diff options
Diffstat (limited to 'parser/html/javasrc')
| -rw-r--r-- | parser/html/javasrc/AttributeName.java | 2473 | ||||
| -rw-r--r-- | parser/html/javasrc/ElementName.java | 1609 | ||||
| -rw-r--r-- | parser/html/javasrc/HtmlAttributes.java | 618 | ||||
| -rw-r--r-- | parser/html/javasrc/MetaScanner.java | 854 | ||||
| -rw-r--r-- | parser/html/javasrc/Portability.java | 150 | ||||
| -rw-r--r-- | parser/html/javasrc/README.txt | 6 | ||||
| -rw-r--r-- | parser/html/javasrc/StackNode.java | 295 | ||||
| -rw-r--r-- | parser/html/javasrc/StateSnapshot.java | 204 | ||||
| -rw-r--r-- | parser/html/javasrc/Tokenizer.java | 7067 | ||||
| -rw-r--r-- | parser/html/javasrc/TreeBuilder.java | 6558 | ||||
| -rw-r--r-- | parser/html/javasrc/UTF16Buffer.java | 151 |
11 files changed, 19985 insertions, 0 deletions
diff --git a/parser/html/javasrc/AttributeName.java b/parser/html/javasrc/AttributeName.java new file mode 100644 index 000000000..7b889e71e --- /dev/null +++ b/parser/html/javasrc/AttributeName.java @@ -0,0 +1,2473 @@ +/* + * 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.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/javasrc/ElementName.java b/parser/html/javasrc/ElementName.java new file mode 100644 index 000000000..ee551a737 --- /dev/null +++ b/parser/html/javasrc/ElementName.java @@ -0,0 +1,1609 @@ +/* + * Copyright (c) 2008-2014 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 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_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_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_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_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_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_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 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_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_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_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_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_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_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_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 POLYGON = new ElementName("polygon", "polygon", TreeBuilder.OTHER); + public static final ElementName PATTERN = new ElementName("pattern", "pattern", TreeBuilder.OTHER); + public static final ElementName PICTURE = new ElementName("picture", "picture", 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_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_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_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, + 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, + POLYGON, + PATTERN, + PICTURE, + 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, + 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, + 252132601, + 252135604, + 251841204, + 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/javasrc/HtmlAttributes.java b/parser/html/javasrc/HtmlAttributes.java new file mode 100644 index 000000000..0ec25f96f --- /dev/null +++ b/parser/html/javasrc/HtmlAttributes.java @@ -0,0 +1,618 @@ +/* + * 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.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/javasrc/MetaScanner.java b/parser/html/javasrc/MetaScanner.java new file mode 100644 index 000000000..be9aabfe3 --- /dev/null +++ b/parser/html/javasrc/MetaScanner.java @@ -0,0 +1,854 @@ +/* + * Copyright (c) 2007 Henri Sivonen + * Copyright (c) 2008-2015 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.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/javasrc/Portability.java b/parser/html/javasrc/Portability.java new file mode 100644 index 000000000..485684ea1 --- /dev/null +++ b/parser/html/javasrc/Portability.java @@ -0,0 +1,150 @@ +/* + * Copyright (c) 2008-2015 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.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/javasrc/README.txt b/parser/html/javasrc/README.txt new file mode 100644 index 000000000..4555969ca --- /dev/null +++ b/parser/html/javasrc/README.txt @@ -0,0 +1,6 @@ +The .java files in this directory were placed here by the Java-to-C++ +translator that lives in parser/html/java/translator. Together they represent +a snapshot of the Java code that was translated to produce the corresponding +.h and .cpp files in the parent directory. Changing these .java files is not +worthwhile, as they will just be overwritten by the next translation. See +parser/html/java/README.txt for information about performing the translation. diff --git a/parser/html/javasrc/StackNode.java b/parser/html/javasrc/StackNode.java new file mode 100644 index 000000000..9aeaba0be --- /dev/null +++ b/parser/html/javasrc/StackNode.java @@ -0,0 +1,295 @@ +/* + * Copyright (c) 2007 Henri Sivonen + * Copyright (c) 2007-2011 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 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/javasrc/StateSnapshot.java b/parser/html/javasrc/StateSnapshot.java new file mode 100644 index 000000000..ff89e0443 --- /dev/null +++ b/parser/html/javasrc/StateSnapshot.java @@ -0,0 +1,204 @@ +/* + * 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; + +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/javasrc/Tokenizer.java b/parser/html/javasrc/Tokenizer.java new file mode 100644 index 000000000..d9eaafeb3 --- /dev/null +++ b/parser/html/javasrc/Tokenizer.java @@ -0,0 +1,7067 @@ +/* + * Copyright (c) 2005-2007 Henri Sivonen + * Copyright (c) 2007-2015 Mozilla Foundation + * 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; + // ∳ 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] + // ∳ 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 + * @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(); + } + + /** + * 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 '\u0000': + break stateloop; + 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); + if (c == '\u0000') { + break stateloop; + } + /* + * 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 '&': + 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); + if (c == '\u0000') { + break stateloop; + } + /* + * 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); + if (c == '\u0000') { + break stateloop; + } + 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 ¬it; I tell you, the + * entity is parsed as "not", as in, I'm ¬it; I tell + * you. But if the markup was I'm ∉ 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() assert (contentModelElement != + * null); Let's implement the above without lookahead. + * strBuf is the 'temporary buffer'. + */ + 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(); + if (c == '\u0000') { + emitReplacementCharacter(buf, pos); + } else { + cstart = pos; // don't drop the + // character + } + 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 ¬it; I tell you, the + * entity is parsed as "not", as in, I'm ¬it; I tell + * you. But if the markup was I'm ∉ 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/javasrc/TreeBuilder.java b/parser/html/javasrc/TreeBuilder.java new file mode 100644 index 000000000..5e83d1847 --- /dev/null +++ b/parser/html/javasrc/TreeBuilder.java @@ -0,0 +1,6558 @@ +/* + * Copyright (c) 2007 Henri Sivonen + * Copyright (c) 2007-2015 Mozilla Foundation + * 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_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.setStateAndEndTagExpectation(Tokenizer.DATA, + contextName); + // 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.setStateAndEndTagExpectation(Tokenizer.DATA, + contextName); + // 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.setStateAndEndTagExpectation(Tokenizer.RCDATA, + contextName); + } else if ("style" == contextName || "xmp" == contextName + || "iframe" == contextName || "noembed" == contextName + || "noframes" == contextName + || (scriptingEnabled && "noscript" == contextName)) { + tokenizer.setStateAndEndTagExpectation(Tokenizer.RAWTEXT, + contextName); + } else if ("plaintext" == contextName) { + tokenizer.setStateAndEndTagExpectation(Tokenizer.PLAINTEXT, + contextName); + } else if ("script" == contextName) { + tokenizer.setStateAndEndTagExpectation( + Tokenizer.SCRIPT_DATA, contextName); + } else { + tokenizer.setStateAndEndTagExpectation(Tokenizer.DATA, + contextName); + } + } + 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_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_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/javasrc/UTF16Buffer.java b/parser/html/javasrc/UTF16Buffer.java new file mode 100644 index 000000000..ec79185ec --- /dev/null +++ b/parser/html/javasrc/UTF16Buffer.java @@ -0,0 +1,151 @@ +/* + * 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; + +/** + * 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; + } +} |