE,
+    ANNOTATION,
+    BLOCKQUOTE,
+    DIVERGENCE,
+    EULERGAMMA,
+    EQUIVALENT,
+    FIGCAPTION,
+    IMAGINARYI,
+    MALIGNMARK,
+    MUNDEROVER,
+    MLABELEDTR,
+    NOTANUMBER,
+    SOLIDCOLOR,
+    ALTGLYPHDEF,
+    DETERMINANT,
+    FEMERGENODE,
+    FECOMPOSITE,
+    FESPOTLIGHT,
+    MALIGNGROUP,
+    MPRESCRIPTS,
+    MOMENTABOUT,
+    NOTPRSUBSET,
+    PARTIALDIFF,
+    ALTGLYPHITEM,
+    ANIMATECOLOR,
+    DATATEMPLATE,
+    EXPONENTIALE,
+    FETURBULENCE,
+    FEPOINTLIGHT,
+    FEDROPSHADOW,
+    FEMORPHOLOGY,
+    OUTERPRODUCT,
+    ANIMATEMOTION,
+    COLOR_PROFILE,
+    FONT_FACE_SRC,
+    FONT_FACE_URI,
+    FOREIGNOBJECT,
+    FECOLORMATRIX,
+    MISSING_GLYPH,
+    MMULTISCRIPTS,
+    SCALARPRODUCT,
+    VECTORPRODUCT,
+    ANNOTATION_XML,
+    DEFINITION_SRC,
+    FONT_FACE_NAME,
+    FEGAUSSIANBLUR,
+    FEDISTANTLIGHT,
+    LINEARGRADIENT,
+    NATURALNUMBERS,
+    RADIALGRADIENT,
+    ANIMATETRANSFORM,
+    CARTESIANPRODUCT,
+    FONT_FACE_FORMAT,
+    FECONVOLVEMATRIX,
+    FEDIFFUSELIGHTING,
+    FEDISPLACEMENTMAP,
+    FESPECULARLIGHTING,
+    DOMAINOFAPPLICATION,
+    FECOMPONENTTRANSFER,
+    };
+    private final static int[] ELEMENT_HASHES = {
+    1057,
+    1090,
+    1255,
+    1321,
+    1552,
+    1585,
+    1651,
+    1717,
+    68162,
+    68899,
+    69059,
+    69764,
+    70020,
+    70276,
+    71077,
+    71205,
+    72134,
+    72232,
+    72264,
+    72296,
+    72328,
+    72360,
+    72392,
+    73351,
+    74312,
+    75209,
+    78124,
+    78284,
+    78476,
+    79149,
+    79309,
+    79341,
+    79469,
+    81295,
+    81487,
+    82224,
+    84050,
+    84498,
+    84626,
+    86164,
+    86292,
+    86612,
+    86676,
+    87445,
+    3183041,
+    3186241,
+    3198017,
+    3218722,
+    3226754,
+    3247715,
+    3256803,
+    3263971,
+    3264995,
+    3289252,
+    3291332,
+    3295524,
+    3299620,
+    3326725,
+    3379303,
+    3392679,
+    3448233,
+    3460553,
+    3461577,
+    3510347,
+    3546604,
+    3552364,
+    3556524,
+    3576461,
+    3586349,
+    3588141,
+    3590797,
+    3596333,
+    3622062,
+    3625454,
+    3627054,
+    3675728,
+    3739282,
+    3749042,
+    3771059,
+    3771571,
+    3776211,
+    3782323,
+    3782963,
+    3784883,
+    3785395,
+    3788979,
+    3815476,
+    3839605,
+    3885110,
+    3917911,
+    3948984,
+    3951096,
+    135304769,
+    135858241,
+    136498210,
+    136906434,
+    137138658,
+    137512995,
+    137531875,
+    137548067,
+    137629283,
+    137645539,
+    137646563,
+    137775779,
+    138529956,
+    138615076,
+    139040932,
+    140954086,
+    141179366,
+    141690439,
+    142738600,
+    143013512,
+    146979116,
+    147175724,
+    147475756,
+    147902637,
+    147936877,
+    148017645,
+    148131885,
+    148228141,
+    148229165,
+    148309165,
+    148317229,
+    148395629,
+    148551853,
+    148618829,
+    149076462,
+    149490158,
+    149572782,
+    151277616,
+    151639440,
+    153268914,
+    153486514,
+    153563314,
+    153750706,
+    153763314,
+    153914034,
+    154406067,
+    154417459,
+    154600979,
+    154678323,
+    154680979,
+    154866835,
+    155366708,
+    155375188,
+    155391572,
+    155465780,
+    155869364,
+    158045494,
+    168988979,
+    169321621,
+    169652752,
+    173151309,
+    174240818,
+    174247297,
+    174669292,
+    175391532,
+    176638123,
+    177380397,
+    177879204,
+    177886734,
+    180753473,
+    181020073,
+    181503558,
+    181686320,
+    181999237,
+    181999311,
+    182048201,
+    182074866,
+    182078003,
+    182083764,
+    182920847,
+    184716457,
+    184976961,
+    185145071,
+    187281445,
+    187872052,
+    188100653,
+    188875944,
+    188919873,
+    188920457,
+    189107250,
+    189203987,
+    189371817,
+    189414886,
+    189567458,
+    190266670,
+    191318187,
+    191337609,
+    202479203,
+    202493027,
+    202835587,
+    202843747,
+    203013219,
+    203036048,
+    203045987,
+    203177552,
+    203898516,
+    204648562,
+    205067918,
+    205078130,
+    205096654,
+    205689142,
+    205690439,
+    205766017,
+    205988909,
+    207213161,
+    207794484,
+    207800999,
+    208023602,
+    208213644,
+    208213647,
+    210261490,
+    210310273,
+    210940978,
+    213325049,
+    213946445,
+    214055079,
+    215125040,
+    215134273,
+    215135028,
+    215237420,
+    215418148,
+    215553166,
+    215553394,
+    215563858,
+    215627949,
+    215754324,
+    217529652,
+    217713834,
+    217732628,
+    218731945,
+    221417045,
+    221424946,
+    221493746,
+    221515401,
+    221658189,
+    221908140,
+    221910626,
+    221921586,
+    222659762,
+    225001091,
+    236105833,
+    236113965,
+    236194995,
+    236195427,
+    236206132,
+    236206387,
+    236211683,
+    236212707,
+    236381647,
+    236571826,
+    237124271,
+    238210544,
+    238270764,
+    238435405,
+    238501172,
+    239224867,
+    239257644,
+    239710497,
+    240307721,
+    241208789,
+    241241557,
+    241318060,
+    241319404,
+    241343533,
+    241344069,
+    241405397,
+    241765845,
+    243864964,
+    244502085,
+    244946220,
+    245109902,
+    247647266,
+    247707956,
+    248648814,
+    248648836,
+    248682161,
+    248986932,
+    249058914,
+    249697357,
+    251841204,
+    252132601,
+    252135604,
+    252317348,
+    255007012,
+    255278388,
+    255641645,
+    256365156,
+    257566121,
+    269763372,
+    271202790,
+    271863856,
+    272049197,
+    272127474,
+    274339449,
+    274939471,
+    275388004,
+    275388005,
+    275388006,
+    275977800,
+    278267602,
+    278513831,
+    278712622,
+    281613765,
+    281683369,
+    282120228,
+    282250732,
+    282498697,
+    282508942,
+    283743649,
+    283787570,
+    284710386,
+    285391148,
+    285478533,
+    285854898,
+    285873762,
+    286931113,
+    288964227,
+    289445441,
+    289591340,
+    289689648,
+    291671489,
+    303512884,
+    305319975,
+    305610036,
+    305764101,
+    308448294,
+    308675890,
+    312085683,
+    312264750,
+    315032867,
+    316391000,
+    317331042,
+    317902135,
+    318950711,
+    319447220,
+    321499182,
+    322538804,
+    323145200,
+    337067316,
+    337826293,
+    339905989,
+    340833697,
+    341457068,
+    342310196,
+    345302593,
+    349554733,
+    349771471,
+    349786245,
+    350819405,
+    356072847,
+    370349192,
+    373962798,
+    375558638,
+    375574835,
+    376053993,
+    383276530,
+    383373833,
+    383407586,
+    384439906,
+    386079012,
+    404133513,
+    404307343,
+    407031852,
+    408072233,
+    409112005,
+    409608425,
+    409713793,
+    409771500,
+    419040932,
+    437730612,
+    439529766,
+    442616365,
+    442813037,
+    443157674,
+    443295316,
+    450118444,
+    450482697,
+    456789668,
+    459935396,
+    471217869,
+    474073645,
+    476230702,
+    476665218,
+    476717289,
+    483014825,
+    485083298,
+    489306281,
+    538364390,
+    540675748,
+    543819186,
+    543958612,
+    576960820,
+    577242548,
+    610515252,
+    642202932,
+    644420819,
+    };
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java
new file mode 100644
index 000000000..f1749e0b3
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java
@@ -0,0 +1,772 @@
+/*
+ * Copyright (c) 2009-2013 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.Inline;
+import nu.validator.htmlparser.annotation.NoLength;
+import nu.validator.htmlparser.common.TokenHandler;
+import nu.validator.htmlparser.common.TransitionHandler;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+
+import java.util.HashMap;
+
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+public class ErrorReportingTokenizer extends Tokenizer {
+
+    /**
+     * Magic value for UTF-16 operations.
+     */
+    private static final int SURROGATE_OFFSET = (0x10000 - (0xD800 << 10) - 0xDC00);
+
+    /**
+     * The policy for non-space non-XML characters.
+     */
+    private XmlViolationPolicy contentNonXmlCharPolicy = XmlViolationPolicy.ALTER_INFOSET;
+
+    /**
+     * Keeps track of PUA warnings.
+     */
+    private boolean alreadyWarnedAboutPrivateUseCharacters;
+
+    /**
+     * The current line number in the current resource being parsed. (First line
+     * is 1.) Passed on as locator data.
+     */
+    private int line;
+
+    private int linePrev;
+
+    /**
+     * The current column number in the current resource being tokenized. (First
+     * column is 1, counted by UTF-16 code units.) Passed on as locator data.
+     */
+    private int col;
+
+    private int colPrev;
+
+    private boolean nextCharOnNewLine;
+
+    private char prev;
+
+    private HashMap<String, String> errorProfileMap = null;
+
+    private TransitionHandler transitionHandler = null;
+
+    private int transitionBaseOffset = 0;
+
+    /**
+     * @param tokenHandler
+     * @param newAttributesEachTime
+     */
+    public ErrorReportingTokenizer(TokenHandler tokenHandler,
+            boolean newAttributesEachTime) {
+        super(tokenHandler, newAttributesEachTime);
+    }
+
+    /**
+     * @param tokenHandler
+     */
+    public ErrorReportingTokenizer(TokenHandler tokenHandler) {
+        super(tokenHandler);
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getLineNumber()
+     */
+    public int getLineNumber() {
+        if (line > 0) {
+            return line;
+        } else {
+            return -1;
+        }
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getColumnNumber()
+     */
+    public int getColumnNumber() {
+        if (col > 0) {
+            return col;
+        } else {
+            return -1;
+        }
+    }
+
+    /**
+     * Sets the contentNonXmlCharPolicy.
+     * 
+     * @param contentNonXmlCharPolicy
+     *            the contentNonXmlCharPolicy to set
+     */
+    public void setContentNonXmlCharPolicy(
+            XmlViolationPolicy contentNonXmlCharPolicy) {
+        this.contentNonXmlCharPolicy = contentNonXmlCharPolicy;
+    }
+
+    /**
+     * Sets the errorProfile.
+     * 
+     * @param errorProfile
+     */
+    public void setErrorProfile(HashMap<String, String> errorProfileMap) {
+        this.errorProfileMap = errorProfileMap;
+    }
+
+    /**
+     * Reports on an event based on profile selected.
+     * 
+     * @param profile
+     *            the profile this message belongs to
+     * @param message
+     *            the message itself
+     * @throws SAXException
+     */
+    public void note(String profile, String message) throws SAXException {
+        if (errorProfileMap == null)
+            return;
+        String level = errorProfileMap.get(profile);
+        if ("warn".equals(level)) {
+            warn(message);
+        } else if ("err".equals(level)) {
+            err(message);
+            // } else if ("info".equals(level)) {
+            // info(message);
+        }
+    }
+
+    protected void startErrorReporting() throws SAXException {
+        line = linePrev = 0;
+        col = colPrev = 1;
+        nextCharOnNewLine = true;
+        prev = '\u0000';
+        alreadyWarnedAboutPrivateUseCharacters = false;
+        transitionBaseOffset = 0;
+    }
+
+    @Inline protected void silentCarriageReturn() {
+        nextCharOnNewLine = true;
+        lastCR = true;
+    }
+
+    @Inline protected void silentLineFeed() {
+        nextCharOnNewLine = true;
+    }
+
+    /**
+     * Returns the line.
+     * 
+     * @return the line
+     */
+    public int getLine() {
+        return line;
+    }
+
+    /**
+     * Returns the col.
+     * 
+     * @return the col
+     */
+    public int getCol() {
+        return col;
+    }
+
+    /**
+     * Returns the nextCharOnNewLine.
+     * 
+     * @return the nextCharOnNewLine
+     */
+    public boolean isNextCharOnNewLine() {
+        return nextCharOnNewLine;
+    }
+
+    /**
+     * Flushes coalesced character tokens.
+     * 
+     * @param buf
+     *            TODO
+     * @param pos
+     *            TODO
+     * 
+     * @throws SAXException
+     */
+    @Override protected void flushChars(char[] buf, int pos)
+            throws SAXException {
+        if (pos > cstart) {
+            int currLine = line;
+            int currCol = col;
+            line = linePrev;
+            col = colPrev;
+            tokenHandler.characters(buf, cstart, pos - cstart);
+            line = currLine;
+            col = currCol;
+        }
+        cstart = 0x7fffffff;
+    }
+
+    @Override protected char checkChar(@NoLength char[] buf, int pos)
+            throws SAXException {
+        linePrev = line;
+        colPrev = col;
+        if (nextCharOnNewLine) {
+            line++;
+            col = 1;
+            nextCharOnNewLine = false;
+        } else {
+            col++;
+        }
+
+        char c = buf[pos];
+        switch (c) {
+            case '\u0000':
+                err("Saw U+0000 in stream.");
+            case '\t':
+            case '\r':
+            case '\n':
+                break;
+            case '\u000C':
+                if (contentNonXmlCharPolicy == XmlViolationPolicy.FATAL) {
+                    fatal("This document is not mappable to XML 1.0 without data loss due to "
+                            + toUPlusString(c)
+                            + " which is not a legal XML 1.0 character.");
+                } else {
+                    if (contentNonXmlCharPolicy == XmlViolationPolicy.ALTER_INFOSET) {
+                        c = buf[pos] = ' ';
+                    }
+                    warn("This document is not mappable to XML 1.0 without data loss due to "
+                            + toUPlusString(c)
+                            + " which is not a legal XML 1.0 character.");
+                }
+                break;
+            default:
+                if ((c & 0xFC00) == 0xDC00) {
+                    // Got a low surrogate. See if prev was high
+                    // surrogate
+                    if ((prev & 0xFC00) == 0xD800) {
+                        int intVal = (prev << 10) + c + SURROGATE_OFFSET;
+                        if ((intVal & 0xFFFE) == 0xFFFE) {
+                            err("Astral non-character.");
+                        }
+                        if (isAstralPrivateUse(intVal)) {
+                            warnAboutPrivateUseChar();
+                        }
+                    }
+                } else if ((c < ' ' || ((c & 0xFFFE) == 0xFFFE))) {
+                    switch (contentNonXmlCharPolicy) {
+                        case FATAL:
+                            fatal("Forbidden code point " + toUPlusString(c)
+                                    + ".");
+                            break;
+                        case ALTER_INFOSET:
+                            c = buf[pos] = '\uFFFD';
+                            // fall through
+                        case ALLOW:
+                            err("Forbidden code point " + toUPlusString(c)
+                                    + ".");
+                    }
+                } else if ((c >= '\u007F') && (c <= '\u009F')
+                        || (c >= '\uFDD0') && (c <= '\uFDEF')) {
+                    err("Forbidden code point " + toUPlusString(c) + ".");
+                } else if (isPrivateUse(c)) {
+                    warnAboutPrivateUseChar();
+                }
+        }
+        prev = c;
+        return c;
+    }
+
+    /**
+     * @throws SAXException
+     * @see nu.validator.htmlparser.impl.Tokenizer#transition(int, int, boolean,
+     *      int)
+     */
+    @Override protected int transition(int from, int to, boolean reconsume,
+            int pos) throws SAXException {
+        if (transitionHandler != null) {
+            transitionHandler.transition(from, to, reconsume,
+                    transitionBaseOffset + pos);
+        }
+        return to;
+    }
+
+    private String toUPlusString(int c) {
+        String hexString = Integer.toHexString(c);
+        switch (hexString.length()) {
+            case 1:
+                return "U+000" + hexString;
+            case 2:
+                return "U+00" + hexString;
+            case 3:
+                return "U+0" + hexString;
+            default:
+                return "U+" + hexString;
+        }
+    }
+
+    /**
+     * Emits a warning about private use characters if the warning has not been
+     * emitted yet.
+     * 
+     * @throws SAXException
+     */
+    private void warnAboutPrivateUseChar() throws SAXException {
+        if (!alreadyWarnedAboutPrivateUseCharacters) {
+            warn("Document uses the Unicode Private Use Area(s), which should not be used in publicly exchanged documents. (Charmod C073)");
+            alreadyWarnedAboutPrivateUseCharacters = true;
+        }
+    }
+
+    /**
+     * Tells if the argument is a BMP PUA character.
+     * 
+     * @param c
+     *            the UTF-16 code unit to check
+     * @return <code>true</code> if PUA character
+     */
+    private boolean isPrivateUse(char c) {
+        return c >= '\uE000' && c <= '\uF8FF';
+    }
+
+    /**
+     * Tells if the argument is an astral PUA character.
+     * 
+     * @param c
+     *            the code point to check
+     * @return <code>true</code> if astral private use
+     */
+    private boolean isAstralPrivateUse(int c) {
+        return (c >= 0xF0000 && c <= 0xFFFFD)
+                || (c >= 0x100000 && c <= 0x10FFFD);
+    }
+
+    @Override protected void errGarbageAfterLtSlash() throws SAXException {
+        err("Garbage after \u201C</\u201D.");
+    }
+
+    @Override protected void errLtSlashGt() throws SAXException {
+        err("Saw \u201C</>\u201D. Probable causes: Unescaped \u201C<\u201D (escape as \u201C&lt;\u201D) or mistyped end tag.");
+    }
+
+    @Override protected void errWarnLtSlashInRcdata() throws SAXException {
+        if (html4) {
+            err((stateSave == Tokenizer.DATA ? "CDATA" : "RCDATA")
+                    + " element \u201C"
+                    + endTagExpectation
+                    + "\u201D contained the string \u201C</\u201D, but it was not the start of the end tag. (HTML4-only error)");
+        } else {
+            warn((stateSave == Tokenizer.DATA ? "CDATA" : "RCDATA")
+                    + " element \u201C"
+                    + endTagExpectation
+                    + "\u201D contained the string \u201C</\u201D, but this did not close the element.");
+        }
+    }
+
+    @Override protected void errHtml4LtSlashInRcdata(char folded)
+            throws SAXException {
+        if (html4 && (index > 0 || (folded >= 'a' && folded <= 'z'))
+                && ElementName.IFRAME != endTagExpectation) {
+            err((stateSave == Tokenizer.DATA ? "CDATA" : "RCDATA")
+                    + " element \u201C"
+                    + endTagExpectation.name
+                    + "\u201D contained the string \u201C</\u201D, but it was not the start of the end tag. (HTML4-only error)");
+        }
+    }
+
+    @Override protected void errCharRefLacksSemicolon() throws SAXException {
+        err("Character reference was not terminated by a semicolon.");
+    }
+
+    @Override protected void errNoDigitsInNCR() throws SAXException {
+        err("No digits after \u201C" + strBufToString() + "\u201D.");
+    }
+
+    @Override protected void errGtInSystemId() throws SAXException {
+        err("\u201C>\u201D in system identifier.");
+    }
+
+    @Override protected void errGtInPublicId() throws SAXException {
+        err("\u201C>\u201D in public identifier.");
+    }
+
+    @Override protected void errNamelessDoctype() throws SAXException {
+        err("Nameless doctype.");
+    }
+
+    @Override protected void errConsecutiveHyphens() throws SAXException {
+        err("Consecutive hyphens did not terminate a comment. \u201C--\u201D is not permitted inside a comment, but e.g. \u201C- -\u201D is.");
+    }
+
+    @Override protected void errPrematureEndOfComment() throws SAXException {
+        err("Premature end of comment. Use \u201C-->\u201D to end a comment properly.");
+    }
+
+    @Override protected void errBogusComment() throws SAXException {
+        err("Bogus comment.");
+    }
+
+    @Override protected void errUnquotedAttributeValOrNull(char c)
+            throws SAXException {
+        switch (c) {
+            case '<':
+                err("\u201C<\u201D in an unquoted attribute value. Probable cause: Missing \u201C>\u201D immediately before.");
+                return;
+            case '`':
+                err("\u201C`\u201D in an unquoted attribute value. Probable cause: Using the wrong character as a quote.");
+                return;
+            case '\uFFFD':
+                return;
+            default:
+                err("\u201C"
+                        + c
+                        + "\u201D in an unquoted attribute value. Probable causes: Attributes running together or a URL query string in an unquoted attribute value.");
+                return;
+        }
+    }
+
+    @Override protected void errSlashNotFollowedByGt() throws SAXException {
+        err("A slash was not immediately followed by \u201C>\u201D.");
+    }
+
+    @Override protected void errHtml4XmlVoidSyntax() throws SAXException {
+        if (html4) {
+            err("The \u201C/>\u201D syntax on void elements is not allowed.  (This is an HTML4-only error.)");
+        }
+    }
+
+    @Override protected void errNoSpaceBetweenAttributes() throws SAXException {
+        err("No space between attributes.");
+    }
+
+    @Override protected void errHtml4NonNameInUnquotedAttribute(char c)
+            throws SAXException {
+        if (html4
+                && !((c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z')
+                        || (c >= '0' && c <= '9') || c == '.' || c == '-'
+                        || c == '_' || c == ':')) {
+            err("Non-name character in an unquoted attribute value. (This is an HTML4-only error.)");
+        }
+    }
+
+    @Override protected void errLtOrEqualsOrGraveInUnquotedAttributeOrNull(
+            char c) throws SAXException {
+        switch (c) {
+            case '=':
+                err("\u201C=\u201D at the start of an unquoted attribute value. Probable cause: Stray duplicate equals sign.");
+                return;
+            case '<':
+                err("\u201C<\u201D at the start of an unquoted attribute value. Probable cause: Missing \u201C>\u201D immediately before.");
+                return;
+            case '`':
+                err("\u201C`\u201D at the start of an unquoted attribute value. Probable cause: Using the wrong character as a quote.");
+                return;
+        }
+    }
+
+    @Override protected void errAttributeValueMissing() throws SAXException {
+        err("Attribute value missing.");
+    }
+
+    @Override protected void errBadCharBeforeAttributeNameOrNull(char c)
+            throws SAXException {
+        if (c == '<') {
+            err("Saw \u201C<\u201D when expecting an attribute name. Probable cause: Missing \u201C>\u201D immediately before.");
+        } else if (c == '=') {
+            errEqualsSignBeforeAttributeName();
+        } else if (c != '\uFFFD') {
+            errQuoteBeforeAttributeName(c);
+        }
+    }
+
+    @Override protected void errEqualsSignBeforeAttributeName()
+            throws SAXException {
+        err("Saw \u201C=\u201D when expecting an attribute name. Probable cause: Attribute name missing.");
+    }
+
+    @Override protected void errBadCharAfterLt(char c) throws SAXException {
+        err("Bad character \u201C"
+                + c
+                + "\u201D after \u201C<\u201D. Probable cause: Unescaped \u201C<\u201D. Try escaping it as \u201C&lt;\u201D.");
+    }
+
+    @Override protected void errLtGt() throws SAXException {
+        err("Saw \u201C<>\u201D. Probable causes: Unescaped \u201C<\u201D (escape as \u201C&lt;\u201D) or mistyped start tag.");
+    }
+
+    @Override protected void errProcessingInstruction() throws SAXException {
+        err("Saw \u201C<?\u201D. Probable cause: Attempt to use an XML processing instruction in HTML. (XML processing instructions are not supported in HTML.)");
+    }
+
+    @Override protected void errUnescapedAmpersandInterpretedAsCharacterReference()
+            throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(
+                "The string following \u201C&\u201D was interpreted as a character reference. (\u201C&\u201D probably should have been escaped as \u201C&amp;\u201D.)",
+                ampersandLocation);
+        errorHandler.error(spe);
+    }
+
+    @Override protected void errNotSemicolonTerminated() throws SAXException {
+        err("Named character reference was not terminated by a semicolon. (Or \u201C&\u201D should have been escaped as \u201C&amp;\u201D.)");
+    }
+
+    @Override protected void errNoNamedCharacterMatch() throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(
+                "\u201C&\u201D did not start a character reference. (\u201C&\u201D probably should have been escaped as \u201C&amp;\u201D.)",
+                ampersandLocation);
+        errorHandler.error(spe);
+    }
+
+    @Override protected void errQuoteBeforeAttributeName(char c)
+            throws SAXException {
+        err("Saw \u201C"
+                + c
+                + "\u201D when expecting an attribute name. Probable cause: \u201C=\u201D missing immediately before.");
+    }
+
+    @Override protected void errQuoteOrLtInAttributeNameOrNull(char c)
+            throws SAXException {
+        if (c == '<') {
+            err("\u201C<\u201D in attribute name. Probable cause: \u201C>\u201D missing immediately before.");
+        } else if (c != '\uFFFD') {
+            err("Quote \u201C"
+                    + c
+                    + "\u201D in attribute name. Probable cause: Matching quote missing somewhere earlier.");
+        }
+    }
+
+    @Override protected void errExpectedPublicId() throws SAXException {
+        err("Expected a public identifier but the doctype ended.");
+    }
+
+    @Override protected void errBogusDoctype() throws SAXException {
+        err("Bogus doctype.");
+    }
+
+    @Override protected void maybeWarnPrivateUseAstral() throws SAXException {
+        if (errorHandler != null && isAstralPrivateUse(value)) {
+            warnAboutPrivateUseChar();
+        }
+    }
+
+    @Override protected void maybeWarnPrivateUse(char ch) throws SAXException {
+        if (errorHandler != null && isPrivateUse(ch)) {
+            warnAboutPrivateUseChar();
+        }
+    }
+
+    @Override protected void maybeErrAttributesOnEndTag(HtmlAttributes attrs)
+            throws SAXException {
+        if (attrs.getLength() != 0) {
+            /*
+             * When an end tag token is emitted with attributes, that is a parse
+             * error.
+             */
+            err("End tag had attributes.");
+        }
+    }
+
+    @Override protected void maybeErrSlashInEndTag(boolean selfClosing)
+            throws SAXException {
+        if (selfClosing && endTag) {
+            err("Stray \u201C/\u201D at the end of an end tag.");
+        }
+    }
+
+    @Override protected char errNcrNonCharacter(char ch) throws SAXException {
+        switch (contentNonXmlCharPolicy) {
+            case FATAL:
+                fatal("Character reference expands to a non-character ("
+                        + toUPlusString((char) value) + ").");
+                break;
+            case ALTER_INFOSET:
+                ch = '\uFFFD';
+                // fall through
+            case ALLOW:
+                err("Character reference expands to a non-character ("
+                        + toUPlusString((char) value) + ").");
+        }
+        return ch;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.Tokenizer#errAstralNonCharacter(int)
+     */
+    @Override protected void errAstralNonCharacter(int ch) throws SAXException {
+        err("Character reference expands to an astral non-character ("
+                + toUPlusString(value) + ").");
+    }
+
+    @Override protected void errNcrSurrogate() throws SAXException {
+        err("Character reference expands to a surrogate.");
+    }
+
+    @Override protected char errNcrControlChar(char ch) throws SAXException {
+        switch (contentNonXmlCharPolicy) {
+            case FATAL:
+                fatal("Character reference expands to a control character ("
+                        + toUPlusString((char) value) + ").");
+                break;
+            case ALTER_INFOSET:
+                ch = '\uFFFD';
+                // fall through
+            case ALLOW:
+                err("Character reference expands to a control character ("
+                        + toUPlusString((char) value) + ").");
+        }
+        return ch;
+    }
+
+    @Override protected void errNcrCr() throws SAXException {
+        err("A numeric character reference expanded to carriage return.");
+    }
+
+    @Override protected void errNcrInC1Range() throws SAXException {
+        err("A numeric character reference expanded to the C1 controls range.");
+    }
+
+    @Override protected void errEofInPublicId() throws SAXException {
+        err("End of file inside public identifier.");
+    }
+
+    @Override protected void errEofInComment() throws SAXException {
+        err("End of file inside comment.");
+    }
+
+    @Override protected void errEofInDoctype() throws SAXException {
+        err("End of file inside doctype.");
+    }
+
+    @Override protected void errEofInAttributeValue() throws SAXException {
+        err("End of file reached when inside an attribute value. Ignoring tag.");
+    }
+
+    @Override protected void errEofInAttributeName() throws SAXException {
+        err("End of file occurred in an attribute name. Ignoring tag.");
+    }
+
+    @Override protected void errEofWithoutGt() throws SAXException {
+        err("Saw end of file without the previous tag ending with \u201C>\u201D. Ignoring tag.");
+    }
+
+    @Override protected void errEofInTagName() throws SAXException {
+        err("End of file seen when looking for tag name. Ignoring tag.");
+    }
+
+    @Override protected void errEofInEndTag() throws SAXException {
+        err("End of file inside end tag. Ignoring tag.");
+    }
+
+    @Override protected void errEofAfterLt() throws SAXException {
+        err("End of file after \u201C<\u201D.");
+    }
+
+    @Override protected void errNcrOutOfRange() throws SAXException {
+        err("Character reference outside the permissible Unicode range.");
+    }
+
+    @Override protected void errNcrUnassigned() throws SAXException {
+        err("Character reference expands to a permanently unassigned code point.");
+    }
+
+    @Override protected void errDuplicateAttribute() throws SAXException {
+        err("Duplicate attribute \u201C"
+                + attributeName.getLocal(AttributeName.HTML) + "\u201D.");
+    }
+
+    @Override protected void errEofInSystemId() throws SAXException {
+        err("End of file inside system identifier.");
+    }
+
+    @Override protected void errExpectedSystemId() throws SAXException {
+        err("Expected a system identifier but the doctype ended.");
+    }
+
+    @Override protected void errMissingSpaceBeforeDoctypeName()
+            throws SAXException {
+        err("Missing space before doctype name.");
+    }
+
+    @Override protected void errHyphenHyphenBang() throws SAXException {
+        err("\u201C--!\u201D found in comment.");
+    }
+
+    @Override protected void errNcrControlChar() throws SAXException {
+        err("Character reference expands to a control character ("
+                + toUPlusString((char) value) + ").");
+    }
+
+    @Override protected void errNcrZero() throws SAXException {
+        err("Character reference expands to zero.");
+    }
+
+    @Override protected void errNoSpaceBetweenDoctypeSystemKeywordAndQuote()
+            throws SAXException {
+        err("No space between the doctype \u201CSYSTEM\u201D keyword and the quote.");
+    }
+
+    @Override protected void errNoSpaceBetweenPublicAndSystemIds()
+            throws SAXException {
+        err("No space between the doctype public and system identifiers.");
+    }
+
+    @Override protected void errNoSpaceBetweenDoctypePublicKeywordAndQuote()
+            throws SAXException {
+        err("No space between the doctype \u201CPUBLIC\u201D keyword and the quote.");
+    }
+
+    @Override protected void noteAttributeWithoutValue() throws SAXException {
+        note("xhtml2", "Attribute without value");
+    }
+
+    @Override protected void noteUnquotedAttributeValue() throws SAXException {
+        note("xhtml1", "Unquoted attribute value.");
+    }
+
+    /**
+     * Sets the transitionHandler.
+     * 
+     * @param transitionHandler
+     *            the transitionHandler to set
+     */
+    public void setTransitionHandler(TransitionHandler transitionHandler) {
+        this.transitionHandler = transitionHandler;
+    }
+
+    /**
+     * Sets an offset to be added to the position reported to
+     * <code>TransitionHandler</code>.
+     * 
+     * @param offset
+     *            the offset
+     */
+    public void setTransitionBaseOffset(int offset) {
+        this.transitionBaseOffset = offset;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/HotSpotWorkaround.txt b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/HotSpotWorkaround.txt
new file mode 100644
index 000000000..c389a8cac
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/HotSpotWorkaround.txt
@@ -0,0 +1,55 @@
+/*
+ * Copyright (c) 2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+   /**
+    * compressed returnValue:
+    *   int     returnState     = returnValue >> 33
+    *   boolean breakOuterState = ((returnValue >> 32) & 0x1) != 0)
+    *   int     pos             = returnValue & 0xFFFFFFFF // same as (int)returnValue
+    */  
+    @SuppressWarnings("unused") private long workAroundHotSpotHugeMethodLimit(
+            int state, char c, int pos, @NoLength char[] buf,
+            boolean reconsume, int returnState, int endPos) throws SAXException {
+        stateloop: for (;;) {
+            switch (state) {
+                // BEGIN HOTSPOT WORKAROUND
+                default:
+                    long returnStateAndPos = workAroundHotSpotHugeMethodLimit(
+                            state, c, pos, buf, reconsume, returnState, endPos);
+                    pos = (int)returnStateAndPos; // 5.1.3 in the Java spec
+                    returnState = (int)(returnStateAndPos >> 33);
+                    state = stateSave;
+                    if ( (pos == endPos) || ( (((int)(returnStateAndPos >> 32)) & 0x1) != 0) ) {
+                        break stateloop;
+                    }
+                    continue stateloop;
+                // END HOTSPOT WORKAROUND
+                default:
+                    assert !reconsume : "Must not reconsume when returning from HotSpot workaround.";
+                    stateSave = state;
+                    return (((long)returnState) << 33) | pos;
+            }
+        }
+        assert !reconsume : "Must not reconsume when returning from HotSpot workaround.";
+        stateSave = state;
+        return (((long)returnState) << 33) | (1L << 32) | pos ;
+    }
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/HtmlAttributes.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/HtmlAttributes.java
new file mode 100644
index 000000000..45c9c6c3e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/HtmlAttributes.java
@@ -0,0 +1,620 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2011 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.Auto;
+import nu.validator.htmlparser.annotation.IdType;
+import nu.validator.htmlparser.annotation.Local;
+import nu.validator.htmlparser.annotation.NsUri;
+import nu.validator.htmlparser.annotation.Prefix;
+import nu.validator.htmlparser.annotation.QName;
+import nu.validator.htmlparser.common.Interner;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.SAXException;
+
+/**
+ * Be careful with this class. QName is the name in from HTML tokenization.
+ * Otherwise, please refer to the interface doc.
+ * 
+ * @version $Id: AttributesImpl.java 206 2008-03-20 14:09:29Z hsivonen $
+ * @author hsivonen
+ */
+public final class HtmlAttributes implements Attributes {
+
+    // [NOCPP[
+
+    private static final AttributeName[] EMPTY_ATTRIBUTENAMES = new AttributeName[0];
+
+    private static final String[] EMPTY_STRINGS = new String[0];
+
+    // ]NOCPP]
+
+    public static final HtmlAttributes EMPTY_ATTRIBUTES = new HtmlAttributes(
+            AttributeName.HTML);
+
+    private int mode;
+
+    private int length;
+
+    private @Auto AttributeName[] names;
+
+    private @Auto String[] values; // XXX perhaps make this @NoLength?
+    
+    // CPPONLY: private @Auto int[] lines; // XXX perhaps make this @NoLength?
+
+    // [NOCPP[
+
+    private String idValue;
+
+    private int xmlnsLength;
+
+    private AttributeName[] xmlnsNames;
+
+    private String[] xmlnsValues;
+
+    // ]NOCPP]
+
+    public HtmlAttributes(int mode) {
+        this.mode = mode;
+        this.length = 0;
+        /*
+         * The length of 5 covers covers 98.3% of elements
+         * according to Hixie, but lets round to the next power of two for
+         * jemalloc.
+         */
+        this.names = new AttributeName[8];
+        this.values = new String[8];
+        // CPPONLY: this.lines = new int[8];
+
+        // [NOCPP[
+
+        this.idValue = null;
+
+        this.xmlnsLength = 0;
+
+        this.xmlnsNames = HtmlAttributes.EMPTY_ATTRIBUTENAMES;
+
+        this.xmlnsValues = HtmlAttributes.EMPTY_STRINGS;
+
+        // ]NOCPP]
+    }
+    /*
+    public HtmlAttributes(HtmlAttributes other) {
+        this.mode = other.mode;
+        this.length = other.length;
+        this.names = new AttributeName[other.length];
+        this.values = new String[other.length];
+        // [NOCPP[
+        this.idValue = other.idValue;
+        this.xmlnsLength = other.xmlnsLength;
+        this.xmlnsNames = new AttributeName[other.xmlnsLength];
+        this.xmlnsValues = new String[other.xmlnsLength];
+        // ]NOCPP]
+    }
+    */
+
+    void destructor() {
+        clear(0);
+    }
+    
+    /**
+     * Only use with a static argument
+     * 
+     * @param name
+     * @return
+     */
+    public int getIndex(AttributeName name) {
+        for (int i = 0; i < length; i++) {
+            if (names[i] == name) {
+                return i;
+            }
+        }
+        return -1;
+    }
+
+    /**
+     * Only use with static argument.
+     * 
+     * @see org.xml.sax.Attributes#getValue(java.lang.String)
+     */
+    public String getValue(AttributeName name) {
+        int index = getIndex(name);
+        if (index == -1) {
+            return null;
+        } else {
+            return getValueNoBoundsCheck(index);
+        }
+    }
+
+    public int getLength() {
+        return length;
+    }
+
+    /**
+     * Variant of <code>getLocalName(int index)</code> without bounds check.
+     * @param index a valid attribute index
+     * @return the local name at index
+     */
+    public @Local String getLocalNameNoBoundsCheck(int index) {
+        // CPPONLY: assert index < length && index >= 0: "Index out of bounds";
+        return names[index].getLocal(mode);
+    }
+
+    /**
+     * Variant of <code>getURI(int index)</code> without bounds check.
+     * @param index a valid attribute index
+     * @return the namespace URI at index
+     */
+    public @NsUri String getURINoBoundsCheck(int index) {
+        // CPPONLY: assert index < length && index >= 0: "Index out of bounds";
+        return names[index].getUri(mode);
+    }
+
+    /**
+     * Variant of <code>getPrefix(int index)</code> without bounds check.
+     * @param index a valid attribute index
+     * @return the namespace prefix at index
+     */
+    public @Prefix String getPrefixNoBoundsCheck(int index) {
+        // CPPONLY: assert index < length && index >= 0: "Index out of bounds";
+        return names[index].getPrefix(mode);
+    }
+
+    /**
+     * Variant of <code>getValue(int index)</code> without bounds check.
+     * @param index a valid attribute index
+     * @return the attribute value at index
+     */
+    public String getValueNoBoundsCheck(int index) {
+        // CPPONLY: assert index < length && index >= 0: "Index out of bounds";
+        return values[index];
+    }
+
+    /**
+     * Variant of <code>getAttributeName(int index)</code> without bounds check.
+     * @param index a valid attribute index
+     * @return the attribute name at index
+     */
+    public AttributeName getAttributeNameNoBoundsCheck(int index) {
+        // CPPONLY: assert index < length && index >= 0: "Index out of bounds";
+        return names[index];
+    }
+
+    // CPPONLY: /**
+    // CPPONLY: * Obtains a line number without bounds check.
+    // CPPONLY: * @param index a valid attribute index
+    // CPPONLY: * @return the line number at index or -1 if unknown
+    // CPPONLY: */
+    // CPPONLY: public int getLineNoBoundsCheck(int index) {
+    // CPPONLY: assert index < length && index >= 0: "Index out of bounds";
+    // CPPONLY: return lines[index];
+    // CPPONLY: }
+
+    // [NOCPP[
+    
+    /**
+     * Variant of <code>getQName(int index)</code> without bounds check.
+     * @param index a valid attribute index
+     * @return the QName at index
+     */
+    public @QName String getQNameNoBoundsCheck(int index) {
+        return names[index].getQName(mode);
+    }
+
+    /**
+     * Variant of <code>getType(int index)</code> without bounds check.
+     * @param index a valid attribute index
+     * @return the attribute type at index
+     */
+    public @IdType String getTypeNoBoundsCheck(int index) {
+        return (names[index] == AttributeName.ID) ? "ID" : "CDATA";
+    }
+
+    public int getIndex(String qName) {
+        for (int i = 0; i < length; i++) {
+            if (names[i].getQName(mode).equals(qName)) {
+                return i;
+            }
+        }
+        return -1;
+    }
+    
+    public int getIndex(String uri, String localName) {
+        for (int i = 0; i < length; i++) {
+            if (names[i].getLocal(mode).equals(localName)
+                    && names[i].getUri(mode).equals(uri)) {
+                return i;
+            }
+        }
+        return -1;
+    }
+
+    public @IdType String getType(String qName) {
+        int index = getIndex(qName);
+        if (index == -1) {
+            return null;
+        } else {
+            return getType(index);
+        }
+    }
+
+    public @IdType String getType(String uri, String localName) {
+        int index = getIndex(uri, localName);
+        if (index == -1) {
+            return null;
+        } else {
+            return getType(index);
+        }
+    }
+    
+    public String getValue(String qName) {
+        int index = getIndex(qName);
+        if (index == -1) {
+            return null;
+        } else {
+            return getValue(index);
+        }
+    }
+
+    public String getValue(String uri, String localName) {
+        int index = getIndex(uri, localName);
+        if (index == -1) {
+            return null;
+        } else {
+            return getValue(index);
+        }
+    }
+    
+    public @Local String getLocalName(int index) {
+        if (index < length && index >= 0) {
+            return names[index].getLocal(mode);
+        } else {
+            return null;
+        }
+    }
+    
+    public @QName String getQName(int index) {
+        if (index < length && index >= 0) {
+            return names[index].getQName(mode);
+        } else {
+            return null;
+        }
+    }
+
+    public @IdType String getType(int index) {
+        if (index < length && index >= 0) {
+            return (names[index] == AttributeName.ID) ? "ID" : "CDATA";
+        } else {
+            return null;
+        }
+    }
+
+    public AttributeName getAttributeName(int index) {
+        if (index < length && index >= 0) {
+            return names[index];
+        } else {
+            return null;
+        }
+    }
+
+    public @NsUri String getURI(int index) {
+        if (index < length && index >= 0) {
+            return names[index].getUri(mode);
+        } else {
+            return null;
+        }
+    }
+
+    public @Prefix String getPrefix(int index) {
+        if (index < length && index >= 0) {
+            return names[index].getPrefix(mode);
+        } else {
+            return null;
+        }
+    }
+
+    public String getValue(int index) {
+        if (index < length && index >= 0) {
+            return values[index];
+        } else {
+            return null;
+        }
+    }
+
+    public String getId() {
+        return idValue;
+    }
+
+    public int getXmlnsLength() {
+        return xmlnsLength;
+    }
+
+    public @Local String getXmlnsLocalName(int index) {
+        if (index < xmlnsLength && index >= 0) {
+            return xmlnsNames[index].getLocal(mode);
+        } else {
+            return null;
+        }
+    }
+
+    public @NsUri String getXmlnsURI(int index) {
+        if (index < xmlnsLength && index >= 0) {
+            return xmlnsNames[index].getUri(mode);
+        } else {
+            return null;
+        }
+    }
+
+    public String getXmlnsValue(int index) {
+        if (index < xmlnsLength && index >= 0) {
+            return xmlnsValues[index];
+        } else {
+            return null;
+        }
+    }
+    
+    public int getXmlnsIndex(AttributeName name) {
+        for (int i = 0; i < xmlnsLength; i++) {
+            if (xmlnsNames[i] == name) {
+                return i;
+            }
+        }
+        return -1;
+    }
+    
+    public String getXmlnsValue(AttributeName name) {
+        int index = getXmlnsIndex(name);
+        if (index == -1) {
+            return null;
+        } else {
+            return getXmlnsValue(index);
+        }
+    }
+    
+    public AttributeName getXmlnsAttributeName(int index) {
+        if (index < xmlnsLength && index >= 0) {
+            return xmlnsNames[index];
+        } else {
+            return null;
+        }
+    }
+
+    // ]NOCPP]
+
+    void addAttribute(AttributeName name, String value
+            // [NOCPP[
+            , XmlViolationPolicy xmlnsPolicy
+            // ]NOCPP]
+            // CPPONLY: , int line
+    ) throws SAXException {
+        // [NOCPP[
+        if (name == AttributeName.ID) {
+            idValue = value;
+        }
+
+        if (name.isXmlns()) {
+            if (xmlnsNames.length == xmlnsLength) {
+                int newLen = xmlnsLength == 0 ? 2 : xmlnsLength << 1;
+                AttributeName[] newNames = new AttributeName[newLen];
+                System.arraycopy(xmlnsNames, 0, newNames, 0, xmlnsNames.length);
+                xmlnsNames = newNames;
+                String[] newValues = new String[newLen];
+                System.arraycopy(xmlnsValues, 0, newValues, 0, xmlnsValues.length);
+                xmlnsValues = newValues;
+            }
+            xmlnsNames[xmlnsLength] = name;
+            xmlnsValues[xmlnsLength] = value;
+            xmlnsLength++;
+            switch (xmlnsPolicy) {
+                case FATAL:
+                    // this is ugly
+                    throw new SAXException("Saw an xmlns attribute.");
+                case ALTER_INFOSET:
+                    return;
+                case ALLOW:
+                    // fall through
+            }
+        }
+
+        // ]NOCPP]
+
+        if (names.length == length) {
+            int newLen = length << 1; // The first growth covers virtually
+            // 100% of elements according to
+            // Hixie
+            AttributeName[] newNames = new AttributeName[newLen];
+            System.arraycopy(names, 0, newNames, 0, names.length);
+            names = newNames;
+            String[] newValues = new String[newLen];
+            System.arraycopy(values, 0, newValues, 0, values.length);
+            values = newValues;
+            // CPPONLY: int[] newLines = new int[newLen];
+            // CPPONLY: System.arraycopy(lines, 0, newLines, 0, lines.length);
+            // CPPONLY: lines = newLines;
+        }
+        names[length] = name;
+        values[length] = value;
+        // CPPONLY: lines[length] = line;
+        length++;
+    }
+
+    void clear(int m) {
+        for (int i = 0; i < length; i++) {
+            names[i].release();
+            names[i] = null;
+            Portability.releaseString(values[i]);
+            values[i] = null;
+        }
+        length = 0;
+        mode = m;
+        // [NOCPP[
+        idValue = null;
+        for (int i = 0; i < xmlnsLength; i++) {
+            xmlnsNames[i] = null;
+            xmlnsValues[i] = null;
+        }
+        xmlnsLength = 0;
+        // ]NOCPP]
+    }
+    
+    /**
+     * This is used in C++ to release special <code>isindex</code>
+     * attribute values whose ownership is not transferred.
+     */
+    void releaseValue(int i) {
+        Portability.releaseString(values[i]);        
+    }
+    
+    /**
+     * This is only used for <code>AttributeName</code> ownership transfer
+     * in the isindex case to avoid freeing custom names twice in C++.
+     */
+    void clearWithoutReleasingContents() {
+        for (int i = 0; i < length; i++) {
+            names[i] = null;
+            values[i] = null;
+        }
+        length = 0;
+    }
+
+    boolean contains(AttributeName name) {
+        for (int i = 0; i < length; i++) {
+            if (name.equalsAnother(names[i])) {
+                return true;
+            }
+        }
+        // [NOCPP[
+        for (int i = 0; i < xmlnsLength; i++) {
+            if (name.equalsAnother(xmlnsNames[i])) {
+                return true;
+            }
+        }
+        // ]NOCPP]
+        return false;
+    }
+
+    public void adjustForMath() {
+        mode = AttributeName.MATHML;
+    }
+
+    public void adjustForSvg() {
+        mode = AttributeName.SVG;
+    }
+
+    public HtmlAttributes cloneAttributes(Interner interner)
+            throws SAXException {
+        assert (length == 0
+                // [NOCPP[
+                && xmlnsLength == 0
+                // ]NOCPP]
+                )
+                || mode == 0 || mode == 3;
+        HtmlAttributes clone = new HtmlAttributes(0);
+        for (int i = 0; i < length; i++) {
+            clone.addAttribute(names[i].cloneAttributeName(interner),
+                    Portability.newStringFromString(values[i])
+                    // [NOCPP[
+                    , XmlViolationPolicy.ALLOW
+                    // ]NOCPP]
+                    // CPPONLY: , lines[i]
+            );
+        }
+        // [NOCPP[
+        for (int i = 0; i < xmlnsLength; i++) {
+            clone.addAttribute(xmlnsNames[i], xmlnsValues[i],
+                    XmlViolationPolicy.ALLOW);
+        }
+        // ]NOCPP]
+        return clone; // XXX!!!
+    }
+
+    public boolean equalsAnother(HtmlAttributes other) {
+        assert mode == 0 || mode == 3 : "Trying to compare attributes in foreign content.";
+        int otherLength = other.getLength();
+        if (length != otherLength) {
+            return false;
+        }
+        for (int i = 0; i < length; i++) {
+            // Work around the limitations of C++
+            boolean found = false;
+            // The comparing just the local names is OK, since these attribute
+            // holders are both supposed to belong to HTML formatting elements
+            @Local String ownLocal = names[i].getLocal(AttributeName.HTML);
+            for (int j = 0; j < otherLength; j++) {
+                if (ownLocal == other.names[j].getLocal(AttributeName.HTML)) {
+                    found = true;
+                    if (!Portability.stringEqualsString(values[i], other.values[j])) {
+                        return false;
+                    }
+                }
+            }
+            if (!found) {
+                return false;
+            }
+        }
+        return true;
+    }
+    
+    // [NOCPP[
+    
+    void processNonNcNames(TreeBuilder<?> treeBuilder, XmlViolationPolicy namePolicy) throws SAXException {
+        for (int i = 0; i < length; i++) {
+            AttributeName attName = names[i];
+            if (!attName.isNcName(mode)) {
+                String name = attName.getLocal(mode);
+                switch (namePolicy) {
+                    case ALTER_INFOSET:
+                        names[i] = AttributeName.create(NCName.escapeName(name));
+                        // fall through
+                    case ALLOW:
+                        if (attName != AttributeName.XML_LANG) {
+                            treeBuilder.warn("Attribute \u201C" + name + "\u201D is not serializable as XML 1.0.");
+                        }
+                        break;
+                    case FATAL:
+                        treeBuilder.fatal("Attribute \u201C" + name + "\u201D is not serializable as XML 1.0.");
+                        break;
+                }
+            }
+        }
+    }
+    
+    public void merge(HtmlAttributes attributes) throws SAXException {
+        int len = attributes.getLength();
+        for (int i = 0; i < len; i++) {
+            AttributeName name = attributes.getAttributeNameNoBoundsCheck(i);
+            if (!contains(name)) {
+                addAttribute(name, attributes.getValueNoBoundsCheck(i), XmlViolationPolicy.ALLOW);
+            }
+        }
+    }
+
+
+    // ]NOCPP]
+    
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/LocatorImpl.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/LocatorImpl.java
new file mode 100644
index 000000000..7a559d903
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/LocatorImpl.java
@@ -0,0 +1,60 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2011 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import org.xml.sax.Locator;
+
+public class LocatorImpl implements Locator {
+
+    private final String systemId;
+
+    private final String publicId;
+
+    private final int column;
+
+    private final int line;
+
+    public LocatorImpl(Locator locator) {
+        this.systemId = locator.getSystemId();
+        this.publicId = locator.getPublicId();
+        this.column = locator.getColumnNumber();
+        this.line = locator.getLineNumber();
+    }
+
+    public final int getColumnNumber() {
+        return column;
+    }
+
+    public final int getLineNumber() {
+        return line;
+    }
+
+    public final String getPublicId() {
+        return publicId;
+    }
+
+    public final String getSystemId() {
+        return systemId;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/MetaScanner.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/MetaScanner.java
new file mode 100644
index 000000000..9a3dc16b2
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/MetaScanner.java
@@ -0,0 +1,856 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2015 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import java.io.IOException;
+
+import nu.validator.htmlparser.annotation.Auto;
+import nu.validator.htmlparser.annotation.Inline;
+import nu.validator.htmlparser.common.ByteReadable;
+
+import org.xml.sax.SAXException;
+
+public abstract class MetaScanner {
+
+    /**
+     * Constant for "charset".
+     */
+    private static final char[] CHARSET = { 'h', 'a', 'r', 's', 'e', 't' };
+    
+    /**
+     * Constant for "content".
+     */
+    private static final char[] CONTENT = { 'o', 'n', 't', 'e', 'n', 't' };
+
+    /**
+     * Constant for "http-equiv".
+     */
+    private static final char[] HTTP_EQUIV = { 't', 't', 'p', '-', 'e', 'q',
+            'u', 'i', 'v' };
+
+    /**
+     * Constant for "content-type".
+     */
+    private static final char[] CONTENT_TYPE = { 'c', 'o', 'n', 't', 'e', 'n',
+            't', '-', 't', 'y', 'p', 'e' };
+
+    private static final int NO = 0;
+
+    private static final int M = 1;
+    
+    private static final int E = 2;
+    
+    private static final int T = 3;
+
+    private static final int A = 4;
+    
+    private static final int DATA = 0;
+
+    private static final int TAG_OPEN = 1;
+
+    private static final int SCAN_UNTIL_GT = 2;
+
+    private static final int TAG_NAME = 3;
+
+    private static final int BEFORE_ATTRIBUTE_NAME = 4;
+
+    private static final int ATTRIBUTE_NAME = 5;
+
+    private static final int AFTER_ATTRIBUTE_NAME = 6;
+
+    private static final int BEFORE_ATTRIBUTE_VALUE = 7;
+
+    private static final int ATTRIBUTE_VALUE_DOUBLE_QUOTED = 8;
+
+    private static final int ATTRIBUTE_VALUE_SINGLE_QUOTED = 9;
+
+    private static final int ATTRIBUTE_VALUE_UNQUOTED = 10;
+
+    private static final int AFTER_ATTRIBUTE_VALUE_QUOTED = 11;
+
+    private static final int MARKUP_DECLARATION_OPEN = 13;
+    
+    private static final int MARKUP_DECLARATION_HYPHEN = 14;
+
+    private static final int COMMENT_START = 15;
+
+    private static final int COMMENT_START_DASH = 16;
+
+    private static final int COMMENT = 17;
+
+    private static final int COMMENT_END_DASH = 18;
+
+    private static final int COMMENT_END = 19;
+    
+    private static final int SELF_CLOSING_START_TAG = 20;
+    
+    private static final int HTTP_EQUIV_NOT_SEEN = 0;
+    
+    private static final int HTTP_EQUIV_CONTENT_TYPE = 1;
+
+    private static final int HTTP_EQUIV_OTHER = 2;
+
+    /**
+     * The data source.
+     */
+    protected ByteReadable readable;
+    
+    /**
+     * The state of the state machine that recognizes the tag name "meta".
+     */
+    private int metaState = NO;
+
+    /**
+     * The current position in recognizing the attribute name "content".
+     */
+    private int contentIndex = Integer.MAX_VALUE;
+    
+    /**
+     * The current position in recognizing the attribute name "charset".
+     */
+    private int charsetIndex = Integer.MAX_VALUE;
+
+    /**
+     * The current position in recognizing the attribute name "http-equive".
+     */
+    private int httpEquivIndex = Integer.MAX_VALUE;
+
+    /**
+     * The current position in recognizing the attribute value "content-type".
+     */
+    private int contentTypeIndex = Integer.MAX_VALUE;
+
+    /**
+     * The tokenizer state.
+     */
+    protected int stateSave = DATA;
+
+    /**
+     * The currently filled length of strBuf.
+     */
+    private int strBufLen;
+
+    /**
+     * Accumulation buffer for attribute values.
+     */
+    private @Auto char[] strBuf;
+    
+    private String content;
+    
+    private String charset;
+    
+    private int httpEquivState;
+    
+    // CPPONLY: private TreeBuilder treeBuilder;
+
+    public MetaScanner(
+        // CPPONLY: TreeBuilder tb
+    ) {
+        this.readable = null;
+        this.metaState = NO;
+        this.contentIndex = Integer.MAX_VALUE;
+        this.charsetIndex = Integer.MAX_VALUE;
+        this.httpEquivIndex = Integer.MAX_VALUE;
+        this.contentTypeIndex = Integer.MAX_VALUE;
+        this.stateSave = DATA;
+        this.strBufLen = 0;
+        this.strBuf = new char[36];
+        this.content = null;
+        this.charset = null;
+        this.httpEquivState = HTTP_EQUIV_NOT_SEEN;
+        // CPPONLY: this.treeBuilder = tb;
+    }
+    
+    @SuppressWarnings("unused") private void destructor() {
+        Portability.releaseString(content);
+        Portability.releaseString(charset);
+    }
+
+    // [NOCPP[
+    
+    /**
+     * Reads a byte from the data source.
+     * 
+     * -1 means end.
+     * @return
+     * @throws IOException
+     */
+    protected int read() throws IOException {
+        return readable.readByte();
+    }
+
+    // ]NOCPP]
+
+    // WARNING When editing this, makes sure the bytecode length shown by javap
+    // stays under 8000 bytes!
+    /**
+     * The runs the meta scanning algorithm.
+     */
+    protected final void stateLoop(int state)
+            throws SAXException, IOException {
+        int c = -1;
+        boolean reconsume = false;
+        stateloop: for (;;) {
+            switch (state) {
+                case DATA:
+                    dataloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            c = read();
+                        }
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '<':
+                                state = MetaScanner.TAG_OPEN;
+                                break dataloop; // FALL THROUGH continue
+                            // stateloop;
+                            default:
+                                continue;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case TAG_OPEN:
+                    tagopenloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case 'm':
+                            case 'M':
+                                metaState = M;
+                                state = MetaScanner.TAG_NAME;
+                                break tagopenloop;
+                                // continue stateloop;                                
+                            case '!':
+                                state = MetaScanner.MARKUP_DECLARATION_OPEN;
+                                continue stateloop;
+                            case '?':
+                            case '/':
+                                state = MetaScanner.SCAN_UNTIL_GT;
+                                continue stateloop;
+                            case '>':
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            default:
+                                if ((c >= 'A' && c <= 'Z') || (c >= 'a' && c <= 'z')) {
+                                    metaState = NO;
+                                    state = MetaScanner.TAG_NAME;
+                                    break tagopenloop;
+                                    // continue stateloop;
+                                }
+                                state = MetaScanner.DATA;
+                                reconsume = true;
+                                continue stateloop;
+                        }
+                    }
+                    // FALL THROUGH DON'T REORDER
+                case TAG_NAME:
+                    tagnameloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case ' ':
+                            case '\t':
+                            case '\n':
+                            case '\u000C':
+                                state = MetaScanner.BEFORE_ATTRIBUTE_NAME;
+                                break tagnameloop;
+                            // continue stateloop;
+                            case '/':
+                                state = MetaScanner.SELF_CLOSING_START_TAG;
+                                continue stateloop;
+                            case '>':
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            case 'e':
+                            case 'E':
+                                if (metaState == M) {
+                                    metaState = E;
+                                } else {
+                                    metaState = NO;
+                                }
+                                continue;
+                            case 't':
+                            case 'T':
+                                if (metaState == E) {
+                                    metaState = T;
+                                } else {
+                                    metaState = NO;
+                                }
+                                continue;
+                            case 'a':
+                            case 'A':
+                                if (metaState == T) {
+                                    metaState = A;
+                                } else {
+                                    metaState = NO;
+                                }
+                                continue;
+                            default:
+                                metaState = NO;
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BEFORE_ATTRIBUTE_NAME:
+                    beforeattributenameloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            c = read();
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case ' ':
+                            case '\t':
+                            case '\n':
+                            case '\u000C':
+                                continue;
+                            case '/':
+                                state = MetaScanner.SELF_CLOSING_START_TAG;
+                                continue stateloop;
+                            case '>':
+                                if (handleTag()) {
+                                    break stateloop;
+                                }
+                                state = DATA;
+                                continue stateloop;
+                            case 'c':
+                            case 'C':
+                                contentIndex = 0;
+                                charsetIndex = 0;
+                                httpEquivIndex = Integer.MAX_VALUE;
+                                contentTypeIndex = Integer.MAX_VALUE;
+                                state = MetaScanner.ATTRIBUTE_NAME;
+                                break beforeattributenameloop;                                
+                            case 'h':
+                            case 'H':
+                                contentIndex = Integer.MAX_VALUE;
+                                charsetIndex = Integer.MAX_VALUE;
+                                httpEquivIndex = 0;
+                                contentTypeIndex = Integer.MAX_VALUE;
+                                state = MetaScanner.ATTRIBUTE_NAME;
+                                break beforeattributenameloop;                                
+                            default:
+                                contentIndex = Integer.MAX_VALUE;
+                                charsetIndex = Integer.MAX_VALUE;
+                                httpEquivIndex = Integer.MAX_VALUE;
+                                contentTypeIndex = Integer.MAX_VALUE;
+                                state = MetaScanner.ATTRIBUTE_NAME;
+                                break beforeattributenameloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case ATTRIBUTE_NAME:
+                    attributenameloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case ' ':
+                            case '\t':
+                            case '\n':
+                            case '\u000C':
+                                state = MetaScanner.AFTER_ATTRIBUTE_NAME;
+                                continue stateloop;
+                            case '/':
+                                state = MetaScanner.SELF_CLOSING_START_TAG;
+                                continue stateloop;
+                            case '=':
+                                strBufLen = 0;
+                                contentTypeIndex = 0;
+                                state = MetaScanner.BEFORE_ATTRIBUTE_VALUE;
+                                break attributenameloop;
+                            // continue stateloop;
+                            case '>':
+                                if (handleTag()) {
+                                    break stateloop;
+                                }
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            default:
+                                if (metaState == A) {
+                                    if (c >= 'A' && c <= 'Z') {
+                                        c += 0x20;
+                                    }
+                                    if (contentIndex < CONTENT.length && c == CONTENT[contentIndex]) {
+                                        ++contentIndex;
+                                    } else {
+                                        contentIndex = Integer.MAX_VALUE;
+                                    }
+                                    if (charsetIndex < CHARSET.length && c == CHARSET[charsetIndex]) {
+                                        ++charsetIndex;
+                                    } else {
+                                        charsetIndex = Integer.MAX_VALUE;
+                                    }
+                                    if (httpEquivIndex < HTTP_EQUIV.length && c == HTTP_EQUIV[httpEquivIndex]) {
+                                        ++httpEquivIndex;
+                                    } else {
+                                        httpEquivIndex = Integer.MAX_VALUE;
+                                    }                                    
+                                }
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BEFORE_ATTRIBUTE_VALUE:
+                    beforeattributevalueloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case ' ':
+                            case '\t':
+                            case '\n':
+                            case '\u000C':
+                                continue;
+                            case '"':
+                                state = MetaScanner.ATTRIBUTE_VALUE_DOUBLE_QUOTED;
+                                break beforeattributevalueloop;
+                            // continue stateloop;
+                            case '\'':
+                                state = MetaScanner.ATTRIBUTE_VALUE_SINGLE_QUOTED;
+                                continue stateloop;
+                            case '>':
+                                if (handleTag()) {
+                                    break stateloop;
+                                }
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            default:
+                                handleCharInAttributeValue(c);
+                                state = MetaScanner.ATTRIBUTE_VALUE_UNQUOTED;
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case ATTRIBUTE_VALUE_DOUBLE_QUOTED:
+                    attributevaluedoublequotedloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            c = read();
+                        }
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '"':
+                                handleAttributeValue();
+                                state = MetaScanner.AFTER_ATTRIBUTE_VALUE_QUOTED;
+                                break attributevaluedoublequotedloop;
+                            // continue stateloop;
+                            default:
+                                handleCharInAttributeValue(c);
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case AFTER_ATTRIBUTE_VALUE_QUOTED:
+                    afterattributevaluequotedloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case ' ':
+                            case '\t':
+                            case '\n':
+                            case '\u000C':
+                                state = MetaScanner.BEFORE_ATTRIBUTE_NAME;
+                                continue stateloop;
+                            case '/':
+                                state = MetaScanner.SELF_CLOSING_START_TAG;
+                                break afterattributevaluequotedloop;
+                            // continue stateloop;
+                            case '>':
+                                if (handleTag()) {
+                                    break stateloop;
+                                }
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            default:
+                                state = MetaScanner.BEFORE_ATTRIBUTE_NAME;
+                                reconsume = true;
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case SELF_CLOSING_START_TAG:
+                    c = read();
+                    switch (c) {
+                        case -1:
+                            break stateloop;
+                        case '>':
+                            if (handleTag()) {
+                                break stateloop;
+                            }
+                            state = MetaScanner.DATA;
+                            continue stateloop;
+                        default:
+                            state = MetaScanner.BEFORE_ATTRIBUTE_NAME;
+                            reconsume = true;
+                            continue stateloop;
+                    }
+                    // XXX reorder point
+                case ATTRIBUTE_VALUE_UNQUOTED:
+                    for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            c = read();
+                        }
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case ' ':
+                            case '\t':
+                            case '\n':
+
+                            case '\u000C':
+                                handleAttributeValue();
+                                state = MetaScanner.BEFORE_ATTRIBUTE_NAME;
+                                continue stateloop;
+                            case '>':
+                                handleAttributeValue();
+                                if (handleTag()) {
+                                    break stateloop;
+                                }
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            default:
+                                handleCharInAttributeValue(c);
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case AFTER_ATTRIBUTE_NAME:
+                    for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case ' ':
+                            case '\t':
+                            case '\n':
+                            case '\u000C':
+                                continue;
+                            case '/':
+                                handleAttributeValue();
+                                state = MetaScanner.SELF_CLOSING_START_TAG;
+                                continue stateloop;
+                            case '=':
+                                strBufLen = 0;
+                                contentTypeIndex = 0;
+                                state = MetaScanner.BEFORE_ATTRIBUTE_VALUE;
+                                continue stateloop;
+                            case '>':
+                                handleAttributeValue();
+                                if (handleTag()) {
+                                    break stateloop;
+                                }
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            case 'c':
+                            case 'C':
+                                contentIndex = 0;
+                                charsetIndex = 0;
+                                state = MetaScanner.ATTRIBUTE_NAME;
+                                continue stateloop;
+                            default:
+                                contentIndex = Integer.MAX_VALUE;
+                                charsetIndex = Integer.MAX_VALUE;
+                                state = MetaScanner.ATTRIBUTE_NAME;
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case MARKUP_DECLARATION_OPEN:
+                    markupdeclarationopenloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '-':
+                                state = MetaScanner.MARKUP_DECLARATION_HYPHEN;
+                                break markupdeclarationopenloop;
+                            // continue stateloop;
+                            default:
+                                state = MetaScanner.SCAN_UNTIL_GT;
+                                reconsume = true;
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case MARKUP_DECLARATION_HYPHEN:
+                    markupdeclarationhyphenloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '-':
+                                state = MetaScanner.COMMENT_START;
+                                break markupdeclarationhyphenloop;
+                            // continue stateloop;
+                            default:
+                                state = MetaScanner.SCAN_UNTIL_GT;
+                                reconsume = true;
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT_START:
+                    commentstartloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '-':
+                                state = MetaScanner.COMMENT_START_DASH;
+                                continue stateloop;
+                            case '>':
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            default:
+                                state = MetaScanner.COMMENT;
+                                break commentstartloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT:
+                    commentloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '-':
+                                state = MetaScanner.COMMENT_END_DASH;
+                                break commentloop;
+                            // continue stateloop;
+                            default:
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT_END_DASH:
+                    commentenddashloop: for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '-':
+                                state = MetaScanner.COMMENT_END;
+                                break commentenddashloop;
+                            // continue stateloop;
+                            default:
+                                state = MetaScanner.COMMENT;
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT_END:
+                    for (;;) {
+                        c = read();
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '>':
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            case '-':
+                                continue;
+                            default:
+                                state = MetaScanner.COMMENT;
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case COMMENT_START_DASH:
+                    c = read();
+                    switch (c) {
+                        case -1:
+                            break stateloop;
+                        case '-':
+                            state = MetaScanner.COMMENT_END;
+                            continue stateloop;
+                        case '>':
+                            state = MetaScanner.DATA;
+                            continue stateloop;
+                        default:
+                            state = MetaScanner.COMMENT;
+                            continue stateloop;
+                    }
+                    // XXX reorder point
+                case ATTRIBUTE_VALUE_SINGLE_QUOTED:
+                    for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            c = read();
+                        }
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '\'':
+                                handleAttributeValue();
+                                state = MetaScanner.AFTER_ATTRIBUTE_VALUE_QUOTED;
+                                continue stateloop;
+                            default:
+                                handleCharInAttributeValue(c);
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case SCAN_UNTIL_GT:
+                    for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            c = read();
+                        }
+                        switch (c) {
+                            case -1:
+                                break stateloop;
+                            case '>':
+                                state = MetaScanner.DATA;
+                                continue stateloop;
+                            default:
+                                continue;
+                        }
+                    }
+            }
+        }
+        stateSave  = state;
+    }
+
+    private void handleCharInAttributeValue(int c) {
+        if (metaState == A) {
+            if (contentIndex == CONTENT.length || charsetIndex == CHARSET.length) {
+                addToBuffer(c);
+            } else if (httpEquivIndex == HTTP_EQUIV.length) {
+                if (contentTypeIndex < CONTENT_TYPE.length && toAsciiLowerCase(c) == CONTENT_TYPE[contentTypeIndex]) {
+                    ++contentTypeIndex;
+                } else {
+                    contentTypeIndex = Integer.MAX_VALUE;
+                }
+            }
+        }
+    }
+
+    @Inline private int toAsciiLowerCase(int c) {
+        if (c >= 'A' && c <= 'Z') {
+            return c + 0x20;
+        }
+        return c;
+    }
+
+    /**
+     * Adds a character to the accumulation buffer.
+     * @param c the character to add
+     */
+    private void addToBuffer(int c) {
+        if (strBufLen == strBuf.length) {
+            char[] newBuf = new char[strBuf.length + (strBuf.length << 1)];
+            System.arraycopy(strBuf, 0, newBuf, 0, strBuf.length);
+            strBuf = newBuf;
+        }
+        strBuf[strBufLen++] = (char)c;
+    }
+
+    /**
+     * Attempts to extract a charset name from the accumulation buffer.
+     * @return <code>true</code> if successful
+     * @throws SAXException
+     */
+    private void handleAttributeValue() throws SAXException {
+        if (metaState != A) {
+            return;
+        }
+        if (contentIndex == CONTENT.length && content == null) {
+            content = Portability.newStringFromBuffer(strBuf, 0, strBufLen
+                 // CPPONLY: , treeBuilder
+            );
+            return;
+        }
+        if (charsetIndex == CHARSET.length && charset == null) {
+            charset = Portability.newStringFromBuffer(strBuf, 0, strBufLen
+                 // CPPONLY: , treeBuilder
+            );
+            return;
+        }
+        if (httpEquivIndex == HTTP_EQUIV.length
+                && httpEquivState == HTTP_EQUIV_NOT_SEEN) {
+            httpEquivState = (contentTypeIndex == CONTENT_TYPE.length) ? HTTP_EQUIV_CONTENT_TYPE
+                    : HTTP_EQUIV_OTHER;
+            return;
+        }
+    }
+
+    private boolean handleTag() throws SAXException {
+        boolean stop = handleTagInner();
+        Portability.releaseString(content);
+        content = null;
+        Portability.releaseString(charset);
+        charset = null;
+        httpEquivState = HTTP_EQUIV_NOT_SEEN;
+        return stop;
+    }
+    
+    private boolean handleTagInner() throws SAXException {
+        if (charset != null && tryCharset(charset)) {
+                return true;
+        }
+        if (content != null && httpEquivState == HTTP_EQUIV_CONTENT_TYPE) {
+            String extract = TreeBuilder.extractCharsetFromContent(content
+                // CPPONLY: , treeBuilder
+            );
+            if (extract == null) {
+                return false;
+            }
+            boolean success = tryCharset(extract);
+            Portability.releaseString(extract);
+            return success;
+        }
+        return false;
+    }
+
+    /**
+     * Tries to switch to an encoding.
+     * 
+     * @param encoding
+     * @return <code>true</code> if successful
+     * @throws SAXException
+     */
+    protected abstract boolean tryCharset(String encoding) throws SAXException;
+    
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NCName.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NCName.java
new file mode 100644
index 000000000..940cf2e9c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NCName.java
@@ -0,0 +1,495 @@
+/*
+ * Copyright (c) 2008-2009 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+public final class NCName {
+    // [NOCPP[
+
+    private static final int SURROGATE_OFFSET = 0x10000 - (0xD800 << 10) - 0xDC00;
+    
+    private static final char[] HEX_TABLE = "0123456789ABCDEF".toCharArray();
+    
+    public static boolean isNCNameStart(char c) {
+        return ((c >= '\u0041' && c <= '\u005A')
+                || (c >= '\u0061' && c <= '\u007A')
+                || (c >= '\u00C0' && c <= '\u00D6')
+                || (c >= '\u00D8' && c <= '\u00F6')
+                || (c >= '\u00F8' && c <= '\u00FF')
+                || (c >= '\u0100' && c <= '\u0131')
+                || (c >= '\u0134' && c <= '\u013E')
+                || (c >= '\u0141' && c <= '\u0148')
+                || (c >= '\u014A' && c <= '\u017E')
+                || (c >= '\u0180' && c <= '\u01C3')
+                || (c >= '\u01CD' && c <= '\u01F0')
+                || (c >= '\u01F4' && c <= '\u01F5')
+                || (c >= '\u01FA' && c <= '\u0217')
+                || (c >= '\u0250' && c <= '\u02A8')
+                || (c >= '\u02BB' && c <= '\u02C1') || (c == '\u0386')
+                || (c >= '\u0388' && c <= '\u038A') || (c == '\u038C')
+                || (c >= '\u038E' && c <= '\u03A1')
+                || (c >= '\u03A3' && c <= '\u03CE')
+                || (c >= '\u03D0' && c <= '\u03D6') || (c == '\u03DA')
+                || (c == '\u03DC') || (c == '\u03DE') || (c == '\u03E0')
+                || (c >= '\u03E2' && c <= '\u03F3')
+                || (c >= '\u0401' && c <= '\u040C')
+                || (c >= '\u040E' && c <= '\u044F')
+                || (c >= '\u0451' && c <= '\u045C')
+                || (c >= '\u045E' && c <= '\u0481')
+                || (c >= '\u0490' && c <= '\u04C4')
+                || (c >= '\u04C7' && c <= '\u04C8')
+                || (c >= '\u04CB' && c <= '\u04CC')
+                || (c >= '\u04D0' && c <= '\u04EB')
+                || (c >= '\u04EE' && c <= '\u04F5')
+                || (c >= '\u04F8' && c <= '\u04F9')
+                || (c >= '\u0531' && c <= '\u0556') || (c == '\u0559')
+                || (c >= '\u0561' && c <= '\u0586')
+                || (c >= '\u05D0' && c <= '\u05EA')
+                || (c >= '\u05F0' && c <= '\u05F2')
+                || (c >= '\u0621' && c <= '\u063A')
+                || (c >= '\u0641' && c <= '\u064A')
+                || (c >= '\u0671' && c <= '\u06B7')
+                || (c >= '\u06BA' && c <= '\u06BE')
+                || (c >= '\u06C0' && c <= '\u06CE')
+                || (c >= '\u06D0' && c <= '\u06D3') || (c == '\u06D5')
+                || (c >= '\u06E5' && c <= '\u06E6')
+                || (c >= '\u0905' && c <= '\u0939') || (c == '\u093D')
+                || (c >= '\u0958' && c <= '\u0961')
+                || (c >= '\u0985' && c <= '\u098C')
+                || (c >= '\u098F' && c <= '\u0990')
+                || (c >= '\u0993' && c <= '\u09A8')
+                || (c >= '\u09AA' && c <= '\u09B0') || (c == '\u09B2')
+                || (c >= '\u09B6' && c <= '\u09B9')
+                || (c >= '\u09DC' && c <= '\u09DD')
+                || (c >= '\u09DF' && c <= '\u09E1')
+                || (c >= '\u09F0' && c <= '\u09F1')
+                || (c >= '\u0A05' && c <= '\u0A0A')
+                || (c >= '\u0A0F' && c <= '\u0A10')
+                || (c >= '\u0A13' && c <= '\u0A28')
+                || (c >= '\u0A2A' && c <= '\u0A30')
+                || (c >= '\u0A32' && c <= '\u0A33')
+                || (c >= '\u0A35' && c <= '\u0A36')
+                || (c >= '\u0A38' && c <= '\u0A39')
+                || (c >= '\u0A59' && c <= '\u0A5C') || (c == '\u0A5E')
+                || (c >= '\u0A72' && c <= '\u0A74')
+                || (c >= '\u0A85' && c <= '\u0A8B') || (c == '\u0A8D')
+                || (c >= '\u0A8F' && c <= '\u0A91')
+                || (c >= '\u0A93' && c <= '\u0AA8')
+                || (c >= '\u0AAA' && c <= '\u0AB0')
+                || (c >= '\u0AB2' && c <= '\u0AB3')
+                || (c >= '\u0AB5' && c <= '\u0AB9') || (c == '\u0ABD')
+                || (c == '\u0AE0') || (c >= '\u0B05' && c <= '\u0B0C')
+                || (c >= '\u0B0F' && c <= '\u0B10')
+                || (c >= '\u0B13' && c <= '\u0B28')
+                || (c >= '\u0B2A' && c <= '\u0B30')
+                || (c >= '\u0B32' && c <= '\u0B33')
+                || (c >= '\u0B36' && c <= '\u0B39') || (c == '\u0B3D')
+                || (c >= '\u0B5C' && c <= '\u0B5D')
+                || (c >= '\u0B5F' && c <= '\u0B61')
+                || (c >= '\u0B85' && c <= '\u0B8A')
+                || (c >= '\u0B8E' && c <= '\u0B90')
+                || (c >= '\u0B92' && c <= '\u0B95')
+                || (c >= '\u0B99' && c <= '\u0B9A') || (c == '\u0B9C')
+                || (c >= '\u0B9E' && c <= '\u0B9F')
+                || (c >= '\u0BA3' && c <= '\u0BA4')
+                || (c >= '\u0BA8' && c <= '\u0BAA')
+                || (c >= '\u0BAE' && c <= '\u0BB5')
+                || (c >= '\u0BB7' && c <= '\u0BB9')
+                || (c >= '\u0C05' && c <= '\u0C0C')
+                || (c >= '\u0C0E' && c <= '\u0C10')
+                || (c >= '\u0C12' && c <= '\u0C28')
+                || (c >= '\u0C2A' && c <= '\u0C33')
+                || (c >= '\u0C35' && c <= '\u0C39')
+                || (c >= '\u0C60' && c <= '\u0C61')
+                || (c >= '\u0C85' && c <= '\u0C8C')
+                || (c >= '\u0C8E' && c <= '\u0C90')
+                || (c >= '\u0C92' && c <= '\u0CA8')
+                || (c >= '\u0CAA' && c <= '\u0CB3')
+                || (c >= '\u0CB5' && c <= '\u0CB9') || (c == '\u0CDE')
+                || (c >= '\u0CE0' && c <= '\u0CE1')
+                || (c >= '\u0D05' && c <= '\u0D0C')
+                || (c >= '\u0D0E' && c <= '\u0D10')
+                || (c >= '\u0D12' && c <= '\u0D28')
+                || (c >= '\u0D2A' && c <= '\u0D39')
+                || (c >= '\u0D60' && c <= '\u0D61')
+                || (c >= '\u0E01' && c <= '\u0E2E') || (c == '\u0E30')
+                || (c >= '\u0E32' && c <= '\u0E33')
+                || (c >= '\u0E40' && c <= '\u0E45')
+                || (c >= '\u0E81' && c <= '\u0E82') || (c == '\u0E84')
+                || (c >= '\u0E87' && c <= '\u0E88') || (c == '\u0E8A')
+                || (c == '\u0E8D') || (c >= '\u0E94' && c <= '\u0E97')
+                || (c >= '\u0E99' && c <= '\u0E9F')
+                || (c >= '\u0EA1' && c <= '\u0EA3') || (c == '\u0EA5')
+                || (c == '\u0EA7') || (c >= '\u0EAA' && c <= '\u0EAB')
+                || (c >= '\u0EAD' && c <= '\u0EAE') || (c == '\u0EB0')
+                || (c >= '\u0EB2' && c <= '\u0EB3') || (c == '\u0EBD')
+                || (c >= '\u0EC0' && c <= '\u0EC4')
+                || (c >= '\u0F40' && c <= '\u0F47')
+                || (c >= '\u0F49' && c <= '\u0F69')
+                || (c >= '\u10A0' && c <= '\u10C5')
+                || (c >= '\u10D0' && c <= '\u10F6') || (c == '\u1100')
+                || (c >= '\u1102' && c <= '\u1103')
+                || (c >= '\u1105' && c <= '\u1107') || (c == '\u1109')
+                || (c >= '\u110B' && c <= '\u110C')
+                || (c >= '\u110E' && c <= '\u1112') || (c == '\u113C')
+                || (c == '\u113E') || (c == '\u1140') || (c == '\u114C')
+                || (c == '\u114E') || (c == '\u1150')
+                || (c >= '\u1154' && c <= '\u1155') || (c == '\u1159')
+                || (c >= '\u115F' && c <= '\u1161') || (c == '\u1163')
+                || (c == '\u1165') || (c == '\u1167') || (c == '\u1169')
+                || (c >= '\u116D' && c <= '\u116E')
+                || (c >= '\u1172' && c <= '\u1173') || (c == '\u1175')
+                || (c == '\u119E') || (c == '\u11A8') || (c == '\u11AB')
+                || (c >= '\u11AE' && c <= '\u11AF')
+                || (c >= '\u11B7' && c <= '\u11B8') || (c == '\u11BA')
+                || (c >= '\u11BC' && c <= '\u11C2') || (c == '\u11EB')
+                || (c == '\u11F0') || (c == '\u11F9')
+                || (c >= '\u1E00' && c <= '\u1E9B')
+                || (c >= '\u1EA0' && c <= '\u1EF9')
+                || (c >= '\u1F00' && c <= '\u1F15')
+                || (c >= '\u1F18' && c <= '\u1F1D')
+                || (c >= '\u1F20' && c <= '\u1F45')
+                || (c >= '\u1F48' && c <= '\u1F4D')
+                || (c >= '\u1F50' && c <= '\u1F57') || (c == '\u1F59')
+                || (c == '\u1F5B') || (c == '\u1F5D')
+                || (c >= '\u1F5F' && c <= '\u1F7D')
+                || (c >= '\u1F80' && c <= '\u1FB4')
+                || (c >= '\u1FB6' && c <= '\u1FBC') || (c == '\u1FBE')
+                || (c >= '\u1FC2' && c <= '\u1FC4')
+                || (c >= '\u1FC6' && c <= '\u1FCC')
+                || (c >= '\u1FD0' && c <= '\u1FD3')
+                || (c >= '\u1FD6' && c <= '\u1FDB')
+                || (c >= '\u1FE0' && c <= '\u1FEC')
+                || (c >= '\u1FF2' && c <= '\u1FF4')
+                || (c >= '\u1FF6' && c <= '\u1FFC') || (c == '\u2126')
+                || (c >= '\u212A' && c <= '\u212B') || (c == '\u212E')
+                || (c >= '\u2180' && c <= '\u2182')
+                || (c >= '\u3041' && c <= '\u3094')
+                || (c >= '\u30A1' && c <= '\u30FA')
+                || (c >= '\u3105' && c <= '\u312C')
+                || (c >= '\uAC00' && c <= '\uD7A3')
+                || (c >= '\u4E00' && c <= '\u9FA5') || (c == '\u3007')
+                || (c >= '\u3021' && c <= '\u3029') || (c == '_'));
+    }
+
+    public static boolean isNCNameTrail(char c) {
+        return ((c >= '\u0030' && c <= '\u0039')
+                || (c >= '\u0660' && c <= '\u0669')
+                || (c >= '\u06F0' && c <= '\u06F9')
+                || (c >= '\u0966' && c <= '\u096F')
+                || (c >= '\u09E6' && c <= '\u09EF')
+                || (c >= '\u0A66' && c <= '\u0A6F')
+                || (c >= '\u0AE6' && c <= '\u0AEF')
+                || (c >= '\u0B66' && c <= '\u0B6F')
+                || (c >= '\u0BE7' && c <= '\u0BEF')
+                || (c >= '\u0C66' && c <= '\u0C6F')
+                || (c >= '\u0CE6' && c <= '\u0CEF')
+                || (c >= '\u0D66' && c <= '\u0D6F')
+                || (c >= '\u0E50' && c <= '\u0E59')
+                || (c >= '\u0ED0' && c <= '\u0ED9')
+                || (c >= '\u0F20' && c <= '\u0F29')
+                || (c >= '\u0041' && c <= '\u005A')
+                || (c >= '\u0061' && c <= '\u007A')
+                || (c >= '\u00C0' && c <= '\u00D6')
+                || (c >= '\u00D8' && c <= '\u00F6')
+                || (c >= '\u00F8' && c <= '\u00FF')
+                || (c >= '\u0100' && c <= '\u0131')
+                || (c >= '\u0134' && c <= '\u013E')
+                || (c >= '\u0141' && c <= '\u0148')
+                || (c >= '\u014A' && c <= '\u017E')
+                || (c >= '\u0180' && c <= '\u01C3')
+                || (c >= '\u01CD' && c <= '\u01F0')
+                || (c >= '\u01F4' && c <= '\u01F5')
+                || (c >= '\u01FA' && c <= '\u0217')
+                || (c >= '\u0250' && c <= '\u02A8')
+                || (c >= '\u02BB' && c <= '\u02C1') || (c == '\u0386')
+                || (c >= '\u0388' && c <= '\u038A') || (c == '\u038C')
+                || (c >= '\u038E' && c <= '\u03A1')
+                || (c >= '\u03A3' && c <= '\u03CE')
+                || (c >= '\u03D0' && c <= '\u03D6') || (c == '\u03DA')
+                || (c == '\u03DC') || (c == '\u03DE') || (c == '\u03E0')
+                || (c >= '\u03E2' && c <= '\u03F3')
+                || (c >= '\u0401' && c <= '\u040C')
+                || (c >= '\u040E' && c <= '\u044F')
+                || (c >= '\u0451' && c <= '\u045C')
+                || (c >= '\u045E' && c <= '\u0481')
+                || (c >= '\u0490' && c <= '\u04C4')
+                || (c >= '\u04C7' && c <= '\u04C8')
+                || (c >= '\u04CB' && c <= '\u04CC')
+                || (c >= '\u04D0' && c <= '\u04EB')
+                || (c >= '\u04EE' && c <= '\u04F5')
+                || (c >= '\u04F8' && c <= '\u04F9')
+                || (c >= '\u0531' && c <= '\u0556') || (c == '\u0559')
+                || (c >= '\u0561' && c <= '\u0586')
+                || (c >= '\u05D0' && c <= '\u05EA')
+                || (c >= '\u05F0' && c <= '\u05F2')
+                || (c >= '\u0621' && c <= '\u063A')
+                || (c >= '\u0641' && c <= '\u064A')
+                || (c >= '\u0671' && c <= '\u06B7')
+                || (c >= '\u06BA' && c <= '\u06BE')
+                || (c >= '\u06C0' && c <= '\u06CE')
+                || (c >= '\u06D0' && c <= '\u06D3') || (c == '\u06D5')
+                || (c >= '\u06E5' && c <= '\u06E6')
+                || (c >= '\u0905' && c <= '\u0939') || (c == '\u093D')
+                || (c >= '\u0958' && c <= '\u0961')
+                || (c >= '\u0985' && c <= '\u098C')
+                || (c >= '\u098F' && c <= '\u0990')
+                || (c >= '\u0993' && c <= '\u09A8')
+                || (c >= '\u09AA' && c <= '\u09B0') || (c == '\u09B2')
+                || (c >= '\u09B6' && c <= '\u09B9')
+                || (c >= '\u09DC' && c <= '\u09DD')
+                || (c >= '\u09DF' && c <= '\u09E1')
+                || (c >= '\u09F0' && c <= '\u09F1')
+                || (c >= '\u0A05' && c <= '\u0A0A')
+                || (c >= '\u0A0F' && c <= '\u0A10')
+                || (c >= '\u0A13' && c <= '\u0A28')
+                || (c >= '\u0A2A' && c <= '\u0A30')
+                || (c >= '\u0A32' && c <= '\u0A33')
+                || (c >= '\u0A35' && c <= '\u0A36')
+                || (c >= '\u0A38' && c <= '\u0A39')
+                || (c >= '\u0A59' && c <= '\u0A5C') || (c == '\u0A5E')
+                || (c >= '\u0A72' && c <= '\u0A74')
+                || (c >= '\u0A85' && c <= '\u0A8B') || (c == '\u0A8D')
+                || (c >= '\u0A8F' && c <= '\u0A91')
+                || (c >= '\u0A93' && c <= '\u0AA8')
+                || (c >= '\u0AAA' && c <= '\u0AB0')
+                || (c >= '\u0AB2' && c <= '\u0AB3')
+                || (c >= '\u0AB5' && c <= '\u0AB9') || (c == '\u0ABD')
+                || (c == '\u0AE0') || (c >= '\u0B05' && c <= '\u0B0C')
+                || (c >= '\u0B0F' && c <= '\u0B10')
+                || (c >= '\u0B13' && c <= '\u0B28')
+                || (c >= '\u0B2A' && c <= '\u0B30')
+                || (c >= '\u0B32' && c <= '\u0B33')
+                || (c >= '\u0B36' && c <= '\u0B39') || (c == '\u0B3D')
+                || (c >= '\u0B5C' && c <= '\u0B5D')
+                || (c >= '\u0B5F' && c <= '\u0B61')
+                || (c >= '\u0B85' && c <= '\u0B8A')
+                || (c >= '\u0B8E' && c <= '\u0B90')
+                || (c >= '\u0B92' && c <= '\u0B95')
+                || (c >= '\u0B99' && c <= '\u0B9A') || (c == '\u0B9C')
+                || (c >= '\u0B9E' && c <= '\u0B9F')
+                || (c >= '\u0BA3' && c <= '\u0BA4')
+                || (c >= '\u0BA8' && c <= '\u0BAA')
+                || (c >= '\u0BAE' && c <= '\u0BB5')
+                || (c >= '\u0BB7' && c <= '\u0BB9')
+                || (c >= '\u0C05' && c <= '\u0C0C')
+                || (c >= '\u0C0E' && c <= '\u0C10')
+                || (c >= '\u0C12' && c <= '\u0C28')
+                || (c >= '\u0C2A' && c <= '\u0C33')
+                || (c >= '\u0C35' && c <= '\u0C39')
+                || (c >= '\u0C60' && c <= '\u0C61')
+                || (c >= '\u0C85' && c <= '\u0C8C')
+                || (c >= '\u0C8E' && c <= '\u0C90')
+                || (c >= '\u0C92' && c <= '\u0CA8')
+                || (c >= '\u0CAA' && c <= '\u0CB3')
+                || (c >= '\u0CB5' && c <= '\u0CB9') || (c == '\u0CDE')
+                || (c >= '\u0CE0' && c <= '\u0CE1')
+                || (c >= '\u0D05' && c <= '\u0D0C')
+                || (c >= '\u0D0E' && c <= '\u0D10')
+                || (c >= '\u0D12' && c <= '\u0D28')
+                || (c >= '\u0D2A' && c <= '\u0D39')
+                || (c >= '\u0D60' && c <= '\u0D61')
+                || (c >= '\u0E01' && c <= '\u0E2E') || (c == '\u0E30')
+                || (c >= '\u0E32' && c <= '\u0E33')
+                || (c >= '\u0E40' && c <= '\u0E45')
+                || (c >= '\u0E81' && c <= '\u0E82') || (c == '\u0E84')
+                || (c >= '\u0E87' && c <= '\u0E88') || (c == '\u0E8A')
+                || (c == '\u0E8D') || (c >= '\u0E94' && c <= '\u0E97')
+                || (c >= '\u0E99' && c <= '\u0E9F')
+                || (c >= '\u0EA1' && c <= '\u0EA3') || (c == '\u0EA5')
+                || (c == '\u0EA7') || (c >= '\u0EAA' && c <= '\u0EAB')
+                || (c >= '\u0EAD' && c <= '\u0EAE') || (c == '\u0EB0')
+                || (c >= '\u0EB2' && c <= '\u0EB3') || (c == '\u0EBD')
+                || (c >= '\u0EC0' && c <= '\u0EC4')
+                || (c >= '\u0F40' && c <= '\u0F47')
+                || (c >= '\u0F49' && c <= '\u0F69')
+                || (c >= '\u10A0' && c <= '\u10C5')
+                || (c >= '\u10D0' && c <= '\u10F6') || (c == '\u1100')
+                || (c >= '\u1102' && c <= '\u1103')
+                || (c >= '\u1105' && c <= '\u1107') || (c == '\u1109')
+                || (c >= '\u110B' && c <= '\u110C')
+                || (c >= '\u110E' && c <= '\u1112') || (c == '\u113C')
+                || (c == '\u113E') || (c == '\u1140') || (c == '\u114C')
+                || (c == '\u114E') || (c == '\u1150')
+                || (c >= '\u1154' && c <= '\u1155') || (c == '\u1159')
+                || (c >= '\u115F' && c <= '\u1161') || (c == '\u1163')
+                || (c == '\u1165') || (c == '\u1167') || (c == '\u1169')
+                || (c >= '\u116D' && c <= '\u116E')
+                || (c >= '\u1172' && c <= '\u1173') || (c == '\u1175')
+                || (c == '\u119E') || (c == '\u11A8') || (c == '\u11AB')
+                || (c >= '\u11AE' && c <= '\u11AF')
+                || (c >= '\u11B7' && c <= '\u11B8') || (c == '\u11BA')
+                || (c >= '\u11BC' && c <= '\u11C2') || (c == '\u11EB')
+                || (c == '\u11F0') || (c == '\u11F9')
+                || (c >= '\u1E00' && c <= '\u1E9B')
+                || (c >= '\u1EA0' && c <= '\u1EF9')
+                || (c >= '\u1F00' && c <= '\u1F15')
+                || (c >= '\u1F18' && c <= '\u1F1D')
+                || (c >= '\u1F20' && c <= '\u1F45')
+                || (c >= '\u1F48' && c <= '\u1F4D')
+                || (c >= '\u1F50' && c <= '\u1F57') || (c == '\u1F59')
+                || (c == '\u1F5B') || (c == '\u1F5D')
+                || (c >= '\u1F5F' && c <= '\u1F7D')
+                || (c >= '\u1F80' && c <= '\u1FB4')
+                || (c >= '\u1FB6' && c <= '\u1FBC') || (c == '\u1FBE')
+                || (c >= '\u1FC2' && c <= '\u1FC4')
+                || (c >= '\u1FC6' && c <= '\u1FCC')
+                || (c >= '\u1FD0' && c <= '\u1FD3')
+                || (c >= '\u1FD6' && c <= '\u1FDB')
+                || (c >= '\u1FE0' && c <= '\u1FEC')
+                || (c >= '\u1FF2' && c <= '\u1FF4')
+                || (c >= '\u1FF6' && c <= '\u1FFC') || (c == '\u2126')
+                || (c >= '\u212A' && c <= '\u212B') || (c == '\u212E')
+                || (c >= '\u2180' && c <= '\u2182')
+                || (c >= '\u3041' && c <= '\u3094')
+                || (c >= '\u30A1' && c <= '\u30FA')
+                || (c >= '\u3105' && c <= '\u312C')
+                || (c >= '\uAC00' && c <= '\uD7A3')
+                || (c >= '\u4E00' && c <= '\u9FA5') || (c == '\u3007')
+                || (c >= '\u3021' && c <= '\u3029') || (c == '_') || (c == '.')
+                || (c == '-') || (c >= '\u0300' && c <= '\u0345')
+                || (c >= '\u0360' && c <= '\u0361')
+                || (c >= '\u0483' && c <= '\u0486')
+                || (c >= '\u0591' && c <= '\u05A1')
+                || (c >= '\u05A3' && c <= '\u05B9')
+                || (c >= '\u05BB' && c <= '\u05BD') || (c == '\u05BF')
+                || (c >= '\u05C1' && c <= '\u05C2') || (c == '\u05C4')
+                || (c >= '\u064B' && c <= '\u0652') || (c == '\u0670')
+                || (c >= '\u06D6' && c <= '\u06DC')
+                || (c >= '\u06DD' && c <= '\u06DF')
+                || (c >= '\u06E0' && c <= '\u06E4')
+                || (c >= '\u06E7' && c <= '\u06E8')
+                || (c >= '\u06EA' && c <= '\u06ED')
+                || (c >= '\u0901' && c <= '\u0903') || (c == '\u093C')
+                || (c >= '\u093E' && c <= '\u094C') || (c == '\u094D')
+                || (c >= '\u0951' && c <= '\u0954')
+                || (c >= '\u0962' && c <= '\u0963')
+                || (c >= '\u0981' && c <= '\u0983') || (c == '\u09BC')
+                || (c == '\u09BE') || (c == '\u09BF')
+                || (c >= '\u09C0' && c <= '\u09C4')
+                || (c >= '\u09C7' && c <= '\u09C8')
+                || (c >= '\u09CB' && c <= '\u09CD') || (c == '\u09D7')
+                || (c >= '\u09E2' && c <= '\u09E3') || (c == '\u0A02')
+                || (c == '\u0A3C') || (c == '\u0A3E') || (c == '\u0A3F')
+                || (c >= '\u0A40' && c <= '\u0A42')
+                || (c >= '\u0A47' && c <= '\u0A48')
+                || (c >= '\u0A4B' && c <= '\u0A4D')
+                || (c >= '\u0A70' && c <= '\u0A71')
+                || (c >= '\u0A81' && c <= '\u0A83') || (c == '\u0ABC')
+                || (c >= '\u0ABE' && c <= '\u0AC5')
+                || (c >= '\u0AC7' && c <= '\u0AC9')
+                || (c >= '\u0ACB' && c <= '\u0ACD')
+                || (c >= '\u0B01' && c <= '\u0B03') || (c == '\u0B3C')
+                || (c >= '\u0B3E' && c <= '\u0B43')
+                || (c >= '\u0B47' && c <= '\u0B48')
+                || (c >= '\u0B4B' && c <= '\u0B4D')
+                || (c >= '\u0B56' && c <= '\u0B57')
+                || (c >= '\u0B82' && c <= '\u0B83')
+                || (c >= '\u0BBE' && c <= '\u0BC2')
+                || (c >= '\u0BC6' && c <= '\u0BC8')
+                || (c >= '\u0BCA' && c <= '\u0BCD') || (c == '\u0BD7')
+                || (c >= '\u0C01' && c <= '\u0C03')
+                || (c >= '\u0C3E' && c <= '\u0C44')
+                || (c >= '\u0C46' && c <= '\u0C48')
+                || (c >= '\u0C4A' && c <= '\u0C4D')
+                || (c >= '\u0C55' && c <= '\u0C56')
+                || (c >= '\u0C82' && c <= '\u0C83')
+                || (c >= '\u0CBE' && c <= '\u0CC4')
+                || (c >= '\u0CC6' && c <= '\u0CC8')
+                || (c >= '\u0CCA' && c <= '\u0CCD')
+                || (c >= '\u0CD5' && c <= '\u0CD6')
+                || (c >= '\u0D02' && c <= '\u0D03')
+                || (c >= '\u0D3E' && c <= '\u0D43')
+                || (c >= '\u0D46' && c <= '\u0D48')
+                || (c >= '\u0D4A' && c <= '\u0D4D') || (c == '\u0D57')
+                || (c == '\u0E31') || (c >= '\u0E34' && c <= '\u0E3A')
+                || (c >= '\u0E47' && c <= '\u0E4E') || (c == '\u0EB1')
+                || (c >= '\u0EB4' && c <= '\u0EB9')
+                || (c >= '\u0EBB' && c <= '\u0EBC')
+                || (c >= '\u0EC8' && c <= '\u0ECD')
+                || (c >= '\u0F18' && c <= '\u0F19') || (c == '\u0F35')
+                || (c == '\u0F37') || (c == '\u0F39') || (c == '\u0F3E')
+                || (c == '\u0F3F') || (c >= '\u0F71' && c <= '\u0F84')
+                || (c >= '\u0F86' && c <= '\u0F8B')
+                || (c >= '\u0F90' && c <= '\u0F95') || (c == '\u0F97')
+                || (c >= '\u0F99' && c <= '\u0FAD')
+                || (c >= '\u0FB1' && c <= '\u0FB7') || (c == '\u0FB9')
+                || (c >= '\u20D0' && c <= '\u20DC') || (c == '\u20E1')
+                || (c >= '\u302A' && c <= '\u302F') || (c == '\u3099')
+                || (c == '\u309A') || (c == '\u00B7') || (c == '\u02D0')
+                || (c == '\u02D1') || (c == '\u0387') || (c == '\u0640')
+                || (c == '\u0E46') || (c == '\u0EC6') || (c == '\u3005')
+                || (c >= '\u3031' && c <= '\u3035')
+                || (c >= '\u309D' && c <= '\u309E') || (c >= '\u30FC' && c <= '\u30FE'));
+    }
+
+    public static boolean isNCName(String str) {
+        if (str == null) {
+            return false;
+        } else {
+            int len = str.length();
+            switch (len) {
+                case 0:
+                    return false;
+                case 1:
+                    return NCName.isNCNameStart(str.charAt(0));
+                default:
+                    if (!NCName.isNCNameStart(str.charAt(0))) {
+                        return false;
+                    }
+                    for (int i = 1; i < len; i++) {
+                        if (!NCName.isNCNameTrail(str.charAt(i))) {
+                            return false;
+                        }
+                    }
+            }
+            return true;
+        }
+    }
+    
+    private static void appendUHexTo(StringBuilder sb, int c) {
+        sb.append('U');
+        for (int i = 0; i < 6; i++) {
+            sb.append(HEX_TABLE[(c & 0xF00000) >> 20]);
+            c <<= 4;
+        }
+    }
+    
+    public static String escapeName(String str) {
+        StringBuilder sb = new StringBuilder();
+        for (int i = 0; i < str.length(); i++) {
+            char c = str.charAt(i);
+            if ((c & 0xFC00) == 0xD800) {
+                char next = str.charAt(++i);
+                appendUHexTo(sb, (c << 10) + next + SURROGATE_OFFSET);          
+            } else if (i == 0 && !isNCNameStart(c)) {
+                appendUHexTo(sb, c);
+            } else if (i != 0 && !isNCNameTrail(c)) {
+                appendUHexTo(sb, c);                
+            } else {
+                sb.append(c);
+            }
+        }
+        return sb.toString().intern();
+    }
+    // ]NOCPP]
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NamedCharacters.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NamedCharacters.java
new file mode 100644
index 000000000..266a5a28e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NamedCharacters.java
@@ -0,0 +1,944 @@
+/*
+ * Copyright 2004-2010 Apple Computer, Inc., Mozilla Foundation, and Opera 
+ * Software ASA.
+ * 
+ * You are granted a license to use, reproduce and create derivative works of 
+ * this document.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.CharacterName;
+import nu.validator.htmlparser.annotation.NoLength;
+
+/**
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class NamedCharacters {
+
+    static final @NoLength @CharacterName String[] NAMES = { "lig", "lig;",
+            "P", "P;", "cute", "cute;", "reve;", "irc", "irc;", "y;", "r;",
+            "rave", "rave;", "pha;", "acr;", "d;", "gon;", "pf;",
+            "plyFunction;", "ing", "ing;", "cr;", "sign;", "ilde", "ilde;",
+            "ml", "ml;", "ckslash;", "rv;", "rwed;", "y;", "cause;",
+            "rnoullis;", "ta;", "r;", "pf;", "eve;", "cr;", "mpeq;", "cy;",
+            "PY", "PY;", "cute;", "p;", "pitalDifferentialD;", "yleys;",
+            "aron;", "edil", "edil;", "irc;", "onint;", "ot;", "dilla;",
+            "nterDot;", "r;", "i;", "rcleDot;", "rcleMinus;", "rclePlus;",
+            "rcleTimes;", "ockwiseContourIntegral;", "oseCurlyDoubleQuote;",
+            "oseCurlyQuote;", "lon;", "lone;", "ngruent;", "nint;",
+            "ntourIntegral;", "pf;", "product;",
+            "unterClockwiseContourIntegral;", "oss;", "cr;", "p;", "pCap;",
+            ";", "otrahd;", "cy;", "cy;", "cy;", "gger;", "rr;", "shv;",
+            "aron;", "y;", "l;", "lta;", "r;", "acriticalAcute;",
+            "acriticalDot;", "acriticalDoubleAcute;", "acriticalGrave;",
+            "acriticalTilde;", "amond;", "fferentialD;", "pf;", "t;", "tDot;",
+            "tEqual;", "ubleContourIntegral;", "ubleDot;", "ubleDownArrow;",
+            "ubleLeftArrow;", "ubleLeftRightArrow;", "ubleLeftTee;",
+            "ubleLongLeftArrow;", "ubleLongLeftRightArrow;",
+            "ubleLongRightArrow;", "ubleRightArrow;", "ubleRightTee;",
+            "ubleUpArrow;", "ubleUpDownArrow;", "ubleVerticalBar;", "wnArrow;",
+            "wnArrowBar;", "wnArrowUpArrow;", "wnBreve;", "wnLeftRightVector;",
+            "wnLeftTeeVector;", "wnLeftVector;", "wnLeftVectorBar;",
+            "wnRightTeeVector;", "wnRightVector;", "wnRightVectorBar;",
+            "wnTee;", "wnTeeArrow;", "wnarrow;", "cr;", "trok;", "G;", "H",
+            "H;", "cute", "cute;", "aron;", "irc", "irc;", "y;", "ot;", "r;",
+            "rave", "rave;", "ement;", "acr;", "ptySmallSquare;",
+            "ptyVerySmallSquare;", "gon;", "pf;", "silon;", "ual;",
+            "ualTilde;", "uilibrium;", "cr;", "im;", "a;", "ml", "ml;",
+            "ists;", "ponentialE;", "y;", "r;", "lledSmallSquare;",
+            "lledVerySmallSquare;", "pf;", "rAll;", "uriertrf;", "cr;", "cy;",
+            "", ";", "mma;", "mmad;", "reve;", "edil;", "irc;", "y;", "ot;",
+            "r;", ";", "pf;", "eaterEqual;", "eaterEqualLess;",
+            "eaterFullEqual;", "eaterGreater;", "eaterLess;",
+            "eaterSlantEqual;", "eaterTilde;", "cr;", ";", "RDcy;", "cek;",
+            "t;", "irc;", "r;", "lbertSpace;", "pf;", "rizontalLine;", "cr;",
+            "trok;", "mpDownHump;", "mpEqual;", "cy;", "lig;", "cy;", "cute",
+            "cute;", "irc", "irc;", "y;", "ot;", "r;", "rave", "rave;", ";",
+            "acr;", "aginaryI;", "plies;", "t;", "tegral;", "tersection;",
+            "visibleComma;", "visibleTimes;", "gon;", "pf;", "ta;", "cr;",
+            "ilde;", "kcy;", "ml", "ml;", "irc;", "y;", "r;", "pf;", "cr;",
+            "ercy;", "kcy;", "cy;", "cy;", "ppa;", "edil;", "y;", "r;", "pf;",
+            "cr;", "cy;", "", ";", "cute;", "mbda;", "ng;", "placetrf;", "rr;",
+            "aron;", "edil;", "y;", "ftAngleBracket;", "ftArrow;",
+            "ftArrowBar;", "ftArrowRightArrow;", "ftCeiling;",
+            "ftDoubleBracket;", "ftDownTeeVector;", "ftDownVector;",
+            "ftDownVectorBar;", "ftFloor;", "ftRightArrow;", "ftRightVector;",
+            "ftTee;", "ftTeeArrow;", "ftTeeVector;", "ftTriangle;",
+            "ftTriangleBar;", "ftTriangleEqual;", "ftUpDownVector;",
+            "ftUpTeeVector;", "ftUpVector;", "ftUpVectorBar;", "ftVector;",
+            "ftVectorBar;", "ftarrow;", "ftrightarrow;", "ssEqualGreater;",
+            "ssFullEqual;", "ssGreater;", "ssLess;", "ssSlantEqual;",
+            "ssTilde;", "r;", ";", "eftarrow;", "idot;", "ngLeftArrow;",
+            "ngLeftRightArrow;", "ngRightArrow;", "ngleftarrow;",
+            "ngleftrightarrow;", "ngrightarrow;", "pf;", "werLeftArrow;",
+            "werRightArrow;", "cr;", "h;", "trok;", ";", "p;", "y;",
+            "diumSpace;", "llintrf;", "r;", "nusPlus;", "pf;", "cr;", ";",
+            "cy;", "cute;", "aron;", "edil;", "y;", "gativeMediumSpace;",
+            "gativeThickSpace;", "gativeThinSpace;", "gativeVeryThinSpace;",
+            "stedGreaterGreater;", "stedLessLess;", "wLine;", "r;", "Break;",
+            "nBreakingSpace;", "pf;", "t;", "tCongruent;", "tCupCap;",
+            "tDoubleVerticalBar;", "tElement;", "tEqual;", "tEqualTilde;",
+            "tExists;", "tGreater;", "tGreaterEqual;", "tGreaterFullEqual;",
+            "tGreaterGreater;", "tGreaterLess;", "tGreaterSlantEqual;",
+            "tGreaterTilde;", "tHumpDownHump;", "tHumpEqual;",
+            "tLeftTriangle;", "tLeftTriangleBar;", "tLeftTriangleEqual;",
+            "tLess;", "tLessEqual;", "tLessGreater;", "tLessLess;",
+            "tLessSlantEqual;", "tLessTilde;", "tNestedGreaterGreater;",
+            "tNestedLessLess;", "tPrecedes;", "tPrecedesEqual;",
+            "tPrecedesSlantEqual;", "tReverseElement;", "tRightTriangle;",
+            "tRightTriangleBar;", "tRightTriangleEqual;", "tSquareSubset;",
+            "tSquareSubsetEqual;", "tSquareSuperset;", "tSquareSupersetEqual;",
+            "tSubset;", "tSubsetEqual;", "tSucceeds;", "tSucceedsEqual;",
+            "tSucceedsSlantEqual;", "tSucceedsTilde;", "tSuperset;",
+            "tSupersetEqual;", "tTilde;", "tTildeEqual;", "tTildeFullEqual;",
+            "tTildeTilde;", "tVerticalBar;", "cr;", "ilde", "ilde;", ";",
+            "lig;", "cute", "cute;", "irc", "irc;", "y;", "blac;", "r;",
+            "rave", "rave;", "acr;", "ega;", "icron;", "pf;",
+            "enCurlyDoubleQuote;", "enCurlyQuote;", ";", "cr;", "lash",
+            "lash;", "ilde", "ilde;", "imes;", "ml", "ml;", "erBar;",
+            "erBrace;", "erBracket;", "erParenthesis;", "rtialD;", "y;", "r;",
+            "i;", ";", "usMinus;", "incareplane;", "pf;", ";", "ecedes;",
+            "ecedesEqual;", "ecedesSlantEqual;", "ecedesTilde;", "ime;",
+            "oduct;", "oportion;", "oportional;", "cr;", "i;", "OT", "OT;",
+            "r;", "pf;", "cr;", "arr;", "G", "G;", "cute;", "ng;", "rr;",
+            "rrtl;", "aron;", "edil;", "y;", ";", "verseElement;",
+            "verseEquilibrium;", "verseUpEquilibrium;", "r;", "o;",
+            "ghtAngleBracket;", "ghtArrow;", "ghtArrowBar;",
+            "ghtArrowLeftArrow;", "ghtCeiling;", "ghtDoubleBracket;",
+            "ghtDownTeeVector;", "ghtDownVector;", "ghtDownVectorBar;",
+            "ghtFloor;", "ghtTee;", "ghtTeeArrow;", "ghtTeeVector;",
+            "ghtTriangle;", "ghtTriangleBar;", "ghtTriangleEqual;",
+            "ghtUpDownVector;", "ghtUpTeeVector;", "ghtUpVector;",
+            "ghtUpVectorBar;", "ghtVector;", "ghtVectorBar;", "ghtarrow;",
+            "pf;", "undImplies;", "ightarrow;", "cr;", "h;", "leDelayed;",
+            "CHcy;", "cy;", "FTcy;", "cute;", ";", "aron;", "edil;", "irc;",
+            "y;", "r;", "ortDownArrow;", "ortLeftArrow;", "ortRightArrow;",
+            "ortUpArrow;", "gma;", "allCircle;", "pf;", "rt;", "uare;",
+            "uareIntersection;", "uareSubset;", "uareSubsetEqual;",
+            "uareSuperset;", "uareSupersetEqual;", "uareUnion;", "cr;", "ar;",
+            "b;", "bset;", "bsetEqual;", "cceeds;", "cceedsEqual;",
+            "cceedsSlantEqual;", "cceedsTilde;", "chThat;", "m;", "p;",
+            "perset;", "persetEqual;", "pset;", "ORN", "ORN;", "ADE;", "Hcy;",
+            "cy;", "b;", "u;", "aron;", "edil;", "y;", "r;", "erefore;",
+            "eta;", "ickSpace;", "inSpace;", "lde;", "ldeEqual;",
+            "ldeFullEqual;", "ldeTilde;", "pf;", "ipleDot;", "cr;", "trok;",
+            "cute", "cute;", "rr;", "rrocir;", "rcy;", "reve;", "irc", "irc;",
+            "y;", "blac;", "r;", "rave", "rave;", "acr;", "derBar;",
+            "derBrace;", "derBracket;", "derParenthesis;", "ion;", "ionPlus;",
+            "gon;", "pf;", "Arrow;", "ArrowBar;", "ArrowDownArrow;",
+            "DownArrow;", "Equilibrium;", "Tee;", "TeeArrow;", "arrow;",
+            "downarrow;", "perLeftArrow;", "perRightArrow;", "si;", "silon;",
+            "ing;", "cr;", "ilde;", "ml", "ml;", "ash;", "ar;", "y;", "ash;",
+            "ashl;", "e;", "rbar;", "rt;", "rticalBar;", "rticalLine;",
+            "rticalSeparator;", "rticalTilde;", "ryThinSpace;", "r;", "pf;",
+            "cr;", "dash;", "irc;", "dge;", "r;", "pf;", "cr;", "r;", ";",
+            "pf;", "cr;", "cy;", "cy;", "cy;", "cute", "cute;", "irc;", "y;",
+            "r;", "pf;", "cr;", "ml;", "cy;", "cute;", "aron;", "y;", "ot;",
+            "roWidthSpace;", "ta;", "r;", "pf;", "cr;", "cute", "cute;",
+            "reve;", ";", "E;", "d;", "irc", "irc;", "ute", "ute;", "y;",
+            "lig", "lig;", ";", "r;", "rave", "rave;", "efsym;", "eph;",
+            "pha;", "acr;", "alg;", "p", "p;", "d;", "dand;", "dd;", "dslope;",
+            "dv;", "g;", "ge;", "gle;", "gmsd;", "gmsdaa;", "gmsdab;",
+            "gmsdac;", "gmsdad;", "gmsdae;", "gmsdaf;", "gmsdag;", "gmsdah;",
+            "grt;", "grtvb;", "grtvbd;", "gsph;", "gst;", "gzarr;", "gon;",
+            "pf;", ";", "E;", "acir;", "e;", "id;", "os;", "prox;", "proxeq;",
+            "ing", "ing;", "cr;", "t;", "ymp;", "ympeq;", "ilde", "ilde;",
+            "ml", "ml;", "conint;", "int;", "ot;", "ckcong;", "ckepsilon;",
+            "ckprime;", "cksim;", "cksimeq;", "rvee;", "rwed;", "rwedge;",
+            "rk;", "rktbrk;", "ong;", "y;", "quo;", "caus;", "cause;",
+            "mptyv;", "psi;", "rnou;", "ta;", "th;", "tween;", "r;", "gcap;",
+            "gcirc;", "gcup;", "godot;", "goplus;", "gotimes;", "gsqcup;",
+            "gstar;", "gtriangledown;", "gtriangleup;", "guplus;", "gvee;",
+            "gwedge;", "arow;", "acklozenge;", "acksquare;", "acktriangle;",
+            "acktriangledown;", "acktriangleleft;", "acktriangleright;",
+            "ank;", "k12;", "k14;", "k34;", "ock;", "e;", "equiv;", "ot;",
+            "pf;", "t;", "ttom;", "wtie;", "xDL;", "xDR;", "xDl;", "xDr;",
+            "xH;", "xHD;", "xHU;", "xHd;", "xHu;", "xUL;", "xUR;", "xUl;",
+            "xUr;", "xV;", "xVH;", "xVL;", "xVR;", "xVh;", "xVl;", "xVr;",
+            "xbox;", "xdL;", "xdR;", "xdl;", "xdr;", "xh;", "xhD;", "xhU;",
+            "xhd;", "xhu;", "xminus;", "xplus;", "xtimes;", "xuL;", "xuR;",
+            "xul;", "xur;", "xv;", "xvH;", "xvL;", "xvR;", "xvh;", "xvl;",
+            "xvr;", "rime;", "eve;", "vbar", "vbar;", "cr;", "emi;", "im;",
+            "ime;", "ol;", "olb;", "olhsub;", "ll;", "llet;", "mp;", "mpE;",
+            "mpe;", "mpeq;", "cute;", "p;", "pand;", "pbrcup;", "pcap;",
+            "pcup;", "pdot;", "ps;", "ret;", "ron;", "aps;", "aron;", "edil",
+            "edil;", "irc;", "ups;", "upssm;", "ot;", "dil", "dil;", "mptyv;",
+            "nt", "nt;", "nterdot;", "r;", "cy;", "eck;", "eckmark;", "i;",
+            "r;", "rE;", "rc;", "rceq;", "rclearrowleft;", "rclearrowright;",
+            "rcledR;", "rcledS;", "rcledast;", "rcledcirc;", "rcleddash;",
+            "re;", "rfnint;", "rmid;", "rscir;", "ubs;", "ubsuit;", "lon;",
+            "lone;", "loneq;", "mma;", "mmat;", "mp;", "mpfn;", "mplement;",
+            "mplexes;", "ng;", "ngdot;", "nint;", "pf;", "prod;", "py", "py;",
+            "pysr;", "arr;", "oss;", "cr;", "ub;", "ube;", "up;", "upe;",
+            "dot;", "darrl;", "darrr;", "epr;", "esc;", "larr;", "larrp;",
+            "p;", "pbrcap;", "pcap;", "pcup;", "pdot;", "por;", "ps;", "rarr;",
+            "rarrm;", "rlyeqprec;", "rlyeqsucc;", "rlyvee;", "rlywedge;",
+            "rren", "rren;", "rvearrowleft;", "rvearrowright;", "vee;", "wed;",
+            "conint;", "int;", "lcty;", "rr;", "ar;", "gger;", "leth;", "rr;",
+            "sh;", "shv;", "karow;", "lac;", "aron;", "y;", ";", "agger;",
+            "arr;", "otseq;", "g", "g;", "lta;", "mptyv;", "isht;", "r;",
+            "arl;", "arr;", "am;", "amond;", "amondsuit;", "ams;", "e;",
+            "gamma;", "sin;", "v;", "vide", "vide;", "videontimes;", "vonx;",
+            "cy;", "corn;", "crop;", "llar;", "pf;", "t;", "teq;", "teqdot;",
+            "tminus;", "tplus;", "tsquare;", "ublebarwedge;", "wnarrow;",
+            "wndownarrows;", "wnharpoonleft;", "wnharpoonright;", "bkarow;",
+            "corn;", "crop;", "cr;", "cy;", "ol;", "trok;", "dot;", "ri;",
+            "rif;", "arr;", "har;", "angle;", "cy;", "igrarr;", "Dot;", "ot;",
+            "cute", "cute;", "ster;", "aron;", "ir;", "irc", "irc;", "olon;",
+            "y;", "ot;", ";", "Dot;", "r;", ";", "rave", "rave;", "s;",
+            "sdot;", ";", "inters;", "l;", "s;", "sdot;", "acr;", "pty;",
+            "ptyset;", "ptyv;", "sp13;", "sp14;", "sp;", "g;", "sp;", "gon;",
+            "pf;", "ar;", "arsl;", "lus;", "si;", "silon;", "siv;", "circ;",
+            "colon;", "sim;", "slantgtr;", "slantless;", "uals;", "uest;",
+            "uiv;", "uivDD;", "vparsl;", "Dot;", "arr;", "cr;", "dot;", "im;",
+            "a;", "h", "h;", "ml", "ml;", "ro;", "cl;", "ist;", "pectation;",
+            "ponentiale;", "llingdotseq;", "y;", "male;", "ilig;", "lig;",
+            "llig;", "r;", "lig;", "lig;", "at;", "lig;", "tns;", "of;", "pf;",
+            "rall;", "rk;", "rkv;", "artint;", "ac12", "ac12;", "ac13;",
+            "ac14", "ac14;", "ac15;", "ac16;", "ac18;", "ac23;", "ac25;",
+            "ac34", "ac34;", "ac35;", "ac38;", "ac45;", "ac56;", "ac58;",
+            "ac78;", "asl;", "own;", "cr;", ";", "l;", "cute;", "mma;",
+            "mmad;", "p;", "reve;", "irc;", "y;", "ot;", ";", "l;", "q;",
+            "qq;", "qslant;", "s;", "scc;", "sdot;", "sdoto;", "sdotol;",
+            "sl;", "sles;", "r;", ";", "g;", "mel;", "cy;", ";", "E;", "a;",
+            "j;", "E;", "ap;", "approx;", "e;", "eq;", "eqq;", "sim;", "pf;",
+            "ave;", "cr;", "im;", "ime;", "iml;", "", ";", "cc;", "cir;",
+            "dot;", "lPar;", "quest;", "rapprox;", "rarr;", "rdot;",
+            "reqless;", "reqqless;", "rless;", "rsim;", "ertneqq;", "nE;",
+            "rr;", "irsp;", "lf;", "milt;", "rdcy;", "rr;", "rrcir;", "rrw;",
+            "ar;", "irc;", "arts;", "artsuit;", "llip;", "rcon;", "r;",
+            "searow;", "swarow;", "arr;", "mtht;", "okleftarrow;",
+            "okrightarrow;", "pf;", "rbar;", "cr;", "lash;", "trok;", "bull;",
+            "phen;", "cute", "cute;", ";", "irc", "irc;", "y;", "cy;", "xcl",
+            "xcl;", "f;", "r;", "rave", "rave;", ";", "iint;", "int;", "nfin;",
+            "ota;", "lig;", "acr;", "age;", "agline;", "agpart;", "ath;",
+            "of;", "ped;", ";", "care;", "fin;", "fintie;", "odot;", "t;",
+            "tcal;", "tegers;", "tercal;", "tlarhk;", "tprod;", "cy;", "gon;",
+            "pf;", "ta;", "rod;", "uest", "uest;", "cr;", "in;", "inE;",
+            "indot;", "ins;", "insv;", "inv;", ";", "ilde;", "kcy;", "ml",
+            "ml;", "irc;", "y;", "r;", "ath;", "pf;", "cr;", "ercy;", "kcy;",
+            "ppa;", "ppav;", "edil;", "y;", "r;", "reen;", "cy;", "cy;", "pf;",
+            "cr;", "arr;", "rr;", "tail;", "arr;", ";", "g;", "ar;", "cute;",
+            "emptyv;", "gran;", "mbda;", "ng;", "ngd;", "ngle;", "p;", "quo",
+            "quo;", "rr;", "rrb;", "rrbfs;", "rrfs;", "rrhk;", "rrlp;",
+            "rrpl;", "rrsim;", "rrtl;", "t;", "tail;", "te;", "tes;", "arr;",
+            "brk;", "race;", "rack;", "rke;", "rksld;", "rkslu;", "aron;",
+            "edil;", "eil;", "ub;", "y;", "ca;", "quo;", "quor;", "rdhar;",
+            "rushar;", "sh;", ";", "ftarrow;", "ftarrowtail;",
+            "ftharpoondown;", "ftharpoonup;", "ftleftarrows;", "ftrightarrow;",
+            "ftrightarrows;", "ftrightharpoons;", "ftrightsquigarrow;",
+            "ftthreetimes;", "g;", "q;", "qq;", "qslant;", "s;", "scc;",
+            "sdot;", "sdoto;", "sdotor;", "sg;", "sges;", "ssapprox;",
+            "ssdot;", "sseqgtr;", "sseqqgtr;", "ssgtr;", "sssim;", "isht;",
+            "loor;", "r;", ";", "E;", "ard;", "aru;", "arul;", "blk;", "cy;",
+            ";", "arr;", "corner;", "hard;", "tri;", "idot;", "oust;",
+            "oustache;", "E;", "ap;", "approx;", "e;", "eq;", "eqq;", "sim;",
+            "ang;", "arr;", "brk;", "ngleftarrow;", "ngleftrightarrow;",
+            "ngmapsto;", "ngrightarrow;", "oparrowleft;", "oparrowright;",
+            "par;", "pf;", "plus;", "times;", "wast;", "wbar;", "z;", "zenge;",
+            "zf;", "ar;", "arlt;", "arr;", "corner;", "har;", "hard;", "m;",
+            "tri;", "aquo;", "cr;", "h;", "im;", "ime;", "img;", "qb;", "quo;",
+            "quor;", "trok;", "", ";", "cc;", "cir;", "dot;", "hree;", "imes;",
+            "larr;", "quest;", "rPar;", "ri;", "rie;", "rif;", "rdshar;",
+            "ruhar;", "ertneqq;", "nE;", "Dot;", "cr", "cr;", "le;", "lt;",
+            "ltese;", "p;", "psto;", "pstodown;", "pstoleft;", "pstoup;",
+            "rker;", "omma;", "y;", "ash;", "asuredangle;", "r;", "o;", "cro",
+            "cro;", "d;", "dast;", "dcir;", "ddot", "ddot;", "nus;", "nusb;",
+            "nusd;", "nusdu;", "cp;", "dr;", "plus;", "dels;", "pf;", ";",
+            "cr;", "tpos;", ";", "ltimap;", "map;", "g;", "t;", "tv;",
+            "eftarrow;", "eftrightarrow;", "l;", "t;", "tv;", "ightarrow;",
+            "Dash;", "dash;", "bla;", "cute;", "ng;", "p;", "pE;", "pid;",
+            "pos;", "pprox;", "tur;", "tural;", "turals;", "sp", "sp;", "ump;",
+            "umpe;", "ap;", "aron;", "edil;", "ong;", "ongdot;", "up;", "y;",
+            "ash;", ";", "Arr;", "arhk;", "arr;", "arrow;", "dot;", "quiv;",
+            "sear;", "sim;", "xist;", "xists;", "r;", "E;", "e;", "eq;",
+            "eqq;", "eqslant;", "es;", "sim;", "t;", "tr;", "Arr;", "arr;",
+            "par;", ";", "s;", "sd;", "v;", "cy;", "Arr;", "E;", "arr;", "dr;",
+            "e;", "eftarrow;", "eftrightarrow;", "eq;", "eqq;", "eqslant;",
+            "es;", "ess;", "sim;", "t;", "tri;", "trie;", "id;", "pf;", "t",
+            "t;", "tin;", "tinE;", "tindot;", "tinva;", "tinvb;", "tinvc;",
+            "tni;", "tniva;", "tnivb;", "tnivc;", "ar;", "arallel;", "arsl;",
+            "art;", "olint;", "r;", "rcue;", "re;", "rec;", "receq;", "Arr;",
+            "arr;", "arrc;", "arrw;", "ightarrow;", "tri;", "trie;", "c;",
+            "ccue;", "ce;", "cr;", "hortmid;", "hortparallel;", "im;", "ime;",
+            "imeq;", "mid;", "par;", "qsube;", "qsupe;", "ub;", "ubE;", "ube;",
+            "ubset;", "ubseteq;", "ubseteqq;", "ucc;", "ucceq;", "up;", "upE;",
+            "upe;", "upset;", "upseteq;", "upseteqq;", "gl;", "ilde", "ilde;",
+            "lg;", "riangleleft;", "rianglelefteq;", "riangleright;",
+            "rianglerighteq;", ";", "m;", "mero;", "msp;", "Dash;", "Harr;",
+            "ap;", "dash;", "ge;", "gt;", "infin;", "lArr;", "le;", "lt;",
+            "ltrie;", "rArr;", "rtrie;", "sim;", "Arr;", "arhk;", "arr;",
+            "arrow;", "near;", ";", "cute", "cute;", "st;", "ir;", "irc",
+            "irc;", "y;", "ash;", "blac;", "iv;", "ot;", "sold;", "lig;",
+            "cir;", "r;", "on;", "rave", "rave;", "t;", "bar;", "m;", "nt;",
+            "arr;", "cir;", "cross;", "ine;", "t;", "acr;", "ega;", "icron;",
+            "id;", "inus;", "pf;", "ar;", "erp;", "lus;", ";", "arr;", "d;",
+            "der;", "derof;", "df", "df;", "dm", "dm;", "igof;", "or;",
+            "slope;", "v;", "cr;", "lash", "lash;", "ol;", "ilde", "ilde;",
+            "imes;", "imesas;", "ml", "ml;", "bar;", "r;", "ra", "ra;",
+            "rallel;", "rsim;", "rsl;", "rt;", "y;", "rcnt;", "riod;", "rmil;",
+            "rp;", "rtenk;", "r;", "i;", "iv;", "mmat;", "one;", ";",
+            "tchfork;", "v;", "anck;", "anckh;", "ankv;", "us;", "usacir;",
+            "usb;", "uscir;", "usdo;", "usdu;", "use;", "usmn", "usmn;",
+            "ussim;", "ustwo;", ";", "intint;", "pf;", "und", "und;", ";",
+            "E;", "ap;", "cue;", "e;", "ec;", "ecapprox;", "eccurlyeq;",
+            "eceq;", "ecnapprox;", "ecneqq;", "ecnsim;", "ecsim;", "ime;",
+            "imes;", "nE;", "nap;", "nsim;", "od;", "ofalar;", "ofline;",
+            "ofsurf;", "op;", "opto;", "sim;", "urel;", "cr;", "i;", "ncsp;",
+            "r;", "nt;", "pf;", "rime;", "cr;", "aternions;", "atint;", "est;",
+            "esteq;", "ot", "ot;", "arr;", "rr;", "tail;", "arr;", "ar;",
+            "ce;", "cute;", "dic;", "emptyv;", "ng;", "ngd;", "nge;", "ngle;",
+            "quo", "quo;", "rr;", "rrap;", "rrb;", "rrbfs;", "rrc;", "rrfs;",
+            "rrhk;", "rrlp;", "rrpl;", "rrsim;", "rrtl;", "rrw;", "tail;",
+            "tio;", "tionals;", "arr;", "brk;", "race;", "rack;", "rke;",
+            "rksld;", "rkslu;", "aron;", "edil;", "eil;", "ub;", "y;", "ca;",
+            "ldhar;", "quo;", "quor;", "sh;", "al;", "aline;", "alpart;",
+            "als;", "ct;", "g", "g;", "isht;", "loor;", "r;", "ard;", "aru;",
+            "arul;", "o;", "ov;", "ghtarrow;", "ghtarrowtail;",
+            "ghtharpoondown;", "ghtharpoonup;", "ghtleftarrows;",
+            "ghtleftharpoons;", "ghtrightarrows;", "ghtsquigarrow;",
+            "ghtthreetimes;", "ng;", "singdotseq;", "arr;", "har;", "m;",
+            "oust;", "oustache;", "mid;", "ang;", "arr;", "brk;", "par;",
+            "pf;", "plus;", "times;", "ar;", "argt;", "polint;", "arr;",
+            "aquo;", "cr;", "h;", "qb;", "quo;", "quor;", "hree;", "imes;",
+            "ri;", "rie;", "rif;", "riltri;", "luhar;", ";", "cute;", "quo;",
+            ";", "E;", "ap;", "aron;", "cue;", "e;", "edil;", "irc;", "nE;",
+            "nap;", "nsim;", "polint;", "sim;", "y;", "ot;", "otb;", "ote;",
+            "Arr;", "arhk;", "arr;", "arrow;", "ct", "ct;", "mi;", "swar;",
+            "tminus;", "tmn;", "xt;", "r;", "rown;", "arp;", "chcy;", "cy;",
+            "ortmid;", "ortparallel;", "y", "y;", "gma;", "gmaf;", "gmav;",
+            "m;", "mdot;", "me;", "meq;", "mg;", "mgE;", "ml;", "mlE;", "mne;",
+            "mplus;", "mrarr;", "arr;", "allsetminus;", "ashp;", "eparsl;",
+            "id;", "ile;", "t;", "te;", "tes;", "ftcy;", "l;", "lb;", "lbar;",
+            "pf;", "ades;", "adesuit;", "ar;", "cap;", "caps;", "cup;",
+            "cups;", "sub;", "sube;", "subset;", "subseteq;", "sup;", "supe;",
+            "supset;", "supseteq;", "u;", "uare;", "uarf;", "uf;", "arr;",
+            "cr;", "etmn;", "mile;", "tarf;", "ar;", "arf;", "raightepsilon;",
+            "raightphi;", "rns;", "b;", "bE;", "bdot;", "be;", "bedot;",
+            "bmult;", "bnE;", "bne;", "bplus;", "brarr;", "bset;", "bseteq;",
+            "bseteqq;", "bsetneq;", "bsetneqq;", "bsim;", "bsub;", "bsup;",
+            "cc;", "ccapprox;", "cccurlyeq;", "cceq;", "ccnapprox;", "ccneqq;",
+            "ccnsim;", "ccsim;", "m;", "ng;", "p1", "p1;", "p2", "p2;", "p3",
+            "p3;", "p;", "pE;", "pdot;", "pdsub;", "pe;", "pedot;", "phsol;",
+            "phsub;", "plarr;", "pmult;", "pnE;", "pne;", "pplus;", "pset;",
+            "pseteq;", "pseteqq;", "psetneq;", "psetneqq;", "psim;", "psub;",
+            "psup;", "Arr;", "arhk;", "arr;", "arrow;", "nwar;", "lig", "lig;",
+            "rget;", "u;", "rk;", "aron;", "edil;", "y;", "ot;", "lrec;", "r;",
+            "ere4;", "erefore;", "eta;", "etasym;", "etav;", "ickapprox;",
+            "icksim;", "insp;", "kap;", "ksim;", "orn", "orn;", "lde;", "mes",
+            "mes;", "mesb;", "mesbar;", "mesd;", "nt;", "ea;", "p;", "pbot;",
+            "pcir;", "pf;", "pfork;", "sa;", "rime;", "ade;", "iangle;",
+            "iangledown;", "iangleleft;", "ianglelefteq;", "iangleq;",
+            "iangleright;", "ianglerighteq;", "idot;", "ie;", "iminus;",
+            "iplus;", "isb;", "itime;", "pezium;", "cr;", "cy;", "hcy;",
+            "trok;", "ixt;", "oheadleftarrow;", "oheadrightarrow;", "rr;",
+            "ar;", "cute", "cute;", "rr;", "rcy;", "reve;", "irc", "irc;",
+            "y;", "arr;", "blac;", "har;", "isht;", "r;", "rave", "rave;",
+            "arl;", "arr;", "blk;", "corn;", "corner;", "crop;", "tri;",
+            "acr;", "l", "l;", "gon;", "pf;", "arrow;", "downarrow;",
+            "harpoonleft;", "harpoonright;", "lus;", "si;", "sih;", "silon;",
+            "uparrows;", "corn;", "corner;", "crop;", "ing;", "tri;", "cr;",
+            "dot;", "ilde;", "ri;", "rif;", "arr;", "ml", "ml;", "angle;",
+            "rr;", "ar;", "arv;", "ash;", "ngrt;", "repsilon;", "rkappa;",
+            "rnothing;", "rphi;", "rpi;", "rpropto;", "rr;", "rrho;",
+            "rsigma;", "rsubsetneq;", "rsubsetneqq;", "rsupsetneq;",
+            "rsupsetneqq;", "rtheta;", "rtriangleleft;", "rtriangleright;",
+            "y;", "ash;", "e;", "ebar;", "eeq;", "llip;", "rbar;", "rt;", "r;",
+            "tri;", "sub;", "sup;", "pf;", "rop;", "tri;", "cr;", "ubnE;",
+            "ubne;", "upnE;", "upne;", "igzag;", "irc;", "dbar;", "dge;",
+            "dgeq;", "ierp;", "r;", "pf;", ";", ";", "eath;", "cr;", "ap;",
+            "irc;", "up;", "tri;", "r;", "Arr;", "arr;", ";", "Arr;", "arr;",
+            "ap;", "is;", "dot;", "pf;", "plus;", "time;", "Arr;", "arr;",
+            "cr;", "qcup;", "plus;", "tri;", "ee;", "edge;", "cute", "cute;",
+            "cy;", "irc;", "y;", "n", "n;", "r;", "cy;", "pf;", "cr;", "cy;",
+            "ml", "ml;", "cute;", "aron;", "y;", "ot;", "etrf;", "ta;", "r;",
+            "cy;", "grarr;", "pf;", "cr;", "j;", "nj;", };
+
+    static final @NoLength char[][] VALUES = { { '\u00c6' }, { '\u00c6' },
+            { '\u0026' }, { '\u0026' }, { '\u00c1' }, { '\u00c1' },
+            { '\u0102' }, { '\u00c2' }, { '\u00c2' }, { '\u0410' },
+            { '\ud835', '\udd04' }, { '\u00c0' }, { '\u00c0' }, { '\u0391' },
+            { '\u0100' }, { '\u2a53' }, { '\u0104' }, { '\ud835', '\udd38' },
+            { '\u2061' }, { '\u00c5' }, { '\u00c5' }, { '\ud835', '\udc9c' },
+            { '\u2254' }, { '\u00c3' }, { '\u00c3' }, { '\u00c4' },
+            { '\u00c4' }, { '\u2216' }, { '\u2ae7' }, { '\u2306' },
+            { '\u0411' }, { '\u2235' }, { '\u212c' }, { '\u0392' },
+            { '\ud835', '\udd05' }, { '\ud835', '\udd39' }, { '\u02d8' },
+            { '\u212c' }, { '\u224e' }, { '\u0427' }, { '\u00a9' },
+            { '\u00a9' }, { '\u0106' }, { '\u22d2' }, { '\u2145' },
+            { '\u212d' }, { '\u010c' }, { '\u00c7' }, { '\u00c7' },
+            { '\u0108' }, { '\u2230' }, { '\u010a' }, { '\u00b8' },
+            { '\u00b7' }, { '\u212d' }, { '\u03a7' }, { '\u2299' },
+            { '\u2296' }, { '\u2295' }, { '\u2297' }, { '\u2232' },
+            { '\u201d' }, { '\u2019' }, { '\u2237' }, { '\u2a74' },
+            { '\u2261' }, { '\u222f' }, { '\u222e' }, { '\u2102' },
+            { '\u2210' }, { '\u2233' }, { '\u2a2f' }, { '\ud835', '\udc9e' },
+            { '\u22d3' }, { '\u224d' }, { '\u2145' }, { '\u2911' },
+            { '\u0402' }, { '\u0405' }, { '\u040f' }, { '\u2021' },
+            { '\u21a1' }, { '\u2ae4' }, { '\u010e' }, { '\u0414' },
+            { '\u2207' }, { '\u0394' }, { '\ud835', '\udd07' }, { '\u00b4' },
+            { '\u02d9' }, { '\u02dd' }, { '\u0060' }, { '\u02dc' },
+            { '\u22c4' }, { '\u2146' }, { '\ud835', '\udd3b' }, { '\u00a8' },
+            { '\u20dc' }, { '\u2250' }, { '\u222f' }, { '\u00a8' },
+            { '\u21d3' }, { '\u21d0' }, { '\u21d4' }, { '\u2ae4' },
+            { '\u27f8' }, { '\u27fa' }, { '\u27f9' }, { '\u21d2' },
+            { '\u22a8' }, { '\u21d1' }, { '\u21d5' }, { '\u2225' },
+            { '\u2193' }, { '\u2913' }, { '\u21f5' }, { '\u0311' },
+            { '\u2950' }, { '\u295e' }, { '\u21bd' }, { '\u2956' },
+            { '\u295f' }, { '\u21c1' }, { '\u2957' }, { '\u22a4' },
+            { '\u21a7' }, { '\u21d3' }, { '\ud835', '\udc9f' }, { '\u0110' },
+            { '\u014a' }, { '\u00d0' }, { '\u00d0' }, { '\u00c9' },
+            { '\u00c9' }, { '\u011a' }, { '\u00ca' }, { '\u00ca' },
+            { '\u042d' }, { '\u0116' }, { '\ud835', '\udd08' }, { '\u00c8' },
+            { '\u00c8' }, { '\u2208' }, { '\u0112' }, { '\u25fb' },
+            { '\u25ab' }, { '\u0118' }, { '\ud835', '\udd3c' }, { '\u0395' },
+            { '\u2a75' }, { '\u2242' }, { '\u21cc' }, { '\u2130' },
+            { '\u2a73' }, { '\u0397' }, { '\u00cb' }, { '\u00cb' },
+            { '\u2203' }, { '\u2147' }, { '\u0424' }, { '\ud835', '\udd09' },
+            { '\u25fc' }, { '\u25aa' }, { '\ud835', '\udd3d' }, { '\u2200' },
+            { '\u2131' }, { '\u2131' }, { '\u0403' }, { '\u003e' },
+            { '\u003e' }, { '\u0393' }, { '\u03dc' }, { '\u011e' },
+            { '\u0122' }, { '\u011c' }, { '\u0413' }, { '\u0120' },
+            { '\ud835', '\udd0a' }, { '\u22d9' }, { '\ud835', '\udd3e' },
+            { '\u2265' }, { '\u22db' }, { '\u2267' }, { '\u2aa2' },
+            { '\u2277' }, { '\u2a7e' }, { '\u2273' }, { '\ud835', '\udca2' },
+            { '\u226b' }, { '\u042a' }, { '\u02c7' }, { '\u005e' },
+            { '\u0124' }, { '\u210c' }, { '\u210b' }, { '\u210d' },
+            { '\u2500' }, { '\u210b' }, { '\u0126' }, { '\u224e' },
+            { '\u224f' }, { '\u0415' }, { '\u0132' }, { '\u0401' },
+            { '\u00cd' }, { '\u00cd' }, { '\u00ce' }, { '\u00ce' },
+            { '\u0418' }, { '\u0130' }, { '\u2111' }, { '\u00cc' },
+            { '\u00cc' }, { '\u2111' }, { '\u012a' }, { '\u2148' },
+            { '\u21d2' }, { '\u222c' }, { '\u222b' }, { '\u22c2' },
+            { '\u2063' }, { '\u2062' }, { '\u012e' }, { '\ud835', '\udd40' },
+            { '\u0399' }, { '\u2110' }, { '\u0128' }, { '\u0406' },
+            { '\u00cf' }, { '\u00cf' }, { '\u0134' }, { '\u0419' },
+            { '\ud835', '\udd0d' }, { '\ud835', '\udd41' },
+            { '\ud835', '\udca5' }, { '\u0408' }, { '\u0404' }, { '\u0425' },
+            { '\u040c' }, { '\u039a' }, { '\u0136' }, { '\u041a' },
+            { '\ud835', '\udd0e' }, { '\ud835', '\udd42' },
+            { '\ud835', '\udca6' }, { '\u0409' }, { '\u003c' }, { '\u003c' },
+            { '\u0139' }, { '\u039b' }, { '\u27ea' }, { '\u2112' },
+            { '\u219e' }, { '\u013d' }, { '\u013b' }, { '\u041b' },
+            { '\u27e8' }, { '\u2190' }, { '\u21e4' }, { '\u21c6' },
+            { '\u2308' }, { '\u27e6' }, { '\u2961' }, { '\u21c3' },
+            { '\u2959' }, { '\u230a' }, { '\u2194' }, { '\u294e' },
+            { '\u22a3' }, { '\u21a4' }, { '\u295a' }, { '\u22b2' },
+            { '\u29cf' }, { '\u22b4' }, { '\u2951' }, { '\u2960' },
+            { '\u21bf' }, { '\u2958' }, { '\u21bc' }, { '\u2952' },
+            { '\u21d0' }, { '\u21d4' }, { '\u22da' }, { '\u2266' },
+            { '\u2276' }, { '\u2aa1' }, { '\u2a7d' }, { '\u2272' },
+            { '\ud835', '\udd0f' }, { '\u22d8' }, { '\u21da' }, { '\u013f' },
+            { '\u27f5' }, { '\u27f7' }, { '\u27f6' }, { '\u27f8' },
+            { '\u27fa' }, { '\u27f9' }, { '\ud835', '\udd43' }, { '\u2199' },
+            { '\u2198' }, { '\u2112' }, { '\u21b0' }, { '\u0141' },
+            { '\u226a' }, { '\u2905' }, { '\u041c' }, { '\u205f' },
+            { '\u2133' }, { '\ud835', '\udd10' }, { '\u2213' },
+            { '\ud835', '\udd44' }, { '\u2133' }, { '\u039c' }, { '\u040a' },
+            { '\u0143' }, { '\u0147' }, { '\u0145' }, { '\u041d' },
+            { '\u200b' }, { '\u200b' }, { '\u200b' }, { '\u200b' },
+            { '\u226b' }, { '\u226a' }, { '\n' }, { '\ud835', '\udd11' },
+            { '\u2060' }, { '\u00a0' }, { '\u2115' }, { '\u2aec' },
+            { '\u2262' }, { '\u226d' }, { '\u2226' }, { '\u2209' },
+            { '\u2260' }, { '\u2242', '\u0338' }, { '\u2204' }, { '\u226f' },
+            { '\u2271' }, { '\u2267', '\u0338' }, { '\u226b', '\u0338' },
+            { '\u2279' }, { '\u2a7e', '\u0338' }, { '\u2275' },
+            { '\u224e', '\u0338' }, { '\u224f', '\u0338' }, { '\u22ea' },
+            { '\u29cf', '\u0338' }, { '\u22ec' }, { '\u226e' }, { '\u2270' },
+            { '\u2278' }, { '\u226a', '\u0338' }, { '\u2a7d', '\u0338' },
+            { '\u2274' }, { '\u2aa2', '\u0338' }, { '\u2aa1', '\u0338' },
+            { '\u2280' }, { '\u2aaf', '\u0338' }, { '\u22e0' }, { '\u220c' },
+            { '\u22eb' }, { '\u29d0', '\u0338' }, { '\u22ed' },
+            { '\u228f', '\u0338' }, { '\u22e2' }, { '\u2290', '\u0338' },
+            { '\u22e3' }, { '\u2282', '\u20d2' }, { '\u2288' }, { '\u2281' },
+            { '\u2ab0', '\u0338' }, { '\u22e1' }, { '\u227f', '\u0338' },
+            { '\u2283', '\u20d2' }, { '\u2289' }, { '\u2241' }, { '\u2244' },
+            { '\u2247' }, { '\u2249' }, { '\u2224' }, { '\ud835', '\udca9' },
+            { '\u00d1' }, { '\u00d1' }, { '\u039d' }, { '\u0152' },
+            { '\u00d3' }, { '\u00d3' }, { '\u00d4' }, { '\u00d4' },
+            { '\u041e' }, { '\u0150' }, { '\ud835', '\udd12' }, { '\u00d2' },
+            { '\u00d2' }, { '\u014c' }, { '\u03a9' }, { '\u039f' },
+            { '\ud835', '\udd46' }, { '\u201c' }, { '\u2018' }, { '\u2a54' },
+            { '\ud835', '\udcaa' }, { '\u00d8' }, { '\u00d8' }, { '\u00d5' },
+            { '\u00d5' }, { '\u2a37' }, { '\u00d6' }, { '\u00d6' },
+            { '\u203e' }, { '\u23de' }, { '\u23b4' }, { '\u23dc' },
+            { '\u2202' }, { '\u041f' }, { '\ud835', '\udd13' }, { '\u03a6' },
+            { '\u03a0' }, { '\u00b1' }, { '\u210c' }, { '\u2119' },
+            { '\u2abb' }, { '\u227a' }, { '\u2aaf' }, { '\u227c' },
+            { '\u227e' }, { '\u2033' }, { '\u220f' }, { '\u2237' },
+            { '\u221d' }, { '\ud835', '\udcab' }, { '\u03a8' }, { '\u0022' },
+            { '\u0022' }, { '\ud835', '\udd14' }, { '\u211a' },
+            { '\ud835', '\udcac' }, { '\u2910' }, { '\u00ae' }, { '\u00ae' },
+            { '\u0154' }, { '\u27eb' }, { '\u21a0' }, { '\u2916' },
+            { '\u0158' }, { '\u0156' }, { '\u0420' }, { '\u211c' },
+            { '\u220b' }, { '\u21cb' }, { '\u296f' }, { '\u211c' },
+            { '\u03a1' }, { '\u27e9' }, { '\u2192' }, { '\u21e5' },
+            { '\u21c4' }, { '\u2309' }, { '\u27e7' }, { '\u295d' },
+            { '\u21c2' }, { '\u2955' }, { '\u230b' }, { '\u22a2' },
+            { '\u21a6' }, { '\u295b' }, { '\u22b3' }, { '\u29d0' },
+            { '\u22b5' }, { '\u294f' }, { '\u295c' }, { '\u21be' },
+            { '\u2954' }, { '\u21c0' }, { '\u2953' }, { '\u21d2' },
+            { '\u211d' }, { '\u2970' }, { '\u21db' }, { '\u211b' },
+            { '\u21b1' }, { '\u29f4' }, { '\u0429' }, { '\u0428' },
+            { '\u042c' }, { '\u015a' }, { '\u2abc' }, { '\u0160' },
+            { '\u015e' }, { '\u015c' }, { '\u0421' }, { '\ud835', '\udd16' },
+            { '\u2193' }, { '\u2190' }, { '\u2192' }, { '\u2191' },
+            { '\u03a3' }, { '\u2218' }, { '\ud835', '\udd4a' }, { '\u221a' },
+            { '\u25a1' }, { '\u2293' }, { '\u228f' }, { '\u2291' },
+            { '\u2290' }, { '\u2292' }, { '\u2294' }, { '\ud835', '\udcae' },
+            { '\u22c6' }, { '\u22d0' }, { '\u22d0' }, { '\u2286' },
+            { '\u227b' }, { '\u2ab0' }, { '\u227d' }, { '\u227f' },
+            { '\u220b' }, { '\u2211' }, { '\u22d1' }, { '\u2283' },
+            { '\u2287' }, { '\u22d1' }, { '\u00de' }, { '\u00de' },
+            { '\u2122' }, { '\u040b' }, { '\u0426' }, { '\u0009' },
+            { '\u03a4' }, { '\u0164' }, { '\u0162' }, { '\u0422' },
+            { '\ud835', '\udd17' }, { '\u2234' }, { '\u0398' },
+            { '\u205f', '\u200a' }, { '\u2009' }, { '\u223c' }, { '\u2243' },
+            { '\u2245' }, { '\u2248' }, { '\ud835', '\udd4b' }, { '\u20db' },
+            { '\ud835', '\udcaf' }, { '\u0166' }, { '\u00da' }, { '\u00da' },
+            { '\u219f' }, { '\u2949' }, { '\u040e' }, { '\u016c' },
+            { '\u00db' }, { '\u00db' }, { '\u0423' }, { '\u0170' },
+            { '\ud835', '\udd18' }, { '\u00d9' }, { '\u00d9' }, { '\u016a' },
+            { '\u005f' }, { '\u23df' }, { '\u23b5' }, { '\u23dd' },
+            { '\u22c3' }, { '\u228e' }, { '\u0172' }, { '\ud835', '\udd4c' },
+            { '\u2191' }, { '\u2912' }, { '\u21c5' }, { '\u2195' },
+            { '\u296e' }, { '\u22a5' }, { '\u21a5' }, { '\u21d1' },
+            { '\u21d5' }, { '\u2196' }, { '\u2197' }, { '\u03d2' },
+            { '\u03a5' }, { '\u016e' }, { '\ud835', '\udcb0' }, { '\u0168' },
+            { '\u00dc' }, { '\u00dc' }, { '\u22ab' }, { '\u2aeb' },
+            { '\u0412' }, { '\u22a9' }, { '\u2ae6' }, { '\u22c1' },
+            { '\u2016' }, { '\u2016' }, { '\u2223' }, { '\u007c' },
+            { '\u2758' }, { '\u2240' }, { '\u200a' }, { '\ud835', '\udd19' },
+            { '\ud835', '\udd4d' }, { '\ud835', '\udcb1' }, { '\u22aa' },
+            { '\u0174' }, { '\u22c0' }, { '\ud835', '\udd1a' },
+            { '\ud835', '\udd4e' }, { '\ud835', '\udcb2' },
+            { '\ud835', '\udd1b' }, { '\u039e' }, { '\ud835', '\udd4f' },
+            { '\ud835', '\udcb3' }, { '\u042f' }, { '\u0407' }, { '\u042e' },
+            { '\u00dd' }, { '\u00dd' }, { '\u0176' }, { '\u042b' },
+            { '\ud835', '\udd1c' }, { '\ud835', '\udd50' },
+            { '\ud835', '\udcb4' }, { '\u0178' }, { '\u0416' }, { '\u0179' },
+            { '\u017d' }, { '\u0417' }, { '\u017b' }, { '\u200b' },
+            { '\u0396' }, { '\u2128' }, { '\u2124' }, { '\ud835', '\udcb5' },
+            { '\u00e1' }, { '\u00e1' }, { '\u0103' }, { '\u223e' },
+            { '\u223e', '\u0333' }, { '\u223f' }, { '\u00e2' }, { '\u00e2' },
+            { '\u00b4' }, { '\u00b4' }, { '\u0430' }, { '\u00e6' },
+            { '\u00e6' }, { '\u2061' }, { '\ud835', '\udd1e' }, { '\u00e0' },
+            { '\u00e0' }, { '\u2135' }, { '\u2135' }, { '\u03b1' },
+            { '\u0101' }, { '\u2a3f' }, { '\u0026' }, { '\u0026' },
+            { '\u2227' }, { '\u2a55' }, { '\u2a5c' }, { '\u2a58' },
+            { '\u2a5a' }, { '\u2220' }, { '\u29a4' }, { '\u2220' },
+            { '\u2221' }, { '\u29a8' }, { '\u29a9' }, { '\u29aa' },
+            { '\u29ab' }, { '\u29ac' }, { '\u29ad' }, { '\u29ae' },
+            { '\u29af' }, { '\u221f' }, { '\u22be' }, { '\u299d' },
+            { '\u2222' }, { '\u00c5' }, { '\u237c' }, { '\u0105' },
+            { '\ud835', '\udd52' }, { '\u2248' }, { '\u2a70' }, { '\u2a6f' },
+            { '\u224a' }, { '\u224b' }, { '\'' }, { '\u2248' }, { '\u224a' },
+            { '\u00e5' }, { '\u00e5' }, { '\ud835', '\udcb6' }, { '\u002a' },
+            { '\u2248' }, { '\u224d' }, { '\u00e3' }, { '\u00e3' },
+            { '\u00e4' }, { '\u00e4' }, { '\u2233' }, { '\u2a11' },
+            { '\u2aed' }, { '\u224c' }, { '\u03f6' }, { '\u2035' },
+            { '\u223d' }, { '\u22cd' }, { '\u22bd' }, { '\u2305' },
+            { '\u2305' }, { '\u23b5' }, { '\u23b6' }, { '\u224c' },
+            { '\u0431' }, { '\u201e' }, { '\u2235' }, { '\u2235' },
+            { '\u29b0' }, { '\u03f6' }, { '\u212c' }, { '\u03b2' },
+            { '\u2136' }, { '\u226c' }, { '\ud835', '\udd1f' }, { '\u22c2' },
+            { '\u25ef' }, { '\u22c3' }, { '\u2a00' }, { '\u2a01' },
+            { '\u2a02' }, { '\u2a06' }, { '\u2605' }, { '\u25bd' },
+            { '\u25b3' }, { '\u2a04' }, { '\u22c1' }, { '\u22c0' },
+            { '\u290d' }, { '\u29eb' }, { '\u25aa' }, { '\u25b4' },
+            { '\u25be' }, { '\u25c2' }, { '\u25b8' }, { '\u2423' },
+            { '\u2592' }, { '\u2591' }, { '\u2593' }, { '\u2588' },
+            { '\u003d', '\u20e5' }, { '\u2261', '\u20e5' }, { '\u2310' },
+            { '\ud835', '\udd53' }, { '\u22a5' }, { '\u22a5' }, { '\u22c8' },
+            { '\u2557' }, { '\u2554' }, { '\u2556' }, { '\u2553' },
+            { '\u2550' }, { '\u2566' }, { '\u2569' }, { '\u2564' },
+            { '\u2567' }, { '\u255d' }, { '\u255a' }, { '\u255c' },
+            { '\u2559' }, { '\u2551' }, { '\u256c' }, { '\u2563' },
+            { '\u2560' }, { '\u256b' }, { '\u2562' }, { '\u255f' },
+            { '\u29c9' }, { '\u2555' }, { '\u2552' }, { '\u2510' },
+            { '\u250c' }, { '\u2500' }, { '\u2565' }, { '\u2568' },
+            { '\u252c' }, { '\u2534' }, { '\u229f' }, { '\u229e' },
+            { '\u22a0' }, { '\u255b' }, { '\u2558' }, { '\u2518' },
+            { '\u2514' }, { '\u2502' }, { '\u256a' }, { '\u2561' },
+            { '\u255e' }, { '\u253c' }, { '\u2524' }, { '\u251c' },
+            { '\u2035' }, { '\u02d8' }, { '\u00a6' }, { '\u00a6' },
+            { '\ud835', '\udcb7' }, { '\u204f' }, { '\u223d' }, { '\u22cd' },
+            { '\\' }, { '\u29c5' }, { '\u27c8' }, { '\u2022' }, { '\u2022' },
+            { '\u224e' }, { '\u2aae' }, { '\u224f' }, { '\u224f' },
+            { '\u0107' }, { '\u2229' }, { '\u2a44' }, { '\u2a49' },
+            { '\u2a4b' }, { '\u2a47' }, { '\u2a40' }, { '\u2229', '\ufe00' },
+            { '\u2041' }, { '\u02c7' }, { '\u2a4d' }, { '\u010d' },
+            { '\u00e7' }, { '\u00e7' }, { '\u0109' }, { '\u2a4c' },
+            { '\u2a50' }, { '\u010b' }, { '\u00b8' }, { '\u00b8' },
+            { '\u29b2' }, { '\u00a2' }, { '\u00a2' }, { '\u00b7' },
+            { '\ud835', '\udd20' }, { '\u0447' }, { '\u2713' }, { '\u2713' },
+            { '\u03c7' }, { '\u25cb' }, { '\u29c3' }, { '\u02c6' },
+            { '\u2257' }, { '\u21ba' }, { '\u21bb' }, { '\u00ae' },
+            { '\u24c8' }, { '\u229b' }, { '\u229a' }, { '\u229d' },
+            { '\u2257' }, { '\u2a10' }, { '\u2aef' }, { '\u29c2' },
+            { '\u2663' }, { '\u2663' }, { '\u003a' }, { '\u2254' },
+            { '\u2254' }, { '\u002c' }, { '\u0040' }, { '\u2201' },
+            { '\u2218' }, { '\u2201' }, { '\u2102' }, { '\u2245' },
+            { '\u2a6d' }, { '\u222e' }, { '\ud835', '\udd54' }, { '\u2210' },
+            { '\u00a9' }, { '\u00a9' }, { '\u2117' }, { '\u21b5' },
+            { '\u2717' }, { '\ud835', '\udcb8' }, { '\u2acf' }, { '\u2ad1' },
+            { '\u2ad0' }, { '\u2ad2' }, { '\u22ef' }, { '\u2938' },
+            { '\u2935' }, { '\u22de' }, { '\u22df' }, { '\u21b6' },
+            { '\u293d' }, { '\u222a' }, { '\u2a48' }, { '\u2a46' },
+            { '\u2a4a' }, { '\u228d' }, { '\u2a45' }, { '\u222a', '\ufe00' },
+            { '\u21b7' }, { '\u293c' }, { '\u22de' }, { '\u22df' },
+            { '\u22ce' }, { '\u22cf' }, { '\u00a4' }, { '\u00a4' },
+            { '\u21b6' }, { '\u21b7' }, { '\u22ce' }, { '\u22cf' },
+            { '\u2232' }, { '\u2231' }, { '\u232d' }, { '\u21d3' },
+            { '\u2965' }, { '\u2020' }, { '\u2138' }, { '\u2193' },
+            { '\u2010' }, { '\u22a3' }, { '\u290f' }, { '\u02dd' },
+            { '\u010f' }, { '\u0434' }, { '\u2146' }, { '\u2021' },
+            { '\u21ca' }, { '\u2a77' }, { '\u00b0' }, { '\u00b0' },
+            { '\u03b4' }, { '\u29b1' }, { '\u297f' }, { '\ud835', '\udd21' },
+            { '\u21c3' }, { '\u21c2' }, { '\u22c4' }, { '\u22c4' },
+            { '\u2666' }, { '\u2666' }, { '\u00a8' }, { '\u03dd' },
+            { '\u22f2' }, { '\u00f7' }, { '\u00f7' }, { '\u00f7' },
+            { '\u22c7' }, { '\u22c7' }, { '\u0452' }, { '\u231e' },
+            { '\u230d' }, { '\u0024' }, { '\ud835', '\udd55' }, { '\u02d9' },
+            { '\u2250' }, { '\u2251' }, { '\u2238' }, { '\u2214' },
+            { '\u22a1' }, { '\u2306' }, { '\u2193' }, { '\u21ca' },
+            { '\u21c3' }, { '\u21c2' }, { '\u2910' }, { '\u231f' },
+            { '\u230c' }, { '\ud835', '\udcb9' }, { '\u0455' }, { '\u29f6' },
+            { '\u0111' }, { '\u22f1' }, { '\u25bf' }, { '\u25be' },
+            { '\u21f5' }, { '\u296f' }, { '\u29a6' }, { '\u045f' },
+            { '\u27ff' }, { '\u2a77' }, { '\u2251' }, { '\u00e9' },
+            { '\u00e9' }, { '\u2a6e' }, { '\u011b' }, { '\u2256' },
+            { '\u00ea' }, { '\u00ea' }, { '\u2255' }, { '\u044d' },
+            { '\u0117' }, { '\u2147' }, { '\u2252' }, { '\ud835', '\udd22' },
+            { '\u2a9a' }, { '\u00e8' }, { '\u00e8' }, { '\u2a96' },
+            { '\u2a98' }, { '\u2a99' }, { '\u23e7' }, { '\u2113' },
+            { '\u2a95' }, { '\u2a97' }, { '\u0113' }, { '\u2205' },
+            { '\u2205' }, { '\u2205' }, { '\u2004' }, { '\u2005' },
+            { '\u2003' }, { '\u014b' }, { '\u2002' }, { '\u0119' },
+            { '\ud835', '\udd56' }, { '\u22d5' }, { '\u29e3' }, { '\u2a71' },
+            { '\u03b5' }, { '\u03b5' }, { '\u03f5' }, { '\u2256' },
+            { '\u2255' }, { '\u2242' }, { '\u2a96' }, { '\u2a95' },
+            { '\u003d' }, { '\u225f' }, { '\u2261' }, { '\u2a78' },
+            { '\u29e5' }, { '\u2253' }, { '\u2971' }, { '\u212f' },
+            { '\u2250' }, { '\u2242' }, { '\u03b7' }, { '\u00f0' },
+            { '\u00f0' }, { '\u00eb' }, { '\u00eb' }, { '\u20ac' },
+            { '\u0021' }, { '\u2203' }, { '\u2130' }, { '\u2147' },
+            { '\u2252' }, { '\u0444' }, { '\u2640' }, { '\ufb03' },
+            { '\ufb00' }, { '\ufb04' }, { '\ud835', '\udd23' }, { '\ufb01' },
+            { '\u0066', '\u006a' }, { '\u266d' }, { '\ufb02' }, { '\u25b1' },
+            { '\u0192' }, { '\ud835', '\udd57' }, { '\u2200' }, { '\u22d4' },
+            { '\u2ad9' }, { '\u2a0d' }, { '\u00bd' }, { '\u00bd' },
+            { '\u2153' }, { '\u00bc' }, { '\u00bc' }, { '\u2155' },
+            { '\u2159' }, { '\u215b' }, { '\u2154' }, { '\u2156' },
+            { '\u00be' }, { '\u00be' }, { '\u2157' }, { '\u215c' },
+            { '\u2158' }, { '\u215a' }, { '\u215d' }, { '\u215e' },
+            { '\u2044' }, { '\u2322' }, { '\ud835', '\udcbb' }, { '\u2267' },
+            { '\u2a8c' }, { '\u01f5' }, { '\u03b3' }, { '\u03dd' },
+            { '\u2a86' }, { '\u011f' }, { '\u011d' }, { '\u0433' },
+            { '\u0121' }, { '\u2265' }, { '\u22db' }, { '\u2265' },
+            { '\u2267' }, { '\u2a7e' }, { '\u2a7e' }, { '\u2aa9' },
+            { '\u2a80' }, { '\u2a82' }, { '\u2a84' }, { '\u22db', '\ufe00' },
+            { '\u2a94' }, { '\ud835', '\udd24' }, { '\u226b' }, { '\u22d9' },
+            { '\u2137' }, { '\u0453' }, { '\u2277' }, { '\u2a92' },
+            { '\u2aa5' }, { '\u2aa4' }, { '\u2269' }, { '\u2a8a' },
+            { '\u2a8a' }, { '\u2a88' }, { '\u2a88' }, { '\u2269' },
+            { '\u22e7' }, { '\ud835', '\udd58' }, { '\u0060' }, { '\u210a' },
+            { '\u2273' }, { '\u2a8e' }, { '\u2a90' }, { '\u003e' },
+            { '\u003e' }, { '\u2aa7' }, { '\u2a7a' }, { '\u22d7' },
+            { '\u2995' }, { '\u2a7c' }, { '\u2a86' }, { '\u2978' },
+            { '\u22d7' }, { '\u22db' }, { '\u2a8c' }, { '\u2277' },
+            { '\u2273' }, { '\u2269', '\ufe00' }, { '\u2269', '\ufe00' },
+            { '\u21d4' }, { '\u200a' }, { '\u00bd' }, { '\u210b' },
+            { '\u044a' }, { '\u2194' }, { '\u2948' }, { '\u21ad' },
+            { '\u210f' }, { '\u0125' }, { '\u2665' }, { '\u2665' },
+            { '\u2026' }, { '\u22b9' }, { '\ud835', '\udd25' }, { '\u2925' },
+            { '\u2926' }, { '\u21ff' }, { '\u223b' }, { '\u21a9' },
+            { '\u21aa' }, { '\ud835', '\udd59' }, { '\u2015' },
+            { '\ud835', '\udcbd' }, { '\u210f' }, { '\u0127' }, { '\u2043' },
+            { '\u2010' }, { '\u00ed' }, { '\u00ed' }, { '\u2063' },
+            { '\u00ee' }, { '\u00ee' }, { '\u0438' }, { '\u0435' },
+            { '\u00a1' }, { '\u00a1' }, { '\u21d4' }, { '\ud835', '\udd26' },
+            { '\u00ec' }, { '\u00ec' }, { '\u2148' }, { '\u2a0c' },
+            { '\u222d' }, { '\u29dc' }, { '\u2129' }, { '\u0133' },
+            { '\u012b' }, { '\u2111' }, { '\u2110' }, { '\u2111' },
+            { '\u0131' }, { '\u22b7' }, { '\u01b5' }, { '\u2208' },
+            { '\u2105' }, { '\u221e' }, { '\u29dd' }, { '\u0131' },
+            { '\u222b' }, { '\u22ba' }, { '\u2124' }, { '\u22ba' },
+            { '\u2a17' }, { '\u2a3c' }, { '\u0451' }, { '\u012f' },
+            { '\ud835', '\udd5a' }, { '\u03b9' }, { '\u2a3c' }, { '\u00bf' },
+            { '\u00bf' }, { '\ud835', '\udcbe' }, { '\u2208' }, { '\u22f9' },
+            { '\u22f5' }, { '\u22f4' }, { '\u22f3' }, { '\u2208' },
+            { '\u2062' }, { '\u0129' }, { '\u0456' }, { '\u00ef' },
+            { '\u00ef' }, { '\u0135' }, { '\u0439' }, { '\ud835', '\udd27' },
+            { '\u0237' }, { '\ud835', '\udd5b' }, { '\ud835', '\udcbf' },
+            { '\u0458' }, { '\u0454' }, { '\u03ba' }, { '\u03f0' },
+            { '\u0137' }, { '\u043a' }, { '\ud835', '\udd28' }, { '\u0138' },
+            { '\u0445' }, { '\u045c' }, { '\ud835', '\udd5c' },
+            { '\ud835', '\udcc0' }, { '\u21da' }, { '\u21d0' }, { '\u291b' },
+            { '\u290e' }, { '\u2266' }, { '\u2a8b' }, { '\u2962' },
+            { '\u013a' }, { '\u29b4' }, { '\u2112' }, { '\u03bb' },
+            { '\u27e8' }, { '\u2991' }, { '\u27e8' }, { '\u2a85' },
+            { '\u00ab' }, { '\u00ab' }, { '\u2190' }, { '\u21e4' },
+            { '\u291f' }, { '\u291d' }, { '\u21a9' }, { '\u21ab' },
+            { '\u2939' }, { '\u2973' }, { '\u21a2' }, { '\u2aab' },
+            { '\u2919' }, { '\u2aad' }, { '\u2aad', '\ufe00' }, { '\u290c' },
+            { '\u2772' }, { '\u007b' }, { '\u005b' }, { '\u298b' },
+            { '\u298f' }, { '\u298d' }, { '\u013e' }, { '\u013c' },
+            { '\u2308' }, { '\u007b' }, { '\u043b' }, { '\u2936' },
+            { '\u201c' }, { '\u201e' }, { '\u2967' }, { '\u294b' },
+            { '\u21b2' }, { '\u2264' }, { '\u2190' }, { '\u21a2' },
+            { '\u21bd' }, { '\u21bc' }, { '\u21c7' }, { '\u2194' },
+            { '\u21c6' }, { '\u21cb' }, { '\u21ad' }, { '\u22cb' },
+            { '\u22da' }, { '\u2264' }, { '\u2266' }, { '\u2a7d' },
+            { '\u2a7d' }, { '\u2aa8' }, { '\u2a7f' }, { '\u2a81' },
+            { '\u2a83' }, { '\u22da', '\ufe00' }, { '\u2a93' }, { '\u2a85' },
+            { '\u22d6' }, { '\u22da' }, { '\u2a8b' }, { '\u2276' },
+            { '\u2272' }, { '\u297c' }, { '\u230a' }, { '\ud835', '\udd29' },
+            { '\u2276' }, { '\u2a91' }, { '\u21bd' }, { '\u21bc' },
+            { '\u296a' }, { '\u2584' }, { '\u0459' }, { '\u226a' },
+            { '\u21c7' }, { '\u231e' }, { '\u296b' }, { '\u25fa' },
+            { '\u0140' }, { '\u23b0' }, { '\u23b0' }, { '\u2268' },
+            { '\u2a89' }, { '\u2a89' }, { '\u2a87' }, { '\u2a87' },
+            { '\u2268' }, { '\u22e6' }, { '\u27ec' }, { '\u21fd' },
+            { '\u27e6' }, { '\u27f5' }, { '\u27f7' }, { '\u27fc' },
+            { '\u27f6' }, { '\u21ab' }, { '\u21ac' }, { '\u2985' },
+            { '\ud835', '\udd5d' }, { '\u2a2d' }, { '\u2a34' }, { '\u2217' },
+            { '\u005f' }, { '\u25ca' }, { '\u25ca' }, { '\u29eb' },
+            { '\u0028' }, { '\u2993' }, { '\u21c6' }, { '\u231f' },
+            { '\u21cb' }, { '\u296d' }, { '\u200e' }, { '\u22bf' },
+            { '\u2039' }, { '\ud835', '\udcc1' }, { '\u21b0' }, { '\u2272' },
+            { '\u2a8d' }, { '\u2a8f' }, { '\u005b' }, { '\u2018' },
+            { '\u201a' }, { '\u0142' }, { '\u003c' }, { '\u003c' },
+            { '\u2aa6' }, { '\u2a79' }, { '\u22d6' }, { '\u22cb' },
+            { '\u22c9' }, { '\u2976' }, { '\u2a7b' }, { '\u2996' },
+            { '\u25c3' }, { '\u22b4' }, { '\u25c2' }, { '\u294a' },
+            { '\u2966' }, { '\u2268', '\ufe00' }, { '\u2268', '\ufe00' },
+            { '\u223a' }, { '\u00af' }, { '\u00af' }, { '\u2642' },
+            { '\u2720' }, { '\u2720' }, { '\u21a6' }, { '\u21a6' },
+            { '\u21a7' }, { '\u21a4' }, { '\u21a5' }, { '\u25ae' },
+            { '\u2a29' }, { '\u043c' }, { '\u2014' }, { '\u2221' },
+            { '\ud835', '\udd2a' }, { '\u2127' }, { '\u00b5' }, { '\u00b5' },
+            { '\u2223' }, { '\u002a' }, { '\u2af0' }, { '\u00b7' },
+            { '\u00b7' }, { '\u2212' }, { '\u229f' }, { '\u2238' },
+            { '\u2a2a' }, { '\u2adb' }, { '\u2026' }, { '\u2213' },
+            { '\u22a7' }, { '\ud835', '\udd5e' }, { '\u2213' },
+            { '\ud835', '\udcc2' }, { '\u223e' }, { '\u03bc' }, { '\u22b8' },
+            { '\u22b8' }, { '\u22d9', '\u0338' }, { '\u226b', '\u20d2' },
+            { '\u226b', '\u0338' }, { '\u21cd' }, { '\u21ce' },
+            { '\u22d8', '\u0338' }, { '\u226a', '\u20d2' },
+            { '\u226a', '\u0338' }, { '\u21cf' }, { '\u22af' }, { '\u22ae' },
+            { '\u2207' }, { '\u0144' }, { '\u2220', '\u20d2' }, { '\u2249' },
+            { '\u2a70', '\u0338' }, { '\u224b', '\u0338' }, { '\u0149' },
+            { '\u2249' }, { '\u266e' }, { '\u266e' }, { '\u2115' },
+            { '\u00a0' }, { '\u00a0' }, { '\u224e', '\u0338' },
+            { '\u224f', '\u0338' }, { '\u2a43' }, { '\u0148' }, { '\u0146' },
+            { '\u2247' }, { '\u2a6d', '\u0338' }, { '\u2a42' }, { '\u043d' },
+            { '\u2013' }, { '\u2260' }, { '\u21d7' }, { '\u2924' },
+            { '\u2197' }, { '\u2197' }, { '\u2250', '\u0338' }, { '\u2262' },
+            { '\u2928' }, { '\u2242', '\u0338' }, { '\u2204' }, { '\u2204' },
+            { '\ud835', '\udd2b' }, { '\u2267', '\u0338' }, { '\u2271' },
+            { '\u2271' }, { '\u2267', '\u0338' }, { '\u2a7e', '\u0338' },
+            { '\u2a7e', '\u0338' }, { '\u2275' }, { '\u226f' }, { '\u226f' },
+            { '\u21ce' }, { '\u21ae' }, { '\u2af2' }, { '\u220b' },
+            { '\u22fc' }, { '\u22fa' }, { '\u220b' }, { '\u045a' },
+            { '\u21cd' }, { '\u2266', '\u0338' }, { '\u219a' }, { '\u2025' },
+            { '\u2270' }, { '\u219a' }, { '\u21ae' }, { '\u2270' },
+            { '\u2266', '\u0338' }, { '\u2a7d', '\u0338' },
+            { '\u2a7d', '\u0338' }, { '\u226e' }, { '\u2274' }, { '\u226e' },
+            { '\u22ea' }, { '\u22ec' }, { '\u2224' }, { '\ud835', '\udd5f' },
+            { '\u00ac' }, { '\u00ac' }, { '\u2209' }, { '\u22f9', '\u0338' },
+            { '\u22f5', '\u0338' }, { '\u2209' }, { '\u22f7' }, { '\u22f6' },
+            { '\u220c' }, { '\u220c' }, { '\u22fe' }, { '\u22fd' },
+            { '\u2226' }, { '\u2226' }, { '\u2afd', '\u20e5' },
+            { '\u2202', '\u0338' }, { '\u2a14' }, { '\u2280' }, { '\u22e0' },
+            { '\u2aaf', '\u0338' }, { '\u2280' }, { '\u2aaf', '\u0338' },
+            { '\u21cf' }, { '\u219b' }, { '\u2933', '\u0338' },
+            { '\u219d', '\u0338' }, { '\u219b' }, { '\u22eb' }, { '\u22ed' },
+            { '\u2281' }, { '\u22e1' }, { '\u2ab0', '\u0338' },
+            { '\ud835', '\udcc3' }, { '\u2224' }, { '\u2226' }, { '\u2241' },
+            { '\u2244' }, { '\u2244' }, { '\u2224' }, { '\u2226' },
+            { '\u22e2' }, { '\u22e3' }, { '\u2284' }, { '\u2ac5', '\u0338' },
+            { '\u2288' }, { '\u2282', '\u20d2' }, { '\u2288' },
+            { '\u2ac5', '\u0338' }, { '\u2281' }, { '\u2ab0', '\u0338' },
+            { '\u2285' }, { '\u2ac6', '\u0338' }, { '\u2289' },
+            { '\u2283', '\u20d2' }, { '\u2289' }, { '\u2ac6', '\u0338' },
+            { '\u2279' }, { '\u00f1' }, { '\u00f1' }, { '\u2278' },
+            { '\u22ea' }, { '\u22ec' }, { '\u22eb' }, { '\u22ed' },
+            { '\u03bd' }, { '\u0023' }, { '\u2116' }, { '\u2007' },
+            { '\u22ad' }, { '\u2904' }, { '\u224d', '\u20d2' }, { '\u22ac' },
+            { '\u2265', '\u20d2' }, { '\u003e', '\u20d2' }, { '\u29de' },
+            { '\u2902' }, { '\u2264', '\u20d2' }, { '\u003c', '\u20d2' },
+            { '\u22b4', '\u20d2' }, { '\u2903' }, { '\u22b5', '\u20d2' },
+            { '\u223c', '\u20d2' }, { '\u21d6' }, { '\u2923' }, { '\u2196' },
+            { '\u2196' }, { '\u2927' }, { '\u24c8' }, { '\u00f3' },
+            { '\u00f3' }, { '\u229b' }, { '\u229a' }, { '\u00f4' },
+            { '\u00f4' }, { '\u043e' }, { '\u229d' }, { '\u0151' },
+            { '\u2a38' }, { '\u2299' }, { '\u29bc' }, { '\u0153' },
+            { '\u29bf' }, { '\ud835', '\udd2c' }, { '\u02db' }, { '\u00f2' },
+            { '\u00f2' }, { '\u29c1' }, { '\u29b5' }, { '\u03a9' },
+            { '\u222e' }, { '\u21ba' }, { '\u29be' }, { '\u29bb' },
+            { '\u203e' }, { '\u29c0' }, { '\u014d' }, { '\u03c9' },
+            { '\u03bf' }, { '\u29b6' }, { '\u2296' }, { '\ud835', '\udd60' },
+            { '\u29b7' }, { '\u29b9' }, { '\u2295' }, { '\u2228' },
+            { '\u21bb' }, { '\u2a5d' }, { '\u2134' }, { '\u2134' },
+            { '\u00aa' }, { '\u00aa' }, { '\u00ba' }, { '\u00ba' },
+            { '\u22b6' }, { '\u2a56' }, { '\u2a57' }, { '\u2a5b' },
+            { '\u2134' }, { '\u00f8' }, { '\u00f8' }, { '\u2298' },
+            { '\u00f5' }, { '\u00f5' }, { '\u2297' }, { '\u2a36' },
+            { '\u00f6' }, { '\u00f6' }, { '\u233d' }, { '\u2225' },
+            { '\u00b6' }, { '\u00b6' }, { '\u2225' }, { '\u2af3' },
+            { '\u2afd' }, { '\u2202' }, { '\u043f' }, { '\u0025' },
+            { '\u002e' }, { '\u2030' }, { '\u22a5' }, { '\u2031' },
+            { '\ud835', '\udd2d' }, { '\u03c6' }, { '\u03d5' }, { '\u2133' },
+            { '\u260e' }, { '\u03c0' }, { '\u22d4' }, { '\u03d6' },
+            { '\u210f' }, { '\u210e' }, { '\u210f' }, { '\u002b' },
+            { '\u2a23' }, { '\u229e' }, { '\u2a22' }, { '\u2214' },
+            { '\u2a25' }, { '\u2a72' }, { '\u00b1' }, { '\u00b1' },
+            { '\u2a26' }, { '\u2a27' }, { '\u00b1' }, { '\u2a15' },
+            { '\ud835', '\udd61' }, { '\u00a3' }, { '\u00a3' }, { '\u227a' },
+            { '\u2ab3' }, { '\u2ab7' }, { '\u227c' }, { '\u2aaf' },
+            { '\u227a' }, { '\u2ab7' }, { '\u227c' }, { '\u2aaf' },
+            { '\u2ab9' }, { '\u2ab5' }, { '\u22e8' }, { '\u227e' },
+            { '\u2032' }, { '\u2119' }, { '\u2ab5' }, { '\u2ab9' },
+            { '\u22e8' }, { '\u220f' }, { '\u232e' }, { '\u2312' },
+            { '\u2313' }, { '\u221d' }, { '\u221d' }, { '\u227e' },
+            { '\u22b0' }, { '\ud835', '\udcc5' }, { '\u03c8' }, { '\u2008' },
+            { '\ud835', '\udd2e' }, { '\u2a0c' }, { '\ud835', '\udd62' },
+            { '\u2057' }, { '\ud835', '\udcc6' }, { '\u210d' }, { '\u2a16' },
+            { '\u003f' }, { '\u225f' }, { '\u0022' }, { '\u0022' },
+            { '\u21db' }, { '\u21d2' }, { '\u291c' }, { '\u290f' },
+            { '\u2964' }, { '\u223d', '\u0331' }, { '\u0155' }, { '\u221a' },
+            { '\u29b3' }, { '\u27e9' }, { '\u2992' }, { '\u29a5' },
+            { '\u27e9' }, { '\u00bb' }, { '\u00bb' }, { '\u2192' },
+            { '\u2975' }, { '\u21e5' }, { '\u2920' }, { '\u2933' },
+            { '\u291e' }, { '\u21aa' }, { '\u21ac' }, { '\u2945' },
+            { '\u2974' }, { '\u21a3' }, { '\u219d' }, { '\u291a' },
+            { '\u2236' }, { '\u211a' }, { '\u290d' }, { '\u2773' },
+            { '\u007d' }, { '\u005d' }, { '\u298c' }, { '\u298e' },
+            { '\u2990' }, { '\u0159' }, { '\u0157' }, { '\u2309' },
+            { '\u007d' }, { '\u0440' }, { '\u2937' }, { '\u2969' },
+            { '\u201d' }, { '\u201d' }, { '\u21b3' }, { '\u211c' },
+            { '\u211b' }, { '\u211c' }, { '\u211d' }, { '\u25ad' },
+            { '\u00ae' }, { '\u00ae' }, { '\u297d' }, { '\u230b' },
+            { '\ud835', '\udd2f' }, { '\u21c1' }, { '\u21c0' }, { '\u296c' },
+            { '\u03c1' }, { '\u03f1' }, { '\u2192' }, { '\u21a3' },
+            { '\u21c1' }, { '\u21c0' }, { '\u21c4' }, { '\u21cc' },
+            { '\u21c9' }, { '\u219d' }, { '\u22cc' }, { '\u02da' },
+            { '\u2253' }, { '\u21c4' }, { '\u21cc' }, { '\u200f' },
+            { '\u23b1' }, { '\u23b1' }, { '\u2aee' }, { '\u27ed' },
+            { '\u21fe' }, { '\u27e7' }, { '\u2986' }, { '\ud835', '\udd63' },
+            { '\u2a2e' }, { '\u2a35' }, { '\u0029' }, { '\u2994' },
+            { '\u2a12' }, { '\u21c9' }, { '\u203a' }, { '\ud835', '\udcc7' },
+            { '\u21b1' }, { '\u005d' }, { '\u2019' }, { '\u2019' },
+            { '\u22cc' }, { '\u22ca' }, { '\u25b9' }, { '\u22b5' },
+            { '\u25b8' }, { '\u29ce' }, { '\u2968' }, { '\u211e' },
+            { '\u015b' }, { '\u201a' }, { '\u227b' }, { '\u2ab4' },
+            { '\u2ab8' }, { '\u0161' }, { '\u227d' }, { '\u2ab0' },
+            { '\u015f' }, { '\u015d' }, { '\u2ab6' }, { '\u2aba' },
+            { '\u22e9' }, { '\u2a13' }, { '\u227f' }, { '\u0441' },
+            { '\u22c5' }, { '\u22a1' }, { '\u2a66' }, { '\u21d8' },
+            { '\u2925' }, { '\u2198' }, { '\u2198' }, { '\u00a7' },
+            { '\u00a7' }, { '\u003b' }, { '\u2929' }, { '\u2216' },
+            { '\u2216' }, { '\u2736' }, { '\ud835', '\udd30' }, { '\u2322' },
+            { '\u266f' }, { '\u0449' }, { '\u0448' }, { '\u2223' },
+            { '\u2225' }, { '\u00ad' }, { '\u00ad' }, { '\u03c3' },
+            { '\u03c2' }, { '\u03c2' }, { '\u223c' }, { '\u2a6a' },
+            { '\u2243' }, { '\u2243' }, { '\u2a9e' }, { '\u2aa0' },
+            { '\u2a9d' }, { '\u2a9f' }, { '\u2246' }, { '\u2a24' },
+            { '\u2972' }, { '\u2190' }, { '\u2216' }, { '\u2a33' },
+            { '\u29e4' }, { '\u2223' }, { '\u2323' }, { '\u2aaa' },
+            { '\u2aac' }, { '\u2aac', '\ufe00' }, { '\u044c' }, { '\u002f' },
+            { '\u29c4' }, { '\u233f' }, { '\ud835', '\udd64' }, { '\u2660' },
+            { '\u2660' }, { '\u2225' }, { '\u2293' }, { '\u2293', '\ufe00' },
+            { '\u2294' }, { '\u2294', '\ufe00' }, { '\u228f' }, { '\u2291' },
+            { '\u228f' }, { '\u2291' }, { '\u2290' }, { '\u2292' },
+            { '\u2290' }, { '\u2292' }, { '\u25a1' }, { '\u25a1' },
+            { '\u25aa' }, { '\u25aa' }, { '\u2192' }, { '\ud835', '\udcc8' },
+            { '\u2216' }, { '\u2323' }, { '\u22c6' }, { '\u2606' },
+            { '\u2605' }, { '\u03f5' }, { '\u03d5' }, { '\u00af' },
+            { '\u2282' }, { '\u2ac5' }, { '\u2abd' }, { '\u2286' },
+            { '\u2ac3' }, { '\u2ac1' }, { '\u2acb' }, { '\u228a' },
+            { '\u2abf' }, { '\u2979' }, { '\u2282' }, { '\u2286' },
+            { '\u2ac5' }, { '\u228a' }, { '\u2acb' }, { '\u2ac7' },
+            { '\u2ad5' }, { '\u2ad3' }, { '\u227b' }, { '\u2ab8' },
+            { '\u227d' }, { '\u2ab0' }, { '\u2aba' }, { '\u2ab6' },
+            { '\u22e9' }, { '\u227f' }, { '\u2211' }, { '\u266a' },
+            { '\u00b9' }, { '\u00b9' }, { '\u00b2' }, { '\u00b2' },
+            { '\u00b3' }, { '\u00b3' }, { '\u2283' }, { '\u2ac6' },
+            { '\u2abe' }, { '\u2ad8' }, { '\u2287' }, { '\u2ac4' },
+            { '\u27c9' }, { '\u2ad7' }, { '\u297b' }, { '\u2ac2' },
+            { '\u2acc' }, { '\u228b' }, { '\u2ac0' }, { '\u2283' },
+            { '\u2287' }, { '\u2ac6' }, { '\u228b' }, { '\u2acc' },
+            { '\u2ac8' }, { '\u2ad4' }, { '\u2ad6' }, { '\u21d9' },
+            { '\u2926' }, { '\u2199' }, { '\u2199' }, { '\u292a' },
+            { '\u00df' }, { '\u00df' }, { '\u2316' }, { '\u03c4' },
+            { '\u23b4' }, { '\u0165' }, { '\u0163' }, { '\u0442' },
+            { '\u20db' }, { '\u2315' }, { '\ud835', '\udd31' }, { '\u2234' },
+            { '\u2234' }, { '\u03b8' }, { '\u03d1' }, { '\u03d1' },
+            { '\u2248' }, { '\u223c' }, { '\u2009' }, { '\u2248' },
+            { '\u223c' }, { '\u00fe' }, { '\u00fe' }, { '\u02dc' },
+            { '\u00d7' }, { '\u00d7' }, { '\u22a0' }, { '\u2a31' },
+            { '\u2a30' }, { '\u222d' }, { '\u2928' }, { '\u22a4' },
+            { '\u2336' }, { '\u2af1' }, { '\ud835', '\udd65' }, { '\u2ada' },
+            { '\u2929' }, { '\u2034' }, { '\u2122' }, { '\u25b5' },
+            { '\u25bf' }, { '\u25c3' }, { '\u22b4' }, { '\u225c' },
+            { '\u25b9' }, { '\u22b5' }, { '\u25ec' }, { '\u225c' },
+            { '\u2a3a' }, { '\u2a39' }, { '\u29cd' }, { '\u2a3b' },
+            { '\u23e2' }, { '\ud835', '\udcc9' }, { '\u0446' }, { '\u045b' },
+            { '\u0167' }, { '\u226c' }, { '\u219e' }, { '\u21a0' },
+            { '\u21d1' }, { '\u2963' }, { '\u00fa' }, { '\u00fa' },
+            { '\u2191' }, { '\u045e' }, { '\u016d' }, { '\u00fb' },
+            { '\u00fb' }, { '\u0443' }, { '\u21c5' }, { '\u0171' },
+            { '\u296e' }, { '\u297e' }, { '\ud835', '\udd32' }, { '\u00f9' },
+            { '\u00f9' }, { '\u21bf' }, { '\u21be' }, { '\u2580' },
+            { '\u231c' }, { '\u231c' }, { '\u230f' }, { '\u25f8' },
+            { '\u016b' }, { '\u00a8' }, { '\u00a8' }, { '\u0173' },
+            { '\ud835', '\udd66' }, { '\u2191' }, { '\u2195' }, { '\u21bf' },
+            { '\u21be' }, { '\u228e' }, { '\u03c5' }, { '\u03d2' },
+            { '\u03c5' }, { '\u21c8' }, { '\u231d' }, { '\u231d' },
+            { '\u230e' }, { '\u016f' }, { '\u25f9' }, { '\ud835', '\udcca' },
+            { '\u22f0' }, { '\u0169' }, { '\u25b5' }, { '\u25b4' },
+            { '\u21c8' }, { '\u00fc' }, { '\u00fc' }, { '\u29a7' },
+            { '\u21d5' }, { '\u2ae8' }, { '\u2ae9' }, { '\u22a8' },
+            { '\u299c' }, { '\u03f5' }, { '\u03f0' }, { '\u2205' },
+            { '\u03d5' }, { '\u03d6' }, { '\u221d' }, { '\u2195' },
+            { '\u03f1' }, { '\u03c2' }, { '\u228a', '\ufe00' },
+            { '\u2acb', '\ufe00' }, { '\u228b', '\ufe00' },
+            { '\u2acc', '\ufe00' }, { '\u03d1' }, { '\u22b2' }, { '\u22b3' },
+            { '\u0432' }, { '\u22a2' }, { '\u2228' }, { '\u22bb' },
+            { '\u225a' }, { '\u22ee' }, { '\u007c' }, { '\u007c' },
+            { '\ud835', '\udd33' }, { '\u22b2' }, { '\u2282', '\u20d2' },
+            { '\u2283', '\u20d2' }, { '\ud835', '\udd67' }, { '\u221d' },
+            { '\u22b3' }, { '\ud835', '\udccb' }, { '\u2acb', '\ufe00' },
+            { '\u228a', '\ufe00' }, { '\u2acc', '\ufe00' },
+            { '\u228b', '\ufe00' }, { '\u299a' }, { '\u0175' }, { '\u2a5f' },
+            { '\u2227' }, { '\u2259' }, { '\u2118' }, { '\ud835', '\udd34' },
+            { '\ud835', '\udd68' }, { '\u2118' }, { '\u2240' }, { '\u2240' },
+            { '\ud835', '\udccc' }, { '\u22c2' }, { '\u25ef' }, { '\u22c3' },
+            { '\u25bd' }, { '\ud835', '\udd35' }, { '\u27fa' }, { '\u27f7' },
+            { '\u03be' }, { '\u27f8' }, { '\u27f5' }, { '\u27fc' },
+            { '\u22fb' }, { '\u2a00' }, { '\ud835', '\udd69' }, { '\u2a01' },
+            { '\u2a02' }, { '\u27f9' }, { '\u27f6' }, { '\ud835', '\udccd' },
+            { '\u2a06' }, { '\u2a04' }, { '\u25b3' }, { '\u22c1' },
+            { '\u22c0' }, { '\u00fd' }, { '\u00fd' }, { '\u044f' },
+            { '\u0177' }, { '\u044b' }, { '\u00a5' }, { '\u00a5' },
+            { '\ud835', '\udd36' }, { '\u0457' }, { '\ud835', '\udd6a' },
+            { '\ud835', '\udcce' }, { '\u044e' }, { '\u00ff' }, { '\u00ff' },
+            { '\u017a' }, { '\u017e' }, { '\u0437' }, { '\u017c' },
+            { '\u2128' }, { '\u03b6' }, { '\ud835', '\udd37' }, { '\u0436' },
+            { '\u21dd' }, { '\ud835', '\udd6b' }, { '\ud835', '\udccf' },
+            { '\u200d' }, { '\u200c' }, };
+
+    final static char[][] WINDOWS_1252 = { { '\u20AC' }, { '\u0081' },
+            { '\u201A' }, { '\u0192' }, { '\u201E' }, { '\u2026' },
+            { '\u2020' }, { '\u2021' }, { '\u02C6' }, { '\u2030' },
+            { '\u0160' }, { '\u2039' }, { '\u0152' }, { '\u008D' },
+            { '\u017D' }, { '\u008F' }, { '\u0090' }, { '\u2018' },
+            { '\u2019' }, { '\u201C' }, { '\u201D' }, { '\u2022' },
+            { '\u2013' }, { '\u2014' }, { '\u02DC' }, { '\u2122' },
+            { '\u0161' }, { '\u203A' }, { '\u0153' }, { '\u009D' },
+            { '\u017E' }, { '\u0178' } };
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NamedCharactersAccel.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NamedCharactersAccel.java
new file mode 100644
index 000000000..311f8f77f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/NamedCharactersAccel.java
@@ -0,0 +1,311 @@
+/*
+ * Copyright 2004-2010 Apple Computer, Inc., Mozilla Foundation, and Opera 
+ * Software ASA.
+ * 
+ * You are granted a license to use, reproduce and create derivative works of 
+ * this document.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.NoLength;
+
+/**
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class NamedCharactersAccel {
+
+    static final @NoLength int[][] HILO_ACCEL = {
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            { 0, 0, 0, 0, 0, 0, 0, 12386493, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 40174181, 0, 0, 0, 0, 60162966, 0, 0, 0,
+                    75367550, 0, 0, 0, 82183396, 0, 0, 0, 0, 0, 115148507, 0,
+                    0, 135989275, 139397199, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 28770743, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    82248935, 0, 0, 0, 0, 0, 115214046, 0, 0, 0, 139528272, 0,
+                    0, 0, 0, },
+            null,
+            { 0, 0, 0, 4980811, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 38470219, 0, 0, 0, 0, 0, 0, 0, 0, 64553944, 0, 0, 0, 0,
+                    0, 0, 0, 92145022, 0, 0, 0, 0, 0, 0, 0, 0, 139593810, 0, 0,
+                    0, 0, },
+            { 65536, 0, 0, 0, 0, 0, 0, 0, 13172937, 0, 0, 0, 0, 0, 25297282, 0,
+                    0, 28901816, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    71500866, 0, 0, 0, 0, 82380008, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, },
+            null,
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    94897574, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 2555943, 0, 0, 0, 0, 0, 0, 0, 15532269, 0, 0, 0, 0, 0, 0,
+                    0, 31785444, 34406924, 0, 0, 0, 0, 0, 40895088, 0, 0, 0,
+                    60228503, 0, 0, 0, 0, 0, 0, 0, 82445546, 0, 0, 0, 0, 0,
+                    115279583, 0, 0, 136054812, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 40239718, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 5046349, 0, 0, 10944679, 0, 13238474, 0, 15597806,
+                    16056565, 0, 20578618, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, },
+            null,
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    95225257, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 196610, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 8454273, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 46072511, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 2687016, 0, 0, 0, 0, 0, 13304011, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 31850982, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            null,
+            null,
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    34472462, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 95290798, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 5111886, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    34603535, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 105776718, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 8585346, 0, 11075752, 0, 0, 0, 0, 16187638, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 28508594, 0, 0,
+                    0, 0, 0, 0, 0, 40305255, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    95421871, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            null,
+            null,
+            null,
+            { 0, 0, 0, 5177423, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            null,
+            null,
+            null,
+            null,
+            null,
+            null,
+            { 327684, 1900571, 2949162, 5374032, 8716420, 0, 11206826,
+                    12517566, 13435084, 0, 15663343, 16515320, 19988785,
+                    20644155, 25428355, 27197855, 0, 29163962, 31916519,
+                    34734609, 36045347, 0, 0, 0, 40436328, 40960625, 41615994,
+                    46596800, 54264627, 60556184, 64750554, 68879387, 71763012,
+                    75826303, 77268122, 0, 81462490, 83952875, 92865919,
+                    96142769, 105973327, 110167691, 0, 116917984, 121833283,
+                    132253665, 136251421, 140707923, 0, 0, 144574620,
+                    145361066, },
+            { 393222, 0, 0, 0, 0, 0, 11272364, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 36176423, 38535756, 0, 0, 0, 0, 41681532, 46727880,
+                    0, 60687261, 0, 0, 71828552, 75891846, 0, 0, 0, 84411650,
+                    0, 96404924, 0, 0, 0, 117376761, 121898820, 132319203,
+                    136382496, 0, 0, 0, 0, 0, },
+            { 589831, 1966110, 3276846, 5505107, 8978566, 10420383, 11468973,
+                    12583104, 13631694, 15139046, 15794416, 16711933, 20054322,
+                    20840764, 25624965, 27263392, 0, 29360574, 32244200,
+                    34931219, 36373033, 38601293, 39584348, 0, 40567402,
+                    41091698, 42205821, 46858954, 54723389, 60818335, 65143773,
+                    68944924, 71959625, 75957383, 77530268, 80938194, 81593564,
+                    84739337, 92997002, 96863680, 106235474, 110233234, 0,
+                    117704448, 122816325, 132515812, 136579106, 140773476,
+                    142149753, 143001732, 144705695, 145492139, },
+            { 0, 0, 3342387, 0, 9044106, 0, 11534512, 0, 13697233, 0, 0, 0, 0,
+                    0, 25690504, 0, 0, 0, 0, 0, 36438572, 38732366, 0, 0, 0,
+                    41157236, 0, 46924492, 54788932, 61080481, 65209315, 0,
+                    72025163, 0, 0, 0, 0, 85132558, 93062540, 96929223,
+                    106563158, 0, 0, 118032133, 123012947, 132581351,
+                    136775717, 140839013, 0, 143067271, 0, 145557677, },
+            { 0, 2162719, 3473460, 5636181, 0, 0, 0, 0, 0, 0, 0, 18809088,
+                    20185395, 21299519, 0, 0, 0, 29622721, 0, 0, 0, 39256656,
+                    39649885, 0, 0, 41288309, 42336901, 47448781, 55182149,
+                    61342629, 65274852, 69010461, 72811596, 76219528, 77726880,
+                    0, 0, 86967572, 93128077, 97650120, 106628699, 110560915,
+                    0, 118490890, 123733846, 132646888, 0, 141232230,
+                    142411898, 0, 144836769, 145688750, },
+            { 655370, 2228258, 3538998, 5701719, 9109643, 10485920, 11600049,
+                    12648641, 13762770, 15204584, 15859954, 18874656, 20250933,
+                    21365062, 25756041, 27328929, 28574132, 29688261, 32309741,
+                    34996758, 36504109, 39322200, 39715422, 39912033, 40632940,
+                    41353847, 42467975, 47514325, 55247691, 61473705, 65405925,
+                    69272606, 72877144, 76285068, 77857955, 81003732, 81659102,
+                    87164208, 93193614, 97715667, 106759772, 110626456,
+                    114296528, 118687505, 123864929, 132712425, 136906792,
+                    141297772, 142477438, 143132808, 144902307, 145754288, },
+            { 786443, 0, 0, 0, 9240716, 0, 11665586, 0, 13893843, 0, 0, 0, 0,
+                    0, 25887114, 0, 0, 0, 0, 0, 36635182, 0, 0, 0, 0, 0,
+                    42599049, 0, 0, 0, 65733607, 0, 73008217, 0, 77989029, 0,
+                    81724639, 87295283, 0, 98305492, 107021918, 0, 0, 0, 0, 0,
+                    137037866, 0, 0, 0, 0, 0, },
+            { 0, 0, 3604535, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 27394466, 0,
+                    29753798, 32571886, 35258903, 0, 0, 0, 0, 0, 0, 0, 0,
+                    55509836, 61604779, 0, 0, 0, 0, 0, 0, 81790176, 87557429,
+                    93259151, 98502109, 107152994, 110888601, 0, 119015188,
+                    124323683, 133498858, 137234476, 0, 0, 143263881, 0,
+                    145819825, },
+            { 0, 0, 3866680, 6160472, 0, 10616993, 0, 12714178, 0, 0, 0, 0,
+                    20316470, 0, 0, 27460003, 0, 31261127, 32637426, 35521051,
+                    0, 0, 0, 39977570, 0, 0, 0, 48366294, 56492880, 62391213,
+                    0, 69338146, 73073755, 0, 78316711, 0, 0, 0, 93980048,
+                    98764256, 107218532, 111085213, 114362065, 119736089,
+                    125241194, 133957622, 0, 0, 0, 143329419, 144967844,
+                    145885362, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 62456761, 0, 69403683, 73139292, 0,
+                    78382252, 0, 81855713, 87622969, 0, 98829796, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 48431843, 0, 0, 0, 0, 0, 76416141, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 851981, 0, 4063292, 0, 9306254, 0, 0, 0, 0, 0, 0, 19005729, 0, 0,
+                    0, 27525540, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 42795659,
+                    49152740, 56623967, 62587834, 66061292, 69600292, 73401437,
+                    0, 0, 0, 0, 87950650, 94111131, 99878373, 107546213,
+                    112002720, 0, 119932708, 125306744, 0, 137496623,
+                    141363309, 0, 143460492, 0, 0, },
+            { 917518, 0, 0, 0, 9502863, 0, 0, 0, 14155989, 0, 0, 19071267, 0,
+                    0, 26083724, 0, 0, 0, 32702963, 0, 36700720, 0, 0, 0, 0, 0,
+                    43057806, 0, 0, 0, 66520049, 0, 0, 0, 78841005, 81069269,
+                    0, 88147263, 0, 99943925, 107873898, 112068270, 0,
+                    120063783, 125831033, 0, 137693235, 0, 0, 143526030, 0, 0, },
+            { 983055, 0, 0, 0, 0, 0, 0, 0, 14483673, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 37093937, 0, 0, 0, 0, 0, 44565138, 49349359, 0, 0,
+                    66651128, 69665831, 73860193, 0, 79561908, 0, 0, 88606018,
+                    94176669, 0, 0, 0, 0, 120129321, 0, 0, 0, 141494382, 0,
+                    143591567, 0, 0, },
+            { 1114128, 2293795, 4587583, 8257631, 9633938, 10813603, 11731123,
+                    12845251, 14680286, 15270121, 15925491, 19661092, 20382007,
+                    24969543, 26149263, 27656613, 28639669, 31392222, 32768500,
+                    35586591, 37225015, 39387737, 39780959, 40043107, 40698477,
+                    41419384, 44696233, 52495090, 57738081, 63439804, 66782202,
+                    69927976, 73925736, 76809359, 79824063, 81134806, 81921250,
+                    89785673, 94307742, 100795894, 107939439, 112330415,
+                    114427602, 120588074, 126158721, 134416381, 137824310,
+                    141559920, 142542975, 143853712, 145033381, 145950899, },
+            { 1179666, 0, 0, 0, 9699476, 0, 0, 0, 0, 0, 0, 0, 0, 0, 26280336,
+                    0, 0, 0, 0, 0, 38076985, 0, 0, 0, 0, 0, 45220523, 52560674,
+                    0, 0, 67175420, 69993516, 0, 0, 79889603, 0, 0, 89916763,
+                    94373280, 101451267, 108136048, 0, 114493139, 120784689,
+                    126355334, 134481924, 138414136, 141625457, 142608512, 0,
+                    0, 0, },
+            { 0, 0, 0, 0, 9896085, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    33292789, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 67830786, 0, 0,
+                    0, 80020676, 0, 0, 0, 0, 0, 0, 0, 0, 0, 127403913, 0, 0, 0,
+                    0, 0, 0, 0, },
+            { 1310739, 2359332, 4653127, 0, 0, 0, 12189876, 0, 0, 0, 0, 0, 0,
+                    0, 26345874, 28246439, 0, 31457760, 0, 35652128, 38142534,
+                    0, 0, 0, 0, 0, 45351603, 52757283, 57869170, 63636425,
+                    67961868, 71304237, 73991273, 0, 0, 0, 0, 90309981, 0,
+                    101910029, 108988019, 114034355, 0, 120850228, 127469465,
+                    135464965, 138741825, 141690994, 142739585, 143984788, 0,
+                    0, },
+            { 1441813, 2424869, 4718664, 8388735, 10027160, 10879142, 12255419,
+                    12976325, 14745825, 15401194, 15991028, 19857709, 20447544,
+                    25035134, 26542483, 28377520, 28705206, 31588833, 33358333,
+                    35783201, 38208071, 39453274, 39846496, 40108644, 40764014,
+                    41484921, 45613749, 53216038, 58196852, 63898572, 68158478,
+                    71369793, 74253418, 77005973, 80479430, 81265879, 81986787,
+                    90965347, 94504353, 103679508, 109250176, 114165453,
+                    114558676, 121243445, 127731610, 135727124, 138807366,
+                    142018675, 142805123, 144115862, 145098918, 146016436, },
+            { 1572887, 0, 0, 0, 10092698, 0, 12320956, 0, 14811362, 0, 0,
+                    19923248, 0, 25166207, 26739094, 0, 0, 0, 33423870, 0,
+                    38273608, 0, 0, 0, 0, 0, 45744825, 0, 58262393, 64095184,
+                    68355089, 0, 75170926, 0, 80610509, 0, 0, 91817325, 0,
+                    104203823, 109512324, 0, 0, 121636667, 128059294, 0,
+                    139069511, 0, 0, 0, 0, 0, },
+            { 1703961, 2490406, 4849737, 0, 10223771, 0, 0, 13107399, 15007971,
+                    15466732, 0, 0, 20513081, 25231745, 26870169, 0, 0,
+                    31654371, 34275839, 0, 38404681, 0, 0, 0, 40829551, 0,
+                    45875899, 53609261, 59900794, 64226259, 68551700, 0, 0, 0,
+                    80807119, 81331417, 0, 91948410, 94700963, 104465975,
+                    109643400, 114230991, 114951893, 121702209, 131663779, 0,
+                    139266123, 0, 0, 144246936, 145295527, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 27132315, 0, 0, 0, 0,
+                    0, 0, 39518811, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 75302012, 0,
+                    0, 0, 0, 92079484, 0, 105383483, 109708938, 0, 0, 0, 0, 0,
+                    0, 0, 0, 144312474, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 46006973, 0, 60031891, 64291797, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 105711177, 0, 0, 0, 0, 131991514, 135923736,
+                    139331662, 0, 0, 144378011, 0, 146147509, },
+            { 0, 0, 0, 0, 10354845, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 68813847, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 121767746, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 60097429, 0, 0, 0, 0, 77137048, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, },
+            { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 0, 0, 64422870, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+                    0, 0, 0, 0, 0, 132122591, 0, 0, 142084216, 0, 0, 0, 0, }, };
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Portability.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Portability.java
new file mode 100644
index 000000000..2b3f96625
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Portability.java
@@ -0,0 +1,152 @@
+/*
+ * Copyright (c) 2008-2015 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.Literal;
+import nu.validator.htmlparser.annotation.Local;
+import nu.validator.htmlparser.annotation.NoLength;
+import nu.validator.htmlparser.common.Interner;
+
+public final class Portability {
+
+    // Allocating methods
+
+    /**
+     * Allocates a new local name object. In C++, the refcount must be set up in such a way that 
+     * calling <code>releaseLocal</code> on the return value balances the refcount set by this method.
+     */
+    public static @Local String newLocalNameFromBuffer(@NoLength char[] buf, int offset, int length, Interner interner) {
+        return new String(buf, offset, length).intern();
+    }
+
+    public static String newStringFromBuffer(@NoLength char[] buf, int offset, int length
+        // CPPONLY: , TreeBuilder treeBuilder
+    ) {
+        return new String(buf, offset, length);
+    }
+
+    public static String newEmptyString() {
+        return "";
+    }
+
+    public static String newStringFromLiteral(@Literal String literal) {
+        return literal;
+    }
+    
+    public static String newStringFromString(String string) {
+        return string;
+    }
+    
+    // XXX get rid of this
+    public static char[] newCharArrayFromLocal(@Local String local) {
+        return local.toCharArray();
+    }
+
+    public static char[] newCharArrayFromString(String string) {
+        return string.toCharArray();
+    }
+    
+    public static @Local String newLocalFromLocal(@Local String local, Interner interner) {
+        return local;
+    }
+    
+    // Deallocation methods
+    
+    public static void releaseString(String str) {
+        // No-op in Java
+    }
+    
+    // Comparison methods
+    
+    public static boolean localEqualsBuffer(@Local String local, @NoLength char[] buf, int offset, int length) {
+        if (local.length() != length) {
+            return false;
+        }
+        for (int i = 0; i < length; i++) {
+            if (local.charAt(i) != buf[offset + i]) {
+                return false;
+            }
+        }
+        return true;
+    }
+
+    public static boolean lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString(@Literal String lowerCaseLiteral,
+            String string) {
+        if (string == null) {
+            return false;
+        }
+        if (lowerCaseLiteral.length() > string.length()) {
+            return false;
+        }
+        for (int i = 0; i < lowerCaseLiteral.length(); i++) {
+            char c0 = lowerCaseLiteral.charAt(i);
+            char c1 = string.charAt(i);
+            if (c1 >= 'A' && c1 <= 'Z') {
+                c1 += 0x20;
+            }
+            if (c0 != c1) {
+                return false;
+            }
+        }
+        return true;
+    }
+    
+    public static boolean lowerCaseLiteralEqualsIgnoreAsciiCaseString(@Literal String lowerCaseLiteral,
+            String string) {
+        if (string == null) {
+            return false;
+        }
+        if (lowerCaseLiteral.length() != string.length()) {
+            return false;
+        }
+        for (int i = 0; i < lowerCaseLiteral.length(); i++) {
+            char c0 = lowerCaseLiteral.charAt(i);
+            char c1 = string.charAt(i);
+            if (c1 >= 'A' && c1 <= 'Z') {
+                c1 += 0x20;
+            }
+            if (c0 != c1) {
+                return false;
+            }
+        }
+        return true;
+    }
+    
+    public static boolean literalEqualsString(@Literal String literal, String string) {
+        return literal.equals(string);
+    }
+
+    public static boolean stringEqualsString(String one, String other) {
+        return one.equals(other);
+    }
+    
+    public static void delete(Object o) {
+        
+    }
+
+    public static void deleteArray(Object o) {
+        
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/PushedLocation.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/PushedLocation.java
new file mode 100644
index 000000000..fad5f43db
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/PushedLocation.java
@@ -0,0 +1,136 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+public class PushedLocation {
+    private final int line;
+
+    private final int linePrev;
+
+    private final int col;
+
+    private final int colPrev;
+
+    private final boolean nextCharOnNewLine;
+
+    private final String publicId;
+
+    private final String systemId;
+
+    private final PushedLocation next;
+
+    /**
+     * @param line
+     * @param linePrev
+     * @param col
+     * @param colPrev
+     * @param nextCharOnNewLine
+     * @param publicId
+     * @param systemId
+     * @param next
+     */
+    public PushedLocation(int line, int linePrev, int col, int colPrev,
+            boolean nextCharOnNewLine, String publicId, String systemId,
+            PushedLocation next) {
+        this.line = line;
+        this.linePrev = linePrev;
+        this.col = col;
+        this.colPrev = colPrev;
+        this.nextCharOnNewLine = nextCharOnNewLine;
+        this.publicId = publicId;
+        this.systemId = systemId;
+        this.next = next;
+    }
+
+    /**
+     * Returns the line.
+     * 
+     * @return the line
+     */
+    public int getLine() {
+        return line;
+    }
+
+    /**
+     * Returns the linePrev.
+     * 
+     * @return the linePrev
+     */
+    public int getLinePrev() {
+        return linePrev;
+    }
+
+    /**
+     * Returns the col.
+     * 
+     * @return the col
+     */
+    public int getCol() {
+        return col;
+    }
+
+    /**
+     * Returns the colPrev.
+     * 
+     * @return the colPrev
+     */
+    public int getColPrev() {
+        return colPrev;
+    }
+
+    /**
+     * Returns the nextCharOnNewLine.
+     * 
+     * @return the nextCharOnNewLine
+     */
+    public boolean isNextCharOnNewLine() {
+        return nextCharOnNewLine;
+    }
+
+    /**
+     * Returns the publicId.
+     * 
+     * @return the publicId
+     */
+    public String getPublicId() {
+        return publicId;
+    }
+
+    /**
+     * Returns the systemId.
+     * 
+     * @return the systemId
+     */
+    public String getSystemId() {
+        return systemId;
+    }
+
+    /**
+     * Returns the next.
+     * 
+     * @return the next
+     */
+    public PushedLocation getNext() {
+        return next;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/StackNode.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/StackNode.java
new file mode 100644
index 000000000..b671bc903
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/StackNode.java
@@ -0,0 +1,297 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2007-2011 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.Inline;
+import nu.validator.htmlparser.annotation.Local;
+import nu.validator.htmlparser.annotation.NsUri;
+
+final class StackNode<T> {
+    final int flags;
+
+    final @Local String name;
+
+    final @Local String popName;
+
+    final @NsUri String ns;
+
+    final T node;
+
+    // Only used on the list of formatting elements
+    HtmlAttributes attributes;
+
+    private int refcount = 1;
+
+    // [NOCPP[
+
+    private final TaintableLocatorImpl locator;
+    
+    public TaintableLocatorImpl getLocator() {
+        return locator;
+    }
+
+    // ]NOCPP]
+
+    @Inline public int getFlags() {
+        return flags;
+    }
+
+    public int getGroup() {
+        return flags & ElementName.GROUP_MASK;
+    }
+
+    public boolean isScoping() {
+        return (flags & ElementName.SCOPING) != 0;
+    }
+
+    public boolean isSpecial() {
+        return (flags & ElementName.SPECIAL) != 0;
+    }
+
+    public boolean isFosterParenting() {
+        return (flags & ElementName.FOSTER_PARENTING) != 0;
+    }
+
+    public boolean isHtmlIntegrationPoint() {
+        return (flags & ElementName.HTML_INTEGRATION_POINT) != 0;
+    }
+
+    // [NOCPP[
+    
+    public boolean isOptionalEndTag() {
+        return (flags & ElementName.OPTIONAL_END_TAG) != 0;
+    }
+    
+    // ]NOCPP]
+
+    /**
+     * Constructor for copying. This doesn't take another <code>StackNode</code>
+     * because in C++ the caller is reponsible for reobtaining the local names
+     * from another interner.
+     * 
+     * @param flags
+     * @param ns
+     * @param name
+     * @param node
+     * @param popName
+     * @param attributes
+     */
+    StackNode(int flags, @NsUri String ns, @Local String name, T node,
+            @Local String popName, HtmlAttributes attributes
+            // [NOCPP[
+            , TaintableLocatorImpl locator
+    // ]NOCPP]
+    ) {
+        this.flags = flags;
+        this.name = name;
+        this.popName = popName;
+        this.ns = ns;
+        this.node = node;
+        this.attributes = attributes;
+        this.refcount = 1;
+        // [NOCPP[
+        this.locator = locator;
+        // ]NOCPP]
+    }
+
+    /**
+     * Short hand for well-known HTML elements.
+     * 
+     * @param elementName
+     * @param node
+     */
+    StackNode(ElementName elementName, T node
+    // [NOCPP[
+            , TaintableLocatorImpl locator
+    // ]NOCPP]
+    ) {
+        this.flags = elementName.getFlags();
+        this.name = elementName.name;
+        this.popName = elementName.name;
+        this.ns = "http://www.w3.org/1999/xhtml";
+        this.node = node;
+        this.attributes = null;
+        this.refcount = 1;
+        assert !elementName.isCustom() : "Don't use this constructor for custom elements.";
+        // [NOCPP[
+        this.locator = locator;
+        // ]NOCPP]
+    }
+
+    /**
+     * Constructor for HTML formatting elements.
+     * 
+     * @param elementName
+     * @param node
+     * @param attributes
+     */
+    StackNode(ElementName elementName, T node, HtmlAttributes attributes
+    // [NOCPP[
+            , TaintableLocatorImpl locator
+    // ]NOCPP]
+    ) {
+        this.flags = elementName.getFlags();
+        this.name = elementName.name;
+        this.popName = elementName.name;
+        this.ns = "http://www.w3.org/1999/xhtml";
+        this.node = node;
+        this.attributes = attributes;
+        this.refcount = 1;
+        assert !elementName.isCustom() : "Don't use this constructor for custom elements.";
+        // [NOCPP[
+        this.locator = locator;
+        // ]NOCPP]
+    }
+
+    /**
+     * The common-case HTML constructor.
+     * 
+     * @param elementName
+     * @param node
+     * @param popName
+     */
+    StackNode(ElementName elementName, T node, @Local String popName
+    // [NOCPP[
+            , TaintableLocatorImpl locator
+    // ]NOCPP]
+    ) {
+        this.flags = elementName.getFlags();
+        this.name = elementName.name;
+        this.popName = popName;
+        this.ns = "http://www.w3.org/1999/xhtml";
+        this.node = node;
+        this.attributes = null;
+        this.refcount = 1;
+        // [NOCPP[
+        this.locator = locator;
+        // ]NOCPP]
+    }
+
+    /**
+     * Constructor for SVG elements. Note that the order of the arguments is
+     * what distinguishes this from the HTML constructor. This is ugly, but
+     * AFAICT the least disruptive way to make this work with Java's generics
+     * and without unnecessary branches. :-(
+     * 
+     * @param elementName
+     * @param popName
+     * @param node
+     */
+    StackNode(ElementName elementName, @Local String popName, T node
+    // [NOCPP[
+            , TaintableLocatorImpl locator
+    // ]NOCPP]
+    ) {
+        this.flags = prepareSvgFlags(elementName.getFlags());
+        this.name = elementName.name;
+        this.popName = popName;
+        this.ns = "http://www.w3.org/2000/svg";
+        this.node = node;
+        this.attributes = null;
+        this.refcount = 1;
+        // [NOCPP[
+        this.locator = locator;
+        // ]NOCPP]
+    }
+
+    /**
+     * Constructor for MathML.
+     * 
+     * @param elementName
+     * @param node
+     * @param popName
+     * @param markAsIntegrationPoint
+     */
+    StackNode(ElementName elementName, T node, @Local String popName,
+            boolean markAsIntegrationPoint
+            // [NOCPP[
+            , TaintableLocatorImpl locator
+    // ]NOCPP]
+    ) {
+        this.flags = prepareMathFlags(elementName.getFlags(),
+                markAsIntegrationPoint);
+        this.name = elementName.name;
+        this.popName = popName;
+        this.ns = "http://www.w3.org/1998/Math/MathML";
+        this.node = node;
+        this.attributes = null;
+        this.refcount = 1;
+        // [NOCPP[
+        this.locator = locator;
+        // ]NOCPP]
+    }
+
+    private static int prepareSvgFlags(int flags) {
+        flags &= ~(ElementName.FOSTER_PARENTING | ElementName.SCOPING
+                | ElementName.SPECIAL | ElementName.OPTIONAL_END_TAG);
+        if ((flags & ElementName.SCOPING_AS_SVG) != 0) {
+            flags |= (ElementName.SCOPING | ElementName.SPECIAL | ElementName.HTML_INTEGRATION_POINT);
+        }
+        return flags;
+    }
+
+    private static int prepareMathFlags(int flags,
+            boolean markAsIntegrationPoint) {
+        flags &= ~(ElementName.FOSTER_PARENTING | ElementName.SCOPING
+                | ElementName.SPECIAL | ElementName.OPTIONAL_END_TAG);
+        if ((flags & ElementName.SCOPING_AS_MATHML) != 0) {
+            flags |= (ElementName.SCOPING | ElementName.SPECIAL);
+        }
+        if (markAsIntegrationPoint) {
+            flags |= ElementName.HTML_INTEGRATION_POINT;
+        }
+        return flags;
+    }
+
+    @SuppressWarnings("unused") private void destructor() {
+        Portability.delete(attributes);
+    }
+
+    public void dropAttributes() {
+        attributes = null;
+    }
+
+    // [NOCPP[
+    /**
+     * @see java.lang.Object#toString()
+     */
+    @Override public @Local String toString() {
+        return name;
+    }
+
+    // ]NOCPP]
+
+    public void retain() {
+        refcount++;
+    }
+
+    public void release() {
+        refcount--;
+        if (refcount == 0) {
+            Portability.delete(this);
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/StateSnapshot.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/StateSnapshot.java
new file mode 100644
index 000000000..d79641bcb
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/StateSnapshot.java
@@ -0,0 +1,206 @@
+/*
+ * Copyright (c) 2009-2010 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.Auto;
+
+
+public class StateSnapshot<T> implements TreeBuilderState<T> {
+
+    private final @Auto StackNode<T>[] stack;
+
+    private final @Auto StackNode<T>[] listOfActiveFormattingElements;
+
+    private final @Auto int[] templateModeStack;
+
+    private final T formPointer;
+
+    private final T headPointer;
+
+    private final T deepTreeSurrogateParent;
+
+    private final int mode;
+
+    private final int originalMode;
+    
+    private final boolean framesetOk;
+
+    private final boolean needToDropLF;
+
+    private final boolean quirks;
+
+    /**
+     * @param stack
+     * @param listOfActiveFormattingElements
+     * @param templateModeStack
+     * @param formPointer
+     * @param headPointer
+     * @param deepTreeSurrogateParent
+     * @param mode
+     * @param originalMode
+     * @param framesetOk
+     * @param needToDropLF
+     * @param quirks
+     */
+    StateSnapshot(StackNode<T>[] stack,
+            StackNode<T>[] listOfActiveFormattingElements, int[] templateModeStack, T formPointer,
+            T headPointer, T deepTreeSurrogateParent, int mode, int originalMode,
+            boolean framesetOk, boolean needToDropLF, boolean quirks) {
+        this.stack = stack;
+        this.listOfActiveFormattingElements = listOfActiveFormattingElements;
+        this.templateModeStack = templateModeStack;
+        this.formPointer = formPointer;
+        this.headPointer = headPointer;
+        this.deepTreeSurrogateParent = deepTreeSurrogateParent;
+        this.mode = mode;
+        this.originalMode = originalMode;
+        this.framesetOk = framesetOk;
+        this.needToDropLF = needToDropLF;
+        this.quirks = quirks;
+    }
+    
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getStack()
+     */
+    public StackNode<T>[] getStack() {
+        return stack;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStack()
+     */
+    public int[] getTemplateModeStack() {
+        return templateModeStack;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElements()
+     */
+    public StackNode<T>[] getListOfActiveFormattingElements() {
+        return listOfActiveFormattingElements;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getFormPointer()
+     */
+    public T getFormPointer() {
+        return formPointer;
+    }
+
+    /**
+     * Returns the headPointer.
+     * 
+     * @return the headPointer
+     */
+    public T getHeadPointer() {
+        return headPointer;
+    }
+
+    /**
+     * Returns the deepTreeSurrogateParent.
+     * 
+     * @return the deepTreeSurrogateParent
+     */
+    public T getDeepTreeSurrogateParent() {
+        return deepTreeSurrogateParent;
+    }
+    
+    /**
+     * Returns the mode.
+     * 
+     * @return the mode
+     */
+    public int getMode() {
+        return mode;
+    }
+
+    /**
+     * Returns the originalMode.
+     * 
+     * @return the originalMode
+     */
+    public int getOriginalMode() {
+        return originalMode;
+    }
+
+    /**
+     * Returns the framesetOk.
+     * 
+     * @return the framesetOk
+     */
+    public boolean isFramesetOk() {
+        return framesetOk;
+    }
+
+    /**
+     * Returns the needToDropLF.
+     * 
+     * @return the needToDropLF
+     */
+    public boolean isNeedToDropLF() {
+        return needToDropLF;
+    }
+
+    /**
+     * Returns the quirks.
+     * 
+     * @return the quirks
+     */
+    public boolean isQuirks() {
+        return quirks;
+    }
+    
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElementsLength()
+     */
+    public int getListOfActiveFormattingElementsLength() {
+        return listOfActiveFormattingElements.length;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getStackLength()
+     */
+    public int getStackLength() {
+        return stack.length;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStackLength()
+     */
+    public int getTemplateModeStackLength() {
+        return templateModeStack.length;
+    }
+
+    @SuppressWarnings("unused") private void destructor() {
+        for (int i = 0; i < stack.length; i++) {
+            stack[i].release();
+        }
+        for (int i = 0; i < listOfActiveFormattingElements.length; i++) {
+            if (listOfActiveFormattingElements[i] != null) {
+                listOfActiveFormattingElements[i].release();                
+            }
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TaintableLocatorImpl.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TaintableLocatorImpl.java
new file mode 100644
index 000000000..37cdb75d3
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TaintableLocatorImpl.java
@@ -0,0 +1,43 @@
+/*
+ * Copyright (c) 2011 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import org.xml.sax.Locator;
+
+public class TaintableLocatorImpl extends LocatorImpl {
+
+    private boolean tainted;
+    
+    public TaintableLocatorImpl(Locator locator) {
+        super(locator);
+        this.tainted = false;
+    }
+    
+    public void markTainted() {
+        tainted = true;
+    }
+
+    public boolean isTainted() {
+        return tainted;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Tokenizer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Tokenizer.java
new file mode 100644
index 000000000..125ef3266
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/Tokenizer.java
@@ -0,0 +1,7080 @@
+/*
+ * Copyright (c) 2005-2007 Henri Sivonen
+ * Copyright (c) 2007-2015 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ * Portions of comments Copyright 2004-2010 Apple Computer, Inc., Mozilla
+ * Foundation, and Opera Software ASA.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * The comments following this one that use the same comment syntax as this
+ * comment are quotes from the WHATWG HTML 5 spec as of 2 June 2007
+ * amended as of June 18 2008 and May 31 2010.
+ * That document came with this statement:
+ * "© Copyright 2004-2010 Apple Computer, Inc., Mozilla Foundation, and
+ * Opera Software ASA. You are granted a license to use, reproduce and
+ * create derivative works of this document."
+ */
+
+package nu.validator.htmlparser.impl;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+import nu.validator.htmlparser.annotation.Auto;
+import nu.validator.htmlparser.annotation.CharacterName;
+import nu.validator.htmlparser.annotation.Const;
+import nu.validator.htmlparser.annotation.Inline;
+import nu.validator.htmlparser.annotation.Local;
+import nu.validator.htmlparser.annotation.NoLength;
+import nu.validator.htmlparser.common.EncodingDeclarationHandler;
+import nu.validator.htmlparser.common.Interner;
+import nu.validator.htmlparser.common.TokenHandler;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+
+/**
+ * An implementation of
+ * https://html.spec.whatwg.org/multipage/syntax.html#tokenization
+ *
+ * This class implements the <code>Locator</code> interface. This is not an
+ * incidental implementation detail: Users of this class are encouraged to make
+ * use of the <code>Locator</code> nature.
+ *
+ * By default, the tokenizer may report data that XML 1.0 bans. The tokenizer
+ * can be configured to treat these conditions as fatal or to coerce the infoset
+ * to something that XML 1.0 allows.
+ *
+ * @version $Id$
+ * @author hsivonen
+ */
+public class Tokenizer implements Locator {
+
+    private static final int DATA_AND_RCDATA_MASK = ~1;
+
+    public static final int DATA = 0;
+
+    public static final int RCDATA = 1;
+
+    public static final int SCRIPT_DATA = 2;
+
+    public static final int RAWTEXT = 3;
+
+    public static final int SCRIPT_DATA_ESCAPED = 4;
+
+    public static final int ATTRIBUTE_VALUE_DOUBLE_QUOTED = 5;
+
+    public static final int ATTRIBUTE_VALUE_SINGLE_QUOTED = 6;
+
+    public static final int ATTRIBUTE_VALUE_UNQUOTED = 7;
+
+    public static final int PLAINTEXT = 8;
+
+    public static final int TAG_OPEN = 9;
+
+    public static final int CLOSE_TAG_OPEN = 10;
+
+    public static final int TAG_NAME = 11;
+
+    public static final int BEFORE_ATTRIBUTE_NAME = 12;
+
+    public static final int ATTRIBUTE_NAME = 13;
+
+    public static final int AFTER_ATTRIBUTE_NAME = 14;
+
+    public static final int BEFORE_ATTRIBUTE_VALUE = 15;
+
+    public static final int AFTER_ATTRIBUTE_VALUE_QUOTED = 16;
+
+    public static final int BOGUS_COMMENT = 17;
+
+    public static final int MARKUP_DECLARATION_OPEN = 18;
+
+    public static final int DOCTYPE = 19;
+
+    public static final int BEFORE_DOCTYPE_NAME = 20;
+
+    public static final int DOCTYPE_NAME = 21;
+
+    public static final int AFTER_DOCTYPE_NAME = 22;
+
+    public static final int BEFORE_DOCTYPE_PUBLIC_IDENTIFIER = 23;
+
+    public static final int DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED = 24;
+
+    public static final int DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED = 25;
+
+    public static final int AFTER_DOCTYPE_PUBLIC_IDENTIFIER = 26;
+
+    public static final int BEFORE_DOCTYPE_SYSTEM_IDENTIFIER = 27;
+
+    public static final int DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED = 28;
+
+    public static final int DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED = 29;
+
+    public static final int AFTER_DOCTYPE_SYSTEM_IDENTIFIER = 30;
+
+    public static final int BOGUS_DOCTYPE = 31;
+
+    public static final int COMMENT_START = 32;
+
+    public static final int COMMENT_START_DASH = 33;
+
+    public static final int COMMENT = 34;
+
+    public static final int COMMENT_END_DASH = 35;
+
+    public static final int COMMENT_END = 36;
+
+    public static final int COMMENT_END_BANG = 37;
+
+    public static final int NON_DATA_END_TAG_NAME = 38;
+
+    public static final int MARKUP_DECLARATION_HYPHEN = 39;
+
+    public static final int MARKUP_DECLARATION_OCTYPE = 40;
+
+    public static final int DOCTYPE_UBLIC = 41;
+
+    public static final int DOCTYPE_YSTEM = 42;
+
+    public static final int AFTER_DOCTYPE_PUBLIC_KEYWORD = 43;
+
+    public static final int BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS = 44;
+
+    public static final int AFTER_DOCTYPE_SYSTEM_KEYWORD = 45;
+
+    public static final int CONSUME_CHARACTER_REFERENCE = 46;
+
+    public static final int CONSUME_NCR = 47;
+
+    public static final int CHARACTER_REFERENCE_TAIL = 48;
+
+    public static final int HEX_NCR_LOOP = 49;
+
+    public static final int DECIMAL_NRC_LOOP = 50;
+
+    public static final int HANDLE_NCR_VALUE = 51;
+
+    public static final int HANDLE_NCR_VALUE_RECONSUME = 52;
+
+    public static final int CHARACTER_REFERENCE_HILO_LOOKUP = 53;
+
+    public static final int SELF_CLOSING_START_TAG = 54;
+
+    public static final int CDATA_START = 55;
+
+    public static final int CDATA_SECTION = 56;
+
+    public static final int CDATA_RSQB = 57;
+
+    public static final int CDATA_RSQB_RSQB = 58;
+
+    public static final int SCRIPT_DATA_LESS_THAN_SIGN = 59;
+
+    public static final int SCRIPT_DATA_ESCAPE_START = 60;
+
+    public static final int SCRIPT_DATA_ESCAPE_START_DASH = 61;
+
+    public static final int SCRIPT_DATA_ESCAPED_DASH = 62;
+
+    public static final int SCRIPT_DATA_ESCAPED_DASH_DASH = 63;
+
+    public static final int BOGUS_COMMENT_HYPHEN = 64;
+
+    public static final int RAWTEXT_RCDATA_LESS_THAN_SIGN = 65;
+
+    public static final int SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN = 66;
+
+    public static final int SCRIPT_DATA_DOUBLE_ESCAPE_START = 67;
+
+    public static final int SCRIPT_DATA_DOUBLE_ESCAPED = 68;
+
+    public static final int SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN = 69;
+
+    public static final int SCRIPT_DATA_DOUBLE_ESCAPED_DASH = 70;
+
+    public static final int SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH = 71;
+
+    public static final int SCRIPT_DATA_DOUBLE_ESCAPE_END = 72;
+
+    public static final int PROCESSING_INSTRUCTION = 73;
+
+    public static final int PROCESSING_INSTRUCTION_QUESTION_MARK = 74;
+
+    /**
+     * Magic value for UTF-16 operations.
+     */
+    private static final int LEAD_OFFSET = (0xD800 - (0x10000 >> 10));
+
+    /**
+     * UTF-16 code unit array containing less than and greater than for emitting
+     * those characters on certain parse errors.
+     */
+    private static final @NoLength char[] LT_GT = { '<', '>' };
+
+    /**
+     * UTF-16 code unit array containing less than and solidus for emitting
+     * those characters on certain parse errors.
+     */
+    private static final @NoLength char[] LT_SOLIDUS = { '<', '/' };
+
+    /**
+     * UTF-16 code unit array containing ]] for emitting those characters on
+     * state transitions.
+     */
+    private static final @NoLength char[] RSQB_RSQB = { ']', ']' };
+
+    /**
+     * Array version of U+FFFD.
+     */
+    private static final @NoLength char[] REPLACEMENT_CHARACTER = { '\uFFFD' };
+
+    // [NOCPP[
+
+    /**
+     * Array version of space.
+     */
+    private static final @NoLength char[] SPACE = { ' ' };
+
+    // ]NOCPP]
+
+    /**
+     * Array version of line feed.
+     */
+    private static final @NoLength char[] LF = { '\n' };
+
+    /**
+     * "CDATA[" as <code>char[]</code>
+     */
+    private static final @NoLength char[] CDATA_LSQB = { 'C', 'D', 'A', 'T',
+            'A', '[' };
+
+    /**
+     * "octype" as <code>char[]</code>
+     */
+    private static final @NoLength char[] OCTYPE = { 'o', 'c', 't', 'y', 'p',
+            'e' };
+
+    /**
+     * "ublic" as <code>char[]</code>
+     */
+    private static final @NoLength char[] UBLIC = { 'u', 'b', 'l', 'i', 'c' };
+
+    /**
+     * "ystem" as <code>char[]</code>
+     */
+    private static final @NoLength char[] YSTEM = { 'y', 's', 't', 'e', 'm' };
+
+    private static final char[] TITLE_ARR = { 't', 'i', 't', 'l', 'e' };
+
+    private static final char[] SCRIPT_ARR = { 's', 'c', 'r', 'i', 'p', 't' };
+
+    private static final char[] STYLE_ARR = { 's', 't', 'y', 'l', 'e' };
+
+    private static final char[] PLAINTEXT_ARR = { 'p', 'l', 'a', 'i', 'n', 't',
+            'e', 'x', 't' };
+
+    private static final char[] XMP_ARR = { 'x', 'm', 'p' };
+
+    private static final char[] TEXTAREA_ARR = { 't', 'e', 'x', 't', 'a', 'r',
+            'e', 'a' };
+
+    private static final char[] IFRAME_ARR = { 'i', 'f', 'r', 'a', 'm', 'e' };
+
+    private static final char[] NOEMBED_ARR = { 'n', 'o', 'e', 'm', 'b', 'e',
+            'd' };
+
+    private static final char[] NOSCRIPT_ARR = { 'n', 'o', 's', 'c', 'r', 'i',
+            'p', 't' };
+
+    private static final char[] NOFRAMES_ARR = { 'n', 'o', 'f', 'r', 'a', 'm',
+            'e', 's' };
+
+    /**
+     * The token handler.
+     */
+    protected final TokenHandler tokenHandler;
+
+    protected EncodingDeclarationHandler encodingDeclarationHandler;
+
+    // [NOCPP[
+
+    /**
+     * The error handler.
+     */
+    protected ErrorHandler errorHandler;
+
+    // ]NOCPP]
+
+    /**
+     * Whether the previous char read was CR.
+     */
+    protected boolean lastCR;
+
+    protected int stateSave;
+
+    private int returnStateSave;
+
+    protected int index;
+
+    private boolean forceQuirks;
+
+    private char additional;
+
+    private int entCol;
+
+    private int firstCharKey;
+
+    private int lo;
+
+    private int hi;
+
+    private int candidate;
+
+    private int charRefBufMark;
+
+    protected int value;
+
+    private boolean seenDigits;
+
+    protected int cstart;
+
+    /**
+     * The SAX public id for the resource being tokenized. (Only passed to back
+     * as part of locator data.)
+     */
+    private String publicId;
+
+    /**
+     * The SAX system id for the resource being tokenized. (Only passed to back
+     * as part of locator data.)
+     */
+    private String systemId;
+
+    /**
+     * Buffer for bufferable things other than those that fit the description
+     * of <code>charRefBuf</code>.
+     */
+    private @Auto char[] strBuf;
+
+    /**
+     * Number of significant <code>char</code>s in <code>strBuf</code>.
+     */
+    private int strBufLen;
+
+    /**
+     * Buffer for characters that might form a character reference but may
+     * end up not forming one.
+     */
+    private final @Auto char[] charRefBuf;
+
+    /**
+     * Number of significant <code>char</code>s in <code>charRefBuf</code>.
+     */
+    private int charRefBufLen;
+
+    /**
+     * Buffer for expanding NCRs falling into the Basic Multilingual Plane.
+     */
+    private final @Auto char[] bmpChar;
+
+    /**
+     * Buffer for expanding astral NCRs.
+     */
+    private final @Auto char[] astralChar;
+
+    /**
+     * The element whose end tag closes the current CDATA or RCDATA element.
+     */
+    protected ElementName endTagExpectation = null;
+
+    private char[] endTagExpectationAsArray; // not @Auto!
+
+    /**
+     * <code>true</code> if tokenizing an end tag
+     */
+    protected boolean endTag;
+
+    /**
+     * The current tag token name.
+     */
+    private ElementName tagName = null;
+
+    /**
+     * The current attribute name.
+     */
+    protected AttributeName attributeName = null;
+
+    // [NOCPP[
+
+    /**
+     * Whether comment tokens are emitted.
+     */
+    private boolean wantsComments = false;
+
+    /**
+     * <code>true</code> when HTML4-specific additional errors are requested.
+     */
+    protected boolean html4;
+
+    /**
+     * Whether the stream is past the first 1024 bytes.
+     */
+    private boolean metaBoundaryPassed;
+
+    // ]NOCPP]
+
+    /**
+     * The name of the current doctype token.
+     */
+    private @Local String doctypeName;
+
+    /**
+     * The public id of the current doctype token.
+     */
+    private String publicIdentifier;
+
+    /**
+     * The system id of the current doctype token.
+     */
+    private String systemIdentifier;
+
+    /**
+     * The attribute holder.
+     */
+    private HtmlAttributes attributes;
+
+    // [NOCPP[
+
+    /**
+     * The policy for vertical tab and form feed.
+     */
+    private XmlViolationPolicy contentSpacePolicy = XmlViolationPolicy.ALTER_INFOSET;
+
+    /**
+     * The policy for comments.
+     */
+    private XmlViolationPolicy commentPolicy = XmlViolationPolicy.ALTER_INFOSET;
+
+    private XmlViolationPolicy xmlnsPolicy = XmlViolationPolicy.ALTER_INFOSET;
+
+    private XmlViolationPolicy namePolicy = XmlViolationPolicy.ALTER_INFOSET;
+
+    private boolean html4ModeCompatibleWithXhtml1Schemata;
+
+    private int mappingLangToXmlLang;
+
+    // ]NOCPP]
+
+    private final boolean newAttributesEachTime;
+
+    private boolean shouldSuspend;
+
+    protected boolean confident;
+
+    private int line;
+
+    /*
+     * The line number of the current attribute. First set to the line of the
+     * attribute name and if there is a value, set to the line the value
+     * started on.
+     */
+    // CPPONLY: private int attributeLine;
+
+    private Interner interner;
+
+    // CPPONLY: private boolean viewingXmlSource;
+
+    // [NOCPP[
+
+    protected LocatorImpl ampersandLocation;
+
+    public Tokenizer(TokenHandler tokenHandler, boolean newAttributesEachTime) {
+        this.tokenHandler = tokenHandler;
+        this.encodingDeclarationHandler = null;
+        this.newAttributesEachTime = newAttributesEachTime;
+        // &CounterClockwiseContourIntegral; is the longest valid char ref and
+        // the semicolon never gets appended to the buffer.
+        this.charRefBuf = new char[32];
+        this.bmpChar = new char[1];
+        this.astralChar = new char[2];
+        this.tagName = null;
+        this.attributeName = null;
+        this.doctypeName = null;
+        this.publicIdentifier = null;
+        this.systemIdentifier = null;
+        this.attributes = null;
+    }
+
+    // ]NOCPP]
+
+    /**
+     * The constructor.
+     *
+     * @param tokenHandler
+     *            the handler for receiving tokens
+     */
+    public Tokenizer(TokenHandler tokenHandler
+    // CPPONLY: , boolean viewingXmlSource
+    ) {
+        this.tokenHandler = tokenHandler;
+        this.encodingDeclarationHandler = null;
+        // [NOCPP[
+        this.newAttributesEachTime = false;
+        // ]NOCPP]
+        // &CounterClockwiseContourIntegral; is the longest valid char ref and
+        // the semicolon never gets appended to the buffer.
+        this.charRefBuf = new char[32];
+        this.bmpChar = new char[1];
+        this.astralChar = new char[2];
+        this.tagName = null;
+        this.attributeName = null;
+        this.doctypeName = null;
+        this.publicIdentifier = null;
+        this.systemIdentifier = null;
+        // [NOCPP[
+        this.attributes = null;
+        // ]NOCPP]
+        // CPPONLY: this.attributes = tokenHandler.HasBuilder() ? new HtmlAttributes(mappingLangToXmlLang) : null;
+        // CPPONLY: this.newAttributesEachTime = !tokenHandler.HasBuilder();
+        // CPPONLY: this.viewingXmlSource = viewingXmlSource;
+    }
+
+    public void setInterner(Interner interner) {
+        this.interner = interner;
+    }
+
+    public void initLocation(String newPublicId, String newSystemId) {
+        this.systemId = newSystemId;
+        this.publicId = newPublicId;
+
+    }
+
+    // CPPONLY: boolean isViewingXmlSource() {
+    // CPPONLY: return viewingXmlSource;
+    // CPPONLY: }
+
+    // [NOCPP[
+
+    /**
+     * Returns the mappingLangToXmlLang.
+     *
+     * @return the mappingLangToXmlLang
+     */
+    public boolean isMappingLangToXmlLang() {
+        return mappingLangToXmlLang == AttributeName.HTML_LANG;
+    }
+
+    /**
+     * Sets the mappingLangToXmlLang.
+     *
+     * @param mappingLangToXmlLang
+     *            the mappingLangToXmlLang to set
+     */
+    public void setMappingLangToXmlLang(boolean mappingLangToXmlLang) {
+        this.mappingLangToXmlLang = mappingLangToXmlLang ? AttributeName.HTML_LANG
+                : AttributeName.HTML;
+    }
+
+    /**
+     * Sets the error handler.
+     *
+     * @see org.xml.sax.XMLReader#setErrorHandler(org.xml.sax.ErrorHandler)
+     */
+    public void setErrorHandler(ErrorHandler eh) {
+        this.errorHandler = eh;
+    }
+
+    public ErrorHandler getErrorHandler() {
+        return this.errorHandler;
+    }
+
+    /**
+     * Sets the commentPolicy.
+     *
+     * @param commentPolicy
+     *            the commentPolicy to set
+     */
+    public void setCommentPolicy(XmlViolationPolicy commentPolicy) {
+        this.commentPolicy = commentPolicy;
+    }
+
+    /**
+     * Sets the contentNonXmlCharPolicy.
+     *
+     * @param contentNonXmlCharPolicy
+     *            the contentNonXmlCharPolicy to set
+     */
+    public void setContentNonXmlCharPolicy(
+            XmlViolationPolicy contentNonXmlCharPolicy) {
+        if (contentNonXmlCharPolicy != XmlViolationPolicy.ALLOW) {
+            throw new IllegalArgumentException(
+                    "Must use ErrorReportingTokenizer to set contentNonXmlCharPolicy to non-ALLOW.");
+        }
+    }
+
+    /**
+     * Sets the contentSpacePolicy.
+     *
+     * @param contentSpacePolicy
+     *            the contentSpacePolicy to set
+     */
+    public void setContentSpacePolicy(XmlViolationPolicy contentSpacePolicy) {
+        this.contentSpacePolicy = contentSpacePolicy;
+    }
+
+    /**
+     * Sets the xmlnsPolicy.
+     *
+     * @param xmlnsPolicy
+     *            the xmlnsPolicy to set
+     */
+    public void setXmlnsPolicy(XmlViolationPolicy xmlnsPolicy) {
+        if (xmlnsPolicy == XmlViolationPolicy.FATAL) {
+            throw new IllegalArgumentException("Can't use FATAL here.");
+        }
+        this.xmlnsPolicy = xmlnsPolicy;
+    }
+
+    public void setNamePolicy(XmlViolationPolicy namePolicy) {
+        this.namePolicy = namePolicy;
+    }
+
+    /**
+     * Sets the html4ModeCompatibleWithXhtml1Schemata.
+     *
+     * @param html4ModeCompatibleWithXhtml1Schemata
+     *            the html4ModeCompatibleWithXhtml1Schemata to set
+     */
+    public void setHtml4ModeCompatibleWithXhtml1Schemata(
+            boolean html4ModeCompatibleWithXhtml1Schemata) {
+        this.html4ModeCompatibleWithXhtml1Schemata = html4ModeCompatibleWithXhtml1Schemata;
+    }
+
+    // ]NOCPP]
+
+    // For the token handler to call
+    /**
+     * Sets the tokenizer state and the associated element name. This should
+     * only ever used to put the tokenizer into one of the states that have
+     * a special end tag expectation.
+     *
+     * @param specialTokenizerState
+     *            the tokenizer state to set
+     */
+    public void setState(int specialTokenizerState) {
+        this.stateSave = specialTokenizerState;
+        this.endTagExpectation = null;
+        this.endTagExpectationAsArray = null;
+    }
+
+    // [NOCPP[
+
+    /**
+     * Sets the tokenizer state and the associated element name. This should
+     * only ever used to put the tokenizer into one of the states that have
+     * a special end tag expectation. For use from the tokenizer test harness.
+     *
+     * @param specialTokenizerState
+     *            the tokenizer state to set
+     * @param endTagExpectation
+     *            the expected end tag for transitioning back to normal
+     */
+    public void setStateAndEndTagExpectation(int specialTokenizerState,
+            @Local String endTagExpectation) {
+        this.stateSave = specialTokenizerState;
+        if (specialTokenizerState == Tokenizer.DATA) {
+            return;
+        }
+        @Auto char[] asArray = Portability.newCharArrayFromLocal(endTagExpectation);
+        this.endTagExpectation = ElementName.elementNameByBuffer(asArray, 0,
+                asArray.length, interner);
+        endTagExpectationToArray();
+    }
+
+    // ]NOCPP]
+
+    /**
+     * Sets the tokenizer state and the associated element name. This should
+     * only ever used to put the tokenizer into one of the states that have
+     * a special end tag expectation.
+     *
+     * @param specialTokenizerState
+     *            the tokenizer state to set
+     * @param endTagExpectation
+     *            the expected end tag for transitioning back to normal
+     */
+    public void setStateAndEndTagExpectation(int specialTokenizerState,
+            ElementName endTagExpectation) {
+        this.stateSave = specialTokenizerState;
+        this.endTagExpectation = endTagExpectation;
+        endTagExpectationToArray();
+    }
+
+    private void endTagExpectationToArray() {
+        switch (endTagExpectation.getGroup()) {
+            case TreeBuilder.TITLE:
+                endTagExpectationAsArray = TITLE_ARR;
+                return;
+            case TreeBuilder.SCRIPT:
+                endTagExpectationAsArray = SCRIPT_ARR;
+                return;
+            case TreeBuilder.STYLE:
+                endTagExpectationAsArray = STYLE_ARR;
+                return;
+            case TreeBuilder.PLAINTEXT:
+                endTagExpectationAsArray = PLAINTEXT_ARR;
+                return;
+            case TreeBuilder.XMP:
+                endTagExpectationAsArray = XMP_ARR;
+                return;
+            case TreeBuilder.TEXTAREA:
+                endTagExpectationAsArray = TEXTAREA_ARR;
+                return;
+            case TreeBuilder.IFRAME:
+                endTagExpectationAsArray = IFRAME_ARR;
+                return;
+            case TreeBuilder.NOEMBED:
+                endTagExpectationAsArray = NOEMBED_ARR;
+                return;
+            case TreeBuilder.NOSCRIPT:
+                endTagExpectationAsArray = NOSCRIPT_ARR;
+                return;
+            case TreeBuilder.NOFRAMES:
+                endTagExpectationAsArray = NOFRAMES_ARR;
+                return;
+            default:
+                assert false: "Bad end tag expectation.";
+                return;
+        }
+    }
+
+    /**
+     * For C++ use only.
+     */
+    public void setLineNumber(int line) {
+        // CPPONLY: this.attributeLine = line; // XXX is this needed?
+        this.line = line;
+    }
+
+    // start Locator impl
+
+    /**
+     * @see org.xml.sax.Locator#getLineNumber()
+     */
+    @Inline public int getLineNumber() {
+        return line;
+    }
+
+    // [NOCPP[
+
+    /**
+     * @see org.xml.sax.Locator#getColumnNumber()
+     */
+    @Inline public int getColumnNumber() {
+        return -1;
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getPublicId()
+     */
+    public String getPublicId() {
+        return publicId;
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getSystemId()
+     */
+    public String getSystemId() {
+        return systemId;
+    }
+
+    // end Locator impl
+
+    // end public API
+
+    public void notifyAboutMetaBoundary() {
+        metaBoundaryPassed = true;
+    }
+
+    void turnOnAdditionalHtml4Errors() {
+        html4 = true;
+    }
+
+    // ]NOCPP]
+
+    HtmlAttributes emptyAttributes() {
+        // [NOCPP[
+        if (newAttributesEachTime) {
+            return new HtmlAttributes(mappingLangToXmlLang);
+        } else {
+            // ]NOCPP]
+            return HtmlAttributes.EMPTY_ATTRIBUTES;
+            // [NOCPP[
+        }
+        // ]NOCPP]
+    }
+
+    @Inline private void appendCharRefBuf(char c) {
+        // CPPONLY: assert charRefBufLen < charRefBuf.length:
+        // CPPONLY:     "RELEASE: Attempted to overrun charRefBuf!";
+        charRefBuf[charRefBufLen++] = c;
+    }
+
+    private void emitOrAppendCharRefBuf(int returnState) throws SAXException {
+        if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+            appendCharRefBufToStrBuf();
+        } else {
+            if (charRefBufLen > 0) {
+                tokenHandler.characters(charRefBuf, 0, charRefBufLen);
+                charRefBufLen = 0;
+            }
+        }
+    }
+
+    @Inline private void clearStrBufAfterUse() {
+        strBufLen = 0;
+    }
+
+    @Inline private void clearStrBufBeforeUse() {
+        assert strBufLen == 0: "strBufLen not reset after previous use!";
+        strBufLen = 0; // no-op in the absence of bugs
+    }
+
+    @Inline private void clearStrBufAfterOneHyphen() {
+        assert strBufLen == 1: "strBufLen length not one!";
+        assert strBuf[0] == '-': "strBuf does not start with a hyphen!";
+        strBufLen = 0;
+    }
+
+    /**
+     * Appends to the buffer.
+     *
+     * @param c
+     *            the UTF-16 code unit to append
+     */
+    @Inline private void appendStrBuf(char c) {
+        // CPPONLY: assert strBufLen < strBuf.length: "Previous buffer length insufficient.";
+        // CPPONLY: if (strBufLen == strBuf.length) {
+        // CPPONLY:     if (!EnsureBufferSpace(1)) {
+        // CPPONLY:         assert false: "RELEASE: Unable to recover from buffer reallocation failure";
+        // CPPONLY:     } // TODO: Add telemetry when outer if fires but inner does not
+        // CPPONLY: }
+        strBuf[strBufLen++] = c;
+    }
+
+    /**
+     * The buffer as a String. Currently only used for error reporting.
+     *
+     * <p>
+     * C++ memory note: The return value must be released.
+     *
+     * @return the buffer as a string
+     */
+    protected String strBufToString() {
+        String str = Portability.newStringFromBuffer(strBuf, 0, strBufLen
+            // CPPONLY: , tokenHandler
+        );
+        clearStrBufAfterUse();
+        return str;
+    }
+
+    /**
+     * Returns the buffer as a local name. The return value is released in
+     * emitDoctypeToken().
+     *
+     * @return the buffer as local name
+     */
+    private void strBufToDoctypeName() {
+        doctypeName = Portability.newLocalNameFromBuffer(strBuf, 0, strBufLen,
+                interner);
+        clearStrBufAfterUse();
+    }
+
+    /**
+     * Emits the buffer as character tokens.
+     *
+     * @throws SAXException
+     *             if the token handler threw
+     */
+    private void emitStrBuf() throws SAXException {
+        if (strBufLen > 0) {
+            tokenHandler.characters(strBuf, 0, strBufLen);
+            clearStrBufAfterUse();
+        }
+    }
+
+    @Inline private void appendSecondHyphenToBogusComment() throws SAXException {
+        // [NOCPP[
+        switch (commentPolicy) {
+            case ALTER_INFOSET:
+                appendStrBuf(' ');
+                // FALLTHROUGH
+            case ALLOW:
+                warn("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment.");
+                // ]NOCPP]
+                appendStrBuf('-');
+                // [NOCPP[
+                break;
+            case FATAL:
+                fatal("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment.");
+                break;
+        }
+        // ]NOCPP]
+    }
+
+    // [NOCPP[
+    private void maybeAppendSpaceToBogusComment() throws SAXException {
+        switch (commentPolicy) {
+            case ALTER_INFOSET:
+                appendStrBuf(' ');
+                // FALLTHROUGH
+            case ALLOW:
+                warn("The document is not mappable to XML 1.0 due to a trailing hyphen in a comment.");
+                break;
+            case FATAL:
+                fatal("The document is not mappable to XML 1.0 due to a trailing hyphen in a comment.");
+                break;
+        }
+    }
+
+    // ]NOCPP]
+
+    @Inline private void adjustDoubleHyphenAndAppendToStrBufAndErr(char c)
+            throws SAXException {
+        errConsecutiveHyphens();
+        // [NOCPP[
+        switch (commentPolicy) {
+            case ALTER_INFOSET:
+                strBufLen--;
+                // WARNING!!! This expands the worst case of the buffer length
+                // given the length of input!
+                appendStrBuf(' ');
+                appendStrBuf('-');
+                // FALLTHROUGH
+            case ALLOW:
+                warn("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment.");
+                // ]NOCPP]
+                appendStrBuf(c);
+                // [NOCPP[
+                break;
+            case FATAL:
+                fatal("The document is not mappable to XML 1.0 due to two consecutive hyphens in a comment.");
+                break;
+        }
+        // ]NOCPP]
+    }
+
+    private void appendStrBuf(@NoLength char[] buffer, int offset, int length) {
+        int newLen = strBufLen + length;
+        // CPPONLY: assert newLen <= strBuf.length: "Previous buffer length insufficient.";
+        // CPPONLY: if (strBuf.length < newLen) {
+        // CPPONLY:     if (!EnsureBufferSpace(length)) {
+        // CPPONLY:         assert false: "RELEASE: Unable to recover from buffer reallocation failure";
+        // CPPONLY:     } // TODO: Add telemetry when outer if fires but inner does not
+        // CPPONLY: }
+        System.arraycopy(buffer, offset, strBuf, strBufLen, length);
+        strBufLen = newLen;
+    }
+
+    /**
+     * Append the contents of the char reference buffer to the main one.
+     */
+    @Inline private void appendCharRefBufToStrBuf() {
+        appendStrBuf(charRefBuf, 0, charRefBufLen);
+        charRefBufLen = 0;
+    }
+
+    /**
+     * Emits the current comment token.
+     *
+     * @param pos
+     *            TODO
+     *
+     * @throws SAXException
+     */
+    private void emitComment(int provisionalHyphens, int pos)
+            throws SAXException {
+        // [NOCPP[
+        if (wantsComments) {
+            // ]NOCPP]
+            tokenHandler.comment(strBuf, 0, strBufLen
+                    - provisionalHyphens);
+            // [NOCPP[
+        }
+        // ]NOCPP]
+        clearStrBufAfterUse();
+        cstart = pos + 1;
+    }
+
+    /**
+     * Flushes coalesced character tokens.
+     *
+     * @param buf
+     *            TODO
+     * @param pos
+     *            TODO
+     *
+     * @throws SAXException
+     */
+    protected void flushChars(@NoLength char[] buf, int pos)
+            throws SAXException {
+        if (pos > cstart) {
+            tokenHandler.characters(buf, cstart, pos - cstart);
+        }
+        cstart = Integer.MAX_VALUE;
+    }
+
+    /**
+     * Reports an condition that would make the infoset incompatible with XML
+     * 1.0 as fatal.
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     * @throws SAXParseException
+     */
+    public void fatal(String message) throws SAXException {
+        SAXParseException spe = new SAXParseException(message, this);
+        if (errorHandler != null) {
+            errorHandler.fatalError(spe);
+        }
+        throw spe;
+    }
+
+    /**
+     * Reports a Parse Error.
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    public void err(String message) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(message, this);
+        errorHandler.error(spe);
+    }
+
+    public void errTreeBuilder(String message) throws SAXException {
+        ErrorHandler eh = null;
+        if (tokenHandler instanceof TreeBuilder<?>) {
+            TreeBuilder<?> treeBuilder = (TreeBuilder<?>) tokenHandler;
+            eh = treeBuilder.getErrorHandler();
+        }
+        if (eh == null) {
+            eh = errorHandler;
+        }
+        if (eh == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(message, this);
+        eh.error(spe);
+    }
+
+    /**
+     * Reports a warning
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    public void warn(String message) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(message, this);
+        errorHandler.warning(spe);
+    }
+
+    private void strBufToElementNameString() {
+        tagName = ElementName.elementNameByBuffer(strBuf, 0, strBufLen,
+                interner);
+        clearStrBufAfterUse();
+    }
+
+    private int emitCurrentTagToken(boolean selfClosing, int pos)
+            throws SAXException {
+        cstart = pos + 1;
+        maybeErrSlashInEndTag(selfClosing);
+        stateSave = Tokenizer.DATA;
+        HtmlAttributes attrs = (attributes == null ? HtmlAttributes.EMPTY_ATTRIBUTES
+                : attributes);
+        if (endTag) {
+            /*
+             * When an end tag token is emitted, the content model flag must be
+             * switched to the PCDATA state.
+             */
+            maybeErrAttributesOnEndTag(attrs);
+            // CPPONLY: if (!viewingXmlSource) {
+            tokenHandler.endTag(tagName);
+            // CPPONLY: }
+            // CPPONLY: if (newAttributesEachTime) {
+            // CPPONLY:   Portability.delete(attributes);
+            // CPPONLY:   attributes = null;
+            // CPPONLY: }
+        } else {
+            // CPPONLY: if (viewingXmlSource) {
+            // CPPONLY:   assert newAttributesEachTime;
+            // CPPONLY:   Portability.delete(attributes);
+            // CPPONLY:   attributes = null;
+            // CPPONLY: } else {
+            tokenHandler.startTag(tagName, attrs, selfClosing);
+            // CPPONLY: }
+        }
+        tagName.release();
+        tagName = null;
+        if (newAttributesEachTime) {
+            attributes = null;
+        } else {
+            attributes.clear(mappingLangToXmlLang);
+        }
+        /*
+         * The token handler may have called setStateAndEndTagExpectation
+         * and changed stateSave since the start of this method.
+         */
+        return stateSave;
+    }
+
+    private void attributeNameComplete() throws SAXException {
+        attributeName = AttributeName.nameByBuffer(strBuf, 0, strBufLen
+        // [NOCPP[
+                , namePolicy != XmlViolationPolicy.ALLOW
+                // ]NOCPP]
+                , interner);
+        clearStrBufAfterUse();
+
+        if (attributes == null) {
+            attributes = new HtmlAttributes(mappingLangToXmlLang);
+        }
+
+        /*
+         * When the user agent leaves the attribute name state (and before
+         * emitting the tag token, if appropriate), the complete attribute's
+         * name must be compared to the other attributes on the same token; if
+         * there is already an attribute on the token with the exact same name,
+         * then this is a parse error and the new attribute must be dropped,
+         * along with the value that gets associated with it (if any).
+         */
+        if (attributes.contains(attributeName)) {
+            errDuplicateAttribute();
+            attributeName.release();
+            attributeName = null;
+        }
+    }
+
+    private void addAttributeWithoutValue() throws SAXException {
+        noteAttributeWithoutValue();
+
+        // [NOCPP[
+        if (metaBoundaryPassed && AttributeName.CHARSET == attributeName
+                && ElementName.META == tagName) {
+            err("A \u201Ccharset\u201D attribute on a \u201Cmeta\u201D element found after the first 512 bytes.");
+        }
+        // ]NOCPP]
+        if (attributeName != null) {
+            // [NOCPP[
+            if (html4) {
+                if (attributeName.isBoolean()) {
+                    if (html4ModeCompatibleWithXhtml1Schemata) {
+                        attributes.addAttribute(attributeName,
+                                attributeName.getLocal(AttributeName.HTML),
+                                xmlnsPolicy);
+                    } else {
+                        attributes.addAttribute(attributeName, "", xmlnsPolicy);
+                    }
+                } else {
+                    if (AttributeName.BORDER != attributeName) {
+                        err("Attribute value omitted for a non-boolean attribute. (HTML4-only error.)");
+                        attributes.addAttribute(attributeName, "", xmlnsPolicy);
+                    }
+                }
+            } else {
+                if (AttributeName.SRC == attributeName
+                        || AttributeName.HREF == attributeName) {
+                    warn("Attribute \u201C"
+                            + attributeName.getLocal(AttributeName.HTML)
+                            + "\u201D without an explicit value seen. The attribute may be dropped by IE7.");
+                }
+                // ]NOCPP]
+                attributes.addAttribute(attributeName,
+                        Portability.newEmptyString()
+                        // [NOCPP[
+                        , xmlnsPolicy
+                // ]NOCPP]
+                // CPPONLY: , attributeLine
+                );
+                // [NOCPP[
+            }
+            // ]NOCPP]
+            attributeName = null; // attributeName has been adopted by the
+            // |attributes| object
+        } else {
+            clearStrBufAfterUse();
+        }
+    }
+
+    private void addAttributeWithValue() throws SAXException {
+        // [NOCPP[
+        if (metaBoundaryPassed && ElementName.META == tagName
+                && AttributeName.CHARSET == attributeName) {
+            err("A \u201Ccharset\u201D attribute on a \u201Cmeta\u201D element found after the first 512 bytes.");
+        }
+        // ]NOCPP]
+        if (attributeName != null) {
+            String val = strBufToString(); // Ownership transferred to
+            // HtmlAttributes
+            // CPPONLY: if (mViewSource) {
+            // CPPONLY:   mViewSource.MaybeLinkifyAttributeValue(attributeName, val);
+            // CPPONLY: }
+            // [NOCPP[
+            if (!endTag && html4 && html4ModeCompatibleWithXhtml1Schemata
+                    && attributeName.isCaseFolded()) {
+                val = newAsciiLowerCaseStringFromString(val);
+            }
+            // ]NOCPP]
+            attributes.addAttribute(attributeName, val
+            // [NOCPP[
+                    , xmlnsPolicy
+            // ]NOCPP]
+            // CPPONLY: , attributeLine
+            );
+            attributeName = null; // attributeName has been adopted by the
+            // |attributes| object
+        } else {
+            // We have a duplicate attribute. Explicitly discard its value.
+            clearStrBufAfterUse();
+        }
+    }
+
+    // [NOCPP[
+
+    private static String newAsciiLowerCaseStringFromString(String str) {
+        if (str == null) {
+            return null;
+        }
+        char[] buf = new char[str.length()];
+        for (int i = 0; i < str.length(); i++) {
+            char c = str.charAt(i);
+            if (c >= 'A' && c <= 'Z') {
+                c += 0x20;
+            }
+            buf[i] = c;
+        }
+        return new String(buf);
+    }
+
+    protected void startErrorReporting() throws SAXException {
+
+    }
+
+    // ]NOCPP]
+
+    public void start() throws SAXException {
+        initializeWithoutStarting();
+        tokenHandler.startTokenization(this);
+        // [NOCPP[
+        startErrorReporting();
+        // ]NOCPP]
+    }
+
+    public boolean tokenizeBuffer(UTF16Buffer buffer) throws SAXException {
+        int state = stateSave;
+        int returnState = returnStateSave;
+        char c = '\u0000';
+        shouldSuspend = false;
+        lastCR = false;
+
+        int start = buffer.getStart();
+        int end = buffer.getEnd();
+
+        // In C++, the caller of tokenizeBuffer needs to do this explicitly.
+        // [NOCPP[
+        ensureBufferSpace(end - start);
+        // ]NOCPP]
+
+        /**
+         * The index of the last <code>char</code> read from <code>buf</code>.
+         */
+        int pos = start - 1;
+
+        /**
+         * The index of the first <code>char</code> in <code>buf</code> that is
+         * part of a coalesced run of character tokens or
+         * <code>Integer.MAX_VALUE</code> if there is not a current run being
+         * coalesced.
+         */
+        switch (state) {
+            case DATA:
+            case RCDATA:
+            case SCRIPT_DATA:
+            case PLAINTEXT:
+            case RAWTEXT:
+            case CDATA_SECTION:
+            case SCRIPT_DATA_ESCAPED:
+            case SCRIPT_DATA_ESCAPE_START:
+            case SCRIPT_DATA_ESCAPE_START_DASH:
+            case SCRIPT_DATA_ESCAPED_DASH:
+            case SCRIPT_DATA_ESCAPED_DASH_DASH:
+            case SCRIPT_DATA_DOUBLE_ESCAPE_START:
+            case SCRIPT_DATA_DOUBLE_ESCAPED:
+            case SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN:
+            case SCRIPT_DATA_DOUBLE_ESCAPED_DASH:
+            case SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH:
+            case SCRIPT_DATA_DOUBLE_ESCAPE_END:
+                cstart = start;
+                break;
+            default:
+                cstart = Integer.MAX_VALUE;
+                break;
+        }
+
+        /**
+         * The number of <code>char</code>s in <code>buf</code> that have
+         * meaning. (The rest of the array is garbage and should not be
+         * examined.)
+         */
+        // CPPONLY: if (mViewSource) {
+        // CPPONLY:   mViewSource.SetBuffer(buffer);
+        // CPPONLY:   pos = stateLoop(state, c, pos, buffer.getBuffer(), false, returnState, buffer.getEnd());
+        // CPPONLY:   mViewSource.DropBuffer((pos == buffer.getEnd()) ? pos : pos + 1);
+        // CPPONLY: } else {
+        // CPPONLY:   pos = stateLoop(state, c, pos, buffer.getBuffer(), false, returnState, buffer.getEnd());
+        // CPPONLY: }
+        // [NOCPP[
+        pos = stateLoop(state, c, pos, buffer.getBuffer(), false, returnState,
+                end);
+        // ]NOCPP]
+        if (pos == end) {
+            // exiting due to end of buffer
+            buffer.setStart(pos);
+        } else {
+            buffer.setStart(pos + 1);
+        }
+        return lastCR;
+    }
+
+    // [NOCPP[
+    private void ensureBufferSpace(int inputLength) throws SAXException {
+        // Add 2 to account for emissions of LT_GT, LT_SOLIDUS and RSQB_RSQB.
+        // Adding to the general worst case instead of only the
+        // TreeBuilder-exposed worst case to avoid re-introducing a bug when
+        // unifying the tokenizer and tree builder buffers in the future.
+        int worstCase = strBufLen + inputLength + charRefBufLen + 2;
+        tokenHandler.ensureBufferSpace(worstCase);
+        if (commentPolicy == XmlViolationPolicy.ALTER_INFOSET) {
+            // When altering infoset, if the comment contents are consecutive
+            // hyphens, each hyphen generates a space, too. These buffer
+            // contents never get emitted as characters() to the tokenHandler,
+            // which is why this calculation happens after the call to
+            // ensureBufferSpace on tokenHandler.
+            worstCase *= 2;
+        }
+        if (strBuf == null) {
+            // Add an arbitrary small value to avoid immediate reallocation
+            // once there are a few characters in the buffer.
+            strBuf = new char[worstCase + 128];
+        } else if (worstCase > strBuf.length) {
+            // HotSpot reportedly allocates memory with 8-byte accuracy, so
+            // there's no point in trying to do math here to avoid slop.
+            // Maybe we should add some small constant to worstCase here
+            // but not doing that without profiling. In C++ with jemalloc,
+            // the corresponding method should do math to round up here
+            // to avoid slop.
+            char[] newBuf = new char[worstCase];
+            System.arraycopy(strBuf, 0, newBuf, 0, strBufLen);
+            strBuf = newBuf;
+        }
+    }
+    // ]NOCPP]
+
+    @SuppressWarnings("unused") private int stateLoop(int state, char c,
+            int pos, @NoLength char[] buf, boolean reconsume, int returnState,
+            int endPos) throws SAXException {
+        /*
+         * Idioms used in this code:
+         *
+         *
+         * Consuming the next input character
+         *
+         * To consume the next input character, the code does this: if (++pos ==
+         * endPos) { break stateloop; } c = checkChar(buf, pos);
+         *
+         *
+         * Staying in a state
+         *
+         * When there's a state that the tokenizer may stay in over multiple
+         * input characters, the state has a wrapper |for(;;)| loop and staying
+         * in the state continues the loop.
+         *
+         *
+         * Switching to another state
+         *
+         * To switch to another state, the code sets the state variable to the
+         * magic number of the new state. Then it either continues stateloop or
+         * breaks out of the state's own wrapper loop if the target state is
+         * right after the current state in source order. (This is a partial
+         * workaround for Java's lack of goto.)
+         *
+         *
+         * Reconsume support
+         *
+         * The spec sometimes says that an input character is reconsumed in
+         * another state. If a state can ever be entered so that an input
+         * character can be reconsumed in it, the state's code starts with an
+         * |if (reconsume)| that sets reconsume to false and skips over the
+         * normal code for consuming a new character.
+         *
+         * To reconsume the current character in another state, the code sets
+         * |reconsume| to true and then switches to the other state.
+         *
+         *
+         * Emitting character tokens
+         *
+         * This method emits character tokens lazily. Whenever a new range of
+         * character tokens starts, the field cstart must be set to the start
+         * index of the range. The flushChars() method must be called at the end
+         * of a range to flush it.
+         *
+         *
+         * U+0000 handling
+         *
+         * The various states have to handle the replacement of U+0000 with
+         * U+FFFD. However, if U+0000 would be reconsumed in another state, the
+         * replacement doesn't need to happen, because it's handled by the
+         * reconsuming state.
+         *
+         *
+         * LF handling
+         *
+         * Every state needs to increment the line number upon LF unless the LF
+         * gets reconsumed by another state which increments the line number.
+         *
+         *
+         * CR handling
+         *
+         * Every state needs to handle CR unless the CR gets reconsumed and is
+         * handled by the reconsuming state. The CR needs to be handled as if it
+         * were and LF, the lastCR field must be set to true and then this
+         * method must return. The IO driver will then swallow the next
+         * character if it is an LF to coalesce CRLF.
+         */
+        stateloop: for (;;) {
+            switch (state) {
+                case DATA:
+                    dataloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        switch (c) {
+                            case '&':
+                                /*
+                                 * U+0026 AMPERSAND (&) Switch to the character
+                                 * reference in data state.
+                                 */
+                                flushChars(buf, pos);
+                                assert charRefBufLen == 0: "charRefBufLen not reset after previous use!";
+                                appendCharRefBuf(c);
+                                setAdditionalAndRememberAmpersandLocation('\u0000');
+                                returnState = state;
+                                state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos);
+                                continue stateloop;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Switch to the tag
+                                 * open state.
+                                 */
+                                flushChars(buf, pos);
+
+                                state = transition(state, Tokenizer.TAG_OPEN, reconsume, pos);
+                                break dataloop; // FALL THROUGH continue
+                            // stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the input character as a
+                                 * character token.
+                                 *
+                                 * Stay in the data state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case TAG_OPEN:
+                    tagopenloop: for (;;) {
+                        /*
+                         * The behavior of this state depends on the content
+                         * model flag.
+                         */
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * If the content model flag is set to the PCDATA state
+                         * Consume the next input character:
+                         */
+                        if (c >= 'A' && c <= 'Z') {
+                            /*
+                             * U+0041 LATIN CAPITAL LETTER A through to U+005A
+                             * LATIN CAPITAL LETTER Z Create a new start tag
+                             * token,
+                             */
+                            endTag = false;
+                            /*
+                             * set its tag name to the lowercase version of the
+                             * input character (add 0x0020 to the character's
+                             * code point),
+                             */
+                            clearStrBufBeforeUse();
+                            appendStrBuf((char) (c + 0x20));
+                            /* then switch to the tag name state. */
+                            state = transition(state, Tokenizer.TAG_NAME, reconsume, pos);
+                            /*
+                             * (Don't emit the token yet; further details will
+                             * be filled in before it is emitted.)
+                             */
+                            break tagopenloop;
+                            // continue stateloop;
+                        } else if (c >= 'a' && c <= 'z') {
+                            /*
+                             * U+0061 LATIN SMALL LETTER A through to U+007A
+                             * LATIN SMALL LETTER Z Create a new start tag
+                             * token,
+                             */
+                            endTag = false;
+                            /*
+                             * set its tag name to the input character,
+                             */
+                            clearStrBufBeforeUse();
+                            appendStrBuf(c);
+                            /* then switch to the tag name state. */
+                            state = transition(state, Tokenizer.TAG_NAME, reconsume, pos);
+                            /*
+                             * (Don't emit the token yet; further details will
+                             * be filled in before it is emitted.)
+                             */
+                            break tagopenloop;
+                            // continue stateloop;
+                        }
+                        switch (c) {
+                            case '!':
+                                /*
+                                 * U+0021 EXCLAMATION MARK (!) Switch to the
+                                 * markup declaration open state.
+                                 */
+                                state = transition(state, Tokenizer.MARKUP_DECLARATION_OPEN, reconsume, pos);
+                                continue stateloop;
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Switch to the close tag
+                                 * open state.
+                                 */
+                                state = transition(state, Tokenizer.CLOSE_TAG_OPEN, reconsume, pos);
+                                continue stateloop;
+                            case '?':
+                                // CPPONLY: if (viewingXmlSource) {
+                                // CPPONLY: state = transition(state,
+                                // CPPONLY: Tokenizer.PROCESSING_INSTRUCTION,
+                                // CPPONLY: reconsume,
+                                // CPPONLY: pos);
+                                // CPPONLY: continue stateloop;
+                                // CPPONLY: }
+                                /*
+                                 * U+003F QUESTION MARK (?) Parse error.
+                                 */
+                                errProcessingInstruction();
+                                /*
+                                 * Switch to the bogus comment state.
+                                 */
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Parse error.
+                                 */
+                                errLtGt();
+                                /*
+                                 * Emit a U+003C LESS-THAN SIGN character token
+                                 * and a U+003E GREATER-THAN SIGN character
+                                 * token.
+                                 */
+                                tokenHandler.characters(Tokenizer.LT_GT, 0, 2);
+                                /* Switch to the data state. */
+                                cstart = pos + 1;
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                /*
+                                 * Anything else Parse error.
+                                 */
+                                errBadCharAfterLt(c);
+                                /*
+                                 * Emit a U+003C LESS-THAN SIGN character token
+                                 */
+                                tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                                /*
+                                 * and reconsume the current input character in
+                                 * the data state.
+                                 */
+                                cstart = pos;
+                                reconsume = true;
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALL THROUGH DON'T REORDER
+                case TAG_NAME:
+                    tagnameloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                strBufToElementNameString();
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the before attribute name state.
+                                 */
+                                strBufToElementNameString();
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                break tagnameloop;
+                            // continue stateloop;
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Switch to the self-closing
+                                 * start tag state.
+                                 */
+                                strBufToElementNameString();
+                                state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * tag token.
+                                 */
+                                strBufToElementNameString();
+                                state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                if (shouldSuspend) {
+                                    break stateloop;
+                                }
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                if (c >= 'A' && c <= 'Z') {
+                                    /*
+                                     * U+0041 LATIN CAPITAL LETTER A through to
+                                     * U+005A LATIN CAPITAL LETTER Z Append the
+                                     * lowercase version of the current input
+                                     * character (add 0x0020 to the character's
+                                     * code point) to the current tag token's
+                                     * tag name.
+                                     */
+                                    c += 0x20;
+                                }
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current tag token's tag
+                                 * name.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the tag name state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BEFORE_ATTRIBUTE_NAME:
+                    beforeattributenameloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the before attribute name state.
+                                 */
+                                continue;
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Switch to the self-closing
+                                 * start tag state.
+                                 */
+                                state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * tag token.
+                                 */
+                                state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                if (shouldSuspend) {
+                                    break stateloop;
+                                }
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            case '\"':
+                            case '\'':
+                            case '<':
+                            case '=':
+                                /*
+                                 * U+0022 QUOTATION MARK (") U+0027 APOSTROPHE
+                                 * (') U+003C LESS-THAN SIGN (<) U+003D EQUALS
+                                 * SIGN (=) Parse error.
+                                 */
+                                errBadCharBeforeAttributeNameOrNull(c);
+                                /*
+                                 * Treat it as per the "anything else" entry
+                                 * below.
+                                 */
+                            default:
+                                /*
+                                 * Anything else Start a new attribute in the
+                                 * current tag token.
+                                 */
+                                if (c >= 'A' && c <= 'Z') {
+                                    /*
+                                     * U+0041 LATIN CAPITAL LETTER A through to
+                                     * U+005A LATIN CAPITAL LETTER Z Set that
+                                     * attribute's name to the lowercase version
+                                     * of the current input character (add
+                                     * 0x0020 to the character's code point)
+                                     */
+                                    c += 0x20;
+                                }
+                                // CPPONLY: attributeLine = line;
+                                /*
+                                 * Set that attribute's name to the current
+                                 * input character,
+                                 */
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                /*
+                                 * and its value to the empty string.
+                                 */
+                                // Will do later.
+                                /*
+                                 * Switch to the attribute name state.
+                                 */
+                                state = transition(state, Tokenizer.ATTRIBUTE_NAME, reconsume, pos);
+                                break beforeattributenameloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case ATTRIBUTE_NAME:
+                    attributenameloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                attributeNameComplete();
+                                state = transition(state, Tokenizer.AFTER_ATTRIBUTE_NAME, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the after attribute name state.
+                                 */
+                                attributeNameComplete();
+                                state = transition(state, Tokenizer.AFTER_ATTRIBUTE_NAME, reconsume, pos);
+                                continue stateloop;
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Switch to the self-closing
+                                 * start tag state.
+                                 */
+                                attributeNameComplete();
+                                addAttributeWithoutValue();
+                                state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos);
+                                continue stateloop;
+                            case '=':
+                                /*
+                                 * U+003D EQUALS SIGN (=) Switch to the before
+                                 * attribute value state.
+                                 */
+                                attributeNameComplete();
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_VALUE, reconsume, pos);
+                                break attributenameloop;
+                            // continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * tag token.
+                                 */
+                                attributeNameComplete();
+                                addAttributeWithoutValue();
+                                state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                if (shouldSuspend) {
+                                    break stateloop;
+                                }
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            case '\"':
+                            case '\'':
+                            case '<':
+                                /*
+                                 * U+0022 QUOTATION MARK (") U+0027 APOSTROPHE
+                                 * (') U+003C LESS-THAN SIGN (<) Parse error.
+                                 */
+                                errQuoteOrLtInAttributeNameOrNull(c);
+                                /*
+                                 * Treat it as per the "anything else" entry
+                                 * below.
+                                 */
+                            default:
+                                if (c >= 'A' && c <= 'Z') {
+                                    /*
+                                     * U+0041 LATIN CAPITAL LETTER A through to
+                                     * U+005A LATIN CAPITAL LETTER Z Append the
+                                     * lowercase version of the current input
+                                     * character (add 0x0020 to the character's
+                                     * code point) to the current attribute's
+                                     * name.
+                                     */
+                                    c += 0x20;
+                                }
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current attribute's name.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the attribute name state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BEFORE_ATTRIBUTE_VALUE:
+                    beforeattributevalueloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the before attribute value state.
+                                 */
+                                continue;
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Switch to the
+                                 * attribute value (double-quoted) state.
+                                 */
+                                // CPPONLY: attributeLine = line;
+                                clearStrBufBeforeUse();
+                                state = transition(state, Tokenizer.ATTRIBUTE_VALUE_DOUBLE_QUOTED, reconsume, pos);
+                                break beforeattributevalueloop;
+                            // continue stateloop;
+                            case '&':
+                                /*
+                                 * U+0026 AMPERSAND (&) Switch to the attribute
+                                 * value (unquoted) state and reconsume this
+                                 * input character.
+                                 */
+                                // CPPONLY: attributeLine = line;
+                                clearStrBufBeforeUse();
+                                reconsume = true;
+                                state = transition(state, Tokenizer.ATTRIBUTE_VALUE_UNQUOTED, reconsume, pos);
+                                noteUnquotedAttributeValue();
+                                continue stateloop;
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Switch to the attribute
+                                 * value (single-quoted) state.
+                                 */
+                                // CPPONLY: attributeLine = line;
+                                clearStrBufBeforeUse();
+                                state = transition(state, Tokenizer.ATTRIBUTE_VALUE_SINGLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Parse error.
+                                 */
+                                errAttributeValueMissing();
+                                /*
+                                 * Emit the current tag token.
+                                 */
+                                addAttributeWithoutValue();
+                                state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                if (shouldSuspend) {
+                                    break stateloop;
+                                }
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            case '<':
+                            case '=':
+                            case '`':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) U+003D EQUALS SIGN
+                                 * (=) U+0060 GRAVE ACCENT (`)
+                                 */
+                                errLtOrEqualsOrGraveInUnquotedAttributeOrNull(c);
+                                /*
+                                 * Treat it as per the "anything else" entry
+                                 * below.
+                                 */
+                            default:
+                                // [NOCPP[
+                                errHtml4NonNameInUnquotedAttribute(c);
+                                // ]NOCPP]
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current attribute's value.
+                                 */
+                                // CPPONLY: attributeLine = line;
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                /*
+                                 * Switch to the attribute value (unquoted)
+                                 * state.
+                                 */
+
+                                state = transition(state, Tokenizer.ATTRIBUTE_VALUE_UNQUOTED, reconsume, pos);
+                                noteUnquotedAttributeValue();
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case ATTRIBUTE_VALUE_DOUBLE_QUOTED:
+                    attributevaluedoublequotedloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Switch to the after
+                                 * attribute value (quoted) state.
+                                 */
+                                addAttributeWithValue();
+
+                                state = transition(state, Tokenizer.AFTER_ATTRIBUTE_VALUE_QUOTED, reconsume, pos);
+                                break attributevaluedoublequotedloop;
+                            // continue stateloop;
+                            case '&':
+                                /*
+                                 * U+0026 AMPERSAND (&) Switch to the character
+                                 * reference in attribute value state, with the
+                                 * additional allowed character being U+0022
+                                 * QUOTATION MARK (").
+                                 */
+                                assert charRefBufLen == 0: "charRefBufLen not reset after previous use!";
+                                appendCharRefBuf(c);
+                                setAdditionalAndRememberAmpersandLocation('\"');
+                                returnState = state;
+                                state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current attribute's value.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the attribute value (double-quoted)
+                                 * state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case AFTER_ATTRIBUTE_VALUE_QUOTED:
+                    afterattributevaluequotedloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the before attribute name state.
+                                 */
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                continue stateloop;
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Switch to the self-closing
+                                 * start tag state.
+                                 */
+                                state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos);
+                                break afterattributevaluequotedloop;
+                            // continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * tag token.
+                                 */
+                                state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                if (shouldSuspend) {
+                                    break stateloop;
+                                }
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                continue stateloop;
+                            default:
+                                /*
+                                 * Anything else Parse error.
+                                 */
+                                errNoSpaceBetweenAttributes();
+                                /*
+                                 * Reconsume the character in the before
+                                 * attribute name state.
+                                 */
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case SELF_CLOSING_START_TAG:
+                    if (++pos == endPos) {
+                        break stateloop;
+                    }
+                    c = checkChar(buf, pos);
+                    /*
+                     * Consume the next input character:
+                     */
+                    switch (c) {
+                        case '>':
+                            /*
+                             * U+003E GREATER-THAN SIGN (>) Set the self-closing
+                             * flag of the current tag token. Emit the current
+                             * tag token.
+                             */
+                            // [NOCPP[
+                            errHtml4XmlVoidSyntax();
+                            // ]NOCPP]
+                            state = transition(state, emitCurrentTagToken(true, pos), reconsume, pos);
+                            if (shouldSuspend) {
+                                break stateloop;
+                            }
+                            /*
+                             * Switch to the data state.
+                             */
+                            continue stateloop;
+                        default:
+                            /* Anything else Parse error. */
+                            errSlashNotFollowedByGt();
+                            /*
+                             * Reconsume the character in the before attribute
+                             * name state.
+                             */
+                            reconsume = true;
+                            state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                            continue stateloop;
+                    }
+                    // XXX reorder point
+                case ATTRIBUTE_VALUE_UNQUOTED:
+                    for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                addAttributeWithValue();
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the before attribute name state.
+                                 */
+                                addAttributeWithValue();
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                continue stateloop;
+                            case '&':
+                                /*
+                                 * U+0026 AMPERSAND (&) Switch to the character
+                                 * reference in attribute value state, with the
+                                 * additional allowed character being U+003E
+                                 * GREATER-THAN SIGN (>)
+                                 */
+                                assert charRefBufLen == 0: "charRefBufLen not reset after previous use!";
+                                appendCharRefBuf(c);
+                                setAdditionalAndRememberAmpersandLocation('>');
+                                returnState = state;
+                                state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * tag token.
+                                 */
+                                addAttributeWithValue();
+                                state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                if (shouldSuspend) {
+                                    break stateloop;
+                                }
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            case '<':
+                            case '\"':
+                            case '\'':
+                            case '=':
+                            case '`':
+                                /*
+                                 * U+0022 QUOTATION MARK (") U+0027 APOSTROPHE
+                                 * (') U+003C LESS-THAN SIGN (<) U+003D EQUALS
+                                 * SIGN (=) U+0060 GRAVE ACCENT (`) Parse error.
+                                 */
+                                errUnquotedAttributeValOrNull(c);
+                                /*
+                                 * Treat it as per the "anything else" entry
+                                 * below.
+                                 */
+                                // fall through
+                            default:
+                                // [NOCPP]
+                                errHtml4NonNameInUnquotedAttribute(c);
+                                // ]NOCPP]
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current attribute's value.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the attribute value (unquoted) state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case AFTER_ATTRIBUTE_NAME:
+                    for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the after attribute name state.
+                                 */
+                                continue;
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Switch to the self-closing
+                                 * start tag state.
+                                 */
+                                addAttributeWithoutValue();
+                                state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos);
+                                continue stateloop;
+                            case '=':
+                                /*
+                                 * U+003D EQUALS SIGN (=) Switch to the before
+                                 * attribute value state.
+                                 */
+                                state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_VALUE, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * tag token.
+                                 */
+                                addAttributeWithoutValue();
+                                state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                if (shouldSuspend) {
+                                    break stateloop;
+                                }
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            case '\"':
+                            case '\'':
+                            case '<':
+                                errQuoteOrLtInAttributeNameOrNull(c);
+                                /*
+                                 * Treat it as per the "anything else" entry
+                                 * below.
+                                 */
+                            default:
+                                addAttributeWithoutValue();
+                                /*
+                                 * Anything else Start a new attribute in the
+                                 * current tag token.
+                                 */
+                                if (c >= 'A' && c <= 'Z') {
+                                    /*
+                                     * U+0041 LATIN CAPITAL LETTER A through to
+                                     * U+005A LATIN CAPITAL LETTER Z Set that
+                                     * attribute's name to the lowercase version
+                                     * of the current input character (add
+                                     * 0x0020 to the character's code point)
+                                     */
+                                    c += 0x20;
+                                }
+                                /*
+                                 * Set that attribute's name to the current
+                                 * input character,
+                                 */
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                /*
+                                 * and its value to the empty string.
+                                 */
+                                // Will do later.
+                                /*
+                                 * Switch to the attribute name state.
+                                 */
+                                state = transition(state, Tokenizer.ATTRIBUTE_NAME, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case MARKUP_DECLARATION_OPEN:
+                    markupdeclarationopenloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * If the next two characters are both U+002D
+                         * HYPHEN-MINUS characters (-), consume those two
+                         * characters, create a comment token whose data is the
+                         * empty string, and switch to the comment start state.
+                         *
+                         * Otherwise, if the next seven characters are an ASCII
+                         * case-insensitive match for the word "DOCTYPE", then
+                         * consume those characters and switch to the DOCTYPE
+                         * state.
+                         *
+                         * Otherwise, if the insertion mode is
+                         * "in foreign content" and the current node is not an
+                         * element in the HTML namespace and the next seven
+                         * characters are an case-sensitive match for the string
+                         * "[CDATA[" (the five uppercase letters "CDATA" with a
+                         * U+005B LEFT SQUARE BRACKET character before and
+                         * after), then consume those characters and switch to
+                         * the CDATA section state.
+                         *
+                         * Otherwise, is is a parse error. Switch to the bogus
+                         * comment state. The next character that is consumed,
+                         * if any, is the first character that will be in the
+                         * comment.
+                         */
+                        switch (c) {
+                            case '-':
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.MARKUP_DECLARATION_HYPHEN, reconsume, pos);
+                                break markupdeclarationopenloop;
+                            // continue stateloop;
+                            case 'd':
+                            case 'D':
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                index = 0;
+                                state = transition(state, Tokenizer.MARKUP_DECLARATION_OCTYPE, reconsume, pos);
+                                continue stateloop;
+                            case '[':
+                                if (tokenHandler.cdataSectionAllowed()) {
+                                    clearStrBufBeforeUse();
+                                    appendStrBuf(c);
+                                    index = 0;
+                                    state = transition(state, Tokenizer.CDATA_START, reconsume, pos);
+                                    continue stateloop;
+                                }
+                                // else fall through
+                            default:
+                                errBogusComment();
+                                clearStrBufBeforeUse();
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case MARKUP_DECLARATION_HYPHEN:
+                    markupdeclarationhyphenloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        switch (c) {
+                            case '-':
+                                clearStrBufAfterOneHyphen();
+                                state = transition(state, Tokenizer.COMMENT_START, reconsume, pos);
+                                break markupdeclarationhyphenloop;
+                            // continue stateloop;
+                            default:
+                                errBogusComment();
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT_START:
+                    commentstartloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Comment start state
+                         *
+                         *
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Switch to the comment
+                                 * start dash state.
+                                 */
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.COMMENT_START_DASH, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Parse error.
+                                 */
+                                errPrematureEndOfComment();
+                                /* Emit the comment token. */
+                                emitComment(0, pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                break commentstartloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the input character to
+                                 * the comment token's data.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Switch to the comment state.
+                                 */
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                break commentstartloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT:
+                    commentloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Comment state Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Switch to the comment
+                                 * end dash state
+                                 */
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.COMMENT_END_DASH, reconsume, pos);
+                                break commentloop;
+                            // continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the input character to
+                                 * the comment token's data.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the comment state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT_END_DASH:
+                    commentenddashloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Comment end dash state Consume the next input
+                         * character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Switch to the comment
+                                 * end state
+                                 */
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.COMMENT_END, reconsume, pos);
+                                break commentenddashloop;
+                            // continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append a U+002D HYPHEN-MINUS
+                                 * (-) character and the input character to the
+                                 * comment token's data.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Switch to the comment state.
+                                 */
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case COMMENT_END:
+                    commentendloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Comment end dash state Consume the next input
+                         * character:
+                         */
+                        switch (c) {
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the comment
+                                 * token.
+                                 */
+                                emitComment(2, pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '-':
+                                /* U+002D HYPHEN-MINUS (-) Parse error. */
+                                /*
+                                 * Append a U+002D HYPHEN-MINUS (-) character to
+                                 * the comment token's data.
+                                 */
+                                adjustDoubleHyphenAndAppendToStrBufAndErr(c);
+                                /*
+                                 * Stay in the comment end state.
+                                 */
+                                continue;
+                            case '\r':
+                                adjustDoubleHyphenAndAppendToStrBufCarriageReturn();
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                adjustDoubleHyphenAndAppendToStrBufLineFeed();
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                continue stateloop;
+                            case '!':
+                                errHyphenHyphenBang();
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.COMMENT_END_BANG, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Append two U+002D HYPHEN-MINUS (-) characters
+                                 * and the input character to the comment
+                                 * token's data.
+                                 */
+                                adjustDoubleHyphenAndAppendToStrBufAndErr(c);
+                                /*
+                                 * Switch to the comment state.
+                                 */
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case COMMENT_END_BANG:
+                    for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Comment end bang state
+                         *
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the comment
+                                 * token.
+                                 */
+                                emitComment(3, pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '-':
+                                /*
+                                 * Append two U+002D HYPHEN-MINUS (-) characters
+                                 * and a U+0021 EXCLAMATION MARK (!) character
+                                 * to the comment token's data.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Switch to the comment end dash state.
+                                 */
+                                state = transition(state, Tokenizer.COMMENT_END_DASH, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append two U+002D HYPHEN-MINUS
+                                 * (-) characters, a U+0021 EXCLAMATION MARK (!)
+                                 * character, and the input character to the
+                                 * comment token's data. Switch to the comment
+                                 * state.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Switch to the comment state.
+                                 */
+                                state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case COMMENT_START_DASH:
+                    if (++pos == endPos) {
+                        break stateloop;
+                    }
+                    c = checkChar(buf, pos);
+                    /*
+                     * Comment start dash state
+                     *
+                     * Consume the next input character:
+                     */
+                    switch (c) {
+                        case '-':
+                            /*
+                             * U+002D HYPHEN-MINUS (-) Switch to the comment end
+                             * state
+                             */
+                            appendStrBuf(c);
+                            state = transition(state, Tokenizer.COMMENT_END, reconsume, pos);
+                            continue stateloop;
+                        case '>':
+                            errPrematureEndOfComment();
+                            /* Emit the comment token. */
+                            emitComment(1, pos);
+                            /*
+                             * Switch to the data state.
+                             */
+                            state = transition(state, Tokenizer.DATA, reconsume, pos);
+                            continue stateloop;
+                        case '\r':
+                            appendStrBufCarriageReturn();
+                            state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                            break stateloop;
+                        case '\n':
+                            appendStrBufLineFeed();
+                            state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                            continue stateloop;
+                        case '\u0000':
+                            c = '\uFFFD';
+                            // fall thru
+                        default:
+                            /*
+                             * Append a U+002D HYPHEN-MINUS character (-) and
+                             * the current input character to the comment
+                             * token's data.
+                             */
+                            appendStrBuf(c);
+                            /*
+                             * Switch to the comment state.
+                             */
+                            state = transition(state, Tokenizer.COMMENT, reconsume, pos);
+                            continue stateloop;
+                    }
+                    // XXX reorder point
+                case CDATA_START:
+                    for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        if (index < 6) { // CDATA_LSQB.length
+                            if (c == Tokenizer.CDATA_LSQB[index]) {
+                                appendStrBuf(c);
+                            } else {
+                                errBogusComment();
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                            }
+                            index++;
+                            continue;
+                        } else {
+                            clearStrBufAfterUse();
+                            cstart = pos; // start coalescing
+                            reconsume = true;
+                            state = transition(state, Tokenizer.CDATA_SECTION, reconsume, pos);
+                            break; // FALL THROUGH continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case CDATA_SECTION:
+                    cdatasectionloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        switch (c) {
+                            case ']':
+                                flushChars(buf, pos);
+                                state = transition(state, Tokenizer.CDATA_RSQB, reconsume, pos);
+                                break cdatasectionloop; // FALL THROUGH
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            default:
+                                continue;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case CDATA_RSQB:
+                    cdatarsqb: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        switch (c) {
+                            case ']':
+                                state = transition(state, Tokenizer.CDATA_RSQB_RSQB, reconsume, pos);
+                                break cdatarsqb;
+                            default:
+                                tokenHandler.characters(Tokenizer.RSQB_RSQB, 0,
+                                        1);
+                                cstart = pos;
+                                reconsume = true;
+                                state = transition(state, Tokenizer.CDATA_SECTION, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case CDATA_RSQB_RSQB:
+                    cdatarsqbrsqb: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        switch (c) {
+                            case ']':
+                                // Saw a third ]. Emit one ] (logically the
+                                // first one) and stay in this state to
+                                // remember that the last two characters seen
+                                // have been ]].
+                                tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 1);
+                                continue;
+                            case '>':
+                                cstart = pos + 1;
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 2);
+                                cstart = pos;
+                                reconsume = true;
+                                state = transition(state, Tokenizer.CDATA_SECTION, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case ATTRIBUTE_VALUE_SINGLE_QUOTED:
+                    attributevaluesinglequotedloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Switch to the after
+                                 * attribute value (quoted) state.
+                                 */
+                                addAttributeWithValue();
+
+                                state = transition(state, Tokenizer.AFTER_ATTRIBUTE_VALUE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '&':
+                                /*
+                                 * U+0026 AMPERSAND (&) Switch to the character
+                                 * reference in attribute value state, with the
+                                 * + additional allowed character being U+0027
+                                 * APOSTROPHE (').
+                                 */
+                                assert charRefBufLen == 0: "charRefBufLen not reset after previous use!";
+                                appendCharRefBuf(c);
+                                setAdditionalAndRememberAmpersandLocation('\'');
+                                returnState = state;
+                                state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos);
+                                break attributevaluesinglequotedloop;
+                            // continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current attribute's value.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the attribute value (double-quoted)
+                                 * state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case CONSUME_CHARACTER_REFERENCE:
+                    if (++pos == endPos) {
+                        break stateloop;
+                    }
+                    c = checkChar(buf, pos);
+                    /*
+                     * Unlike the definition is the spec, this state does not
+                     * return a value and never requires the caller to
+                     * backtrack. This state takes care of emitting characters
+                     * or appending to the current attribute value. It also
+                     * takes care of that in the case when consuming the
+                     * character reference fails.
+                     */
+                    /*
+                     * This section defines how to consume a character
+                     * reference. This definition is used when parsing character
+                     * references in text and in attributes.
+                     *
+                     * The behavior depends on the identity of the next
+                     * character (the one immediately after the U+0026 AMPERSAND
+                     * character):
+                     */
+                    switch (c) {
+                        case ' ':
+                        case '\t':
+                        case '\n':
+                        case '\r': // we'll reconsume!
+                        case '\u000C':
+                        case '<':
+                        case '&':
+                        case '\u0000':
+                            emitOrAppendCharRefBuf(returnState);
+                            if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                cstart = pos;
+                            }
+                            reconsume = true;
+                            state = transition(state, returnState, reconsume, pos);
+                            continue stateloop;
+                        case '#':
+                            /*
+                             * U+0023 NUMBER SIGN (#) Consume the U+0023 NUMBER
+                             * SIGN.
+                             */
+                            appendCharRefBuf('#');
+                            state = transition(state, Tokenizer.CONSUME_NCR, reconsume, pos);
+                            continue stateloop;
+                        default:
+                            if (c == additional) {
+                                emitOrAppendCharRefBuf(returnState);
+                                reconsume = true;
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                            }
+                            if (c >= 'a' && c <= 'z') {
+                                firstCharKey = c - 'a' + 26;
+                            } else if (c >= 'A' && c <= 'Z') {
+                                firstCharKey = c - 'A';
+                            } else {
+                                // No match
+                                /*
+                                 * If no match can be made, then this is a parse
+                                 * error.
+                                 */
+                                errNoNamedCharacterMatch();
+                                emitOrAppendCharRefBuf(returnState);
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos;
+                                }
+                                reconsume = true;
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                            }
+                            // Didn't fail yet
+                            appendCharRefBuf(c);
+                            state = transition(state, Tokenizer.CHARACTER_REFERENCE_HILO_LOOKUP, reconsume, pos);
+                            // FALL THROUGH continue stateloop;
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case CHARACTER_REFERENCE_HILO_LOOKUP:
+                    {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * The data structure is as follows:
+                         *
+                         * HILO_ACCEL is a two-dimensional int array whose major
+                         * index corresponds to the second character of the
+                         * character reference (code point as index) and the
+                         * minor index corresponds to the first character of the
+                         * character reference (packed so that A-Z runs from 0
+                         * to 25 and a-z runs from 26 to 51). This layout makes
+                         * it easier to use the sparseness of the data structure
+                         * to omit parts of it: The second dimension of the
+                         * table is null when no character reference starts with
+                         * the character corresponding to that row.
+                         *
+                         * The int value HILO_ACCEL (by these indeces) is zero
+                         * if there exists no character reference starting with
+                         * that two-letter prefix. Otherwise, the value is an
+                         * int that packs two shorts so that the higher short is
+                         * the index of the highest character reference name
+                         * with that prefix in NAMES and the lower short
+                         * corresponds to the index of the lowest character
+                         * reference name with that prefix. (It happens that the
+                         * first two character reference names share their
+                         * prefix so the packed int cannot be 0 by packing the
+                         * two shorts.)
+                         *
+                         * NAMES is an array of byte arrays where each byte
+                         * array encodes the name of a character references as
+                         * ASCII. The names omit the first two letters of the
+                         * name. (Since storing the first two letters would be
+                         * redundant with the data contained in HILO_ACCEL.) The
+                         * entries are lexically sorted.
+                         *
+                         * For a given index in NAMES, the same index in VALUES
+                         * contains the corresponding expansion as an array of
+                         * two UTF-16 code units (either the character and
+                         * U+0000 or a suggogate pair).
+                         */
+                        int hilo = 0;
+                        if (c <= 'z') {
+                            @Const @NoLength int[] row = NamedCharactersAccel.HILO_ACCEL[c];
+                            if (row != null) {
+                                hilo = row[firstCharKey];
+                            }
+                        }
+                        if (hilo == 0) {
+                            /*
+                             * If no match can be made, then this is a parse
+                             * error.
+                             */
+                            errNoNamedCharacterMatch();
+                            emitOrAppendCharRefBuf(returnState);
+                            if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                cstart = pos;
+                            }
+                            reconsume = true;
+                            state = transition(state, returnState, reconsume, pos);
+                            continue stateloop;
+                        }
+                        // Didn't fail yet
+                        appendCharRefBuf(c);
+                        lo = hilo & 0xFFFF;
+                        hi = hilo >> 16;
+                        entCol = -1;
+                        candidate = -1;
+                        charRefBufMark = 0;
+                        state = transition(state, Tokenizer.CHARACTER_REFERENCE_TAIL, reconsume, pos);
+                        // FALL THROUGH continue stateloop;
+                    }
+                case CHARACTER_REFERENCE_TAIL:
+                    outer: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        entCol++;
+                        /*
+                         * Consume the maximum number of characters possible,
+                         * with the consumed characters matching one of the
+                         * identifiers in the first column of the named
+                         * character references table (in a case-sensitive
+                         * manner).
+                         */
+                        loloop: for (;;) {
+                            if (hi < lo) {
+                                break outer;
+                            }
+                            if (entCol == NamedCharacters.NAMES[lo].length()) {
+                                candidate = lo;
+                                charRefBufMark = charRefBufLen;
+                                lo++;
+                            } else if (entCol > NamedCharacters.NAMES[lo].length()) {
+                                break outer;
+                            } else if (c > NamedCharacters.NAMES[lo].charAt(entCol)) {
+                                lo++;
+                            } else {
+                                break loloop;
+                            }
+                        }
+
+                        hiloop: for (;;) {
+                            if (hi < lo) {
+                                break outer;
+                            }
+                            if (entCol == NamedCharacters.NAMES[hi].length()) {
+                                break hiloop;
+                            }
+                            if (entCol > NamedCharacters.NAMES[hi].length()) {
+                                break outer;
+                            } else if (c < NamedCharacters.NAMES[hi].charAt(entCol)) {
+                                hi--;
+                            } else {
+                                break hiloop;
+                            }
+                        }
+
+                        if (c == ';') {
+                            // If we see a semicolon, there cannot be a
+                            // longer match. Break the loop. However, before
+                            // breaking, take the longest match so far as the
+                            // candidate, if we are just about to complete a
+                            // match.
+                            if (entCol + 1 == NamedCharacters.NAMES[lo].length()) {
+                                candidate = lo;
+                                charRefBufMark = charRefBufLen;
+                            }
+                            break outer;
+                        }
+
+                        if (hi < lo) {
+                            break outer;
+                        }
+                        appendCharRefBuf(c);
+                        continue;
+                    }
+
+                    if (candidate == -1) {
+                        // reconsume deals with CR, LF or nul
+                        /*
+                         * If no match can be made, then this is a parse error.
+                         */
+                        errNoNamedCharacterMatch();
+                        emitOrAppendCharRefBuf(returnState);
+                        if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                            cstart = pos;
+                        }
+                        reconsume = true;
+                        state = transition(state, returnState, reconsume, pos);
+                        continue stateloop;
+                    } else {
+                        // c can't be CR, LF or nul if we got here
+                        @Const @CharacterName String candidateName = NamedCharacters.NAMES[candidate];
+                        if (candidateName.length() == 0
+                                || candidateName.charAt(candidateName.length() - 1) != ';') {
+                            /*
+                             * If the last character matched is not a U+003B
+                             * SEMICOLON (;), there is a parse error.
+                             */
+                            if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+                                /*
+                                 * If the entity is being consumed as part of an
+                                 * attribute, and the last character matched is
+                                 * not a U+003B SEMICOLON (;),
+                                 */
+                                char ch;
+                                if (charRefBufMark == charRefBufLen) {
+                                    ch = c;
+                                } else {
+                                    ch = charRefBuf[charRefBufMark];
+                                }
+                                if (ch == '=' || (ch >= '0' && ch <= '9')
+                                        || (ch >= 'A' && ch <= 'Z')
+                                        || (ch >= 'a' && ch <= 'z')) {
+                                    /*
+                                     * and the next character is either a U+003D
+                                     * EQUALS SIGN character (=) or in the range
+                                     * U+0030 DIGIT ZERO to U+0039 DIGIT NINE,
+                                     * U+0041 LATIN CAPITAL LETTER A to U+005A
+                                     * LATIN CAPITAL LETTER Z, or U+0061 LATIN
+                                     * SMALL LETTER A to U+007A LATIN SMALL
+                                     * LETTER Z, then, for historical reasons,
+                                     * all the characters that were matched
+                                     * after the U+0026 AMPERSAND (&) must be
+                                     * unconsumed, and nothing is returned.
+                                     */
+                                    errNoNamedCharacterMatch();
+                                    appendCharRefBufToStrBuf();
+                                    reconsume = true;
+                                    state = transition(state, returnState, reconsume, pos);
+                                    continue stateloop;
+                                }
+                            }
+                            if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+                                errUnescapedAmpersandInterpretedAsCharacterReference();
+                            } else {
+                                errNotSemicolonTerminated();
+                            }
+                        }
+
+                        /*
+                         * Otherwise, return a character token for the character
+                         * corresponding to the entity name (as given by the
+                         * second column of the named character references
+                         * table).
+                         */
+                        // CPPONLY: completedNamedCharacterReference();
+                        @Const @NoLength char[] val = NamedCharacters.VALUES[candidate];
+                        if (
+                        // [NOCPP[
+                        val.length == 1
+                        // ]NOCPP]
+                        // CPPONLY: val[1] == 0
+                        ) {
+                            emitOrAppendOne(val, returnState);
+                        } else {
+                            emitOrAppendTwo(val, returnState);
+                        }
+                        // this is so complicated!
+                        if (charRefBufMark < charRefBufLen) {
+                            if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+                                appendStrBuf(charRefBuf, charRefBufMark,
+                                        charRefBufLen - charRefBufMark);
+                            } else {
+                                tokenHandler.characters(charRefBuf, charRefBufMark,
+                                        charRefBufLen - charRefBufMark);
+                            }
+                        }
+                        // charRefBufLen will be zeroed below!
+
+                        // Check if we broke out early with c being the last
+                        // character that matched as opposed to being the
+                        // first one that didn't match. In the case of an
+                        // early break, the next run on text should start
+                        // *after* the current character and the current
+                        // character shouldn't be reconsumed.
+                        boolean earlyBreak = (c == ';' && charRefBufMark == charRefBufLen);
+                        charRefBufLen = 0;
+                        if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                            cstart = earlyBreak ? pos + 1 : pos;
+                        }
+                        reconsume = !earlyBreak;
+                        state = transition(state, returnState, reconsume, pos);
+                        continue stateloop;
+                        /*
+                         * If the markup contains I'm &notit; I tell you, the
+                         * entity is parsed as "not", as in, I'm ¬it; I tell
+                         * you. But if the markup was I'm &notin; I tell you,
+                         * the entity would be parsed as "notin;", resulting in
+                         * I'm ∉ I tell you.
+                         */
+                    }
+                    // XXX reorder point
+                case CONSUME_NCR:
+                    if (++pos == endPos) {
+                        break stateloop;
+                    }
+                    c = checkChar(buf, pos);
+                    value = 0;
+                    seenDigits = false;
+                    /*
+                     * The behavior further depends on the character after the
+                     * U+0023 NUMBER SIGN:
+                     */
+                    switch (c) {
+                        case 'x':
+                        case 'X':
+
+                            /*
+                             * U+0078 LATIN SMALL LETTER X U+0058 LATIN CAPITAL
+                             * LETTER X Consume the X.
+                             *
+                             * Follow the steps below, but using the range of
+                             * characters U+0030 DIGIT ZERO through to U+0039
+                             * DIGIT NINE, U+0061 LATIN SMALL LETTER A through
+                             * to U+0066 LATIN SMALL LETTER F, and U+0041 LATIN
+                             * CAPITAL LETTER A, through to U+0046 LATIN CAPITAL
+                             * LETTER F (in other words, 0-9, A-F, a-f).
+                             *
+                             * When it comes to interpreting the number,
+                             * interpret it as a hexadecimal number.
+                             */
+                            appendCharRefBuf(c);
+                            state = transition(state, Tokenizer.HEX_NCR_LOOP, reconsume, pos);
+                            continue stateloop;
+                        default:
+                            /*
+                             * Anything else Follow the steps below, but using
+                             * the range of characters U+0030 DIGIT ZERO through
+                             * to U+0039 DIGIT NINE (i.e. just 0-9).
+                             *
+                             * When it comes to interpreting the number,
+                             * interpret it as a decimal number.
+                             */
+                            reconsume = true;
+                            state = transition(state, Tokenizer.DECIMAL_NRC_LOOP, reconsume, pos);
+                            // FALL THROUGH continue stateloop;
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case DECIMAL_NRC_LOOP:
+                    decimalloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume as many characters as match the range of
+                         * characters given above.
+                         */
+                        assert value >= 0: "value must not become negative.";
+                        if (c >= '0' && c <= '9') {
+                            seenDigits = true;
+                            // Avoid overflow
+                            if (value <= 0x10FFFF) {
+                                value *= 10;
+                                value += c - '0';
+                            }
+                            continue;
+                        } else if (c == ';') {
+                            if (seenDigits) {
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos + 1;
+                                }
+                                state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos);
+                                // FALL THROUGH continue stateloop;
+                                break decimalloop;
+                            } else {
+                                errNoDigitsInNCR();
+                                appendCharRefBuf(';');
+                                emitOrAppendCharRefBuf(returnState);
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos + 1;
+                                }
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                            }
+                        } else {
+                            /*
+                             * If no characters match the range, then don't
+                             * consume any characters (and unconsume the U+0023
+                             * NUMBER SIGN character and, if appropriate, the X
+                             * character). This is a parse error; nothing is
+                             * returned.
+                             *
+                             * Otherwise, if the next character is a U+003B
+                             * SEMICOLON, consume that too. If it isn't, there
+                             * is a parse error.
+                             */
+                            if (!seenDigits) {
+                                errNoDigitsInNCR();
+                                emitOrAppendCharRefBuf(returnState);
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos;
+                                }
+                                reconsume = true;
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                            } else {
+                                errCharRefLacksSemicolon();
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos;
+                                }
+                                reconsume = true;
+                                state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos);
+                                // FALL THROUGH continue stateloop;
+                                break decimalloop;
+                            }
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case HANDLE_NCR_VALUE:
+                    // WARNING previous state sets reconsume
+                    // We are not going to emit the contents of charRefBuf.
+                    charRefBufLen = 0;
+                    // XXX inline this case if the method size can take it
+                    handleNcrValue(returnState);
+                    state = transition(state, returnState, reconsume, pos);
+                    continue stateloop;
+                    // XXX reorder point
+                case HEX_NCR_LOOP:
+                    for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume as many characters as match the range of
+                         * characters given above.
+                         */
+                        assert value >= 0: "value must not become negative.";
+                        if (c >= '0' && c <= '9') {
+                            seenDigits = true;
+                            // Avoid overflow
+                            if (value <= 0x10FFFF) {
+                                value *= 16;
+                                value += c - '0';
+                            }
+                            continue;
+                        } else if (c >= 'A' && c <= 'F') {
+                            seenDigits = true;
+                            // Avoid overflow
+                            if (value <= 0x10FFFF) {
+                                value *= 16;
+                                value += c - 'A' + 10;
+                            }
+                            continue;
+                        } else if (c >= 'a' && c <= 'f') {
+                            seenDigits = true;
+                            // Avoid overflow
+                            if (value <= 0x10FFFF) {
+                                value *= 16;
+                                value += c - 'a' + 10;
+                            }
+                            continue;
+                        } else if (c == ';') {
+                            if (seenDigits) {
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos + 1;
+                                }
+                                state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos);
+                                continue stateloop;
+                            } else {
+                                errNoDigitsInNCR();
+                                appendCharRefBuf(';');
+                                emitOrAppendCharRefBuf(returnState);
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos + 1;
+                                }
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                            }
+                        } else {
+                            /*
+                             * If no characters match the range, then don't
+                             * consume any characters (and unconsume the U+0023
+                             * NUMBER SIGN character and, if appropriate, the X
+                             * character). This is a parse error; nothing is
+                             * returned.
+                             *
+                             * Otherwise, if the next character is a U+003B
+                             * SEMICOLON, consume that too. If it isn't, there
+                             * is a parse error.
+                             */
+                            if (!seenDigits) {
+                                errNoDigitsInNCR();
+                                emitOrAppendCharRefBuf(returnState);
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos;
+                                }
+                                reconsume = true;
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                            } else {
+                                errCharRefLacksSemicolon();
+                                if ((returnState & DATA_AND_RCDATA_MASK) == 0) {
+                                    cstart = pos;
+                                }
+                                reconsume = true;
+                                state = transition(state, Tokenizer.HANDLE_NCR_VALUE, reconsume, pos);
+                                continue stateloop;
+                            }
+                        }
+                    }
+                    // XXX reorder point
+                case PLAINTEXT:
+                    plaintextloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        switch (c) {
+                            case '\u0000':
+                                emitPlaintextReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Stay in the
+                                 * RAWTEXT state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case CLOSE_TAG_OPEN:
+                    if (++pos == endPos) {
+                        break stateloop;
+                    }
+                    c = checkChar(buf, pos);
+                    /*
+                     * Otherwise, if the content model flag is set to the PCDATA
+                     * state, or if the next few characters do match that tag
+                     * name, consume the next input character:
+                     */
+                    switch (c) {
+                        case '>':
+                            /* U+003E GREATER-THAN SIGN (>) Parse error. */
+                            errLtSlashGt();
+                            /*
+                             * Switch to the data state.
+                             */
+                            cstart = pos + 1;
+                            state = transition(state, Tokenizer.DATA, reconsume, pos);
+                            continue stateloop;
+                        case '\r':
+                            silentCarriageReturn();
+                            /* Anything else Parse error. */
+                            errGarbageAfterLtSlash();
+                            /*
+                             * Switch to the bogus comment state.
+                             */
+                            clearStrBufBeforeUse();
+                            appendStrBuf('\n');
+                            state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                            break stateloop;
+                        case '\n':
+                            silentLineFeed();
+                            /* Anything else Parse error. */
+                            errGarbageAfterLtSlash();
+                            /*
+                             * Switch to the bogus comment state.
+                             */
+                            clearStrBufBeforeUse();
+                            appendStrBuf(c);
+                            state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                            continue stateloop;
+                        case '\u0000':
+                            c = '\uFFFD';
+                            // fall thru
+                        default:
+                            if (c >= 'A' && c <= 'Z') {
+                                c += 0x20;
+                            }
+                            if (c >= 'a' && c <= 'z') {
+                                /*
+                                 * U+0061 LATIN SMALL LETTER A through to U+007A
+                                 * LATIN SMALL LETTER Z Create a new end tag
+                                 * token,
+                                 */
+                                endTag = true;
+                                /*
+                                 * set its tag name to the input character,
+                                 */
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                /*
+                                 * then switch to the tag name state. (Don't
+                                 * emit the token yet; further details will be
+                                 * filled in before it is emitted.)
+                                 */
+                                state = transition(state, Tokenizer.TAG_NAME, reconsume, pos);
+                                continue stateloop;
+                            } else {
+                                /* Anything else Parse error. */
+                                errGarbageAfterLtSlash();
+                                /*
+                                 * Switch to the bogus comment state.
+                                 */
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                            }
+                    }
+                    // XXX reorder point
+                case RCDATA:
+                    rcdataloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        switch (c) {
+                            case '&':
+                                /*
+                                 * U+0026 AMPERSAND (&) Switch to the character
+                                 * reference in RCDATA state.
+                                 */
+                                flushChars(buf, pos);
+                                assert charRefBufLen == 0: "charRefBufLen not reset after previous use!";
+                                appendCharRefBuf(c);
+                                setAdditionalAndRememberAmpersandLocation('\u0000');
+                                returnState = state;
+                                state = transition(state, Tokenizer.CONSUME_CHARACTER_REFERENCE, reconsume, pos);
+                                continue stateloop;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Switch to the
+                                 * RCDATA less-than sign state.
+                                 */
+                                flushChars(buf, pos);
+
+                                returnState = state;
+                                state = transition(state, Tokenizer.RAWTEXT_RCDATA_LESS_THAN_SIGN, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Emit the current input character as a
+                                 * character token. Stay in the RCDATA state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case RAWTEXT:
+                    rawtextloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        switch (c) {
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Switch to the
+                                 * RAWTEXT less-than sign state.
+                                 */
+                                flushChars(buf, pos);
+
+                                returnState = state;
+                                state = transition(state, Tokenizer.RAWTEXT_RCDATA_LESS_THAN_SIGN, reconsume, pos);
+                                break rawtextloop;
+                            // FALL THRU continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Emit the current input character as a
+                                 * character token. Stay in the RAWTEXT state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // XXX fallthru don't reorder
+                case RAWTEXT_RCDATA_LESS_THAN_SIGN:
+                    rawtextrcdatalessthansignloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        switch (c) {
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Set the temporary buffer
+                                 * to the empty string. Switch to the script
+                                 * data end tag open state.
+                                 */
+                                index = 0;
+                                clearStrBufBeforeUse();
+                                state = transition(state, Tokenizer.NON_DATA_END_TAG_NAME, reconsume, pos);
+                                break rawtextrcdatalessthansignloop;
+                            // FALL THRU continue stateloop;
+                            default:
+                                /*
+                                 * Otherwise, emit a U+003C LESS-THAN SIGN
+                                 * character token
+                                 */
+                                tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                                /*
+                                 * and reconsume the current input character in
+                                 * the data state.
+                                 */
+                                cstart = pos;
+                                reconsume = true;
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // XXX fall thru. don't reorder.
+                case NON_DATA_END_TAG_NAME:
+                    for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * ASSERT! when entering this state, set index to 0 and
+                         * call clearStrBufBeforeUse(); Let's implement the above
+                         * without lookahead. strBuf is the 'temporary buffer'.
+                         */
+                        if (endTagExpectationAsArray == null) {
+                            tokenHandler.characters(Tokenizer.LT_SOLIDUS,
+                                    0, 2);
+                            cstart = pos;
+                            reconsume = true;
+                            state = transition(state, returnState, reconsume, pos);
+                            continue stateloop;
+                        } else if (index < endTagExpectationAsArray.length) {
+                            char e = endTagExpectationAsArray[index];
+                            char folded = c;
+                            if (c >= 'A' && c <= 'Z') {
+                                folded += 0x20;
+                            }
+                            if (folded != e) {
+                                // [NOCPP[
+                                errHtml4LtSlashInRcdata(folded);
+                                // ]NOCPP]
+                                tokenHandler.characters(Tokenizer.LT_SOLIDUS,
+                                        0, 2);
+                                emitStrBuf();
+                                cstart = pos;
+                                reconsume = true;
+                                state = transition(state, returnState, reconsume, pos);
+                                continue stateloop;
+                            }
+                            appendStrBuf(c);
+                            index++;
+                            continue;
+                        } else {
+                            endTag = true;
+                            // XXX replace contentModelElement with different
+                            // type
+                            tagName = endTagExpectation;
+                            switch (c) {
+                                case '\r':
+                                    silentCarriageReturn();
+                                    clearStrBufAfterUse(); // strBuf not used
+                                    state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                    break stateloop;
+                                case '\n':
+                                    silentLineFeed();
+                                    // fall thru
+                                case ' ':
+                                case '\t':
+                                case '\u000C':
+                                    /*
+                                     * U+0009 CHARACTER TABULATION U+000A LINE
+                                     * FEED (LF) U+000C FORM FEED (FF) U+0020
+                                     * SPACE If the current end tag token is an
+                                     * appropriate end tag token, then switch to
+                                     * the before attribute name state.
+                                     */
+                                    clearStrBufAfterUse(); // strBuf not used
+                                    state = transition(state, Tokenizer.BEFORE_ATTRIBUTE_NAME, reconsume, pos);
+                                    continue stateloop;
+                                case '/':
+                                    /*
+                                     * U+002F SOLIDUS (/) If the current end tag
+                                     * token is an appropriate end tag token,
+                                     * then switch to the self-closing start tag
+                                     * state.
+                                     */
+                                    clearStrBufAfterUse(); // strBuf not used
+                                    state = transition(state, Tokenizer.SELF_CLOSING_START_TAG, reconsume, pos);
+                                    continue stateloop;
+                                case '>':
+                                    /*
+                                     * U+003E GREATER-THAN SIGN (>) If the
+                                     * current end tag token is an appropriate
+                                     * end tag token, then emit the current tag
+                                     * token and switch to the data state.
+                                     */
+                                    clearStrBufAfterUse(); // strBuf not used
+                                    state = transition(state, emitCurrentTagToken(false, pos), reconsume, pos);
+                                    if (shouldSuspend) {
+                                        break stateloop;
+                                    }
+                                    continue stateloop;
+                                default:
+                                    /*
+                                     * Emit a U+003C LESS-THAN SIGN character
+                                     * token, a U+002F SOLIDUS character token,
+                                     * a character token for each of the
+                                     * characters in the temporary buffer (in
+                                     * the order they were added to the buffer),
+                                     * and reconsume the current input character
+                                     * in the RAWTEXT state.
+                                     */
+                                    // [NOCPP[
+                                    errWarnLtSlashInRcdata();
+                                    // ]NOCPP]
+                                    tokenHandler.characters(
+                                            Tokenizer.LT_SOLIDUS, 0, 2);
+                                    emitStrBuf();
+                                    cstart = pos; // don't drop the
+                                                  // character
+                                    reconsume = true;
+                                    state = transition(state, returnState, reconsume, pos);
+                                    continue stateloop;
+                            }
+                        }
+                    }
+                    // XXX reorder point
+                    // BEGIN HOTSPOT WORKAROUND
+                case BOGUS_COMMENT:
+                    boguscommentloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume every character up to and including the first
+                         * U+003E GREATER-THAN SIGN character (>) or the end of
+                         * the file (EOF), whichever comes first. Emit a comment
+                         * token whose data is the concatenation of all the
+                         * characters starting from and including the character
+                         * that caused the state machine to switch into the
+                         * bogus comment state, up to and including the
+                         * character immediately before the last consumed
+                         * character (i.e. up to the character just before the
+                         * U+003E or EOF character). (If the comment was started
+                         * by the end of the file (EOF), the token is empty.)
+                         *
+                         * Switch to the data state.
+                         *
+                         * If the end of the file was reached, reconsume the EOF
+                         * character.
+                         */
+                        switch (c) {
+                            case '>':
+                                emitComment(0, pos);
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '-':
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.BOGUS_COMMENT_HYPHEN, reconsume, pos);
+                                break boguscommentloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                appendStrBuf(c);
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BOGUS_COMMENT_HYPHEN:
+                    boguscommenthyphenloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        switch (c) {
+                            case '>':
+                                // [NOCPP[
+                                maybeAppendSpaceToBogusComment();
+                                // ]NOCPP]
+                                emitComment(0, pos);
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '-':
+                                appendSecondHyphenToBogusComment();
+                                continue boguscommenthyphenloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                appendStrBuf(c);
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case SCRIPT_DATA:
+                    scriptdataloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        switch (c) {
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Switch to the
+                                 * script data less-than sign state.
+                                 */
+                                flushChars(buf, pos);
+                                returnState = state;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_LESS_THAN_SIGN, reconsume, pos);
+                                break scriptdataloop; // FALL THRU continue
+                            // stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Stay in the
+                                 * script data state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_LESS_THAN_SIGN:
+                    scriptdatalessthansignloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        switch (c) {
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Set the temporary buffer
+                                 * to the empty string. Switch to the script
+                                 * data end tag open state.
+                                 */
+                                index = 0;
+                                clearStrBufBeforeUse();
+                                state = transition(state, Tokenizer.NON_DATA_END_TAG_NAME, reconsume, pos);
+                                continue stateloop;
+                            case '!':
+                                tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                                cstart = pos;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPE_START, reconsume, pos);
+                                break scriptdatalessthansignloop; // FALL THRU
+                            // continue
+                            // stateloop;
+                            default:
+                                /*
+                                 * Otherwise, emit a U+003C LESS-THAN SIGN
+                                 * character token
+                                 */
+                                tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                                /*
+                                 * and reconsume the current input character in
+                                 * the data state.
+                                 */
+                                cstart = pos;
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_ESCAPE_START:
+                    scriptdataescapestartloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Switch to the
+                                 * script data escape start dash state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPE_START_DASH, reconsume, pos);
+                                break scriptdataescapestartloop; // FALL THRU
+                            // continue
+                            // stateloop;
+                            default:
+                                /*
+                                 * Anything else Reconsume the current input
+                                 * character in the script data state.
+                                 */
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_ESCAPE_START_DASH:
+                    scriptdataescapestartdashloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Switch to the
+                                 * script data escaped dash dash state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_DASH_DASH, reconsume, pos);
+                                break scriptdataescapestartdashloop;
+                            // continue stateloop;
+                            default:
+                                /*
+                                 * Anything else Reconsume the current input
+                                 * character in the script data state.
+                                 */
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_ESCAPED_DASH_DASH:
+                    scriptdataescapeddashdashloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Stay in the
+                                 * script data escaped dash dash state.
+                                 */
+                                continue;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Switch to the
+                                 * script data escaped less-than sign state.
+                                 */
+                                flushChars(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit a U+003E
+                                 * GREATER-THAN SIGN character token. Switch to
+                                 * the script data state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                break scriptdataescapeddashdashloop;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Switch to the
+                                 * script data escaped state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                break scriptdataescapeddashdashloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_ESCAPED:
+                    scriptdataescapedloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Switch to the
+                                 * script data escaped dash state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_DASH, reconsume, pos);
+                                break scriptdataescapedloop; // FALL THRU
+                            // continue
+                            // stateloop;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Switch to the
+                                 * script data escaped less-than sign state.
+                                 */
+                                flushChars(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Stay in the
+                                 * script data escaped state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_ESCAPED_DASH:
+                    scriptdataescapeddashloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Switch to the
+                                 * script data escaped dash dash state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_DASH_DASH, reconsume, pos);
+                                continue stateloop;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Switch to the
+                                 * script data escaped less-than sign state.
+                                 */
+                                flushChars(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN, reconsume, pos);
+                                break scriptdataescapeddashloop;
+                            // continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Switch to the
+                                 * script data escaped state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN:
+                    scriptdataescapedlessthanloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Set the temporary buffer
+                                 * to the empty string. Switch to the script
+                                 * data escaped end tag open state.
+                                 */
+                                index = 0;
+                                clearStrBufBeforeUse();
+                                returnState = Tokenizer.SCRIPT_DATA_ESCAPED;
+                                state = transition(state, Tokenizer.NON_DATA_END_TAG_NAME, reconsume, pos);
+                                continue stateloop;
+                            case 'S':
+                            case 's':
+                                /*
+                                 * U+0041 LATIN CAPITAL LETTER A through to
+                                 * U+005A LATIN CAPITAL LETTER Z Emit a U+003C
+                                 * LESS-THAN SIGN character token and the
+                                 * current input character as a character token.
+                                 */
+                                tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                                cstart = pos;
+                                index = 1;
+                                /*
+                                 * Set the temporary buffer to the empty string.
+                                 * Append the lowercase version of the current
+                                 * input character (add 0x0020 to the
+                                 * character's code point) to the temporary
+                                 * buffer. Switch to the script data double
+                                 * escape start state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPE_START, reconsume, pos);
+                                break scriptdataescapedlessthanloop;
+                            // continue stateloop;
+                            default:
+                                /*
+                                 * Anything else Emit a U+003C LESS-THAN SIGN
+                                 * character token and reconsume the current
+                                 * input character in the script data escaped
+                                 * state.
+                                 */
+                                tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                                cstart = pos;
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_DOUBLE_ESCAPE_START:
+                    scriptdatadoubleescapestartloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        assert index > 0;
+                        if (index < 6) { // SCRIPT_ARR.length
+                            char folded = c;
+                            if (c >= 'A' && c <= 'Z') {
+                                folded += 0x20;
+                            }
+                            if (folded != Tokenizer.SCRIPT_ARR[index]) {
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                            }
+                            index++;
+                            continue;
+                        }
+                        switch (c) {
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                            case '/':
+                            case '>':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * U+002F SOLIDUS (/) U+003E GREATER-THAN SIGN
+                                 * (>) Emit the current input character as a
+                                 * character token. If the temporary buffer is
+                                 * the string "script", then switch to the
+                                 * script data double escaped state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                break scriptdatadoubleescapestartloop;
+                            // continue stateloop;
+                            default:
+                                /*
+                                 * Anything else Reconsume the current input
+                                 * character in the script data escaped state.
+                                 */
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_DOUBLE_ESCAPED:
+                    scriptdatadoubleescapedloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Switch to the
+                                 * script data double escaped dash state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_DASH, reconsume, pos);
+                                break scriptdatadoubleescapedloop; // FALL THRU
+                            // continue
+                            // stateloop;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Emit a U+003C
+                                 * LESS-THAN SIGN character token. Switch to the
+                                 * script data double escaped less-than sign
+                                 * state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                continue;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Stay in the
+                                 * script data double escaped state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_DOUBLE_ESCAPED_DASH:
+                    scriptdatadoubleescapeddashloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Switch to the
+                                 * script data double escaped dash dash state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH, reconsume, pos);
+                                break scriptdatadoubleescapeddashloop;
+                            // continue stateloop;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Emit a U+003C
+                                 * LESS-THAN SIGN character token. Switch to the
+                                 * script data double escaped less-than sign
+                                 * state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Switch to the
+                                 * script data double escaped state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_DOUBLE_ESCAPED_DASH_DASH:
+                    scriptdatadoubleescapeddashdashloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '-':
+                                /*
+                                 * U+002D HYPHEN-MINUS (-) Emit a U+002D
+                                 * HYPHEN-MINUS character token. Stay in the
+                                 * script data double escaped dash dash state.
+                                 */
+                                continue;
+                            case '<':
+                                /*
+                                 * U+003C LESS-THAN SIGN (<) Emit a U+003C
+                                 * LESS-THAN SIGN character token. Switch to the
+                                 * script data double escaped less-than sign
+                                 * state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN, reconsume, pos);
+                                break scriptdatadoubleescapeddashdashloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit a U+003E
+                                 * GREATER-THAN SIGN character token. Switch to
+                                 * the script data state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                emitReplacementCharacter(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            default:
+                                /*
+                                 * Anything else Emit the current input
+                                 * character as a character token. Switch to the
+                                 * script data double escaped state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_DOUBLE_ESCAPED_LESS_THAN_SIGN:
+                    scriptdatadoubleescapedlessthanloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '/':
+                                /*
+                                 * U+002F SOLIDUS (/) Emit a U+002F SOLIDUS
+                                 * character token. Set the temporary buffer to
+                                 * the empty string. Switch to the script data
+                                 * double escape end state.
+                                 */
+                                index = 0;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPE_END, reconsume, pos);
+                                break scriptdatadoubleescapedlessthanloop;
+                            default:
+                                /*
+                                 * Anything else Reconsume the current input
+                                 * character in the script data double escaped
+                                 * state.
+                                 */
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // WARNING FALLTHRU CASE TRANSITION: DON'T REORDER
+                case SCRIPT_DATA_DOUBLE_ESCAPE_END:
+                    scriptdatadoubleescapeendloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        if (index < 6) { // SCRIPT_ARR.length
+                            char folded = c;
+                            if (c >= 'A' && c <= 'Z') {
+                                folded += 0x20;
+                            }
+                            if (folded != Tokenizer.SCRIPT_ARR[index]) {
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                            }
+                            index++;
+                            continue;
+                        }
+                        switch (c) {
+                            case '\r':
+                                emitCarriageReturn(buf, pos);
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                            case '/':
+                            case '>':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * U+002F SOLIDUS (/) U+003E GREATER-THAN SIGN
+                                 * (>) Emit the current input character as a
+                                 * character token. If the temporary buffer is
+                                 * the string "script", then switch to the
+                                 * script data escaped state.
+                                 */
+                                state = transition(state, Tokenizer.SCRIPT_DATA_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                /*
+                                 * Reconsume the current input character in the
+                                 * script data double escaped state.
+                                 */
+                                reconsume = true;
+                                state = transition(state, Tokenizer.SCRIPT_DATA_DOUBLE_ESCAPED, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // XXX reorder point
+                case MARKUP_DECLARATION_OCTYPE:
+                    markupdeclarationdoctypeloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        if (index < 6) { // OCTYPE.length
+                            char folded = c;
+                            if (c >= 'A' && c <= 'Z') {
+                                folded += 0x20;
+                            }
+                            if (folded == Tokenizer.OCTYPE[index]) {
+                                appendStrBuf(c);
+                            } else {
+                                errBogusComment();
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BOGUS_COMMENT, reconsume, pos);
+                                continue stateloop;
+                            }
+                            index++;
+                            continue;
+                        } else {
+                            reconsume = true;
+                            state = transition(state, Tokenizer.DOCTYPE, reconsume, pos);
+                            break markupdeclarationdoctypeloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case DOCTYPE:
+                    doctypeloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        initDoctypeFields();
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                state = transition(state, Tokenizer.BEFORE_DOCTYPE_NAME, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the before DOCTYPE name state.
+                                 */
+                                state = transition(state, Tokenizer.BEFORE_DOCTYPE_NAME, reconsume, pos);
+                                break doctypeloop;
+                            // continue stateloop;
+                            default:
+                                /*
+                                 * Anything else Parse error.
+                                 */
+                                errMissingSpaceBeforeDoctypeName();
+                                /*
+                                 * Reconsume the current character in the before
+                                 * DOCTYPE name state.
+                                 */
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BEFORE_DOCTYPE_NAME, reconsume, pos);
+                                break doctypeloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BEFORE_DOCTYPE_NAME:
+                    beforedoctypenameloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the before DOCTYPE name state.
+                                 */
+                                continue;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Parse error.
+                                 */
+                                errNamelessDoctype();
+                                /*
+                                 * Create a new DOCTYPE token. Set its
+                                 * force-quirks flag to on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit the token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                if (c >= 'A' && c <= 'Z') {
+                                    /*
+                                     * U+0041 LATIN CAPITAL LETTER A through to
+                                     * U+005A LATIN CAPITAL LETTER Z Create a
+                                     * new DOCTYPE token. Set the token's name
+                                     * to the lowercase version of the input
+                                     * character (add 0x0020 to the character's
+                                     * code point).
+                                     */
+                                    c += 0x20;
+                                }
+                                /* Anything else Create a new DOCTYPE token. */
+                                /*
+                                 * Set the token's name name to the current
+                                 * input character.
+                                 */
+                                clearStrBufBeforeUse();
+                                appendStrBuf(c);
+                                /*
+                                 * Switch to the DOCTYPE name state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_NAME, reconsume, pos);
+                                break beforedoctypenameloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case DOCTYPE_NAME:
+                    doctypenameloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                strBufToDoctypeName();
+                                state = transition(state, Tokenizer.AFTER_DOCTYPE_NAME, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the after DOCTYPE name state.
+                                 */
+                                strBufToDoctypeName();
+                                state = transition(state, Tokenizer.AFTER_DOCTYPE_NAME, reconsume, pos);
+                                break doctypenameloop;
+                            // continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * DOCTYPE token.
+                                 */
+                                strBufToDoctypeName();
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * U+0041 LATIN CAPITAL LETTER A through to
+                                 * U+005A LATIN CAPITAL LETTER Z Append the
+                                 * lowercase version of the input character (add
+                                 * 0x0020 to the character's code point) to the
+                                 * current DOCTYPE token's name.
+                                 */
+                                if (c >= 'A' && c <= 'Z') {
+                                    c += 0x0020;
+                                }
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current DOCTYPE token's
+                                 * name.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the DOCTYPE name state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case AFTER_DOCTYPE_NAME:
+                    afterdoctypenameloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the after DOCTYPE name state.
+                                 */
+                                continue;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case 'p':
+                            case 'P':
+                                index = 0;
+                                state = transition(state, Tokenizer.DOCTYPE_UBLIC, reconsume, pos);
+                                break afterdoctypenameloop;
+                            // continue stateloop;
+                            case 's':
+                            case 'S':
+                                index = 0;
+                                state = transition(state, Tokenizer.DOCTYPE_YSTEM, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                /*
+                                 * Otherwise, this is the parse error.
+                                 */
+                                bogusDoctype();
+
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                // done by bogusDoctype();
+                                /*
+                                 * Switch to the bogus DOCTYPE state.
+                                 */
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case DOCTYPE_UBLIC:
+                    doctypeublicloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * If the six characters starting from the current input
+                         * character are an ASCII case-insensitive match for the
+                         * word "PUBLIC", then consume those characters and
+                         * switch to the before DOCTYPE public identifier state.
+                         */
+                        if (index < 5) { // UBLIC.length
+                            char folded = c;
+                            if (c >= 'A' && c <= 'Z') {
+                                folded += 0x20;
+                            }
+                            if (folded != Tokenizer.UBLIC[index]) {
+                                bogusDoctype();
+                                // forceQuirks = true;
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                            }
+                            index++;
+                            continue;
+                        } else {
+                            reconsume = true;
+                            state = transition(state, Tokenizer.AFTER_DOCTYPE_PUBLIC_KEYWORD, reconsume, pos);
+                            break doctypeublicloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case AFTER_DOCTYPE_PUBLIC_KEYWORD:
+                    afterdoctypepublickeywordloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                state = transition(state, Tokenizer.BEFORE_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the before DOCTYPE public
+                                 * identifier state.
+                                 */
+                                state = transition(state, Tokenizer.BEFORE_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos);
+                                break afterdoctypepublickeywordloop;
+                            // FALL THROUGH continue stateloop
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Parse Error.
+                                 */
+                                errNoSpaceBetweenDoctypePublicKeywordAndQuote();
+                                /*
+                                 * Set the DOCTYPE token's public identifier to
+                                 * the empty string (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE public identifier
+                                 * (double-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Parse Error.
+                                 */
+                                errNoSpaceBetweenDoctypePublicKeywordAndQuote();
+                                /*
+                                 * Set the DOCTYPE token's public identifier to
+                                 * the empty string (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE public identifier
+                                 * (single-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /* U+003E GREATER-THAN SIGN (>) Parse error. */
+                                errExpectedPublicId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                bogusDoctype();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                // done by bogusDoctype();
+                                /*
+                                 * Switch to the bogus DOCTYPE state.
+                                 */
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BEFORE_DOCTYPE_PUBLIC_IDENTIFIER:
+                    beforedoctypepublicidentifierloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the before DOCTYPE public identifier
+                                 * state.
+                                 */
+                                continue;
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Set the DOCTYPE
+                                 * token's public identifier to the empty string
+                                 * (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE public identifier
+                                 * (double-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos);
+                                break beforedoctypepublicidentifierloop;
+                            // continue stateloop;
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Set the DOCTYPE token's
+                                 * public identifier to the empty string (not
+                                 * missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE public identifier
+                                 * (single-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /* U+003E GREATER-THAN SIGN (>) Parse error. */
+                                errExpectedPublicId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                bogusDoctype();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                // done by bogusDoctype();
+                                /*
+                                 * Switch to the bogus DOCTYPE state.
+                                 */
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED:
+                    doctypepublicidentifierdoublequotedloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Switch to the after
+                                 * DOCTYPE public identifier state.
+                                 */
+                                publicIdentifier = strBufToString();
+                                state = transition(state, Tokenizer.AFTER_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos);
+                                break doctypepublicidentifierdoublequotedloop;
+                            // continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Parse error.
+                                 */
+                                errGtInPublicId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                publicIdentifier = strBufToString();
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current DOCTYPE token's
+                                 * public identifier.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the DOCTYPE public identifier
+                                 * (double-quoted) state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case AFTER_DOCTYPE_PUBLIC_IDENTIFIER:
+                    afterdoctypepublicidentifierloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                state = transition(state, Tokenizer.BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the between DOCTYPE public and
+                                 * system identifiers state.
+                                 */
+                                state = transition(state, Tokenizer.BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS, reconsume, pos);
+                                break afterdoctypepublicidentifierloop;
+                            // continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Parse error.
+                                 */
+                                errNoSpaceBetweenPublicAndSystemIds();
+                                /*
+                                 * Set the DOCTYPE token's system identifier to
+                                 * the empty string (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE system identifier
+                                 * (double-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Parse error.
+                                 */
+                                errNoSpaceBetweenPublicAndSystemIds();
+                                /*
+                                 * Set the DOCTYPE token's system identifier to
+                                 * the empty string (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE system identifier
+                                 * (single-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                bogusDoctype();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                // done by bogusDoctype();
+                                /*
+                                 * Switch to the bogus DOCTYPE state.
+                                 */
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS:
+                    betweendoctypepublicandsystemidentifiersloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the between DOCTYPE public and system
+                                 * identifiers state.
+                                 */
+                                continue;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Set the DOCTYPE
+                                 * token's system identifier to the empty string
+                                 * (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE system identifier
+                                 * (double-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos);
+                                break betweendoctypepublicandsystemidentifiersloop;
+                            // continue stateloop;
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Set the DOCTYPE token's
+                                 * system identifier to the empty string (not
+                                 * missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE system identifier
+                                 * (single-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                bogusDoctype();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                // done by bogusDoctype();
+                                /*
+                                 * Switch to the bogus DOCTYPE state.
+                                 */
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED:
+                    doctypesystemidentifierdoublequotedloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Switch to the after
+                                 * DOCTYPE system identifier state.
+                                 */
+                                systemIdentifier = strBufToString();
+                                state = transition(state, Tokenizer.AFTER_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Parse error.
+                                 */
+                                errGtInSystemId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                systemIdentifier = strBufToString();
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current DOCTYPE token's
+                                 * system identifier.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the DOCTYPE system identifier
+                                 * (double-quoted) state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case AFTER_DOCTYPE_SYSTEM_IDENTIFIER:
+                    afterdoctypesystemidentifierloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the after DOCTYPE system identifier state.
+                                 */
+                                continue;
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit the current
+                                 * DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                /*
+                                 * Switch to the bogus DOCTYPE state. (This does
+                                 * not set the DOCTYPE token's force-quirks flag
+                                 * to on.)
+                                 */
+                                bogusDoctypeWithoutQuirks();
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                break afterdoctypesystemidentifierloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BOGUS_DOCTYPE:
+                    for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '>':
+                                /*
+                                 * U+003E GREATER-THAN SIGN (>) Emit that
+                                 * DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Stay in the bogus DOCTYPE
+                                 * state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case DOCTYPE_YSTEM:
+                    doctypeystemloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Otherwise, if the six characters starting from the
+                         * current input character are an ASCII case-insensitive
+                         * match for the word "SYSTEM", then consume those
+                         * characters and switch to the before DOCTYPE system
+                         * identifier state.
+                         */
+                        if (index < 5) { // YSTEM.length
+                            char folded = c;
+                            if (c >= 'A' && c <= 'Z') {
+                                folded += 0x20;
+                            }
+                            if (folded != Tokenizer.YSTEM[index]) {
+                                bogusDoctype();
+                                reconsume = true;
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                            }
+                            index++;
+                            continue stateloop;
+                        } else {
+                            reconsume = true;
+                            state = transition(state, Tokenizer.AFTER_DOCTYPE_SYSTEM_KEYWORD, reconsume, pos);
+                            break doctypeystemloop;
+                            // continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case AFTER_DOCTYPE_SYSTEM_KEYWORD:
+                    afterdoctypesystemkeywordloop: for (;;) {
+                        if (reconsume) {
+                            reconsume = false;
+                        } else {
+                            if (++pos == endPos) {
+                                break stateloop;
+                            }
+                            c = checkChar(buf, pos);
+                        }
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                state = transition(state, Tokenizer.BEFORE_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos);
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE
+                                 * Switch to the before DOCTYPE public
+                                 * identifier state.
+                                 */
+                                state = transition(state, Tokenizer.BEFORE_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos);
+                                break afterdoctypesystemkeywordloop;
+                            // FALL THROUGH continue stateloop
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Parse Error.
+                                 */
+                                errNoSpaceBetweenDoctypeSystemKeywordAndQuote();
+                                /*
+                                 * Set the DOCTYPE token's system identifier to
+                                 * the empty string (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE public identifier
+                                 * (double-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Parse Error.
+                                 */
+                                errNoSpaceBetweenDoctypeSystemKeywordAndQuote();
+                                /*
+                                 * Set the DOCTYPE token's public identifier to
+                                 * the empty string (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE public identifier
+                                 * (single-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                /* U+003E GREATER-THAN SIGN (>) Parse error. */
+                                errExpectedPublicId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                bogusDoctype();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                // done by bogusDoctype();
+                                /*
+                                 * Switch to the bogus DOCTYPE state.
+                                 */
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case BEFORE_DOCTYPE_SYSTEM_IDENTIFIER:
+                    beforedoctypesystemidentifierloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\r':
+                                silentCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                silentLineFeed();
+                                // fall thru
+                            case ' ':
+                            case '\t':
+                            case '\u000C':
+                                /*
+                                 * U+0009 CHARACTER TABULATION U+000A LINE FEED
+                                 * (LF) U+000C FORM FEED (FF) U+0020 SPACE Stay
+                                 * in the before DOCTYPE system identifier
+                                 * state.
+                                 */
+                                continue;
+                            case '"':
+                                /*
+                                 * U+0022 QUOTATION MARK (") Set the DOCTYPE
+                                 * token's system identifier to the empty string
+                                 * (not missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE system identifier
+                                 * (double-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED, reconsume, pos);
+                                continue stateloop;
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Set the DOCTYPE token's
+                                 * system identifier to the empty string (not
+                                 * missing),
+                                 */
+                                clearStrBufBeforeUse();
+                                /*
+                                 * then switch to the DOCTYPE system identifier
+                                 * (single-quoted) state.
+                                 */
+                                state = transition(state, Tokenizer.DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED, reconsume, pos);
+                                break beforedoctypesystemidentifierloop;
+                            // continue stateloop;
+                            case '>':
+                                /* U+003E GREATER-THAN SIGN (>) Parse error. */
+                                errExpectedSystemId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            default:
+                                bogusDoctype();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                // done by bogusDoctype();
+                                /*
+                                 * Switch to the bogus DOCTYPE state.
+                                 */
+                                state = transition(state, Tokenizer.BOGUS_DOCTYPE, reconsume, pos);
+                                continue stateloop;
+                        }
+                    }
+                    // FALLTHRU DON'T REORDER
+                case DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED:
+                    for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Switch to the after
+                                 * DOCTYPE system identifier state.
+                                 */
+                                systemIdentifier = strBufToString();
+                                state = transition(state, Tokenizer.AFTER_DOCTYPE_SYSTEM_IDENTIFIER, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                errGtInSystemId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                systemIdentifier = strBufToString();
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current DOCTYPE token's
+                                 * system identifier.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the DOCTYPE system identifier
+                                 * (double-quoted) state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED:
+                    for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        /*
+                         * Consume the next input character:
+                         */
+                        switch (c) {
+                            case '\'':
+                                /*
+                                 * U+0027 APOSTROPHE (') Switch to the after
+                                 * DOCTYPE public identifier state.
+                                 */
+                                publicIdentifier = strBufToString();
+                                state = transition(state, Tokenizer.AFTER_DOCTYPE_PUBLIC_IDENTIFIER, reconsume, pos);
+                                continue stateloop;
+                            case '>':
+                                errGtInPublicId();
+                                /*
+                                 * Set the DOCTYPE token's force-quirks flag to
+                                 * on.
+                                 */
+                                forceQuirks = true;
+                                /*
+                                 * Emit that DOCTYPE token.
+                                 */
+                                publicIdentifier = strBufToString();
+                                emitDoctypeToken(pos);
+                                /*
+                                 * Switch to the data state.
+                                 */
+                                state = transition(state, Tokenizer.DATA, reconsume, pos);
+                                continue stateloop;
+                            case '\r':
+                                appendStrBufCarriageReturn();
+                                break stateloop;
+                            case '\n':
+                                appendStrBufLineFeed();
+                                continue;
+                            case '\u0000':
+                                c = '\uFFFD';
+                                // fall thru
+                            default:
+                                /*
+                                 * Anything else Append the current input
+                                 * character to the current DOCTYPE token's
+                                 * public identifier.
+                                 */
+                                appendStrBuf(c);
+                                /*
+                                 * Stay in the DOCTYPE public identifier
+                                 * (single-quoted) state.
+                                 */
+                                continue;
+                        }
+                    }
+                    // XXX reorder point
+                case PROCESSING_INSTRUCTION:
+                    processinginstructionloop: for (;;) {
+                        if (++pos == endPos) {
+                            break stateloop;
+                        }
+                        c = checkChar(buf, pos);
+                        switch (c) {
+                            case '?':
+                                state = transition(
+                                        state,
+                                        Tokenizer.PROCESSING_INSTRUCTION_QUESTION_MARK,
+                                        reconsume, pos);
+                                break processinginstructionloop;
+                            // continue stateloop;
+                            default:
+                                continue;
+                        }
+                    }
+                case PROCESSING_INSTRUCTION_QUESTION_MARK:
+                    if (++pos == endPos) {
+                        break stateloop;
+                    }
+                    c = checkChar(buf, pos);
+                    switch (c) {
+                        case '>':
+                            state = transition(state, Tokenizer.DATA,
+                                    reconsume, pos);
+                            continue stateloop;
+                        default:
+                            state = transition(state,
+                                    Tokenizer.PROCESSING_INSTRUCTION,
+                                    reconsume, pos);
+                            continue stateloop;
+                    }
+                    // END HOTSPOT WORKAROUND
+            }
+        }
+        flushChars(buf, pos);
+        /*
+         * if (prevCR && pos != endPos) { // why is this needed? pos--; col--; }
+         */
+        // Save locals
+        stateSave = state;
+        returnStateSave = returnState;
+        return pos;
+    }
+
+    // HOTSPOT WORKAROUND INSERTION POINT
+
+    // [NOCPP[
+
+    protected int transition(int from, int to, boolean reconsume, int pos) throws SAXException {
+        return to;
+    }
+
+    // ]NOCPP]
+
+    private void initDoctypeFields() {
+        // Discard the characters "DOCTYPE" accumulated as a potential bogus
+        // comment into strBuf.
+        clearStrBufAfterUse();
+        doctypeName = "";
+        if (systemIdentifier != null) {
+            Portability.releaseString(systemIdentifier);
+            systemIdentifier = null;
+        }
+        if (publicIdentifier != null) {
+            Portability.releaseString(publicIdentifier);
+            publicIdentifier = null;
+        }
+        forceQuirks = false;
+    }
+
+    @Inline private void adjustDoubleHyphenAndAppendToStrBufCarriageReturn()
+            throws SAXException {
+        silentCarriageReturn();
+        adjustDoubleHyphenAndAppendToStrBufAndErr('\n');
+    }
+
+    @Inline private void adjustDoubleHyphenAndAppendToStrBufLineFeed()
+            throws SAXException {
+        silentLineFeed();
+        adjustDoubleHyphenAndAppendToStrBufAndErr('\n');
+    }
+
+    @Inline private void appendStrBufLineFeed() {
+        silentLineFeed();
+        appendStrBuf('\n');
+    }
+
+    @Inline private void appendStrBufCarriageReturn() {
+        silentCarriageReturn();
+        appendStrBuf('\n');
+    }
+
+    @Inline protected void silentCarriageReturn() {
+        ++line;
+        lastCR = true;
+    }
+
+    @Inline protected void silentLineFeed() {
+        ++line;
+    }
+
+    private void emitCarriageReturn(@NoLength char[] buf, int pos)
+            throws SAXException {
+        silentCarriageReturn();
+        flushChars(buf, pos);
+        tokenHandler.characters(Tokenizer.LF, 0, 1);
+        cstart = Integer.MAX_VALUE;
+    }
+
+    private void emitReplacementCharacter(@NoLength char[] buf, int pos)
+            throws SAXException {
+        flushChars(buf, pos);
+        tokenHandler.zeroOriginatingReplacementCharacter();
+        cstart = pos + 1;
+    }
+
+    private void emitPlaintextReplacementCharacter(@NoLength char[] buf, int pos)
+            throws SAXException {
+        flushChars(buf, pos);
+        tokenHandler.characters(REPLACEMENT_CHARACTER, 0, 1);
+        cstart = pos + 1;
+    }
+
+    private void setAdditionalAndRememberAmpersandLocation(char add) {
+        additional = add;
+        // [NOCPP[
+        ampersandLocation = new LocatorImpl(this);
+        // ]NOCPP]
+    }
+
+    private void bogusDoctype() throws SAXException {
+        errBogusDoctype();
+        forceQuirks = true;
+    }
+
+    private void bogusDoctypeWithoutQuirks() throws SAXException {
+        errBogusDoctype();
+        forceQuirks = false;
+    }
+
+    private void handleNcrValue(int returnState) throws SAXException {
+        /*
+         * If one or more characters match the range, then take them all and
+         * interpret the string of characters as a number (either hexadecimal or
+         * decimal as appropriate).
+         */
+        if (value <= 0xFFFF) {
+            if (value >= 0x80 && value <= 0x9f) {
+                /*
+                 * If that number is one of the numbers in the first column of
+                 * the following table, then this is a parse error.
+                 */
+                errNcrInC1Range();
+                /*
+                 * Find the row with that number in the first column, and return
+                 * a character token for the Unicode character given in the
+                 * second column of that row.
+                 */
+                @NoLength char[] val = NamedCharacters.WINDOWS_1252[value - 0x80];
+                emitOrAppendOne(val, returnState);
+                // [NOCPP[
+            } else if (value == 0xC
+                    && contentSpacePolicy != XmlViolationPolicy.ALLOW) {
+                if (contentSpacePolicy == XmlViolationPolicy.ALTER_INFOSET) {
+                    emitOrAppendOne(Tokenizer.SPACE, returnState);
+                } else if (contentSpacePolicy == XmlViolationPolicy.FATAL) {
+                    fatal("A character reference expanded to a form feed which is not legal XML 1.0 white space.");
+                }
+                // ]NOCPP]
+            } else if (value == 0x0) {
+                errNcrZero();
+                emitOrAppendOne(Tokenizer.REPLACEMENT_CHARACTER, returnState);
+            } else if ((value & 0xF800) == 0xD800) {
+                errNcrSurrogate();
+                emitOrAppendOne(Tokenizer.REPLACEMENT_CHARACTER, returnState);
+            } else {
+                /*
+                 * Otherwise, return a character token for the Unicode character
+                 * whose code point is that number.
+                 */
+                char ch = (char) value;
+                // [NOCPP[
+                if (value == 0x0D) {
+                    errNcrCr();
+                } else if ((value <= 0x0008) || (value == 0x000B)
+                        || (value >= 0x000E && value <= 0x001F)) {
+                    ch = errNcrControlChar(ch);
+                } else if (value >= 0xFDD0 && value <= 0xFDEF) {
+                    errNcrUnassigned();
+                } else if ((value & 0xFFFE) == 0xFFFE) {
+                    ch = errNcrNonCharacter(ch);
+                } else if (value >= 0x007F && value <= 0x009F) {
+                    errNcrControlChar();
+                } else {
+                    maybeWarnPrivateUse(ch);
+                }
+                // ]NOCPP]
+                bmpChar[0] = ch;
+                emitOrAppendOne(bmpChar, returnState);
+            }
+        } else if (value <= 0x10FFFF) {
+            // [NOCPP[
+            maybeWarnPrivateUseAstral();
+            if ((value & 0xFFFE) == 0xFFFE) {
+                errAstralNonCharacter(value);
+            }
+            // ]NOCPP]
+            astralChar[0] = (char) (Tokenizer.LEAD_OFFSET + (value >> 10));
+            astralChar[1] = (char) (0xDC00 + (value & 0x3FF));
+            emitOrAppendTwo(astralChar, returnState);
+        } else {
+            errNcrOutOfRange();
+            emitOrAppendOne(Tokenizer.REPLACEMENT_CHARACTER, returnState);
+        }
+    }
+
+    public void eof() throws SAXException {
+        int state = stateSave;
+        int returnState = returnStateSave;
+
+        eofloop: for (;;) {
+            switch (state) {
+                case SCRIPT_DATA_LESS_THAN_SIGN:
+                case SCRIPT_DATA_ESCAPED_LESS_THAN_SIGN:
+                    /*
+                     * Otherwise, emit a U+003C LESS-THAN SIGN character token
+                     */
+                    tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                    /*
+                     * and reconsume the current input character in the data
+                     * state.
+                     */
+                    break eofloop;
+                case TAG_OPEN:
+                    /*
+                     * The behavior of this state depends on the content model
+                     * flag.
+                     */
+                    /*
+                     * Anything else Parse error.
+                     */
+                    errEofAfterLt();
+                    /*
+                     * Emit a U+003C LESS-THAN SIGN character token
+                     */
+                    tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                    /*
+                     * and reconsume the current input character in the data
+                     * state.
+                     */
+                    break eofloop;
+                case RAWTEXT_RCDATA_LESS_THAN_SIGN:
+                    /*
+                     * Emit a U+003C LESS-THAN SIGN character token
+                     */
+                    tokenHandler.characters(Tokenizer.LT_GT, 0, 1);
+                    /*
+                     * and reconsume the current input character in the RCDATA
+                     * state.
+                     */
+                    break eofloop;
+                case NON_DATA_END_TAG_NAME:
+                    /*
+                     * Emit a U+003C LESS-THAN SIGN character token, a U+002F
+                     * SOLIDUS character token,
+                     */
+                    tokenHandler.characters(Tokenizer.LT_SOLIDUS, 0, 2);
+                    /*
+                     * a character token for each of the characters in the
+                     * temporary buffer (in the order they were added to the
+                     * buffer),
+                     */
+                    emitStrBuf();
+                    /*
+                     * and reconsume the current input character in the RCDATA
+                     * state.
+                     */
+                    break eofloop;
+                case CLOSE_TAG_OPEN:
+                    /* EOF Parse error. */
+                    errEofAfterLt();
+                    /*
+                     * Emit a U+003C LESS-THAN SIGN character token and a U+002F
+                     * SOLIDUS character token.
+                     */
+                    tokenHandler.characters(Tokenizer.LT_SOLIDUS, 0, 2);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case TAG_NAME:
+                    /*
+                     * EOF Parse error.
+                     */
+                    errEofInTagName();
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case BEFORE_ATTRIBUTE_NAME:
+                case AFTER_ATTRIBUTE_VALUE_QUOTED:
+                case SELF_CLOSING_START_TAG:
+                    /* EOF Parse error. */
+                    errEofWithoutGt();
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case ATTRIBUTE_NAME:
+                    /*
+                     * EOF Parse error.
+                     */
+                    errEofInAttributeName();
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case AFTER_ATTRIBUTE_NAME:
+                case BEFORE_ATTRIBUTE_VALUE:
+                    /* EOF Parse error. */
+                    errEofWithoutGt();
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case ATTRIBUTE_VALUE_DOUBLE_QUOTED:
+                case ATTRIBUTE_VALUE_SINGLE_QUOTED:
+                case ATTRIBUTE_VALUE_UNQUOTED:
+                    /* EOF Parse error. */
+                    errEofInAttributeValue();
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case BOGUS_COMMENT:
+                    emitComment(0, 0);
+                    break eofloop;
+                case BOGUS_COMMENT_HYPHEN:
+                    // [NOCPP[
+                    maybeAppendSpaceToBogusComment();
+                    // ]NOCPP]
+                    emitComment(0, 0);
+                    break eofloop;
+                case MARKUP_DECLARATION_OPEN:
+                    errBogusComment();
+                    emitComment(0, 0);
+                    break eofloop;
+                case MARKUP_DECLARATION_HYPHEN:
+                    errBogusComment();
+                    emitComment(0, 0);
+                    break eofloop;
+                case MARKUP_DECLARATION_OCTYPE:
+                    if (index < 6) {
+                        errBogusComment();
+                        emitComment(0, 0);
+                    } else {
+                        /* EOF Parse error. */
+                        errEofInDoctype();
+                        /*
+                         * Create a new DOCTYPE token. Set its force-quirks flag
+                         * to on.
+                         */
+                        doctypeName = "";
+                        if (systemIdentifier != null) {
+                            Portability.releaseString(systemIdentifier);
+                            systemIdentifier = null;
+                        }
+                        if (publicIdentifier != null) {
+                            Portability.releaseString(publicIdentifier);
+                            publicIdentifier = null;
+                        }
+                        forceQuirks = true;
+                        /*
+                         * Emit the token.
+                         */
+                        emitDoctypeToken(0);
+                        /*
+                         * Reconsume the EOF character in the data state.
+                         */
+                        break eofloop;
+                    }
+                    break eofloop;
+                case COMMENT_START:
+                case COMMENT:
+                    /*
+                     * EOF Parse error.
+                     */
+                    errEofInComment();
+                    /* Emit the comment token. */
+                    emitComment(0, 0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case COMMENT_END:
+                    errEofInComment();
+                    /* Emit the comment token. */
+                    emitComment(2, 0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case COMMENT_END_DASH:
+                case COMMENT_START_DASH:
+                    errEofInComment();
+                    /* Emit the comment token. */
+                    emitComment(1, 0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case COMMENT_END_BANG:
+                    errEofInComment();
+                    /* Emit the comment token. */
+                    emitComment(3, 0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case DOCTYPE:
+                case BEFORE_DOCTYPE_NAME:
+                    errEofInDoctype();
+                    /*
+                     * Create a new DOCTYPE token. Set its force-quirks flag to
+                     * on.
+                     */
+                    forceQuirks = true;
+                    /*
+                     * Emit the token.
+                     */
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case DOCTYPE_NAME:
+                    errEofInDoctype();
+                    strBufToDoctypeName();
+                    /*
+                     * Set the DOCTYPE token's force-quirks flag to on.
+                     */
+                    forceQuirks = true;
+                    /*
+                     * Emit that DOCTYPE token.
+                     */
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case DOCTYPE_UBLIC:
+                case DOCTYPE_YSTEM:
+                case AFTER_DOCTYPE_NAME:
+                case AFTER_DOCTYPE_PUBLIC_KEYWORD:
+                case AFTER_DOCTYPE_SYSTEM_KEYWORD:
+                case BEFORE_DOCTYPE_PUBLIC_IDENTIFIER:
+                    errEofInDoctype();
+                    /*
+                     * Set the DOCTYPE token's force-quirks flag to on.
+                     */
+                    forceQuirks = true;
+                    /*
+                     * Emit that DOCTYPE token.
+                     */
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case DOCTYPE_PUBLIC_IDENTIFIER_DOUBLE_QUOTED:
+                case DOCTYPE_PUBLIC_IDENTIFIER_SINGLE_QUOTED:
+                    /* EOF Parse error. */
+                    errEofInPublicId();
+                    /*
+                     * Set the DOCTYPE token's force-quirks flag to on.
+                     */
+                    forceQuirks = true;
+                    /*
+                     * Emit that DOCTYPE token.
+                     */
+                    publicIdentifier = strBufToString();
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case AFTER_DOCTYPE_PUBLIC_IDENTIFIER:
+                case BEFORE_DOCTYPE_SYSTEM_IDENTIFIER:
+                case BETWEEN_DOCTYPE_PUBLIC_AND_SYSTEM_IDENTIFIERS:
+                    errEofInDoctype();
+                    /*
+                     * Set the DOCTYPE token's force-quirks flag to on.
+                     */
+                    forceQuirks = true;
+                    /*
+                     * Emit that DOCTYPE token.
+                     */
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case DOCTYPE_SYSTEM_IDENTIFIER_DOUBLE_QUOTED:
+                case DOCTYPE_SYSTEM_IDENTIFIER_SINGLE_QUOTED:
+                    /* EOF Parse error. */
+                    errEofInSystemId();
+                    /*
+                     * Set the DOCTYPE token's force-quirks flag to on.
+                     */
+                    forceQuirks = true;
+                    /*
+                     * Emit that DOCTYPE token.
+                     */
+                    systemIdentifier = strBufToString();
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case AFTER_DOCTYPE_SYSTEM_IDENTIFIER:
+                    errEofInDoctype();
+                    /*
+                     * Set the DOCTYPE token's force-quirks flag to on.
+                     */
+                    forceQuirks = true;
+                    /*
+                     * Emit that DOCTYPE token.
+                     */
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case BOGUS_DOCTYPE:
+                    /*
+                     * Emit that DOCTYPE token.
+                     */
+                    emitDoctypeToken(0);
+                    /*
+                     * Reconsume the EOF character in the data state.
+                     */
+                    break eofloop;
+                case CONSUME_CHARACTER_REFERENCE:
+                    /*
+                     * Unlike the definition is the spec, this state does not
+                     * return a value and never requires the caller to
+                     * backtrack. This state takes care of emitting characters
+                     * or appending to the current attribute value. It also
+                     * takes care of that in the case when consuming the entity
+                     * fails.
+                     */
+                    /*
+                     * This section defines how to consume an entity. This
+                     * definition is used when parsing entities in text and in
+                     * attributes.
+                     *
+                     * The behavior depends on the identity of the next
+                     * character (the one immediately after the U+0026 AMPERSAND
+                     * character):
+                     */
+
+                    emitOrAppendCharRefBuf(returnState);
+                    state = returnState;
+                    continue;
+                case CHARACTER_REFERENCE_HILO_LOOKUP:
+                    errNoNamedCharacterMatch();
+                    emitOrAppendCharRefBuf(returnState);
+                    state = returnState;
+                    continue;
+                case CHARACTER_REFERENCE_TAIL:
+                    outer: for (;;) {
+                        char c = '\u0000';
+                        entCol++;
+                        /*
+                         * Consume the maximum number of characters possible,
+                         * with the consumed characters matching one of the
+                         * identifiers in the first column of the named
+                         * character references table (in a case-sensitive
+                         * manner).
+                         */
+                        hiloop: for (;;) {
+                            if (hi == -1) {
+                                break hiloop;
+                            }
+                            if (entCol == NamedCharacters.NAMES[hi].length()) {
+                                break hiloop;
+                            }
+                            if (entCol > NamedCharacters.NAMES[hi].length()) {
+                                break outer;
+                            } else if (c < NamedCharacters.NAMES[hi].charAt(entCol)) {
+                                hi--;
+                            } else {
+                                break hiloop;
+                            }
+                        }
+
+                        loloop: for (;;) {
+                            if (hi < lo) {
+                                break outer;
+                            }
+                            if (entCol == NamedCharacters.NAMES[lo].length()) {
+                                candidate = lo;
+                                charRefBufMark = charRefBufLen;
+                                lo++;
+                            } else if (entCol > NamedCharacters.NAMES[lo].length()) {
+                                break outer;
+                            } else if (c > NamedCharacters.NAMES[lo].charAt(entCol)) {
+                                lo++;
+                            } else {
+                                break loloop;
+                            }
+                        }
+                        if (hi < lo) {
+                            break outer;
+                        }
+                        continue;
+                    }
+
+                    if (candidate == -1) {
+                        /*
+                         * If no match can be made, then this is a parse error.
+                         */
+                        errNoNamedCharacterMatch();
+                        emitOrAppendCharRefBuf(returnState);
+                        state = returnState;
+                        continue eofloop;
+                    } else {
+                        @Const @CharacterName String candidateName = NamedCharacters.NAMES[candidate];
+                        if (candidateName.length() == 0
+                                || candidateName.charAt(candidateName.length() - 1) != ';') {
+                            /*
+                             * If the last character matched is not a U+003B
+                             * SEMICOLON (;), there is a parse error.
+                             */
+                            if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+                                /*
+                                 * If the entity is being consumed as part of an
+                                 * attribute, and the last character matched is
+                                 * not a U+003B SEMICOLON (;),
+                                 */
+                                char ch;
+                                if (charRefBufMark == charRefBufLen) {
+                                    ch = '\u0000';
+                                } else {
+                                    ch = charRefBuf[charRefBufMark];
+                                }
+                                if ((ch >= '0' && ch <= '9')
+                                        || (ch >= 'A' && ch <= 'Z')
+                                        || (ch >= 'a' && ch <= 'z')) {
+                                    /*
+                                     * and the next character is in the range
+                                     * U+0030 DIGIT ZERO to U+0039 DIGIT NINE,
+                                     * U+0041 LATIN CAPITAL LETTER A to U+005A
+                                     * LATIN CAPITAL LETTER Z, or U+0061 LATIN
+                                     * SMALL LETTER A to U+007A LATIN SMALL
+                                     * LETTER Z, then, for historical reasons,
+                                     * all the characters that were matched
+                                     * after the U+0026 AMPERSAND (&) must be
+                                     * unconsumed, and nothing is returned.
+                                     */
+                                    errNoNamedCharacterMatch();
+                                    appendCharRefBufToStrBuf();
+                                    state = returnState;
+                                    continue eofloop;
+                                }
+                            }
+                            if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+                                errUnescapedAmpersandInterpretedAsCharacterReference();
+                            } else {
+                                errNotSemicolonTerminated();
+                            }
+                        }
+
+                        /*
+                         * Otherwise, return a character token for the character
+                         * corresponding to the entity name (as given by the
+                         * second column of the named character references
+                         * table).
+                         */
+                        @Const @NoLength char[] val = NamedCharacters.VALUES[candidate];
+                        if (
+                        // [NOCPP[
+                        val.length == 1
+                        // ]NOCPP]
+                        // CPPONLY: val[1] == 0
+                        ) {
+                            emitOrAppendOne(val, returnState);
+                        } else {
+                            emitOrAppendTwo(val, returnState);
+                        }
+                        // this is so complicated!
+                        if (charRefBufMark < charRefBufLen) {
+                            if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+                                appendStrBuf(charRefBuf, charRefBufMark,
+                                        charRefBufLen - charRefBufMark);
+                            } else {
+                                tokenHandler.characters(charRefBuf, charRefBufMark,
+                                        charRefBufLen - charRefBufMark);
+                            }
+                        }
+                        charRefBufLen = 0;
+                        state = returnState;
+                        continue eofloop;
+                        /*
+                         * If the markup contains I'm &notit; I tell you, the
+                         * entity is parsed as "not", as in, I'm ¬it; I tell
+                         * you. But if the markup was I'm &notin; I tell you,
+                         * the entity would be parsed as "notin;", resulting in
+                         * I'm ∉ I tell you.
+                         */
+                    }
+                case CONSUME_NCR:
+                case DECIMAL_NRC_LOOP:
+                case HEX_NCR_LOOP:
+                    /*
+                     * If no characters match the range, then don't consume any
+                     * characters (and unconsume the U+0023 NUMBER SIGN
+                     * character and, if appropriate, the X character). This is
+                     * a parse error; nothing is returned.
+                     *
+                     * Otherwise, if the next character is a U+003B SEMICOLON,
+                     * consume that too. If it isn't, there is a parse error.
+                     */
+                    if (!seenDigits) {
+                        errNoDigitsInNCR();
+                        emitOrAppendCharRefBuf(returnState);
+                        state = returnState;
+                        continue;
+                    } else {
+                        errCharRefLacksSemicolon();
+                    }
+                    // WARNING previous state sets reconsume
+                    handleNcrValue(returnState);
+                    state = returnState;
+                    continue;
+                case CDATA_RSQB:
+                    tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 1);
+                    break eofloop;
+                case CDATA_RSQB_RSQB:
+                    tokenHandler.characters(Tokenizer.RSQB_RSQB, 0, 2);
+                    break eofloop;
+                case DATA:
+                default:
+                    break eofloop;
+            }
+        }
+        // case DATA:
+        /*
+         * EOF Emit an end-of-file token.
+         */
+        tokenHandler.eof();
+        return;
+    }
+
+    private void emitDoctypeToken(int pos) throws SAXException {
+        cstart = pos + 1;
+        tokenHandler.doctype(doctypeName, publicIdentifier, systemIdentifier,
+                forceQuirks);
+        // It is OK and sufficient to release these here, since
+        // there's no way out of the doctype states than through paths
+        // that call this method.
+        doctypeName = null;
+        Portability.releaseString(publicIdentifier);
+        publicIdentifier = null;
+        Portability.releaseString(systemIdentifier);
+        systemIdentifier = null;
+    }
+
+    @Inline protected char checkChar(@NoLength char[] buf, int pos)
+            throws SAXException {
+        return buf[pos];
+    }
+
+    public boolean internalEncodingDeclaration(String internalCharset)
+            throws SAXException {
+        if (encodingDeclarationHandler != null) {
+            return encodingDeclarationHandler.internalEncodingDeclaration(internalCharset);
+        }
+        return false;
+    }
+
+    /**
+     * @param val
+     * @throws SAXException
+     */
+    private void emitOrAppendTwo(@Const @NoLength char[] val, int returnState)
+            throws SAXException {
+        if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+            appendStrBuf(val[0]);
+            appendStrBuf(val[1]);
+        } else {
+            tokenHandler.characters(val, 0, 2);
+        }
+    }
+
+    private void emitOrAppendOne(@Const @NoLength char[] val, int returnState)
+            throws SAXException {
+        if ((returnState & DATA_AND_RCDATA_MASK) != 0) {
+            appendStrBuf(val[0]);
+        } else {
+            tokenHandler.characters(val, 0, 1);
+        }
+    }
+
+    public void end() throws SAXException {
+        strBuf = null;
+        doctypeName = null;
+        if (systemIdentifier != null) {
+            Portability.releaseString(systemIdentifier);
+            systemIdentifier = null;
+        }
+        if (publicIdentifier != null) {
+            Portability.releaseString(publicIdentifier);
+            publicIdentifier = null;
+        }
+        if (tagName != null) {
+            tagName.release();
+            tagName = null;
+        }
+        if (attributeName != null) {
+            attributeName.release();
+            attributeName = null;
+        }
+        tokenHandler.endTokenization();
+        if (attributes != null) {
+            // [NOCPP[
+            attributes = null;
+            // ]NOCPP]
+            // CPPONLY: attributes.clear(mappingLangToXmlLang);
+        }
+    }
+
+    public void requestSuspension() {
+        shouldSuspend = true;
+    }
+
+    // [NOCPP[
+
+    public void becomeConfident() {
+        confident = true;
+    }
+
+    /**
+     * Returns the nextCharOnNewLine.
+     *
+     * @return the nextCharOnNewLine
+     */
+    public boolean isNextCharOnNewLine() {
+        return false;
+    }
+
+    public boolean isPrevCR() {
+        return lastCR;
+    }
+
+    /**
+     * Returns the line.
+     *
+     * @return the line
+     */
+    public int getLine() {
+        return -1;
+    }
+
+    /**
+     * Returns the col.
+     *
+     * @return the col
+     */
+    public int getCol() {
+        return -1;
+    }
+
+    // ]NOCPP]
+
+    public boolean isInDataState() {
+        return (stateSave == DATA);
+    }
+
+    public void resetToDataState() {
+        clearStrBufAfterUse();
+        charRefBufLen = 0;
+        stateSave = Tokenizer.DATA;
+        // line = 1; XXX line numbers
+        lastCR = false;
+        index = 0;
+        forceQuirks = false;
+        additional = '\u0000';
+        entCol = -1;
+        firstCharKey = -1;
+        lo = 0;
+        hi = 0; // will always be overwritten before use anyway
+        candidate = -1;
+        charRefBufMark = 0;
+        value = 0;
+        seenDigits = false;
+        endTag = false;
+        shouldSuspend = false;
+        initDoctypeFields();
+        if (tagName != null) {
+            tagName.release();
+            tagName = null;
+        }
+        if (attributeName != null) {
+            attributeName.release();
+            attributeName = null;
+        }
+        if (newAttributesEachTime) {
+            if (attributes != null) {
+                Portability.delete(attributes);
+                attributes = null;
+            }
+        }
+    }
+
+    public void loadState(Tokenizer other) throws SAXException {
+        strBufLen = other.strBufLen;
+        if (strBufLen > strBuf.length) {
+            strBuf = new char[strBufLen];
+        }
+        System.arraycopy(other.strBuf, 0, strBuf, 0, strBufLen);
+
+        charRefBufLen = other.charRefBufLen;
+        System.arraycopy(other.charRefBuf, 0, charRefBuf, 0, charRefBufLen);
+
+        stateSave = other.stateSave;
+        returnStateSave = other.returnStateSave;
+        endTagExpectation = other.endTagExpectation;
+        endTagExpectationAsArray = other.endTagExpectationAsArray;
+        // line = 1; XXX line numbers
+        lastCR = other.lastCR;
+        index = other.index;
+        forceQuirks = other.forceQuirks;
+        additional = other.additional;
+        entCol = other.entCol;
+        firstCharKey = other.firstCharKey;
+        lo = other.lo;
+        hi = other.hi;
+        candidate = other.candidate;
+        charRefBufMark = other.charRefBufMark;
+        value = other.value;
+        seenDigits = other.seenDigits;
+        endTag = other.endTag;
+        shouldSuspend = false;
+
+        if (other.doctypeName == null) {
+            doctypeName = null;
+        } else {
+            doctypeName = Portability.newLocalFromLocal(other.doctypeName,
+                    interner);
+        }
+
+        Portability.releaseString(systemIdentifier);
+        if (other.systemIdentifier == null) {
+            systemIdentifier = null;
+        } else {
+            systemIdentifier = Portability.newStringFromString(other.systemIdentifier);
+        }
+
+        Portability.releaseString(publicIdentifier);
+        if (other.publicIdentifier == null) {
+            publicIdentifier = null;
+        } else {
+            publicIdentifier = Portability.newStringFromString(other.publicIdentifier);
+        }
+
+        if (tagName != null) {
+            tagName.release();
+        }
+        if (other.tagName == null) {
+            tagName = null;
+        } else {
+            tagName = other.tagName.cloneElementName(interner);
+        }
+
+        if (attributeName != null) {
+            attributeName.release();
+        }
+        if (other.attributeName == null) {
+            attributeName = null;
+        } else {
+            attributeName = other.attributeName.cloneAttributeName(interner);
+        }
+
+        Portability.delete(attributes);
+        if (other.attributes == null) {
+            attributes = null;
+        } else {
+            attributes = other.attributes.cloneAttributes(interner);
+        }
+    }
+
+    public void initializeWithoutStarting() throws SAXException {
+        confident = false;
+        strBuf = null;
+        line = 1;
+        // CPPONLY: attributeLine = 1;
+        // [NOCPP[
+        html4 = false;
+        metaBoundaryPassed = false;
+        wantsComments = tokenHandler.wantsComments();
+        if (!newAttributesEachTime) {
+            attributes = new HtmlAttributes(mappingLangToXmlLang);
+        }
+        // ]NOCPP]
+        resetToDataState();
+    }
+
+    protected void errGarbageAfterLtSlash() throws SAXException {
+    }
+
+    protected void errLtSlashGt() throws SAXException {
+    }
+
+    protected void errWarnLtSlashInRcdata() throws SAXException {
+    }
+
+    protected void errHtml4LtSlashInRcdata(char folded) throws SAXException {
+    }
+
+    protected void errCharRefLacksSemicolon() throws SAXException {
+    }
+
+    protected void errNoDigitsInNCR() throws SAXException {
+    }
+
+    protected void errGtInSystemId() throws SAXException {
+    }
+
+    protected void errGtInPublicId() throws SAXException {
+    }
+
+    protected void errNamelessDoctype() throws SAXException {
+    }
+
+    protected void errConsecutiveHyphens() throws SAXException {
+    }
+
+    protected void errPrematureEndOfComment() throws SAXException {
+    }
+
+    protected void errBogusComment() throws SAXException {
+    }
+
+    protected void errUnquotedAttributeValOrNull(char c) throws SAXException {
+    }
+
+    protected void errSlashNotFollowedByGt() throws SAXException {
+    }
+
+    protected void errHtml4XmlVoidSyntax() throws SAXException {
+    }
+
+    protected void errNoSpaceBetweenAttributes() throws SAXException {
+    }
+
+    protected void errHtml4NonNameInUnquotedAttribute(char c)
+            throws SAXException {
+    }
+
+    protected void errLtOrEqualsOrGraveInUnquotedAttributeOrNull(char c)
+            throws SAXException {
+    }
+
+    protected void errAttributeValueMissing() throws SAXException {
+    }
+
+    protected void errBadCharBeforeAttributeNameOrNull(char c)
+            throws SAXException {
+    }
+
+    protected void errEqualsSignBeforeAttributeName() throws SAXException {
+    }
+
+    protected void errBadCharAfterLt(char c) throws SAXException {
+    }
+
+    protected void errLtGt() throws SAXException {
+    }
+
+    protected void errProcessingInstruction() throws SAXException {
+    }
+
+    protected void errUnescapedAmpersandInterpretedAsCharacterReference()
+            throws SAXException {
+    }
+
+    protected void errNotSemicolonTerminated() throws SAXException {
+    }
+
+    protected void errNoNamedCharacterMatch() throws SAXException {
+    }
+
+    protected void errQuoteBeforeAttributeName(char c) throws SAXException {
+    }
+
+    protected void errQuoteOrLtInAttributeNameOrNull(char c)
+            throws SAXException {
+    }
+
+    protected void errExpectedPublicId() throws SAXException {
+    }
+
+    protected void errBogusDoctype() throws SAXException {
+    }
+
+    protected void maybeWarnPrivateUseAstral() throws SAXException {
+    }
+
+    protected void maybeWarnPrivateUse(char ch) throws SAXException {
+    }
+
+    protected void maybeErrAttributesOnEndTag(HtmlAttributes attrs)
+            throws SAXException {
+    }
+
+    protected void maybeErrSlashInEndTag(boolean selfClosing)
+            throws SAXException {
+    }
+
+    protected char errNcrNonCharacter(char ch) throws SAXException {
+        return ch;
+    }
+
+    protected void errAstralNonCharacter(int ch) throws SAXException {
+    }
+
+    protected void errNcrSurrogate() throws SAXException {
+    }
+
+    protected char errNcrControlChar(char ch) throws SAXException {
+        return ch;
+    }
+
+    protected void errNcrCr() throws SAXException {
+    }
+
+    protected void errNcrInC1Range() throws SAXException {
+    }
+
+    protected void errEofInPublicId() throws SAXException {
+    }
+
+    protected void errEofInComment() throws SAXException {
+    }
+
+    protected void errEofInDoctype() throws SAXException {
+    }
+
+    protected void errEofInAttributeValue() throws SAXException {
+    }
+
+    protected void errEofInAttributeName() throws SAXException {
+    }
+
+    protected void errEofWithoutGt() throws SAXException {
+    }
+
+    protected void errEofInTagName() throws SAXException {
+    }
+
+    protected void errEofInEndTag() throws SAXException {
+    }
+
+    protected void errEofAfterLt() throws SAXException {
+    }
+
+    protected void errNcrOutOfRange() throws SAXException {
+    }
+
+    protected void errNcrUnassigned() throws SAXException {
+    }
+
+    protected void errDuplicateAttribute() throws SAXException {
+    }
+
+    protected void errEofInSystemId() throws SAXException {
+    }
+
+    protected void errExpectedSystemId() throws SAXException {
+    }
+
+    protected void errMissingSpaceBeforeDoctypeName() throws SAXException {
+    }
+
+    protected void errHyphenHyphenBang() throws SAXException {
+    }
+
+    protected void errNcrControlChar() throws SAXException {
+    }
+
+    protected void errNcrZero() throws SAXException {
+    }
+
+    protected void errNoSpaceBetweenDoctypeSystemKeywordAndQuote()
+            throws SAXException {
+    }
+
+    protected void errNoSpaceBetweenPublicAndSystemIds() throws SAXException {
+    }
+
+    protected void errNoSpaceBetweenDoctypePublicKeywordAndQuote()
+            throws SAXException {
+    }
+
+    protected void noteAttributeWithoutValue() throws SAXException {
+    }
+
+    protected void noteUnquotedAttributeValue() throws SAXException {
+    }
+
+    /**
+     * Sets the encodingDeclarationHandler.
+     *
+     * @param encodingDeclarationHandler
+     *            the encodingDeclarationHandler to set
+     */
+    public void setEncodingDeclarationHandler(
+            EncodingDeclarationHandler encodingDeclarationHandler) {
+        this.encodingDeclarationHandler = encodingDeclarationHandler;
+    }
+
+    void destructor() {
+        // The translator will write refcount tracing stuff here
+        Portability.delete(attributes);
+        attributes = null;
+    }
+
+    // [NOCPP[
+
+    /**
+     * Sets an offset to be added to the position reported to
+     * <code>TransitionHandler</code>.
+     *
+     * @param offset the offset
+     */
+    public void setTransitionBaseOffset(int offset) {
+
+    }
+
+    // ]NOCPP]
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TreeBuilder.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TreeBuilder.java
new file mode 100644
index 000000000..de7d8478d
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TreeBuilder.java
@@ -0,0 +1,6553 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2007-2015 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ * Portions of comments Copyright 2004-2008 Apple Computer, Inc., Mozilla
+ * Foundation, and Opera Software ASA.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/*
+ * The comments following this one that use the same comment syntax as this
+ * comment are quotes from the WHATWG HTML 5 spec as of 27 June 2007
+ * amended as of June 28 2007.
+ * That document came with this statement:
+ * "© Copyright 2004-2007 Apple Computer, Inc., Mozilla Foundation, and
+ * Opera Software ASA. You are granted a license to use, reproduce and
+ * create derivative works of this document."
+ */
+
+package nu.validator.htmlparser.impl;
+
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.Map;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+import nu.validator.htmlparser.annotation.Auto;
+import nu.validator.htmlparser.annotation.Const;
+import nu.validator.htmlparser.annotation.IdType;
+import nu.validator.htmlparser.annotation.Inline;
+import nu.validator.htmlparser.annotation.Literal;
+import nu.validator.htmlparser.annotation.Local;
+import nu.validator.htmlparser.annotation.NoLength;
+import nu.validator.htmlparser.annotation.NsUri;
+import nu.validator.htmlparser.common.DoctypeExpectation;
+import nu.validator.htmlparser.common.DocumentMode;
+import nu.validator.htmlparser.common.DocumentModeHandler;
+import nu.validator.htmlparser.common.Interner;
+import nu.validator.htmlparser.common.TokenHandler;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+
+public abstract class TreeBuilder<T> implements TokenHandler,
+        TreeBuilderState<T> {
+
+    /**
+     * Array version of U+FFFD.
+     */
+    private static final @NoLength char[] REPLACEMENT_CHARACTER = { '\uFFFD' };
+
+    // Start dispatch groups
+
+    final static int OTHER = 0;
+
+    final static int A = 1;
+
+    final static int BASE = 2;
+
+    final static int BODY = 3;
+
+    final static int BR = 4;
+
+    final static int BUTTON = 5;
+
+    final static int CAPTION = 6;
+
+    final static int COL = 7;
+
+    final static int COLGROUP = 8;
+
+    final static int FORM = 9;
+
+    final static int FRAME = 10;
+
+    final static int FRAMESET = 11;
+
+    final static int IMAGE = 12;
+
+    final static int INPUT = 13;
+
+    final static int ISINDEX = 14;
+
+    final static int LI = 15;
+
+    final static int LINK_OR_BASEFONT_OR_BGSOUND = 16;
+
+    final static int MATH = 17;
+
+    final static int META = 18;
+
+    final static int SVG = 19;
+
+    final static int HEAD = 20;
+
+    final static int HR = 22;
+
+    final static int HTML = 23;
+
+    final static int NOBR = 24;
+
+    final static int NOFRAMES = 25;
+
+    final static int NOSCRIPT = 26;
+
+    final static int OPTGROUP = 27;
+
+    final static int OPTION = 28;
+
+    final static int P = 29;
+
+    final static int PLAINTEXT = 30;
+
+    final static int SCRIPT = 31;
+
+    final static int SELECT = 32;
+
+    final static int STYLE = 33;
+
+    final static int TABLE = 34;
+
+    final static int TEXTAREA = 35;
+
+    final static int TITLE = 36;
+
+    final static int TR = 37;
+
+    final static int XMP = 38;
+
+    final static int TBODY_OR_THEAD_OR_TFOOT = 39;
+
+    final static int TD_OR_TH = 40;
+
+    final static int DD_OR_DT = 41;
+
+    final static int H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6 = 42;
+
+    final static int MARQUEE_OR_APPLET = 43;
+
+    final static int PRE_OR_LISTING = 44;
+
+    final static int B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U = 45;
+
+    final static int UL_OR_OL_OR_DL = 46;
+
+    final static int IFRAME = 47;
+
+    final static int EMBED = 48;
+
+    final static int AREA_OR_WBR = 49;
+
+    final static int DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU = 50;
+
+    final static int ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY = 51;
+
+    final static int RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR = 52;
+
+    final static int RB_OR_RTC = 53;
+
+    final static int PARAM_OR_SOURCE_OR_TRACK = 55;
+
+    final static int MGLYPH_OR_MALIGNMARK = 56;
+
+    final static int MI_MO_MN_MS_MTEXT = 57;
+
+    final static int ANNOTATION_XML = 58;
+
+    final static int FOREIGNOBJECT_OR_DESC = 59;
+
+    final static int NOEMBED = 60;
+
+    final static int FIELDSET = 61;
+
+    final static int OUTPUT = 62;
+
+    final static int OBJECT = 63;
+
+    final static int FONT = 64;
+
+    final static int KEYGEN = 65;
+
+    final static int MENUITEM = 66;
+
+    final static int TEMPLATE = 67;
+
+    final static int IMG = 68;
+
+    final static int RT_OR_RP = 69;
+
+    // start insertion modes
+
+    private static final int IN_ROW = 0;
+
+    private static final int IN_TABLE_BODY = 1;
+
+    private static final int IN_TABLE = 2;
+
+    private static final int IN_CAPTION = 3;
+
+    private static final int IN_CELL = 4;
+
+    private static final int FRAMESET_OK = 5;
+
+    private static final int IN_BODY = 6;
+
+    private static final int IN_HEAD = 7;
+
+    private static final int IN_HEAD_NOSCRIPT = 8;
+
+    // no fall-through
+
+    private static final int IN_COLUMN_GROUP = 9;
+
+    // no fall-through
+
+    private static final int IN_SELECT_IN_TABLE = 10;
+
+    private static final int IN_SELECT = 11;
+
+    // no fall-through
+
+    private static final int AFTER_BODY = 12;
+
+    // no fall-through
+
+    private static final int IN_FRAMESET = 13;
+
+    private static final int AFTER_FRAMESET = 14;
+
+    // no fall-through
+
+    private static final int INITIAL = 15;
+
+    // could add fall-through
+
+    private static final int BEFORE_HTML = 16;
+
+    // could add fall-through
+
+    private static final int BEFORE_HEAD = 17;
+
+    // no fall-through
+
+    private static final int AFTER_HEAD = 18;
+
+    // no fall-through
+
+    private static final int AFTER_AFTER_BODY = 19;
+
+    // no fall-through
+
+    private static final int AFTER_AFTER_FRAMESET = 20;
+
+    // no fall-through
+
+    private static final int TEXT = 21;
+
+    private static final int IN_TEMPLATE = 22;
+
+    // start charset states
+
+    private static final int CHARSET_INITIAL = 0;
+
+    private static final int CHARSET_C = 1;
+
+    private static final int CHARSET_H = 2;
+
+    private static final int CHARSET_A = 3;
+
+    private static final int CHARSET_R = 4;
+
+    private static final int CHARSET_S = 5;
+
+    private static final int CHARSET_E = 6;
+
+    private static final int CHARSET_T = 7;
+
+    private static final int CHARSET_EQUALS = 8;
+
+    private static final int CHARSET_SINGLE_QUOTED = 9;
+
+    private static final int CHARSET_DOUBLE_QUOTED = 10;
+
+    private static final int CHARSET_UNQUOTED = 11;
+
+    // end pseudo enums
+
+    // [NOCPP[
+
+    private final static String[] HTML4_PUBLIC_IDS = {
+            "-//W3C//DTD HTML 4.0 Frameset//EN",
+            "-//W3C//DTD HTML 4.0 Transitional//EN",
+            "-//W3C//DTD HTML 4.0//EN", "-//W3C//DTD HTML 4.01 Frameset//EN",
+            "-//W3C//DTD HTML 4.01 Transitional//EN",
+            "-//W3C//DTD HTML 4.01//EN" };
+
+    // ]NOCPP]
+
+    @Literal private final static String[] QUIRKY_PUBLIC_IDS = {
+            "+//silmaril//dtd html pro v0r11 19970101//",
+            "-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
+            "-//as//dtd html 3.0 aswedit + extensions//",
+            "-//ietf//dtd html 2.0 level 1//",
+            "-//ietf//dtd html 2.0 level 2//",
+            "-//ietf//dtd html 2.0 strict level 1//",
+            "-//ietf//dtd html 2.0 strict level 2//",
+            "-//ietf//dtd html 2.0 strict//",
+            "-//ietf//dtd html 2.0//",
+            "-//ietf//dtd html 2.1e//",
+            "-//ietf//dtd html 3.0//",
+            "-//ietf//dtd html 3.2 final//",
+            "-//ietf//dtd html 3.2//",
+            "-//ietf//dtd html 3//",
+            "-//ietf//dtd html level 0//",
+            "-//ietf//dtd html level 1//",
+            "-//ietf//dtd html level 2//",
+            "-//ietf//dtd html level 3//",
+            "-//ietf//dtd html strict level 0//",
+            "-//ietf//dtd html strict level 1//",
+            "-//ietf//dtd html strict level 2//",
+            "-//ietf//dtd html strict level 3//",
+            "-//ietf//dtd html strict//",
+            "-//ietf//dtd html//",
+            "-//metrius//dtd metrius presentational//",
+            "-//microsoft//dtd internet explorer 2.0 html strict//",
+            "-//microsoft//dtd internet explorer 2.0 html//",
+            "-//microsoft//dtd internet explorer 2.0 tables//",
+            "-//microsoft//dtd internet explorer 3.0 html strict//",
+            "-//microsoft//dtd internet explorer 3.0 html//",
+            "-//microsoft//dtd internet explorer 3.0 tables//",
+            "-//netscape comm. corp.//dtd html//",
+            "-//netscape comm. corp.//dtd strict html//",
+            "-//o'reilly and associates//dtd html 2.0//",
+            "-//o'reilly and associates//dtd html extended 1.0//",
+            "-//o'reilly and associates//dtd html extended relaxed 1.0//",
+            "-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
+            "-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
+            "-//spyglass//dtd html 2.0 extended//",
+            "-//sq//dtd html 2.0 hotmetal + extensions//",
+            "-//sun microsystems corp.//dtd hotjava html//",
+            "-//sun microsystems corp.//dtd hotjava strict html//",
+            "-//w3c//dtd html 3 1995-03-24//", "-//w3c//dtd html 3.2 draft//",
+            "-//w3c//dtd html 3.2 final//", "-//w3c//dtd html 3.2//",
+            "-//w3c//dtd html 3.2s draft//", "-//w3c//dtd html 4.0 frameset//",
+            "-//w3c//dtd html 4.0 transitional//",
+            "-//w3c//dtd html experimental 19960712//",
+            "-//w3c//dtd html experimental 970421//", "-//w3c//dtd w3 html//",
+            "-//w3o//dtd w3 html 3.0//", "-//webtechs//dtd mozilla html 2.0//",
+            "-//webtechs//dtd mozilla html//" };
+
+    private static final int NOT_FOUND_ON_STACK = Integer.MAX_VALUE;
+
+    // [NOCPP[
+
+    private static final @Local String HTML_LOCAL = "html";
+
+    // ]NOCPP]
+
+    private int mode = INITIAL;
+
+    private int originalMode = INITIAL;
+
+    /**
+     * Used only when moving back to IN_BODY.
+     */
+    private boolean framesetOk = true;
+
+    protected Tokenizer tokenizer;
+
+    // [NOCPP[
+
+    protected ErrorHandler errorHandler;
+
+    private DocumentModeHandler documentModeHandler;
+
+    private DoctypeExpectation doctypeExpectation = DoctypeExpectation.HTML;
+
+    private LocatorImpl firstCommentLocation;
+
+    // ]NOCPP]
+
+    private boolean scriptingEnabled = false;
+
+    private boolean needToDropLF;
+
+    // [NOCPP[
+
+    private boolean wantingComments;
+
+    // ]NOCPP]
+
+    private boolean fragment;
+
+    private @Local String contextName;
+
+    private @NsUri String contextNamespace;
+
+    private T contextNode;
+
+    /**
+     * Stack of template insertion modes
+     */
+    private @Auto int[] templateModeStack;
+
+    /**
+     * Current template mode stack pointer.
+     */
+    private int templateModePtr = -1;
+
+    private @Auto StackNode<T>[] stack;
+
+    private int currentPtr = -1;
+
+    private @Auto StackNode<T>[] listOfActiveFormattingElements;
+
+    private int listPtr = -1;
+
+    private T formPointer;
+
+    private T headPointer;
+
+    /**
+     * Used to work around Gecko limitations. Not used in Java.
+     */
+    private T deepTreeSurrogateParent;
+
+    protected @Auto char[] charBuffer;
+
+    protected int charBufferLen = 0;
+
+    private boolean quirks = false;
+
+    private boolean isSrcdocDocument = false;
+
+    // [NOCPP[
+
+    private boolean reportingDoctype = true;
+
+    private XmlViolationPolicy namePolicy = XmlViolationPolicy.ALTER_INFOSET;
+
+    private final Map<String, LocatorImpl> idLocations = new HashMap<String, LocatorImpl>();
+
+    private boolean html4;
+
+    // ]NOCPP]
+
+    protected TreeBuilder() {
+        fragment = false;
+    }
+
+    /**
+     * Reports an condition that would make the infoset incompatible with XML
+     * 1.0 as fatal.
+     *
+     * @throws SAXException
+     * @throws SAXParseException
+     */
+    protected void fatal() throws SAXException {
+    }
+
+    // [NOCPP[
+
+    protected final void fatal(Exception e) throws SAXException {
+        SAXParseException spe = new SAXParseException(e.getMessage(),
+                tokenizer, e);
+        if (errorHandler != null) {
+            errorHandler.fatalError(spe);
+        }
+        throw spe;
+    }
+
+    final void fatal(String s) throws SAXException {
+        SAXParseException spe = new SAXParseException(s, tokenizer);
+        if (errorHandler != null) {
+            errorHandler.fatalError(spe);
+        }
+        throw spe;
+    }
+
+    /**
+     * Reports a Parse Error.
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    final void err(String message) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck(message);
+    }
+
+    /**
+     * Reports a Parse Error without checking if an error handler is present.
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    final void errNoCheck(String message) throws SAXException {
+        SAXParseException spe = new SAXParseException(message, tokenizer);
+        errorHandler.error(spe);
+    }
+
+    private void errListUnclosedStartTags(int eltPos) throws SAXException {
+        if (currentPtr != -1) {
+            for (int i = currentPtr; i > eltPos; i--) {
+                reportUnclosedElementNameAndLocation(i);
+            }
+        }
+    }
+
+    /**
+     * Reports the name and location of an unclosed element.
+     *
+     * @throws SAXException
+     */
+    private final void reportUnclosedElementNameAndLocation(int pos) throws SAXException {
+        StackNode<T> node = stack[pos];
+        if (node.isOptionalEndTag()) {
+            return;
+        }
+        TaintableLocatorImpl locator = node.getLocator();
+        if (locator.isTainted()) {
+            return;
+        }
+        locator.markTainted();
+        SAXParseException spe = new SAXParseException(
+                "Unclosed element \u201C" + node.popName + "\u201D.", locator);
+        errorHandler.error(spe);
+    }
+
+    /**
+     * Reports a warning
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    final void warn(String message) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(message, tokenizer);
+        errorHandler.warning(spe);
+    }
+
+    /**
+     * Reports a warning with an explicit locator
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    final void warn(String message, Locator locator) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(message, locator);
+        errorHandler.warning(spe);
+    }
+
+    // ]NOCPP]
+
+    @SuppressWarnings("unchecked") public final void startTokenization(Tokenizer self) throws SAXException {
+        tokenizer = self;
+        stack = new StackNode[64];
+        templateModeStack = new int[64];
+        listOfActiveFormattingElements = new StackNode[64];
+        needToDropLF = false;
+        originalMode = INITIAL;
+        templateModePtr = -1;
+        currentPtr = -1;
+        listPtr = -1;
+        formPointer = null;
+        headPointer = null;
+        deepTreeSurrogateParent = null;
+        // [NOCPP[
+        html4 = false;
+        idLocations.clear();
+        wantingComments = wantsComments();
+        firstCommentLocation = null;
+        // ]NOCPP]
+        start(fragment);
+        charBufferLen = 0;
+        charBuffer = null;
+        framesetOk = true;
+        if (fragment) {
+            T elt;
+            if (contextNode != null) {
+                elt = contextNode;
+            } else {
+                elt = createHtmlElementSetAsRoot(tokenizer.emptyAttributes());
+            }
+            // When the context node is not in the HTML namespace, contrary
+            // to the spec, the first node on the stack is not set to "html"
+            // in the HTML namespace. Instead, it is set to a node that has
+            // the characteristics of the appropriate "adjusted current node".
+            // This way, there is no need to perform "adjusted current node"
+            // checks during tree construction. Instead, it's sufficient to
+            // just look at the current node. However, this also means that it
+            // is not safe to treat "html" in the HTML namespace as a sentinel
+            // that ends stack popping. Instead, stack popping loops that are
+            // meant not to pop the first element on the stack need to check
+            // for currentPos becoming zero.
+            if (contextNamespace == "http://www.w3.org/2000/svg") {
+                ElementName elementName = ElementName.SVG;
+                if ("title" == contextName || "desc" == contextName
+                        || "foreignObject" == contextName) {
+                    // These elements are all alike and we don't care about
+                    // the exact name.
+                    elementName = ElementName.FOREIGNOBJECT;
+                }
+                // This is the SVG variant of the StackNode constructor.
+                StackNode<T> node = new StackNode<T>(elementName,
+                        elementName.camelCaseName, elt
+                        // [NOCPP[
+                        , errorHandler == null ? null
+                                : new TaintableLocatorImpl(tokenizer)
+                // ]NOCPP]
+                );
+                currentPtr++;
+                stack[currentPtr] = node;
+                tokenizer.setState(Tokenizer.DATA);
+                // The frameset-ok flag is set even though <frameset> never
+                // ends up being allowed as HTML frameset in the fragment case.
+                mode = FRAMESET_OK;
+            } else if (contextNamespace == "http://www.w3.org/1998/Math/MathML") {
+                ElementName elementName = ElementName.MATH;
+                if ("mi" == contextName || "mo" == contextName
+                        || "mn" == contextName || "ms" == contextName
+                        || "mtext" == contextName) {
+                    // These elements are all alike and we don't care about
+                    // the exact name.
+                    elementName = ElementName.MTEXT;
+                } else if ("annotation-xml" == contextName) {
+                    elementName = ElementName.ANNOTATION_XML;
+                    // Blink does not check the encoding attribute of the
+                    // annotation-xml element innerHTML is being set on.
+                    // Let's do the same at least until
+                    // https://www.w3.org/Bugs/Public/show_bug.cgi?id=26783
+                    // is resolved.
+                }
+                // This is the MathML variant of the StackNode constructor.
+                StackNode<T> node = new StackNode<T>(elementName, elt,
+                        elementName.name, false
+                        // [NOCPP[
+                        , errorHandler == null ? null
+                                : new TaintableLocatorImpl(tokenizer)
+                // ]NOCPP]
+                );
+                currentPtr++;
+                stack[currentPtr] = node;
+                tokenizer.setState(Tokenizer.DATA);
+                // The frameset-ok flag is set even though <frameset> never
+                // ends up being allowed as HTML frameset in the fragment case.
+                mode = FRAMESET_OK;
+            } else { // html
+                StackNode<T> node = new StackNode<T>(ElementName.HTML, elt
+                // [NOCPP[
+                        , errorHandler == null ? null
+                                : new TaintableLocatorImpl(tokenizer)
+                // ]NOCPP]
+                );
+                currentPtr++;
+                stack[currentPtr] = node;
+                if ("template" == contextName) {
+                    pushTemplateMode(IN_TEMPLATE);
+                }
+                resetTheInsertionMode();
+                formPointer = getFormPointerForContext(contextNode);
+                if ("title" == contextName || "textarea" == contextName) {
+                    tokenizer.setState(Tokenizer.RCDATA);
+                } else if ("style" == contextName || "xmp" == contextName
+                        || "iframe" == contextName || "noembed" == contextName
+                        || "noframes" == contextName
+                        || (scriptingEnabled && "noscript" == contextName)) {
+                    tokenizer.setState(Tokenizer.RAWTEXT);
+                } else if ("plaintext" == contextName) {
+                    tokenizer.setState(Tokenizer.PLAINTEXT);
+                } else if ("script" == contextName) {
+                    tokenizer.setState(Tokenizer.SCRIPT_DATA);
+                } else {
+                    tokenizer.setState(Tokenizer.DATA);
+                }
+            }
+            contextName = null;
+            contextNode = null;
+        } else {
+            mode = INITIAL;
+            // If we are viewing XML source, put a foreign element permanently
+            // on the stack so that cdataSectionAllowed() returns true.
+            // CPPONLY: if (tokenizer.isViewingXmlSource()) {
+            // CPPONLY: T elt = createElement("http://www.w3.org/2000/svg",
+            // CPPONLY: "svg",
+            // CPPONLY: tokenizer.emptyAttributes(), null);
+            // CPPONLY: StackNode<T> node = new StackNode<T>(ElementName.SVG,
+            // CPPONLY: "svg",
+            // CPPONLY: elt);
+            // CPPONLY: currentPtr++;
+            // CPPONLY: stack[currentPtr] = node;
+            // CPPONLY: }
+        }
+    }
+
+    public final void doctype(@Local String name, String publicIdentifier,
+            String systemIdentifier, boolean forceQuirks) throws SAXException {
+        needToDropLF = false;
+        if (!isInForeign() && mode == INITIAL) {
+            // [NOCPP[
+            if (reportingDoctype) {
+                // ]NOCPP]
+                String emptyString = Portability.newEmptyString();
+                appendDoctypeToDocument(name == null ? "" : name,
+                        publicIdentifier == null ? emptyString
+                                : publicIdentifier,
+                        systemIdentifier == null ? emptyString
+                                : systemIdentifier);
+                Portability.releaseString(emptyString);
+                // [NOCPP[
+            }
+            switch (doctypeExpectation) {
+                case HTML:
+                    // ]NOCPP]
+                    if (isQuirky(name, publicIdentifier, systemIdentifier,
+                            forceQuirks)) {
+                        errQuirkyDoctype();
+                        documentModeInternal(DocumentMode.QUIRKS_MODE,
+                                publicIdentifier, systemIdentifier, false);
+                    } else if (isAlmostStandards(publicIdentifier,
+                            systemIdentifier)) {
+                        // [NOCPP[
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        // ]NOCPP]
+                        errAlmostStandardsDoctype();
+                        documentModeInternal(
+                                DocumentMode.ALMOST_STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, false);
+                    } else {
+                        // [NOCPP[
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        if ((Portability.literalEqualsString(
+                                "-//W3C//DTD HTML 4.0//EN", publicIdentifier) && (systemIdentifier == null || Portability.literalEqualsString(
+                                "http://www.w3.org/TR/REC-html40/strict.dtd",
+                                systemIdentifier)))
+                                || (Portability.literalEqualsString(
+                                        "-//W3C//DTD HTML 4.01//EN",
+                                        publicIdentifier) && (systemIdentifier == null || Portability.literalEqualsString(
+                                        "http://www.w3.org/TR/html4/strict.dtd",
+                                        systemIdentifier)))
+                                || (Portability.literalEqualsString(
+                                        "-//W3C//DTD XHTML 1.0 Strict//EN",
+                                        publicIdentifier) && Portability.literalEqualsString(
+                                        "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd",
+                                        systemIdentifier))
+                                || (Portability.literalEqualsString(
+                                        "-//W3C//DTD XHTML 1.1//EN",
+                                        publicIdentifier) && Portability.literalEqualsString(
+                                        "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd",
+                                        systemIdentifier))
+
+                        ) {
+                            warn("Obsolete doctype. Expected \u201C<!DOCTYPE html>\u201D.");
+                        } else if (!((systemIdentifier == null || Portability.literalEqualsString(
+                                "about:legacy-compat", systemIdentifier)) && publicIdentifier == null)) {
+                            err("Legacy doctype. Expected \u201C<!DOCTYPE html>\u201D.");
+                        }
+                        // ]NOCPP]
+                        documentModeInternal(DocumentMode.STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, false);
+                    }
+                    // [NOCPP[
+                    break;
+                case HTML401_STRICT:
+                    html4 = true;
+                    tokenizer.turnOnAdditionalHtml4Errors();
+                    if (isQuirky(name, publicIdentifier, systemIdentifier,
+                            forceQuirks)) {
+                        err("Quirky doctype. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                        documentModeInternal(DocumentMode.QUIRKS_MODE,
+                                publicIdentifier, systemIdentifier, true);
+                    } else if (isAlmostStandards(publicIdentifier,
+                            systemIdentifier)) {
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        err("Almost standards mode doctype. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                        documentModeInternal(
+                                DocumentMode.ALMOST_STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, true);
+                    } else {
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        if ("-//W3C//DTD HTML 4.01//EN".equals(publicIdentifier)) {
+                            if (!"http://www.w3.org/TR/html4/strict.dtd".equals(systemIdentifier)) {
+                                warn("The doctype did not contain the system identifier prescribed by the HTML 4.01 specification. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                            }
+                        } else {
+                            err("The doctype was not the HTML 4.01 Strict doctype. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                        }
+                        documentModeInternal(DocumentMode.STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, true);
+                    }
+                    break;
+                case HTML401_TRANSITIONAL:
+                    html4 = true;
+                    tokenizer.turnOnAdditionalHtml4Errors();
+                    if (isQuirky(name, publicIdentifier, systemIdentifier,
+                            forceQuirks)) {
+                        err("Quirky doctype. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                        documentModeInternal(DocumentMode.QUIRKS_MODE,
+                                publicIdentifier, systemIdentifier, true);
+                    } else if (isAlmostStandards(publicIdentifier,
+                            systemIdentifier)) {
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        if ("-//W3C//DTD HTML 4.01 Transitional//EN".equals(publicIdentifier)
+                                && systemIdentifier != null) {
+                            if (!"http://www.w3.org/TR/html4/loose.dtd".equals(systemIdentifier)) {
+                                warn("The doctype did not contain the system identifier prescribed by the HTML 4.01 specification. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                            }
+                        } else {
+                            err("The doctype was not a non-quirky HTML 4.01 Transitional doctype. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                        }
+                        documentModeInternal(
+                                DocumentMode.ALMOST_STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, true);
+                    } else {
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        err("The doctype was not the HTML 4.01 Transitional doctype. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                        documentModeInternal(DocumentMode.STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, true);
+                    }
+                    break;
+                case AUTO:
+                    html4 = isHtml4Doctype(publicIdentifier);
+                    if (html4) {
+                        tokenizer.turnOnAdditionalHtml4Errors();
+                    }
+                    if (isQuirky(name, publicIdentifier, systemIdentifier,
+                            forceQuirks)) {
+                        err("Quirky doctype. Expected e.g. \u201C<!DOCTYPE html>\u201D.");
+                        documentModeInternal(DocumentMode.QUIRKS_MODE,
+                                publicIdentifier, systemIdentifier, html4);
+                    } else if (isAlmostStandards(publicIdentifier,
+                            systemIdentifier)) {
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        if ("-//W3C//DTD HTML 4.01 Transitional//EN".equals(publicIdentifier)) {
+                            if (!"http://www.w3.org/TR/html4/loose.dtd".equals(systemIdentifier)) {
+                                warn("The doctype did not contain the system identifier prescribed by the HTML 4.01 specification. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                            }
+                        } else {
+                            err("Almost standards mode doctype. Expected e.g. \u201C<!DOCTYPE html>\u201D.");
+                        }
+                        documentModeInternal(
+                                DocumentMode.ALMOST_STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, html4);
+                    } else {
+                        if (firstCommentLocation != null) {
+                            warn("Comments seen before doctype. Internet Explorer will go into the quirks mode.",
+                                    firstCommentLocation);
+                        }
+                        if ("-//W3C//DTD HTML 4.01//EN".equals(publicIdentifier)) {
+                            if (!"http://www.w3.org/TR/html4/strict.dtd".equals(systemIdentifier)) {
+                                warn("The doctype did not contain the system identifier prescribed by the HTML 4.01 specification. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                            }
+                        } else if ("-//W3C//DTD XHTML 1.0 Strict//EN".equals(publicIdentifier)) {
+                            if (!"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd".equals(systemIdentifier)) {
+                                warn("The doctype did not contain the system identifier prescribed by the XHTML 1.0 specification. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD XHTML 1.0 Strict//EN\" \"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd\">\u201D.");
+                            }
+                        } else if ("//W3C//DTD XHTML 1.1//EN".equals(publicIdentifier)) {
+                            if (!"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd".equals(systemIdentifier)) {
+                                warn("The doctype did not contain the system identifier prescribed by the XHTML 1.1 specification. Expected \u201C<!DOCTYPE HTML PUBLIC \"//W3C//DTD XHTML 1.1//EN\" \"http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd\">\u201D.");
+                            }
+                        } else if (!((systemIdentifier == null || Portability.literalEqualsString(
+                                "about:legacy-compat", systemIdentifier)) && publicIdentifier == null)) {
+                            err("Unexpected doctype. Expected, e.g., \u201C<!DOCTYPE html>\u201D.");
+                        }
+                        documentModeInternal(DocumentMode.STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, html4);
+                    }
+                    break;
+                case NO_DOCTYPE_ERRORS:
+                    if (isQuirky(name, publicIdentifier, systemIdentifier,
+                            forceQuirks)) {
+                        documentModeInternal(DocumentMode.QUIRKS_MODE,
+                                publicIdentifier, systemIdentifier, false);
+                    } else if (isAlmostStandards(publicIdentifier,
+                            systemIdentifier)) {
+                        documentModeInternal(
+                                DocumentMode.ALMOST_STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, false);
+                    } else {
+                        documentModeInternal(DocumentMode.STANDARDS_MODE,
+                                publicIdentifier, systemIdentifier, false);
+                    }
+                    break;
+            }
+            // ]NOCPP]
+
+            /*
+             *
+             * Then, switch to the root element mode of the tree construction
+             * stage.
+             */
+            mode = BEFORE_HTML;
+            return;
+        }
+        /*
+         * A DOCTYPE token Parse error.
+         */
+        errStrayDoctype();
+        /*
+         * Ignore the token.
+         */
+        return;
+    }
+
+    // [NOCPP[
+
+    private boolean isHtml4Doctype(String publicIdentifier) {
+        if (publicIdentifier != null
+                && (Arrays.binarySearch(TreeBuilder.HTML4_PUBLIC_IDS,
+                        publicIdentifier) > -1)) {
+            return true;
+        }
+        return false;
+    }
+
+    // ]NOCPP]
+
+    public final void comment(@NoLength char[] buf, int start, int length)
+            throws SAXException {
+        needToDropLF = false;
+        // [NOCPP[
+        if (firstCommentLocation == null) {
+            firstCommentLocation = new LocatorImpl(tokenizer);
+        }
+        if (!wantingComments) {
+            return;
+        }
+        // ]NOCPP]
+        if (!isInForeign()) {
+            switch (mode) {
+                case INITIAL:
+                case BEFORE_HTML:
+                case AFTER_AFTER_BODY:
+                case AFTER_AFTER_FRAMESET:
+                    /*
+                     * A comment token Append a Comment node to the Document
+                     * object with the data attribute set to the data given in
+                     * the comment token.
+                     */
+                    appendCommentToDocument(buf, start, length);
+                    return;
+                case AFTER_BODY:
+                    /*
+                     * A comment token Append a Comment node to the first
+                     * element in the stack of open elements (the html element),
+                     * with the data attribute set to the data given in the
+                     * comment token.
+                     */
+                    flushCharacters();
+                    appendComment(stack[0].node, buf, start, length);
+                    return;
+                default:
+                    break;
+            }
+        }
+        /*
+         * A comment token Append a Comment node to the current node with the
+         * data attribute set to the data given in the comment token.
+         */
+        flushCharacters();
+        appendComment(stack[currentPtr].node, buf, start, length);
+        return;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.common.TokenHandler#characters(char[], int,
+     *      int)
+     */
+    public final void characters(@Const @NoLength char[] buf, int start, int length)
+            throws SAXException {
+        // Note: Can't attach error messages to EOF in C++ yet
+
+        // CPPONLY: if (tokenizer.isViewingXmlSource()) {
+        // CPPONLY: return;
+        // CPPONLY: }
+        if (needToDropLF) {
+            needToDropLF = false;
+            if (buf[start] == '\n') {
+                start++;
+                length--;
+                if (length == 0) {
+                    return;
+                }
+            }
+        }
+
+        // optimize the most common case
+        switch (mode) {
+            case IN_BODY:
+            case IN_CELL:
+            case IN_CAPTION:
+                if (!isInForeignButNotHtmlOrMathTextIntegrationPoint()) {
+                    reconstructTheActiveFormattingElements();
+                }
+                // fall through
+            case TEXT:
+                accumulateCharacters(buf, start, length);
+                return;
+            case IN_TABLE:
+            case IN_TABLE_BODY:
+            case IN_ROW:
+                accumulateCharactersForced(buf, start, length);
+                return;
+            default:
+                int end = start + length;
+                charactersloop: for (int i = start; i < end; i++) {
+                    switch (buf[i]) {
+                        case ' ':
+                        case '\t':
+                        case '\n':
+                        case '\r':
+                        case '\u000C':
+                            /*
+                             * A character token that is one of one of U+0009
+                             * CHARACTER TABULATION, U+000A LINE FEED (LF),
+                             * U+000C FORM FEED (FF), or U+0020 SPACE
+                             */
+                            switch (mode) {
+                                case INITIAL:
+                                case BEFORE_HTML:
+                                case BEFORE_HEAD:
+                                    /*
+                                     * Ignore the token.
+                                     */
+                                    start = i + 1;
+                                    continue;
+                                case IN_HEAD:
+                                case IN_HEAD_NOSCRIPT:
+                                case AFTER_HEAD:
+                                case IN_COLUMN_GROUP:
+                                case IN_FRAMESET:
+                                case AFTER_FRAMESET:
+                                    /*
+                                     * Append the character to the current node.
+                                     */
+                                    continue;
+                                case FRAMESET_OK:
+                                case IN_TEMPLATE:
+                                case IN_BODY:
+                                case IN_CELL:
+                                case IN_CAPTION:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+
+                                    /*
+                                     * Reconstruct the active formatting
+                                     * elements, if any.
+                                     */
+                                    if (!isInForeignButNotHtmlOrMathTextIntegrationPoint()) {
+                                        flushCharacters();
+                                        reconstructTheActiveFormattingElements();
+                                    }
+                                    /*
+                                     * Append the token's character to the
+                                     * current node.
+                                     */
+                                    break charactersloop;
+                                case IN_SELECT:
+                                case IN_SELECT_IN_TABLE:
+                                    break charactersloop;
+                                case IN_TABLE:
+                                case IN_TABLE_BODY:
+                                case IN_ROW:
+                                    accumulateCharactersForced(buf, i, 1);
+                                    start = i + 1;
+                                    continue;
+                                case AFTER_BODY:
+                                case AFTER_AFTER_BODY:
+                                case AFTER_AFTER_FRAMESET:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+                                    /*
+                                     * Reconstruct the active formatting
+                                     * elements, if any.
+                                     */
+                                    flushCharacters();
+                                    reconstructTheActiveFormattingElements();
+                                    /*
+                                     * Append the token's character to the
+                                     * current node.
+                                     */
+                                    continue;
+                            }
+                        default:
+                            /*
+                             * A character token that is not one of one of
+                             * U+0009 CHARACTER TABULATION, U+000A LINE FEED
+                             * (LF), U+000C FORM FEED (FF), or U+0020 SPACE
+                             */
+                            switch (mode) {
+                                case INITIAL:
+                                    /*
+                                     * Parse error.
+                                     */
+                                    // [NOCPP[
+                                    switch (doctypeExpectation) {
+                                        case AUTO:
+                                            err("Non-space characters found without seeing a doctype first. Expected e.g. \u201C<!DOCTYPE html>\u201D.");
+                                            break;
+                                        case HTML:
+                                            // XXX figure out a way to report this in the Gecko View Source case
+                                            err("Non-space characters found without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D.");
+                                            break;
+                                        case HTML401_STRICT:
+                                            err("Non-space characters found without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                                            break;
+                                        case HTML401_TRANSITIONAL:
+                                            err("Non-space characters found without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                                            break;
+                                        case NO_DOCTYPE_ERRORS:
+                                    }
+                                    // ]NOCPP]
+                                    /*
+                                     *
+                                     * Set the document to quirks mode.
+                                     */
+                                    documentModeInternal(
+                                            DocumentMode.QUIRKS_MODE, null,
+                                            null, false);
+                                    /*
+                                     * Then, switch to the root element mode of
+                                     * the tree construction stage
+                                     */
+                                    mode = BEFORE_HTML;
+                                    /*
+                                     * and reprocess the current token.
+                                     */
+                                    i--;
+                                    continue;
+                                case BEFORE_HTML:
+                                    /*
+                                     * Create an HTMLElement node with the tag
+                                     * name html, in the HTML namespace. Append
+                                     * it to the Document object.
+                                     */
+                                    // No need to flush characters here,
+                                    // because there's nothing to flush.
+                                    appendHtmlElementToDocumentAndPush();
+                                    /* Switch to the main mode */
+                                    mode = BEFORE_HEAD;
+                                    /*
+                                     * reprocess the current token.
+                                     */
+                                    i--;
+                                    continue;
+                                case BEFORE_HEAD:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+                                    /*
+                                     * /Act as if a start tag token with the tag
+                                     * name "head" and no attributes had been
+                                     * seen,
+                                     */
+                                    flushCharacters();
+                                    appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES);
+                                    mode = IN_HEAD;
+                                    /*
+                                     * then reprocess the current token.
+                                     *
+                                     * This will result in an empty head element
+                                     * being generated, with the current token
+                                     * being reprocessed in the "after head"
+                                     * insertion mode.
+                                     */
+                                    i--;
+                                    continue;
+                                case IN_HEAD:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+                                    /*
+                                     * Act as if an end tag token with the tag
+                                     * name "head" had been seen,
+                                     */
+                                    flushCharacters();
+                                    pop();
+                                    mode = AFTER_HEAD;
+                                    /*
+                                     * and reprocess the current token.
+                                     */
+                                    i--;
+                                    continue;
+                                case IN_HEAD_NOSCRIPT:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+                                    /*
+                                     * Parse error. Act as if an end tag with
+                                     * the tag name "noscript" had been seen
+                                     */
+                                    errNonSpaceInNoscriptInHead();
+                                    flushCharacters();
+                                    pop();
+                                    mode = IN_HEAD;
+                                    /*
+                                     * and reprocess the current token.
+                                     */
+                                    i--;
+                                    continue;
+                                case AFTER_HEAD:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+                                    /*
+                                     * Act as if a start tag token with the tag
+                                     * name "body" and no attributes had been
+                                     * seen,
+                                     */
+                                    flushCharacters();
+                                    appendToCurrentNodeAndPushBodyElement();
+                                    mode = FRAMESET_OK;
+                                    /*
+                                     * and then reprocess the current token.
+                                     */
+                                    i--;
+                                    continue;
+                                case FRAMESET_OK:
+                                    framesetOk = false;
+                                    mode = IN_BODY;
+                                    i--;
+                                    continue;
+                                case IN_TEMPLATE:
+                                case IN_BODY:
+                                case IN_CELL:
+                                case IN_CAPTION:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+                                    /*
+                                     * Reconstruct the active formatting
+                                     * elements, if any.
+                                     */
+                                    if (!isInForeignButNotHtmlOrMathTextIntegrationPoint()) {
+                                        flushCharacters();
+                                        reconstructTheActiveFormattingElements();
+                                    }
+                                    /*
+                                     * Append the token's character to the
+                                     * current node.
+                                     */
+                                    break charactersloop;
+                                case IN_TABLE:
+                                case IN_TABLE_BODY:
+                                case IN_ROW:
+                                    accumulateCharactersForced(buf, i, 1);
+                                    start = i + 1;
+                                    continue;
+                                case IN_COLUMN_GROUP:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        start = i;
+                                    }
+                                    /*
+                                     * Act as if an end tag with the tag name
+                                     * "colgroup" had been seen, and then, if
+                                     * that token wasn't ignored, reprocess the
+                                     * current token.
+                                     */
+                                    if (currentPtr == 0 || stack[currentPtr].getGroup() ==
+                                            TreeBuilder.TEMPLATE) {
+                                        errNonSpaceInColgroupInFragment();
+                                        start = i + 1;
+                                        continue;
+                                    }
+                                    flushCharacters();
+                                    pop();
+                                    mode = IN_TABLE;
+                                    i--;
+                                    continue;
+                                case IN_SELECT:
+                                case IN_SELECT_IN_TABLE:
+                                    break charactersloop;
+                                case AFTER_BODY:
+                                    errNonSpaceAfterBody();
+                                    fatal();
+                                    mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                                    i--;
+                                    continue;
+                                case IN_FRAMESET:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        // start index is adjusted below.
+                                    }
+                                    /*
+                                     * Parse error.
+                                     */
+                                    errNonSpaceInFrameset();
+                                    /*
+                                     * Ignore the token.
+                                     */
+                                    start = i + 1;
+                                    continue;
+                                case AFTER_FRAMESET:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        // start index is adjusted below.
+                                    }
+                                    /*
+                                     * Parse error.
+                                     */
+                                    errNonSpaceAfterFrameset();
+                                    /*
+                                     * Ignore the token.
+                                     */
+                                    start = i + 1;
+                                    continue;
+                                case AFTER_AFTER_BODY:
+                                    /*
+                                     * Parse error.
+                                     */
+                                    errNonSpaceInTrailer();
+                                    /*
+                                     * Switch back to the main mode and
+                                     * reprocess the token.
+                                     */
+                                    mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                                    i--;
+                                    continue;
+                                case AFTER_AFTER_FRAMESET:
+                                    if (start < i) {
+                                        accumulateCharacters(buf, start, i
+                                                - start);
+                                        // start index is adjusted below.
+                                    }
+                                    /*
+                                     * Parse error.
+                                     */
+                                    errNonSpaceInTrailer();
+                                    /*
+                                     * Ignore the token.
+                                     */
+                                    start = i + 1;
+                                    continue;
+                            }
+                    }
+                }
+                if (start < end) {
+                    accumulateCharacters(buf, start, end - start);
+                }
+        }
+    }
+
+    /**
+     * @see nu.validator.htmlparser.common.TokenHandler#zeroOriginatingReplacementCharacter()
+     */
+    public void zeroOriginatingReplacementCharacter() throws SAXException {
+        if (mode == TEXT) {
+            accumulateCharacters(REPLACEMENT_CHARACTER, 0, 1);
+            return;
+        }
+        if (currentPtr >= 0) {
+            if (isSpecialParentInForeign(stack[currentPtr])) {
+                return;
+            }
+            accumulateCharacters(REPLACEMENT_CHARACTER, 0, 1);
+        }
+    }
+
+    public final void eof() throws SAXException {
+        flushCharacters();
+        // Note: Can't attach error messages to EOF in C++ yet
+        eofloop: for (;;) {
+            switch (mode) {
+                case INITIAL:
+                    /*
+                     * Parse error.
+                     */
+                    // [NOCPP[
+                    switch (doctypeExpectation) {
+                        case AUTO:
+                            err("End of file seen without seeing a doctype first. Expected e.g. \u201C<!DOCTYPE html>\u201D.");
+                            break;
+                        case HTML:
+                            err("End of file seen without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D.");
+                            break;
+                        case HTML401_STRICT:
+                            err("End of file seen without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                            break;
+                        case HTML401_TRANSITIONAL:
+                            err("End of file seen without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                            break;
+                        case NO_DOCTYPE_ERRORS:
+                    }
+                    // ]NOCPP]
+                    /*
+                     *
+                     * Set the document to quirks mode.
+                     */
+                    documentModeInternal(DocumentMode.QUIRKS_MODE, null, null,
+                            false);
+                    /*
+                     * Then, switch to the root element mode of the tree
+                     * construction stage
+                     */
+                    mode = BEFORE_HTML;
+                    /*
+                     * and reprocess the current token.
+                     */
+                    continue;
+                case BEFORE_HTML:
+                    /*
+                     * Create an HTMLElement node with the tag name html, in the
+                     * HTML namespace. Append it to the Document object.
+                     */
+                    appendHtmlElementToDocumentAndPush();
+                    // XXX application cache manifest
+                    /* Switch to the main mode */
+                    mode = BEFORE_HEAD;
+                    /*
+                     * reprocess the current token.
+                     */
+                    continue;
+                case BEFORE_HEAD:
+                    appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES);
+                    mode = IN_HEAD;
+                    continue;
+                case IN_HEAD:
+                    // [NOCPP[
+                    if (errorHandler != null && currentPtr > 1) {
+                        errEofWithUnclosedElements();
+                    }
+                    // ]NOCPP]
+                    while (currentPtr > 0) {
+                        popOnEof();
+                    }
+                    mode = AFTER_HEAD;
+                    continue;
+                case IN_HEAD_NOSCRIPT:
+                    // [NOCPP[
+                    errEofWithUnclosedElements();
+                    // ]NOCPP]
+                    while (currentPtr > 1) {
+                        popOnEof();
+                    }
+                    mode = IN_HEAD;
+                    continue;
+                case AFTER_HEAD:
+                    appendToCurrentNodeAndPushBodyElement();
+                    mode = IN_BODY;
+                    continue;
+                case IN_TABLE_BODY:
+                case IN_ROW:
+                case IN_TABLE:
+                case IN_SELECT_IN_TABLE:
+                case IN_SELECT:
+                case IN_COLUMN_GROUP:
+                case FRAMESET_OK:
+                case IN_CAPTION:
+                case IN_CELL:
+                case IN_BODY:
+                    // [NOCPP[
+                    // i > 0 to stop in time in the foreign fragment case.
+                    openelementloop: for (int i = currentPtr; i > 0; i--) {
+                        int group = stack[i].getGroup();
+                        switch (group) {
+                            case DD_OR_DT:
+                            case LI:
+                            case P:
+                            case TBODY_OR_THEAD_OR_TFOOT:
+                            case TD_OR_TH:
+                            case BODY:
+                            case HTML:
+                                break;
+                            default:
+                                errEofWithUnclosedElements();
+                                break openelementloop;
+                        }
+                    }
+                    // ]NOCPP]
+
+                    if (isTemplateModeStackEmpty()) {
+                        break eofloop;
+                    }
+
+                    // fall through to IN_TEMPLATE
+                case IN_TEMPLATE:
+                    int eltPos = findLast("template");
+                    if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                        assert fragment;
+                        break eofloop;
+                    }
+                    if (errorHandler != null) {
+                        errUnclosedElements(eltPos, "template");
+                    }
+                    while (currentPtr >= eltPos) {
+                        pop();
+                    }
+                    clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+                    popTemplateMode();
+                    resetTheInsertionMode();
+
+                    // Reprocess token.
+                    continue;
+                case TEXT:
+                    // [NOCPP[
+                    if (errorHandler != null) {
+                        errNoCheck("End of file seen when expecting text or an end tag.");
+                        errListUnclosedStartTags(0);
+                    }
+                    // ]NOCPP]
+                    // XXX mark script as already executed
+                    if (originalMode == AFTER_HEAD) {
+                        popOnEof();
+                    }
+                    popOnEof();
+                    mode = originalMode;
+                    continue;
+                case IN_FRAMESET:
+                    // [NOCPP[
+                    if (errorHandler != null && currentPtr > 0) {
+                        errEofWithUnclosedElements();
+                    }
+                    // ]NOCPP]
+                    break eofloop;
+                case AFTER_BODY:
+                case AFTER_FRAMESET:
+                case AFTER_AFTER_BODY:
+                case AFTER_AFTER_FRAMESET:
+                default:
+                    // [NOCPP[
+                    if (currentPtr == 0) { // This silliness is here to poison
+                        // buggy compiler optimizations in
+                        // GWT
+                        System.currentTimeMillis();
+                    }
+                    // ]NOCPP]
+                    break eofloop;
+            }
+        }
+        while (currentPtr > 0) {
+            popOnEof();
+        }
+        if (!fragment) {
+            popOnEof();
+        }
+        /* Stop parsing. */
+    }
+
+    /**
+     * @see nu.validator.htmlparser.common.TokenHandler#endTokenization()
+     */
+    public final void endTokenization() throws SAXException {
+        formPointer = null;
+        headPointer = null;
+        deepTreeSurrogateParent = null;
+        templateModeStack = null;
+        if (stack != null) {
+            while (currentPtr > -1) {
+                stack[currentPtr].release();
+                currentPtr--;
+            }
+            stack = null;
+        }
+        if (listOfActiveFormattingElements != null) {
+            while (listPtr > -1) {
+                if (listOfActiveFormattingElements[listPtr] != null) {
+                    listOfActiveFormattingElements[listPtr].release();
+                }
+                listPtr--;
+            }
+            listOfActiveFormattingElements = null;
+        }
+        // [NOCPP[
+        idLocations.clear();
+        // ]NOCPP]
+        charBuffer = null;
+        end();
+    }
+
+    public final void startTag(ElementName elementName,
+            HtmlAttributes attributes, boolean selfClosing) throws SAXException {
+        flushCharacters();
+
+        // [NOCPP[
+        if (errorHandler != null) {
+            // ID uniqueness
+            @IdType String id = attributes.getId();
+            if (id != null) {
+                LocatorImpl oldLoc = idLocations.get(id);
+                if (oldLoc != null) {
+                    err("Duplicate ID \u201C" + id + "\u201D.");
+                    errorHandler.warning(new SAXParseException(
+                            "The first occurrence of ID \u201C" + id
+                            + "\u201D was here.", oldLoc));
+                } else {
+                    idLocations.put(id, new LocatorImpl(tokenizer));
+                }
+            }
+        }
+        // ]NOCPP]
+
+        int eltPos;
+        needToDropLF = false;
+        starttagloop: for (;;) {
+            int group = elementName.getGroup();
+            @Local String name = elementName.name;
+            if (isInForeign()) {
+                StackNode<T> currentNode = stack[currentPtr];
+                @NsUri String currNs = currentNode.ns;
+                if (!(currentNode.isHtmlIntegrationPoint() || (currNs == "http://www.w3.org/1998/Math/MathML" && ((currentNode.getGroup() == MI_MO_MN_MS_MTEXT && group != MGLYPH_OR_MALIGNMARK) || (currentNode.getGroup() == ANNOTATION_XML && group == SVG))))) {
+                    switch (group) {
+                        case B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U:
+                        case DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU:
+                        case BODY:
+                        case BR:
+                        case RUBY_OR_SPAN_OR_SUB_OR_SUP_OR_VAR:
+                        case DD_OR_DT:
+                        case UL_OR_OL_OR_DL:
+                        case EMBED:
+                        case IMG:
+                        case H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6:
+                        case HEAD:
+                        case HR:
+                        case LI:
+                        case META:
+                        case NOBR:
+                        case P:
+                        case PRE_OR_LISTING:
+                        case TABLE:
+                        case FONT:
+                            // re-check FONT to deal with the special case
+                            if (!(group == FONT && !(attributes.contains(AttributeName.COLOR)
+                                    || attributes.contains(AttributeName.FACE) || attributes.contains(AttributeName.SIZE)))) {
+                                errHtmlStartTagInForeignContext(name);
+                                if (!fragment) {
+                                    while (!isSpecialParentInForeign(stack[currentPtr])) {
+                                        pop();
+                                    }
+                                    continue starttagloop;
+                                } // else fall thru
+                            }
+                            // else fall thru
+                        default:
+                            if ("http://www.w3.org/2000/svg" == currNs) {
+                                attributes.adjustForSvg();
+                                if (selfClosing) {
+                                    appendVoidElementToCurrentMayFosterSVG(
+                                            elementName, attributes);
+                                    selfClosing = false;
+                                } else {
+                                    appendToCurrentNodeAndPushElementMayFosterSVG(
+                                            elementName, attributes);
+                                }
+                                attributes = null; // CPP
+                                break starttagloop;
+                            } else {
+                                attributes.adjustForMath();
+                                if (selfClosing) {
+                                    appendVoidElementToCurrentMayFosterMathML(
+                                            elementName, attributes);
+                                    selfClosing = false;
+                                } else {
+                                    appendToCurrentNodeAndPushElementMayFosterMathML(
+                                            elementName, attributes);
+                                }
+                                attributes = null; // CPP
+                                break starttagloop;
+                            }
+                    } // switch
+                } // foreignObject / annotation-xml
+            }
+            switch (mode) {
+                case IN_TEMPLATE:
+                    switch (group) {
+                        case COL:
+                            popTemplateMode();
+                            pushTemplateMode(IN_COLUMN_GROUP);
+                            mode = IN_COLUMN_GROUP;
+                            // Reprocess token.
+                            continue;
+                        case CAPTION:
+                        case COLGROUP:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                            popTemplateMode();
+                            pushTemplateMode(IN_TABLE);
+                            mode = IN_TABLE;
+                            // Reprocess token.
+                            continue;
+                        case TR:
+                            popTemplateMode();
+                            pushTemplateMode(IN_TABLE_BODY);
+                            mode = IN_TABLE_BODY;
+                            // Reprocess token.
+                            continue;
+                        case TD_OR_TH:
+                            popTemplateMode();
+                            pushTemplateMode(IN_ROW);
+                            mode = IN_ROW;
+                            // Reprocess token.
+                            continue;
+                        case META:
+                            checkMetaCharset(attributes);
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case TITLE:
+                            startTagTitleInHead(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case BASE:
+                        case LINK_OR_BASEFONT_OR_BGSOUND:
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case SCRIPT:
+                            startTagScriptInHead(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case NOFRAMES:
+                        case STYLE:
+                            startTagGenericRawText(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case TEMPLATE:
+                            startTagTemplateInHead(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            popTemplateMode();
+                            pushTemplateMode(IN_BODY);
+                            mode = IN_BODY;
+                            // Reprocess token.
+                            continue;
+                    }
+                case IN_ROW:
+                    switch (group) {
+                        case TD_OR_TH:
+                            clearStackBackTo(findLastOrRoot(TreeBuilder.TR));
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            mode = IN_CELL;
+                            insertMarker();
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TR:
+                            eltPos = findLastOrRoot(TreeBuilder.TR);
+                            if (eltPos == 0) {
+                                assert fragment || isTemplateContents();
+                                errNoTableRowToClose();
+                                break starttagloop;
+                            }
+                            clearStackBackTo(eltPos);
+                            pop();
+                            mode = IN_TABLE_BODY;
+                            continue;
+                        default:
+                            // fall through to IN_TABLE
+                    }
+                case IN_TABLE_BODY:
+                    switch (group) {
+                        case TR:
+                            clearStackBackTo(findLastInTableScopeOrRootTemplateTbodyTheadTfoot());
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            mode = IN_ROW;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case TD_OR_TH:
+                            errStartTagInTableBody(name);
+                            clearStackBackTo(findLastInTableScopeOrRootTemplateTbodyTheadTfoot());
+                            appendToCurrentNodeAndPushElement(
+                                    ElementName.TR,
+                                    HtmlAttributes.EMPTY_ATTRIBUTES);
+                            mode = IN_ROW;
+                            continue;
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                            eltPos = findLastInTableScopeOrRootTemplateTbodyTheadTfoot();
+                            if (eltPos == 0 || stack[eltPos].getGroup() == TEMPLATE) {
+                                assert fragment || isTemplateContents();
+                                errStrayStartTag(name);
+                                break starttagloop;
+                            } else {
+                                clearStackBackTo(eltPos);
+                                pop();
+                                mode = IN_TABLE;
+                                continue;
+                            }
+                        default:
+                            // fall through to IN_TABLE
+                    }
+                case IN_TABLE:
+                    intableloop: for (;;) {
+                        switch (group) {
+                            case CAPTION:
+                                clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE));
+                                insertMarker();
+                                appendToCurrentNodeAndPushElement(
+                                        elementName,
+                                        attributes);
+                                mode = IN_CAPTION;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case COLGROUP:
+                                clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE));
+                                appendToCurrentNodeAndPushElement(
+                                        elementName,
+                                        attributes);
+                                mode = IN_COLUMN_GROUP;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case COL:
+                                clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE));
+                                appendToCurrentNodeAndPushElement(
+                                        ElementName.COLGROUP,
+                                        HtmlAttributes.EMPTY_ATTRIBUTES);
+                                mode = IN_COLUMN_GROUP;
+                                continue starttagloop;
+                            case TBODY_OR_THEAD_OR_TFOOT:
+                                clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE));
+                                appendToCurrentNodeAndPushElement(
+                                        elementName,
+                                        attributes);
+                                mode = IN_TABLE_BODY;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case TR:
+                            case TD_OR_TH:
+                                clearStackBackTo(findLastOrRoot(TreeBuilder.TABLE));
+                                appendToCurrentNodeAndPushElement(
+                                        ElementName.TBODY,
+                                        HtmlAttributes.EMPTY_ATTRIBUTES);
+                                mode = IN_TABLE_BODY;
+                                continue starttagloop;
+                            case TEMPLATE:
+                                // fall through to IN_HEAD
+                                break intableloop;
+                            case TABLE:
+                                errTableSeenWhileTableOpen();
+                                eltPos = findLastInTableScope(name);
+                                if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                    assert fragment || isTemplateContents();
+                                    break starttagloop;
+                                }
+                                generateImpliedEndTags();
+                                if (errorHandler != null && !isCurrent("table")) {
+                                    errNoCheckUnclosedElementsOnStack();
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                                resetTheInsertionMode();
+                                continue starttagloop;
+                            case SCRIPT:
+                                // XXX need to manage much more stuff
+                                // here if
+                                // supporting
+                                // document.write()
+                                appendToCurrentNodeAndPushElement(
+                                        elementName,
+                                        attributes);
+                                originalMode = mode;
+                                mode = TEXT;
+                                tokenizer.setStateAndEndTagExpectation(
+                                        Tokenizer.SCRIPT_DATA, elementName);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case STYLE:
+                                appendToCurrentNodeAndPushElement(
+                                        elementName,
+                                        attributes);
+                                originalMode = mode;
+                                mode = TEXT;
+                                tokenizer.setStateAndEndTagExpectation(
+                                        Tokenizer.RAWTEXT, elementName);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case INPUT:
+                                errStartTagInTable(name);
+                                if (!Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                                        "hidden",
+                                        attributes.getValue(AttributeName.TYPE))) {
+                                    break intableloop;
+                                }
+                                appendVoidElementToCurrent(
+                                        name, attributes,
+                                        formPointer);
+                                selfClosing = false;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case FORM:
+                                if (formPointer != null || isTemplateContents()) {
+                                    errFormWhenFormOpen();
+                                    break starttagloop;
+                                } else {
+                                    errStartTagInTable(name);
+                                    appendVoidFormToCurrent(attributes);
+                                    attributes = null; // CPP
+                                    break starttagloop;
+                                }
+                            default:
+                                errStartTagInTable(name);
+                                // fall through to IN_BODY
+                                break intableloop;
+                        }
+                    }
+                case IN_CAPTION:
+                    switch (group) {
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TR:
+                        case TD_OR_TH:
+                            errStrayStartTag(name);
+                            eltPos = findLastInTableScope("caption");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                break starttagloop;
+                            }
+                            generateImpliedEndTags();
+                            if (errorHandler != null && currentPtr != eltPos) {
+                                errNoCheckUnclosedElementsOnStack();
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+                            mode = IN_TABLE;
+                            continue;
+                        default:
+                            // fall through to IN_BODY
+                    }
+                case IN_CELL:
+                    switch (group) {
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TR:
+                        case TD_OR_TH:
+                            eltPos = findLastInTableScopeTdTh();
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errNoCellToClose();
+                                break starttagloop;
+                            } else {
+                                closeTheCell(eltPos);
+                                continue;
+                            }
+                        default:
+                            // fall through to IN_BODY
+                    }
+                case FRAMESET_OK:
+                    switch (group) {
+                        case FRAMESET:
+                            if (mode == FRAMESET_OK) {
+                                if (currentPtr == 0 || stack[1].getGroup() != BODY) {
+                                    assert fragment || isTemplateContents();
+                                    errStrayStartTag(name);
+                                    break starttagloop;
+                                } else {
+                                    errFramesetStart();
+                                    detachFromParent(stack[1].node);
+                                    while (currentPtr > 0) {
+                                        pop();
+                                    }
+                                    appendToCurrentNodeAndPushElement(
+                                            elementName,
+                                            attributes);
+                                    mode = IN_FRAMESET;
+                                    attributes = null; // CPP
+                                    break starttagloop;
+                                }
+                            } else {
+                                errStrayStartTag(name);
+                                break starttagloop;
+                            }
+                            // NOT falling through!
+                        case PRE_OR_LISTING:
+                        case LI:
+                        case DD_OR_DT:
+                        case BUTTON:
+                        case MARQUEE_OR_APPLET:
+                        case OBJECT:
+                        case TABLE:
+                        case AREA_OR_WBR:
+                        case BR:
+                        case EMBED:
+                        case IMG:
+                        case INPUT:
+                        case KEYGEN:
+                        case HR:
+                        case TEXTAREA:
+                        case XMP:
+                        case IFRAME:
+                        case SELECT:
+                            if (mode == FRAMESET_OK
+                                    && !(group == INPUT && Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                                            "hidden",
+                                            attributes.getValue(AttributeName.TYPE)))) {
+                                framesetOk = false;
+                                mode = IN_BODY;
+                            }
+                            // fall through to IN_BODY
+                        default:
+                            // fall through to IN_BODY
+                    }
+                case IN_BODY:
+                    inbodyloop: for (;;) {
+                        switch (group) {
+                            case HTML:
+                                errStrayStartTag(name);
+                                if (!fragment && !isTemplateContents()) {
+                                    addAttributesToHtml(attributes);
+                                    attributes = null; // CPP
+                                }
+                                break starttagloop;
+                            case BASE:
+                            case LINK_OR_BASEFONT_OR_BGSOUND:
+                            case META:
+                            case STYLE:
+                            case SCRIPT:
+                            case TITLE:
+                            case TEMPLATE:
+                                // Fall through to IN_HEAD
+                                break inbodyloop;
+                            case BODY:
+                                if (currentPtr == 0 || stack[1].getGroup() != BODY || isTemplateContents()) {
+                                    assert fragment || isTemplateContents();
+                                    errStrayStartTag(name);
+                                    break starttagloop;
+                                }
+                                errFooSeenWhenFooOpen(name);
+                                framesetOk = false;
+                                if (mode == FRAMESET_OK) {
+                                    mode = IN_BODY;
+                                }
+                                if (addAttributesToBody(attributes)) {
+                                    attributes = null; // CPP
+                                }
+                                break starttagloop;
+                            case P:
+                            case DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU:
+                            case UL_OR_OL_OR_DL:
+                            case ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY:
+                                implicitlyCloseP();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6:
+                                implicitlyCloseP();
+                                if (stack[currentPtr].getGroup() == H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6) {
+                                    errHeadingWhenHeadingOpen();
+                                    pop();
+                                }
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case FIELDSET:
+                                implicitlyCloseP();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes, formPointer);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case PRE_OR_LISTING:
+                                implicitlyCloseP();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                needToDropLF = true;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case FORM:
+                                if (formPointer != null && !isTemplateContents()) {
+                                    errFormWhenFormOpen();
+                                    break starttagloop;
+                                } else {
+                                    implicitlyCloseP();
+                                    appendToCurrentNodeAndPushFormElementMayFoster(attributes);
+                                    attributes = null; // CPP
+                                    break starttagloop;
+                                }
+                            case LI:
+                            case DD_OR_DT:
+                                eltPos = currentPtr;
+                                for (;;) {
+                                    StackNode<T> node = stack[eltPos]; // weak
+                                    // ref
+                                    if (node.getGroup() == group) { // LI or
+                                        // DD_OR_DT
+                                        generateImpliedEndTagsExceptFor(node.name);
+                                        if (errorHandler != null
+                                                && eltPos != currentPtr) {
+                                            errUnclosedElementsImplied(eltPos, name);
+                                        }
+                                        while (currentPtr >= eltPos) {
+                                            pop();
+                                        }
+                                        break;
+                                    } else if (eltPos == 0 || (node.isSpecial()
+                                            && (node.ns != "http://www.w3.org/1999/xhtml"
+                                                    || (node.name != "p"
+                                                            && node.name != "address"
+                                                            && node.name != "div")))) {
+                                        break;
+                                    }
+                                    eltPos--;
+                                }
+                                implicitlyCloseP();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case PLAINTEXT:
+                                implicitlyCloseP();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                tokenizer.setStateAndEndTagExpectation(
+                                        Tokenizer.PLAINTEXT, elementName);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case A:
+                                int activeAPos = findInListOfActiveFormattingElementsContainsBetweenEndAndLastMarker("a");
+                                if (activeAPos != -1) {
+                                    errFooSeenWhenFooOpen(name);
+                                    StackNode<T> activeA = listOfActiveFormattingElements[activeAPos];
+                                    activeA.retain();
+                                    adoptionAgencyEndTag("a");
+                                    removeFromStack(activeA);
+                                    activeAPos = findInListOfActiveFormattingElements(activeA);
+                                    if (activeAPos != -1) {
+                                        removeFromListOfActiveFormattingElements(activeAPos);
+                                    }
+                                    activeA.release();
+                                }
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushFormattingElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U:
+                            case FONT:
+                                reconstructTheActiveFormattingElements();
+                                maybeForgetEarlierDuplicateFormattingElement(elementName.name, attributes);
+                                appendToCurrentNodeAndPushFormattingElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case NOBR:
+                                reconstructTheActiveFormattingElements();
+                                if (TreeBuilder.NOT_FOUND_ON_STACK != findLastInScope("nobr")) {
+                                    errFooSeenWhenFooOpen(name);
+                                    adoptionAgencyEndTag("nobr");
+                                    reconstructTheActiveFormattingElements();
+                                }
+                                appendToCurrentNodeAndPushFormattingElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case BUTTON:
+                                eltPos = findLastInScope(name);
+                                if (eltPos != TreeBuilder.NOT_FOUND_ON_STACK) {
+                                    errFooSeenWhenFooOpen(name);
+                                    generateImpliedEndTags();
+                                    if (errorHandler != null
+                                            && !isCurrent(name)) {
+                                        errUnclosedElementsImplied(eltPos, name);
+                                    }
+                                    while (currentPtr >= eltPos) {
+                                        pop();
+                                    }
+                                    continue starttagloop;
+                                } else {
+                                    reconstructTheActiveFormattingElements();
+                                    appendToCurrentNodeAndPushElementMayFoster(
+                                            elementName,
+                                            attributes, formPointer);
+                                    attributes = null; // CPP
+                                    break starttagloop;
+                                }
+                            case OBJECT:
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes, formPointer);
+                                insertMarker();
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case MARQUEE_OR_APPLET:
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                insertMarker();
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case TABLE:
+                                // The only quirk. Blame Hixie and
+                                // Acid2.
+                                if (!quirks) {
+                                    implicitlyCloseP();
+                                }
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                mode = IN_TABLE;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case BR:
+                            case EMBED:
+                            case AREA_OR_WBR:
+                                reconstructTheActiveFormattingElements();
+                                // FALL THROUGH to PARAM_OR_SOURCE_OR_TRACK
+                            // CPPONLY: case MENUITEM:
+                            case PARAM_OR_SOURCE_OR_TRACK:
+                                appendVoidElementToCurrentMayFoster(
+                                        elementName,
+                                        attributes);
+                                selfClosing = false;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case HR:
+                                implicitlyCloseP();
+                                appendVoidElementToCurrentMayFoster(
+                                        elementName,
+                                        attributes);
+                                selfClosing = false;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case IMAGE:
+                                errImage();
+                                elementName = ElementName.IMG;
+                                continue starttagloop;
+                            case IMG:
+                            case KEYGEN:
+                            case INPUT:
+                                reconstructTheActiveFormattingElements();
+                                appendVoidElementToCurrentMayFoster(
+                                        name, attributes,
+                                        formPointer);
+                                selfClosing = false;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case ISINDEX:
+                                errIsindex();
+                                if (formPointer != null && !isTemplateContents()) {
+                                    break starttagloop;
+                                }
+                                implicitlyCloseP();
+                                HtmlAttributes formAttrs = new HtmlAttributes(0);
+                                int actionIndex = attributes.getIndex(AttributeName.ACTION);
+                                if (actionIndex > -1) {
+                                    formAttrs.addAttribute(
+                                            AttributeName.ACTION,
+                                            attributes.getValueNoBoundsCheck(actionIndex)
+                                            // [NOCPP[
+                                            , XmlViolationPolicy.ALLOW
+                                    // ]NOCPP]
+                                            // CPPONLY: , attributes.getLineNoBoundsCheck(actionIndex)
+                                    );
+                                }
+                                appendToCurrentNodeAndPushFormElementMayFoster(formAttrs);
+                                appendVoidElementToCurrentMayFoster(
+                                        ElementName.HR,
+                                        HtmlAttributes.EMPTY_ATTRIBUTES);
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        ElementName.LABEL,
+                                        HtmlAttributes.EMPTY_ATTRIBUTES);
+                                int promptIndex = attributes.getIndex(AttributeName.PROMPT);
+                                if (promptIndex > -1) {
+                                    @Auto char[] prompt = Portability.newCharArrayFromString(attributes.getValueNoBoundsCheck(promptIndex));
+                                    appendCharacters(stack[currentPtr].node,
+                                            prompt, 0, prompt.length);
+                                } else {
+                                    appendIsindexPrompt(stack[currentPtr].node);
+                                }
+                                HtmlAttributes inputAttributes = new HtmlAttributes(
+                                        0);
+                                inputAttributes.addAttribute(
+                                        AttributeName.NAME,
+                                        Portability.newStringFromLiteral("isindex")
+                                        // [NOCPP[
+                                        , XmlViolationPolicy.ALLOW
+                                // ]NOCPP]
+                                // CPPONLY: , tokenizer.getLineNumber()
+                                );
+                                for (int i = 0; i < attributes.getLength(); i++) {
+                                    AttributeName attributeQName = attributes.getAttributeNameNoBoundsCheck(i);
+                                    if (AttributeName.NAME == attributeQName
+                                            || AttributeName.PROMPT == attributeQName) {
+                                        attributes.releaseValue(i);
+                                    } else if (AttributeName.ACTION != attributeQName) {
+                                        inputAttributes.addAttribute(
+                                                attributeQName,
+                                                attributes.getValueNoBoundsCheck(i)
+                                                // [NOCPP[
+                                                , XmlViolationPolicy.ALLOW
+                                        // ]NOCPP]
+                                        // CPPONLY: , attributes.getLineNoBoundsCheck(i)
+                                        );
+                                    }
+                                }
+                                attributes.clearWithoutReleasingContents();
+                                appendVoidElementToCurrentMayFoster(
+                                        "input",
+                                        inputAttributes, formPointer);
+                                pop(); // label
+                                appendVoidElementToCurrentMayFoster(
+                                        ElementName.HR,
+                                        HtmlAttributes.EMPTY_ATTRIBUTES);
+                                pop(); // form
+
+                                if (!isTemplateContents()) {
+                                    formPointer = null;
+                                }
+
+                                selfClosing = false;
+                                // Portability.delete(formAttrs);
+                                // Portability.delete(inputAttributes);
+                                // Don't delete attributes, they are deleted
+                                // later
+                                break starttagloop;
+                            case TEXTAREA:
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes, formPointer);
+                                tokenizer.setStateAndEndTagExpectation(
+                                        Tokenizer.RCDATA, elementName);
+                                originalMode = mode;
+                                mode = TEXT;
+                                needToDropLF = true;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case XMP:
+                                implicitlyCloseP();
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                originalMode = mode;
+                                mode = TEXT;
+                                tokenizer.setStateAndEndTagExpectation(
+                                        Tokenizer.RAWTEXT, elementName);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case NOSCRIPT:
+                                if (!scriptingEnabled) {
+                                    reconstructTheActiveFormattingElements();
+                                    appendToCurrentNodeAndPushElementMayFoster(
+                                            elementName,
+                                            attributes);
+                                    attributes = null; // CPP
+                                    break starttagloop;
+                                } else {
+                                    // fall through
+                                }
+                            case NOFRAMES:
+                            case IFRAME:
+                            case NOEMBED:
+                                startTagGenericRawText(elementName, attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case SELECT:
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes, formPointer);
+                                switch (mode) {
+                                    case IN_TABLE:
+                                    case IN_CAPTION:
+                                    case IN_COLUMN_GROUP:
+                                    case IN_TABLE_BODY:
+                                    case IN_ROW:
+                                    case IN_CELL:
+                                        mode = IN_SELECT_IN_TABLE;
+                                        break;
+                                    default:
+                                        mode = IN_SELECT;
+                                        break;
+                                }
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case OPTGROUP:
+                            case OPTION:
+                                if (isCurrent("option")) {
+                                    pop();
+                                }
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case RB_OR_RTC:
+                                eltPos = findLastInScope("ruby");
+                                if (eltPos != NOT_FOUND_ON_STACK) {
+                                    generateImpliedEndTags();
+                                }
+                                if (eltPos != currentPtr) {
+                                    if (eltPos == NOT_FOUND_ON_STACK) {
+                                        errStartTagSeenWithoutRuby(name);
+                                    } else {
+                                        errUnclosedChildrenInRuby();
+                                    }
+                                }
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case RT_OR_RP:
+                                eltPos = findLastInScope("ruby");
+                                if (eltPos != NOT_FOUND_ON_STACK) {
+                                    generateImpliedEndTagsExceptFor("rtc");
+                                }
+                                if (eltPos != currentPtr) {
+                                    if (!isCurrent("rtc")) {
+                                        if (eltPos == NOT_FOUND_ON_STACK) {
+                                            errStartTagSeenWithoutRuby(name);
+                                        } else {
+                                            errUnclosedChildrenInRuby();
+                                        }
+                                    }
+                                }
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case MATH:
+                                reconstructTheActiveFormattingElements();
+                                attributes.adjustForMath();
+                                if (selfClosing) {
+                                    appendVoidElementToCurrentMayFosterMathML(
+                                            elementName, attributes);
+                                    selfClosing = false;
+                                } else {
+                                    appendToCurrentNodeAndPushElementMayFosterMathML(
+                                            elementName, attributes);
+                                }
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case SVG:
+                                reconstructTheActiveFormattingElements();
+                                attributes.adjustForSvg();
+                                if (selfClosing) {
+                                    appendVoidElementToCurrentMayFosterSVG(
+                                            elementName,
+                                            attributes);
+                                    selfClosing = false;
+                                } else {
+                                    appendToCurrentNodeAndPushElementMayFosterSVG(
+                                            elementName, attributes);
+                                }
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case CAPTION:
+                            case COL:
+                            case COLGROUP:
+                            case TBODY_OR_THEAD_OR_TFOOT:
+                            case TR:
+                            case TD_OR_TH:
+                            case FRAME:
+                            case FRAMESET:
+                            case HEAD:
+                                errStrayStartTag(name);
+                                break starttagloop;
+                            case OUTPUT:
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes, formPointer);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            default:
+                                reconstructTheActiveFormattingElements();
+                                appendToCurrentNodeAndPushElementMayFoster(
+                                        elementName,
+                                        attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                        }
+                    }
+                case IN_HEAD:
+                    inheadloop: for (;;) {
+                        switch (group) {
+                            case HTML:
+                                errStrayStartTag(name);
+                                if (!fragment && !isTemplateContents()) {
+                                    addAttributesToHtml(attributes);
+                                    attributes = null; // CPP
+                                }
+                                break starttagloop;
+                            case BASE:
+                            case LINK_OR_BASEFONT_OR_BGSOUND:
+                                appendVoidElementToCurrentMayFoster(
+                                        elementName,
+                                        attributes);
+                                selfClosing = false;
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case META:
+                                // Fall through to IN_HEAD_NOSCRIPT
+                                break inheadloop;
+                            case TITLE:
+                                startTagTitleInHead(elementName, attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case NOSCRIPT:
+                                if (scriptingEnabled) {
+                                    appendToCurrentNodeAndPushElement(
+                                            elementName,
+                                            attributes);
+                                    originalMode = mode;
+                                    mode = TEXT;
+                                    tokenizer.setStateAndEndTagExpectation(
+                                            Tokenizer.RAWTEXT, elementName);
+                                } else {
+                                    appendToCurrentNodeAndPushElementMayFoster(
+                                            elementName,
+                                            attributes);
+                                    mode = IN_HEAD_NOSCRIPT;
+                                }
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case SCRIPT:
+                                startTagScriptInHead(elementName, attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case STYLE:
+                            case NOFRAMES:
+                                startTagGenericRawText(elementName, attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            case HEAD:
+                                /* Parse error. */
+                                errFooSeenWhenFooOpen(name);
+                                /* Ignore the token. */
+                                break starttagloop;
+                            case TEMPLATE:
+                                startTagTemplateInHead(elementName, attributes);
+                                attributes = null; // CPP
+                                break starttagloop;
+                            default:
+                                pop();
+                                mode = AFTER_HEAD;
+                                continue starttagloop;
+                        }
+                    }
+                case IN_HEAD_NOSCRIPT:
+                    switch (group) {
+                        case HTML:
+                            // XXX did Hixie really mean to omit "base"
+                            // here?
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        case LINK_OR_BASEFONT_OR_BGSOUND:
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case META:
+                            checkMetaCharset(attributes);
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case STYLE:
+                        case NOFRAMES:
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            originalMode = mode;
+                            mode = TEXT;
+                            tokenizer.setStateAndEndTagExpectation(
+                                    Tokenizer.RAWTEXT, elementName);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case HEAD:
+                            errFooSeenWhenFooOpen(name);
+                            break starttagloop;
+                        case NOSCRIPT:
+                            errFooSeenWhenFooOpen(name);
+                            break starttagloop;
+                        default:
+                            errBadStartTagInHead(name);
+                            pop();
+                            mode = IN_HEAD;
+                            continue;
+                    }
+                case IN_COLUMN_GROUP:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        case COL:
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case TEMPLATE:
+                            startTagTemplateInHead(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            if (currentPtr == 0 || stack[currentPtr].getGroup() == TEMPLATE) {
+                                assert fragment || isTemplateContents();
+                                errGarbageInColgroup();
+                                break starttagloop;
+                            }
+                            pop();
+                            mode = IN_TABLE;
+                            continue;
+                    }
+                case IN_SELECT_IN_TABLE:
+                    switch (group) {
+                        case CAPTION:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TR:
+                        case TD_OR_TH:
+                        case TABLE:
+                            errStartTagWithSelectOpen(name);
+                            eltPos = findLastInTableScope("select");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                assert fragment;
+                                break starttagloop; // http://www.w3.org/Bugs/Public/show_bug.cgi?id=8375
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            resetTheInsertionMode();
+                            continue;
+                        default:
+                            // fall through to IN_SELECT
+                    }
+                case IN_SELECT:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        case OPTION:
+                            if (isCurrent("option")) {
+                                pop();
+                            }
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case OPTGROUP:
+                            if (isCurrent("option")) {
+                                pop();
+                            }
+                            if (isCurrent("optgroup")) {
+                                pop();
+                            }
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case SELECT:
+                            errStartSelectWhereEndSelectExpected();
+                            eltPos = findLastInTableScope(name);
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                assert fragment;
+                                errNoSelectInTableScope();
+                                break starttagloop;
+                            } else {
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                                resetTheInsertionMode();
+                                break starttagloop;
+                            }
+                        case INPUT:
+                        case TEXTAREA:
+                        case KEYGEN:
+                            errStartTagWithSelectOpen(name);
+                            eltPos = findLastInTableScope("select");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                assert fragment;
+                                break starttagloop;
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            resetTheInsertionMode();
+                            continue;
+                        case SCRIPT:
+                            startTagScriptInHead(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case TEMPLATE:
+                            startTagTemplateInHead(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            errStrayStartTag(name);
+                            break starttagloop;
+                    }
+                case AFTER_BODY:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        default:
+                            errStrayStartTag(name);
+                            mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                            continue;
+                    }
+                case IN_FRAMESET:
+                    switch (group) {
+                        case FRAMESET:
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case FRAME:
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            // fall through to AFTER_FRAMESET
+                    }
+                case AFTER_FRAMESET:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        case NOFRAMES:
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            originalMode = mode;
+                            mode = TEXT;
+                            tokenizer.setStateAndEndTagExpectation(
+                                    Tokenizer.RAWTEXT, elementName);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            errStrayStartTag(name);
+                            break starttagloop;
+                    }
+                case INITIAL:
+                    /*
+                     * Parse error.
+                     */
+                    // [NOCPP[
+                    switch (doctypeExpectation) {
+                        case AUTO:
+                            err("Start tag seen without seeing a doctype first. Expected e.g. \u201C<!DOCTYPE html>\u201D.");
+                            break;
+                        case HTML:
+                            // ]NOCPP]
+                            errStartTagWithoutDoctype();
+                            // [NOCPP[
+                            break;
+                        case HTML401_STRICT:
+                            err("Start tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                            break;
+                        case HTML401_TRANSITIONAL:
+                            err("Start tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                            break;
+                        case NO_DOCTYPE_ERRORS:
+                    }
+                    // ]NOCPP]
+                    /*
+                     *
+                     * Set the document to quirks mode.
+                     */
+                    documentModeInternal(DocumentMode.QUIRKS_MODE, null, null,
+                            false);
+                    /*
+                     * Then, switch to the root element mode of the tree
+                     * construction stage
+                     */
+                    mode = BEFORE_HTML;
+                    /*
+                     * and reprocess the current token.
+                     */
+                    continue;
+                case BEFORE_HTML:
+                    switch (group) {
+                        case HTML:
+                            // optimize error check and streaming SAX by
+                            // hoisting
+                            // "html" handling here.
+                            if (attributes == HtmlAttributes.EMPTY_ATTRIBUTES) {
+                                // This has the right magic side effect
+                                // that
+                                // it
+                                // makes attributes in SAX Tree mutable.
+                                appendHtmlElementToDocumentAndPush();
+                            } else {
+                                appendHtmlElementToDocumentAndPush(attributes);
+                            }
+                            // XXX application cache should fire here
+                            mode = BEFORE_HEAD;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            /*
+                             * Create an HTMLElement node with the tag name
+                             * html, in the HTML namespace. Append it to the
+                             * Document object.
+                             */
+                            appendHtmlElementToDocumentAndPush();
+                            /* Switch to the main mode */
+                            mode = BEFORE_HEAD;
+                            /*
+                             * reprocess the current token.
+                             */
+                            continue;
+                    }
+                case BEFORE_HEAD:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        case HEAD:
+                            /*
+                             * A start tag whose tag name is "head"
+                             *
+                             * Create an element for the token.
+                             *
+                             * Set the head element pointer to this new element
+                             * node.
+                             *
+                             * Append the new element to the current node and
+                             * push it onto the stack of open elements.
+                             */
+                            appendToCurrentNodeAndPushHeadElement(attributes);
+                            /*
+                             * Change the insertion mode to "in head".
+                             */
+                            mode = IN_HEAD;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            /*
+                             * Any other start tag token
+                             *
+                             * Act as if a start tag token with the tag name
+                             * "head" and no attributes had been seen,
+                             */
+                            appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES);
+                            mode = IN_HEAD;
+                            /*
+                             * then reprocess the current token.
+                             *
+                             * This will result in an empty head element being
+                             * generated, with the current token being
+                             * reprocessed in the "after head" insertion mode.
+                             */
+                            continue;
+                    }
+                case AFTER_HEAD:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        case BODY:
+                            if (attributes.getLength() == 0) {
+                                // This has the right magic side effect
+                                // that
+                                // it
+                                // makes attributes in SAX Tree mutable.
+                                appendToCurrentNodeAndPushBodyElement();
+                            } else {
+                                appendToCurrentNodeAndPushBodyElement(attributes);
+                            }
+                            framesetOk = false;
+                            mode = IN_BODY;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case FRAMESET:
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            mode = IN_FRAMESET;
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case TEMPLATE:
+                            errFooBetweenHeadAndBody(name);
+                            pushHeadPointerOntoStack();
+                            StackNode<T> headOnStack = stack[currentPtr];
+                            startTagTemplateInHead(elementName, attributes);
+                            removeFromStack(headOnStack);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case BASE:
+                        case LINK_OR_BASEFONT_OR_BGSOUND:
+                            errFooBetweenHeadAndBody(name);
+                            pushHeadPointerOntoStack();
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            pop(); // head
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case META:
+                            errFooBetweenHeadAndBody(name);
+                            checkMetaCharset(attributes);
+                            pushHeadPointerOntoStack();
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    attributes);
+                            selfClosing = false;
+                            pop(); // head
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case SCRIPT:
+                            errFooBetweenHeadAndBody(name);
+                            pushHeadPointerOntoStack();
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            originalMode = mode;
+                            mode = TEXT;
+                            tokenizer.setStateAndEndTagExpectation(
+                                    Tokenizer.SCRIPT_DATA, elementName);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case STYLE:
+                        case NOFRAMES:
+                            errFooBetweenHeadAndBody(name);
+                            pushHeadPointerOntoStack();
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            originalMode = mode;
+                            mode = TEXT;
+                            tokenizer.setStateAndEndTagExpectation(
+                                    Tokenizer.RAWTEXT, elementName);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case TITLE:
+                            errFooBetweenHeadAndBody(name);
+                            pushHeadPointerOntoStack();
+                            appendToCurrentNodeAndPushElement(
+                                    elementName,
+                                    attributes);
+                            originalMode = mode;
+                            mode = TEXT;
+                            tokenizer.setStateAndEndTagExpectation(
+                                    Tokenizer.RCDATA, elementName);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        case HEAD:
+                            errStrayStartTag(name);
+                            break starttagloop;
+                        default:
+                            appendToCurrentNodeAndPushBodyElement();
+                            mode = FRAMESET_OK;
+                            continue;
+                    }
+                case AFTER_AFTER_BODY:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        default:
+                            errStrayStartTag(name);
+                            fatal();
+                            mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                            continue;
+                    }
+                case AFTER_AFTER_FRAMESET:
+                    switch (group) {
+                        case HTML:
+                            errStrayStartTag(name);
+                            if (!fragment && !isTemplateContents()) {
+                                addAttributesToHtml(attributes);
+                                attributes = null; // CPP
+                            }
+                            break starttagloop;
+                        case NOFRAMES:
+                            startTagGenericRawText(elementName, attributes);
+                            attributes = null; // CPP
+                            break starttagloop;
+                        default:
+                            errStrayStartTag(name);
+                            break starttagloop;
+                    }
+                case TEXT:
+                    assert false;
+                    break starttagloop; // Avoid infinite loop if the assertion
+                                        // fails
+            }
+        }
+        if (selfClosing) {
+            errSelfClosing();
+        }
+        // CPPONLY: if (mBuilder == null && attributes != HtmlAttributes.EMPTY_ATTRIBUTES) {
+        // CPPONLY:    Portability.delete(attributes);
+        // CPPONLY: }
+    }
+
+    private void startTagTitleInHead(ElementName elementName, HtmlAttributes attributes) throws SAXException {
+        appendToCurrentNodeAndPushElementMayFoster(elementName, attributes);
+        originalMode = mode;
+        mode = TEXT;
+        tokenizer.setStateAndEndTagExpectation(Tokenizer.RCDATA, elementName);
+    }
+
+    private void startTagGenericRawText(ElementName elementName, HtmlAttributes attributes) throws SAXException {
+        appendToCurrentNodeAndPushElementMayFoster(elementName, attributes);
+        originalMode = mode;
+        mode = TEXT;
+        tokenizer.setStateAndEndTagExpectation(Tokenizer.RAWTEXT, elementName);
+    }
+
+    private void startTagScriptInHead(ElementName elementName, HtmlAttributes attributes) throws SAXException {
+        // XXX need to manage much more stuff here if supporting document.write()
+        appendToCurrentNodeAndPushElementMayFoster(elementName, attributes);
+        originalMode = mode;
+        mode = TEXT;
+        tokenizer.setStateAndEndTagExpectation(Tokenizer.SCRIPT_DATA, elementName);
+    }
+
+    private void startTagTemplateInHead(ElementName elementName, HtmlAttributes attributes) throws SAXException {
+        appendToCurrentNodeAndPushElement(elementName, attributes);
+        insertMarker();
+        framesetOk = false;
+        originalMode = mode;
+        mode = IN_TEMPLATE;
+        pushTemplateMode(IN_TEMPLATE);
+    }
+
+    private boolean isTemplateContents() {
+        return TreeBuilder.NOT_FOUND_ON_STACK != findLast("template");
+    }
+
+    private boolean isTemplateModeStackEmpty() {
+        return templateModePtr == -1;
+    }
+
+    private boolean isSpecialParentInForeign(StackNode<T> stackNode) {
+        @NsUri String ns = stackNode.ns;
+        return ("http://www.w3.org/1999/xhtml" == ns)
+                || (stackNode.isHtmlIntegrationPoint())
+                || (("http://www.w3.org/1998/Math/MathML" == ns) && (stackNode.getGroup() == MI_MO_MN_MS_MTEXT));
+    }
+
+    /**
+     *
+     * <p>
+     * C++ memory note: The return value must be released.
+     *
+     * @return
+     * @throws SAXException
+     * @throws StopSniffingException
+     */
+    public static String extractCharsetFromContent(String attributeValue
+        // CPPONLY: , TreeBuilder tb
+    ) {
+        // This is a bit ugly. Converting the string to char array in order to
+        // make the portability layer smaller.
+        int charsetState = CHARSET_INITIAL;
+        int start = -1;
+        int end = -1;
+        @Auto char[] buffer = Portability.newCharArrayFromString(attributeValue);
+
+        charsetloop: for (int i = 0; i < buffer.length; i++) {
+            char c = buffer[i];
+            switch (charsetState) {
+                case CHARSET_INITIAL:
+                    switch (c) {
+                        case 'c':
+                        case 'C':
+                            charsetState = CHARSET_C;
+                            continue;
+                        default:
+                            continue;
+                    }
+                case CHARSET_C:
+                    switch (c) {
+                        case 'h':
+                        case 'H':
+                            charsetState = CHARSET_H;
+                            continue;
+                        default:
+                            charsetState = CHARSET_INITIAL;
+                            continue;
+                    }
+                case CHARSET_H:
+                    switch (c) {
+                        case 'a':
+                        case 'A':
+                            charsetState = CHARSET_A;
+                            continue;
+                        default:
+                            charsetState = CHARSET_INITIAL;
+                            continue;
+                    }
+                case CHARSET_A:
+                    switch (c) {
+                        case 'r':
+                        case 'R':
+                            charsetState = CHARSET_R;
+                            continue;
+                        default:
+                            charsetState = CHARSET_INITIAL;
+                            continue;
+                    }
+                case CHARSET_R:
+                    switch (c) {
+                        case 's':
+                        case 'S':
+                            charsetState = CHARSET_S;
+                            continue;
+                        default:
+                            charsetState = CHARSET_INITIAL;
+                            continue;
+                    }
+                case CHARSET_S:
+                    switch (c) {
+                        case 'e':
+                        case 'E':
+                            charsetState = CHARSET_E;
+                            continue;
+                        default:
+                            charsetState = CHARSET_INITIAL;
+                            continue;
+                    }
+                case CHARSET_E:
+                    switch (c) {
+                        case 't':
+                        case 'T':
+                            charsetState = CHARSET_T;
+                            continue;
+                        default:
+                            charsetState = CHARSET_INITIAL;
+                            continue;
+                    }
+                case CHARSET_T:
+                    switch (c) {
+                        case '\t':
+                        case '\n':
+                        case '\u000C':
+                        case '\r':
+                        case ' ':
+                            continue;
+                        case '=':
+                            charsetState = CHARSET_EQUALS;
+                            continue;
+                        default:
+                            return null;
+                    }
+                case CHARSET_EQUALS:
+                    switch (c) {
+                        case '\t':
+                        case '\n':
+                        case '\u000C':
+                        case '\r':
+                        case ' ':
+                            continue;
+                        case '\'':
+                            start = i + 1;
+                            charsetState = CHARSET_SINGLE_QUOTED;
+                            continue;
+                        case '\"':
+                            start = i + 1;
+                            charsetState = CHARSET_DOUBLE_QUOTED;
+                            continue;
+                        default:
+                            start = i;
+                            charsetState = CHARSET_UNQUOTED;
+                            continue;
+                    }
+                case CHARSET_SINGLE_QUOTED:
+                    switch (c) {
+                        case '\'':
+                            end = i;
+                            break charsetloop;
+                        default:
+                            continue;
+                    }
+                case CHARSET_DOUBLE_QUOTED:
+                    switch (c) {
+                        case '\"':
+                            end = i;
+                            break charsetloop;
+                        default:
+                            continue;
+                    }
+                case CHARSET_UNQUOTED:
+                    switch (c) {
+                        case '\t':
+                        case '\n':
+                        case '\u000C':
+                        case '\r':
+                        case ' ':
+                        case ';':
+                            end = i;
+                            break charsetloop;
+                        default:
+                            continue;
+                    }
+            }
+        }
+        String charset = null;
+        if (start != -1) {
+            if (end == -1) {
+                end = buffer.length;
+            }
+            charset = Portability.newStringFromBuffer(buffer, start, end
+                    - start
+                // CPPONLY: , tb
+            );
+        }
+        return charset;
+    }
+
+    private void checkMetaCharset(HtmlAttributes attributes)
+            throws SAXException {
+        String charset = attributes.getValue(AttributeName.CHARSET);
+        if (charset != null) {
+            if (tokenizer.internalEncodingDeclaration(charset)) {
+                requestSuspension();
+                return;
+            }
+            return;
+        }
+        if (!Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                "content-type",
+                attributes.getValue(AttributeName.HTTP_EQUIV))) {
+            return;
+        }
+        String content = attributes.getValue(AttributeName.CONTENT);
+        if (content != null) {
+            String extract = TreeBuilder.extractCharsetFromContent(content
+                // CPPONLY: , this
+            );
+            // remember not to return early without releasing the string
+            if (extract != null) {
+                if (tokenizer.internalEncodingDeclaration(extract)) {
+                    requestSuspension();
+                }
+            }
+            Portability.releaseString(extract);
+        }
+    }
+
+    public final void endTag(ElementName elementName) throws SAXException {
+        flushCharacters();
+        needToDropLF = false;
+        int eltPos;
+        int group = elementName.getGroup();
+        @Local String name = elementName.name;
+        endtagloop: for (;;) {
+            if (isInForeign()) {
+                if (stack[currentPtr].name != name) {
+                    if (currentPtr == 0) {
+                        errStrayEndTag(name);
+                    } else {
+                        errEndTagDidNotMatchCurrentOpenElement(name, stack[currentPtr].popName);
+                    }
+                }
+                eltPos = currentPtr;
+                for (;;) {
+                    if (eltPos == 0) {
+                        assert fragment: "We can get this close to the root of the stack in foreign content only in the fragment case.";
+                        break endtagloop;
+                    }
+                    if (stack[eltPos].name == name) {
+                        while (currentPtr >= eltPos) {
+                            pop();
+                        }
+                        break endtagloop;
+                    }
+                    if (stack[--eltPos].ns == "http://www.w3.org/1999/xhtml") {
+                        break;
+                    }
+                }
+            }
+            switch (mode) {
+                case IN_TEMPLATE:
+                    switch (group) {
+                        case TEMPLATE:
+                            // fall through to IN_HEAD
+                            break;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case IN_ROW:
+                    switch (group) {
+                        case TR:
+                            eltPos = findLastOrRoot(TreeBuilder.TR);
+                            if (eltPos == 0) {
+                                assert fragment || isTemplateContents();
+                                errNoTableRowToClose();
+                                break endtagloop;
+                            }
+                            clearStackBackTo(eltPos);
+                            pop();
+                            mode = IN_TABLE_BODY;
+                            break endtagloop;
+                        case TABLE:
+                            eltPos = findLastOrRoot(TreeBuilder.TR);
+                            if (eltPos == 0) {
+                                assert fragment || isTemplateContents();
+                                errNoTableRowToClose();
+                                break endtagloop;
+                            }
+                            clearStackBackTo(eltPos);
+                            pop();
+                            mode = IN_TABLE_BODY;
+                            continue;
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                            if (findLastInTableScope(name) == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            eltPos = findLastOrRoot(TreeBuilder.TR);
+                            if (eltPos == 0) {
+                                assert fragment || isTemplateContents();
+                                errNoTableRowToClose();
+                                break endtagloop;
+                            }
+                            clearStackBackTo(eltPos);
+                            pop();
+                            mode = IN_TABLE_BODY;
+                            continue;
+                        case BODY:
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case HTML:
+                        case TD_OR_TH:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                        default:
+                            // fall through to IN_TABLE
+                    }
+                case IN_TABLE_BODY:
+                    switch (group) {
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                            eltPos = findLastOrRoot(name);
+                            if (eltPos == 0) {
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            clearStackBackTo(eltPos);
+                            pop();
+                            mode = IN_TABLE;
+                            break endtagloop;
+                        case TABLE:
+                            eltPos = findLastInTableScopeOrRootTemplateTbodyTheadTfoot();
+                            if (eltPos == 0 || stack[eltPos].getGroup() == TEMPLATE) {
+                                assert fragment || isTemplateContents();
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            clearStackBackTo(eltPos);
+                            pop();
+                            mode = IN_TABLE;
+                            continue;
+                        case BODY:
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case HTML:
+                        case TD_OR_TH:
+                        case TR:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                        default:
+                            // fall through to IN_TABLE
+                    }
+                case IN_TABLE:
+                    switch (group) {
+                        case TABLE:
+                            eltPos = findLast("table");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                assert fragment || isTemplateContents();
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            resetTheInsertionMode();
+                            break endtagloop;
+                        case BODY:
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case HTML:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TD_OR_TH:
+                        case TR:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                        case TEMPLATE:
+                            // fall through to IN_HEAD
+                            break;
+                        default:
+                            errStrayEndTag(name);
+                            // fall through to IN_BODY
+                    }
+                case IN_CAPTION:
+                    switch (group) {
+                        case CAPTION:
+                            eltPos = findLastInTableScope("caption");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                break endtagloop;
+                            }
+                            generateImpliedEndTags();
+                            if (errorHandler != null && currentPtr != eltPos) {
+                                errUnclosedElements(eltPos, name);
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+                            mode = IN_TABLE;
+                            break endtagloop;
+                        case TABLE:
+                            errTableClosedWhileCaptionOpen();
+                            eltPos = findLastInTableScope("caption");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                break endtagloop;
+                            }
+                            generateImpliedEndTags();
+                            if (errorHandler != null && currentPtr != eltPos) {
+                                errUnclosedElements(eltPos, name);
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+                            mode = IN_TABLE;
+                            continue;
+                        case BODY:
+                        case COL:
+                        case COLGROUP:
+                        case HTML:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TD_OR_TH:
+                        case TR:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                        default:
+                            // fall through to IN_BODY
+                    }
+                case IN_CELL:
+                    switch (group) {
+                        case TD_OR_TH:
+                            eltPos = findLastInTableScope(name);
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            generateImpliedEndTags();
+                            if (errorHandler != null && !isCurrent(name)) {
+                                errUnclosedElements(eltPos, name);
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+                            mode = IN_ROW;
+                            break endtagloop;
+                        case TABLE:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TR:
+                            if (findLastInTableScope(name) == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                assert name == "tbody" || name == "tfoot" || name == "thead" || fragment || isTemplateContents();
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            closeTheCell(findLastInTableScopeTdTh());
+                            continue;
+                        case BODY:
+                        case CAPTION:
+                        case COL:
+                        case COLGROUP:
+                        case HTML:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                        default:
+                            // fall through to IN_BODY
+                    }
+                case FRAMESET_OK:
+                case IN_BODY:
+                    switch (group) {
+                        case BODY:
+                            if (!isSecondOnStackBody()) {
+                                assert fragment || isTemplateContents();
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            assert currentPtr >= 1;
+                            if (errorHandler != null) {
+                                uncloseloop1: for (int i = 2; i <= currentPtr; i++) {
+                                    switch (stack[i].getGroup()) {
+                                        case DD_OR_DT:
+                                        case LI:
+                                        case OPTGROUP:
+                                        case OPTION: // is this possible?
+                                        case P:
+                                        case RB_OR_RTC:
+                                        case RT_OR_RP:
+                                        case TD_OR_TH:
+                                        case TBODY_OR_THEAD_OR_TFOOT:
+                                            break;
+                                        default:
+                                            errEndWithUnclosedElements(name);
+                                            break uncloseloop1;
+                                    }
+                                }
+                            }
+                            mode = AFTER_BODY;
+                            break endtagloop;
+                        case HTML:
+                            if (!isSecondOnStackBody()) {
+                                assert fragment || isTemplateContents();
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            if (errorHandler != null) {
+                                uncloseloop2: for (int i = 0; i <= currentPtr; i++) {
+                                    switch (stack[i].getGroup()) {
+                                        case DD_OR_DT:
+                                        case LI:
+                                        case P:
+                                        case RB_OR_RTC:
+                                        case RT_OR_RP:
+                                        case TBODY_OR_THEAD_OR_TFOOT:
+                                        case TD_OR_TH:
+                                        case BODY:
+                                        case HTML:
+                                            break;
+                                        default:
+                                            errEndWithUnclosedElements(name);
+                                            break uncloseloop2;
+                                    }
+                                }
+                            }
+                            mode = AFTER_BODY;
+                            continue;
+                        case DIV_OR_BLOCKQUOTE_OR_CENTER_OR_MENU:
+                        case UL_OR_OL_OR_DL:
+                        case PRE_OR_LISTING:
+                        case FIELDSET:
+                        case BUTTON:
+                        case ADDRESS_OR_ARTICLE_OR_ASIDE_OR_DETAILS_OR_DIALOG_OR_DIR_OR_FIGCAPTION_OR_FIGURE_OR_FOOTER_OR_HEADER_OR_HGROUP_OR_MAIN_OR_NAV_OR_SECTION_OR_SUMMARY:
+                            eltPos = findLastInScope(name);
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errStrayEndTag(name);
+                            } else {
+                                generateImpliedEndTags();
+                                if (errorHandler != null && !isCurrent(name)) {
+                                    errUnclosedElements(eltPos, name);
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                            }
+                            break endtagloop;
+                        case FORM:
+                            if (!isTemplateContents()) {
+                                if (formPointer == null) {
+                                    errStrayEndTag(name);
+                                    break endtagloop;
+                                }
+                                formPointer = null;
+                                eltPos = findLastInScope(name);
+                                if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                    errStrayEndTag(name);
+                                    break endtagloop;
+                                }
+                                generateImpliedEndTags();
+                                if (errorHandler != null && !isCurrent(name)) {
+                                    errUnclosedElements(eltPos, name);
+                                }
+                                removeFromStack(eltPos);
+                                break endtagloop;
+                            } else {
+                                eltPos = findLastInScope(name);
+                                if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                    errStrayEndTag(name);
+                                    break endtagloop;
+                                }
+                                generateImpliedEndTags();
+                                if (errorHandler != null && !isCurrent(name)) {
+                                    errUnclosedElements(eltPos, name);
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                                break endtagloop;
+                            }
+                        case P:
+                            eltPos = findLastInButtonScope("p");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errNoElementToCloseButEndTagSeen("p");
+                                // XXX Can the 'in foreign' case happen anymore?
+                                if (isInForeign()) {
+                                    errHtmlStartTagInForeignContext(name);
+                                    // Check for currentPtr for the fragment
+                                    // case.
+                                    while (currentPtr >= 0 && stack[currentPtr].ns != "http://www.w3.org/1999/xhtml") {
+                                        pop();
+                                    }
+                                }
+                                appendVoidElementToCurrentMayFoster(
+                                        elementName,
+                                        HtmlAttributes.EMPTY_ATTRIBUTES);
+                                break endtagloop;
+                            }
+                            generateImpliedEndTagsExceptFor("p");
+                            assert eltPos != TreeBuilder.NOT_FOUND_ON_STACK;
+                            if (errorHandler != null && eltPos != currentPtr) {
+                                errUnclosedElements(eltPos, name);
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            break endtagloop;
+                        case LI:
+                            eltPos = findLastInListScope(name);
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errNoElementToCloseButEndTagSeen(name);
+                            } else {
+                                generateImpliedEndTagsExceptFor(name);
+                                if (errorHandler != null
+                                        && eltPos != currentPtr) {
+                                    errUnclosedElements(eltPos, name);
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                            }
+                            break endtagloop;
+                        case DD_OR_DT:
+                            eltPos = findLastInScope(name);
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errNoElementToCloseButEndTagSeen(name);
+                            } else {
+                                generateImpliedEndTagsExceptFor(name);
+                                if (errorHandler != null
+                                        && eltPos != currentPtr) {
+                                    errUnclosedElements(eltPos, name);
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                            }
+                            break endtagloop;
+                        case H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6:
+                            eltPos = findLastInScopeHn();
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errStrayEndTag(name);
+                            } else {
+                                generateImpliedEndTags();
+                                if (errorHandler != null && !isCurrent(name)) {
+                                    errUnclosedElements(eltPos, name);
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                            }
+                            break endtagloop;
+                        case OBJECT:
+                        case MARQUEE_OR_APPLET:
+                            eltPos = findLastInScope(name);
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                errStrayEndTag(name);
+                            } else {
+                                generateImpliedEndTags();
+                                if (errorHandler != null && !isCurrent(name)) {
+                                    errUnclosedElements(eltPos, name);
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                                clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+                            }
+                            break endtagloop;
+                        case BR:
+                            errEndTagBr();
+                            if (isInForeign()) {
+                                // XXX can this happen anymore?
+                                errHtmlStartTagInForeignContext(name);
+                                // Check for currentPtr for the fragment
+                                // case.
+                                while (currentPtr >= 0 && stack[currentPtr].ns != "http://www.w3.org/1999/xhtml") {
+                                    pop();
+                                }
+                            }
+                            reconstructTheActiveFormattingElements();
+                            appendVoidElementToCurrentMayFoster(
+                                    elementName,
+                                    HtmlAttributes.EMPTY_ATTRIBUTES);
+                            break endtagloop;
+                        case TEMPLATE:
+                            // fall through to IN_HEAD;
+                            break;
+                        case AREA_OR_WBR:
+                        // CPPONLY: case MENUITEM:
+                        case PARAM_OR_SOURCE_OR_TRACK:
+                        case EMBED:
+                        case IMG:
+                        case IMAGE:
+                        case INPUT:
+                        case KEYGEN: // XXX??
+                        case HR:
+                        case ISINDEX:
+                        case IFRAME:
+                        case NOEMBED: // XXX???
+                        case NOFRAMES: // XXX??
+                        case SELECT:
+                        case TABLE:
+                        case TEXTAREA: // XXX??
+                            errStrayEndTag(name);
+                            break endtagloop;
+                        case NOSCRIPT:
+                            if (scriptingEnabled) {
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            } else {
+                                // fall through
+                            }
+                        case A:
+                        case B_OR_BIG_OR_CODE_OR_EM_OR_I_OR_S_OR_SMALL_OR_STRIKE_OR_STRONG_OR_TT_OR_U:
+                        case FONT:
+                        case NOBR:
+                            if (adoptionAgencyEndTag(name)) {
+                                break endtagloop;
+                            }
+                            // else handle like any other tag
+                        default:
+                            if (isCurrent(name)) {
+                                pop();
+                                break endtagloop;
+                            }
+
+                            eltPos = currentPtr;
+                            for (;;) {
+                                StackNode<T> node = stack[eltPos];
+                                if (node.ns == "http://www.w3.org/1999/xhtml" && node.name == name) {
+                                    generateImpliedEndTags();
+                                    if (errorHandler != null
+                                            && !isCurrent(name)) {
+                                        errUnclosedElements(eltPos, name);
+                                    }
+                                    while (currentPtr >= eltPos) {
+                                        pop();
+                                    }
+                                    break endtagloop;
+                                } else if (eltPos == 0 || node.isSpecial()) {
+                                    errStrayEndTag(name);
+                                    break endtagloop;
+                                }
+                                eltPos--;
+                            }
+                    }
+                case IN_HEAD:
+                    switch (group) {
+                        case HEAD:
+                            pop();
+                            mode = AFTER_HEAD;
+                            break endtagloop;
+                        case BR:
+                        case HTML:
+                        case BODY:
+                            pop();
+                            mode = AFTER_HEAD;
+                            continue;
+                        case TEMPLATE:
+                            endTagTemplateInHead();
+                            break endtagloop;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case IN_HEAD_NOSCRIPT:
+                    switch (group) {
+                        case NOSCRIPT:
+                            pop();
+                            mode = IN_HEAD;
+                            break endtagloop;
+                        case BR:
+                            errStrayEndTag(name);
+                            pop();
+                            mode = IN_HEAD;
+                            continue;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case IN_COLUMN_GROUP:
+                    switch (group) {
+                        case COLGROUP:
+                            if (currentPtr == 0 || stack[currentPtr].getGroup() ==
+                                    TreeBuilder.TEMPLATE) {
+                                assert fragment || isTemplateContents();
+                                errGarbageInColgroup();
+                                break endtagloop;
+                            }
+                            pop();
+                            mode = IN_TABLE;
+                            break endtagloop;
+                        case COL:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                        case TEMPLATE:
+                            endTagTemplateInHead();
+                            break endtagloop;
+                        default:
+                            if (currentPtr == 0 || stack[currentPtr].getGroup() ==
+                                    TreeBuilder.TEMPLATE) {
+                                assert fragment || isTemplateContents();
+                                errGarbageInColgroup();
+                                break endtagloop;
+                            }
+                            pop();
+                            mode = IN_TABLE;
+                            continue;
+                    }
+                case IN_SELECT_IN_TABLE:
+                    switch (group) {
+                        case CAPTION:
+                        case TABLE:
+                        case TBODY_OR_THEAD_OR_TFOOT:
+                        case TR:
+                        case TD_OR_TH:
+                            errEndTagSeenWithSelectOpen(name);
+                            if (findLastInTableScope(name) != TreeBuilder.NOT_FOUND_ON_STACK) {
+                                eltPos = findLastInTableScope("select");
+                                if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                    assert fragment;
+                                    break endtagloop; // http://www.w3.org/Bugs/Public/show_bug.cgi?id=8375
+                                }
+                                while (currentPtr >= eltPos) {
+                                    pop();
+                                }
+                                resetTheInsertionMode();
+                                continue;
+                            } else {
+                                break endtagloop;
+                            }
+                        default:
+                            // fall through to IN_SELECT
+                    }
+                case IN_SELECT:
+                    switch (group) {
+                        case OPTION:
+                            if (isCurrent("option")) {
+                                pop();
+                                break endtagloop;
+                            } else {
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                        case OPTGROUP:
+                            if (isCurrent("option")
+                                    && "optgroup" == stack[currentPtr - 1].name) {
+                                pop();
+                            }
+                            if (isCurrent("optgroup")) {
+                                pop();
+                            } else {
+                                errStrayEndTag(name);
+                            }
+                            break endtagloop;
+                        case SELECT:
+                            eltPos = findLastInTableScope("select");
+                            if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+                                assert fragment;
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            while (currentPtr >= eltPos) {
+                                pop();
+                            }
+                            resetTheInsertionMode();
+                            break endtagloop;
+                        case TEMPLATE:
+                            endTagTemplateInHead();
+                            break endtagloop;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case AFTER_BODY:
+                    switch (group) {
+                        case HTML:
+                            if (fragment) {
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            } else {
+                                mode = AFTER_AFTER_BODY;
+                                break endtagloop;
+                            }
+                        default:
+                            errEndTagAfterBody();
+                            mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                            continue;
+                    }
+                case IN_FRAMESET:
+                    switch (group) {
+                        case FRAMESET:
+                            if (currentPtr == 0) {
+                                assert fragment;
+                                errStrayEndTag(name);
+                                break endtagloop;
+                            }
+                            pop();
+                            if ((!fragment) && !isCurrent("frameset")) {
+                                mode = AFTER_FRAMESET;
+                            }
+                            break endtagloop;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case AFTER_FRAMESET:
+                    switch (group) {
+                        case HTML:
+                            mode = AFTER_AFTER_FRAMESET;
+                            break endtagloop;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case INITIAL:
+                    /*
+                     * Parse error.
+                     */
+                    // [NOCPP[
+                    switch (doctypeExpectation) {
+                        case AUTO:
+                            err("End tag seen without seeing a doctype first. Expected e.g. \u201C<!DOCTYPE html>\u201D.");
+                            break;
+                        case HTML:
+                            // ]NOCPP]
+                            errEndTagSeenWithoutDoctype();
+                            // [NOCPP[
+                            break;
+                        case HTML401_STRICT:
+                            err("End tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01//EN\" \"http://www.w3.org/TR/html4/strict.dtd\">\u201D.");
+                            break;
+                        case HTML401_TRANSITIONAL:
+                            err("End tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE HTML PUBLIC \"-//W3C//DTD HTML 4.01 Transitional//EN\" \"http://www.w3.org/TR/html4/loose.dtd\">\u201D.");
+                            break;
+                        case NO_DOCTYPE_ERRORS:
+                    }
+                    // ]NOCPP]
+                    /*
+                     *
+                     * Set the document to quirks mode.
+                     */
+                    documentModeInternal(DocumentMode.QUIRKS_MODE, null, null,
+                            false);
+                    /*
+                     * Then, switch to the root element mode of the tree
+                     * construction stage
+                     */
+                    mode = BEFORE_HTML;
+                    /*
+                     * and reprocess the current token.
+                     */
+                    continue;
+                case BEFORE_HTML:
+                    switch (group) {
+                        case HEAD:
+                        case BR:
+                        case HTML:
+                        case BODY:
+                            /*
+                             * Create an HTMLElement node with the tag name
+                             * html, in the HTML namespace. Append it to the
+                             * Document object.
+                             */
+                            appendHtmlElementToDocumentAndPush();
+                            /* Switch to the main mode */
+                            mode = BEFORE_HEAD;
+                            /*
+                             * reprocess the current token.
+                             */
+                            continue;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case BEFORE_HEAD:
+                    switch (group) {
+                        case HEAD:
+                        case BR:
+                        case HTML:
+                        case BODY:
+                            appendToCurrentNodeAndPushHeadElement(HtmlAttributes.EMPTY_ATTRIBUTES);
+                            mode = IN_HEAD;
+                            continue;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case AFTER_HEAD:
+                    switch (group) {
+                        case TEMPLATE:
+                            endTagTemplateInHead();
+                            break endtagloop;
+                        case HTML:
+                        case BODY:
+                        case BR:
+                            appendToCurrentNodeAndPushBodyElement();
+                            mode = FRAMESET_OK;
+                            continue;
+                        default:
+                            errStrayEndTag(name);
+                            break endtagloop;
+                    }
+                case AFTER_AFTER_BODY:
+                    errStrayEndTag(name);
+                    mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                    continue;
+                case AFTER_AFTER_FRAMESET:
+                    errStrayEndTag(name);
+                    break endtagloop;
+                case TEXT:
+                    // XXX need to manage insertion point here
+                    pop();
+                    if (originalMode == AFTER_HEAD) {
+                        silentPop();
+                    }
+                    mode = originalMode;
+                    break endtagloop;
+            }
+        } // endtagloop
+    }
+
+    private void endTagTemplateInHead() throws SAXException {
+        int eltPos = findLast("template");
+        if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+            errStrayEndTag("template");
+            return;
+        }
+        generateImpliedEndTags();
+        if (errorHandler != null && !isCurrent("template")) {
+            errUnclosedElements(eltPos, "template");
+        }
+        while (currentPtr >= eltPos) {
+            pop();
+        }
+        clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+        popTemplateMode();
+        resetTheInsertionMode();
+    }
+
+    private int findLastInTableScopeOrRootTemplateTbodyTheadTfoot() {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].getGroup() == TreeBuilder.TBODY_OR_THEAD_OR_TFOOT ||
+                    stack[i].getGroup() == TreeBuilder.TEMPLATE) {
+                return i;
+            }
+        }
+        return 0;
+    }
+
+    private int findLast(@Local String name) {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].ns == "http://www.w3.org/1999/xhtml" && stack[i].name == name) {
+                return i;
+            }
+        }
+        return TreeBuilder.NOT_FOUND_ON_STACK;
+    }
+
+    private int findLastInTableScope(@Local String name) {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].ns == "http://www.w3.org/1999/xhtml") {
+                if (stack[i].name == name) {
+                    return i;
+                } else if (stack[i].name == "table" || stack[i].name == "template") {
+                    return TreeBuilder.NOT_FOUND_ON_STACK;
+                }
+            }
+        }
+        return TreeBuilder.NOT_FOUND_ON_STACK;
+    }
+
+    private int findLastInButtonScope(@Local String name) {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].ns == "http://www.w3.org/1999/xhtml") {
+                if (stack[i].name == name) {
+                    return i;
+                } else if (stack[i].name == "button") {
+                    return TreeBuilder.NOT_FOUND_ON_STACK;
+                }
+            }
+
+            if (stack[i].isScoping()) {
+                return TreeBuilder.NOT_FOUND_ON_STACK;
+            }
+        }
+        return TreeBuilder.NOT_FOUND_ON_STACK;
+    }
+
+    private int findLastInScope(@Local String name) {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].ns == "http://www.w3.org/1999/xhtml" && stack[i].name == name) {
+                return i;
+            } else if (stack[i].isScoping()) {
+                return TreeBuilder.NOT_FOUND_ON_STACK;
+            }
+        }
+        return TreeBuilder.NOT_FOUND_ON_STACK;
+    }
+
+    private int findLastInListScope(@Local String name) {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].ns == "http://www.w3.org/1999/xhtml") {
+                if (stack[i].name == name) {
+                    return i;
+                } else if (stack[i].name == "ul" || stack[i].name == "ol") {
+                    return TreeBuilder.NOT_FOUND_ON_STACK;
+                }
+            }
+
+            if (stack[i].isScoping()) {
+                return TreeBuilder.NOT_FOUND_ON_STACK;
+            }
+        }
+        return TreeBuilder.NOT_FOUND_ON_STACK;
+    }
+
+    private int findLastInScopeHn() {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].getGroup() == TreeBuilder.H1_OR_H2_OR_H3_OR_H4_OR_H5_OR_H6) {
+                return i;
+            } else if (stack[i].isScoping()) {
+                return TreeBuilder.NOT_FOUND_ON_STACK;
+            }
+        }
+        return TreeBuilder.NOT_FOUND_ON_STACK;
+    }
+
+    private void generateImpliedEndTagsExceptFor(@Local String name)
+            throws SAXException {
+        for (;;) {
+            StackNode<T> node = stack[currentPtr];
+            switch (node.getGroup()) {
+                case P:
+                case LI:
+                case DD_OR_DT:
+                case OPTION:
+                case OPTGROUP:
+                case RB_OR_RTC:
+                case RT_OR_RP:
+                    if (node.ns == "http://www.w3.org/1999/xhtml" && node.name == name) {
+                        return;
+                    }
+                    pop();
+                    continue;
+                default:
+                    return;
+            }
+        }
+    }
+
+    private void generateImpliedEndTags() throws SAXException {
+        for (;;) {
+            switch (stack[currentPtr].getGroup()) {
+                case P:
+                case LI:
+                case DD_OR_DT:
+                case OPTION:
+                case OPTGROUP:
+                case RB_OR_RTC:
+                case RT_OR_RP:
+                    pop();
+                    continue;
+                default:
+                    return;
+            }
+        }
+    }
+
+    private boolean isSecondOnStackBody() {
+        return currentPtr >= 1 && stack[1].getGroup() == TreeBuilder.BODY;
+    }
+
+    private void documentModeInternal(DocumentMode m, String publicIdentifier,
+            String systemIdentifier, boolean html4SpecificAdditionalErrorChecks)
+            throws SAXException {
+
+        if (isSrcdocDocument) {
+            // Srcdoc documents are always rendered in standards mode.
+            quirks = false;
+            if (documentModeHandler != null) {
+                documentModeHandler.documentMode(
+                        DocumentMode.STANDARDS_MODE
+                        // [NOCPP[
+                        , null, null, false
+                // ]NOCPP]
+                );
+            }
+            return;
+        }
+
+        quirks = (m == DocumentMode.QUIRKS_MODE);
+        if (documentModeHandler != null) {
+            documentModeHandler.documentMode(
+                    m
+                    // [NOCPP[
+                    , publicIdentifier, systemIdentifier,
+                    html4SpecificAdditionalErrorChecks
+            // ]NOCPP]
+            );
+        }
+        // [NOCPP[
+        documentMode(m, publicIdentifier, systemIdentifier,
+                html4SpecificAdditionalErrorChecks);
+        // ]NOCPP]
+    }
+
+    private boolean isAlmostStandards(String publicIdentifier,
+            String systemIdentifier) {
+        if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                "-//w3c//dtd xhtml 1.0 transitional//en", publicIdentifier)) {
+            return true;
+        }
+        if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                "-//w3c//dtd xhtml 1.0 frameset//en", publicIdentifier)) {
+            return true;
+        }
+        if (systemIdentifier != null) {
+            if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                    "-//w3c//dtd html 4.01 transitional//en", publicIdentifier)) {
+                return true;
+            }
+            if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                    "-//w3c//dtd html 4.01 frameset//en", publicIdentifier)) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    private boolean isQuirky(@Local String name, String publicIdentifier,
+            String systemIdentifier, boolean forceQuirks) {
+        if (forceQuirks) {
+            return true;
+        }
+        if (name != HTML_LOCAL) {
+            return true;
+        }
+        if (publicIdentifier != null) {
+            for (int i = 0; i < TreeBuilder.QUIRKY_PUBLIC_IDS.length; i++) {
+                if (Portability.lowerCaseLiteralIsPrefixOfIgnoreAsciiCaseString(
+                        TreeBuilder.QUIRKY_PUBLIC_IDS[i], publicIdentifier)) {
+                    return true;
+                }
+            }
+            if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                    "-//w3o//dtd w3 html strict 3.0//en//", publicIdentifier)
+                    || Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                            "-/w3c/dtd html 4.0 transitional/en",
+                            publicIdentifier)
+                    || Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                            "html", publicIdentifier)) {
+                return true;
+            }
+        }
+        if (systemIdentifier == null) {
+            if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                    "-//w3c//dtd html 4.01 transitional//en", publicIdentifier)) {
+                return true;
+            } else if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                    "-//w3c//dtd html 4.01 frameset//en", publicIdentifier)) {
+                return true;
+            }
+        } else if (Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd",
+                systemIdentifier)) {
+            return true;
+        }
+        return false;
+    }
+
+    private void closeTheCell(int eltPos) throws SAXException {
+        generateImpliedEndTags();
+        if (errorHandler != null && eltPos != currentPtr) {
+            errUnclosedElementsCell(eltPos);
+        }
+        while (currentPtr >= eltPos) {
+            pop();
+        }
+        clearTheListOfActiveFormattingElementsUpToTheLastMarker();
+        mode = IN_ROW;
+        return;
+    }
+
+    private int findLastInTableScopeTdTh() {
+        for (int i = currentPtr; i > 0; i--) {
+            @Local String name = stack[i].name;
+            if (stack[i].ns == "http://www.w3.org/1999/xhtml") {
+                if ("td" == name || "th" == name) {
+                    return i;
+                } else if (name == "table" || name == "template") {
+                    return TreeBuilder.NOT_FOUND_ON_STACK;
+                }
+            }
+        }
+        return TreeBuilder.NOT_FOUND_ON_STACK;
+    }
+
+    private void clearStackBackTo(int eltPos) throws SAXException {
+        int eltGroup = stack[eltPos].getGroup();
+        while (currentPtr > eltPos) { // > not >= intentional
+            if (stack[currentPtr].ns == "http://www.w3.org/1999/xhtml"
+                    && stack[currentPtr].getGroup() == TEMPLATE
+                    && (eltGroup == TABLE || eltGroup == TBODY_OR_THEAD_OR_TFOOT|| eltGroup == TR || eltPos == 0)) {
+                return;
+            }
+            pop();
+        }
+    }
+
+    private void resetTheInsertionMode() {
+        StackNode<T> node;
+        @Local String name;
+        @NsUri String ns;
+        for (int i = currentPtr; i >= 0; i--) {
+            node = stack[i];
+            name = node.name;
+            ns = node.ns;
+            if (i == 0) {
+                if (!(contextNamespace == "http://www.w3.org/1999/xhtml" && (contextName == "td" || contextName == "th"))) {
+                    if (fragment) {
+                        // Make sure we are parsing a fragment otherwise the context element doesn't make sense.
+                        name = contextName;
+                        ns = contextNamespace;
+                    }
+                } else {
+                    mode = framesetOk ? FRAMESET_OK : IN_BODY; // XXX from Hixie's email
+                    return;
+                }
+            }
+            if ("select" == name) {
+                int ancestorIndex = i;
+                while (ancestorIndex > 0) {
+                    StackNode<T> ancestor = stack[ancestorIndex--];
+                    if ("http://www.w3.org/1999/xhtml" == ancestor.ns) {
+                        if ("template" == ancestor.name) {
+                            break;
+                        }
+                        if ("table" == ancestor.name) {
+                            mode = IN_SELECT_IN_TABLE;
+                            return;
+                        }
+                    }
+                }
+                mode = IN_SELECT;
+                return;
+            } else if ("td" == name || "th" == name) {
+                mode = IN_CELL;
+                return;
+            } else if ("tr" == name) {
+                mode = IN_ROW;
+                return;
+            } else if ("tbody" == name || "thead" == name || "tfoot" == name) {
+                mode = IN_TABLE_BODY;
+                return;
+            } else if ("caption" == name) {
+                mode = IN_CAPTION;
+                return;
+            } else if ("colgroup" == name) {
+                mode = IN_COLUMN_GROUP;
+                return;
+            } else if ("table" == name) {
+                mode = IN_TABLE;
+                return;
+            } else if ("http://www.w3.org/1999/xhtml" != ns) {
+                mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                return;
+            } else if ("template" == name) {
+                assert templateModePtr >= 0;
+                mode = templateModeStack[templateModePtr];
+                return;
+            }  else if ("head" == name) {
+                if (name == contextName) {
+                    mode = framesetOk ? FRAMESET_OK : IN_BODY; // really
+                } else {
+                    mode = IN_HEAD;
+                }
+                return;
+            } else if ("body" == name) {
+                mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                return;
+            } else if ("frameset" == name) {
+                // TODO: Fragment case. Add error reporting.
+                mode = IN_FRAMESET;
+                return;
+            } else if ("html" == name) {
+                if (headPointer == null) {
+                    // TODO: Fragment case. Add error reporting.
+                    mode = BEFORE_HEAD;
+                } else {
+                    mode = AFTER_HEAD;
+                }
+                return;
+            } else if (i == 0) {
+                mode = framesetOk ? FRAMESET_OK : IN_BODY;
+                return;
+            }
+        }
+    }
+
+    /**
+     * @throws SAXException
+     *
+     */
+    private void implicitlyCloseP() throws SAXException {
+        int eltPos = findLastInButtonScope("p");
+        if (eltPos == TreeBuilder.NOT_FOUND_ON_STACK) {
+            return;
+        }
+        generateImpliedEndTagsExceptFor("p");
+        if (errorHandler != null && eltPos != currentPtr) {
+            errUnclosedElementsImplied(eltPos, "p");
+        }
+        while (currentPtr >= eltPos) {
+            pop();
+        }
+    }
+
+    private boolean debugOnlyClearLastStackSlot() {
+        stack[currentPtr] = null;
+        return true;
+    }
+
+    private boolean debugOnlyClearLastListSlot() {
+        listOfActiveFormattingElements[listPtr] = null;
+        return true;
+    }
+
+    private void pushTemplateMode(int mode) {
+        templateModePtr++;
+        if (templateModePtr == templateModeStack.length) {
+            int[] newStack = new int[templateModeStack.length + 64];
+            System.arraycopy(templateModeStack, 0, newStack, 0, templateModeStack.length);
+            templateModeStack = newStack;
+        }
+        templateModeStack[templateModePtr] = mode;
+    }
+
+    @SuppressWarnings("unchecked") private void push(StackNode<T> node) throws SAXException {
+        currentPtr++;
+        if (currentPtr == stack.length) {
+            StackNode<T>[] newStack = new StackNode[stack.length + 64];
+            System.arraycopy(stack, 0, newStack, 0, stack.length);
+            stack = newStack;
+        }
+        stack[currentPtr] = node;
+        elementPushed(node.ns, node.popName, node.node);
+    }
+
+    @SuppressWarnings("unchecked") private void silentPush(StackNode<T> node) throws SAXException {
+        currentPtr++;
+        if (currentPtr == stack.length) {
+            StackNode<T>[] newStack = new StackNode[stack.length + 64];
+            System.arraycopy(stack, 0, newStack, 0, stack.length);
+            stack = newStack;
+        }
+        stack[currentPtr] = node;
+    }
+
+    @SuppressWarnings("unchecked") private void append(StackNode<T> node) {
+        listPtr++;
+        if (listPtr == listOfActiveFormattingElements.length) {
+            StackNode<T>[] newList = new StackNode[listOfActiveFormattingElements.length + 64];
+            System.arraycopy(listOfActiveFormattingElements, 0, newList, 0,
+                    listOfActiveFormattingElements.length);
+            listOfActiveFormattingElements = newList;
+        }
+        listOfActiveFormattingElements[listPtr] = node;
+    }
+
+    @Inline private void insertMarker() {
+        append(null);
+    }
+
+    private void clearTheListOfActiveFormattingElementsUpToTheLastMarker() {
+        while (listPtr > -1) {
+            if (listOfActiveFormattingElements[listPtr] == null) {
+                --listPtr;
+                return;
+            }
+            listOfActiveFormattingElements[listPtr].release();
+            --listPtr;
+        }
+    }
+
+    @Inline private boolean isCurrent(@Local String name) {
+        return stack[currentPtr].ns == "http://www.w3.org/1999/xhtml" &&
+                name == stack[currentPtr].name;
+    }
+
+    private void removeFromStack(int pos) throws SAXException {
+        if (currentPtr == pos) {
+            pop();
+        } else {
+            fatal();
+            stack[pos].release();
+            System.arraycopy(stack, pos + 1, stack, pos, currentPtr - pos);
+            assert debugOnlyClearLastStackSlot();
+            currentPtr--;
+        }
+    }
+
+    private void removeFromStack(StackNode<T> node) throws SAXException {
+        if (stack[currentPtr] == node) {
+            pop();
+        } else {
+            int pos = currentPtr - 1;
+            while (pos >= 0 && stack[pos] != node) {
+                pos--;
+            }
+            if (pos == -1) {
+                // dead code?
+                return;
+            }
+            fatal();
+            node.release();
+            System.arraycopy(stack, pos + 1, stack, pos, currentPtr - pos);
+            currentPtr--;
+        }
+    }
+
+    private void removeFromListOfActiveFormattingElements(int pos) {
+        assert listOfActiveFormattingElements[pos] != null;
+        listOfActiveFormattingElements[pos].release();
+        if (pos == listPtr) {
+            assert debugOnlyClearLastListSlot();
+            listPtr--;
+            return;
+        }
+        assert pos < listPtr;
+        System.arraycopy(listOfActiveFormattingElements, pos + 1,
+                listOfActiveFormattingElements, pos, listPtr - pos);
+        assert debugOnlyClearLastListSlot();
+        listPtr--;
+    }
+
+    /**
+     * Adoption agency algorithm.
+     *
+     * @param name subject as described in the specified algorithm.
+     * @return Returns true if the algorithm has completed and there is nothing remaining to
+     * be done. Returns false if the algorithm needs to "act as described in the 'any other
+     * end tag' entry" as described in the specified algorithm.
+     * @throws SAXException
+     */
+    private boolean adoptionAgencyEndTag(@Local String name) throws SAXException {
+        // This check intends to ensure that for properly nested tags, closing tags will match
+        // against the stack instead of the listOfActiveFormattingElements.
+        if (stack[currentPtr].ns == "http://www.w3.org/1999/xhtml" &&
+                stack[currentPtr].name == name &&
+                findInListOfActiveFormattingElements(stack[currentPtr]) == -1) {
+            // If the current element matches the name but isn't on the list of active
+            // formatting elements, then it is possible that the list was mangled by the Noah's Ark
+            // clause. In this case, we want to match the end tag against the stack instead of
+            // proceeding with the AAA algorithm that may match against the list of
+            // active formatting elements (and possibly mangle the tree in unexpected ways).
+            pop();
+            return true;
+        }
+
+        // If you crash around here, perhaps some stack node variable claimed to
+        // be a weak ref isn't.
+        for (int i = 0; i < 8; ++i) {
+            int formattingEltListPos = listPtr;
+            while (formattingEltListPos > -1) {
+                StackNode<T> listNode = listOfActiveFormattingElements[formattingEltListPos]; // weak ref
+                if (listNode == null) {
+                    formattingEltListPos = -1;
+                    break;
+                } else if (listNode.name == name) {
+                    break;
+                }
+                formattingEltListPos--;
+            }
+            if (formattingEltListPos == -1) {
+                return false;
+            }
+            // this *looks* like a weak ref to the list of formatting elements
+            StackNode<T> formattingElt = listOfActiveFormattingElements[formattingEltListPos];
+            int formattingEltStackPos = currentPtr;
+            boolean inScope = true;
+            while (formattingEltStackPos > -1) {
+                StackNode<T> node = stack[formattingEltStackPos]; // weak ref
+                if (node == formattingElt) {
+                    break;
+                } else if (node.isScoping()) {
+                    inScope = false;
+                }
+                formattingEltStackPos--;
+            }
+            if (formattingEltStackPos == -1) {
+                errNoElementToCloseButEndTagSeen(name);
+                removeFromListOfActiveFormattingElements(formattingEltListPos);
+                return true;
+            }
+            if (!inScope) {
+                errNoElementToCloseButEndTagSeen(name);
+                return true;
+            }
+            // stackPos now points to the formatting element and it is in scope
+            if (formattingEltStackPos != currentPtr) {
+                errEndTagViolatesNestingRules(name);
+            }
+            int furthestBlockPos = formattingEltStackPos + 1;
+            while (furthestBlockPos <= currentPtr) {
+                StackNode<T> node = stack[furthestBlockPos]; // weak ref
+                assert furthestBlockPos > 0: "How is formattingEltStackPos + 1 not > 0?";
+                if (node.isSpecial()) {
+                    break;
+                }
+                furthestBlockPos++;
+            }
+            if (furthestBlockPos > currentPtr) {
+                // no furthest block
+                while (currentPtr >= formattingEltStackPos) {
+                    pop();
+                }
+                removeFromListOfActiveFormattingElements(formattingEltListPos);
+                return true;
+            }
+            StackNode<T> commonAncestor = stack[formattingEltStackPos - 1]; // weak ref
+            StackNode<T> furthestBlock = stack[furthestBlockPos]; // weak ref
+            // detachFromParent(furthestBlock.node); XXX AAA CHANGE
+            int bookmark = formattingEltListPos;
+            int nodePos = furthestBlockPos;
+            StackNode<T> lastNode = furthestBlock; // weak ref
+            int j = 0;
+            for (;;) {
+                ++j;
+                nodePos--;
+                if (nodePos == formattingEltStackPos) {
+                    break;
+                }
+                StackNode<T> node = stack[nodePos]; // weak ref
+                int nodeListPos = findInListOfActiveFormattingElements(node);
+
+                if (j > 3 && nodeListPos != -1) {
+                    removeFromListOfActiveFormattingElements(nodeListPos);
+
+                    // Adjust the indices into the list to account
+                    // for the removal of nodeListPos.
+                    if (nodeListPos <= formattingEltListPos) {
+                        formattingEltListPos--;
+                    }
+                    if (nodeListPos <= bookmark) {
+                        bookmark--;
+                    }
+
+                    // Update position to reflect removal from list.
+                    nodeListPos = -1;
+                }
+
+                if (nodeListPos == -1) {
+                    assert formattingEltStackPos < nodePos;
+                    assert bookmark < nodePos;
+                    assert furthestBlockPos > nodePos;
+                    removeFromStack(nodePos); // node is now a bad pointer in C++
+                    furthestBlockPos--;
+                    continue;
+                }
+                // now node is both on stack and in the list
+                if (nodePos == furthestBlockPos) {
+                    bookmark = nodeListPos + 1;
+                }
+                // if (hasChildren(node.node)) { XXX AAA CHANGE
+                assert node == listOfActiveFormattingElements[nodeListPos];
+                assert node == stack[nodePos];
+                T clone = createElement("http://www.w3.org/1999/xhtml",
+                        node.name, node.attributes.cloneAttributes(null), commonAncestor.node);
+                StackNode<T> newNode = new StackNode<T>(node.getFlags(), node.ns,
+                        node.name, clone, node.popName, node.attributes
+                        // [NOCPP[
+                        , node.getLocator()
+                        // ]NOCPP]
+                ); // creation ownership goes to stack
+                node.dropAttributes(); // adopt ownership to newNode
+                stack[nodePos] = newNode;
+                newNode.retain(); // retain for list
+                listOfActiveFormattingElements[nodeListPos] = newNode;
+                node.release(); // release from stack
+                node.release(); // release from list
+                node = newNode;
+                // } XXX AAA CHANGE
+                detachFromParent(lastNode.node);
+                appendElement(lastNode.node, node.node);
+                lastNode = node;
+            }
+            if (commonAncestor.isFosterParenting()) {
+                fatal();
+                detachFromParent(lastNode.node);
+                insertIntoFosterParent(lastNode.node);
+            } else {
+                detachFromParent(lastNode.node);
+                appendElement(lastNode.node, commonAncestor.node);
+            }
+            T clone = createElement("http://www.w3.org/1999/xhtml",
+                    formattingElt.name,
+                    formattingElt.attributes.cloneAttributes(null), furthestBlock.node);
+            StackNode<T> formattingClone = new StackNode<T>(
+                    formattingElt.getFlags(), formattingElt.ns,
+                    formattingElt.name, clone, formattingElt.popName,
+                    formattingElt.attributes
+                    // [NOCPP[
+                    , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+                    // ]NOCPP]
+            ); // Ownership transfers to stack below
+            formattingElt.dropAttributes(); // transfer ownership to
+                                            // formattingClone
+            appendChildrenToNewParent(furthestBlock.node, clone);
+            appendElement(clone, furthestBlock.node);
+            removeFromListOfActiveFormattingElements(formattingEltListPos);
+            insertIntoListOfActiveFormattingElements(formattingClone, bookmark);
+            assert formattingEltStackPos < furthestBlockPos;
+            removeFromStack(formattingEltStackPos);
+            // furthestBlockPos is now off by one and points to the slot after
+            // it
+            insertIntoStack(formattingClone, furthestBlockPos);
+        }
+        return true;
+    }
+
+    private void insertIntoStack(StackNode<T> node, int position)
+            throws SAXException {
+        assert currentPtr + 1 < stack.length;
+        assert position <= currentPtr + 1;
+        if (position == currentPtr + 1) {
+            push(node);
+        } else {
+            System.arraycopy(stack, position, stack, position + 1,
+                    (currentPtr - position) + 1);
+            currentPtr++;
+            stack[position] = node;
+        }
+    }
+
+    private void insertIntoListOfActiveFormattingElements(
+            StackNode<T> formattingClone, int bookmark) {
+        formattingClone.retain();
+        assert listPtr + 1 < listOfActiveFormattingElements.length;
+        if (bookmark <= listPtr) {
+            System.arraycopy(listOfActiveFormattingElements, bookmark,
+                    listOfActiveFormattingElements, bookmark + 1,
+                    (listPtr - bookmark) + 1);
+        }
+        listPtr++;
+        listOfActiveFormattingElements[bookmark] = formattingClone;
+    }
+
+    private int findInListOfActiveFormattingElements(StackNode<T> node) {
+        for (int i = listPtr; i >= 0; i--) {
+            if (node == listOfActiveFormattingElements[i]) {
+                return i;
+            }
+        }
+        return -1;
+    }
+
+    private int findInListOfActiveFormattingElementsContainsBetweenEndAndLastMarker(
+            @Local String name) {
+        for (int i = listPtr; i >= 0; i--) {
+            StackNode<T> node = listOfActiveFormattingElements[i];
+            if (node == null) {
+                return -1;
+            } else if (node.name == name) {
+                return i;
+            }
+        }
+        return -1;
+    }
+
+
+    private void maybeForgetEarlierDuplicateFormattingElement(
+            @Local String name, HtmlAttributes attributes) throws SAXException {
+        int candidate = -1;
+        int count = 0;
+        for (int i = listPtr; i >= 0; i--) {
+            StackNode<T> node = listOfActiveFormattingElements[i];
+            if (node == null) {
+                break;
+            }
+            if (node.name == name && node.attributes.equalsAnother(attributes)) {
+                candidate = i;
+                ++count;
+            }
+        }
+        if (count >= 3) {
+            removeFromListOfActiveFormattingElements(candidate);
+        }
+    }
+
+    private int findLastOrRoot(@Local String name) {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].ns == "http://www.w3.org/1999/xhtml" && stack[i].name == name) {
+                return i;
+            }
+        }
+        return 0;
+    }
+
+    private int findLastOrRoot(int group) {
+        for (int i = currentPtr; i > 0; i--) {
+            if (stack[i].getGroup() == group) {
+                return i;
+            }
+        }
+        return 0;
+    }
+
+    /**
+     * Attempt to add attribute to the body element.
+     * @param attributes the attributes
+     * @return <code>true</code> iff the attributes were added
+     * @throws SAXException
+     */
+    private boolean addAttributesToBody(HtmlAttributes attributes)
+            throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        if (currentPtr >= 1) {
+            StackNode<T> body = stack[1];
+            if (body.getGroup() == TreeBuilder.BODY) {
+                addAttributesToElement(body.node, attributes);
+                return true;
+            }
+        }
+        return false;
+    }
+
+    private void addAttributesToHtml(HtmlAttributes attributes)
+            throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        addAttributesToElement(stack[0].node, attributes);
+    }
+
+    private void pushHeadPointerOntoStack() throws SAXException {
+        assert headPointer != null;
+        assert mode == AFTER_HEAD;
+        fatal();
+        silentPush(new StackNode<T>(ElementName.HEAD, headPointer
+        // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        ));
+    }
+
+    /**
+     * @throws SAXException
+     *
+     */
+    private void reconstructTheActiveFormattingElements() throws SAXException {
+        if (listPtr == -1) {
+            return;
+        }
+        StackNode<T> mostRecent = listOfActiveFormattingElements[listPtr];
+        if (mostRecent == null || isInStack(mostRecent)) {
+            return;
+        }
+        int entryPos = listPtr;
+        for (;;) {
+            entryPos--;
+            if (entryPos == -1) {
+                break;
+            }
+            if (listOfActiveFormattingElements[entryPos] == null) {
+                break;
+            }
+            if (isInStack(listOfActiveFormattingElements[entryPos])) {
+                break;
+            }
+        }
+        while (entryPos < listPtr) {
+            entryPos++;
+            StackNode<T> entry = listOfActiveFormattingElements[entryPos];
+            StackNode<T> currentNode = stack[currentPtr];
+
+            T clone;
+            if (currentNode.isFosterParenting()) {
+                clone = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", entry.name,
+                        entry.attributes.cloneAttributes(null));
+            } else {
+                clone = createElement("http://www.w3.org/1999/xhtml", entry.name,
+                        entry.attributes.cloneAttributes(null), currentNode.node);
+                appendElement(clone, currentNode.node);
+            }
+
+            StackNode<T> entryClone = new StackNode<T>(entry.getFlags(),
+                    entry.ns, entry.name, clone, entry.popName,
+                    entry.attributes
+                    // [NOCPP[
+                    , entry.getLocator()
+                    // ]NOCPP]
+            );
+
+            entry.dropAttributes(); // transfer ownership to entryClone
+
+            push(entryClone);
+            // stack takes ownership of the local variable
+            listOfActiveFormattingElements[entryPos] = entryClone;
+            // overwriting the old entry on the list, so release & retain
+            entry.release();
+            entryClone.retain();
+        }
+    }
+
+    private void insertIntoFosterParent(T child) throws SAXException {
+        int tablePos = findLastOrRoot(TreeBuilder.TABLE);
+        int templatePos = findLastOrRoot(TreeBuilder.TEMPLATE);
+
+        if (templatePos >= tablePos) {
+            appendElement(child, stack[templatePos].node);
+            return;
+        }
+
+        StackNode<T> node = stack[tablePos];
+        insertFosterParentedChild(child, node.node, stack[tablePos - 1].node);
+    }
+
+    private T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name,
+            HtmlAttributes attributes) throws SAXException {
+        return createAndInsertFosterParentedElement(ns, name, attributes, null);
+    }
+
+    private T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name,
+            HtmlAttributes attributes, T form) throws SAXException {
+        int tablePos = findLastOrRoot(TreeBuilder.TABLE);
+        int templatePos = findLastOrRoot(TreeBuilder.TEMPLATE);
+
+        if (templatePos >= tablePos) {
+            T child = createElement(ns, name, attributes, form, stack[templatePos].node);
+            appendElement(child, stack[templatePos].node);
+            return child;
+        }
+
+        StackNode<T> node = stack[tablePos];
+        return createAndInsertFosterParentedElement(ns, name, attributes, form, node.node, stack[tablePos - 1].node);
+    }
+
+    private boolean isInStack(StackNode<T> node) {
+        for (int i = currentPtr; i >= 0; i--) {
+            if (stack[i] == node) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    private void popTemplateMode() {
+        templateModePtr--;
+    }
+
+    private void pop() throws SAXException {
+        StackNode<T> node = stack[currentPtr];
+        assert debugOnlyClearLastStackSlot();
+        currentPtr--;
+        elementPopped(node.ns, node.popName, node.node);
+        node.release();
+    }
+
+    private void silentPop() throws SAXException {
+        StackNode<T> node = stack[currentPtr];
+        assert debugOnlyClearLastStackSlot();
+        currentPtr--;
+        node.release();
+    }
+
+    private void popOnEof() throws SAXException {
+        StackNode<T> node = stack[currentPtr];
+        assert debugOnlyClearLastStackSlot();
+        currentPtr--;
+        markMalformedIfScript(node.node);
+        elementPopped(node.ns, node.popName, node.node);
+        node.release();
+    }
+
+    // [NOCPP[
+    private void checkAttributes(HtmlAttributes attributes, @NsUri String ns)
+            throws SAXException {
+        if (errorHandler != null) {
+            int len = attributes.getXmlnsLength();
+            for (int i = 0; i < len; i++) {
+                AttributeName name = attributes.getXmlnsAttributeName(i);
+                if (name == AttributeName.XMLNS) {
+                    if (html4) {
+                        err("Attribute \u201Cxmlns\u201D not allowed here. (HTML4-only error.)");
+                    } else {
+                        String xmlns = attributes.getXmlnsValue(i);
+                        if (!ns.equals(xmlns)) {
+                            err("Bad value \u201C"
+                                    + xmlns
+                                    + "\u201D for the attribute \u201Cxmlns\u201D (only \u201C"
+                                    + ns + "\u201D permitted here).");
+                            switch (namePolicy) {
+                                case ALTER_INFOSET:
+                                    // fall through
+                                case ALLOW:
+                                    warn("Attribute \u201Cxmlns\u201D is not serializable as XML 1.0.");
+                                    break;
+                                case FATAL:
+                                    fatal("Attribute \u201Cxmlns\u201D is not serializable as XML 1.0.");
+                                    break;
+                            }
+                        }
+                    }
+                } else if (ns != "http://www.w3.org/1999/xhtml"
+                        && name == AttributeName.XMLNS_XLINK) {
+                    String xmlns = attributes.getXmlnsValue(i);
+                    if (!"http://www.w3.org/1999/xlink".equals(xmlns)) {
+                        err("Bad value \u201C"
+                                + xmlns
+                                + "\u201D for the attribute \u201Cxmlns:link\u201D (only \u201Chttp://www.w3.org/1999/xlink\u201D permitted here).");
+                        switch (namePolicy) {
+                            case ALTER_INFOSET:
+                                // fall through
+                            case ALLOW:
+                                warn("Attribute \u201Cxmlns:xlink\u201D with a value other than \u201Chttp://www.w3.org/1999/xlink\u201D is not serializable as XML 1.0 without changing document semantics.");
+                                break;
+                            case FATAL:
+                                fatal("Attribute \u201Cxmlns:xlink\u201D with a value other than \u201Chttp://www.w3.org/1999/xlink\u201D is not serializable as XML 1.0 without changing document semantics.");
+                                break;
+                        }
+                    }
+                } else {
+                    err("Attribute \u201C" + attributes.getXmlnsLocalName(i)
+                            + "\u201D not allowed here.");
+                    switch (namePolicy) {
+                        case ALTER_INFOSET:
+                            // fall through
+                        case ALLOW:
+                            warn("Attribute with the local name \u201C"
+                                    + attributes.getXmlnsLocalName(i)
+                                    + "\u201D is not serializable as XML 1.0.");
+                            break;
+                        case FATAL:
+                            fatal("Attribute with the local name \u201C"
+                                    + attributes.getXmlnsLocalName(i)
+                                    + "\u201D is not serializable as XML 1.0.");
+                            break;
+                    }
+                }
+            }
+        }
+        attributes.processNonNcNames(this, namePolicy);
+    }
+
+    private String checkPopName(@Local String name) throws SAXException {
+        if (NCName.isNCName(name)) {
+            return name;
+        } else {
+            switch (namePolicy) {
+                case ALLOW:
+                    warn("Element name \u201C" + name
+                            + "\u201D cannot be represented as XML 1.0.");
+                    return name;
+                case ALTER_INFOSET:
+                    warn("Element name \u201C" + name
+                            + "\u201D cannot be represented as XML 1.0.");
+                    return NCName.escapeName(name);
+                case FATAL:
+                    fatal("Element name \u201C" + name
+                            + "\u201D cannot be represented as XML 1.0.");
+            }
+        }
+        return null; // keep compiler happy
+    }
+
+    // ]NOCPP]
+
+    private void appendHtmlElementToDocumentAndPush(HtmlAttributes attributes)
+            throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        T elt = createHtmlElementSetAsRoot(attributes);
+        StackNode<T> node = new StackNode<T>(ElementName.HTML,
+                elt
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+    }
+
+    private void appendHtmlElementToDocumentAndPush() throws SAXException {
+        appendHtmlElementToDocumentAndPush(tokenizer.emptyAttributes());
+    }
+
+    private void appendToCurrentNodeAndPushHeadElement(HtmlAttributes attributes)
+            throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        T currentNode = stack[currentPtr].node;
+        T elt = createElement("http://www.w3.org/1999/xhtml", "head", attributes, currentNode);
+        appendElement(elt, currentNode);
+        headPointer = elt;
+        StackNode<T> node = new StackNode<T>(ElementName.HEAD,
+                elt
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+    }
+
+    private void appendToCurrentNodeAndPushBodyElement(HtmlAttributes attributes)
+            throws SAXException {
+        appendToCurrentNodeAndPushElement(ElementName.BODY,
+                attributes);
+    }
+
+    private void appendToCurrentNodeAndPushBodyElement() throws SAXException {
+        appendToCurrentNodeAndPushBodyElement(tokenizer.emptyAttributes());
+    }
+
+    private void appendToCurrentNodeAndPushFormElementMayFoster(
+            HtmlAttributes attributes) throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", "form", attributes);
+        } else {
+            elt = createElement("http://www.w3.org/1999/xhtml", "form", attributes, current.node);
+            appendElement(elt, current.node);
+        }
+
+        if (!isTemplateContents()) {
+            formPointer = elt;
+        }
+
+        StackNode<T> node = new StackNode<T>(ElementName.FORM,
+                elt
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+                // ]NOCPP]
+        );
+        push(node);
+    }
+
+    private void appendToCurrentNodeAndPushFormattingElementMayFoster(
+            ElementName elementName, HtmlAttributes attributes)
+            throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        // This method can't be called for custom elements
+        HtmlAttributes clone = attributes.cloneAttributes(null);
+        // Attributes must not be read after calling createElement, because
+        // createElement may delete attributes in C++.
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", elementName.name, attributes);
+        } else {
+            elt = createElement("http://www.w3.org/1999/xhtml", elementName.name, attributes, current.node);
+            appendElement(elt, current.node);
+        }
+        StackNode<T> node = new StackNode<T>(elementName, elt, clone
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+        append(node);
+        node.retain(); // append doesn't retain itself
+    }
+
+    private void appendToCurrentNodeAndPushElement(ElementName elementName,
+            HtmlAttributes attributes)
+            throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        // This method can't be called for custom elements
+        T currentNode = stack[currentPtr].node;
+        T elt = createElement("http://www.w3.org/1999/xhtml", elementName.name, attributes, currentNode);
+        appendElement(elt, currentNode);
+        if (ElementName.TEMPLATE == elementName) {
+            elt = getDocumentFragmentForTemplate(elt);
+        }
+        StackNode<T> node = new StackNode<T>(elementName, elt
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+    }
+
+    private void appendToCurrentNodeAndPushElementMayFoster(ElementName elementName,
+            HtmlAttributes attributes)
+            throws SAXException {
+        @Local String popName = elementName.name;
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        if (elementName.isCustom()) {
+            popName = checkPopName(popName);
+        }
+        // ]NOCPP]
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", popName, attributes);
+        } else {
+            elt = createElement("http://www.w3.org/1999/xhtml", popName, attributes, current.node);
+            appendElement(elt, current.node);
+        }
+        StackNode<T> node = new StackNode<T>(elementName, elt, popName
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+    }
+
+    private void appendToCurrentNodeAndPushElementMayFosterMathML(
+            ElementName elementName, HtmlAttributes attributes)
+            throws SAXException {
+        @Local String popName = elementName.name;
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1998/Math/MathML");
+        if (elementName.isCustom()) {
+            popName = checkPopName(popName);
+        }
+        // ]NOCPP]
+        boolean markAsHtmlIntegrationPoint = false;
+        if (ElementName.ANNOTATION_XML == elementName
+                && annotationXmlEncodingPermitsHtml(attributes)) {
+            markAsHtmlIntegrationPoint = true;
+        }
+        // Attributes must not be read after calling createElement(), since
+        // createElement may delete the object in C++.
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1998/Math/MathML", popName, attributes);
+        } else {
+            elt  = createElement("http://www.w3.org/1998/Math/MathML", popName, attributes, current.node);
+            appendElement(elt, current.node);
+        }
+        StackNode<T> node = new StackNode<T>(elementName, elt, popName,
+                markAsHtmlIntegrationPoint
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+    }
+
+    // [NOCPP[
+    T getDocumentFragmentForTemplate(T template) {
+        return template;
+    }
+
+    T getFormPointerForContext(T context) {
+        return null;
+    }
+    // ]NOCPP]
+
+    private boolean annotationXmlEncodingPermitsHtml(HtmlAttributes attributes) {
+        String encoding = attributes.getValue(AttributeName.ENCODING);
+        if (encoding == null) {
+            return false;
+        }
+        return Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                "application/xhtml+xml", encoding)
+                || Portability.lowerCaseLiteralEqualsIgnoreAsciiCaseString(
+                        "text/html", encoding);
+    }
+
+    private void appendToCurrentNodeAndPushElementMayFosterSVG(
+            ElementName elementName, HtmlAttributes attributes)
+            throws SAXException {
+        @Local String popName = elementName.camelCaseName;
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/2000/svg");
+        if (elementName.isCustom()) {
+            popName = checkPopName(popName);
+        }
+        // ]NOCPP]
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/2000/svg", popName, attributes);
+        } else {
+            elt = createElement("http://www.w3.org/2000/svg", popName, attributes, current.node);
+            appendElement(elt, current.node);
+        }
+        StackNode<T> node = new StackNode<T>(elementName, popName, elt
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+    }
+
+    private void appendToCurrentNodeAndPushElementMayFoster(ElementName elementName,
+            HtmlAttributes attributes, T form)
+            throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        // Can't be called for custom elements
+        T elt;
+        T formOwner = form == null || fragment || isTemplateContents() ? null : form;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", elementName.name,
+                    attributes, formOwner);
+        } else {
+            elt = createElement("http://www.w3.org/1999/xhtml", elementName.name,
+                    attributes, formOwner, current.node);
+            appendElement(elt, current.node);
+        }
+        StackNode<T> node = new StackNode<T>(elementName, elt
+                // [NOCPP[
+                , errorHandler == null ? null : new TaintableLocatorImpl(tokenizer)
+        // ]NOCPP]
+        );
+        push(node);
+    }
+
+    private void appendVoidElementToCurrentMayFoster(
+            @Local String name, HtmlAttributes attributes, T form) throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        // Can't be called for custom elements
+        T elt;
+        T formOwner = form == null || fragment || isTemplateContents() ? null : form;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", name,
+                    attributes, formOwner);
+        } else {
+            elt = createElement("http://www.w3.org/1999/xhtml", name,
+                    attributes, formOwner, current.node);
+            appendElement(elt, current.node);
+        }
+        elementPushed("http://www.w3.org/1999/xhtml", name, elt);
+        elementPopped("http://www.w3.org/1999/xhtml", name, elt);
+    }
+
+    private void appendVoidElementToCurrentMayFoster(
+            ElementName elementName, HtmlAttributes attributes)
+            throws SAXException {
+        @Local String popName = elementName.name;
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        if (elementName.isCustom()) {
+            popName = checkPopName(popName);
+        }
+        // ]NOCPP]
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1999/xhtml", popName, attributes);
+        } else {
+            elt = createElement("http://www.w3.org/1999/xhtml", popName, attributes, current.node);
+            appendElement(elt, current.node);
+        }
+        elementPushed("http://www.w3.org/1999/xhtml", popName, elt);
+        elementPopped("http://www.w3.org/1999/xhtml", popName, elt);
+    }
+
+    private void appendVoidElementToCurrentMayFosterSVG(
+            ElementName elementName, HtmlAttributes attributes)
+            throws SAXException {
+        @Local String popName = elementName.camelCaseName;
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/2000/svg");
+        if (elementName.isCustom()) {
+            popName = checkPopName(popName);
+        }
+        // ]NOCPP]
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/2000/svg", popName, attributes);
+        } else {
+            elt = createElement("http://www.w3.org/2000/svg", popName, attributes, current.node);
+            appendElement(elt, current.node);
+        }
+        elementPushed("http://www.w3.org/2000/svg", popName, elt);
+        elementPopped("http://www.w3.org/2000/svg", popName, elt);
+    }
+
+    private void appendVoidElementToCurrentMayFosterMathML(
+            ElementName elementName, HtmlAttributes attributes)
+            throws SAXException {
+        @Local String popName = elementName.name;
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1998/Math/MathML");
+        if (elementName.isCustom()) {
+            popName = checkPopName(popName);
+        }
+        // ]NOCPP]
+        T elt;
+        StackNode<T> current = stack[currentPtr];
+        if (current.isFosterParenting()) {
+            fatal();
+            elt = createAndInsertFosterParentedElement("http://www.w3.org/1998/Math/MathML", popName, attributes);
+        } else {
+            elt = createElement("http://www.w3.org/1998/Math/MathML", popName, attributes, current.node);
+            appendElement(elt, current.node);
+        }
+        elementPushed("http://www.w3.org/1998/Math/MathML", popName, elt);
+        elementPopped("http://www.w3.org/1998/Math/MathML", popName, elt);
+    }
+
+    private void appendVoidElementToCurrent(
+            @Local String name, HtmlAttributes attributes, T form) throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        // Can't be called for custom elements
+        T currentNode = stack[currentPtr].node;
+        T elt = createElement("http://www.w3.org/1999/xhtml", name, attributes,
+                form == null || fragment || isTemplateContents() ? null : form, currentNode);
+        appendElement(elt, currentNode);
+        elementPushed("http://www.w3.org/1999/xhtml", name, elt);
+        elementPopped("http://www.w3.org/1999/xhtml", name, elt);
+    }
+
+    private void appendVoidFormToCurrent(HtmlAttributes attributes) throws SAXException {
+        // [NOCPP[
+        checkAttributes(attributes, "http://www.w3.org/1999/xhtml");
+        // ]NOCPP]
+        T currentNode = stack[currentPtr].node;
+        T elt = createElement("http://www.w3.org/1999/xhtml", "form",
+                attributes, currentNode);
+        formPointer = elt;
+        // ownership transferred to form pointer
+        appendElement(elt, currentNode);
+        elementPushed("http://www.w3.org/1999/xhtml", "form", elt);
+        elementPopped("http://www.w3.org/1999/xhtml", "form", elt);
+    }
+
+    // [NOCPP[
+
+    private final void accumulateCharactersForced(@Const @NoLength char[] buf,
+            int start, int length) throws SAXException {
+        System.arraycopy(buf, start, charBuffer, charBufferLen, length);
+        charBufferLen += length;
+    }
+
+    @Override public void ensureBufferSpace(int inputLength)
+            throws SAXException {
+        // TODO: Unify Tokenizer.strBuf and TreeBuilder.charBuffer so that
+        // this method becomes unnecessary.
+        int worstCase = charBufferLen + inputLength;
+        if (charBuffer == null) {
+            // Add an arbitrary small value to avoid immediate reallocation
+            // once there are a few characters in the buffer.
+            charBuffer = new char[worstCase + 128];
+        } else if (worstCase > charBuffer.length) {
+            // HotSpot reportedly allocates memory with 8-byte accuracy, so
+            // there's no point in trying to do math here to avoid slop.
+            // Maybe we should add some small constant to worstCase here
+            // but not doing that without profiling. In C++ with jemalloc,
+            // the corresponding method should do math to round up here
+            // to avoid slop.
+            char[] newBuf = new char[worstCase];
+            System.arraycopy(charBuffer, 0, newBuf, 0, charBufferLen);
+            charBuffer = newBuf;
+        }
+    }
+
+    // ]NOCPP]
+
+    protected void accumulateCharacters(@Const @NoLength char[] buf, int start,
+            int length) throws SAXException {
+        appendCharacters(stack[currentPtr].node, buf, start, length);
+    }
+
+    // ------------------------------- //
+
+    protected final void requestSuspension() {
+        tokenizer.requestSuspension();
+    }
+
+    protected abstract T createElement(@NsUri String ns, @Local String name,
+            HtmlAttributes attributes, T intendedParent) throws SAXException;
+
+    protected T createElement(@NsUri String ns, @Local String name,
+            HtmlAttributes attributes, T form, T intendedParent) throws SAXException {
+        return createElement("http://www.w3.org/1999/xhtml", name, attributes, intendedParent);
+    }
+
+    protected abstract T createHtmlElementSetAsRoot(HtmlAttributes attributes)
+            throws SAXException;
+
+    protected abstract void detachFromParent(T element) throws SAXException;
+
+    protected abstract boolean hasChildren(T element) throws SAXException;
+
+    protected abstract void appendElement(T child, T newParent)
+            throws SAXException;
+
+    protected abstract void appendChildrenToNewParent(T oldParent, T newParent)
+            throws SAXException;
+
+    protected abstract void insertFosterParentedChild(T child, T table,
+            T stackParent) throws SAXException;
+
+    // We don't generate CPP code for this method because it is not used in generated CPP
+    // code. Instead, the form owner version of this method is called with a null form owner.
+    // [NOCPP[
+
+    protected abstract T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name,
+            HtmlAttributes attributes, T table, T stackParent) throws SAXException;
+
+    // ]NOCPP]
+
+    protected T createAndInsertFosterParentedElement(@NsUri String ns, @Local String name,
+            HtmlAttributes attributes, T form, T table, T stackParent) throws SAXException {
+        return createAndInsertFosterParentedElement(ns, name, attributes, table, stackParent);
+    };
+
+    protected abstract void insertFosterParentedCharacters(
+            @NoLength char[] buf, int start, int length, T table, T stackParent)
+            throws SAXException;
+
+    protected abstract void appendCharacters(T parent, @NoLength char[] buf,
+            int start, int length) throws SAXException;
+
+    protected abstract void appendIsindexPrompt(T parent) throws SAXException;
+
+    protected abstract void appendComment(T parent, @NoLength char[] buf,
+            int start, int length) throws SAXException;
+
+    protected abstract void appendCommentToDocument(@NoLength char[] buf,
+            int start, int length) throws SAXException;
+
+    protected abstract void addAttributesToElement(T element,
+            HtmlAttributes attributes) throws SAXException;
+
+    protected void markMalformedIfScript(T elt) throws SAXException {
+
+    }
+
+    protected void start(boolean fragmentMode) throws SAXException {
+
+    }
+
+    protected void end() throws SAXException {
+
+    }
+
+    protected void appendDoctypeToDocument(@Local String name,
+            String publicIdentifier, String systemIdentifier)
+            throws SAXException {
+
+    }
+
+    protected void elementPushed(@NsUri String ns, @Local String name, T node)
+            throws SAXException {
+
+    }
+
+    protected void elementPopped(@NsUri String ns, @Local String name, T node)
+            throws SAXException {
+
+    }
+
+    // [NOCPP[
+
+    protected void documentMode(DocumentMode m, String publicIdentifier,
+            String systemIdentifier, boolean html4SpecificAdditionalErrorChecks)
+            throws SAXException {
+
+    }
+
+    /**
+     * @see nu.validator.htmlparser.common.TokenHandler#wantsComments()
+     */
+    public boolean wantsComments() {
+        return wantingComments;
+    }
+
+    public void setIgnoringComments(boolean ignoreComments) {
+        wantingComments = !ignoreComments;
+    }
+
+    /**
+     * Sets the errorHandler.
+     *
+     * @param errorHandler
+     *            the errorHandler to set
+     */
+    public final void setErrorHandler(ErrorHandler errorHandler) {
+        this.errorHandler = errorHandler;
+    }
+
+    /**
+     * Returns the errorHandler.
+     *
+     * @return the errorHandler
+     */
+    public ErrorHandler getErrorHandler() {
+        return errorHandler;
+    }
+
+    /**
+     * The argument MUST be an interned string or <code>null</code>.
+     *
+     * @param context
+     */
+    public final void setFragmentContext(@Local String context) {
+        this.contextName = context;
+        this.contextNamespace = "http://www.w3.org/1999/xhtml";
+        this.contextNode = null;
+        this.fragment = (contextName != null);
+        this.quirks = false;
+    }
+
+    // ]NOCPP]
+
+    /**
+     * @see nu.validator.htmlparser.common.TokenHandler#cdataSectionAllowed()
+     */
+    @Inline public boolean cdataSectionAllowed() throws SAXException {
+        return isInForeign();
+    }
+
+    private boolean isInForeign() {
+        return currentPtr >= 0
+                && stack[currentPtr].ns != "http://www.w3.org/1999/xhtml";
+    }
+
+    private boolean isInForeignButNotHtmlOrMathTextIntegrationPoint() {
+        if (currentPtr < 0) {
+            return false;
+        }
+        return !isSpecialParentInForeign(stack[currentPtr]);
+    }
+
+    /**
+     * The argument MUST be an interned string or <code>null</code>.
+     *
+     * @param context
+     */
+    public final void setFragmentContext(@Local String context,
+            @NsUri String ns, T node, boolean quirks) {
+        // [NOCPP[
+        if (!((context == null && ns == null)
+                || "http://www.w3.org/1999/xhtml" == ns
+                || "http://www.w3.org/2000/svg" == ns || "http://www.w3.org/1998/Math/MathML" == ns)) {
+            throw new IllegalArgumentException(
+                    "The namespace must be the HTML, SVG or MathML namespace (or null when the local name is null). Got: "
+                            + ns);
+        }
+        // ]NOCPP]
+        this.contextName = context;
+        this.contextNamespace = ns;
+        this.contextNode = node;
+        this.fragment = (contextName != null);
+        this.quirks = quirks;
+    }
+
+    protected final T currentNode() {
+        return stack[currentPtr].node;
+    }
+
+    /**
+     * Returns the scriptingEnabled.
+     *
+     * @return the scriptingEnabled
+     */
+    public boolean isScriptingEnabled() {
+        return scriptingEnabled;
+    }
+
+    /**
+     * Sets the scriptingEnabled.
+     *
+     * @param scriptingEnabled
+     *            the scriptingEnabled to set
+     */
+    public void setScriptingEnabled(boolean scriptingEnabled) {
+        this.scriptingEnabled = scriptingEnabled;
+    }
+
+    public void setIsSrcdocDocument(boolean isSrcdocDocument) {
+        this.isSrcdocDocument = isSrcdocDocument;
+    }
+
+    // [NOCPP[
+
+    /**
+     * Sets the doctypeExpectation.
+     *
+     * @param doctypeExpectation
+     *            the doctypeExpectation to set
+     */
+    public void setDoctypeExpectation(DoctypeExpectation doctypeExpectation) {
+        this.doctypeExpectation = doctypeExpectation;
+    }
+
+    public void setNamePolicy(XmlViolationPolicy namePolicy) {
+        this.namePolicy = namePolicy;
+    }
+
+    /**
+     * Sets the documentModeHandler.
+     *
+     * @param documentModeHandler
+     *            the documentModeHandler to set
+     */
+    public void setDocumentModeHandler(DocumentModeHandler documentModeHandler) {
+        this.documentModeHandler = documentModeHandler;
+    }
+
+    /**
+     * Sets the reportingDoctype.
+     *
+     * @param reportingDoctype
+     *            the reportingDoctype to set
+     */
+    public void setReportingDoctype(boolean reportingDoctype) {
+        this.reportingDoctype = reportingDoctype;
+    }
+
+    // ]NOCPP]
+
+    /**
+     * Flushes the pending characters. Public for document.write use cases only.
+     * @throws SAXException
+     */
+    public final void flushCharacters() throws SAXException {
+        if (charBufferLen > 0) {
+            if ((mode == IN_TABLE || mode == IN_TABLE_BODY || mode == IN_ROW)
+                    && charBufferContainsNonWhitespace()) {
+                errNonSpaceInTable();
+                reconstructTheActiveFormattingElements();
+                if (!stack[currentPtr].isFosterParenting()) {
+                    // reconstructing gave us a new current node
+                    appendCharacters(currentNode(), charBuffer, 0,
+                            charBufferLen);
+                    charBufferLen = 0;
+                    return;
+                }
+
+                int tablePos = findLastOrRoot(TreeBuilder.TABLE);
+                int templatePos = findLastOrRoot(TreeBuilder.TEMPLATE);
+
+                if (templatePos >= tablePos) {
+                    appendCharacters(stack[templatePos].node, charBuffer, 0, charBufferLen);
+                    charBufferLen = 0;
+                    return;
+                }
+
+                StackNode<T> tableElt = stack[tablePos];
+                insertFosterParentedCharacters(charBuffer, 0, charBufferLen,
+                        tableElt.node, stack[tablePos - 1].node);
+                charBufferLen = 0;
+                return;
+            }
+            appendCharacters(currentNode(), charBuffer, 0, charBufferLen);
+            charBufferLen = 0;
+        }
+    }
+
+    private boolean charBufferContainsNonWhitespace() {
+        for (int i = 0; i < charBufferLen; i++) {
+            switch (charBuffer[i]) {
+                case ' ':
+                case '\t':
+                case '\n':
+                case '\r':
+                case '\u000C':
+                    continue;
+                default:
+                    return true;
+            }
+        }
+        return false;
+    }
+
+    /**
+     * Creates a comparable snapshot of the tree builder state. Snapshot
+     * creation is only supported immediately after a script end tag has been
+     * processed. In C++ the caller is responsible for calling
+     * <code>delete</code> on the returned object.
+     *
+     * @return a snapshot.
+     * @throws SAXException
+     */
+    @SuppressWarnings("unchecked") public TreeBuilderState<T> newSnapshot()
+            throws SAXException {
+        StackNode<T>[] listCopy = new StackNode[listPtr + 1];
+        for (int i = 0; i < listCopy.length; i++) {
+            StackNode<T> node = listOfActiveFormattingElements[i];
+            if (node != null) {
+                StackNode<T> newNode = new StackNode<T>(node.getFlags(), node.ns,
+                        node.name, node.node, node.popName,
+                        node.attributes.cloneAttributes(null)
+                        // [NOCPP[
+                        , node.getLocator()
+                // ]NOCPP]
+                );
+                listCopy[i] = newNode;
+            } else {
+                listCopy[i] = null;
+            }
+        }
+        StackNode<T>[] stackCopy = new StackNode[currentPtr + 1];
+        for (int i = 0; i < stackCopy.length; i++) {
+            StackNode<T> node = stack[i];
+            int listIndex = findInListOfActiveFormattingElements(node);
+            if (listIndex == -1) {
+                StackNode<T> newNode = new StackNode<T>(node.getFlags(), node.ns,
+                        node.name, node.node, node.popName,
+                        null
+                        // [NOCPP[
+                        , node.getLocator()
+                // ]NOCPP]
+                );
+                stackCopy[i] = newNode;
+            } else {
+                stackCopy[i] = listCopy[listIndex];
+                stackCopy[i].retain();
+            }
+        }
+        int[] templateModeStackCopy = new int[templateModePtr + 1];
+        System.arraycopy(templateModeStack, 0, templateModeStackCopy, 0,
+                templateModeStackCopy.length);
+        return new StateSnapshot<T>(stackCopy, listCopy, templateModeStackCopy, formPointer,
+                headPointer, deepTreeSurrogateParent, mode, originalMode, framesetOk,
+                needToDropLF, quirks);
+    }
+
+    public boolean snapshotMatches(TreeBuilderState<T> snapshot) {
+        StackNode<T>[] stackCopy = snapshot.getStack();
+        int stackLen = snapshot.getStackLength();
+        StackNode<T>[] listCopy = snapshot.getListOfActiveFormattingElements();
+        int listLen = snapshot.getListOfActiveFormattingElementsLength();
+        int[] templateModeStackCopy = snapshot.getTemplateModeStack();
+        int templateModeStackLen = snapshot.getTemplateModeStackLength();
+
+        if (stackLen != currentPtr + 1
+                || listLen != listPtr + 1
+                || templateModeStackLen != templateModePtr + 1
+                || formPointer != snapshot.getFormPointer()
+                || headPointer != snapshot.getHeadPointer()
+                || deepTreeSurrogateParent != snapshot.getDeepTreeSurrogateParent()
+                || mode != snapshot.getMode()
+                || originalMode != snapshot.getOriginalMode()
+                || framesetOk != snapshot.isFramesetOk()
+                || needToDropLF != snapshot.isNeedToDropLF()
+                || quirks != snapshot.isQuirks()) { // maybe just assert quirks
+            return false;
+        }
+        for (int i = listLen - 1; i >= 0; i--) {
+            if (listCopy[i] == null
+                    && listOfActiveFormattingElements[i] == null) {
+                continue;
+            } else if (listCopy[i] == null
+                    || listOfActiveFormattingElements[i] == null) {
+                return false;
+            }
+            if (listCopy[i].node != listOfActiveFormattingElements[i].node) {
+                return false; // it's possible that this condition is overly
+                              // strict
+            }
+        }
+        for (int i = stackLen - 1; i >= 0; i--) {
+            if (stackCopy[i].node != stack[i].node) {
+                return false;
+            }
+        }
+        for (int i = templateModeStackLen - 1; i >=0; i--) {
+            if (templateModeStackCopy[i] != templateModeStack[i]) {
+                return false;
+            }
+        }
+        return true;
+    }
+
+    @SuppressWarnings("unchecked") public void loadState(
+            TreeBuilderState<T> snapshot, Interner interner)
+            throws SAXException {
+        StackNode<T>[] stackCopy = snapshot.getStack();
+        int stackLen = snapshot.getStackLength();
+        StackNode<T>[] listCopy = snapshot.getListOfActiveFormattingElements();
+        int listLen = snapshot.getListOfActiveFormattingElementsLength();
+        int[] templateModeStackCopy = snapshot.getTemplateModeStack();
+        int templateModeStackLen = snapshot.getTemplateModeStackLength();
+
+        for (int i = 0; i <= listPtr; i++) {
+            if (listOfActiveFormattingElements[i] != null) {
+                listOfActiveFormattingElements[i].release();
+            }
+        }
+        if (listOfActiveFormattingElements.length < listLen) {
+            listOfActiveFormattingElements = new StackNode[listLen];
+        }
+        listPtr = listLen - 1;
+
+        for (int i = 0; i <= currentPtr; i++) {
+            stack[i].release();
+        }
+        if (stack.length < stackLen) {
+            stack = new StackNode[stackLen];
+        }
+        currentPtr = stackLen - 1;
+
+        if (templateModeStack.length < templateModeStackLen) {
+            templateModeStack = new int[templateModeStackLen];
+        }
+        templateModePtr = templateModeStackLen - 1;
+
+        for (int i = 0; i < listLen; i++) {
+            StackNode<T> node = listCopy[i];
+            if (node != null) {
+                StackNode<T> newNode = new StackNode<T>(node.getFlags(), node.ns,
+                        Portability.newLocalFromLocal(node.name, interner), node.node,
+                        Portability.newLocalFromLocal(node.popName, interner),
+                        node.attributes.cloneAttributes(null)
+                        // [NOCPP[
+                        , node.getLocator()
+                // ]NOCPP]
+                );
+                listOfActiveFormattingElements[i] = newNode;
+            } else {
+                listOfActiveFormattingElements[i] = null;
+            }
+        }
+        for (int i = 0; i < stackLen; i++) {
+            StackNode<T> node = stackCopy[i];
+            int listIndex = findInArray(node, listCopy);
+            if (listIndex == -1) {
+                StackNode<T> newNode = new StackNode<T>(node.getFlags(), node.ns,
+                        Portability.newLocalFromLocal(node.name, interner), node.node,
+                        Portability.newLocalFromLocal(node.popName, interner),
+                        null
+                        // [NOCPP[
+                        , node.getLocator()
+                // ]NOCPP]
+                );
+                stack[i] = newNode;
+            } else {
+                stack[i] = listOfActiveFormattingElements[listIndex];
+                stack[i].retain();
+            }
+        }
+        System.arraycopy(templateModeStackCopy, 0, templateModeStack, 0, templateModeStackLen);
+        formPointer = snapshot.getFormPointer();
+        headPointer = snapshot.getHeadPointer();
+        deepTreeSurrogateParent = snapshot.getDeepTreeSurrogateParent();
+        mode = snapshot.getMode();
+        originalMode = snapshot.getOriginalMode();
+        framesetOk = snapshot.isFramesetOk();
+        needToDropLF = snapshot.isNeedToDropLF();
+        quirks = snapshot.isQuirks();
+    }
+
+    private int findInArray(StackNode<T> node, StackNode<T>[] arr) {
+        for (int i = listPtr; i >= 0; i--) {
+            if (node == arr[i]) {
+                return i;
+            }
+        }
+        return -1;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getFormPointer()
+     */
+    public T getFormPointer() {
+        return formPointer;
+    }
+
+    /**
+     * Returns the headPointer.
+     *
+     * @return the headPointer
+     */
+    public T getHeadPointer() {
+        return headPointer;
+    }
+
+    /**
+     * Returns the deepTreeSurrogateParent.
+     *
+     * @return the deepTreeSurrogateParent
+     */
+    public T getDeepTreeSurrogateParent() {
+        return deepTreeSurrogateParent;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElements()
+     */
+    public StackNode<T>[] getListOfActiveFormattingElements() {
+        return listOfActiveFormattingElements;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getStack()
+     */
+    public StackNode<T>[] getStack() {
+        return stack;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStack()
+     */
+    public int[] getTemplateModeStack() {
+        return templateModeStack;
+    }
+
+    /**
+     * Returns the mode.
+     *
+     * @return the mode
+     */
+    public int getMode() {
+        return mode;
+    }
+
+    /**
+     * Returns the originalMode.
+     *
+     * @return the originalMode
+     */
+    public int getOriginalMode() {
+        return originalMode;
+    }
+
+    /**
+     * Returns the framesetOk.
+     *
+     * @return the framesetOk
+     */
+    public boolean isFramesetOk() {
+        return framesetOk;
+    }
+
+    /**
+     * Returns the needToDropLF.
+     *
+     * @return the needToDropLF
+     */
+    public boolean isNeedToDropLF() {
+        return needToDropLF;
+    }
+
+    /**
+     * Returns the quirks.
+     *
+     * @return the quirks
+     */
+    public boolean isQuirks() {
+        return quirks;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getListOfActiveFormattingElementsLength()
+     */
+    public int getListOfActiveFormattingElementsLength() {
+        return listPtr + 1;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getStackLength()
+     */
+    public int getStackLength() {
+        return currentPtr + 1;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilderState#getTemplateModeStackLength()
+     */
+    public int getTemplateModeStackLength() {
+        return templateModePtr + 1;
+    }
+
+    /**
+     * Reports a stray start tag.
+     * @param name the name of the stray tag
+     *
+     * @throws SAXException
+     */
+    private void errStrayStartTag(@Local String name) throws SAXException {
+        err("Stray start tag \u201C" + name + "\u201D.");
+    }
+
+    /**
+     * Reports a stray end tag.
+     * @param name the name of the stray tag
+     *
+     * @throws SAXException
+     */
+    private void errStrayEndTag(@Local String name) throws SAXException {
+        err("Stray end tag \u201C" + name + "\u201D.");
+    }
+
+    /**
+     * Reports a state when elements expected to be closed were not.
+     *
+     * @param eltPos the position of the start tag on the stack of the element
+     * being closed.
+     * @param name the name of the end tag
+     *
+     * @throws SAXException
+     */
+    private void errUnclosedElements(int eltPos, @Local String name) throws SAXException {
+        errNoCheck("End tag \u201C" + name + "\u201D seen, but there were open elements.");
+        errListUnclosedStartTags(eltPos);
+    }
+
+    /**
+     * Reports a state when elements expected to be closed ahead of an implied
+     * end tag but were not.
+     *
+     * @param eltPos the position of the start tag on the stack of the element
+     * being closed.
+     * @param name the name of the end tag
+     *
+     * @throws SAXException
+     */
+    private void errUnclosedElementsImplied(int eltPos, String name) throws SAXException {
+        errNoCheck("End tag \u201C" + name + "\u201D implied, but there were open elements.");
+        errListUnclosedStartTags(eltPos);
+    }
+
+    /**
+     * Reports a state when elements expected to be closed ahead of an implied
+     * table cell close.
+     *
+     * @param eltPos the position of the start tag on the stack of the element
+     * being closed.
+     * @throws SAXException
+     */
+    private void errUnclosedElementsCell(int eltPos) throws SAXException {
+        errNoCheck("A table cell was implicitly closed, but there were open elements.");
+        errListUnclosedStartTags(eltPos);
+    }
+
+    private void errStrayDoctype() throws SAXException {
+        err("Stray doctype.");
+    }
+
+    private void errAlmostStandardsDoctype() throws SAXException {
+        if (!isSrcdocDocument) {
+            err("Almost standards mode doctype. Expected \u201C<!DOCTYPE html>\u201D.");
+        }
+    }
+
+    private void errQuirkyDoctype() throws SAXException {
+        if (!isSrcdocDocument) {
+            err("Quirky doctype. Expected \u201C<!DOCTYPE html>\u201D.");
+        }
+    }
+
+    private void errNonSpaceInTrailer() throws SAXException {
+        err("Non-space character in page trailer.");
+    }
+
+    private void errNonSpaceAfterFrameset() throws SAXException {
+        err("Non-space after \u201Cframeset\u201D.");
+    }
+
+    private void errNonSpaceInFrameset() throws SAXException {
+        err("Non-space in \u201Cframeset\u201D.");
+    }
+
+    private void errNonSpaceAfterBody() throws SAXException {
+        err("Non-space character after body.");
+    }
+
+    private void errNonSpaceInColgroupInFragment() throws SAXException {
+        err("Non-space in \u201Ccolgroup\u201D when parsing fragment.");
+    }
+
+    private void errNonSpaceInNoscriptInHead() throws SAXException {
+        err("Non-space character inside \u201Cnoscript\u201D inside \u201Chead\u201D.");
+    }
+
+    private void errFooBetweenHeadAndBody(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("\u201C" + name + "\u201D element between \u201Chead\u201D and \u201Cbody\u201D.");
+    }
+
+    private void errStartTagWithoutDoctype() throws SAXException {
+        if (!isSrcdocDocument) {
+            err("Start tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D.");
+        }
+    }
+
+    private void errNoSelectInTableScope() throws SAXException {
+        err("No \u201Cselect\u201D in table scope.");
+    }
+
+    private void errStartSelectWhereEndSelectExpected() throws SAXException {
+        err("\u201Cselect\u201D start tag where end tag expected.");
+    }
+
+    private void errStartTagWithSelectOpen(@Local String name)
+            throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("\u201C" + name
+                + "\u201D start tag with \u201Cselect\u201D open.");
+    }
+
+    private void errBadStartTagInHead(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("Bad start tag in \u201C" + name
+                + "\u201D in \u201Chead\u201D.");
+    }
+
+    private void errImage() throws SAXException {
+        err("Saw a start tag \u201Cimage\u201D.");
+    }
+
+    private void errIsindex() throws SAXException {
+        err("\u201Cisindex\u201D seen.");
+    }
+
+    private void errFooSeenWhenFooOpen(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("An \u201C" + name + "\u201D start tag seen but an element of the same type was already open.");
+    }
+
+    private void errHeadingWhenHeadingOpen() throws SAXException {
+        err("Heading cannot be a child of another heading.");
+    }
+
+    private void errFramesetStart() throws SAXException {
+        err("\u201Cframeset\u201D start tag seen.");
+    }
+
+    private void errNoCellToClose() throws SAXException {
+        err("No cell to close.");
+    }
+
+    private void errStartTagInTable(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("Start tag \u201C" + name
+                + "\u201D seen in \u201Ctable\u201D.");
+    }
+
+    private void errFormWhenFormOpen() throws SAXException {
+        err("Saw a \u201Cform\u201D start tag, but there was already an active \u201Cform\u201D element. Nested forms are not allowed. Ignoring the tag.");
+    }
+
+    private void errTableSeenWhileTableOpen() throws SAXException {
+        err("Start tag for \u201Ctable\u201D seen but the previous \u201Ctable\u201D is still open.");
+    }
+
+    private void errStartTagInTableBody(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("\u201C" + name + "\u201D start tag in table body.");
+    }
+
+    private void errEndTagSeenWithoutDoctype() throws SAXException {
+        if (!isSrcdocDocument) {
+            err("End tag seen without seeing a doctype first. Expected \u201C<!DOCTYPE html>\u201D.");
+        }
+    }
+
+    private void errEndTagAfterBody() throws SAXException {
+        err("Saw an end tag after \u201Cbody\u201D had been closed.");
+    }
+
+    private void errEndTagSeenWithSelectOpen(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("\u201C" + name
+                + "\u201D end tag with \u201Cselect\u201D open.");
+    }
+
+    private void errGarbageInColgroup() throws SAXException {
+        err("Garbage in \u201Ccolgroup\u201D fragment.");
+    }
+
+    private void errEndTagBr() throws SAXException {
+        err("End tag \u201Cbr\u201D.");
+    }
+
+    private void errNoElementToCloseButEndTagSeen(@Local String name)
+            throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("No \u201C" + name + "\u201D element in scope but a \u201C"
+                + name + "\u201D end tag seen.");
+    }
+
+    private void errHtmlStartTagInForeignContext(@Local String name)
+            throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("HTML start tag \u201C" + name
+                + "\u201D in a foreign namespace context.");
+    }
+
+    private void errTableClosedWhileCaptionOpen() throws SAXException {
+        err("\u201Ctable\u201D closed but \u201Ccaption\u201D was still open.");
+    }
+
+    private void errNoTableRowToClose() throws SAXException {
+        err("No table row to close.");
+    }
+
+    private void errNonSpaceInTable() throws SAXException {
+        err("Misplaced non-space characters insided a table.");
+    }
+
+    private void errUnclosedChildrenInRuby() throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("Unclosed children in \u201Cruby\u201D.");
+    }
+
+    private void errStartTagSeenWithoutRuby(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("Start tag \u201C"
+                + name
+                + "\u201D seen without a \u201Cruby\u201D element being open.");
+    }
+
+    private void errSelfClosing() throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("Self-closing syntax (\u201C/>\u201D) used on a non-void HTML element. Ignoring the slash and treating as a start tag.");
+    }
+
+    private void errNoCheckUnclosedElementsOnStack() throws SAXException {
+        errNoCheck("Unclosed elements on stack.");
+    }
+
+    private void errEndTagDidNotMatchCurrentOpenElement(@Local String name,
+            @Local String currOpenName) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("End tag \u201C"
+                + name
+                + "\u201D did not match the name of the current open element (\u201C"
+                + currOpenName + "\u201D).");
+    }
+
+    private void errEndTagViolatesNestingRules(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("End tag \u201C" + name + "\u201D violates nesting rules.");
+    }
+
+    private void errEofWithUnclosedElements() throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("End of file seen and there were open elements.");
+        // just report all remaining unclosed elements
+        errListUnclosedStartTags(0);
+    }
+
+    /**
+     * Reports arriving at/near end of document with unclosed elements remaining.
+     *
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    private void errEndWithUnclosedElements(@Local String name) throws SAXException {
+        if (errorHandler == null) {
+            return;
+        }
+        errNoCheck("End tag for  \u201C"
+                + name
+                + "\u201D seen, but there were unclosed elements.");
+        // just report all remaining unclosed elements
+        errListUnclosedStartTags(0);
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TreeBuilderState.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TreeBuilderState.java
new file mode 100644
index 000000000..c4e2d4afb
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/TreeBuilderState.java
@@ -0,0 +1,129 @@
+/*
+ * Copyright (c) 2009-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+/**
+ * Interface for exposing the state of the HTML5 tree builder so that the
+ * interface can be implemented by the tree builder itself and by snapshots.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface TreeBuilderState<T> {
+
+    /**
+     * Returns the stack.
+     * 
+     * @return the stack
+     */
+    public StackNode<T>[] getStack();
+
+    /**
+     * Returns the listOfActiveFormattingElements.
+     *
+     * @return the listOfActiveFormattingElements
+     */
+    public StackNode<T>[] getListOfActiveFormattingElements();
+
+    /**
+     * Returns the stack of template insertion modes.
+     *
+     * @return the stack of template insertion modes
+     */
+    public int[] getTemplateModeStack();
+
+    /**
+     * Returns the formPointer.
+     * 
+     * @return the formPointer
+     */
+    public T getFormPointer();
+
+    /**
+     * Returns the headPointer.
+     * 
+     * @return the headPointer
+     */
+    public T getHeadPointer();
+    
+    /**
+     * Returns the deepTreeSurrogateParent.
+     * 
+     * @return the deepTreeSurrogateParent
+     */
+    public T getDeepTreeSurrogateParent();
+
+    /**
+     * Returns the mode.
+     * 
+     * @return the mode
+     */
+    public int getMode();
+
+    /**
+     * Returns the originalMode.
+     * 
+     * @return the originalMode
+     */
+    public int getOriginalMode();
+
+    /**
+     * Returns the framesetOk.
+     * 
+     * @return the framesetOk
+     */
+    public boolean isFramesetOk();
+    
+    /**
+     * Returns the needToDropLF.
+     * 
+     * @return the needToDropLF
+     */
+    public boolean isNeedToDropLF();
+
+    /**
+     * Returns the quirks.
+     * 
+     * @return the quirks
+     */
+    public boolean isQuirks();
+
+    /**
+     * Return the length of the stack.
+     * @return the length of the stack.
+     */
+    public int getStackLength();
+
+    /**
+     * Return the length of the list of active formatting elements.
+     * @return the length of the list of active formatting elements.
+     */
+    public int getListOfActiveFormattingElementsLength();
+
+    /**
+     * Return the length of the stack of template insertion modes.
+     *
+     * @return the length of the stack of template insertion modes.
+     */
+    int getTemplateModeStackLength();
+}
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/UTF16Buffer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/UTF16Buffer.java
new file mode 100644
index 000000000..35f1ac055
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/UTF16Buffer.java
@@ -0,0 +1,153 @@
+/*
+ * Copyright (c) 2008-2010 Mozilla Foundation
+ * Copyright (c) 2018-2020 Moonchild Productions
+ * Copyright (c) 2020 Binary Outcast
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.impl;
+
+import nu.validator.htmlparser.annotation.NoLength;
+
+/**
+ * An UTF-16 buffer that knows the start and end indeces of its unconsumed
+ * content.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class UTF16Buffer {
+
+    /**
+     * The backing store of the buffer. May be larger than the logical content
+     * of this <code>UTF16Buffer</code>.
+     */
+    private final @NoLength char[] buffer;
+
+    /**
+     * The index of the first unconsumed character in the backing buffer.
+     */
+    private int start;
+
+    /**
+     * The index of the slot immediately after the last character in the backing
+     * buffer that is part of the logical content of this
+     * <code>UTF16Buffer</code>.
+     */
+    private int end;
+
+    //[NOCPP[
+    
+    /**
+     * Constructor for wrapping an existing UTF-16 code unit array.
+     * 
+     * @param buffer
+     *            the backing buffer
+     * @param start
+     *            the index of the first character to consume
+     * @param end
+     *            the index immediately after the last character to consume
+     */
+    public UTF16Buffer(@NoLength char[] buffer, int start, int end) {
+        this.buffer = buffer;
+        this.start = start;
+        this.end = end;
+    }
+
+    // ]NOCPP]
+    
+    /**
+     * Returns the start index.
+     * 
+     * @return the start index
+     */
+    public int getStart() {
+        return start;
+    }
+
+    /**
+     * Sets the start index.
+     * 
+     * @param start
+     *            the start index
+     */
+    public void setStart(int start) {
+        this.start = start;
+    }
+
+    /**
+     * Returns the backing buffer.
+     * 
+     * @return the backing buffer
+     */
+    public @NoLength char[] getBuffer() {
+        return buffer;
+    }
+
+    /**
+     * Returns the end index.
+     * 
+     * @return the end index
+     */
+    public int getEnd() {
+        return end;
+    }
+
+    /**
+     * Checks if the buffer has data left.
+     * 
+     * @return <code>true</code> if there's data left
+     */
+    public boolean hasMore() {
+        return start < end;
+    }
+
+    /**
+     * Returns <code>end - start</code>.
+     *
+     * @return <code>end - start</code>
+     */
+    public int getLength() {
+        return end - start;
+    }
+
+    /**
+     * Adjusts the start index to skip over the first character if it is a line
+     * feed and the previous character was a carriage return.
+     * 
+     * @param lastWasCR
+     *            whether the previous character was a carriage return
+     */
+    public void adjust(boolean lastWasCR) {
+        if (lastWasCR && buffer[start] == '\n') {
+            start++;
+        }
+    }
+
+    /**
+     * Sets the end index.
+     * 
+     * @param end
+     *            the end index
+     */
+    public void setEnd(int end) {
+        this.end = end;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/package.html b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/package.html
new file mode 100644
index 000000000..6d029a13e
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/impl/package.html
@@ -0,0 +1,30 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
+<html>
+<head><title>Package Overview</title>
+<!--
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a 
+ copy of this software and associated documentation files (the "Software"), 
+ to deal in the Software without restriction, including without limitation 
+ the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ and/or sell copies of the Software, and to permit persons to whom the 
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in 
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ DEALINGS IN THE SOFTWARE.
+-->
+</head>
+<body bgcolor="white">
+<p>This package contains the bulk of parser internals. Only implementors of 
+additional tree builders or token handlers should look here.</p>
+</body>
+</html>
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/BomSniffer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/BomSniffer.java
new file mode 100644
index 000000000..42d7a837f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/BomSniffer.java
@@ -0,0 +1,79 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.io;
+
+import java.io.IOException;
+
+import nu.validator.htmlparser.common.ByteReadable;
+
+/**
+ * The BOM sniffing part of the HTML5 encoding sniffing algorithm.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class BomSniffer {
+    
+    private final ByteReadable source;
+
+    /**
+     * @param source
+     */
+    public BomSniffer(final ByteReadable source) {
+        this.source = source;
+    }
+    
+    Encoding sniff() throws IOException {
+        int b = source.readByte();
+        if (b == 0xEF) { // UTF-8
+            b = source.readByte();
+            if (b == 0xBB) {
+                b = source.readByte();
+                if (b == 0xBF) {
+                    return Encoding.UTF8;
+                } else {
+                    return null;
+                }
+            } else {
+                return null;
+            }
+        } else if (b == 0xFF) { // little-endian
+            b = source.readByte();
+            if (b == 0xFE) {
+                return Encoding.UTF16LE;
+            } else {
+                return null;
+            }
+        } else if (b == 0xFE) { // big-endian UTF-16
+            b = source.readByte();
+            if (b == 0xFF) {
+                return Encoding.UTF16BE;
+            } else {
+                return null;
+            }
+        } else {
+            return null;            
+        }
+    }
+    
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Confidence.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Confidence.java
new file mode 100644
index 000000000..1a2d49746
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Confidence.java
@@ -0,0 +1,27 @@
+/*
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.io;
+
+public enum Confidence {
+    TENTATIVE, CERTAIN
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Driver.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Driver.java
new file mode 100644
index 000000000..f0b0cc55d
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Driver.java
@@ -0,0 +1,597 @@
+/*
+ * Copyright (c) 2005, 2006, 2007 Henri Sivonen
+ * Copyright (c) 2007-2013 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.io;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.Reader;
+import java.nio.charset.UnsupportedCharsetException;
+
+import nu.validator.htmlparser.common.CharacterHandler;
+import nu.validator.htmlparser.common.EncodingDeclarationHandler;
+import nu.validator.htmlparser.common.Heuristics;
+import nu.validator.htmlparser.common.TransitionHandler;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+import nu.validator.htmlparser.extra.NormalizationChecker;
+import nu.validator.htmlparser.impl.ErrorReportingTokenizer;
+import nu.validator.htmlparser.impl.Tokenizer;
+import nu.validator.htmlparser.impl.UTF16Buffer;
+import nu.validator.htmlparser.rewindable.RewindableInputStream;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.InputSource;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+public class Driver implements EncodingDeclarationHandler {
+
+    /**
+     * The input UTF-16 code unit stream. If a byte stream was given, this
+     * object is an instance of <code>HtmlInputStreamReader</code>.
+     */
+    private Reader reader;
+
+    /**
+     * The reference to the rewindable byte stream. <code>null</code> if 
+     * prohibited or no longer needed.
+     */
+    private RewindableInputStream rewindableInputStream;
+
+    private boolean swallowBom;
+
+    private Encoding characterEncoding;
+
+    private boolean allowRewinding = true;
+
+    private Heuristics heuristics = Heuristics.NONE;
+    
+    private final Tokenizer tokenizer;
+    
+    private Confidence confidence;
+
+    /**
+     * Used for NFC checking if non-<code>null</code>, source code capture,
+     * etc.
+     */
+    private CharacterHandler[] characterHandlers = new CharacterHandler[0];
+
+    public Driver(Tokenizer tokenizer) {
+        this.tokenizer = tokenizer;
+        tokenizer.setEncodingDeclarationHandler(this);
+    }
+    
+    /**
+     * Returns the allowRewinding.
+     * 
+     * @return the allowRewinding
+     */
+    public boolean isAllowRewinding() {
+        return allowRewinding;
+    }
+
+    /**
+     * Sets the allowRewinding.
+     * 
+     * @param allowRewinding
+     *            the allowRewinding to set
+     */
+    public void setAllowRewinding(boolean allowRewinding) {
+        this.allowRewinding = allowRewinding;
+    }
+
+    /**
+     * Turns NFC checking on or off.
+     * 
+     * @param enable
+     *            <code>true</code> if checking on
+     */
+    public void setCheckingNormalization(boolean enable) {
+        if (enable) {
+            if (isCheckingNormalization()) {
+                return;
+            } else {
+                NormalizationChecker normalizationChecker = new NormalizationChecker(tokenizer);
+                normalizationChecker.setErrorHandler(tokenizer.getErrorHandler());
+
+            }
+        } else {
+            if (isCheckingNormalization()) {
+                CharacterHandler[] newHandlers = new CharacterHandler[characterHandlers.length - 1];
+                boolean skipped = false;
+                int j = 0;
+                for (int i = 0; i < characterHandlers.length; i++) {
+                    CharacterHandler ch = characterHandlers[i];
+                    if (!(!skipped && (ch instanceof NormalizationChecker))) {
+                        newHandlers[j] = ch;
+                        j++;
+                    }
+                }
+                characterHandlers = newHandlers;
+            } else {
+                return;
+            }
+        }
+    }
+
+    public void addCharacterHandler(CharacterHandler characterHandler) {
+        if (characterHandler == null) {
+            throw new IllegalArgumentException("Null argument.");
+        }
+        CharacterHandler[] newHandlers = new CharacterHandler[characterHandlers.length + 1];
+        System.arraycopy(characterHandlers, 0, newHandlers, 0,
+                characterHandlers.length);
+        newHandlers[characterHandlers.length] = characterHandler;
+        characterHandlers = newHandlers;
+    }
+
+    /**
+     * Query if checking normalization.
+     * 
+     * @return <code>true</code> if checking on
+     */
+    public boolean isCheckingNormalization() {
+        for (int i = 0; i < characterHandlers.length; i++) {
+            CharacterHandler ch = characterHandlers[i];
+            if (ch instanceof NormalizationChecker) {
+                return true;
+            }
+        }
+        return false;
+    }
+
+    /**
+     * Runs the tokenization. This is the main entry point.
+     * 
+     * @param is
+     *            the input source
+     * @throws SAXException
+     *             on fatal error (if configured to treat XML violations as
+     *             fatal) or if the token handler threw
+     * @throws IOException
+     *             if the stream threw
+     */
+    public void tokenize(InputSource is) throws SAXException, IOException {
+        if (is == null) {
+            throw new IllegalArgumentException("InputSource was null.");
+        }
+        tokenizer.start();
+        confidence = Confidence.TENTATIVE;
+        swallowBom = true;
+        rewindableInputStream = null;
+        tokenizer.initLocation(is.getPublicId(), is.getSystemId());
+        this.reader = is.getCharacterStream();
+        this.characterEncoding = encodingFromExternalDeclaration(is.getEncoding());
+        if (this.reader == null) {
+            InputStream inputStream = is.getByteStream();
+            if (inputStream == null) {
+                throw new SAXException("Both streams in InputSource were null.");
+            }
+            if (this.characterEncoding == null) {
+                if (allowRewinding) {
+                    inputStream = rewindableInputStream = new RewindableInputStream(
+                            inputStream);
+                }
+                this.reader = new HtmlInputStreamReader(inputStream,
+                        tokenizer.getErrorHandler(), tokenizer, this, heuristics);
+            } else {
+                if (this.characterEncoding != Encoding.UTF8) {
+                    warnWithoutLocation("Legacy encoding \u201C"
+                            + this.characterEncoding.getCanonName()
+                            + "\u201D used. Documents should use UTF-8.");
+                }
+                becomeConfident();
+                this.reader = new HtmlInputStreamReader(inputStream,
+                        tokenizer.getErrorHandler(), tokenizer, this, this.characterEncoding);
+            }
+        } else {
+            becomeConfident();
+        }
+        Throwable t = null;
+        try {
+            for (;;) {
+                try {
+                    for (int i = 0; i < characterHandlers.length; i++) {
+                        CharacterHandler ch = characterHandlers[i];
+                        ch.start();
+                    }
+                    runStates();
+                    break;
+                } catch (ReparseException e) {
+                    if (rewindableInputStream == null) {
+                        tokenizer.fatal("Changing encoding at this point would need non-streamable behavior.");
+                    } else {
+                        rewindableInputStream.rewind();
+                        becomeConfident();
+                        this.reader = new HtmlInputStreamReader(
+                                rewindableInputStream, tokenizer.getErrorHandler(), tokenizer,
+                                this, this.characterEncoding);
+                    }
+                    continue;
+                }
+            }
+        } catch (Throwable tr) {
+            t = tr;
+        } finally {
+            try {
+                tokenizer.end();
+                characterEncoding = null;
+                for (int i = 0; i < characterHandlers.length; i++) {
+                    CharacterHandler ch = characterHandlers[i];
+                    ch.end();
+                }
+                reader.close();
+                reader = null;
+                rewindableInputStream = null;
+            } catch (Throwable tr) {
+                if (t == null) {
+                    t = tr;
+                } // else drop the later throwable
+            }
+            if (t != null) {
+                if (t instanceof IOException) {
+                    throw (IOException) t;
+                } else if (t instanceof SAXException) {
+                    throw (SAXException) t;
+                } else if (t instanceof RuntimeException) {
+                    throw (RuntimeException) t;
+                } else if (t instanceof Error) {
+                    throw (Error) t;
+                } else {
+                    // impossible
+                    throw new RuntimeException(t);
+                }
+            }
+        }
+    }
+
+    void dontSwallowBom() {
+        swallowBom = false;
+    }
+
+    private void runStates() throws SAXException, IOException {
+        char[] buffer = new char[2048];
+        UTF16Buffer bufr = new UTF16Buffer(buffer, 0, 0);
+        boolean lastWasCR = false;
+        int len = -1;
+        if ((len = reader.read(buffer)) != -1) {
+            assert len > 0;
+            int streamOffset = 0;
+            int offset = 0;
+            int length = len;
+            if (swallowBom) {
+                if (buffer[0] == '\uFEFF') {
+                    streamOffset = -1;
+                    offset = 1;
+                    length--;
+                }
+            }
+            if (length > 0) {
+                for (int i = 0; i < characterHandlers.length; i++) {
+                    CharacterHandler ch = characterHandlers[i];
+                    ch.characters(buffer, offset, length);
+                }
+                tokenizer.setTransitionBaseOffset(streamOffset);
+                bufr.setStart(offset);
+                bufr.setEnd(offset + length);
+                while (bufr.hasMore()) {
+                    bufr.adjust(lastWasCR);
+                    lastWasCR = false;
+                    if (bufr.hasMore()) {
+                        lastWasCR = tokenizer.tokenizeBuffer(bufr);                    
+                    }
+                }
+            }
+            streamOffset = length;
+            while ((len = reader.read(buffer)) != -1) {
+                assert len > 0;
+                for (int i = 0; i < characterHandlers.length; i++) {
+                    CharacterHandler ch = characterHandlers[i];
+                    ch.characters(buffer, 0, len);
+                }
+                tokenizer.setTransitionBaseOffset(streamOffset);
+                bufr.setStart(0);
+                bufr.setEnd(len);
+                while (bufr.hasMore()) {
+                    bufr.adjust(lastWasCR);
+                    lastWasCR = false;
+                    if (bufr.hasMore()) {
+                        lastWasCR = tokenizer.tokenizeBuffer(bufr);                    
+                    }
+                }
+                streamOffset += len;
+            }
+        }
+        tokenizer.eof();
+    }
+
+    public void setEncoding(Encoding encoding, Confidence confidence) {
+        this.characterEncoding = encoding;
+        if (confidence == Confidence.CERTAIN) {
+            becomeConfident();
+        }
+    }
+
+    public boolean internalEncodingDeclaration(String internalCharset)
+            throws SAXException {
+        try {
+            internalCharset = Encoding.toAsciiLowerCase(internalCharset);
+            Encoding cs;
+            if ("utf-16".equals(internalCharset)
+                    || "utf-16be".equals(internalCharset)
+                    || "utf-16le".equals(internalCharset)) {
+                tokenizer.errTreeBuilder("Internal encoding declaration specified \u201C"
+                        + internalCharset
+                        + "\u201D which is not an ASCII superset. Continuing as if the encoding had been \u201Cutf-8\u201D.");
+                cs = Encoding.UTF8;
+                internalCharset = "utf-8";
+            } else {
+                cs = Encoding.forName(internalCharset);
+            }
+            Encoding actual = cs.getActualHtmlEncoding();
+            if (actual == null) {
+                actual = cs;
+            }
+            if (!actual.isAsciiSuperset()) {
+                tokenizer.errTreeBuilder("Internal encoding declaration specified \u201C"
+                        + internalCharset
+                        + "\u201D which is not an ASCII superset. Not changing the encoding.");
+                return false;
+            }
+            if (characterEncoding == null) {
+                // Reader case
+                return true;
+            }
+            if (characterEncoding == actual) {
+                becomeConfident();
+                return true;
+            }
+            if (confidence == Confidence.CERTAIN && actual != characterEncoding) {
+                tokenizer.errTreeBuilder("Internal encoding declaration \u201C"
+                        + internalCharset
+                        + "\u201D disagrees with the actual encoding of the document (\u201C"
+                        + characterEncoding.getCanonName() + "\u201D).");
+            } else {
+                Encoding newEnc = whineAboutEncodingAndReturnActual(
+                        internalCharset, cs);
+                tokenizer.errTreeBuilder("Changing character encoding \u201C"
+                        + internalCharset + "\u201D and reparsing.");
+                characterEncoding = newEnc;
+                throw new ReparseException();
+            }
+            return true;
+        } catch (UnsupportedCharsetException e) {
+            tokenizer.errTreeBuilder("Internal encoding declaration named an unsupported chararacter encoding \u201C"
+                    + internalCharset + "\u201D.");
+            return false;
+        }
+    }
+
+    /**
+     * 
+     */
+    private void becomeConfident() {
+        if (rewindableInputStream != null) {
+            rewindableInputStream.willNotRewind();
+        }
+        confidence = Confidence.CERTAIN;
+        tokenizer.becomeConfident();
+    }
+
+    /**
+     * Sets the encoding sniffing heuristics.
+     * 
+     * @param heuristics
+     *            the heuristics to set
+     */
+    public void setHeuristics(Heuristics heuristics) {
+        this.heuristics = heuristics;
+    }
+
+    /**
+     * Reports a warning without line/col
+     * 
+     * @param message
+     *            the message
+     * @throws SAXException
+     */
+    protected void warnWithoutLocation(String message) throws SAXException {
+        ErrorHandler errorHandler = tokenizer.getErrorHandler();
+        if (errorHandler == null) {
+            return;
+        }
+        SAXParseException spe = new SAXParseException(message, null,
+                tokenizer.getSystemId(), -1, -1);
+        errorHandler.warning(spe);
+    }
+
+    /**
+     * Initializes a decoder from external decl.
+     */
+    protected Encoding encodingFromExternalDeclaration(String encoding)
+            throws SAXException {
+        if (encoding == null) {
+            return null;
+        }
+        encoding = Encoding.toAsciiLowerCase(encoding);
+        try {
+            Encoding cs = Encoding.forName(encoding);
+            if ("utf-16".equals(cs.getCanonName())
+                    || "utf-32".equals(cs.getCanonName())) {
+                swallowBom = false;
+            }
+            return whineAboutEncodingAndReturnActual(encoding, cs);
+        } catch (UnsupportedCharsetException e) {
+            tokenizer.err("Unsupported character encoding name: \u201C" + encoding
+                    + "\u201D. Will sniff.");
+            swallowBom = true;
+        }
+        return null; // keep the compiler happy
+    }
+
+    /**
+     * @param encoding
+     * @param cs
+     * @return
+     * @throws SAXException
+     */
+    protected Encoding whineAboutEncodingAndReturnActual(String encoding,
+            Encoding cs) throws SAXException {
+        String canonName = cs.getCanonName();
+        if (!cs.isRegistered()) {
+            if (encoding.startsWith("x-")) {
+                tokenizer.err("The encoding \u201C"
+                        + encoding
+                        + "\u201D is not an IANA-registered encoding. (Charmod C022)");
+            } else {
+                tokenizer.err("The encoding \u201C"
+                        + encoding
+                        + "\u201D is not an IANA-registered encoding and did not use the \u201Cx-\u201D prefix. (Charmod C023)");
+            }
+        } else if (!canonName.equals(encoding)) {
+            tokenizer.err("The encoding \u201C"
+                    + encoding
+                    + "\u201D is not the preferred name of the character encoding in use. The preferred name is \u201C"
+                    + canonName + "\u201D. (Charmod C024)");
+        }
+        if (cs.isShouldNot()) {
+            tokenizer.warn("Authors should not use the character encoding \u201C"
+                    + encoding
+                    + "\u201D. It is recommended to use \u201CUTF-8\u201D.");
+        } else if (cs.isLikelyEbcdic()) {
+            tokenizer.warn("Authors should not use EBCDIC-based encodings. It is recommended to use \u201CUTF-8\u201D.");
+        } else if (cs.isObscure()) {
+            tokenizer.warn("The character encoding \u201C"
+                    + encoding
+                    + "\u201D is not widely supported. Better interoperability may be achieved by using \u201CUTF-8\u201D.");
+        }
+        Encoding actual = cs.getActualHtmlEncoding();
+        if (actual == null) {
+            return cs;
+        } else {
+            tokenizer.warn("Using \u201C" + actual.getCanonName()
+                    + "\u201D instead of the declared encoding \u201C"
+                    + encoding + "\u201D.");
+            return actual;
+        }
+    }
+
+    private class ReparseException extends SAXException {
+
+    }
+
+    void notifyAboutMetaBoundary() {
+        tokenizer.notifyAboutMetaBoundary();
+    }
+
+    /**
+     * @param commentPolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setCommentPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setCommentPolicy(XmlViolationPolicy commentPolicy) {
+        tokenizer.setCommentPolicy(commentPolicy);
+    }
+
+    /**
+     * @param contentNonXmlCharPolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentNonXmlCharPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentNonXmlCharPolicy(
+            XmlViolationPolicy contentNonXmlCharPolicy) {
+        tokenizer.setContentNonXmlCharPolicy(contentNonXmlCharPolicy);
+    }
+
+    /**
+     * @param contentSpacePolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentSpacePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentSpacePolicy(XmlViolationPolicy contentSpacePolicy) {
+        tokenizer.setContentSpacePolicy(contentSpacePolicy);
+    }
+
+    /**
+     * @param eh
+     * @see nu.validator.htmlparser.impl.Tokenizer#setErrorHandler(org.xml.sax.ErrorHandler)
+     */
+    public void setErrorHandler(ErrorHandler eh) {
+        tokenizer.setErrorHandler(eh);
+        for (int i = 0; i < characterHandlers.length; i++) {
+            CharacterHandler ch = characterHandlers[i];
+            if (ch instanceof NormalizationChecker) {
+                NormalizationChecker nc = (NormalizationChecker) ch;
+                nc.setErrorHandler(eh);
+            }
+        }
+    }
+    
+    public void setTransitionHandler(TransitionHandler transitionHandler) {
+        if (tokenizer instanceof ErrorReportingTokenizer) {
+            ErrorReportingTokenizer ert = (ErrorReportingTokenizer) tokenizer;
+            ert.setTransitionHandler(transitionHandler);
+        } else if (transitionHandler != null) {
+            throw new IllegalStateException("Attempt to set a transition handler on a plain tokenizer.");
+        }
+    }
+
+    /**
+     * @param html4ModeCompatibleWithXhtml1Schemata
+     * @see nu.validator.htmlparser.impl.Tokenizer#setHtml4ModeCompatibleWithXhtml1Schemata(boolean)
+     */
+    public void setHtml4ModeCompatibleWithXhtml1Schemata(
+            boolean html4ModeCompatibleWithXhtml1Schemata) {
+        tokenizer.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata);
+    }
+
+    /**
+     * @param mappingLangToXmlLang
+     * @see nu.validator.htmlparser.impl.Tokenizer#setMappingLangToXmlLang(boolean)
+     */
+    public void setMappingLangToXmlLang(boolean mappingLangToXmlLang) {
+        tokenizer.setMappingLangToXmlLang(mappingLangToXmlLang);
+    }
+
+    /**
+     * @param namePolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setNamePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setNamePolicy(XmlViolationPolicy namePolicy) {
+        tokenizer.setNamePolicy(namePolicy);
+    }
+
+    /**
+     * @param xmlnsPolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setXmlnsPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setXmlnsPolicy(XmlViolationPolicy xmlnsPolicy) {
+        tokenizer.setXmlnsPolicy(xmlnsPolicy);
+    }
+
+    public String getCharacterEncoding() throws SAXException {
+        return characterEncoding.getCanonName();
+    }
+
+    public Locator getDocumentLocator() {
+        return tokenizer;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Encoding.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Encoding.java
new file mode 100644
index 000000000..3bbc606fa
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/Encoding.java
@@ -0,0 +1,395 @@
+/*
+ * Copyright (c) 2006 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.io;
+
+import java.io.ByteArrayInputStream;
+import java.io.IOException;
+import java.io.InputStreamReader;
+import java.io.Reader;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CharsetEncoder;
+import java.nio.charset.CoderMalfunctionError;
+import java.nio.charset.CodingErrorAction;
+import java.nio.charset.UnsupportedCharsetException;
+import java.util.Arrays;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.Map;
+import java.util.Set;
+import java.util.SortedMap;
+
+public class Encoding {
+
+    public static final Encoding UTF8;
+
+    public static final Encoding UTF16;
+
+    public static final Encoding UTF16LE;
+
+    public static final Encoding UTF16BE;
+
+    public static final Encoding WINDOWS1252;
+
+    private static String[] SHOULD_NOT = { "jisx02121990", "xjis0208" };
+
+    private static String[] BANNED = { "bocu1", "cesu8", "compoundtext",
+            "iscii91", "macarabic", "maccentraleurroman", "maccroatian",
+            "maccyrillic", "macdevanagari", "macfarsi", "macgreek",
+            "macgujarati", "macgurmukhi", "machebrew", "macicelandic",
+            "macroman", "macromanian", "macthai", "macturkish", "macukranian",
+            "scsu", "utf32", "utf32be", "utf32le", "utf7", "ximapmailboxname",
+            "xjisautodetect", "xutf16bebom", "xutf16lebom", "xutf32bebom",
+            "xutf32lebom", "xutf16oppositeendian", "xutf16platformendian",
+            "xutf32oppositeendian", "xutf32platformendian" };
+
+    private static String[] NOT_OBSCURE = { "big5", "big5hkscs", "eucjp",
+            "euckr", "gb18030", "gbk", "iso2022jp", "iso2022kr", "iso88591",
+            "iso885913", "iso885915", "iso88592", "iso88593", "iso88594",
+            "iso88595", "iso88596", "iso88597", "iso88598", "iso88599",
+            "koi8r", "shiftjis", "tis620", "usascii", "utf16", "utf16be",
+            "utf16le", "utf8", "windows1250", "windows1251", "windows1252",
+            "windows1253", "windows1254", "windows1255", "windows1256",
+            "windows1257", "windows1258" };
+
+    private static Map<String, Encoding> encodingByCookedName = new HashMap<String, Encoding>();
+
+    private final String canonName;
+
+    private final Charset charset;
+
+    private final boolean asciiSuperset;
+
+    private final boolean obscure;
+
+    private final boolean shouldNot;
+
+    private final boolean likelyEbcdic;
+
+    private Encoding actualHtmlEncoding = null;
+
+    static {
+        byte[] testBuf = new byte[0x7F];
+        for (int i = 0; i < 0x7F; i++) {
+            if (isAsciiSupersetnessSensitive(i)) {
+                testBuf[i] = (byte) i;
+            } else {
+                testBuf[i] = (byte) 0x20;
+            }
+        }
+
+        Set<Encoding> encodings = new HashSet<Encoding>();
+
+        SortedMap<String, Charset> charsets = Charset.availableCharsets();
+        for (Map.Entry<String, Charset> entry : charsets.entrySet()) {
+            Charset cs = entry.getValue();
+            String name = toNameKey(cs.name());
+            String canonName = toAsciiLowerCase(cs.name());
+            if (!isBanned(name)) {
+                name = name.intern();
+                boolean asciiSuperset = asciiMapsToBasicLatin(testBuf, cs);
+                Encoding enc = new Encoding(canonName.intern(), cs,
+                        asciiSuperset, isObscure(name), isShouldNot(name),
+                        isLikelyEbcdic(name, asciiSuperset));
+                encodings.add(enc);
+                Set<String> aliases = cs.aliases();
+                for (String alias : aliases) {
+                    encodingByCookedName.put(toNameKey(alias).intern(), enc);
+                }
+            }
+        }
+        // Overwrite possible overlapping aliases with the real things--just in
+        // case
+        for (Encoding encoding : encodings) {
+            encodingByCookedName.put(toNameKey(encoding.getCanonName()),
+                    encoding);
+        }
+        UTF8 = forName("utf-8");
+        UTF16 = forName("utf-16");
+        UTF16BE = forName("utf-16be");
+        UTF16LE = forName("utf-16le");
+        WINDOWS1252 = forName("windows-1252");
+        try {
+            forName("iso-8859-1").actualHtmlEncoding = forName("windows-1252");
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            forName("iso-8859-9").actualHtmlEncoding = forName("windows-1254");
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            forName("iso-8859-11").actualHtmlEncoding = forName("windows-874");
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            forName("x-iso-8859-11").actualHtmlEncoding = forName("windows-874");
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            forName("tis-620").actualHtmlEncoding = forName("windows-874");
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            forName("gb_2312-80").actualHtmlEncoding = forName("gbk");
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            forName("gb2312").actualHtmlEncoding = forName("gbk");
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            encodingByCookedName.put("x-x-big5", forName("big5"));
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            encodingByCookedName.put("euc-kr", forName("windows-949"));
+        } catch (UnsupportedCharsetException e) {
+        }
+        try {
+            encodingByCookedName.put("ks_c_5601-1987", forName("windows-949"));
+        } catch (UnsupportedCharsetException e) {
+        }
+    }
+
+    private static boolean isAsciiSupersetnessSensitive(int c) {
+        return (c >= 0x09 && c <= 0x0D) || (c >= 0x20 && c <= 0x22)
+                || (c >= 0x26 && c <= 0x27) || (c >= 0x2C && c <= 0x3F)
+                || (c >= 0x41 && c <= 0x5A) || (c >= 0x61 && c <= 0x7A);
+    }
+
+    private static boolean isObscure(String lowerCasePreferredIanaName) {
+        return !(Arrays.binarySearch(NOT_OBSCURE, lowerCasePreferredIanaName) > -1);
+    }
+
+    private static boolean isBanned(String lowerCasePreferredIanaName) {
+        if (lowerCasePreferredIanaName.startsWith("xibm")) {
+            return true;
+        }
+        return (Arrays.binarySearch(BANNED, lowerCasePreferredIanaName) > -1);
+    }
+
+    private static boolean isShouldNot(String lowerCasePreferredIanaName) {
+        return (Arrays.binarySearch(SHOULD_NOT, lowerCasePreferredIanaName) > -1);
+    }
+
+    /**
+     * @param testBuf
+     * @param cs
+     */
+    private static boolean asciiMapsToBasicLatin(byte[] testBuf, Charset cs) {
+        CharsetDecoder dec = cs.newDecoder();
+        dec.onMalformedInput(CodingErrorAction.REPORT);
+        dec.onUnmappableCharacter(CodingErrorAction.REPORT);
+        Reader r = new InputStreamReader(new ByteArrayInputStream(testBuf), dec);
+        try {
+            for (int i = 0; i < 0x7F; i++) {
+                if (isAsciiSupersetnessSensitive(i)) {
+                    if (r.read() != i) {
+                        return false;
+                    }
+                } else {
+                    if (r.read() != 0x20) {
+                        return false;
+                    }
+                }
+            }
+        } catch (IOException e) {
+            return false;
+        } catch (Exception e) {
+            return false;
+        } catch (CoderMalfunctionError e) {
+            return false;
+        }
+
+        return true;
+    }
+
+    private static boolean isLikelyEbcdic(String canonName,
+            boolean asciiSuperset) {
+        if (!asciiSuperset) {
+            return (canonName.startsWith("cp") || canonName.startsWith("ibm") || canonName.startsWith("xibm"));
+        } else {
+            return false;
+        }
+    }
+
+    public static Encoding forName(String name) {
+        Encoding rv = encodingByCookedName.get(toNameKey(name));
+        if (rv == null) {
+            throw new UnsupportedCharsetException(name);
+        } else {
+            return rv;
+        }
+    }
+
+    public static String toNameKey(String str) {
+        if (str == null) {
+            return null;
+        }
+        int j = 0;
+        char[] buf = new char[str.length()];
+        for (int i = 0; i < str.length(); i++) {
+            char c = str.charAt(i);
+            if (c >= 'A' && c <= 'Z') {
+                c += 0x20;
+            }
+            if (!((c >= '\t' && c <= '\r') || (c >= '\u0020' && c <= '\u002F')
+                    || (c >= '\u003A' && c <= '\u0040')
+                    || (c >= '\u005B' && c <= '\u0060') || (c >= '\u007B' && c <= '\u007E'))) {
+                buf[j] = c;
+                j++;
+            }
+        }
+        return new String(buf, 0, j);
+    }
+
+    public static String toAsciiLowerCase(String str) {
+        if (str == null) {
+            return null;
+        }
+        char[] buf = new char[str.length()];
+        for (int i = 0; i < str.length(); i++) {
+            char c = str.charAt(i);
+            if (c >= 'A' && c <= 'Z') {
+                c += 0x20;
+            }
+            buf[i] = c;
+        }
+        return new String(buf);
+    }
+
+    /**
+     * @param canonName
+     * @param charset
+     * @param asciiSuperset
+     * @param obscure
+     * @param shouldNot
+     * @param likelyEbcdic
+     */
+    private Encoding(final String canonName, final Charset charset,
+            final boolean asciiSuperset, final boolean obscure,
+            final boolean shouldNot, final boolean likelyEbcdic) {
+        this.canonName = canonName;
+        this.charset = charset;
+        this.asciiSuperset = asciiSuperset;
+        this.obscure = obscure;
+        this.shouldNot = shouldNot;
+        this.likelyEbcdic = likelyEbcdic;
+    }
+
+    /**
+     * Returns the asciiSuperset.
+     * 
+     * @return the asciiSuperset
+     */
+    public boolean isAsciiSuperset() {
+        return asciiSuperset;
+    }
+
+    /**
+     * Returns the canonName.
+     * 
+     * @return the canonName
+     */
+    public String getCanonName() {
+        return canonName;
+    }
+
+    /**
+     * Returns the likelyEbcdic.
+     * 
+     * @return the likelyEbcdic
+     */
+    public boolean isLikelyEbcdic() {
+        return likelyEbcdic;
+    }
+
+    /**
+     * Returns the obscure.
+     * 
+     * @return the obscure
+     */
+    public boolean isObscure() {
+        return obscure;
+    }
+
+    /**
+     * Returns the shouldNot.
+     * 
+     * @return the shouldNot
+     */
+    public boolean isShouldNot() {
+        return shouldNot;
+    }
+
+    public boolean isRegistered() {
+        return !canonName.startsWith("x-");
+    }
+
+    /**
+     * @return
+     * @see java.nio.charset.Charset#canEncode()
+     */
+    public boolean canEncode() {
+        return charset.canEncode();
+    }
+
+    /**
+     * @return
+     * @see java.nio.charset.Charset#newDecoder()
+     */
+    public CharsetDecoder newDecoder() {
+        return charset.newDecoder();
+    }
+
+    /**
+     * @return
+     * @see java.nio.charset.Charset#newEncoder()
+     */
+    public CharsetEncoder newEncoder() {
+        return charset.newEncoder();
+    }
+
+    /**
+     * Returns the actualHtmlEncoding.
+     * 
+     * @return the actualHtmlEncoding
+     */
+    public Encoding getActualHtmlEncoding() {
+        return actualHtmlEncoding;
+    }
+
+    public static void main(String[] args) {
+        for (Map.Entry<String, Encoding> entry : encodingByCookedName.entrySet()) {
+            String name = entry.getKey();
+            Encoding enc = entry.getValue();
+            System.out.printf(
+                    "%21s: canon %21s, obs %5s, reg %5s, asc %5s, ebc %5s\n",
+                    name, enc.getCanonName(), enc.isObscure(),
+                    enc.isRegistered(), enc.isAsciiSuperset(),
+                    enc.isLikelyEbcdic());
+        }
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/HtmlInputStreamReader.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/HtmlInputStreamReader.java
new file mode 100644
index 000000000..413f0d9e9
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/HtmlInputStreamReader.java
@@ -0,0 +1,512 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2013 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.io;
+
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.Reader;
+import java.nio.ByteBuffer;
+import java.nio.CharBuffer;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CoderResult;
+import java.nio.charset.CodingErrorAction;
+
+import nu.validator.htmlparser.common.ByteReadable;
+import nu.validator.htmlparser.common.Heuristics;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+import nu.validator.htmlparser.extra.ChardetSniffer;
+import nu.validator.htmlparser.extra.IcuDetectorSniffer;
+import nu.validator.htmlparser.impl.Tokenizer;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+/**
+ * Be very careful with this class. It is not a general-purpose subclass of of
+ * <code>Reader</code>. Instead, it is the minimal implementation that does
+ * what <code>Tokenizer</code> needs while being an instance of
+ * <code>Reader</code>.
+ * 
+ * The only reason why this is a public class is that it needs to be visible to
+ * test code in another package.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class HtmlInputStreamReader extends Reader implements
+        ByteReadable, Locator {
+
+    private static final int SNIFFING_LIMIT = 1024;
+
+    private final InputStream inputStream;
+
+    private final ErrorHandler errorHandler;
+
+    private final Tokenizer tokenizer;
+
+    private final Driver driver;
+
+    private CharsetDecoder decoder = null;
+
+    private boolean sniffing = true;
+
+    private int limit = 0;
+
+    private int position = 0;
+
+    private int bytesRead = 0;
+
+    private boolean eofSeen = false;
+
+    private boolean shouldReadBytes = false;
+
+    private boolean charsetBoundaryPassed = false;
+
+    private final byte[] byteArray = new byte[4096]; // Length must be >=
+
+    // SNIFFING_LIMIT
+
+    private final ByteBuffer byteBuffer = ByteBuffer.wrap(byteArray);
+
+    private boolean needToNotifyTokenizer = false;
+
+    private boolean flushing = false;
+
+    private int line = -1;
+
+    private int col = -1;
+
+    private int lineColPos;
+
+    private boolean hasPendingReplacementCharacter = false;
+
+    private boolean nextCharOnNewLine;
+
+    private boolean prevWasCR;
+
+    /**
+     * @param inputStream
+     * @param errorHandler
+     * @param locator
+     * @throws IOException
+     * @throws SAXException
+     */
+    public HtmlInputStreamReader(InputStream inputStream,
+            ErrorHandler errorHandler, Tokenizer tokenizer, Driver driver,
+            Heuristics heuristics) throws SAXException, IOException {
+        this.inputStream = inputStream;
+        this.errorHandler = errorHandler;
+        this.tokenizer = tokenizer;
+        this.driver = driver;
+        this.sniffing = true;
+        Encoding encoding = (new BomSniffer(this)).sniff();
+        if (encoding == null) {
+            position = 0;
+            encoding = (new MetaSniffer(errorHandler, this)).sniff(this);
+            boolean declared = true;
+            if (encoding == null) {
+                declared = false;
+            } else if (encoding != Encoding.UTF8) {
+                warn("Legacy encoding \u201C"
+                        + encoding.getCanonName()
+                        + "\u201D used. Documents should use UTF-8.");
+            }
+            if (encoding == null
+                    && (heuristics == Heuristics.CHARDET || heuristics == Heuristics.ALL)) {
+                encoding = (new ChardetSniffer(byteArray, limit)).sniff();
+            }
+            if (encoding == null
+                    && (heuristics == Heuristics.ICU || heuristics == Heuristics.ALL)) {
+                position = 0;
+                encoding = (new IcuDetectorSniffer(this)).sniff();
+            }
+            sniffing = false;
+            if (encoding == null) {
+                encoding = Encoding.WINDOWS1252;
+            }
+            if (!declared) {
+                err("The character encoding was not declared. Proceeding using \u201C" + encoding.getCanonName() + "\u201D.");
+            }
+            if (driver != null) {
+                driver.setEncoding(encoding, Confidence.TENTATIVE);
+            }
+        } else {
+            if (encoding == Encoding.UTF8) {
+                if (driver != null) {
+                    driver.setEncoding(Encoding.UTF8, Confidence.CERTAIN);
+                }
+            } else {
+                warn("Legacy encoding \u201C"
+                        + encoding.getCanonName()
+                        + "\u201D used. Documents should use UTF-8.");
+                if (driver != null) {
+                    driver.setEncoding(Encoding.UTF16, Confidence.CERTAIN);
+                }
+            }
+        }
+        this.decoder = encoding.newDecoder();
+        sniffing = false;
+        position = 0;
+        bytesRead = 0;
+        byteBuffer.position(position);
+        byteBuffer.limit(limit);
+        initDecoder();
+    }
+
+    /**
+     * 
+     */
+    private void initDecoder() {
+        this.decoder.onMalformedInput(CodingErrorAction.REPORT);
+        this.decoder.onUnmappableCharacter(CodingErrorAction.REPORT);
+    }
+
+    public HtmlInputStreamReader(InputStream inputStream,
+            ErrorHandler errorHandler, Tokenizer tokenizer, Driver driver,
+            Encoding encoding) throws SAXException, IOException {
+        this.inputStream = inputStream;
+        this.errorHandler = errorHandler;
+        this.tokenizer = tokenizer;
+        this.driver = driver;
+        this.decoder = encoding.newDecoder();
+        this.sniffing = false;
+        position = 0;
+        bytesRead = 0;
+        byteBuffer.position(0);
+        byteBuffer.limit(0);
+        shouldReadBytes = true;
+        initDecoder();
+    }
+
+    @Override public void close() throws IOException {
+        inputStream.close();
+    }
+
+    @Override public int read(char[] charArray) throws IOException {
+        lineColPos = 0;
+        assert !sniffing;
+        assert charArray.length >= 2;
+        if (needToNotifyTokenizer) {
+            if (driver != null) {
+                driver.notifyAboutMetaBoundary();
+            }
+            needToNotifyTokenizer = false;
+        }
+        CharBuffer charBuffer = CharBuffer.wrap(charArray);
+        charBuffer.limit(charArray.length);
+        charBuffer.position(0);
+        if (flushing) {
+            decoder.flush(charBuffer);
+            // return -1 if zero
+            int cPos = charBuffer.position();
+            return cPos == 0 ? -1 : cPos;
+        }
+        if (hasPendingReplacementCharacter) {
+            charBuffer.put('\uFFFD');
+            hasPendingReplacementCharacter = false;
+        }
+        for (;;) {
+            if (shouldReadBytes) {
+                int oldLimit = byteBuffer.limit();
+                int readLen;
+                if (charsetBoundaryPassed) {
+                    readLen = byteArray.length - oldLimit;
+                } else {
+                    readLen = SNIFFING_LIMIT - oldLimit;
+                }
+                int num = inputStream.read(byteArray, oldLimit, readLen);
+                if (num == -1) {
+                    eofSeen = true;
+                    inputStream.close();
+                } else {
+                    byteBuffer.position(0);
+                    byteBuffer.limit(oldLimit + num);
+                }
+                shouldReadBytes = false;
+            }
+            boolean finalDecode = false;
+            for (;;) {
+                int oldBytePos = byteBuffer.position();
+                CoderResult cr = decoder.decode(byteBuffer, charBuffer,
+                        finalDecode);
+                bytesRead += byteBuffer.position() - oldBytePos;
+                if (cr == CoderResult.OVERFLOW) {
+                    // Decoder will remember surrogates
+                    return charBuffer.position();
+                } else if (cr == CoderResult.UNDERFLOW) {
+                    int remaining = byteBuffer.remaining();
+                    if (!charsetBoundaryPassed) {
+                        if (bytesRead + remaining >= SNIFFING_LIMIT) {
+                            needToNotifyTokenizer = true;
+                            charsetBoundaryPassed = true;
+                        }
+                    }
+
+                    // XXX what happens if the entire byte buffer consists of 
+                    // a pathologically long malformed sequence?
+
+                    // If the buffer was not fully consumed, there may be an
+                    // incomplete byte sequence that needs to seed the next
+                    // buffer.
+                    if (remaining > 0) {
+                        System.arraycopy(byteArray, byteBuffer.position(),
+                                byteArray, 0, remaining);
+                    }
+                    byteBuffer.position(0);
+                    byteBuffer.limit(remaining);
+                    if (flushing) {
+                        // The final decode was successful. Not sure if this
+                        // ever happens.
+                        // Let's get out in any case.
+                        int cPos = charBuffer.position();
+                        return cPos == 0 ? -1 : cPos;
+                    } else if (eofSeen) {
+                        // If there's something left, it isn't something that
+                        // would be
+                        // consumed in the middle of the stream. Rerun the loop
+                        // once
+                        // in the final mode.
+                        shouldReadBytes = false;
+                        finalDecode = true;
+                        flushing = true;
+                        continue;
+                    } else {
+                        // The usual stuff. Want more bytes next time.
+                        shouldReadBytes = true;
+                        int cPos = charBuffer.position();
+                        if (cPos == 0) {
+                            // No output. Read more bytes right away
+                            break;
+                        }
+                        return cPos;
+                    }
+                } else {
+                    // The result is in error. No need to test.
+                    StringBuilder sb = new StringBuilder();
+                    for (int i = 0; i < cr.length(); i++) {
+                        if (i > 0) {
+                            sb.append(", ");
+                        }
+                        sb.append('\u201C');
+                        sb.append(Integer.toHexString(byteBuffer.get() & 0xFF));
+                        bytesRead++;
+                        sb.append('\u201D');
+                    }
+                    if (charBuffer.hasRemaining()) {
+                        charBuffer.put('\uFFFD');                     
+                    } else {
+                        hasPendingReplacementCharacter = true;
+                    }
+                    calculateLineAndCol(charBuffer);
+                    if (cr.isMalformed()) {
+                        err("Malformed byte sequence: " + sb + ".");
+                    } else if (cr.isUnmappable()) {
+                        err("Unmappable byte sequence: " + sb + ".");
+                    } else {
+                        throw new RuntimeException(
+                                "CoderResult was none of overflow, underflow, malformed or unmappable.");
+                    }
+                    if (finalDecode) {
+                        // These were the last bytes of input. Return without
+                        // relooping.
+                        // return -1 if zero
+                        int cPos = charBuffer.position();
+                        return cPos == 0 ? -1 : cPos;
+                    }
+                }
+            }
+        }
+    }
+
+    private void calculateLineAndCol(CharBuffer charBuffer) {
+        if (tokenizer != null) {
+            if (lineColPos == 0) {
+                line = tokenizer.getLine();
+                col = tokenizer.getCol();
+                nextCharOnNewLine = tokenizer.isNextCharOnNewLine();
+                prevWasCR = tokenizer.isPrevCR();
+            }
+            
+            char[] charArray = charBuffer.array();
+            int i = lineColPos;
+            while (i < charBuffer.position()) {
+                char c;
+                if (nextCharOnNewLine) {
+                    line++;
+                    col = 1;
+                    nextCharOnNewLine = false;
+                } else {
+                    col++;
+                }
+
+                c = charArray[i];
+                switch (c) {
+                    case '\r':
+                        nextCharOnNewLine = true;
+                        prevWasCR = true;
+                        break;
+                    case '\n':
+                        if (prevWasCR) {
+                            col--;
+                        } else {
+                            nextCharOnNewLine = true;
+                        }
+                        break;
+                }
+                i++;
+            }
+            lineColPos = i;
+        }
+    }
+
+    public int readByte() throws IOException {
+        if (!sniffing) {
+            throw new IllegalStateException(
+                    "readByte() called when not in the sniffing state.");
+        }
+        if (position == SNIFFING_LIMIT) {
+            return -1;
+        } else if (position < limit) {
+            return byteArray[position++] & 0xFF;
+        } else {
+            int num = inputStream.read(byteArray, limit, SNIFFING_LIMIT - limit);
+            if (num == -1) {
+                return -1;
+            } else {
+                limit += num;
+                return byteArray[position++] & 0xFF;
+            }
+        }
+    }
+
+    public static void main(String[] args) {
+        CharsetDecoder dec = Charset.forName("UTF-8").newDecoder();
+        dec.onMalformedInput(CodingErrorAction.REPORT);
+        dec.onUnmappableCharacter(CodingErrorAction.REPORT);
+        byte[] bytes = { (byte) 0xF0, (byte) 0x9D, (byte) 0x80, (byte) 0x80 };
+        byte[] bytes2 = { (byte) 0xB8, (byte) 0x80, 0x63, 0x64, 0x65 };
+        ByteBuffer byteBuf = ByteBuffer.wrap(bytes);
+        ByteBuffer byteBuf2 = ByteBuffer.wrap(bytes2);
+        char[] chars = new char[1];
+        CharBuffer charBuf = CharBuffer.wrap(chars);
+
+        CoderResult cr = dec.decode(byteBuf, charBuf, false);
+        System.out.println(cr);
+        System.out.println(byteBuf);
+        // byteBuf.get();
+        cr = dec.decode(byteBuf2, charBuf, false);
+        System.out.println(cr);
+        System.out.println(byteBuf2);
+
+    }
+
+    public int getColumnNumber() {
+        if (tokenizer != null) {
+            return col;
+        }
+        return -1;
+    }
+
+    public int getLineNumber() {
+        if (tokenizer != null) {
+            return line;
+        }
+        return -1;
+    }
+
+    public String getPublicId() {
+        if (tokenizer != null) {
+            return tokenizer.getPublicId();
+        }
+        return null;
+    }
+
+    public String getSystemId() {
+        if (tokenizer != null) {
+            return tokenizer.getSystemId();
+        }
+        return null;
+    }
+
+    /**
+     * @param string
+     * @throws SAXException
+     */
+    private void err(String message) throws IOException {
+        // TODO remove wrapping when changing read() to take a CharBuffer
+        try {
+            if (errorHandler != null) {
+                SAXParseException spe = new SAXParseException(message, this);
+                errorHandler.error(spe);
+            }
+        } catch (SAXException e) {
+            throw (IOException) new IOException(e.getMessage()).initCause(e);
+        }
+    }
+
+    private void warn(String message) throws IOException {
+        // TODO remove wrapping when changing read() to take a CharBuffer
+        try {
+            if (errorHandler != null) {
+                SAXParseException spe = new SAXParseException(message, this);
+                errorHandler.warning(spe);
+            }
+        } catch (SAXException e) {
+            throw (IOException) new IOException(e.getMessage()).initCause(e);
+        }
+    }
+
+    public Charset getCharset() {
+        return decoder.charset();
+    }
+
+    /**
+     * @see java.io.Reader#read()
+     */
+    @Override public int read() throws IOException {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * @see java.io.Reader#read(char[], int, int)
+     */
+    @Override public int read(char[] cbuf, int off, int len) throws IOException {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * @see java.io.Reader#read(java.nio.CharBuffer)
+     */
+    @Override public int read(CharBuffer target) throws IOException {
+        throw new UnsupportedOperationException();
+    }
+
+    public void switchEncoding(Encoding newEnc) {
+        this.decoder = newEnc.newDecoder();
+        initDecoder();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/MetaSniffer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/MetaSniffer.java
new file mode 100644
index 000000000..baa04e44f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/io/MetaSniffer.java
@@ -0,0 +1,199 @@
+/*
+ * Copyright (c) 2009 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.io;
+
+import java.io.IOException;
+import java.nio.charset.UnsupportedCharsetException;
+
+import nu.validator.htmlparser.common.ByteReadable;
+import nu.validator.htmlparser.impl.MetaScanner;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+public class MetaSniffer extends MetaScanner implements Locator {
+    
+    private Encoding characterEncoding = null;
+
+    private final ErrorHandler errorHandler;
+    
+    private final Locator locator;
+    
+    private int line = 1;
+    
+    private int col = 0;
+    
+    private boolean prevWasCR = false;
+
+    public MetaSniffer(ErrorHandler eh, Locator locator) {
+        this.errorHandler = eh;
+        this.locator = locator;
+        this.characterEncoding = null;
+    }
+    
+    /**
+     * -1 means end.
+     * @return
+     * @throws IOException
+     */
+    protected int read() throws IOException {
+        int b = readable.readByte();
+        // [NOCPP[
+        switch (b) {
+            case '\n':
+                if (!prevWasCR) {
+                    line++;
+                    col = 0;
+                }
+                prevWasCR = false;
+                break;
+            case '\r':
+                line++;
+                col = 0;
+                prevWasCR = true;
+                break;
+            default:
+                col++;
+                prevWasCR = false;
+                break;
+        }
+        // ]NOCPP]
+        return b;
+    }
+
+    /**
+     * Main loop.
+     * 
+     * @return
+     * 
+     * @throws SAXException
+     * @throws IOException
+     * @throws
+     */
+    public Encoding sniff(ByteReadable readable) throws SAXException, IOException {
+        this.readable = readable;
+        stateLoop(stateSave);
+        return characterEncoding;
+    }
+    
+
+    /**
+     * @param string
+     * @throws SAXException
+     */
+    private void err(String message) throws SAXException {
+        if (errorHandler != null) {
+          SAXParseException spe = new SAXParseException(message, this);
+          errorHandler.error(spe);
+        }
+    }
+
+    /**
+     * @param string
+     * @throws SAXException
+     */
+    private void warn(String message) throws SAXException {
+        if (errorHandler != null) {
+          SAXParseException spe = new SAXParseException(message, this);
+          errorHandler.warning(spe);
+        }
+    }
+    
+    public int getColumnNumber() {
+        return col;
+    }
+
+    public int getLineNumber() {
+        return line;
+    }
+
+    public String getPublicId() {
+        if (locator != null) {
+            return locator.getPublicId();
+        }
+        return null;
+    }
+
+    public String getSystemId() {
+        if (locator != null) {
+            return locator.getSystemId();
+        }
+        return null;
+    }
+    
+    protected boolean tryCharset(String encoding) throws SAXException {
+        encoding = Encoding.toAsciiLowerCase(encoding);
+        try {
+            // XXX spec says only UTF-16
+            if ("utf-16".equals(encoding) || "utf-16be".equals(encoding) || "utf-16le".equals(encoding) || "utf-32".equals(encoding) || "utf-32be".equals(encoding) || "utf-32le".equals(encoding)) {
+                this.characterEncoding = Encoding.UTF8;
+                err("The internal character encoding declaration specified \u201C" + encoding + "\u201D which is not a rough superset of ASCII. Using \u201CUTF-8\u201D instead.");
+                return true;
+            } else {
+                Encoding cs = Encoding.forName(encoding);
+                String canonName = cs.getCanonName();
+                if (!cs.isAsciiSuperset()) {
+                    err("The encoding \u201C"
+                                + encoding
+                                + "\u201D is not an ASCII superset and, therefore, cannot be used in an internal encoding declaration. Continuing the sniffing algorithm.");
+                    return false;
+                }
+                if (!cs.isRegistered()) {
+                    if (encoding.startsWith("x-")) {
+                        err("The encoding \u201C"
+                                + encoding
+                                + "\u201D is not an IANA-registered encoding. (Charmod C022)");                    
+                    } else {
+                        err("The encoding \u201C"
+                                + encoding
+                                + "\u201D is not an IANA-registered encoding and did not use the \u201Cx-\u201D prefix. (Charmod C023)");
+                    }
+                } else if (!cs.getCanonName().equals(encoding)) {
+                    err("The encoding \u201C" + encoding
+                            + "\u201D is not the preferred name of the character encoding in use. The preferred name is \u201C"
+                            + canonName + "\u201D. (Charmod C024)");
+                }
+                if (cs.isShouldNot()) {
+                    warn("Authors should not use the character encoding \u201C"
+                            + encoding
+                            + "\u201D. It is recommended to use \u201CUTF-8\u201D.");                
+                } else if (cs.isObscure()) {
+                    warn("The character encoding \u201C" + encoding + "\u201D is not widely supported. Better interoperability may be achieved by using \u201CUTF-8\u201D.");
+                }
+                Encoding actual = cs.getActualHtmlEncoding();
+                if (actual == null) {
+                    this.characterEncoding = cs;
+                } else {
+                    warn("Using \u201C" + actual.getCanonName() + "\u201D instead of the declared encoding \u201C" + encoding + "\u201D.");
+                    this.characterEncoding = actual;
+                }
+                return true;
+            }
+        } catch (UnsupportedCharsetException e) {
+            err("Unsupported character encoding name: \u201C" + encoding + "\u201D. Will continue sniffing.");
+        }
+        return false;
+    }
+}    
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/rewindable/Rewindable.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/rewindable/Rewindable.java
new file mode 100644
index 000000000..47a3d5eb0
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/rewindable/Rewindable.java
@@ -0,0 +1,42 @@
+/*
+ * Copyright (c) 2001-2003 Thai Open Source Software Center Ltd
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without 
+ * modification, are permitted provided that the following conditions 
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright 
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above 
+ *    copyright notice, this list of conditions and the following 
+ *    disclaimer in the documentation and/or other materials provided 
+ *    with the distribution.
+ *  * Neither the name of the Thai Open Source Software Center Ltd nor 
+ *    the names of its contributors may be used to endorse or promote 
+ *    products derived from this software without specific prior 
+ *    written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 
+ * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+ * REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 
+ * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 
+ * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 
+ * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 
+ * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+package nu.validator.htmlparser.rewindable;
+
+public interface Rewindable {
+    void willNotRewind();
+
+    void rewind();
+
+    boolean canRewind();
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/rewindable/RewindableInputStream.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/rewindable/RewindableInputStream.java
new file mode 100644
index 000000000..3a1cc1b91
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/rewindable/RewindableInputStream.java
@@ -0,0 +1,235 @@
+/*
+ * Copyright (c) 2001-2003 Thai Open Source Software Center Ltd
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without 
+ * modification, are permitted provided that the following conditions 
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright 
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above 
+ *    copyright notice, this list of conditions and the following 
+ *    disclaimer in the documentation and/or other materials provided 
+ *    with the distribution.
+ *  * Neither the name of the Thai Open Source Software Center Ltd nor 
+ *    the names of its contributors may be used to endorse or promote 
+ *    products derived from this software without specific prior 
+ *    written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS 
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT 
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS 
+ * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
+ * REGENTS OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 
+ * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, 
+ * BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 
+ * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER 
+ * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN 
+ * ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+package nu.validator.htmlparser.rewindable;
+
+import java.io.IOException;
+import java.io.InputStream;
+
+public class RewindableInputStream extends InputStream implements Rewindable {
+    static class Block {
+        Block next;
+
+        final byte[] buf;
+
+        int used = 0;
+
+        static final int MIN_SIZE = 1024;
+
+        Block(int minSize) {
+            buf = new byte[Math.max(MIN_SIZE, minSize)];
+        }
+
+        Block() {
+            this(0);
+        }
+
+        void append(byte b) {
+            buf[used++] = b;
+        }
+
+        void append(byte[] b, int off, int len) {
+            System.arraycopy(b, off, buf, used, len);
+            used += len;
+        }
+    }
+
+    private Block head;
+
+    /**
+     * If curBlockAvail > 0, then there are curBlockAvail bytes available to be
+     * returned starting at curBlockPos in curBlock.buf.
+     */
+    private int curBlockAvail;
+
+    private Block curBlock;
+
+    private int curBlockPos;
+
+    private Block lastBlock;
+
+    /**
+     * true unless willNotRewind has been called
+     */
+    private boolean saving = true;
+
+    private final InputStream in;
+
+    private boolean pretendClosed = false;
+
+    /**
+     * true if we have got an EOF from the underlying InputStream
+     */
+    private boolean eof;
+
+    public RewindableInputStream(InputStream in) {
+        if (in == null)
+            throw new NullPointerException();
+        this.in = in;
+    }
+
+    public void close() throws IOException {
+        if (saving) {
+            curBlockAvail = 0;
+            curBlock = null;
+            pretendClosed = true;
+        } else {
+            head = null;
+            curBlock = null;
+            lastBlock = null;
+            saving = false;
+            curBlockAvail = 0;
+            in.close();
+        }
+    }
+
+    public void rewind() {
+        if (!saving)
+            throw new IllegalStateException("rewind() after willNotRewind()");
+        pretendClosed = false;
+        if (head == null)
+            return;
+        curBlock = head;
+        curBlockPos = 0;
+        curBlockAvail = curBlock.used;
+    }
+
+    public boolean canRewind() {
+        return saving;
+    }
+
+    public void willNotRewind() {
+        saving = false;
+        head = null;
+        lastBlock = null;
+        if (pretendClosed) {
+            pretendClosed = false;
+            try {
+                in.close();
+            } catch (IOException e) {
+            }
+        }
+    }
+
+    public int read() throws IOException {
+        if (curBlockAvail > 0) {
+            int c = curBlock.buf[curBlockPos++] & 0xFF;
+            --curBlockAvail;
+            if (curBlockAvail == 0) {
+                curBlock = curBlock.next;
+                if (curBlock != null) {
+                    curBlockPos = 0;
+                    curBlockAvail = curBlock.used;
+                }
+            }
+            return c;
+        }
+        int c = in.read();
+        if (saving && c != -1) {
+            if (lastBlock == null)
+                lastBlock = head = new Block();
+            else if (lastBlock.used == lastBlock.buf.length)
+                lastBlock = lastBlock.next = new Block();
+            lastBlock.append((byte) c);
+        }
+        return c;
+    }
+
+    public int read(byte b[], int off, int len) throws IOException {
+        if (curBlockAvail == 0 && !saving)
+            return in.read(b, off, len);
+        if (b == null)
+            throw new NullPointerException();
+        if (len < 0)
+            throw new IndexOutOfBoundsException();
+        int nRead = 0;
+        if (curBlockAvail != 0) {
+            for (;;) {
+                if (len == 0)
+                    return nRead;
+                b[off++] = curBlock.buf[curBlockPos++];
+                --len;
+                nRead++;
+                --curBlockAvail;
+                if (curBlockAvail == 0) {
+                    curBlock = curBlock.next;
+                    if (curBlock == null)
+                        break;
+                    curBlockAvail = curBlock.used;
+                    curBlockPos = 0;
+                }
+            }
+        }
+        if (len == 0)
+            return nRead;
+        if (eof)
+            return nRead > 0 ? nRead : -1;
+        try {
+            int n = in.read(b, off, len);
+            if (n < 0) {
+                eof = true;
+                return nRead > 0 ? nRead : -1;
+            }
+            nRead += n;
+            if (saving) {
+                if (lastBlock == null)
+                    lastBlock = head = new Block(n);
+                else if (lastBlock.buf.length - lastBlock.used < n) {
+                    if (lastBlock.used != lastBlock.buf.length) {
+                        int free = lastBlock.buf.length - lastBlock.used;
+                        lastBlock.append(b, off, free);
+                        off += free;
+                        n -= free;
+                    }
+                    lastBlock = lastBlock.next = new Block(n);
+                }
+                lastBlock.append(b, off, n);
+            }
+        } catch (IOException e) {
+            eof = true;
+            if (nRead == 0)
+                throw e;
+        }
+        return nRead;
+    }
+
+    public int available() throws IOException {
+        if (curBlockAvail == 0)
+            return in.available();
+        int n = curBlockAvail;
+        for (Block b = curBlock.next; b != null; b = b.next)
+            n += b.used;
+        return n + in.available();
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/HtmlParser.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/HtmlParser.java
new file mode 100644
index 000000000..714053e70
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/HtmlParser.java
@@ -0,0 +1,1097 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2007-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.sax;
+
+import java.io.IOException;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.LinkedList;
+import java.util.List;
+import java.util.HashMap;
+
+import nu.validator.htmlparser.common.CharacterHandler;
+import nu.validator.htmlparser.common.DoctypeExpectation;
+import nu.validator.htmlparser.common.DocumentModeHandler;
+import nu.validator.htmlparser.common.Heuristics;
+import nu.validator.htmlparser.common.TokenHandler;
+import nu.validator.htmlparser.common.TransitionHandler;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+import nu.validator.htmlparser.impl.ErrorReportingTokenizer;
+import nu.validator.htmlparser.impl.Tokenizer;
+import nu.validator.htmlparser.impl.TreeBuilder;
+import nu.validator.htmlparser.io.Driver;
+import nu.validator.saxtree.Document;
+import nu.validator.saxtree.DocumentFragment;
+import nu.validator.saxtree.TreeParser;
+
+import org.xml.sax.ContentHandler;
+import org.xml.sax.DTDHandler;
+import org.xml.sax.EntityResolver;
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.InputSource;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXNotRecognizedException;
+import org.xml.sax.SAXNotSupportedException;
+import org.xml.sax.XMLReader;
+import org.xml.sax.ext.LexicalHandler;
+import org.xml.sax.helpers.DefaultHandler;
+
+/**
+ * This class implements an HTML5 parser that exposes data through the SAX2 
+ * interface. 
+ * 
+ * <p>By default, when using the constructor without arguments, the 
+ * this parser coerces XML 1.0-incompatible infosets into XML 1.0-compatible
+ * infosets. This corresponds to <code>ALTER_INFOSET</code> as the general 
+ * XML violation policy. To make the parser support non-conforming HTML fully 
+ * per the HTML 5 spec while on the other hand potentially violating the SAX2 
+ * API contract, set the general XML violation policy to <code>ALLOW</code>. 
+ * It is possible to treat XML 1.0 infoset violations as fatal by setting 
+ * the general XML violation policy to <code>FATAL</code>. 
+ * 
+ * <p>By default, this parser doesn't do true streaming but buffers everything 
+ * first. The parser can be made truly streaming by calling 
+ * <code>setStreamabilityViolationPolicy(XmlViolationPolicy.FATAL)</code>. This 
+ * has the consequence that errors that require non-streamable recovery are 
+ * treated as fatal.
+ * 
+ * <p>By default, in order to make the parse events emulate the parse events 
+ * for a DTDless XML document, the parser does not report the doctype through 
+ * <code>LexicalHandler</code>. Doctype reporting through 
+ * <code>LexicalHandler</code> can be turned on by calling 
+ * <code>setReportingDoctype(true)</code>.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public class HtmlParser implements XMLReader {
+
+    private Driver driver = null;
+
+    private TreeBuilder<?> treeBuilder = null;
+
+    private SAXStreamer saxStreamer = null; // work around javac bug
+
+    private SAXTreeBuilder saxTreeBuilder = null; // work around javac bug
+
+    private ContentHandler contentHandler = null;
+
+    private LexicalHandler lexicalHandler = null;
+
+    private DTDHandler dtdHandler = null;
+
+    private EntityResolver entityResolver = null;
+
+    private ErrorHandler errorHandler = null;
+
+    private DocumentModeHandler documentModeHandler = null;
+
+    private DoctypeExpectation doctypeExpectation = DoctypeExpectation.HTML;
+
+    private boolean checkingNormalization = false;
+
+    private boolean scriptingEnabled = false;
+
+    private final List<CharacterHandler> characterHandlers = new LinkedList<CharacterHandler>();
+    
+    private XmlViolationPolicy contentSpacePolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy contentNonXmlCharPolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy commentPolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy namePolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy streamabilityViolationPolicy = XmlViolationPolicy.ALLOW;
+    
+    private boolean html4ModeCompatibleWithXhtml1Schemata = false;
+
+    private boolean mappingLangToXmlLang = false;
+
+    private XmlViolationPolicy xmlnsPolicy = XmlViolationPolicy.FATAL;
+    
+    private boolean reportingDoctype = true;
+
+    private ErrorHandler treeBuilderErrorHandler = null;
+
+    private Heuristics heuristics = Heuristics.NONE;
+
+    private HashMap<String, String> errorProfileMap = null;
+
+    private TransitionHandler transitionHandler = null;
+    
+    /**
+     * Instantiates the parser with a fatal XML violation policy.
+     *
+     */
+    public HtmlParser() {
+        this(XmlViolationPolicy.FATAL);
+    }
+    
+    /**
+     * Instantiates the parser with a specific XML violation policy.
+     * @param xmlPolicy the policy
+     */
+    public HtmlParser(XmlViolationPolicy xmlPolicy) {
+        setXmlPolicy(xmlPolicy);
+    }    
+
+    private Tokenizer newTokenizer(TokenHandler handler, boolean newAttributesEachTime) {
+        if (errorHandler == null && transitionHandler == null &&
+            contentNonXmlCharPolicy == XmlViolationPolicy.ALLOW) {
+            return new Tokenizer(handler, newAttributesEachTime);
+        }
+        ErrorReportingTokenizer tokenizer = 
+            new ErrorReportingTokenizer(handler, newAttributesEachTime);
+        tokenizer.setErrorProfile(errorProfileMap);
+        return tokenizer;
+   }
+    
+    /**
+     * This class wraps different tree builders depending on configuration. This 
+     * method does the work of hiding this from the user of the class.
+     */
+    private void lazyInit() {
+        if (driver == null) {
+            if (streamabilityViolationPolicy == XmlViolationPolicy.ALLOW) {
+                this.saxTreeBuilder = new SAXTreeBuilder();
+                this.treeBuilder = this.saxTreeBuilder;
+                this.saxStreamer = null;
+                this.driver = new Driver(newTokenizer(treeBuilder, true));
+            } else {
+                this.saxStreamer = new SAXStreamer();
+                this.treeBuilder = this.saxStreamer;
+                this.saxTreeBuilder = null;
+                this.driver = new Driver(newTokenizer(treeBuilder, false));
+            }
+            this.driver.setErrorHandler(errorHandler);
+            this.driver.setTransitionHandler(transitionHandler);
+            this.treeBuilder.setErrorHandler(treeBuilderErrorHandler);
+            this.driver.setCheckingNormalization(checkingNormalization);
+            this.driver.setCommentPolicy(commentPolicy);
+            this.driver.setContentNonXmlCharPolicy(contentNonXmlCharPolicy);
+            this.driver.setContentSpacePolicy(contentSpacePolicy);
+            this.driver.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata);
+            this.driver.setMappingLangToXmlLang(mappingLangToXmlLang);
+            this.driver.setXmlnsPolicy(xmlnsPolicy);
+            this.driver.setHeuristics(heuristics);
+            for (CharacterHandler characterHandler : characterHandlers) {
+                this.driver.addCharacterHandler(characterHandler);
+            }
+            this.treeBuilder.setDoctypeExpectation(doctypeExpectation);
+            this.treeBuilder.setDocumentModeHandler(documentModeHandler);
+            this.treeBuilder.setIgnoringComments(lexicalHandler == null);
+            this.treeBuilder.setScriptingEnabled(scriptingEnabled);
+            this.treeBuilder.setReportingDoctype(reportingDoctype);
+            this.treeBuilder.setNamePolicy(namePolicy);
+            if (saxStreamer != null) {
+                saxStreamer.setContentHandler(contentHandler == null ? new DefaultHandler()
+                        : contentHandler);
+                saxStreamer.setLexicalHandler(lexicalHandler);
+                driver.setAllowRewinding(false);
+            }
+        }
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#getContentHandler()
+     */
+    public ContentHandler getContentHandler() {
+        return contentHandler;
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#getDTDHandler()
+     */
+    public DTDHandler getDTDHandler() {
+        return dtdHandler;
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#getEntityResolver()
+     */
+    public EntityResolver getEntityResolver() {
+        return entityResolver;
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#getErrorHandler()
+     */
+    public ErrorHandler getErrorHandler() {
+        return errorHandler;
+    }
+
+    /**
+     * Exposes the configuration of the emulated XML parser as well as
+     * boolean-valued configuration without using non-<code>XMLReader</code>
+     * getters directly.
+     * 
+     * <dl>
+     * <dt><code>http://xml.org/sax/features/external-general-entities</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/external-parameter-entities</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/is-standalone</code></dt>
+     * <dd><code>true</code></dd>
+     * <dt><code>http://xml.org/sax/features/lexical-handler/parameter-entities</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/namespaces</code></dt>
+     * <dd><code>true</code></dd>
+     * <dt><code>http://xml.org/sax/features/namespace-prefixes</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/resolve-dtd-uris</code></dt>
+     * <dd><code>true</code></dd>
+     * <dt><code>http://xml.org/sax/features/string-interning</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/unicode-normalization-checking</code></dt>
+     * <dd><code>isCheckingNormalization</code></dd>
+     * <dt><code>http://xml.org/sax/features/use-attributes2</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/use-locator2</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/use-entity-resolver2</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/validation</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/xmlns-uris</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://xml.org/sax/features/xml-1.1</code></dt>
+     * <dd><code>false</code></dd>
+     * <dt><code>http://validator.nu/features/html4-mode-compatible-with-xhtml1-schemata</code></dt>
+     * <dd><code>isHtml4ModeCompatibleWithXhtml1Schemata</code></dd>
+     * <dt><code>http://validator.nu/features/mapping-lang-to-xml-lang</code></dt>
+     * <dd><code>isMappingLangToXmlLang</code></dd>
+     * <dt><code>http://validator.nu/features/scripting-enabled</code></dt>
+     * <dd><code>isScriptingEnabled</code></dd>
+     * </dl>
+     * 
+     * @param name
+     *            feature URI string
+     * @return a value per the list above
+     * @see org.xml.sax.XMLReader#getFeature(java.lang.String)
+     */
+    public boolean getFeature(String name) throws SAXNotRecognizedException,
+            SAXNotSupportedException {
+        if ("http://xml.org/sax/features/external-general-entities".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/external-parameter-entities".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/is-standalone".equals(name)) {
+            return true;
+        } else if ("http://xml.org/sax/features/lexical-handler/parameter-entities".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/namespaces".equals(name)) {
+            return true;
+        } else if ("http://xml.org/sax/features/namespace-prefixes".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/resolve-dtd-uris".equals(name)) {
+            return true; // default value--applicable scenario never happens
+        } else if ("http://xml.org/sax/features/string-interning".equals(name)) {
+            return true;
+        } else if ("http://xml.org/sax/features/unicode-normalization-checking".equals(name)) {
+            return isCheckingNormalization(); // the checks aren't really per
+            // XML 1.1
+        } else if ("http://xml.org/sax/features/use-attributes2".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/use-locator2".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/use-entity-resolver2".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/validation".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/xmlns-uris".equals(name)) {
+            return false;
+        } else if ("http://xml.org/sax/features/xml-1.1".equals(name)) {
+            return false;
+        } else if ("http://validator.nu/features/html4-mode-compatible-with-xhtml1-schemata".equals(name)) {
+            return isHtml4ModeCompatibleWithXhtml1Schemata();
+        } else if ("http://validator.nu/features/mapping-lang-to-xml-lang".equals(name)) {
+            return isMappingLangToXmlLang();
+        } else if ("http://validator.nu/features/scripting-enabled".equals(name)) {
+            return isScriptingEnabled();
+        } else {
+            throw new SAXNotRecognizedException();
+        }
+    }
+
+    /**
+     * Allows <code>XMLReader</code>-level access to non-boolean valued
+     * getters.
+     * 
+     * <p>
+     * The properties are mapped as follows:
+     * 
+     * <dl>
+     * <dt><code>http://xml.org/sax/properties/document-xml-version</code></dt>
+     * <dd><code>"1.0"</code></dd>
+     * <dt><code>http://xml.org/sax/properties/lexical-handler</code></dt>
+     * <dd><code>getLexicalHandler</code></dd>
+     * <dt><code>http://validator.nu/properties/content-space-policy</code></dt>
+     * <dd><code>getContentSpacePolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/content-non-xml-char-policy</code></dt>
+     * <dd><code>getContentNonXmlCharPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/comment-policy</code></dt>
+     * <dd><code>getCommentPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/xmlns-policy</code></dt>
+     * <dd><code>getXmlnsPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/name-policy</code></dt>
+     * <dd><code>getNamePolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/streamability-violation-policy</code></dt>
+     * <dd><code>getStreamabilityViolationPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/document-mode-handler</code></dt>
+     * <dd><code>getDocumentModeHandler</code></dd>
+     * <dt><code>http://validator.nu/properties/doctype-expectation</code></dt>
+     * <dd><code>getDoctypeExpectation</code></dd>
+     * <dt><code>http://xml.org/sax/features/unicode-normalization-checking</code></dt>
+     * </dl>
+     * 
+     * @param name
+     *            property URI string
+     * @return a value per the list above
+     * @see org.xml.sax.XMLReader#getProperty(java.lang.String)
+     */
+    public Object getProperty(String name) throws SAXNotRecognizedException,
+            SAXNotSupportedException {
+        if ("http://xml.org/sax/properties/declaration-handler".equals(name)) {
+            throw new SAXNotSupportedException(
+                    "This parser does not suppert DeclHandler.");
+        } else if ("http://xml.org/sax/properties/document-xml-version".equals(name)) {
+            return "1.0"; // Emulating an XML 1.1 parser is not supported.
+        } else if ("http://xml.org/sax/properties/dom-node".equals(name)) {
+            throw new SAXNotSupportedException(
+                    "This parser does not walk the DOM.");
+        } else if ("http://xml.org/sax/properties/lexical-handler".equals(name)) {
+            return getLexicalHandler();
+        } else if ("http://xml.org/sax/properties/xml-string".equals(name)) {
+            throw new SAXNotSupportedException(
+                    "This parser does not expose the source as a string.");
+        } else if ("http://validator.nu/properties/content-space-policy".equals(name)) {
+            return getContentSpacePolicy();
+        } else if ("http://validator.nu/properties/content-non-xml-char-policy".equals(name)) {
+            return getContentNonXmlCharPolicy();
+        } else if ("http://validator.nu/properties/comment-policy".equals(name)) {
+            return getCommentPolicy();
+        } else if ("http://validator.nu/properties/xmlns-policy".equals(name)) {
+            return getXmlnsPolicy();
+        } else if ("http://validator.nu/properties/name-policy".equals(name)) {
+            return getNamePolicy();
+        } else if ("http://validator.nu/properties/streamability-violation-policy".equals(name)) {
+            return getStreamabilityViolationPolicy();
+        } else if ("http://validator.nu/properties/document-mode-handler".equals(name)) {
+            return getDocumentModeHandler();
+        } else if ("http://validator.nu/properties/doctype-expectation".equals(name)) {
+            return getDoctypeExpectation();
+        } else if ("http://validator.nu/properties/xml-policy".equals(name)) {
+            throw new SAXNotSupportedException(
+                    "Cannot get a convenience setter.");
+        } else if ("http://validator.nu/properties/heuristics".equals(name)) {
+            return getHeuristics();
+        } else {
+            throw new SAXNotRecognizedException();
+        }
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#parse(org.xml.sax.InputSource)
+     */
+    public void parse(InputSource input) throws IOException, SAXException {
+        lazyInit();
+        try {
+            treeBuilder.setFragmentContext(null);
+            tokenize(input);
+        } finally {
+            if (saxTreeBuilder != null) {
+                Document document = saxTreeBuilder.getDocument();
+                if (document != null) {
+                    new TreeParser(contentHandler, lexicalHandler).parse(document);
+                }
+            }
+        }
+    }
+
+    /**
+     * Parses a fragment with HTML context.
+     * 
+     * @param input the input to parse
+     * @param context the name of the context element (HTML namespace assumed)
+     * @throws IOException
+     * @throws SAXException
+     */
+    public void parseFragment(InputSource input, String context)
+            throws IOException, SAXException {
+        lazyInit();
+        try {
+            treeBuilder.setFragmentContext(context.intern());
+            tokenize(input);
+        } finally {
+            if (saxTreeBuilder != null) {
+                DocumentFragment fragment = saxTreeBuilder.getDocumentFragment();
+                new TreeParser(contentHandler, lexicalHandler).parse(fragment);
+            }
+        }
+    }
+    
+    /**
+     * Parses a fragment.
+     * 
+     * @param input the input to parse
+     * @param contextLocal the local name of the context element
+     * @param contextNamespace the namespace of the context element
+     * @throws IOException
+     * @throws SAXException
+     */
+    public void parseFragment(InputSource input, String contextLocal, String contextNamespace)
+            throws IOException, SAXException {
+        lazyInit();
+        try {
+            treeBuilder.setFragmentContext(contextLocal.intern(), contextNamespace.intern(), null, false);
+            tokenize(input);
+        } finally {
+            if (saxTreeBuilder != null) {
+                DocumentFragment fragment = saxTreeBuilder.getDocumentFragment();
+                new TreeParser(contentHandler, lexicalHandler).parse(fragment);
+            }
+        }
+    }
+    
+    /**
+     * @param is
+     * @throws SAXException
+     * @throws IOException
+     * @throws MalformedURLException
+     */
+    private void tokenize(InputSource is) throws SAXException, IOException, MalformedURLException {
+        if (is == null) {
+            throw new IllegalArgumentException("Null input.");            
+        }
+        if (is.getByteStream() == null && is.getCharacterStream() == null) {
+            String systemId = is.getSystemId();
+            if (systemId == null) {
+                throw new IllegalArgumentException("No byte stream, no character stream nor URI.");
+            }
+            if (entityResolver != null) {
+                is = entityResolver.resolveEntity(is.getPublicId(), systemId);
+            }
+            if (is.getByteStream() == null || is.getCharacterStream() == null) {
+                is = new InputSource();
+                is.setSystemId(systemId);
+                is.setByteStream(new URL(systemId).openStream());
+            }
+        }
+        driver.tokenize(is);
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#parse(java.lang.String)
+     */
+    public void parse(String systemId) throws IOException, SAXException {
+        parse(new InputSource(systemId));
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#setContentHandler(org.xml.sax.ContentHandler)
+     */
+    public void setContentHandler(ContentHandler handler) {
+        contentHandler = handler;
+        if (saxStreamer != null) {
+            saxStreamer.setContentHandler(contentHandler == null ? new DefaultHandler()
+                    : contentHandler);
+        }
+    }
+
+    /**
+     * Sets the lexical handler.
+     * @param handler the hander.
+     */
+    public void setLexicalHandler(LexicalHandler handler) {
+        lexicalHandler = handler;
+        if (treeBuilder != null) {
+            treeBuilder.setIgnoringComments(handler == null);
+            if (saxStreamer != null) {
+                saxStreamer.setLexicalHandler(handler);
+            }
+        }
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#setDTDHandler(org.xml.sax.DTDHandler)
+     */
+    public void setDTDHandler(DTDHandler handler) {
+        dtdHandler = handler;
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#setEntityResolver(org.xml.sax.EntityResolver)
+     */
+    public void setEntityResolver(EntityResolver resolver) {
+        entityResolver = resolver;
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#setErrorHandler(org.xml.sax.ErrorHandler)
+     */
+    public void setErrorHandler(ErrorHandler handler) {
+        errorHandler = handler;
+        treeBuilderErrorHandler = handler;
+        driver = null;
+    }
+
+    public void setTransitionHandler(TransitionHandler handler) {
+        transitionHandler = handler;
+        driver = null;
+    }
+    
+    /**
+     * @see org.xml.sax.XMLReader#setErrorHandler(org.xml.sax.ErrorHandler)
+     * @deprecated For Validator.nu internal use
+     */
+    public void setTreeBuilderErrorHandlerOverride(ErrorHandler handler) {
+        treeBuilderErrorHandler = handler;
+        if (driver != null) {
+            treeBuilder.setErrorHandler(handler);
+        }
+    }
+    
+    /**
+     * Sets a boolean feature without having to use non-<code>XMLReader</code>
+     * setters directly.
+     * 
+     * <p>
+     * The supported features are:
+     * 
+     * <dl>
+     * <dt><code>http://xml.org/sax/features/unicode-normalization-checking</code></dt>
+     * <dd><code>setCheckingNormalization</code></dd>
+     * <dt><code>http://validator.nu/features/html4-mode-compatible-with-xhtml1-schemata</code></dt>
+     * <dd><code>setHtml4ModeCompatibleWithXhtml1Schemata</code></dd>
+     * <dt><code>http://validator.nu/features/mapping-lang-to-xml-lang</code></dt>
+     * <dd><code>setMappingLangToXmlLang</code></dd>
+     * <dt><code>http://validator.nu/features/scripting-enabled</code></dt>
+     * <dd><code>setScriptingEnabled</code></dd>
+     * </dl>
+     * 
+     * @see org.xml.sax.XMLReader#setFeature(java.lang.String, boolean)
+     */
+    public void setFeature(String name, boolean value)
+            throws SAXNotRecognizedException, SAXNotSupportedException {
+        if ("http://xml.org/sax/features/external-general-entities".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/external-parameter-entities".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/is-standalone".equals(name)) {
+            if (!value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/lexical-handler/parameter-entities".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/namespaces".equals(name)) {
+            if (!value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/namespace-prefixes".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/resolve-dtd-uris".equals(name)) {
+            if (!value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/string-interning".equals(name)) {
+            if (!value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/unicode-normalization-checking".equals(name)) {
+            setCheckingNormalization(value);
+        } else if ("http://xml.org/sax/features/use-attributes2".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/use-locator2".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/use-entity-resolver2".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/validation".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/xmlns-uris".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://xml.org/sax/features/xml-1.1".equals(name)) {
+            if (value) {
+                throw new SAXNotSupportedException("Cannot set " + name + ".");
+            }
+        } else if ("http://validator.nu/features/html4-mode-compatible-with-xhtml1-schemata".equals(name)) {
+            setHtml4ModeCompatibleWithXhtml1Schemata(value);
+        } else if ("http://validator.nu/features/mapping-lang-to-xml-lang".equals(name)) {
+            setMappingLangToXmlLang(value);
+        } else if ("http://validator.nu/features/scripting-enabled".equals(name)) {
+            setScriptingEnabled(value);
+        } else {
+            throw new SAXNotRecognizedException();
+        }
+    }
+
+    /**
+     * Sets a non-boolean property without having to use non-<code>XMLReader</code>
+     * setters directly.
+     * 
+     * <dl>
+     * <dt><code>http://xml.org/sax/properties/lexical-handler</code></dt>
+     * <dd><code>setLexicalHandler</code></dd>
+     * <dt><code>http://validator.nu/properties/content-space-policy</code></dt>
+     * <dd><code>setContentSpacePolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/content-non-xml-char-policy</code></dt>
+     * <dd><code>setContentNonXmlCharPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/comment-policy</code></dt>
+     * <dd><code>setCommentPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/xmlns-policy</code></dt>
+     * <dd><code>setXmlnsPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/name-policy</code></dt>
+     * <dd><code>setNamePolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/streamability-violation-policy</code></dt>
+     * <dd><code>setStreamabilityViolationPolicy</code></dd>
+     * <dt><code>http://validator.nu/properties/document-mode-handler</code></dt>
+     * <dd><code>setDocumentModeHandler</code></dd>
+     * <dt><code>http://validator.nu/properties/doctype-expectation</code></dt>
+     * <dd><code>setDoctypeExpectation</code></dd>
+     * <dt><code>http://validator.nu/properties/xml-policy</code></dt>
+     * <dd><code>setXmlPolicy</code></dd>
+     * </dl>
+     * 
+     * @see org.xml.sax.XMLReader#setProperty(java.lang.String,
+     *      java.lang.Object)
+     */
+    public void setProperty(String name, Object value)
+            throws SAXNotRecognizedException, SAXNotSupportedException {
+        if ("http://xml.org/sax/properties/declaration-handler".equals(name)) {
+            throw new SAXNotSupportedException(
+                    "This parser does not suppert DeclHandler.");
+        } else if ("http://xml.org/sax/properties/document-xml-version".equals(name)) {
+            throw new SAXNotSupportedException(
+                    "Can't set document-xml-version.");
+        } else if ("http://xml.org/sax/properties/dom-node".equals(name)) {
+            throw new SAXNotSupportedException("Can't set dom-node.");
+        } else if ("http://xml.org/sax/properties/lexical-handler".equals(name)) {
+            setLexicalHandler((LexicalHandler) value);
+        } else if ("http://xml.org/sax/properties/xml-string".equals(name)) {
+            throw new SAXNotSupportedException("Can't set xml-string.");
+        } else if ("http://validator.nu/properties/content-space-policy".equals(name)) {
+            setContentSpacePolicy((XmlViolationPolicy) value);
+        } else if ("http://validator.nu/properties/content-non-xml-char-policy".equals(name)) {
+            setContentNonXmlCharPolicy((XmlViolationPolicy) value);
+        } else if ("http://validator.nu/properties/comment-policy".equals(name)) {
+            setCommentPolicy((XmlViolationPolicy) value);
+        } else if ("http://validator.nu/properties/xmlns-policy".equals(name)) {
+            setXmlnsPolicy((XmlViolationPolicy) value);
+        } else if ("http://validator.nu/properties/name-policy".equals(name)) {
+            setNamePolicy((XmlViolationPolicy) value);
+        } else if ("http://validator.nu/properties/streamability-violation-policy".equals(name)) {
+            setStreamabilityViolationPolicy((XmlViolationPolicy) value);
+        } else if ("http://validator.nu/properties/document-mode-handler".equals(name)) {
+            setDocumentModeHandler((DocumentModeHandler) value);
+        } else if ("http://validator.nu/properties/doctype-expectation".equals(name)) {
+            setDoctypeExpectation((DoctypeExpectation) value);
+        } else if ("http://validator.nu/properties/xml-policy".equals(name)) {
+            setXmlPolicy((XmlViolationPolicy) value);
+        } else if ("http://validator.nu/properties/heuristics".equals(name)) {
+            setHeuristics((Heuristics) value);
+        } else {
+            throw new SAXNotRecognizedException();
+        }
+    }
+
+    /**
+     * Indicates whether NFC normalization of source is being checked.
+     * @return <code>true</code> if NFC normalization of source is being checked.
+     * @see nu.validator.htmlparser.impl.Tokenizer#isCheckingNormalization()
+     */
+    public boolean isCheckingNormalization() {
+        return checkingNormalization;
+    }
+
+    /**
+     * Toggles the checking of the NFC normalization of source.
+     * @param enable <code>true</code> to check normalization
+     * @see nu.validator.htmlparser.impl.Tokenizer#setCheckingNormalization(boolean)
+     */
+    public void setCheckingNormalization(boolean enable) {
+        this.checkingNormalization = enable;
+        if (driver != null) {
+            driver.setCheckingNormalization(checkingNormalization);
+        }
+    }
+
+    /**
+     * Sets the policy for consecutive hyphens in comments.
+     * @param commentPolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setCommentPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setCommentPolicy(XmlViolationPolicy commentPolicy) {
+        this.commentPolicy = commentPolicy;
+        if (driver != null) {
+            driver.setCommentPolicy(commentPolicy);
+        }
+    }
+
+    /**
+     * Sets the policy for non-XML characters except white space.
+     * @param contentNonXmlCharPolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentNonXmlCharPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentNonXmlCharPolicy(
+            XmlViolationPolicy contentNonXmlCharPolicy) {
+        this.contentNonXmlCharPolicy = contentNonXmlCharPolicy;
+        driver = null;
+    }
+
+    /**
+     * Sets the policy for non-XML white space.
+     * @param contentSpacePolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentSpacePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentSpacePolicy(XmlViolationPolicy contentSpacePolicy) {
+        this.contentSpacePolicy = contentSpacePolicy;
+        if (driver != null) {
+            driver.setContentSpacePolicy(contentSpacePolicy);
+        }
+    }
+
+    /**
+     * Whether the parser considers scripting to be enabled for noscript treatment.
+     * 
+     * @return <code>true</code> if enabled
+     * @see nu.validator.htmlparser.impl.TreeBuilder#isScriptingEnabled()
+     */
+    public boolean isScriptingEnabled() {
+        return scriptingEnabled;
+    }
+
+    /**
+     * Sets whether the parser considers scripting to be enabled for noscript treatment.
+     * @param scriptingEnabled <code>true</code> to enable
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setScriptingEnabled(boolean)
+     */
+    public void setScriptingEnabled(boolean scriptingEnabled) {
+        this.scriptingEnabled = scriptingEnabled;
+        if (treeBuilder != null) {
+            treeBuilder.setScriptingEnabled(scriptingEnabled);
+        }
+    }
+
+    /**
+     * Returns the doctype expectation.
+     * 
+     * @return the doctypeExpectation
+     */
+    public DoctypeExpectation getDoctypeExpectation() {
+        return doctypeExpectation;
+    }
+
+    /**
+     * Sets the doctype expectation.
+     * 
+     * @param doctypeExpectation
+     *            the doctypeExpectation to set
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setDoctypeExpectation(nu.validator.htmlparser.common.DoctypeExpectation)
+     */
+    public void setDoctypeExpectation(DoctypeExpectation doctypeExpectation) {
+        this.doctypeExpectation = doctypeExpectation;
+        if (treeBuilder != null) {
+            treeBuilder.setDoctypeExpectation(doctypeExpectation);
+        }
+    }
+
+    /**
+     * Returns the document mode handler.
+     * 
+     * @return the documentModeHandler
+     */
+    public DocumentModeHandler getDocumentModeHandler() {
+        return documentModeHandler;
+    }
+
+    /**
+     * Sets the document mode handler.
+     * 
+     * @param documentModeHandler
+     *            the documentModeHandler to set
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setDocumentModeHandler(nu.validator.htmlparser.common.DocumentModeHandler)
+     */
+    public void setDocumentModeHandler(DocumentModeHandler documentModeHandler) {
+        this.documentModeHandler = documentModeHandler;
+    }
+
+    /**
+     * Returns the streamabilityViolationPolicy.
+     * 
+     * @return the streamabilityViolationPolicy
+     */
+    public XmlViolationPolicy getStreamabilityViolationPolicy() {
+        return streamabilityViolationPolicy;
+    }
+
+    /**
+     * Sets the streamabilityViolationPolicy.
+     * 
+     * @param streamabilityViolationPolicy
+     *            the streamabilityViolationPolicy to set
+     */
+    public void setStreamabilityViolationPolicy(
+            XmlViolationPolicy streamabilityViolationPolicy) {
+        this.streamabilityViolationPolicy = streamabilityViolationPolicy;
+        driver = null;
+    }
+
+    /**
+     * Whether the HTML 4 mode reports boolean attributes in a way that repeats
+     * the name in the value.
+     * @param html4ModeCompatibleWithXhtml1Schemata
+     */
+    public void setHtml4ModeCompatibleWithXhtml1Schemata(
+            boolean html4ModeCompatibleWithXhtml1Schemata) {
+        this.html4ModeCompatibleWithXhtml1Schemata = html4ModeCompatibleWithXhtml1Schemata;
+        if (driver != null) {
+            driver.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata);
+        }
+    }
+
+    /**
+     * Returns the <code>Locator</code> during parse.
+     * @return the <code>Locator</code>
+     */
+    public Locator getDocumentLocator() {
+        return driver.getDocumentLocator();
+    }
+
+    /**
+     * Whether the HTML 4 mode reports boolean attributes in a way that repeats
+     * the name in the value.
+     * 
+     * @return the html4ModeCompatibleWithXhtml1Schemata
+     */
+    public boolean isHtml4ModeCompatibleWithXhtml1Schemata() {
+        return html4ModeCompatibleWithXhtml1Schemata;
+    }
+
+    /**
+     * Whether <code>lang</code> is mapped to <code>xml:lang</code>.
+     * @param mappingLangToXmlLang
+     * @see nu.validator.htmlparser.impl.Tokenizer#setMappingLangToXmlLang(boolean)
+     */
+    public void setMappingLangToXmlLang(boolean mappingLangToXmlLang) {
+        this.mappingLangToXmlLang = mappingLangToXmlLang;
+        if (driver != null) {
+            driver.setMappingLangToXmlLang(mappingLangToXmlLang);
+        }
+    }
+
+    /**
+     * Whether <code>lang</code> is mapped to <code>xml:lang</code>.
+     * 
+     * @return the mappingLangToXmlLang
+     */
+    public boolean isMappingLangToXmlLang() {
+        return mappingLangToXmlLang;
+    }
+
+    /**
+     * Whether the <code>xmlns</code> attribute on the root element is 
+     * passed to through. (FATAL not allowed.)
+     * @param xmlnsPolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setXmlnsPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setXmlnsPolicy(XmlViolationPolicy xmlnsPolicy) {
+        if (xmlnsPolicy == XmlViolationPolicy.FATAL) {
+            throw new IllegalArgumentException("Can't use FATAL here.");
+        }
+        this.xmlnsPolicy = xmlnsPolicy;
+        if (driver != null) {
+            driver.setXmlnsPolicy(xmlnsPolicy);
+        }
+    }
+
+    /**
+     * Returns the xmlnsPolicy.
+     * 
+     * @return the xmlnsPolicy
+     */
+    public XmlViolationPolicy getXmlnsPolicy() {
+        return xmlnsPolicy;
+    }
+
+    /**
+     * Returns the lexicalHandler.
+     * 
+     * @return the lexicalHandler
+     */
+    public LexicalHandler getLexicalHandler() {
+        return lexicalHandler;
+    }
+
+    /**
+     * Returns the commentPolicy.
+     * 
+     * @return the commentPolicy
+     */
+    public XmlViolationPolicy getCommentPolicy() {
+        return commentPolicy;
+    }
+
+    /**
+     * Returns the contentNonXmlCharPolicy.
+     * 
+     * @return the contentNonXmlCharPolicy
+     */
+    public XmlViolationPolicy getContentNonXmlCharPolicy() {
+        return contentNonXmlCharPolicy;
+    }
+
+    /**
+     * Returns the contentSpacePolicy.
+     * 
+     * @return the contentSpacePolicy
+     */
+    public XmlViolationPolicy getContentSpacePolicy() {
+        return contentSpacePolicy;
+    }
+
+    /**
+     * @param reportingDoctype
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setReportingDoctype(boolean)
+     */
+    public void setReportingDoctype(boolean reportingDoctype) {
+        this.reportingDoctype = reportingDoctype;
+        if (treeBuilder != null) {
+            treeBuilder.setReportingDoctype(reportingDoctype);
+        }
+    }
+
+    /**
+     * Returns the reportingDoctype.
+     * 
+     * @return the reportingDoctype
+     */
+    public boolean isReportingDoctype() {
+        return reportingDoctype;
+    }
+
+    /**
+     * @param errorProfile
+     * @see nu.validator.htmlparser.impl.errorReportingTokenizer#setErrorProfile(set)
+     */
+    public void setErrorProfile(HashMap<String, String> errorProfileMap) {
+        this.errorProfileMap = errorProfileMap;
+    }
+
+    /**
+     * The policy for non-NCName element and attribute names.
+     * @param namePolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setNamePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setNamePolicy(XmlViolationPolicy namePolicy) {
+        this.namePolicy = namePolicy;
+        if (driver != null) {
+            driver.setNamePolicy(namePolicy);
+            treeBuilder.setNamePolicy(namePolicy);
+        }
+    }
+    
+    /**
+     * Sets the encoding sniffing heuristics.
+     * 
+     * @param heuristics the heuristics to set
+     * @see nu.validator.htmlparser.impl.Tokenizer#setHeuristics(nu.validator.htmlparser.common.Heuristics)
+     */
+    public void setHeuristics(Heuristics heuristics) {
+        this.heuristics = heuristics;
+        if (driver != null) {
+            driver.setHeuristics(heuristics);
+        }
+    }
+    
+    public Heuristics getHeuristics() {
+        return this.heuristics;
+    }
+
+    /**
+     * This is a catch-all convenience method for setting name, xmlns, content space, 
+     * content non-XML char and comment policies in one go. This does not affect the 
+     * streamability policy or doctype reporting.
+     * 
+     * @param xmlPolicy
+     */
+    public void setXmlPolicy(XmlViolationPolicy xmlPolicy) {
+        setNamePolicy(xmlPolicy);
+        setXmlnsPolicy(xmlPolicy == XmlViolationPolicy.FATAL ? XmlViolationPolicy.ALTER_INFOSET : xmlPolicy);
+        setContentSpacePolicy(xmlPolicy);
+        setContentNonXmlCharPolicy(xmlPolicy);
+        setCommentPolicy(xmlPolicy);
+    }
+
+    /**
+     * The policy for non-NCName element and attribute names.
+     * 
+     * @return the namePolicy
+     */
+    public XmlViolationPolicy getNamePolicy() {
+        return namePolicy;
+    }
+
+    /**
+     * Does nothing.
+     * @deprecated
+     */
+    public void setBogusXmlnsPolicy(
+            XmlViolationPolicy bogusXmlnsPolicy) {
+    }
+
+    /**
+     * Returns <code>XmlViolationPolicy.ALTER_INFOSET</code>.
+     * @deprecated
+     * @return <code>XmlViolationPolicy.ALTER_INFOSET</code>
+     */
+    public XmlViolationPolicy getBogusXmlnsPolicy() {
+        return XmlViolationPolicy.ALTER_INFOSET;
+    }
+    
+    public void addCharacterHandler(CharacterHandler characterHandler) {
+        this.characterHandlers.add(characterHandler);
+        if (driver != null) {
+            driver.addCharacterHandler(characterHandler);
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/HtmlSerializer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/HtmlSerializer.java
new file mode 100644
index 000000000..3312398d5
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/HtmlSerializer.java
@@ -0,0 +1,269 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2011 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.sax;
+
+import java.io.IOException;
+import java.io.OutputStream;
+import java.io.OutputStreamWriter;
+import java.io.UnsupportedEncodingException;
+import java.io.Writer;
+import java.util.Arrays;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.ext.LexicalHandler;
+
+public class HtmlSerializer implements ContentHandler, LexicalHandler {
+
+    private static final String[] VOID_ELEMENTS = { "area", "base", "basefont",
+            "bgsound", "br", "col", "command", "embed", "frame", "hr", "img",
+            "input", "keygen", "link", "meta", "param", "source", "track",
+            "wbr" };
+
+    private static final String[] NON_ESCAPING = { "iframe", "noembed",
+            "noframes", "noscript", "plaintext", "script", "style", "xmp" };
+
+    private static Writer wrap(OutputStream out) {
+        try {
+            return new OutputStreamWriter(out, "UTF-8");
+        } catch (UnsupportedEncodingException e) {
+            throw new RuntimeException(e);
+        }
+    }
+
+    private int ignoreLevel = 0;
+
+    private int escapeLevel = 0;
+
+    private final Writer writer;
+
+    public HtmlSerializer(OutputStream out) {
+        this(wrap(out));
+    }
+
+    public HtmlSerializer(Writer out) {
+        this.writer = out;
+    }
+
+    public void characters(char[] ch, int start, int length)
+            throws SAXException {
+        try {
+            if (escapeLevel > 0) {
+                writer.write(ch, start, length);
+            } else {
+                for (int i = start; i < start + length; i++) {
+                    char c = ch[i];
+                    switch (c) {
+                        case '<':
+                            writer.write("&lt;");
+                            break;
+                        case '>':
+                            writer.write("&gt;");
+                            break;
+                        case '&':
+                            writer.write("&amp;");
+                            break;
+                        case '\u00A0':
+                            writer.write("&nbsp;");
+                            break;
+                        default:
+                            writer.write(c);
+                            break;
+                    }
+                }
+            }
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public void endDocument() throws SAXException {
+        try {
+            writer.flush();
+            writer.close();
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public void endElement(String uri, String localName, String qName)
+            throws SAXException {
+        if (escapeLevel > 0) {
+            escapeLevel--;
+        }
+        if (ignoreLevel > 0) {
+            ignoreLevel--;
+        } else {
+            try {
+                writer.write('<');
+                writer.write('/');
+                writer.write(localName);
+                writer.write('>');
+            } catch (IOException e) {
+                throw new SAXException(e);
+            }
+        }
+    }
+
+    public void ignorableWhitespace(char[] ch, int start, int length)
+            throws SAXException {
+        characters(ch, start, length);
+    }
+
+    public void processingInstruction(String target, String data)
+            throws SAXException {
+    }
+
+    public void setDocumentLocator(Locator locator) {
+    }
+
+    public void startDocument() throws SAXException {
+        try {
+            writer.write("<!DOCTYPE html>\n");
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public void startElement(String uri, String localName, String qName,
+            Attributes atts) throws SAXException {
+        if (escapeLevel > 0) {
+            escapeLevel++;
+        }
+        boolean xhtml = "http://www.w3.org/1999/xhtml".equals(uri);
+        if (ignoreLevel > 0
+                || !(xhtml || "http://www.w3.org/2000/svg".equals(uri) || "http://www.w3.org/1998/Math/MathML".equals(uri))) {
+            ignoreLevel++;
+            return;
+        }
+        try {
+            writer.write('<');
+            writer.write(localName);
+            for (int i = 0; i < atts.getLength(); i++) {
+                String attUri = atts.getURI(i);
+                String attLocal = atts.getLocalName(i);
+                if (attUri.length() == 0) {
+                    writer.write(' ');
+                } else if (!xhtml
+                        && "http://www.w3.org/1999/xlink".equals(attUri)) {
+                    writer.write(" xlink:");
+                } else if ("http://www.w3.org/XML/1998/namespace".equals(attUri)) {
+                    if (xhtml) {
+                        if ("lang".equals(attLocal)) {
+                            writer.write(' ');
+                        } else {
+                            continue;
+                        }
+                    } else {
+                        writer.write(" xml:");
+                    }
+                } else {
+                    continue;
+                }
+                writer.write(atts.getLocalName(i));
+                writer.write('=');
+                writer.write('"');
+                String val = atts.getValue(i);
+                for (int j = 0; j < val.length(); j++) {
+                    char c = val.charAt(j);
+                    switch (c) {
+                        case '"':
+                            writer.write("&quot;");
+                            break;
+                        case '&':
+                            writer.write("&amp;");
+                            break;
+                        case '\u00A0':
+                            writer.write("&nbsp;");
+                            break;
+                        default:
+                            writer.write(c);
+                            break;
+                    }
+                }
+                writer.write('"');
+            }
+            writer.write('>');
+            if (Arrays.binarySearch(VOID_ELEMENTS, localName) > -1) {
+                ignoreLevel++;
+                return;
+            }
+            if ("pre".equals(localName) || "textarea".equals(localName)
+                    || "listing".equals(localName)) {
+                writer.write('\n');
+            }
+            if (escapeLevel == 0
+                    && Arrays.binarySearch(NON_ESCAPING, localName) > -1) {
+                escapeLevel = 1;
+            }
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public void comment(char[] ch, int start, int length) throws SAXException {
+        if (ignoreLevel > 0 || escapeLevel > 0) {
+            return;
+        }
+        try {
+            writer.write("<!--");
+            writer.write(ch, start, length);
+            writer.write("-->");
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public void endCDATA() throws SAXException {
+    }
+
+    public void endDTD() throws SAXException {
+    }
+
+    public void endEntity(String name) throws SAXException {
+    }
+
+    public void startCDATA() throws SAXException {
+    }
+
+    public void startDTD(String name, String publicId, String systemId)
+            throws SAXException {
+    }
+
+    public void startEntity(String name) throws SAXException {
+    }
+
+    public void startPrefixMapping(String prefix, String uri)
+            throws SAXException {
+    }
+
+    public void endPrefixMapping(String prefix) throws SAXException {
+    }
+
+    public void skippedEntity(String name) throws SAXException {
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/InfosetCoercingHtmlParser.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/InfosetCoercingHtmlParser.java
new file mode 100644
index 000000000..33e98dbe8
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/InfosetCoercingHtmlParser.java
@@ -0,0 +1,47 @@
+/*
+ * Copyright (c) 2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.sax;
+
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+
+/**
+ * This subclass of <code>HtmlParser</code> simply provides a no-argument
+ * constructor that calls the constructor of the superclass with the
+ * <code>ALTER_INFOSET</code> policy. This is convenient when another Java
+ * component wants an implementation of <code>XMLReader</code> with a 
+ * no-argument constructor and infoset coercion is the wanted behavior.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public class InfosetCoercingHtmlParser extends HtmlParser {
+
+    /**
+     * A constructor that passes <code>ALTER_INFOSET</code> to the superclass'
+     * constructor.
+     */
+    public InfosetCoercingHtmlParser() {
+        super(XmlViolationPolicy.ALTER_INFOSET);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java
new file mode 100644
index 000000000..b6cb2f872
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java
@@ -0,0 +1,51 @@
+/*
+ * Copyright (c) 2009 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.sax;
+
+import java.io.OutputStream;
+import java.io.Writer;
+
+import nu.validator.htmlparser.impl.NCName;
+
+import org.xml.sax.SAXException;
+
+public class NameCheckingXmlSerializer extends XmlSerializer {
+
+    public NameCheckingXmlSerializer(OutputStream out) {
+        super(out);
+    }
+
+    public NameCheckingXmlSerializer(Writer out) {
+        super(out);
+    }
+
+    /**
+     * @see nu.validator.htmlparser.sax.XmlSerializer#checkNCName()
+     */
+    @Override protected void checkNCName(String name) throws SAXException {
+        if (!NCName.isNCName(name)) {
+            throw new SAXException("Not an XML 1.0 4th ed. NCName: " + name);
+        }
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/SAXStreamer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/SAXStreamer.java
new file mode 100644
index 000000000..07ff5da4a
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/SAXStreamer.java
@@ -0,0 +1,196 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2009 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.sax;
+
+import nu.validator.htmlparser.impl.HtmlAttributes;
+import nu.validator.htmlparser.impl.TreeBuilder;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+import org.xml.sax.ext.LexicalHandler;
+
+class SAXStreamer extends TreeBuilder<Attributes>{
+
+    private static final char[] ISINDEX_PROMPT = "This is a searchable index. Enter search keywords: ".toCharArray();
+
+    private ContentHandler contentHandler = null;
+    private LexicalHandler lexicalHandler = null;
+    
+    SAXStreamer() {
+        super();
+    }
+    
+    @Override
+    protected void addAttributesToElement(Attributes element, HtmlAttributes attributes) throws SAXException {
+        Attributes existingAttrs = element;
+        for (int i = 0; i < attributes.getLength(); i++) {
+            String qName = attributes.getQNameNoBoundsCheck(i);
+            if (existingAttrs.getIndex(qName) < 0) {
+                fatal();
+            }
+        }
+    }
+
+    @Override
+    protected void appendCharacters(Attributes parent, char[] buf, int start, int length) throws SAXException {
+        contentHandler.characters(buf, start, length);
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendIsindexPrompt(java.lang.Object)
+     */
+    @Override protected void appendIsindexPrompt(Attributes parent)
+            throws SAXException {
+        contentHandler.characters(ISINDEX_PROMPT, 0, ISINDEX_PROMPT.length);
+    }
+
+    @Override
+    protected void appendChildrenToNewParent(Attributes oldParent, Attributes newParent) throws SAXException {
+        fatal();
+    }
+
+    @Override
+    protected void appendComment(Attributes parent, char[] buf, int start, int length) throws SAXException {
+        if (lexicalHandler != null) {
+            lexicalHandler.comment(buf, start, length);
+        }
+    }
+
+    @Override
+    protected void appendCommentToDocument(char[] buf, int start, int length)
+            throws SAXException {
+        if (lexicalHandler != null) {
+            lexicalHandler.comment(buf, start, length);
+        }
+    }
+
+    @Override
+    protected Attributes createElement(String ns, String name, HtmlAttributes attributes, Attributes intendedParent) throws SAXException {
+        return attributes;
+    }
+
+    @Override
+    protected Attributes createHtmlElementSetAsRoot(HtmlAttributes attributes) throws SAXException {
+        return attributes;
+    }
+
+    @Override
+    protected void detachFromParent(Attributes element) throws SAXException {
+        fatal();
+    }
+
+    @Override
+    protected void appendElement(Attributes child, Attributes newParent) throws SAXException {
+    }
+
+    @Override
+    protected boolean hasChildren(Attributes element) throws SAXException {
+        return false;
+    }
+    
+    public void setContentHandler(ContentHandler handler) {
+        contentHandler = handler;
+    }
+
+    public void setLexicalHandler(LexicalHandler handler) {
+        lexicalHandler = handler;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendDoctypeToDocument(java.lang.String, java.lang.String, java.lang.String)
+     */
+    @Override
+    protected void appendDoctypeToDocument(String name, String publicIdentifier, String systemIdentifier) throws SAXException {
+        if (lexicalHandler != null) {
+            lexicalHandler.startDTD(name, publicIdentifier, systemIdentifier);
+            lexicalHandler.endDTD();
+        }
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#elementPopped(String, java.lang.String, java.lang.Object)
+     */
+    @Override
+    protected void elementPopped(String ns, String name, Attributes node) throws SAXException {
+        contentHandler.endElement(ns, name, name);
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#elementPushed(String, java.lang.String, java.lang.Object)
+     */
+    @Override
+    protected void elementPushed(String ns, String name, Attributes node) throws SAXException {
+        contentHandler.startElement(ns, name, name, node);
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#end()
+     */
+    @Override
+    protected void end() throws SAXException {
+        contentHandler.endDocument();
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#start()
+     */
+    @Override
+    protected void start(boolean fragment) throws SAXException {
+        contentHandler.setDocumentLocator(tokenizer);
+        if (!fragment) {
+            contentHandler.startDocument();
+        }
+    }
+
+    protected void fatal() throws SAXException {
+        SAXParseException spe = new SAXParseException(
+                "Cannot recover after last error. Any further errors will be ignored.",
+                tokenizer);
+        if (errorHandler != null) {
+            errorHandler.fatalError(spe);
+        }
+        throw spe;
+    }
+
+    @Override
+    protected Attributes createAndInsertFosterParentedElement(String ns, String name,
+            HtmlAttributes attributes, Attributes table, Attributes stackParent) throws SAXException {
+        fatal();
+        throw new RuntimeException("Unreachable");
+    }
+
+    @Override protected void insertFosterParentedCharacters(char[] buf,
+            int start, int length, Attributes table, Attributes stackParent)
+            throws SAXException {
+        fatal();
+    }
+
+    @Override protected void insertFosterParentedChild(Attributes child,
+            Attributes table, Attributes stackParent) throws SAXException {
+        fatal();
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/SAXTreeBuilder.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/SAXTreeBuilder.java
new file mode 100644
index 000000000..ef51d2a51
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/SAXTreeBuilder.java
@@ -0,0 +1,210 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.sax;
+
+import nu.validator.htmlparser.impl.HtmlAttributes;
+import nu.validator.htmlparser.impl.TreeBuilder;
+import nu.validator.saxtree.Characters;
+import nu.validator.saxtree.Comment;
+import nu.validator.saxtree.DTD;
+import nu.validator.saxtree.Document;
+import nu.validator.saxtree.DocumentFragment;
+import nu.validator.saxtree.Element;
+import nu.validator.saxtree.Node;
+import nu.validator.saxtree.ParentNode;
+
+import org.xml.sax.SAXException;
+
+class SAXTreeBuilder extends TreeBuilder<Element> {
+
+    private static final char[] ISINDEX_PROMPT = "This is a searchable index. Enter search keywords: ".toCharArray();
+
+    private Document document;
+
+    private Node cachedTable = null;
+    
+    private Node cachedTablePreviousSibling = null;
+    
+    SAXTreeBuilder() {
+        super();
+    }
+    
+    @Override
+    protected void appendComment(Element parent, char[] buf, int start, int length) {
+        parent.appendChild(new Comment(tokenizer, buf, start, length));
+    }
+
+    @Override
+    protected void appendCommentToDocument(char[] buf, int start, int length) {
+        document.appendChild(new Comment(tokenizer, buf, start, length));
+    }
+
+    @Override
+    protected void appendCharacters(Element parent, char[] buf, int start, int length) {
+        parent.appendChild(new Characters(tokenizer, buf, start, length));
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendIsindexPrompt(java.lang.Object)
+     */
+    @Override protected void appendIsindexPrompt(Element parent)
+            throws SAXException {
+        parent.appendChild(new Characters(tokenizer, ISINDEX_PROMPT, 0, ISINDEX_PROMPT.length));
+    }
+
+    @Override
+    protected boolean hasChildren(Element element) {
+        return element.getFirstChild() != null;
+    }
+
+    @Override
+    protected void appendElement(Element child, Element newParent) {
+        newParent.appendChild(child);
+    }
+
+    @Override
+    protected Element createHtmlElementSetAsRoot(HtmlAttributes attributes) {
+        Element newElt = new Element(tokenizer, "http://www.w3.org/1999/xhtml", "html", "html", attributes, true, null);
+        document.appendChild(newElt);
+        return newElt;
+    }
+
+    @Override
+    protected void addAttributesToElement(Element element, HtmlAttributes attributes) throws SAXException {
+        HtmlAttributes existingAttrs = (HtmlAttributes) element.getAttributes();
+        existingAttrs.merge(attributes);
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#appendDoctypeToDocument(java.lang.String, java.lang.String, java.lang.String)
+     */
+    @Override
+    protected void appendDoctypeToDocument(String name, String publicIdentifier, String systemIdentifier) {
+         DTD dtd = new DTD(tokenizer, name, publicIdentifier, systemIdentifier);
+         dtd.setEndLocator(tokenizer);
+         document.appendChild(dtd);
+    }
+    
+    /**
+     * Returns the document.
+     * 
+     * @return the document
+     */
+    Document getDocument() {
+        Document rv = document;
+        document = null;
+        return rv;
+    }
+    
+    DocumentFragment getDocumentFragment() {
+        DocumentFragment rv = new DocumentFragment();
+        rv.appendChildren(document.getFirstChild());
+        document = null;
+        return rv;
+    }
+
+    /**
+     * @throws SAXException 
+     * @see nu.validator.htmlparser.impl.TreeBuilder#end()
+     */
+    @Override
+    protected void end() throws SAXException {
+        document.setEndLocator(tokenizer);
+        cachedTable = null;
+        cachedTablePreviousSibling = null;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#start()
+     */
+    @Override
+    protected void start(boolean fragment) {
+        document = new Document(tokenizer);
+        cachedTable = null;
+        cachedTablePreviousSibling = null;
+    }
+
+    @Override
+    protected void appendChildrenToNewParent(Element oldParent, Element newParent) throws SAXException {
+        newParent.appendChildren(oldParent);
+    }
+
+    @Override
+    protected Element createElement(String ns, String name, HtmlAttributes attributes,
+            Element intendedParent) throws SAXException {
+        return new Element(tokenizer, ns, name, name, attributes, true, null);
+    }
+
+    @Override
+    protected Element createAndInsertFosterParentedElement(String ns, String name,
+            HtmlAttributes attributes, Element table, Element stackParent) throws SAXException {
+        ParentNode parent = table.getParentNode();
+        Element child = createElement(ns, name, attributes, parent != null ? (Element) parent : stackParent);
+        if (parent != null) { // always an element if not null
+            parent.insertBetween(child, previousSibling(table), table);
+            cachedTablePreviousSibling = child;
+        } else {
+            stackParent.appendChild(child);
+        }
+
+        return child;
+    }
+
+    @Override protected void insertFosterParentedCharacters(char[] buf,
+            int start, int length, Element table, Element stackParent) throws SAXException {
+        Node child = new Characters(tokenizer, buf, start, length);
+        ParentNode parent = table.getParentNode();
+        if (parent != null) { // always an element if not null
+            parent.insertBetween(child, previousSibling(table), table);
+            cachedTablePreviousSibling = child;
+        } else {
+            stackParent.appendChild(child);
+        }        
+    }
+
+    @Override protected void insertFosterParentedChild(Element child,
+            Element table, Element stackParent) throws SAXException {
+        ParentNode parent = table.getParentNode();
+        if (parent != null) { // always an element if not null
+            parent.insertBetween(child, previousSibling(table), table);
+            cachedTablePreviousSibling = child;
+        } else {
+            stackParent.appendChild(child);
+        }
+    }
+
+    private Node previousSibling(Node table) {
+        if (table == cachedTable) {
+            return cachedTablePreviousSibling;   
+        } else {
+            cachedTable = table;
+            return (cachedTablePreviousSibling = table.getPreviousSibling());
+        }
+    }
+
+    @Override protected void detachFromParent(Element element)
+            throws SAXException {
+        element.detach();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/XmlSerializer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/XmlSerializer.java
new file mode 100644
index 000000000..5dccf5d3a
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/XmlSerializer.java
@@ -0,0 +1,737 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2009 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.sax;
+
+import java.io.IOException;
+import java.io.OutputStream;
+import java.io.OutputStreamWriter;
+import java.io.UnsupportedEncodingException;
+import java.io.Writer;
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetEncoder;
+import java.nio.charset.CodingErrorAction;
+import java.util.HashMap;
+import java.util.HashSet;
+import java.util.LinkedList;
+import java.util.Map;
+import java.util.Set;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.ext.LexicalHandler;
+
+public class XmlSerializer implements ContentHandler, LexicalHandler {
+
+    private final class PrefixMapping {
+        public final String uri;
+
+        public final String prefix;
+
+        /**
+         * @param uri
+         * @param prefix
+         */
+        public PrefixMapping(String uri, String prefix) {
+            this.uri = uri;
+            this.prefix = prefix;
+        }
+
+        /**
+         * @see java.lang.Object#equals(java.lang.Object)
+         */
+        @Override public final boolean equals(Object obj) {
+            if (obj instanceof PrefixMapping) {
+                PrefixMapping other = (PrefixMapping) obj;
+                return this.prefix.equals(other.prefix);
+            } else {
+                return false;
+            }
+        }
+
+        /**
+         * @see java.lang.Object#hashCode()
+         */
+        @Override public final int hashCode() {
+            return prefix.hashCode();
+        }
+
+    }
+
+    private final class StackNode {
+        public final String uri;
+
+        public final String prefix;
+
+        public final String qName;
+
+        public final Set<PrefixMapping> mappings = new HashSet<PrefixMapping>();
+
+        /**
+         * @param uri
+         * @param qName
+         */
+        public StackNode(String uri, String qName, String prefix) {
+            this.uri = uri;
+            this.qName = qName;
+            this.prefix = prefix;
+        }
+    }
+
+    private final static Map<String, String> WELL_KNOWN_ATTRIBUTE_PREFIXES = new HashMap<String, String>();
+
+    static {
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("adobe:ns:meta/", "x");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://inkscape.sourceforge.net/DTD/sodipodi-0.dtd",
+                "sodipodi");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://ns.adobe.com/AdobeIllustrator/10.0/", "i");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://ns.adobe.com/AdobeSVGViewerExtensions/3.0/", "a");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://ns.adobe.com/Extensibility/1.0/", "x");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://ns.adobe.com/illustrator/1.0/", "illustrator");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://ns.adobe.com/pdf/1.3/", "pdf");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://ns.adobe.com/photoshop/1.0/",
+                "photoshop");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://ns.adobe.com/tiff/1.0/",
+                "tiff");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://ns.adobe.com/xap/1.0/", "xap");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://ns.adobe.com/xap/1.0/g/",
+                "xapG");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://ns.adobe.com/xap/1.0/mm/",
+                "xapMM");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://ns.adobe.com/xap/1.0/rights/", "xapRights");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://ns.adobe.com/xap/1.0/sType/Dimensions#", "stDim");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://ns.adobe.com/xap/1.0/sType/ResourceRef#", "stRef");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://ns.adobe.com/xap/1.0/t/pg/",
+                "xapTPg");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://purl.org/dc/elements/1.1/",
+                "dc");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://schemas.microsoft.com/visio/2003/SVGExtensions/", "v");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd",
+                "sodipodi");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://w3.org/1999/xlink", "xlink");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://www.carto.net/attrib/",
+                "attrib");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://www.iki.fi/pav/software/textext/", "textext");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://www.inkscape.org/namespaces/inkscape", "inkscape");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://www.justsystem.co.jp/hanako13/svg", "jsh");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://www.w3.org/1999/02/22-rdf-syntax-ns#", "rdf");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://www.w3.org/1999/xlink",
+                "xlink");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put(
+                "http://www.w3.org/2001/XMLSchema-instance", "xsi");
+        WELL_KNOWN_ATTRIBUTE_PREFIXES.put("http://www.w3.org/1999/xlink",
+                "xlink");
+    }
+
+    private final static Map<String, String> WELL_KNOWN_ELEMENT_PREFIXES = new HashMap<String, String>();
+
+    static {
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://www.w3.org/1999/XSL/Transform",
+                "xsl");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://www.w3.org/1999/02/22-rdf-syntax-ns#", "rdf");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://purl.org/dc/elements/1.1/",
+                "dc");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://www.w3.org/2001/XMLSchema-instance", "xsi");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://www.ascc.net/xml/schematron",
+                "sch");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://purl.oclc.org/dsdl/schematron",
+                "sch");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://www.inkscape.org/namespaces/inkscape", "inkscape");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd",
+                "sodipodi");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://ns.adobe.com/AdobeSVGViewerExtensions/3.0/", "a");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://ns.adobe.com/AdobeIllustrator/10.0/", "i");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("adobe:ns:meta/", "x");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/xap/1.0/", "xap");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/pdf/1.3/", "pdf");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/tiff/1.0/", "tiff");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://creativecommons.org/ns#", "cc");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://inkscape.sourceforge.net/DTD/sodipodi-0.dtd",
+                "sodipodi");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://iptc.org/std/Iptc4xmpCore/1.0/xmlns/", "Iptc4xmpCore");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/exif/1.0/", "exif");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://ns.adobe.com/Extensibility/1.0/", "x");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/illustrator/1.0/",
+                "illustrator");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/pdfx/1.3/", "pdfx");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/photoshop/1.0/",
+                "photoshop");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/Variables/1.0/",
+                "v");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/xap/1.0/g/",
+                "xapG");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/xap/1.0/g/img/",
+                "xapGImg");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/xap/1.0/mm/",
+                "xapMM");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/xap/1.0/rights/",
+                "xapRights");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://ns.adobe.com/xap/1.0/sType/Dimensions#", "stDim");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://ns.adobe.com/xap/1.0/sType/Font#", "stFnt");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://ns.adobe.com/xap/1.0/sType/ResourceRef#", "stRef");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://ns.adobe.com/xap/1.0/t/pg/",
+                "xapTPg");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://product.corel.com/CGS/11/cddns/", "odm");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://schemas.microsoft.com/visio/2003/SVGExtensions/", "v");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://web.resource.org/cc/", "cc");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://www.freesoftware.fsf.org/bkchem/cdml", "cdml");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://www.opengis.net/gml", "gml");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://www.svgmaker.com/svgns",
+                "svgmaker");
+        WELL_KNOWN_ELEMENT_PREFIXES.put(
+                "http://www.w3.org/2000/01/rdf-schema#", "rdfs");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://xmlns.com/foaf/0.1/", "foaf");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://www.xml-cml.org/schema/stmml",
+                "stm");
+        WELL_KNOWN_ELEMENT_PREFIXES.put("http://www.iupac.org/foo/ichi", "ichi");
+    }
+
+    private final static Writer wrap(OutputStream out) {
+        Charset charset = Charset.forName("utf-8");
+        CharsetEncoder encoder = charset.newEncoder();
+        encoder.onMalformedInput(CodingErrorAction.REPLACE);
+        encoder.onUnmappableCharacter(CodingErrorAction.REPLACE);
+        try {
+            encoder.replaceWith("\uFFFD".getBytes("utf-8"));
+        } catch (UnsupportedEncodingException e) {
+            throw new RuntimeException(e);
+        }
+        return new OutputStreamWriter(out, encoder);
+    }
+
+    // grows from head
+    private final LinkedList<StackNode> stack = new LinkedList<StackNode>();
+
+    private final Writer writer;
+
+    public XmlSerializer(OutputStream out) {
+        this(wrap(out));
+    }
+
+    public XmlSerializer(Writer out) {
+        this.writer = out;
+    }
+    
+    protected void checkNCName(String name) throws SAXException {
+        
+    }
+
+    private final void push(String uri, String local, String prefix) {
+        stack.addFirst(new StackNode(uri, local, prefix));
+    }
+
+    private final String pop() {
+        String rv = stack.removeFirst().qName;
+        stack.getFirst().mappings.clear();
+        return rv;
+    }
+
+    private final String lookupPrefixAttribute(String ns) {
+        if ("http://www.w3.org/XML/1998/namespace".equals(ns)) {
+            return "xml";
+        }
+        Set<String> hidden = new HashSet<String>();
+        for (StackNode node : stack) {
+            for (PrefixMapping mapping : node.mappings) {
+                if (mapping.prefix.length() != 0 && mapping.uri.equals(ns)
+                        && !hidden.contains(mapping.prefix)) {
+                    return mapping.prefix;
+                }
+                hidden.add(mapping.prefix);
+            }
+        }
+        return null;
+    }
+
+    private final String lookupUri(String prefix) {
+        for (StackNode node : stack) {
+            for (PrefixMapping mapping : node.mappings) {
+                if (mapping.prefix.equals(prefix)) {
+                    return mapping.uri;
+                }
+            }
+        }
+        return null;
+    }
+
+    private final boolean xmlNsQname(String name) {
+        if (name == null) {
+            return false;
+        } else if ("xmlns".equals(name)) {
+            return true;
+        } else if (name.startsWith("xmlns:")) {
+            return true;
+        } else {
+            return false;
+        }
+    }
+
+    private final void writeAttributeValue(String val) throws IOException {
+        boolean prevWasSpace = true;
+        int last = val.length() - 1;
+        for (int i = 0; i <= last; i++) {
+            char c = val.charAt(i);
+            switch (c) {
+                case '<':
+                    writer.write("&lt;");
+                    prevWasSpace = false;
+                    break;
+                case '>':
+                    writer.write("&gt;");
+                    prevWasSpace = false;
+                    break;
+                case '&':
+                    writer.write("&amp;");
+                    prevWasSpace = false;
+                    break;
+                case '"':
+                    writer.write("&quot;");
+                    prevWasSpace = false;
+                    break;
+                case '\r':
+                    writer.write("&#xD;");
+                    prevWasSpace = false;
+                    break;
+                case '\t':
+                    writer.write("&#x9;");
+                    prevWasSpace = false;
+                    break;
+                case '\n':
+                    writer.write("&#xA;");
+                    prevWasSpace = false;
+                    break;
+                case ' ':
+                    if (prevWasSpace || i == last) {
+                        writer.write("&#x20;");
+                        prevWasSpace = false;
+                    } else {
+                        writer.write(' ');
+                        prevWasSpace = true;
+                    }
+                    break;
+                case '\uFFFE':
+                    writer.write('\uFFFD');
+                    prevWasSpace = false;
+                    break;
+                case '\uFFFF':
+                    writer.write('\uFFFD');
+                    prevWasSpace = false;
+                    break;
+                default:
+                    if (c < ' ') {
+                        writer.write('\uFFFD');
+                    } else {
+                        writer.write(c);
+                    }
+                    prevWasSpace = false;
+                    break;
+            }
+        }
+    }
+
+    private final void generatePrefix(String uri) throws SAXException {
+        int counter = 0;
+        String candidate = WELL_KNOWN_ATTRIBUTE_PREFIXES.get(uri);
+        if (candidate == null) {
+            candidate = "p" + (counter++);
+        }
+        while (lookupUri(candidate) != null) {
+            candidate = "p" + (counter++);
+        }
+        startPrefixMappingPrivate(candidate, uri);
+    }
+
+    public final void characters(char[] ch, int start, int length)
+            throws SAXException {
+        try {
+            for (int i = start; i < start + length; i++) {
+                char c = ch[i];
+                switch (c) {
+                    case '<':
+                        writer.write("&lt;");
+                        break;
+                    case '>':
+                        writer.write("&gt;");
+                        break;
+                    case '&':
+                        writer.write("&amp;");
+                        break;
+                    case '\r':
+                        writer.write("&#xD;");
+                        break;
+                    case '\t':
+                        writer.write('\t');
+                        break;
+                    case '\n':
+                        writer.write('\n');
+                        break;
+                    case '\uFFFE':
+                        writer.write('\uFFFD');
+                        break;
+                    case '\uFFFF':
+                        writer.write('\uFFFD');
+                        break;
+                    default:
+                        if (c < ' ') {
+                            writer.write('\uFFFD');
+                        } else {
+                            writer.write(c);
+                        }
+                        break;
+                }
+            }
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public final void endDocument() throws SAXException {
+        try {
+            stack.clear();
+            writer.flush();
+            writer.close();
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public final void endElement(String uri, String localName, String qName)
+            throws SAXException {
+        try {
+            writer.write('<');
+            writer.write('/');
+            writer.write(pop());
+            writer.write('>');
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public final void ignorableWhitespace(char[] ch, int start, int length)
+            throws SAXException {
+        characters(ch, start, length);
+    }
+
+    public final void processingInstruction(String target, String data)
+            throws SAXException {
+        try {
+            checkNCName(target);
+            writer.write("<?");
+            writer.write(target);
+            writer.write(' ');
+            boolean prevWasQuestionmark = false;
+            for (int i = 0; i < data.length(); i++) {
+                char c = data.charAt(i);
+                switch (c) {
+                    case '?':
+                        writer.write('?');
+                        prevWasQuestionmark = true;
+                        break;
+                    case '>':
+                        if (prevWasQuestionmark) {
+                            writer.write(" >");
+                        } else {
+                            writer.write('>');
+                        }
+                        prevWasQuestionmark = false;
+                        break;
+                    case '\t':
+                        writer.write('\t');
+                        prevWasQuestionmark = false;
+                        break;
+                    case '\r':
+                    case '\n':
+                        writer.write('\n');
+                        prevWasQuestionmark = false;
+                        break;
+                    case '\uFFFE':
+                        writer.write('\uFFFD');
+                        prevWasQuestionmark = false;
+                        break;
+                    case '\uFFFF':
+                        writer.write('\uFFFD');
+                        prevWasQuestionmark = false;
+                        break;
+                    default:
+                        if (c < ' ') {
+                            writer.write('\uFFFD');
+                        } else {
+                            writer.write(c);
+                        }
+                        prevWasQuestionmark = false;
+                        break;
+                }
+            }
+            writer.write("?>");
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public final void setDocumentLocator(Locator locator) {
+    }
+
+    public final void startDocument() throws SAXException {
+        try {
+            writer.write("<?xml version='1.0' encoding='utf-8'?>\n");
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+        stack.clear();
+        push(null, null, null);
+    }
+
+    public final void startElement(String uri, String localName, String q,
+            Attributes atts) throws SAXException {
+        checkNCName(localName);
+        String prefix;
+        String qName;
+        if (uri.length() == 0) {
+            prefix = "";
+            qName = localName;
+            // generate xmlns
+            startPrefixMappingPrivate(prefix, uri);
+        } else {
+            prefix = WELL_KNOWN_ELEMENT_PREFIXES.get(uri);
+            if (prefix == null) {
+                prefix = "";
+            }
+            String lookup = lookupUri(prefix);
+            if (lookup != null && !lookup.equals(uri)) {
+                prefix = "";
+            }
+            startPrefixMappingPrivate(prefix, uri);
+            if (prefix.length() == 0) {
+                qName = localName;
+            } else {
+                qName = prefix + ':' + localName;
+            }
+        }
+
+        int attLen = atts.getLength();
+        for (int i = 0; i < attLen; i++) {
+            String attUri = atts.getURI(i);
+            if (attUri.length() == 0
+                    || "http://www.w3.org/XML/1998/namespace".equals(attUri)
+                    || "http://www.w3.org/2000/xmlns/".equals(attUri)
+                    || atts.getLocalName(i).length() == 0
+                    || xmlNsQname(atts.getQName(i))) {
+                continue;
+            }
+            if (lookupPrefixAttribute(attUri) == null) {
+                generatePrefix(attUri);
+            }
+        }
+
+        try {
+            writer.write('<');
+            writer.write(qName);
+            for (PrefixMapping mapping : stack.getFirst().mappings) {
+                writer.write(' ');
+                if (mapping.prefix.length() == 0) {
+                    writer.write("xmlns");
+                } else {
+                    writer.write("xmlns:");
+                    writer.write(mapping.prefix);
+                }
+                writer.write('=');
+                writer.write('"');
+                writeAttributeValue(mapping.uri);
+                writer.write('"');
+            }
+
+            for (int i = 0; i < attLen; i++) {
+                String attUri = atts.getURI(i);
+                if ("http://www.w3.org/XML/1998/namespace".equals(attUri)
+                        || "http://www.w3.org/2000/xmlns/".equals(attUri)
+                        || atts.getLocalName(i).length() == 0
+                        || xmlNsQname(atts.getQName(i))) {
+                    continue;
+                }
+                writer.write(' ');
+                if (attUri.length() != 0) {
+                    writer.write(lookupPrefixAttribute(attUri));
+                    writer.write(':');
+                }
+                String attLocal = atts.getLocalName(i);
+                checkNCName(attLocal);
+                writer.write(attLocal);
+                writer.write('=');
+                writer.write('"');
+                writeAttributeValue(atts.getValue(i));
+                writer.write('"');
+            }
+            writer.write('>');
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+        push(uri, qName, prefix);
+    }
+
+    public final void comment(char[] ch, int start, int length) throws SAXException {
+        try {
+            boolean prevWasHyphen = false;
+            writer.write("<!--");
+            for (int i = start; i < start + length; i++) {
+                char c = ch[i];
+                switch (c) {
+                    case '-':
+                        if (prevWasHyphen) {
+                            writer.write(" -");
+                        } else {
+                            writer.write('-');
+                            prevWasHyphen = true;
+                        }
+                        break;
+                    case '\t':
+                        writer.write('\t');
+                        prevWasHyphen = false;
+                        break;
+                    case '\r':
+                    case '\n':
+                        writer.write('\n');
+                        prevWasHyphen = false;
+                        break;
+                    case '\uFFFE':
+                        writer.write('\uFFFD');
+                        prevWasHyphen = false;
+                        break;
+                    case '\uFFFF':
+                        writer.write('\uFFFD');
+                        prevWasHyphen = false;
+                        break;
+                    default:
+                        if (c < ' ') {
+                            writer.write('\uFFFD');
+                        } else {
+                            writer.write(c);
+                        }
+                        prevWasHyphen = false;
+                        break;
+                }
+            }
+            if (prevWasHyphen) {
+                writer.write(' ');
+            }
+            writer.write("-->");
+        } catch (IOException e) {
+            throw new SAXException(e);
+        }
+    }
+
+    public final void endCDATA() throws SAXException {
+    }
+
+    public final void endDTD() throws SAXException {
+    }
+
+    public final void endEntity(String name) throws SAXException {
+    }
+
+    public final void startCDATA() throws SAXException {
+    }
+
+    public final void startDTD(String name, String publicId, String systemId)
+            throws SAXException {
+    }
+
+    public final void startEntity(String name) throws SAXException {
+    }
+
+    public final void startPrefixMapping(String prefix, String uri)
+            throws SAXException {
+        if (prefix.length() == 0 || uri.equals(lookupUri(prefix))) {
+            return;
+        }
+        if (uri.equals(lookupUri(prefix))) {
+            return;
+        }
+        if ("http://www.w3.org/XML/1998/namespace".equals(uri)) {
+            if ("xml".equals(prefix)) {
+                return;
+            } else {
+                throw new SAXException("Attempt to declare a reserved NS uri.");
+            }
+        }
+        if ("http://www.w3.org/2000/xmlns/".equals(uri)) {
+            throw new SAXException("Attempt to declare a reserved NS uri.");
+        }
+        if (uri.length() == 0 && prefix.length() != 0) {
+            throw new SAXException("Can bind a prefix to no namespace.");           
+        }
+        checkNCName(prefix);
+        Set<PrefixMapping> theSet = stack.getFirst().mappings;
+        PrefixMapping mapping = new PrefixMapping(uri, prefix);
+        if (theSet.contains(mapping)) {
+            throw new SAXException(
+                    "Attempt to map one prefix to two URIs on one element.");
+        }
+        theSet.add(mapping);
+    }
+
+    public final void startPrefixMappingPrivate(String prefix, String uri)
+            throws SAXException {
+        if (uri.equals(lookupUri(prefix))) {
+            return;
+        }
+        stack.getFirst().mappings.add(new PrefixMapping(uri, prefix));
+    }
+
+    public final void endPrefixMapping(String prefix) throws SAXException {
+    }
+
+    public final void skippedEntity(String name) throws SAXException {
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/package.html b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/package.html
new file mode 100644
index 000000000..60532962f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/sax/package.html
@@ -0,0 +1,29 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
+<html>
+<head><title>Package Overview</title>
+<!--
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a 
+ copy of this software and associated documentation files (the "Software"), 
+ to deal in the Software without restriction, including without limitation 
+ the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ and/or sell copies of the Software, and to permit persons to whom the 
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in 
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ DEALINGS IN THE SOFTWARE.
+-->
+</head>
+<body bgcolor="white">
+<p>This package provides an HTML5 parser that exposes the document through the SAX API.</p>
+</body>
+</html>
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/FormPointer.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/FormPointer.java
new file mode 100644
index 000000000..6dcff5600
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/FormPointer.java
@@ -0,0 +1,49 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.xom;
+
+import nu.xom.Element;
+
+/**
+ * Interface for elements that have an associated form pointer.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface FormPointer {
+
+    /**
+     * Returns the form.
+     * 
+     * @return the form
+     */
+    public abstract Element getForm();
+
+    /**
+     * Sets the form.
+     * 
+     * @param form the form to set
+     */
+    public abstract void setForm(Element form);
+
+}
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/FormPtrElement.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/FormPtrElement.java
new file mode 100644
index 000000000..2e2e18df7
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/FormPtrElement.java
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.xom;
+
+import nu.xom.Element;
+
+/**
+ * Element with an associated form.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public class FormPtrElement extends Element implements FormPointer {
+
+    private Element form = null;
+    
+    /**
+     * Copy constructor (<code>FormPointer</code>-aware).
+     * @param elt
+     */
+    public FormPtrElement(Element elt) {
+        super(elt);
+        if (elt instanceof FormPointer) {
+            FormPointer other = (FormPointer) elt;
+            this.setForm(other.getForm());
+        }
+    }
+
+    /**
+     * Null form.
+     * 
+     * @param name
+     * @param uri
+     */
+    public FormPtrElement(String name, String uri) {
+        super(name, uri);
+    }
+
+    /**
+     * Full constructor.
+     * 
+     * @param name
+     * @param uri
+     * @param form
+     */
+    public FormPtrElement(String name, String uri, Element form) {
+        super(name, uri);
+        this.form = form;
+    }
+    
+    /**
+     * Gets the form.
+     * @see nu.validator.htmlparser.xom.FormPointer#getForm()
+     */
+    public Element getForm() {
+        return form;
+    }
+
+    /**
+     * Sets the form.
+     * @see nu.validator.htmlparser.xom.FormPointer#setForm(nu.xom.Element)
+     */
+    public void setForm(Element form) {
+        this.form = form;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/HtmlBuilder.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/HtmlBuilder.java
new file mode 100644
index 000000000..845ea15cf
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/HtmlBuilder.java
@@ -0,0 +1,773 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2007-2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.xom;
+
+import java.io.File;
+import java.io.FileInputStream;
+import java.io.IOException;
+import java.io.InputStream;
+import java.io.Reader;
+import java.io.StringReader;
+import java.net.MalformedURLException;
+import java.net.URL;
+import java.util.LinkedList;
+import java.util.List;
+
+import nu.validator.htmlparser.common.CharacterHandler;
+import nu.validator.htmlparser.common.DoctypeExpectation;
+import nu.validator.htmlparser.common.DocumentModeHandler;
+import nu.validator.htmlparser.common.Heuristics;
+import nu.validator.htmlparser.common.TokenHandler;
+import nu.validator.htmlparser.common.TransitionHandler;
+import nu.validator.htmlparser.common.XmlViolationPolicy;
+import nu.validator.htmlparser.impl.ErrorReportingTokenizer;
+import nu.validator.htmlparser.impl.Tokenizer;
+import nu.validator.htmlparser.io.Driver;
+import nu.xom.Builder;
+import nu.xom.Document;
+import nu.xom.Nodes;
+import nu.xom.ParsingException;
+import nu.xom.ValidityException;
+
+import org.xml.sax.EntityResolver;
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.InputSource;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+/**
+ * This class implements an HTML5 parser that exposes data through the XOM 
+ * interface. 
+ * 
+ * <p>By default, when using the constructor without arguments, the 
+ * this parser coerces XML 1.0-incompatible infosets into XML 1.0-compatible
+ * infosets. This corresponds to <code>ALTER_INFOSET</code> as the general 
+ * XML violation policy. It is possible to treat XML 1.0 infoset violations 
+ * as fatal by setting the general XML violation policy to <code>FATAL</code>. 
+ * 
+ * <p>The doctype is not represented in the tree.
+ * 
+ * <p>The document mode is represented via the <code>Mode</code> 
+ * interface on the <code>Document</code> node if the node implements 
+ * that interface (depends on the used node factory).
+ * 
+ * <p>The form pointer is stored if the node factory supports storing it.
+ * 
+ * <p>This package has its own node factory class because the official 
+ * XOM node factory may return multiple nodes instead of one confusing 
+ * the assumptions of the DOM-oriented HTML5 parsing algorithm.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public class HtmlBuilder extends Builder {
+
+    private Driver driver;
+
+    private final XOMTreeBuilder treeBuilder;
+
+    private final SimpleNodeFactory simpleNodeFactory;
+
+    private EntityResolver entityResolver;
+
+    private ErrorHandler errorHandler = null;
+
+    private DocumentModeHandler documentModeHandler = null;
+
+    private DoctypeExpectation doctypeExpectation = DoctypeExpectation.HTML;
+
+    private boolean checkingNormalization = false;
+
+    private boolean scriptingEnabled = false;
+
+    private final List<CharacterHandler> characterHandlers = new LinkedList<CharacterHandler>();
+    
+    private XmlViolationPolicy contentSpacePolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy contentNonXmlCharPolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy commentPolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy namePolicy = XmlViolationPolicy.FATAL;
+
+    private XmlViolationPolicy streamabilityViolationPolicy = XmlViolationPolicy.ALLOW;
+    
+    private boolean html4ModeCompatibleWithXhtml1Schemata = false;
+
+    private boolean mappingLangToXmlLang = false;
+
+    private XmlViolationPolicy xmlnsPolicy = XmlViolationPolicy.FATAL;
+    
+    private boolean reportingDoctype = true;
+
+    private ErrorHandler treeBuilderErrorHandler = null;
+
+    private Heuristics heuristics = Heuristics.NONE;
+
+    private TransitionHandler transitionHandler = null;
+    
+    /**
+     * Constructor with default node factory and fatal XML violation policy.
+     */
+    public HtmlBuilder() {
+        this(new SimpleNodeFactory(), XmlViolationPolicy.FATAL);
+    }
+    
+    /**
+     * Constructor with given node factory and fatal XML violation policy.
+     * @param nodeFactory the factory
+     */
+    public HtmlBuilder(SimpleNodeFactory nodeFactory) {
+        this(nodeFactory, XmlViolationPolicy.FATAL);
+    }
+
+    /**
+     * Constructor with default node factory and given XML violation policy.
+     * @param xmlPolicy the policy
+     */
+    public HtmlBuilder(XmlViolationPolicy xmlPolicy) {
+        this(new SimpleNodeFactory(), xmlPolicy);
+    }
+    
+    /**
+     * Constructor with given node factory and given XML violation policy.
+     * @param nodeFactory the factory
+     * @param xmlPolicy the policy
+     */
+    public HtmlBuilder(SimpleNodeFactory nodeFactory, XmlViolationPolicy xmlPolicy) {
+        super();
+        this.simpleNodeFactory = nodeFactory;
+        this.treeBuilder = new XOMTreeBuilder(nodeFactory);
+        this.driver = null;
+        setXmlPolicy(xmlPolicy);
+    }
+
+    private Tokenizer newTokenizer(TokenHandler handler, boolean newAttributesEachTime) {
+        if (errorHandler == null && transitionHandler == null
+                && contentNonXmlCharPolicy == XmlViolationPolicy.ALLOW) {
+            return new Tokenizer(handler, newAttributesEachTime);
+        } else {
+            return new ErrorReportingTokenizer(handler, newAttributesEachTime);
+        }
+   }
+    
+    /**
+     * This class wraps different tree builders depending on configuration. This 
+     * method does the work of hiding this from the user of the class.
+     */
+    private void lazyInit() {
+        if (driver == null) {
+            this.driver = new Driver(newTokenizer(treeBuilder, false));
+            this.driver.setErrorHandler(errorHandler);
+            this.driver.setTransitionHandler(transitionHandler);
+            this.treeBuilder.setErrorHandler(treeBuilderErrorHandler);
+            this.driver.setCheckingNormalization(checkingNormalization);
+            this.driver.setCommentPolicy(commentPolicy);
+            this.driver.setContentNonXmlCharPolicy(contentNonXmlCharPolicy);
+            this.driver.setContentSpacePolicy(contentSpacePolicy);
+            this.driver.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata);
+            this.driver.setMappingLangToXmlLang(mappingLangToXmlLang);
+            this.driver.setXmlnsPolicy(xmlnsPolicy);
+            this.driver.setHeuristics(heuristics);
+            for (CharacterHandler characterHandler : characterHandlers) {
+                this.driver.addCharacterHandler(characterHandler);
+            }
+            this.treeBuilder.setDoctypeExpectation(doctypeExpectation);
+            this.treeBuilder.setDocumentModeHandler(documentModeHandler);
+            this.treeBuilder.setScriptingEnabled(scriptingEnabled);
+            this.treeBuilder.setReportingDoctype(reportingDoctype);
+            this.treeBuilder.setNamePolicy(namePolicy);
+        }
+    }
+
+    
+    private void tokenize(InputSource is) throws ParsingException, IOException,
+            MalformedURLException {
+        try {
+            if (is == null) {
+                throw new IllegalArgumentException("Null input.");
+            }
+            if (is.getByteStream() == null && is.getCharacterStream() == null) {
+                String systemId = is.getSystemId();
+                if (systemId == null) {
+                    throw new IllegalArgumentException(
+                            "No byte stream, no character stream nor URI.");
+                }
+                if (entityResolver != null) {
+                    is = entityResolver.resolveEntity(is.getPublicId(),
+                            systemId);
+                }
+                if (is.getByteStream() == null
+                        || is.getCharacterStream() == null) {
+                    is = new InputSource();
+                    is.setSystemId(systemId);
+                    is.setByteStream(new URL(systemId).openStream());
+                }
+            }
+            driver.tokenize(is);
+        } catch (SAXParseException e) {
+            throw new ParsingException(e.getMessage(), e.getSystemId(), e.getLineNumber(),
+                    e.getColumnNumber(), e);
+        } catch (SAXException e) {
+            throw new ParsingException(e.getMessage(), e);
+        }
+    }
+
+    /**
+     * Parse from SAX <code>InputSource</code>.
+     * @param is the <code>InputSource</code>
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     */
+    public Document build(InputSource is) throws ParsingException, IOException {
+        lazyInit();
+        treeBuilder.setFragmentContext(null);
+        tokenize(is);
+        return treeBuilder.getDocument();
+    }
+
+    /**
+     * Parse a fragment from SAX <code>InputSource</code> assuming an HTML
+     * context.
+     * @param is the <code>InputSource</code>
+     * @param context the name of the context element (HTML namespace assumed)
+     * @return the fragment
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     */
+    public Nodes buildFragment(InputSource is, String context)
+            throws IOException, ParsingException {
+        lazyInit();
+        treeBuilder.setFragmentContext(context.intern());
+        tokenize(is);
+        return treeBuilder.getDocumentFragment();
+    }
+
+    /**
+     * Parse a fragment from SAX <code>InputSource</code>.
+     * @param is the <code>InputSource</code>
+     * @param contextLocal the local name of the context element
+     * @parem contextNamespace the namespace of the context element
+     * @return the fragment
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     */
+    public Nodes buildFragment(InputSource is, String contextLocal, String contextNamespace)
+            throws IOException, ParsingException {
+        lazyInit();
+        treeBuilder.setFragmentContext(contextLocal.intern(), contextNamespace.intern(), null, false);
+        tokenize(is);
+        return treeBuilder.getDocumentFragment();
+    }
+    
+    /**
+     * Parse from <code>File</code>.
+     * @param file the file
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     * @see nu.xom.Builder#build(java.io.File)
+     */
+    @Override
+    public Document build(File file) throws ParsingException,
+            ValidityException, IOException {
+        return build(new FileInputStream(file), file.toURI().toASCIIString());
+    }
+
+    /**
+     * Parse from <code>InputStream</code>.
+     * @param stream the stream
+     * @param uri the base URI
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     * @see nu.xom.Builder#build(java.io.InputStream, java.lang.String)
+     */
+    @Override
+    public Document build(InputStream stream, String uri)
+            throws ParsingException, ValidityException, IOException {
+        InputSource is = new InputSource(stream);
+        is.setSystemId(uri);
+        return build(is);
+    }
+
+    /**
+     * Parse from <code>InputStream</code>.
+     * @param stream the stream
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     * @see nu.xom.Builder#build(java.io.InputStream)
+     */
+    @Override
+    public Document build(InputStream stream) throws ParsingException,
+            ValidityException, IOException {
+        return build(new InputSource(stream));
+    }
+
+    /**
+     * Parse from <code>Reader</code>.
+     * @param stream the reader
+     * @param uri the base URI
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     * @see nu.xom.Builder#build(java.io.Reader, java.lang.String)
+     */
+    @Override
+    public Document build(Reader stream, String uri) throws ParsingException,
+            ValidityException, IOException {
+        InputSource is = new InputSource(stream);
+        is.setSystemId(uri);
+        return build(is);
+    }
+
+    /**
+     * Parse from <code>Reader</code>.
+     * @param stream the reader
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     * @see nu.xom.Builder#build(java.io.Reader)
+     */
+    @Override
+    public Document build(Reader stream) throws ParsingException,
+            ValidityException, IOException {
+        return build(new InputSource(stream));
+    }
+
+    /**
+     * Parse from <code>String</code>.
+     * @param content the HTML source as string
+     * @param uri the base URI
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     * @see nu.xom.Builder#build(java.lang.String, java.lang.String)
+     */
+    @Override
+    public Document build(String content, String uri) throws ParsingException,
+            ValidityException, IOException {
+        return build(new StringReader(content), uri);
+    }
+
+    /**
+     * Parse from URI.
+     * @param uri the URI of the document
+     * @return the document
+     * @throws ParsingException in case of an XML violation
+     * @throws IOException if IO goes wrang
+     * @see nu.xom.Builder#build(java.lang.String)
+     */
+    @Override
+    public Document build(String uri) throws ParsingException,
+            ValidityException, IOException {
+        return build(new InputSource(uri));
+    }
+
+    /**
+     * Gets the node factory
+     */
+    public SimpleNodeFactory getSimpleNodeFactory() {
+        return simpleNodeFactory;
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#setEntityResolver(org.xml.sax.EntityResolver)
+     */
+    public void setEntityResolver(EntityResolver resolver) {
+        entityResolver = resolver;
+    }
+
+    /**
+     * @see org.xml.sax.XMLReader#setErrorHandler(org.xml.sax.ErrorHandler)
+     */
+    public void setErrorHandler(ErrorHandler handler) {
+        errorHandler = handler;
+        treeBuilderErrorHandler = handler;
+        driver = null;
+    }
+    
+    public void setTransitionHander(TransitionHandler handler) {
+        transitionHandler = handler;
+        driver = null;
+    }
+
+    /**
+     * Indicates whether NFC normalization of source is being checked.
+     * @return <code>true</code> if NFC normalization of source is being checked.
+     * @see nu.validator.htmlparser.impl.Tokenizer#isCheckingNormalization()
+     */
+    public boolean isCheckingNormalization() {
+        return checkingNormalization;
+    }
+
+    /**
+     * Toggles the checking of the NFC normalization of source.
+     * @param enable <code>true</code> to check normalization
+     * @see nu.validator.htmlparser.impl.Tokenizer#setCheckingNormalization(boolean)
+     */
+    public void setCheckingNormalization(boolean enable) {
+        this.checkingNormalization = enable;
+        if (driver != null) {
+            driver.setCheckingNormalization(checkingNormalization);
+        }
+    }
+
+    /**
+     * Sets the policy for consecutive hyphens in comments.
+     * @param commentPolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setCommentPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setCommentPolicy(XmlViolationPolicy commentPolicy) {
+        this.commentPolicy = commentPolicy;
+        if (driver != null) {
+            driver.setCommentPolicy(commentPolicy);
+        }
+    }
+
+    /**
+     * Sets the policy for non-XML characters except white space.
+     * @param contentNonXmlCharPolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentNonXmlCharPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentNonXmlCharPolicy(
+            XmlViolationPolicy contentNonXmlCharPolicy) {
+        this.contentNonXmlCharPolicy = contentNonXmlCharPolicy;
+        driver = null;
+    }
+
+    /**
+     * Sets the policy for non-XML white space.
+     * @param contentSpacePolicy the policy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setContentSpacePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setContentSpacePolicy(XmlViolationPolicy contentSpacePolicy) {
+        this.contentSpacePolicy = contentSpacePolicy;
+        if (driver != null) {
+            driver.setContentSpacePolicy(contentSpacePolicy);
+        }
+    }
+
+    /**
+     * Whether the parser considers scripting to be enabled for noscript treatment.
+     * 
+     * @return <code>true</code> if enabled
+     * @see nu.validator.htmlparser.impl.TreeBuilder#isScriptingEnabled()
+     */
+    public boolean isScriptingEnabled() {
+        return scriptingEnabled;
+    }
+
+    /**
+     * Sets whether the parser considers scripting to be enabled for noscript treatment.
+     * @param scriptingEnabled <code>true</code> to enable
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setScriptingEnabled(boolean)
+     */
+    public void setScriptingEnabled(boolean scriptingEnabled) {
+        this.scriptingEnabled = scriptingEnabled;
+        if (treeBuilder != null) {
+            treeBuilder.setScriptingEnabled(scriptingEnabled);
+        }
+    }
+
+    /**
+     * Returns the doctype expectation.
+     * 
+     * @return the doctypeExpectation
+     */
+    public DoctypeExpectation getDoctypeExpectation() {
+        return doctypeExpectation;
+    }
+
+    /**
+     * Sets the doctype expectation.
+     * 
+     * @param doctypeExpectation
+     *            the doctypeExpectation to set
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setDoctypeExpectation(nu.validator.htmlparser.common.DoctypeExpectation)
+     */
+    public void setDoctypeExpectation(DoctypeExpectation doctypeExpectation) {
+        this.doctypeExpectation = doctypeExpectation;
+        if (treeBuilder != null) {
+            treeBuilder.setDoctypeExpectation(doctypeExpectation);
+        }
+    }
+
+    /**
+     * Returns the document mode handler.
+     * 
+     * @return the documentModeHandler
+     */
+    public DocumentModeHandler getDocumentModeHandler() {
+        return documentModeHandler;
+    }
+
+    /**
+     * Sets the document mode handler.
+     * 
+     * @param documentModeHandler
+     *            the documentModeHandler to set
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setDocumentModeHandler(nu.validator.htmlparser.common.DocumentModeHandler)
+     */
+    public void setDocumentModeHandler(DocumentModeHandler documentModeHandler) {
+        this.documentModeHandler = documentModeHandler;
+    }
+
+    /**
+     * Returns the streamabilityViolationPolicy.
+     * 
+     * @return the streamabilityViolationPolicy
+     */
+    public XmlViolationPolicy getStreamabilityViolationPolicy() {
+        return streamabilityViolationPolicy;
+    }
+
+    /**
+     * Sets the streamabilityViolationPolicy.
+     * 
+     * @param streamabilityViolationPolicy
+     *            the streamabilityViolationPolicy to set
+     */
+    public void setStreamabilityViolationPolicy(
+            XmlViolationPolicy streamabilityViolationPolicy) {
+        this.streamabilityViolationPolicy = streamabilityViolationPolicy;
+        driver = null;
+    }
+
+    /**
+     * Whether the HTML 4 mode reports boolean attributes in a way that repeats
+     * the name in the value.
+     * @param html4ModeCompatibleWithXhtml1Schemata
+     */
+    public void setHtml4ModeCompatibleWithXhtml1Schemata(
+            boolean html4ModeCompatibleWithXhtml1Schemata) {
+        this.html4ModeCompatibleWithXhtml1Schemata = html4ModeCompatibleWithXhtml1Schemata;
+        if (driver != null) {
+            driver.setHtml4ModeCompatibleWithXhtml1Schemata(html4ModeCompatibleWithXhtml1Schemata);
+        }
+    }
+
+    /**
+     * Returns the <code>Locator</code> during parse.
+     * @return the <code>Locator</code>
+     */
+    public Locator getDocumentLocator() {
+        return driver.getDocumentLocator();
+    }
+
+    /**
+     * Whether the HTML 4 mode reports boolean attributes in a way that repeats
+     * the name in the value.
+     * 
+     * @return the html4ModeCompatibleWithXhtml1Schemata
+     */
+    public boolean isHtml4ModeCompatibleWithXhtml1Schemata() {
+        return html4ModeCompatibleWithXhtml1Schemata;
+    }
+
+    /**
+     * Whether <code>lang</code> is mapped to <code>xml:lang</code>.
+     * @param mappingLangToXmlLang
+     * @see nu.validator.htmlparser.impl.Tokenizer#setMappingLangToXmlLang(boolean)
+     */
+    public void setMappingLangToXmlLang(boolean mappingLangToXmlLang) {
+        this.mappingLangToXmlLang = mappingLangToXmlLang;
+        if (driver != null) {
+            driver.setMappingLangToXmlLang(mappingLangToXmlLang);
+        }
+    }
+
+    /**
+     * Whether <code>lang</code> is mapped to <code>xml:lang</code>.
+     * 
+     * @return the mappingLangToXmlLang
+     */
+    public boolean isMappingLangToXmlLang() {
+        return mappingLangToXmlLang;
+    }
+
+    /**
+     * Whether the <code>xmlns</code> attribute on the root element is 
+     * passed to through. (FATAL not allowed.)
+     * @param xmlnsPolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setXmlnsPolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setXmlnsPolicy(XmlViolationPolicy xmlnsPolicy) {
+        if (xmlnsPolicy == XmlViolationPolicy.FATAL) {
+            throw new IllegalArgumentException("Can't use FATAL here.");
+        }
+        this.xmlnsPolicy = xmlnsPolicy;
+        if (driver != null) {
+            driver.setXmlnsPolicy(xmlnsPolicy);
+        }
+    }
+
+    /**
+     * Returns the xmlnsPolicy.
+     * 
+     * @return the xmlnsPolicy
+     */
+    public XmlViolationPolicy getXmlnsPolicy() {
+        return xmlnsPolicy;
+    }
+
+    /**
+     * Returns the commentPolicy.
+     * 
+     * @return the commentPolicy
+     */
+    public XmlViolationPolicy getCommentPolicy() {
+        return commentPolicy;
+    }
+
+    /**
+     * Returns the contentNonXmlCharPolicy.
+     * 
+     * @return the contentNonXmlCharPolicy
+     */
+    public XmlViolationPolicy getContentNonXmlCharPolicy() {
+        return contentNonXmlCharPolicy;
+    }
+
+    /**
+     * Returns the contentSpacePolicy.
+     * 
+     * @return the contentSpacePolicy
+     */
+    public XmlViolationPolicy getContentSpacePolicy() {
+        return contentSpacePolicy;
+    }
+
+    /**
+     * @param reportingDoctype
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setReportingDoctype(boolean)
+     */
+    public void setReportingDoctype(boolean reportingDoctype) {
+        this.reportingDoctype = reportingDoctype;
+        if (treeBuilder != null) {
+            treeBuilder.setReportingDoctype(reportingDoctype);
+        }
+    }
+
+    /**
+     * Returns the reportingDoctype.
+     * 
+     * @return the reportingDoctype
+     */
+    public boolean isReportingDoctype() {
+        return reportingDoctype;
+    }
+
+    /**
+     * The policy for non-NCName element and attribute names.
+     * @param namePolicy
+     * @see nu.validator.htmlparser.impl.Tokenizer#setNamePolicy(nu.validator.htmlparser.common.XmlViolationPolicy)
+     */
+    public void setNamePolicy(XmlViolationPolicy namePolicy) {
+        this.namePolicy = namePolicy;
+        if (driver != null) {
+            driver.setNamePolicy(namePolicy);
+            treeBuilder.setNamePolicy(namePolicy);
+        }
+    }
+    
+    /**
+     * Sets the encoding sniffing heuristics.
+     * 
+     * @param heuristics the heuristics to set
+     * @see nu.validator.htmlparser.impl.Tokenizer#setHeuristics(nu.validator.htmlparser.common.Heuristics)
+     */
+    public void setHeuristics(Heuristics heuristics) {
+        this.heuristics = heuristics;
+        if (driver != null) {
+            driver.setHeuristics(heuristics);
+        }
+    }
+    
+    public Heuristics getHeuristics() {
+        return this.heuristics;
+    }
+
+    /**
+     * This is a catch-all convenience method for setting name, xmlns, content space, 
+     * content non-XML char and comment policies in one go. This does not affect the 
+     * streamability policy or doctype reporting.
+     * 
+     * @param xmlPolicy
+     */
+    public void setXmlPolicy(XmlViolationPolicy xmlPolicy) {
+        setNamePolicy(xmlPolicy);
+        setXmlnsPolicy(xmlPolicy == XmlViolationPolicy.FATAL ? XmlViolationPolicy.ALTER_INFOSET : xmlPolicy);
+        setContentSpacePolicy(xmlPolicy);
+        setContentNonXmlCharPolicy(xmlPolicy);
+        setCommentPolicy(xmlPolicy);
+    }
+
+    /**
+     * The policy for non-NCName element and attribute names.
+     * 
+     * @return the namePolicy
+     */
+    public XmlViolationPolicy getNamePolicy() {
+        return namePolicy;
+    }
+
+    /**
+     * Does nothing.
+     * @deprecated
+     */
+    public void setBogusXmlnsPolicy(
+            XmlViolationPolicy bogusXmlnsPolicy) {
+    }
+
+    /**
+     * Returns <code>XmlViolationPolicy.ALTER_INFOSET</code>.
+     * @deprecated
+     * @return <code>XmlViolationPolicy.ALTER_INFOSET</code>
+     */
+    public XmlViolationPolicy getBogusXmlnsPolicy() {
+        return XmlViolationPolicy.ALTER_INFOSET;
+    }
+    
+    public void addCharacterHandler(CharacterHandler characterHandler) {
+        this.characterHandlers.add(characterHandler);
+        if (driver != null) {
+            driver.addCharacterHandler(characterHandler);
+        }
+    }
+
+    
+    /**
+     * Sets whether comment nodes appear in the tree.
+     * @param ignoreComments <code>true</code> to ignore comments
+     * @see nu.validator.htmlparser.impl.TreeBuilder#setIgnoringComments(boolean)
+     */
+    public void setIgnoringComments(boolean ignoreComments) {
+        treeBuilder.setIgnoringComments(ignoreComments);
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/ModalDocument.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/ModalDocument.java
new file mode 100644
index 000000000..3b76b1421
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/ModalDocument.java
@@ -0,0 +1,75 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.xom;
+
+import nu.validator.htmlparser.common.DocumentMode;
+import nu.xom.Document;
+import nu.xom.Element;
+
+/**
+ * Document with <code>Mode</code>.
+ * @version $Id$
+ * @author hsivonen
+ */
+public class ModalDocument extends Document implements Mode {
+
+    private DocumentMode mode = null;
+    
+    /**
+     * Copy constructor (<code>Mode</code>-aware).
+     * @param doc
+     */
+    public ModalDocument(Document doc) {
+        super(doc);
+        if (doc instanceof Mode) {
+            Mode modal = (Mode) doc;
+            setMode(modal.getMode());
+        }
+    }
+
+    /**
+     * With root.
+     * 
+     * @param elt
+     */
+    public ModalDocument(Element elt) {
+        super(elt);
+    }
+
+    /**
+     * Gets the mode.
+     * @see nu.validator.htmlparser.xom.Mode#getMode()
+     */
+    public DocumentMode getMode() {
+        return mode;
+    }
+
+    /**
+     * Sets the mode.
+     * @see nu.validator.htmlparser.xom.Mode#setMode(nu.validator.htmlparser.common.DocumentMode)
+     */
+    public void setMode(DocumentMode mode) {
+        this.mode = mode;
+    }
+    
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/Mode.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/Mode.java
new file mode 100644
index 000000000..bd2dcbc26
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/Mode.java
@@ -0,0 +1,48 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.xom;
+
+import nu.validator.htmlparser.common.DocumentMode;
+
+/**
+ * Interface for attaching a <code>DocumentMode</code> on a Document.
+ * @version $Id$
+ * @author hsivonen
+ */
+public interface Mode {
+
+    /**
+     * Returns the mode.
+     * 
+     * @return the mode
+     */
+    public abstract DocumentMode getMode();
+
+    /**
+     * Sets the mode.
+     * 
+     * @param mode the mode to set
+     */
+    public abstract void setMode(DocumentMode mode);
+
+}
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/SimpleNodeFactory.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/SimpleNodeFactory.java
new file mode 100644
index 000000000..147b5d930
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/SimpleNodeFactory.java
@@ -0,0 +1,102 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.xom;
+
+import nu.xom.Attribute;
+import nu.xom.Comment;
+import nu.xom.Document;
+import nu.xom.Element;
+import nu.xom.Text;
+import nu.xom.Attribute.Type;
+
+/**
+ * A simpler node factory that does not use <code>Nodes</code>..
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public class SimpleNodeFactory {
+
+    /**
+     * <code>return new Attribute(localName, uri, value, type);</code>
+     * @param localName
+     * @param uri
+     * @param value
+     * @param type
+     * @return
+     */
+    public Attribute makeAttribute(String localName, String uri, String value, Type type) {
+        return new Attribute(localName, uri, value, type);
+    }
+
+    /**
+     * <code>return new Text(string);</code>
+     * @param string
+     * @return
+     */
+    public Text makeText(String string) {
+        return new Text(string);
+    }
+
+    /**
+     * <code>return new Comment(string);</code>
+     * @param string
+     * @return
+     */
+    public Comment makeComment(String string) {
+        return new Comment(string);
+    }
+
+    /**
+     * <code>return new Element(name, namespace);</code>
+     * @param name
+     * @param namespace
+     * @return
+     */
+    public Element makeElement(String name, String namespace) {
+        return new Element(name, namespace);
+    }
+
+    /**
+     * <code>return new FormPtrElement(name, namespace, form);</code>
+     * @param name
+     * @param namespace
+     * @param form
+     * @return
+     */
+    public Element makeElement(String name, String namespace, Element form) {
+        return new FormPtrElement(name, namespace, form);
+    }
+    
+    /**
+     * <code>return new ModalDocument(new Element("root", "http://www.xom.nu/fakeRoot"));</code>
+     * 
+     * <p>Subclasses adviced to return an instance of <code>Mode</code>. (Not required, though.)
+     * 
+     * @return
+     */
+    public Document makeDocument() {
+        return new ModalDocument(new Element("root", "http://www.xom.nu/fakeRoot"));
+    }
+    
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/XOMTreeBuilder.java b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/XOMTreeBuilder.java
new file mode 100644
index 000000000..623f31927
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/XOMTreeBuilder.java
@@ -0,0 +1,351 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008-2010 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.xom;
+
+import nu.validator.htmlparser.common.DocumentMode;
+import nu.validator.htmlparser.impl.CoalescingTreeBuilder;
+import nu.validator.htmlparser.impl.HtmlAttributes;
+import nu.xom.Attribute;
+import nu.xom.Document;
+import nu.xom.Element;
+import nu.xom.Node;
+import nu.xom.Nodes;
+import nu.xom.ParentNode;
+import nu.xom.Text;
+import nu.xom.XMLException;
+
+import org.xml.sax.SAXException;
+
+class XOMTreeBuilder extends CoalescingTreeBuilder<Element> {
+
+    private final SimpleNodeFactory nodeFactory;
+
+    private Document document;
+    
+    private int cachedTableIndex = -1;
+    
+    private Element cachedTable = null;
+
+    protected XOMTreeBuilder(SimpleNodeFactory nodeFactory) {
+        super();
+        this.nodeFactory = nodeFactory;
+    }
+
+    @Override
+    protected void addAttributesToElement(Element element, HtmlAttributes attributes)
+            throws SAXException {
+        try {
+            for (int i = 0; i < attributes.getLength(); i++) {
+                String localName = attributes.getLocalNameNoBoundsCheck(i);
+                String uri = attributes.getURINoBoundsCheck(i);
+                if (element.getAttribute(localName, uri) == null) {
+                    element.addAttribute(nodeFactory.makeAttribute(
+                            localName,
+                            uri,
+                            attributes.getValueNoBoundsCheck(i),
+                            attributes.getTypeNoBoundsCheck(i) == "ID" ? Attribute.Type.ID
+                                    : Attribute.Type.CDATA));
+                }
+            }
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override protected void appendCharacters(Element parent, String text)
+            throws SAXException {
+        try {
+            int childCount = parent.getChildCount();
+            Node lastChild;
+            if (childCount != 0
+                    && ((lastChild = parent.getChild(childCount - 1)) instanceof Text)) {
+                Text lastAsText = (Text) lastChild;
+                lastAsText.setValue(lastAsText.getValue() + text);
+                return;
+            }
+            parent.appendChild(nodeFactory.makeText(text));
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override
+    protected void appendChildrenToNewParent(Element oldParent,
+            Element newParent) throws SAXException {
+        try {
+            Nodes children = oldParent.removeChildren();
+            for (int i = 0; i < children.size(); i++) {
+                newParent.appendChild(children.get(i));
+            }
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override
+    protected void appendComment(Element parent, String comment) throws SAXException {
+        try {
+            parent.appendChild(nodeFactory.makeComment(comment));
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override
+    protected void appendCommentToDocument(String comment)
+            throws SAXException {
+        try {
+            Element root = document.getRootElement();
+            if ("http://www.xom.nu/fakeRoot".equals(root.getNamespaceURI())) {
+                document.insertChild(nodeFactory.makeComment(comment), document.indexOf(root));
+            } else {
+                document.appendChild(nodeFactory.makeComment(comment));
+            }
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override
+ protected Element createElement(String ns, String name,
+            HtmlAttributes attributes, Element intendedParent) throws SAXException {
+        try {
+            Element rv = nodeFactory.makeElement(name, ns);
+            for (int i = 0; i < attributes.getLength(); i++) {
+                rv.addAttribute(nodeFactory.makeAttribute(
+                        attributes.getLocalNameNoBoundsCheck(i),
+                        attributes.getURINoBoundsCheck(i),
+                        attributes.getValueNoBoundsCheck(i),
+                        attributes.getTypeNoBoundsCheck(i) == "ID" ? Attribute.Type.ID
+                                : Attribute.Type.CDATA));
+            }
+            return rv;
+        } catch (XMLException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    @Override
+ protected Element createHtmlElementSetAsRoot(
+            HtmlAttributes attributes) throws SAXException {
+        try {
+            Element rv = nodeFactory.makeElement("html",
+                    "http://www.w3.org/1999/xhtml");
+            for (int i = 0; i < attributes.getLength(); i++) {
+                rv.addAttribute(nodeFactory.makeAttribute(
+                        attributes.getLocalNameNoBoundsCheck(i),
+                        attributes.getURINoBoundsCheck(i),
+                        attributes.getValueNoBoundsCheck(i),
+                        attributes.getTypeNoBoundsCheck(i) == "ID" ? Attribute.Type.ID
+                                : Attribute.Type.CDATA));
+            }
+            document.setRootElement(rv);
+            return rv;
+        } catch (XMLException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    @Override
+    protected void detachFromParent(Element element) throws SAXException {
+        try {
+            element.detach();
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override
+    protected void appendElement(Element child,
+            Element newParent) throws SAXException {
+        try {
+            child.detach();
+            newParent.appendChild(child);
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override
+    protected boolean hasChildren(Element element) throws SAXException {
+        try {
+            return element.getChildCount() != 0;
+        } catch (XMLException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    /**
+     * Returns the document.
+     * 
+     * @return the document
+     */
+    Document getDocument() {
+        Document rv = document;
+        document = null;
+        return rv;
+    }
+
+    Nodes getDocumentFragment() {
+        Element rootElt = document.getRootElement();
+        Nodes rv = rootElt.removeChildren();
+        document = null;
+        return rv;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#createElement(String,
+     *      java.lang.String, org.xml.sax.Attributes, java.lang.Object)
+     */
+    @Override
+    protected Element createElement(String ns, String name,
+            HtmlAttributes attributes, Element form, Element intendedParent) throws SAXException {
+        try {
+            Element rv = nodeFactory.makeElement(name,
+ ns, form);
+            for (int i = 0; i < attributes.getLength(); i++) {
+                rv.addAttribute(nodeFactory.makeAttribute(
+                        attributes.getLocalName(i),
+                        attributes.getURINoBoundsCheck(i),
+                        attributes.getValueNoBoundsCheck(i),
+                        attributes.getTypeNoBoundsCheck(i) == "ID" ? Attribute.Type.ID
+                                : Attribute.Type.CDATA));
+            }
+            return rv;
+        } catch (XMLException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#start()
+     */
+    @Override
+    protected void start(boolean fragment) throws SAXException {
+        document = nodeFactory.makeDocument();
+        cachedTableIndex = -1;
+        cachedTable = null;
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#documentMode(nu.validator.htmlparser.common.DocumentMode,
+     *      java.lang.String, java.lang.String, boolean)
+     */
+    @Override
+    protected void documentMode(DocumentMode mode, String publicIdentifier,
+            String systemIdentifier, boolean html4SpecificAdditionalErrorChecks)
+            throws SAXException {
+        if (document instanceof Mode) {
+            Mode modal = (Mode) document;
+            modal.setMode(mode);
+        }
+    }
+
+    @Override
+    protected Element createAndInsertFosterParentedElement(String ns, String name,
+            HtmlAttributes attributes, Element table, Element stackParent) throws SAXException {
+        try {
+            Node parent = table.getParent();
+            Element child = createElement(ns, name, attributes, parent != null ? (Element) parent : stackParent);
+            if (parent != null) { // always an element if not null
+                ((ParentNode) parent).insertChild(child, indexOfTable(table, stackParent));
+                cachedTableIndex++;
+            } else {
+                stackParent.appendChild(child);
+            }
+            return child;
+        } catch (XMLException e) {
+            fatal(e);
+            throw new RuntimeException("Unreachable");
+        }
+    }
+
+    @Override protected void insertFosterParentedCharacters(String text,
+            Element table, Element stackParent) throws SAXException {
+        try {
+            Node parent = table.getParent();
+            if (parent != null) { // always an element if not null
+                Element parentAsElt = (Element) parent;
+                int tableIndex = indexOfTable(table, parentAsElt);
+                Node prevSibling;
+                if (tableIndex != 0
+                        && ((prevSibling = parentAsElt.getChild(tableIndex - 1)) instanceof Text)) {
+                    Text prevAsText = (Text) prevSibling;
+                    prevAsText.setValue(prevAsText.getValue() + text);
+                    return;
+                }
+                parentAsElt.insertChild(nodeFactory.makeText(text), tableIndex);
+                cachedTableIndex++;
+                return;
+            }
+            int childCount = stackParent.getChildCount();
+            Node lastChild;
+            if (childCount != 0
+                    && ((lastChild = stackParent.getChild(childCount - 1)) instanceof Text)) {
+                Text lastAsText = (Text) lastChild;
+                lastAsText.setValue(lastAsText.getValue() + text);
+                return;
+            }
+            stackParent.appendChild(nodeFactory.makeText(text));
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+
+    @Override protected void insertFosterParentedChild(Element child,
+            Element table, Element stackParent) throws SAXException {
+        try {
+            Node parent = table.getParent();
+            if (parent != null) { // always an element if not null
+                ((ParentNode)parent).insertChild(child, indexOfTable(table, stackParent));
+                cachedTableIndex++;
+            } else {
+                stackParent.appendChild(child);
+            }
+        } catch (XMLException e) {
+            fatal(e);
+        }
+    }
+    
+    private int indexOfTable(Element table, Element stackParent) {
+        if (table == cachedTable) {
+            return cachedTableIndex;
+        } else {
+            cachedTable = table;
+            return (cachedTableIndex = stackParent.indexOf(table));
+        }
+    }
+
+    /**
+     * @see nu.validator.htmlparser.impl.TreeBuilder#end()
+     */
+    @Override protected void end() throws SAXException {
+        cachedTableIndex = -1;
+        cachedTable = null;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/package.html b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/package.html
new file mode 100644
index 000000000..a936d5e3a
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/htmlparser/xom/package.html
@@ -0,0 +1,29 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
+<html>
+<head><title>Package Overview</title>
+<!--
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a 
+ copy of this software and associated documentation files (the "Software"), 
+ to deal in the Software without restriction, including without limitation 
+ the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ and/or sell copies of the Software, and to permit persons to whom the 
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in 
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ DEALINGS IN THE SOFTWARE.
+-->
+</head>
+<body bgcolor="white">
+<p>This package provides an HTML5 parser that exposes the document through the XOM API.</p>
+</body>
+</html>
\ No newline at end of file
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/CDATA.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/CDATA.java
new file mode 100644
index 000000000..f17ce3f89
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/CDATA.java
@@ -0,0 +1,70 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A CDATA section.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class CDATA extends ParentNode {
+
+    /**
+     * The constructor.
+     * @param locator the locator
+     */
+    public CDATA(Locator locator) {
+        super(locator);
+    }
+
+    /**
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.startCDATA(this);
+    }
+
+    /**
+     * 
+     * @throws SAXException if things go wrong
+     * @see nu.validator.saxtree.Node#revisit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void revisit(TreeParser treeParser) throws SAXException {
+        treeParser.endCDATA(endLocator);
+    }
+
+    /**
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.CDATA;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/CharBufferNode.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/CharBufferNode.java
new file mode 100644
index 000000000..55c7715f6
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/CharBufferNode.java
@@ -0,0 +1,62 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+
+/**
+ * A common superclass for character buffer node classes.
+ * @version $Id$
+ * @author hsivonen
+ */
+public abstract class CharBufferNode extends Node {
+
+    /**
+     * The buffer.
+     */
+    protected final char[] buffer;
+    
+    /**
+     * The constructor.
+     * @param locator the locator
+     * @param buf the buffer
+     * @param start the offset
+     * @param length the length
+     */
+    CharBufferNode(Locator locator, char[] buf, int start, int length) {
+        super(locator);
+        this.buffer = new char[length];
+        System.arraycopy(buf, start, buffer, 0, length);
+    }
+
+    /**
+     * Returns the wrapped buffer as a string.
+     * 
+     * @see java.lang.Object#toString()
+     */
+    @Override
+    public String toString() {
+        return new String(buffer);
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/Characters.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/Characters.java
new file mode 100644
index 000000000..b8cc2d6d6
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/Characters.java
@@ -0,0 +1,65 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A run of characters
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class Characters extends CharBufferNode {
+
+    /**
+     * The constructor.
+     * @param locator the locator
+     * @param buf the buffer
+     * @param start the offset in the buffer
+     * @param length the length
+     */
+    public Characters(Locator locator, char[] buf, int start, int length) {
+        super(locator, buf, start, length);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.characters(buffer, 0, buffer.length, this);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.CHARACTERS;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/Comment.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/Comment.java
new file mode 100644
index 000000000..f010462fb
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/Comment.java
@@ -0,0 +1,66 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A comment.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class Comment extends CharBufferNode {
+
+    /**
+     * The constructor.
+     * @param locator the locator
+     * @param buf the buffer
+     * @param start the offset
+     * @param length the length
+     */
+    public Comment(Locator locator, char[] buf, int start, int length) {
+        super(locator, buf, start, length);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.comment(buffer, 0, buffer.length, this);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.COMMENT;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/DTD.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/DTD.java
new file mode 100644
index 000000000..2169e0571
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/DTD.java
@@ -0,0 +1,118 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A doctype.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class DTD extends ParentNode {
+
+    /**
+     * The name.
+     */
+    private final String name;
+    
+    /**
+     * The public id.
+     */
+    private final String publicIdentifier;
+    
+    /**
+     * The system id.
+     */
+    private final String systemIdentifier;
+
+    /**
+     * The constructor.
+     * @param locator the locator
+     * @param name the name
+     * @param publicIdentifier the public id
+     * @param systemIdentifier the system id
+     */
+    public DTD(Locator locator, String name, String publicIdentifier, String systemIdentifier) {
+        super(locator);
+        this.name = name;
+        this.publicIdentifier = publicIdentifier;
+        this.systemIdentifier = systemIdentifier;
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.startDTD(name, publicIdentifier, systemIdentifier, this);
+    }
+
+    /**
+     * @see nu.validator.saxtree.Node#revisit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void revisit(TreeParser treeParser) throws SAXException {
+        treeParser.endDTD(endLocator);
+    }
+
+    /**
+     * Returns the name.
+     * 
+     * @return the name
+     */
+    public String getName() {
+        return name;
+    }
+
+    /**
+     * Returns the publicIdentifier.
+     * 
+     * @return the publicIdentifier
+     */
+    public String getPublicIdentifier() {
+        return publicIdentifier;
+    }
+
+    /**
+     * Returns the systemIdentifier.
+     * 
+     * @return the systemIdentifier
+     */
+    public String getSystemIdentifier() {
+        return systemIdentifier;
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.DTD;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/Document.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/Document.java
new file mode 100644
index 000000000..3bb6f09c7
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/Document.java
@@ -0,0 +1,70 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A document.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class Document extends ParentNode {
+
+    /**
+     * The constructor.
+     * @param locator the locator
+     */
+    public Document(Locator locator) {
+        super(locator);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.startDocument(this);
+    }
+
+    /**
+     * @see nu.validator.saxtree.Node#revisit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void revisit(TreeParser treeParser) throws SAXException {
+        treeParser.endDocument(endLocator);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.DOCUMENT;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/DocumentFragment.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/DocumentFragment.java
new file mode 100644
index 000000000..06816932f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/DocumentFragment.java
@@ -0,0 +1,58 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.helpers.LocatorImpl;
+
+/**
+ * A document fragment.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class DocumentFragment extends ParentNode {
+
+    /**
+     * The constructor.
+     */
+    public DocumentFragment() {
+        super(new LocatorImpl());
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override void visit(TreeParser treeParser) {
+        // nothing
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override public NodeType getNodeType() {
+        return NodeType.DOCUMENT_FRAGMENT;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/Element.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/Element.java
new file mode 100644
index 000000000..3d33164e5
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/Element.java
@@ -0,0 +1,172 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import java.util.List;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.helpers.AttributesImpl;
+
+/**
+ * An element.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class Element extends ParentNode {
+
+    /**
+     * The namespace URI.
+     */
+    private final String uri;
+
+    /**
+     * The local name.
+     */
+    private final String localName;
+
+    /**
+     * The qualified name.
+     */
+    private final String qName;
+
+    /**
+     * The attributes.
+     */
+    private final Attributes attributes;
+
+    /**
+     * The namespace prefix mappings.
+     */
+    private final List<PrefixMapping> prefixMappings;
+
+    /**
+     * The contructor.
+     * @param locator the locator.
+     * @param uri the namespace URI
+     * @param localName the local name
+     * @param qName the qualified name
+     * @param atts the attributes
+     * @param retainAttributes <code>true</code> to retain the attributes instead of copying
+     * @param prefixMappings the prefix mappings
+     */
+    public Element(Locator locator, String uri, String localName, String qName,
+            Attributes atts, boolean retainAttributes,
+            List<PrefixMapping> prefixMappings) {
+        super(locator);
+        this.uri = uri;
+        this.localName = localName;
+        this.qName = qName;
+        if (retainAttributes) {
+            this.attributes = atts;
+        } else {
+            this.attributes = new AttributesImpl(atts);
+        }
+        this.prefixMappings = prefixMappings;
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        if (prefixMappings != null) {
+            for (PrefixMapping mapping : prefixMappings) {
+                treeParser.startPrefixMapping(mapping.getPrefix(),
+                        mapping.getUri(), this);
+            }
+        }
+        treeParser.startElement(uri, localName, qName, attributes, this);
+    }
+
+    /**
+     * @see nu.validator.saxtree.Node#revisit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void revisit(TreeParser treeParser) throws SAXException {
+        treeParser.endElement(uri, localName, qName, endLocator);
+        if (prefixMappings != null) {
+            for (PrefixMapping mapping : prefixMappings) {
+                treeParser.endPrefixMapping(mapping.getPrefix(), endLocator);
+            }
+        }
+    }
+
+    /**
+     * Returns the attributes.
+     * 
+     * @return the attributes
+     */
+    public Attributes getAttributes() {
+        return attributes;
+    }
+
+    /**
+     * Returns the localName.
+     * 
+     * @return the localName
+     */
+    public String getLocalName() {
+        return localName;
+    }
+
+    /**
+     * Returns the prefixMappings.
+     * 
+     * @return the prefixMappings
+     */
+    public List<PrefixMapping> getPrefixMappings() {
+        return prefixMappings;
+    }
+
+    /**
+     * Returns the qName.
+     * 
+     * @return the qName
+     */
+    public String getQName() {
+        return qName;
+    }
+
+    /**
+     * Returns the uri.
+     * 
+     * @return the uri
+     */
+    public String getUri() {
+        return uri;
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.ELEMENT;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/Entity.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/Entity.java
new file mode 100644
index 000000000..091013736
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/Entity.java
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * An entity.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class Entity extends ParentNode {
+
+    /**
+     * The name.
+     */
+    private final String name;
+
+    /**
+     * The constructor.
+     * @param locator the locator
+     * @param name the name
+     */
+    public Entity(Locator locator, String name) {
+        super(locator);
+        this.name = name;
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.startEntity(name, this);
+    }
+
+    /**
+     * @see nu.validator.saxtree.Node#revisit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void revisit(TreeParser treeParser) throws SAXException {
+        treeParser.endEntity(name, endLocator);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.ENTITY;
+    }
+
+    /**
+     * Returns the name.
+     * 
+     * @return the name
+     */
+    public String getName() {
+        return name;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/IgnorableWhitespace.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/IgnorableWhitespace.java
new file mode 100644
index 000000000..e5fcf350f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/IgnorableWhitespace.java
@@ -0,0 +1,65 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A run ignorable whitespace.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class IgnorableWhitespace extends CharBufferNode {
+
+    /**
+     * The constructor.
+     * @param locator the locator
+     * @param buf the buffer
+     * @param start the offset
+     * @param length the length
+     */
+    public IgnorableWhitespace(Locator locator, char[] buf, int start, int length) {
+        super(locator, buf, start, length);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.ignorableWhitespace(buffer, 0, buffer.length, this);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.IGNORABLE_WHITESPACE;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/LocatorImpl.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/LocatorImpl.java
new file mode 100644
index 000000000..37c0c6325
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/LocatorImpl.java
@@ -0,0 +1,104 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2007-2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+
+/**
+ * A locator implementation.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class LocatorImpl implements Locator {
+
+    /**
+     * The system id.
+     */
+    private final String systemId;
+    
+    /**
+     * The public id.
+     */
+    private final String publicId;
+    
+    /**
+     * The column.
+     */
+    private final int column;
+    
+    /**
+     * The line.
+     */
+    private final int line;
+    
+    /**
+     * The constructor.
+     * @param locator the locator
+     */
+    public LocatorImpl(Locator locator) {
+        if (locator == null) {
+            this.systemId = null;
+            this.publicId = null;
+            this.column = -1;
+            this.line = -1;
+        } else {
+            this.systemId = locator.getSystemId();
+            this.publicId = locator.getPublicId();
+            this.column = locator.getColumnNumber();
+            this.line = locator.getLineNumber();
+        }
+    }
+    
+    /**
+     * 
+     * @see org.xml.sax.Locator#getColumnNumber()
+     */
+    public int getColumnNumber() {
+        return column;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.Locator#getLineNumber()
+     */
+    public int getLineNumber() {
+        return line;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.Locator#getPublicId()
+     */
+    public String getPublicId() {
+        return publicId;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.Locator#getSystemId()
+     */
+    public String getSystemId() {
+        return systemId;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/Node.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/Node.java
new file mode 100644
index 000000000..7aed83b75
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/Node.java
@@ -0,0 +1,307 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2007-2009 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import java.util.List;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * The common node superclass.
+ * @version $Id$
+ * @author hsivonen
+ */
+public abstract class Node implements Locator {
+
+    /**
+     * The system id.
+     */
+    private final String systemId;
+    
+    /**
+     * The public id.
+     */
+    private final String publicId;
+    
+    /**
+     * The column.
+     */
+    private final int column;
+    
+    /**
+     * The line.
+     */
+    private final int line;
+
+    /**
+     * The next sibling.
+     */
+    private Node nextSibling = null;
+    
+    /**
+     * The parent.
+     */
+    private ParentNode parentNode = null;
+
+    /**
+     * The constructor.
+     * 
+     * @param locator the locator
+     */
+    Node(Locator locator) {
+        if (locator == null) {
+            this.systemId = null;
+            this.publicId = null;
+            this.column = -1;
+            this.line = -1;
+        } else {
+            this.systemId = locator.getSystemId();
+            this.publicId = locator.getPublicId();
+            this.column = locator.getColumnNumber();
+            this.line = locator.getLineNumber();
+        }
+    }
+    
+    /**
+     * 
+     * @see org.xml.sax.Locator#getColumnNumber()
+     */
+    public int getColumnNumber() {
+        return column;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.Locator#getLineNumber()
+     */
+    public int getLineNumber() {
+        return line;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.Locator#getPublicId()
+     */
+    public String getPublicId() {
+        return publicId;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.Locator#getSystemId()
+     */
+    public String getSystemId() {
+        return systemId;
+    }
+
+    /**
+     * Visit the node.
+     * 
+     * @param treeParser the visitor
+     * @throws SAXException if stuff goes wrong
+     */
+    abstract void visit(TreeParser treeParser) throws SAXException;
+    
+    /**
+     * Revisit the node.
+     * 
+     * @param treeParser the visitor
+     * @throws SAXException if stuff goes wrong
+     */
+    void revisit(TreeParser treeParser) throws SAXException {
+        return;
+    }
+    
+    /**
+     * Return the first child.
+     * @return the first child
+     */
+    public Node getFirstChild() {
+        return null;
+    }
+
+    /**
+     * Returns the nextSibling.
+     * 
+     * @return the nextSibling
+     */
+    public final Node getNextSibling() {
+        return nextSibling;
+    }
+    
+    /**
+     * Returns the previous sibling
+     * @return the previous sibling
+     */
+    public final Node getPreviousSibling() {
+        Node prev = null;
+        Node next = parentNode.getFirstChild();
+        for(;;) {
+            if (this == next) {
+                return prev;
+            }
+            prev = next;
+            next = next.nextSibling;
+        }
+    }
+
+    /**
+     * Sets the nextSibling.
+     * 
+     * @param nextSibling the nextSibling to set
+     */
+    void setNextSibling(Node nextSibling) {
+        this.nextSibling = nextSibling;
+    }
+    
+    
+    /**
+     * Returns the parentNode.
+     * 
+     * @return the parentNode
+     */
+    public final ParentNode getParentNode() {
+        return parentNode;
+    }
+    
+    /**
+     * Sets the parentNode.
+     * 
+     * @param parentNode the parentNode to set
+     */
+    void setParentNode(ParentNode parentNode) {
+        this.parentNode = parentNode;
+    }
+    
+    /**
+     * Return the node type.
+     * @return the node type
+     */
+    public abstract NodeType getNodeType();
+    
+    // Subclass-specific accessors that are hoisted here to 
+    // avoid casting.
+    
+    /**
+     * Detach this node from its parent.
+     */
+    public void detach() {
+        if (parentNode != null) {
+            parentNode.removeChild(this);
+            parentNode = null;
+        }
+    }
+    
+    /**
+     * Returns the name.
+     * 
+     * @return the name
+     */
+    public String getName() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the publicIdentifier.
+     * 
+     * @return the publicIdentifier
+     */
+    public String getPublicIdentifier() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the systemIdentifier.
+     * 
+     * @return the systemIdentifier
+     */
+    public String getSystemIdentifier() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the attributes.
+     * 
+     * @return the attributes
+     */
+    public Attributes getAttributes() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the localName.
+     * 
+     * @return the localName
+     */
+    public String getLocalName() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the prefixMappings.
+     * 
+     * @return the prefixMappings
+     */
+    public List<PrefixMapping> getPrefixMappings() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the qName.
+     * 
+     * @return the qName
+     */
+    public String getQName() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the uri.
+     * 
+     * @return the uri
+     */
+    public String getUri() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the data.
+     * 
+     * @return the data
+     */
+    public String getData() {
+        throw new UnsupportedOperationException();
+    }
+
+    /**
+     * Returns the target.
+     * 
+     * @return the target
+     */
+    public String getTarget() {
+        throw new UnsupportedOperationException();
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/NodeType.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/NodeType.java
new file mode 100644
index 000000000..c3c927f0d
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/NodeType.java
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+/**
+ * The node type.
+ * @version $Id$
+ * @author hsivonen
+ */
+public enum NodeType {
+    /**
+     * A CDATA section.
+     */
+    CDATA,
+    /**
+     * A run of characters.
+     */
+    CHARACTERS,
+    /**
+     * A comment.
+     */
+    COMMENT,
+    /**
+     * A document.
+     */
+    DOCUMENT,
+    /**
+     * A document fragment.
+     */
+    DOCUMENT_FRAGMENT,
+    /**
+     * A DTD.
+     */
+    DTD,
+    /**
+     * An element.
+     */
+    ELEMENT,
+    /**
+     * An entity.
+     */
+    ENTITY,
+    /**
+     * A run of ignorable whitespace.
+     */
+    IGNORABLE_WHITESPACE,
+    /**
+     * A processing instruction.
+     */
+    PROCESSING_INSTRUCTION,
+    /**
+     * A skipped entity.
+     */
+    SKIPPED_ENTITY
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/NullLexicalHandler.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/NullLexicalHandler.java
new file mode 100644
index 000000000..de63f3b57
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/NullLexicalHandler.java
@@ -0,0 +1,85 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.SAXException;
+import org.xml.sax.ext.LexicalHandler;
+
+/**
+ * A lexical handler that does nothing.
+ * @version $Id$
+ * @author hsivonen
+ */
+final class NullLexicalHandler implements LexicalHandler {
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#comment(char[], int, int)
+     */
+    public void comment(char[] arg0, int arg1, int arg2) throws SAXException {
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#endCDATA()
+     */
+    public void endCDATA() throws SAXException {
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#endDTD()
+     */
+    public void endDTD() throws SAXException {
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#endEntity(java.lang.String)
+     */
+    public void endEntity(String arg0) throws SAXException {
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#startCDATA()
+     */
+    public void startCDATA() throws SAXException {
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#startDTD(java.lang.String, java.lang.String, java.lang.String)
+     */
+    public void startDTD(String arg0, String arg1, String arg2) throws SAXException {
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#startEntity(java.lang.String)
+     */
+    public void startEntity(String arg0) throws SAXException {
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/ParentNode.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/ParentNode.java
new file mode 100644
index 000000000..6cc96003f
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/ParentNode.java
@@ -0,0 +1,208 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+
+/**
+ * Common superclass for parent nodes.
+ * @version $Id$
+ * @author hsivonen
+ */
+public abstract class ParentNode extends Node {
+
+    /**
+     * The end locator.
+     */
+    protected Locator endLocator;
+    
+    /**
+     * The first child.
+     */
+    private Node firstChild = null;
+    
+    /**
+     * The last child (for efficiency).
+     */
+    private Node lastChild = null;
+    
+    /**
+     * The constuctor.
+     * @param locator the locator
+     */
+    ParentNode(Locator locator) {
+        super(locator);
+    }
+
+    /**
+     * Sets the endLocator.
+     * 
+     * @param endLocator the endLocator to set
+     */
+    public void setEndLocator(Locator endLocator) {
+        this.endLocator = new LocatorImpl(endLocator);
+    }
+
+    /**
+     * Copies the endLocator from another node.
+     * 
+     * @param another the another node
+     */
+    public void copyEndLocator(ParentNode another) {
+        this.endLocator = another.endLocator;
+    }
+    
+    /**
+     * Returns the firstChild.
+     * 
+     * @return the firstChild
+     */
+    public final Node getFirstChild() {
+        return firstChild;
+    }
+
+    /**
+     * Returns the lastChild.
+     * 
+     * @return the lastChild
+     */
+    public final Node getLastChild() {
+        return lastChild;
+    }
+
+    /**
+     * Insert a new child before a pre-existing child and return the newly inserted child.
+     * @param child the new child
+     * @param sibling the existing child before which to insert (must be a child of this node) or <code>null</code> to append
+     * @return <code>child</code>
+     */
+    public Node insertBefore(Node child, Node sibling) {
+        assert sibling == null || this == sibling.getParentNode();
+        if (sibling == null) {
+            return appendChild(child);
+        }
+        child.detach();
+        child.setParentNode(this);
+        if (firstChild == sibling) {
+            child.setNextSibling(sibling);
+            firstChild = child;
+        } else {
+            Node prev = firstChild;
+            Node next = firstChild.getNextSibling();
+            while (next != sibling) {
+                prev = next;
+                next = next.getNextSibling();
+            }
+            prev.setNextSibling(child);
+            child.setNextSibling(next);
+        }
+        return child;
+    }
+    
+    public Node insertBetween(Node child, Node prev, Node next) {
+        assert prev == null || this == prev.getParentNode();
+        assert next == null || this == next.getParentNode();
+        assert prev != null || next == firstChild;
+        assert next != null || prev == lastChild;
+        assert prev == null || next == null || prev.getNextSibling() == next;
+        if (next == null) {
+            return appendChild(child);            
+        }
+        child.detach();
+        child.setParentNode(this);
+        child.setNextSibling(next);
+        if (prev == null) {
+            firstChild = child;
+        } else {
+            prev.setNextSibling(child);
+        }        
+        return child;
+    }
+    
+    /**
+     * Append a child to this node and return the child.
+     * 
+     * @param child the child to append.
+     * @return <code>child</code>
+     */
+    public Node appendChild(Node child) {
+        child.detach();
+        child.setParentNode(this);
+        if (firstChild == null) {
+            firstChild = child;
+        } else {
+            lastChild.setNextSibling(child);
+        }
+        lastChild = child;
+        return child;
+    }
+    
+    /**
+     * Append the children of another node to this node removing them from the other node .
+     * @param parent the other node whose children to append to this one
+     */
+    public void appendChildren(Node parent) {
+        Node child = parent.getFirstChild();
+        if (child == null) {
+            return;
+        }
+        ParentNode another = (ParentNode) parent;
+        if (firstChild == null) {
+            firstChild = child;
+        } else {
+            lastChild.setNextSibling(child);
+        }
+        lastChild = another.lastChild;
+        do {
+            child.setParentNode(this);
+        } while ((child = child.getNextSibling()) != null);
+        another.firstChild = null;
+        another.lastChild = null;
+    }
+
+    /**
+     * Remove a child from this node.
+     * @param node the child to remove
+     */
+    void removeChild(Node node) {
+        assert this == node.getParentNode();
+        if (firstChild == node) {
+            firstChild = node.getNextSibling();
+            if (lastChild == node) {
+                lastChild = null;
+            }
+        } else {
+            Node prev = firstChild;
+            Node next = firstChild.getNextSibling();
+            while (next != node) {
+                prev = next;
+                next = next.getNextSibling();
+            }
+            prev.setNextSibling(node.getNextSibling());
+            if (lastChild == node) {
+                lastChild = prev;
+            }            
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/PrefixMapping.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/PrefixMapping.java
new file mode 100644
index 000000000..8ffaf4a2c
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/PrefixMapping.java
@@ -0,0 +1,65 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+/**
+ * A prefix mapping.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class PrefixMapping {
+    /**
+     * The namespace prefix.
+     */
+    private final String prefix;
+    /**
+     * The namespace URI.
+     */
+    private final String uri;
+    /**
+     * Constructor.
+     * @param prefix the prefix
+     * @param uri the URI
+     */
+    public PrefixMapping(final String prefix, final String uri) {
+        this.prefix = prefix;
+        this.uri = uri;
+    }
+    /**
+     * Returns the prefix.
+     * 
+     * @return the prefix
+     */
+    public String getPrefix() {
+        return prefix;
+    }
+    /**
+     * Returns the uri.
+     * 
+     * @return the uri
+     */
+    public String getUri() {
+        return uri;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/ProcessingInstruction.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/ProcessingInstruction.java
new file mode 100644
index 000000000..014e63821
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/ProcessingInstruction.java
@@ -0,0 +1,94 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A processing instruction.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class ProcessingInstruction extends Node {
+
+    /**
+     * PI target.
+     */
+    private final String target;
+    
+    /**
+     * PI data.
+     */
+    private final String data;
+
+    /**
+     * Constructor.
+     * @param locator the locator
+     * @param target PI target
+     * @param data PI data
+     */
+    public ProcessingInstruction(Locator locator, String target, String data) {
+        super(locator);
+        this.target = target;
+        this.data = data;
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.processingInstruction(target, data, this);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.PROCESSING_INSTRUCTION;
+    }
+
+    /**
+     * Returns the data.
+     * 
+     * @return the data
+     */
+    public String getData() {
+        return data;
+    }
+
+    /**
+     * Returns the target.
+     * 
+     * @return the target
+     */
+    public String getTarget() {
+        return target;
+    }
+
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/SkippedEntity.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/SkippedEntity.java
new file mode 100644
index 000000000..01ca61490
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/SkippedEntity.java
@@ -0,0 +1,77 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+
+/**
+ * A skipped entity.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class SkippedEntity extends Node {
+
+    /**
+     * The name.
+     */
+    private final String name;
+
+    /**
+     * Constructor.
+     * @param locator the locator
+     * @param name the name
+     */
+    public SkippedEntity(Locator locator, String name) {
+        super(locator);
+        this.name = name;
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#visit(nu.validator.saxtree.TreeParser)
+     */
+    @Override
+    void visit(TreeParser treeParser) throws SAXException {
+        treeParser.skippedEntity(name, this);
+    }
+
+    /**
+     * 
+     * @see nu.validator.saxtree.Node#getNodeType()
+     */
+    @Override
+    public NodeType getNodeType() {
+        return NodeType.SKIPPED_ENTITY;
+    }
+
+    /**
+     * Returns the name.
+     * 
+     * @return the name
+     */
+    public String getName() {
+        return name;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/TreeBuilder.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/TreeBuilder.java
new file mode 100644
index 000000000..39fe236b3
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/TreeBuilder.java
@@ -0,0 +1,250 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import java.util.LinkedList;
+import java.util.List;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.ext.LexicalHandler;
+
+/**
+ * Builds a SAX Tree representation of a document or a fragment 
+ * streamed as <code>ContentHandler</code> and 
+ * <code>LexicalHandler</code> events. The start/end event matching 
+ * is expected to adhere to the SAX API contract. Things will 
+ * simply break if this is not the case. Fragments are expected to
+ * omit <code>startDocument()</code> and <code>endDocument()</code>
+ * calls.
+ * 
+ * @version $Id$
+ * @author hsivonen
+ */
+public class TreeBuilder implements ContentHandler, LexicalHandler {
+
+    /**
+     * The locator.
+     */
+    private Locator locator;
+
+    /**
+     * The current node.
+     */
+    private ParentNode current;
+
+    /**
+     * Whether to retain attribute objects.
+     */
+    private final boolean retainAttributes;
+
+    /**
+     * The prefix mappings for the next element to be inserted.
+     */
+    private List<PrefixMapping> prefixMappings;
+    
+    /**
+     * Constructs a reusable <code>TreeBuilder</code> that builds 
+     * <code>Document</code>s and copies attributes.
+     */
+    public TreeBuilder() {
+        this(false, false);
+    }
+    
+    /**
+     * The constructor. The instance will be reusabe if building a full 
+     * document and not reusable if building a fragment.
+     * 
+     * @param fragment whether this <code>TreeBuilder</code> should build 
+     * a <code>DocumentFragment</code> instead of a <code>Document</code>.
+     * @param retainAttributes whether instances of the <code>Attributes</code>
+     * interface passed to <code>startElement</code> should be retained 
+     * (the alternative is copying).
+     */
+    public TreeBuilder(boolean fragment, boolean retainAttributes) {
+        if (fragment) {
+            current = new DocumentFragment();
+        }
+        this.retainAttributes = retainAttributes;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#characters(char[], int, int)
+     */
+    public void characters(char[] ch, int start, int length) throws SAXException {
+        current.appendChild(new Characters(locator, ch, start, length));
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#endDocument()
+     */
+    public void endDocument() throws SAXException {
+        current.setEndLocator(locator);
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#endElement(java.lang.String, java.lang.String, java.lang.String)
+     */
+    public void endElement(String uri, String localName, String qName) throws SAXException {
+        current.setEndLocator(locator);
+        current = current.getParentNode();
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#endPrefixMapping(java.lang.String)
+     */
+    public void endPrefixMapping(String prefix) throws SAXException {
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#ignorableWhitespace(char[], int, int)
+     */
+    public void ignorableWhitespace(char[] ch, int start, int length) throws SAXException {
+        current.appendChild(new IgnorableWhitespace(locator, ch, start, length));
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#processingInstruction(java.lang.String, java.lang.String)
+     */
+    public void processingInstruction(String target, String data) throws SAXException {
+        current.appendChild(new ProcessingInstruction(locator, target, data));
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#setDocumentLocator(org.xml.sax.Locator)
+     */
+    public void setDocumentLocator(Locator locator) {
+        this.locator = locator;
+    }
+
+    public void skippedEntity(String name) throws SAXException {
+        current.appendChild(new SkippedEntity(locator, name));
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#startDocument()
+     */
+    public void startDocument() throws SAXException {
+        current = new Document(locator);
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#startElement(java.lang.String, java.lang.String, java.lang.String, org.xml.sax.Attributes)
+     */
+    public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException {
+        current = (ParentNode) current.appendChild(new Element(locator, uri, localName, qName, atts, retainAttributes, prefixMappings));
+        prefixMappings = null;
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ContentHandler#startPrefixMapping(java.lang.String, java.lang.String)
+     */
+    public void startPrefixMapping(String prefix, String uri) throws SAXException {
+        if (prefixMappings == null) {
+            prefixMappings = new LinkedList<PrefixMapping>();
+        }
+        prefixMappings.add(new PrefixMapping(prefix, uri));
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#comment(char[], int, int)
+     */
+    public void comment(char[] ch, int start, int length) throws SAXException {
+        current.appendChild(new Comment(locator, ch, start, length));
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#endCDATA()
+     */
+    public void endCDATA() throws SAXException {
+        current.setEndLocator(locator);
+        current = current.getParentNode();
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#endDTD()
+     */
+    public void endDTD() throws SAXException {
+        current.setEndLocator(locator);
+        current = current.getParentNode();
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#endEntity(java.lang.String)
+     */
+    public void endEntity(String name) throws SAXException {
+        current.setEndLocator(locator);
+        current = current.getParentNode();
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#startCDATA()
+     */
+    public void startCDATA() throws SAXException {
+        current = (ParentNode) current.appendChild(new CDATA(locator));        
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#startDTD(java.lang.String, java.lang.String, java.lang.String)
+     */
+    public void startDTD(String name, String publicId, String systemId) throws SAXException {
+        current = (ParentNode) current.appendChild(new DTD(locator, name, publicId, systemId));        
+    }
+
+    /**
+     * 
+     * @see org.xml.sax.ext.LexicalHandler#startEntity(java.lang.String)
+     */
+    public void startEntity(String name) throws SAXException {
+        current = (ParentNode) current.appendChild(new Entity(locator, name));        
+    }
+
+    /**
+     * Returns the root (<code>Document</code> if building a full document or 
+     * <code>DocumentFragment</code> if building a fragment.).
+     * 
+     * @return the root
+     */
+    public ParentNode getRoot() {
+        return current;
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/TreeParser.java b/parser/html/java/htmlparser/src/nu/validator/saxtree/TreeParser.java
new file mode 100644
index 000000000..a9d92deb0
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/TreeParser.java
@@ -0,0 +1,301 @@
+/*
+ * Copyright (c) 2007 Henri Sivonen
+ * Copyright (c) 2008 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a 
+ * copy of this software and associated documentation files (the "Software"), 
+ * to deal in the Software without restriction, including without limitation 
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ * and/or sell copies of the Software, and to permit persons to whom the 
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in 
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.saxtree;
+
+import org.xml.sax.Attributes;
+import org.xml.sax.ContentHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.ext.LexicalHandler;
+
+/**
+ * A tree visitor that replays a tree as SAX events.
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class TreeParser implements Locator {
+    
+    /**
+     * The content handler.
+     */
+    private final ContentHandler contentHandler;
+
+    /**
+     * The lexical handler.
+     */
+    private final LexicalHandler lexicalHandler;
+
+    /**
+     * The current locator.
+     */
+    private Locator locatorDelegate;
+
+    /**
+     * The constructor.
+     * 
+     * @param contentHandler
+     *            must not be <code>null</code>
+     * @param lexicalHandler
+     *            may be <code>null</code>
+     */
+    public TreeParser(final ContentHandler contentHandler,
+            final LexicalHandler lexicalHandler) {
+        if (contentHandler == null) {
+            throw new IllegalArgumentException("contentHandler was null.");
+        }
+        this.contentHandler = contentHandler;
+        if (lexicalHandler == null) {
+            this.lexicalHandler = new NullLexicalHandler();
+        } else {
+            this.lexicalHandler = lexicalHandler;
+        }
+    }
+
+    /**
+     * Causes SAX events for the tree rooted at the argument to be emitted.
+     * <code>startDocument()</code> and <code>endDocument()</code> are only
+     * emitted for a <code>Document</code> node.
+     * 
+     * @param node
+     *            the root
+     * @throws SAXException
+     */
+    public void parse(Node node) throws SAXException {
+        contentHandler.setDocumentLocator(this);
+        Node current = node;
+        Node next;
+        for (;;) {
+            current.visit(this);
+            if ((next = current.getFirstChild()) != null) {
+                current = next;
+                continue;
+            }
+            for (;;) {
+                current.revisit(this);
+                if (current == node) {
+                    return;
+                }
+                if ((next = current.getNextSibling()) != null) {
+                    current = next;
+                    break;
+                }
+                current = current.getParentNode();
+            }
+        }
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#characters(char[], int, int)
+     */
+    void characters(char[] ch, int start, int length, Locator locator)
+            throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.characters(ch, start, length);
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#endDocument()
+     */
+    void endDocument(Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.endDocument();
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#endElement(java.lang.String,
+     *      java.lang.String, java.lang.String)
+     */
+    void endElement(String uri, String localName, String qName, Locator locator)
+            throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.endElement(uri, localName, qName);
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#endPrefixMapping(java.lang.String)
+     */
+    void endPrefixMapping(String prefix, Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.endPrefixMapping(prefix);
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#ignorableWhitespace(char[], int, int)
+     */
+    void ignorableWhitespace(char[] ch, int start, int length, Locator locator)
+            throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.ignorableWhitespace(ch, start, length);
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#processingInstruction(java.lang.String,
+     *      java.lang.String)
+     */
+    void processingInstruction(String target, String data, Locator locator)
+            throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.processingInstruction(target, data);
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#skippedEntity(java.lang.String)
+     */
+    void skippedEntity(String name, Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.skippedEntity(name);
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#startDocument()
+     */
+    void startDocument(Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.startDocument();
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#startElement(java.lang.String,
+     *      java.lang.String, java.lang.String, org.xml.sax.Attributes)
+     */
+    void startElement(String uri, String localName, String qName,
+            Attributes atts, Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.startElement(uri, localName, qName, atts);
+    }
+
+    /**
+     * @see org.xml.sax.ContentHandler#startPrefixMapping(java.lang.String,
+     *      java.lang.String)
+     */
+    void startPrefixMapping(String prefix, String uri, Locator locator)
+            throws SAXException {
+        this.locatorDelegate = locator;
+        contentHandler.startPrefixMapping(prefix, uri);
+    }
+
+    /**
+     * @see org.xml.sax.ext.LexicalHandler#comment(char[], int, int)
+     */
+    void comment(char[] ch, int start, int length, Locator locator)
+            throws SAXException {
+        this.locatorDelegate = locator;
+        lexicalHandler.comment(ch, start, length);
+    }
+
+    /**
+     * @see org.xml.sax.ext.LexicalHandler#endCDATA()
+     */
+    void endCDATA(Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        lexicalHandler.endCDATA();
+    }
+
+    /**
+     * @see org.xml.sax.ext.LexicalHandler#endDTD()
+     */
+    void endDTD(Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        lexicalHandler.endDTD();
+    }
+
+    /**
+     * @see org.xml.sax.ext.LexicalHandler#endEntity(java.lang.String)
+     */
+    void endEntity(String name, Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        lexicalHandler.endEntity(name);
+    }
+
+    /**
+     * @see org.xml.sax.ext.LexicalHandler#startCDATA()
+     */
+    void startCDATA(Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        lexicalHandler.startCDATA();
+    }
+
+    /**
+     * @see org.xml.sax.ext.LexicalHandler#startDTD(java.lang.String,
+     *      java.lang.String, java.lang.String)
+     */
+    void startDTD(String name, String publicId, String systemId, Locator locator)
+            throws SAXException {
+        this.locatorDelegate = locator;
+        lexicalHandler.startDTD(name, publicId, systemId);
+    }
+
+    /**
+     * @see org.xml.sax.ext.LexicalHandler#startEntity(java.lang.String)
+     */
+    void startEntity(String name, Locator locator) throws SAXException {
+        this.locatorDelegate = locator;
+        lexicalHandler.startEntity(name);
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getColumnNumber()
+     */
+    public int getColumnNumber() {
+        if (locatorDelegate == null) {
+            return -1;
+        } else {
+            return locatorDelegate.getColumnNumber();
+        }
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getLineNumber()
+     */
+    public int getLineNumber() {
+        if (locatorDelegate == null) {
+            return -1;
+        } else {
+            return locatorDelegate.getLineNumber();
+        }
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getPublicId()
+     */
+    public String getPublicId() {
+        if (locatorDelegate == null) {
+            return null;
+        } else {
+
+            return locatorDelegate.getPublicId();
+        }
+    }
+
+    /**
+     * @see org.xml.sax.Locator#getSystemId()
+     */
+    public String getSystemId() {
+        if (locatorDelegate == null) {
+            return null;
+        } else {
+            return locatorDelegate.getSystemId();
+        }
+    }
+}
diff --git a/parser/html/java/htmlparser/src/nu/validator/saxtree/package.html b/parser/html/java/htmlparser/src/nu/validator/saxtree/package.html
new file mode 100644
index 000000000..0c34dad81
--- /dev/null
+++ b/parser/html/java/htmlparser/src/nu/validator/saxtree/package.html
@@ -0,0 +1,46 @@
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2 Final//EN">
+<html>
+<head><title>Package Overview</title>
+<!--
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a 
+ copy of this software and associated documentation files (the "Software"), 
+ to deal in the Software without restriction, including without limitation 
+ the rights to use, copy, modify, merge, publish, distribute, sublicense, 
+ and/or sell copies of the Software, and to permit persons to whom the 
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in 
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL 
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING 
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER 
+ DEALINGS IN THE SOFTWARE.
+-->
+</head>
+<body bgcolor="white">
+<p>This package provides SAX Tree: a tree model optimized for creation from SAX 
+events and replay as SAX events.</p>
+<h2>Design Principles</h2>
+<ol>
+<li>Preserve information exposed through <code>ContentHandler</code>, 
+<code>LexicalHandler</code> <em>and</em> <code>Locator</code>.
+<li>Creation from SAX events or as part of the parse of a conforming 
+HTML5 document should be <em>fast</em>.</li>
+<li>Emitting SAX events based on the tree should be <em>fast</em>.</li>
+<li>Mutations should be <em>possible</em> but should not make the above 
+"fast" cases slower.</li>
+<li>Concurrent reads should work without locking when there are no 
+concurrent mutations.</li>
+<li>The user of the API has the responsibility of using the API properly: 
+for the sake of performance, the model does not check if it is being 
+used properly. Improper use may, therefore, put the model in and 
+inconsistent state.</li>
+</ol>
+</body>
+</html>
\ No newline at end of file