summaryrefslogtreecommitdiffstats
path: root/devtools/shared/css/lexer.js
blob: 192fa95b3421df0d9cecb4ded5541f29c8422bb9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this
 * file, You can obtain one at http://mozilla.org/MPL/2.0/. */

// A CSS Lexer.  This file is a bit unusual -- it is a more or less
// direct translation of layout/style/nsCSSScanner.cpp and
// layout/style/CSSLexer.cpp into JS.  This implements the
// CSSLexer.webidl interface, and the intent is to try to keep it in
// sync with changes to the platform CSS lexer.  Due to this goal,
// this file violates some naming conventions and consequently locally
// disables some eslint rules.

/* eslint-disable camelcase, no-inline-comments, mozilla/no-aArgs */
/* eslint-disable no-else-return */

"use strict";

// White space of any kind.  No value fields are used.  Note that
// comments do *not* count as white space; comments separate tokens
// but are not themselves tokens.
const eCSSToken_Whitespace = "whitespace";     //
// A comment.
const eCSSToken_Comment = "comment";        // /*...*/

// Identifier-like tokens.  mIdent is the text of the identifier.
// The difference between ID and Hash is: if the text after the #
// would have been a valid Ident if the # hadn't been there, the
// scanner produces an ID token.  Otherwise it produces a Hash token.
// (This distinction is required by css3-selectors.)
const eCSSToken_Ident = "ident";          // word
const eCSSToken_Function = "function";       // word(
const eCSSToken_AtKeyword = "at";      // @word
const eCSSToken_ID = "id";             // #word
const eCSSToken_Hash = "hash";           // #0word

// Numeric tokens.  mNumber is the floating-point value of the
// number, and mHasSign indicates whether there was an explicit sign
// (+ or -) in front of the number.  If mIntegerValid is true, the
// number had the lexical form of an integer, and mInteger is its
// integer value.  Lexically integer values outside the range of a
// 32-bit signed number are clamped to the maximum values; mNumber
// will indicate a 'truer' value in that case.  Percentage tokens
// are always considered not to be integers, even if their numeric
// value is integral (100% => mNumber = 1.0).  For Dimension
// tokens, mIdent holds the text of the unit.
const eCSSToken_Number = "number";         // 1 -5 +2e3 3.14159 7.297352e-3
const eCSSToken_Dimension = "dimension";      // 24px 8.5in
const eCSSToken_Percentage = "percentage";     // 85% 1280.4%

// String-like tokens.  In all cases, mIdent holds the text
// belonging to the string, and mSymbol holds the delimiter
// character, which may be ', ", or zero (only for unquoted URLs).
// Bad_String and Bad_URL tokens are emitted when the closing
// delimiter or parenthesis was missing.
const eCSSToken_String = "string";         // 'foo bar' "foo bar"
const eCSSToken_Bad_String = "bad_string";     // 'foo bar
const eCSSToken_URL = "url";            // url(foobar) url("foo bar")
const eCSSToken_Bad_URL = "bad_url";        // url(foo

// Any one-character symbol.  mSymbol holds the character.
const eCSSToken_Symbol = "symbol";         // . ; { } ! *

// Match operators.  These are single tokens rather than pairs of
// Symbol tokens because css3-selectors forbids the presence of
// comments between the two characters.  No value fields are used;
// the token type indicates which operator.
const eCSSToken_Includes = "includes";       // ~=
const eCSSToken_Dashmatch = "dashmatch";      // |=
const eCSSToken_Beginsmatch = "beginsmatch";    // ^=
const eCSSToken_Endsmatch = "endsmatch";      // $=
const eCSSToken_Containsmatch = "containsmatch";  // *=

// Unicode-range token: currently used only in @font-face.
// The lexical rule for this token includes several forms that are
// semantically invalid.  Therefore, mIdent always holds the
// complete original text of the token (so we can print it
// accurately in diagnostics), and mIntegerValid is true iff the
// token is semantically valid.  In that case, mInteger holds the
// lowest value included in the range, and mInteger2 holds the
// highest value included in the range.
const eCSSToken_URange = "urange";         // U+007e U+01?? U+2000-206F

// HTML comment delimiters, ignored as a unit when they appear at
// the top level of a style sheet, for compatibility with websites
// written for compatibility with pre-CSS browsers.  This token type
// subsumes the css2.1 CDO and CDC tokens, which are always treated
// the same by the parser.  mIdent holds the text of the token, for
// diagnostics.
const eCSSToken_HTMLComment = "htmlcomment";    // <!-- -->

const eEOFCharacters_None = 0x0000;

// to handle \<EOF> inside strings
const eEOFCharacters_DropBackslash = 0x0001;

// to handle \<EOF> outside strings
const eEOFCharacters_ReplacementChar = 0x0002;

// to close comments
const eEOFCharacters_Asterisk = 0x0004;
const eEOFCharacters_Slash = 0x0008;

// to close double-quoted strings
const eEOFCharacters_DoubleQuote = 0x0010;

// to close single-quoted strings
const eEOFCharacters_SingleQuote = 0x0020;

// to close URLs
const eEOFCharacters_CloseParen = 0x0040;

// Bridge the char/string divide.
const APOSTROPHE = "'".charCodeAt(0);
const ASTERISK = "*".charCodeAt(0);
const CARRIAGE_RETURN = "\r".charCodeAt(0);
const CIRCUMFLEX_ACCENT = "^".charCodeAt(0);
const COMMERCIAL_AT = "@".charCodeAt(0);
const DIGIT_NINE = "9".charCodeAt(0);
const DIGIT_ZERO = "0".charCodeAt(0);
const DOLLAR_SIGN = "$".charCodeAt(0);
const EQUALS_SIGN = "=".charCodeAt(0);
const EXCLAMATION_MARK = "!".charCodeAt(0);
const FULL_STOP = ".".charCodeAt(0);
const GREATER_THAN_SIGN = ">".charCodeAt(0);
const HYPHEN_MINUS = "-".charCodeAt(0);
const LATIN_CAPITAL_LETTER_E = "E".charCodeAt(0);
const LATIN_CAPITAL_LETTER_U = "U".charCodeAt(0);
const LATIN_SMALL_LETTER_E = "e".charCodeAt(0);
const LATIN_SMALL_LETTER_U = "u".charCodeAt(0);
const LEFT_PARENTHESIS = "(".charCodeAt(0);
const LESS_THAN_SIGN = "<".charCodeAt(0);
const LINE_FEED = "\n".charCodeAt(0);
const NUMBER_SIGN = "#".charCodeAt(0);
const PERCENT_SIGN = "%".charCodeAt(0);
const PLUS_SIGN = "+".charCodeAt(0);
const QUESTION_MARK = "?".charCodeAt(0);
const QUOTATION_MARK = "\"".charCodeAt(0);
const REVERSE_SOLIDUS = "\\".charCodeAt(0);
const RIGHT_PARENTHESIS = ")".charCodeAt(0);
const SOLIDUS = "/".charCodeAt(0);
const TILDE = "~".charCodeAt(0);
const VERTICAL_LINE = "|".charCodeAt(0);

const UCS2_REPLACEMENT_CHAR = 0xFFFD;

const kImpliedEOFCharacters = [
  UCS2_REPLACEMENT_CHAR,
  ASTERISK,
  SOLIDUS,
  QUOTATION_MARK,
  APOSTROPHE,
  RIGHT_PARENTHESIS,
  0
];

/**
 * Ensure that the character is valid.  If it is valid, return it;
 * otherwise, return the replacement character.
 *
 * @param {Number} c the character to check
 * @return {Number} the character or its replacement
 */
function ensureValidChar(c) {
  if (c >= 0x00110000 || (c & 0xFFF800) == 0xD800) {
    // Out of range or a surrogate.
    return UCS2_REPLACEMENT_CHAR;
  }
  return c;
}

/**
 * Turn a string into an array of character codes.
 *
 * @param {String} str the input string
 * @return {Array} an array of character codes, one per character in
 *         the input string.
 */
function stringToCodes(str) {
  return Array.prototype.map.call(str, (c) => c.charCodeAt(0));
}

const IS_HEX_DIGIT = 0x01;
const IS_IDSTART = 0x02;
const IS_IDCHAR = 0x04;
const IS_URL_CHAR = 0x08;
const IS_HSPACE = 0x10;
const IS_VSPACE = 0x20;
const IS_SPACE = IS_HSPACE | IS_VSPACE;
const IS_STRING = 0x40;

const H = IS_HSPACE;
const V = IS_VSPACE;
const I = IS_IDCHAR;
const J = IS_IDSTART;
const U = IS_URL_CHAR;
const S = IS_STRING;
const X = IS_HEX_DIGIT;

const SH = S | H;
const SU = S | U;
const SUI = S | U | I;
const SUIJ = S | U | I | J;
const SUIX = S | U | I | X;
const SUIJX = S | U | I | J | X;

/* eslint-disable indent, no-multi-spaces, comma-spacing, spaced-comment */
const gLexTable = [
// 00    01    02    03    04    05    06    07
    0,    S,    S,    S,    S,    S,    S,    S,
// 08   TAB    LF    0B    FF    CR    0E    0F
    S,   SH,    V,    S,    V,    V,    S,    S,
// 10    11    12    13    14    15    16    17
    S,    S,    S,    S,    S,    S,    S,    S,
// 18    19    1A    1B    1C    1D    1E    1F
    S,    S,    S,    S,    S,    S,    S,    S,
//SPC     !     "     #     $     %     &     '
   SH,   SU,    0,   SU,   SU,   SU,   SU,    0,
//  (     )     *     +     ,     -     .     /
    S,    S,   SU,   SU,   SU,  SUI,   SU,   SU,
//  0     1     2     3     4     5     6     7
 SUIX, SUIX, SUIX, SUIX, SUIX, SUIX, SUIX, SUIX,
//  8     9     :     ;     <     =     >     ?
 SUIX, SUIX,   SU,   SU,   SU,   SU,   SU,   SU,
//  @     A     B     C     D     E     F     G
   SU,SUIJX,SUIJX,SUIJX,SUIJX,SUIJX,SUIJX, SUIJ,
//  H     I     J     K     L     M     N     O
 SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ,
//  P     Q     R     S     T     U     V     W
 SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ,
//  X     Y     Z     [     \     ]     ^     _
 SUIJ, SUIJ, SUIJ,   SU,    J,   SU,   SU, SUIJ,
//  `     a     b     c     d     e     f     g
   SU,SUIJX,SUIJX,SUIJX,SUIJX,SUIJX,SUIJX, SUIJ,
//  h     i     j     k     l     m     n     o
 SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ,
//  p     q     r     s     t     u     v     w
 SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ, SUIJ,
//  x     y     z     {     |     }     ~    7F
 SUIJ, SUIJ, SUIJ,   SU,   SU,   SU,   SU,    S,
];
/* eslint-enable indent, no-multi-spaces, comma-spacing, spaced-comment */

/**
 * True if 'ch' is in character class 'cls', which should be one of
 * the constants above or some combination of them.  All characters
 * above U+007F are considered to be in 'cls'.  EOF is never in 'cls'.
 */
function IsOpenCharClass(ch, cls) {
  return ch >= 0 && (ch >= 128 || (gLexTable[ch] & cls) != 0);
}

/**
 * True if 'ch' is in character class 'cls', which should be one of
 * the constants above or some combination of them.  No characters
 * above U+007F are considered to be in 'cls'. EOF is never in 'cls'.
 */
function IsClosedCharClass(ch, cls) {
  return ch >= 0 && ch < 128 && (gLexTable[ch] & cls) != 0;
}

/**
 * True if 'ch' is CSS whitespace, i.e. any of the ASCII characters
 * TAB, LF, FF, CR, or SPC.
 */
function IsWhitespace(ch) {
  return IsClosedCharClass(ch, IS_SPACE);
}

/**
 * True if 'ch' is horizontal whitespace, i.e. TAB or SPC.
 */
function IsHorzSpace(ch) {
  return IsClosedCharClass(ch, IS_HSPACE);
}

/**
 * True if 'ch' is vertical whitespace, i.e. LF, FF, or CR.  Vertical
 * whitespace requires special handling when consumed, see AdvanceLine.
 */
function IsVertSpace(ch) {
  return IsClosedCharClass(ch, IS_VSPACE);
}

/**
 * True if 'ch' is a character that can appear in the middle of an identifier.
 * This includes U+0000 since it is handled as U+FFFD, but for purposes of
 * GatherText it should not be included in IsOpenCharClass.
 */
function IsIdentChar(ch) {
  return IsOpenCharClass(ch, IS_IDCHAR) || ch == 0;
}

/**
 * True if 'ch' is a character that by itself begins an identifier.
 * This includes U+0000 since it is handled as U+FFFD, but for purposes of
 * GatherText it should not be included in IsOpenCharClass.
 * (This is a subset of IsIdentChar.)
 */
function IsIdentStart(ch) {
  return IsOpenCharClass(ch, IS_IDSTART) || ch == 0;
}

/**
 * True if the two-character sequence aFirstChar+aSecondChar begins an
 * identifier.
 */
function StartsIdent(aFirstChar, aSecondChar) {
  return IsIdentStart(aFirstChar) ||
    (aFirstChar == HYPHEN_MINUS && (aSecondChar == HYPHEN_MINUS ||
                                    IsIdentStart(aSecondChar)));
}

/**
 * True if 'ch' is a decimal digit.
 */
function IsDigit(ch) {
  return (ch >= DIGIT_ZERO) && (ch <= DIGIT_NINE);
}

/**
 * True if 'ch' is a hexadecimal digit.
 */
function IsHexDigit(ch) {
  return IsClosedCharClass(ch, IS_HEX_DIGIT);
}

/**
 * Assuming that 'ch' is a decimal digit, return its numeric value.
 */
function DecimalDigitValue(ch) {
  return ch - DIGIT_ZERO;
}

/**
 * Assuming that 'ch' is a hexadecimal digit, return its numeric value.
 */
function HexDigitValue(ch) {
  if (IsDigit(ch)) {
    return DecimalDigitValue(ch);
  } else {
    // Note: c&7 just keeps the low three bits which causes
    // upper and lower case alphabetics to both yield their
    // "relative to 10" value for computing the hex value.
    return (ch & 0x7) + 9;
  }
}

/**
 * If 'ch' can be the first character of a two-character match operator
 * token, return the token type code for that token, otherwise return
 * eCSSToken_Symbol to indicate that it can't.
 */
function MatchOperatorType(ch) {
  switch (ch) {
    case TILDE: return eCSSToken_Includes;
    case VERTICAL_LINE: return eCSSToken_Dashmatch;
    case CIRCUMFLEX_ACCENT: return eCSSToken_Beginsmatch;
    case DOLLAR_SIGN: return eCSSToken_Endsmatch;
    case ASTERISK: return eCSSToken_Containsmatch;
    default: return eCSSToken_Symbol;
  }
}

function Scanner(buffer) {
  this.mBuffer = buffer || "";
  this.mOffset = 0;
  this.mCount = this.mBuffer.length;
  this.mLineNumber = 1;
  this.mLineOffset = 0;
  this.mTokenLineOffset = 0;
  this.mTokenOffset = 0;
  this.mTokenLineNumber = 1;
  this.mEOFCharacters = eEOFCharacters_None;
}

Scanner.prototype = {
  /**
   * @see CSSLexer.lineNumber
   */
  get lineNumber() {
    return this.mTokenLineNumber - 1;
  },

  /**
   * @see CSSLexer.columnNumber
   */
  get columnNumber() {
    return this.mTokenOffset - this.mTokenLineOffset;
  },

  /**
   * @see CSSLexer.performEOFFixup
   */
  performEOFFixup: function (aInputString, aPreserveBackslash) {
    let result = aInputString;

    let eofChars = this.mEOFCharacters;

    if (aPreserveBackslash &&
        (eofChars & (eEOFCharacters_DropBackslash |
                     eEOFCharacters_ReplacementChar)) != 0) {
      eofChars &= ~(eEOFCharacters_DropBackslash |
                    eEOFCharacters_ReplacementChar);
      result += "\\";
    }

    if ((eofChars & eEOFCharacters_DropBackslash) != 0 &&
        result.length > 0 && result.endsWith("\\")) {
      result = result.slice(0, -1);
    }

    let extra = [];
    this.AppendImpliedEOFCharacters(eofChars, extra);
    let asString = String.fromCharCode.apply(null, extra);

    return result + asString;
  },

  /**
   * @see CSSLexer.nextToken
   */
  nextToken: function () {
    let token = {};
    if (!this.Next(token)) {
      return null;
    }

    let resultToken = {};
    resultToken.tokenType = token.mType;
    resultToken.startOffset = this.mTokenOffset;
    resultToken.endOffset = this.mOffset;

    let constructText = () => {
      return String.fromCharCode.apply(null, token.mIdent);
    };

    switch (token.mType) {
      case eCSSToken_Whitespace:
        break;

      case eCSSToken_Ident:
      case eCSSToken_Function:
      case eCSSToken_AtKeyword:
      case eCSSToken_ID:
      case eCSSToken_Hash:
        resultToken.text = constructText();
        break;

      case eCSSToken_Dimension:
        resultToken.text = constructText();
        /* Fall through.  */
      case eCSSToken_Number:
      case eCSSToken_Percentage:
        resultToken.number = token.mNumber;
        resultToken.hasSign = token.mHasSign;
        resultToken.isInteger = token.mIntegerValid;
        break;

      case eCSSToken_String:
      case eCSSToken_Bad_String:
      case eCSSToken_URL:
      case eCSSToken_Bad_URL:
        resultToken.text = constructText();
        /* Don't bother emitting the delimiter, as it is readily extracted
           from the source string when needed.  */
        break;

      case eCSSToken_Symbol:
        resultToken.text = String.fromCharCode(token.mSymbol);
        break;

      case eCSSToken_Includes:
      case eCSSToken_Dashmatch:
      case eCSSToken_Beginsmatch:
      case eCSSToken_Endsmatch:
      case eCSSToken_Containsmatch:
      case eCSSToken_URange:
        break;

      case eCSSToken_Comment:
      case eCSSToken_HTMLComment:
        /* The comment text is easily extracted from the source string,
           and is rarely useful.  */
        break;
    }

    return resultToken;
  },

  /**
   * Return the raw UTF-16 code unit at position |this.mOffset + n| within
   * the read buffer.  If that is beyond the end of the buffer, returns
   * -1 to indicate end of input.
   */
  Peek: function (n = 0) {
    if (this.mOffset + n >= this.mCount) {
      return -1;
    }
    return this.mBuffer.charCodeAt(this.mOffset + n);
  },

  /**
   * Advance |this.mOffset| over |n| code units.  Advance(0) is a no-op.
   * If |n| is greater than the distance to end of input, will silently
   * stop at the end.  May not be used to advance over a line boundary;
   * AdvanceLine() must be used instead.
   */
  Advance: function (n = 1) {
    if (this.mOffset + n >= this.mCount || this.mOffset + n < this.mOffset) {
      this.mOffset = this.mCount;
    } else {
      this.mOffset += n;
    }
  },

  /**
   * Advance |this.mOffset| over a line boundary.
   */
  AdvanceLine: function () {
    // Advance over \r\n as a unit.
    if (this.mBuffer.charCodeAt(this.mOffset) == CARRIAGE_RETURN &&
        this.mOffset + 1 < this.mCount &&
        this.mBuffer.charCodeAt(this.mOffset + 1) == LINE_FEED) {
      this.mOffset += 2;
    } else {
      this.mOffset += 1;
    }
    // 0 is a magical line number meaning that we don't know (i.e., script)
    if (this.mLineNumber != 0) {
      this.mLineNumber++;
    }
    this.mLineOffset = this.mOffset;
  },

  /**
   * Skip over a sequence of whitespace characters (vertical or
   * horizontal) starting at the current read position.
   */
  SkipWhitespace: function () {
    for (;;) {
      let ch = this.Peek();
      if (!IsWhitespace(ch)) { // EOF counts as non-whitespace
        break;
      }
      if (IsVertSpace(ch)) {
        this.AdvanceLine();
      } else {
        this.Advance();
      }
    }
  },

  /**
   * Skip over one CSS comment starting at the current read position.
   */
  SkipComment: function () {
    this.Advance(2);
    for (;;) {
      let ch = this.Peek();
      if (ch < 0) {
        this.SetEOFCharacters(eEOFCharacters_Asterisk | eEOFCharacters_Slash);
        return;
      }
      if (ch == ASTERISK) {
        this.Advance();
        ch = this.Peek();
        if (ch < 0) {
          this.SetEOFCharacters(eEOFCharacters_Slash);
          return;
        }
        if (ch == SOLIDUS) {
          this.Advance();
          return;
        }
      } else if (IsVertSpace(ch)) {
        this.AdvanceLine();
      } else {
        this.Advance();
      }
    }
  },

  /**
   * If there is a valid escape sequence starting at the current read
   * position, consume it, decode it, append the result to |aOutput|,
   * and return true.  Otherwise, consume nothing, leave |aOutput|
   * unmodified, and return false.  If |aInString| is true, accept the
   * additional form of escape sequence allowed within string-like tokens.
   */
  GatherEscape: function (aOutput, aInString) {
    let ch = this.Peek(1);
    if (ch < 0) {
      // If we are in a string (or a url() containing a string), we want to drop
      // the backslash on the floor.  Otherwise, we want to treat it as a U+FFFD
      // character.
      this.Advance();
      if (aInString) {
        this.SetEOFCharacters(eEOFCharacters_DropBackslash);
      } else {
        aOutput.push(UCS2_REPLACEMENT_CHAR);
        this.SetEOFCharacters(eEOFCharacters_ReplacementChar);
      }
      return true;
    }
    if (IsVertSpace(ch)) {
      if (aInString) {
        // In strings (and in url() containing a string), escaped
        // newlines are completely removed, to allow splitting over
        // multiple lines.
        this.Advance();
        this.AdvanceLine();
        return true;
      }
      // Outside of strings, backslash followed by a newline is not an escape.
      return false;
    }

    if (!IsHexDigit(ch)) {
      // "Any character (except a hexadecimal digit, linefeed, carriage
      // return, or form feed) can be escaped with a backslash to remove
      // its special meaning." -- CSS2.1 section 4.1.3
      this.Advance(2);
      if (ch == 0) {
        aOutput.push(UCS2_REPLACEMENT_CHAR);
      } else {
        aOutput.push(ch);
      }
      return true;
    }

    // "[at most six hexadecimal digits following a backslash] stand
    // for the ISO 10646 character with that number, which must not be
    // zero. (It is undefined in CSS 2.1 what happens if a style sheet
    // does contain a character with Unicode codepoint zero.)"
    //   -- CSS2.1 section 4.1.3

    // At this point we know we have \ followed by at least one
    // hexadecimal digit, therefore the escape sequence is valid and we
    // can go ahead and consume the backslash.
    this.Advance();
    let val = 0;
    let i = 0;
    do {
      val = val * 16 + HexDigitValue(ch);
      i++;
      this.Advance();
      ch = this.Peek();
    } while (i < 6 && IsHexDigit(ch));

    // "Interpret the hex digits as a hexadecimal number. If this
    // number is zero, or is greater than the maximum allowed
    // codepoint, return U+FFFD REPLACEMENT CHARACTER" -- CSS Syntax
    // Level 3
    if (val == 0) {
      aOutput.push(UCS2_REPLACEMENT_CHAR);
    } else {
      aOutput.push(ensureValidChar(val));
    }

    // Consume exactly one whitespace character after a
    // hexadecimal escape sequence.
    if (IsVertSpace(ch)) {
      this.AdvanceLine();
    } else if (IsHorzSpace(ch)) {
      this.Advance();
    }
    return true;
  },

  /**
   * Consume a run of "text" beginning with the current read position,
   * consisting of characters in the class |aClass| (which must be a
   * suitable argument to IsOpenCharClass) plus escape sequences.
   * Append the text to |aText|, after decoding escape sequences.
   *
   * Returns true if at least one character was appended to |aText|,
   * false otherwise.
   */
  GatherText: function (aClass, aText) {
    let start = this.mOffset;
    let inString = aClass == IS_STRING;

    for (;;) {
      // Consume runs of unescaped characters in one go.
      let n = this.mOffset;
      while (n < this.mCount && IsOpenCharClass(this.mBuffer.charCodeAt(n),
                                                aClass)) {
        n++;
      }
      if (n > this.mOffset) {
        let substr = this.mBuffer.slice(this.mOffset, n);
        Array.prototype.push.apply(aText, stringToCodes(substr));
        this.mOffset = n;
      }
      if (n == this.mCount) {
        break;
      }

      let ch = this.Peek();
      if (ch == 0) {
        this.Advance();
        aText.push(UCS2_REPLACEMENT_CHAR);
        continue;
      }

      if (ch != REVERSE_SOLIDUS) {
        break;
      }
      if (!this.GatherEscape(aText, inString)) {
        break;
      }
    }

    return this.mOffset > start;
  },

  /**
   * Scan an Ident token.  This also handles Function and URL tokens,
   * both of which begin indistinguishably from an identifier.  It can
   * produce a Symbol token when an apparent identifier actually led
   * into an invalid escape sequence.
   */
  ScanIdent: function (aToken) {
    if (!this.GatherText(IS_IDCHAR, aToken.mIdent)) {
      aToken.mSymbol = this.Peek();
      this.Advance();
      return true;
    }

    if (this.Peek() != LEFT_PARENTHESIS) {
      aToken.mType = eCSSToken_Ident;
      return true;
    }

    this.Advance();
    aToken.mType = eCSSToken_Function;

    let asString = String.fromCharCode.apply(null, aToken.mIdent);
    if (asString.toLowerCase() === "url") {
      this.NextURL(aToken);
    }
    return true;
  },

  /**
   * Scan an AtKeyword token.  Also handles production of Symbol when
   * an '@' is not followed by an identifier.
   */
  ScanAtKeyword: function (aToken) {
    // Fall back for when '@' isn't followed by an identifier.
    aToken.mSymbol = COMMERCIAL_AT;
    this.Advance();

    let ch = this.Peek();
    if (StartsIdent(ch, this.Peek(1))) {
      if (this.GatherText(IS_IDCHAR, aToken.mIdent)) {
        aToken.mType = eCSSToken_AtKeyword;
      }
    }
    return true;
  },

  /**
   * Scan a Hash token.  Handles the distinction between eCSSToken_ID
   * and eCSSToken_Hash, and handles production of Symbol when a '#'
   * is not followed by identifier characters.
   */
  ScanHash: function (aToken) {
    // Fall back for when '#' isn't followed by identifier characters.
    aToken.mSymbol = NUMBER_SIGN;
    this.Advance();

    let ch = this.Peek();
    if (IsIdentChar(ch) || ch == REVERSE_SOLIDUS) {
      let type =
          StartsIdent(ch, this.Peek(1)) ? eCSSToken_ID : eCSSToken_Hash;
      aToken.mIdent.length = 0;
      if (this.GatherText(IS_IDCHAR, aToken.mIdent)) {
        aToken.mType = type;
      }
    }

    return true;
  },

  /**
   * Scan a Number, Percentage, or Dimension token (all of which begin
   * like a Number).  Can produce a Symbol when a '.' is not followed by
   * digits, or when '+' or '-' are not followed by either a digit or a
   * '.' and then a digit.  Can also produce a HTMLComment when it
   * encounters '-->'.
   */
  ScanNumber: function (aToken) {
    let c = this.Peek();

    // Sign of the mantissa (-1 or 1).
    let sign = c == HYPHEN_MINUS ? -1 : 1;
    // Absolute value of the integer part of the mantissa.  This is a double so
    // we don't run into overflow issues for consumers that only care about our
    // floating-point value while still being able to express the full int32_t
    // range for consumers who want integers.
    let intPart = 0;
    // Fractional part of the mantissa.  This is a double so that when
    // we convert to float at the end we'll end up rounding to nearest
    // float instead of truncating down (as we would if fracPart were
    // a float and we just effectively lost the last several digits).
    let fracPart = 0;
    // Absolute value of the power of 10 that we should multiply by
    // (only relevant for numbers in scientific notation).  Has to be
    // a signed integer, because multiplication of signed by unsigned
    // converts the unsigned to signed, so if we plan to actually
    // multiply by expSign...
    let exponent = 0;
    // Sign of the exponent.
    let expSign = 1;

    aToken.mHasSign = (c == PLUS_SIGN || c == HYPHEN_MINUS);
    if (aToken.mHasSign) {
      this.Advance();
      c = this.Peek();
    }

    let gotDot = (c == FULL_STOP);

    if (!gotDot) {
      // Scan the integer part of the mantissa.
      do {
        intPart = 10 * intPart + DecimalDigitValue(c);
        this.Advance();
        c = this.Peek();
      } while (IsDigit(c));

      gotDot = (c == FULL_STOP) && IsDigit(this.Peek(1));
    }

    if (gotDot) {
      // Scan the fractional part of the mantissa.
      this.Advance();
      c = this.Peek();
      // Power of ten by which we need to divide our next digit
      let divisor = 10;
      do {
        fracPart += DecimalDigitValue(c) / divisor;
        divisor *= 10;
        this.Advance();
        c = this.Peek();
      } while (IsDigit(c));
    }

    let gotE = false;
    if (c == LATIN_SMALL_LETTER_E || c == LATIN_CAPITAL_LETTER_E) {
      let expSignChar = this.Peek(1);
      let nextChar = this.Peek(2);
      if (IsDigit(expSignChar) ||
          ((expSignChar == HYPHEN_MINUS || expSignChar == PLUS_SIGN) &&
           IsDigit(nextChar))) {
        gotE = true;
        if (expSignChar == HYPHEN_MINUS) {
          expSign = -1;
        }
        this.Advance(); // consumes the E
        if (expSignChar == HYPHEN_MINUS || expSignChar == PLUS_SIGN) {
          this.Advance();
          c = nextChar;
        } else {
          c = expSignChar;
        }
        do {
          exponent = 10 * exponent + DecimalDigitValue(c);
          this.Advance();
          c = this.Peek();
        } while (IsDigit(c));
      }
    }

    let type = eCSSToken_Number;

    // Set mIntegerValid for all cases (except %, below) because we need
    // it for the "2n" in :nth-child(2n).
    aToken.mIntegerValid = false;

    // Time to reassemble our number.
    // Do all the math in double precision so it's truncated only once.
    let value = sign * (intPart + fracPart);
    if (gotE) {
      // Explicitly cast expSign*exponent to double to avoid issues with
      // overloaded pow() on Windows.
      value *= Math.pow(10.0, expSign * exponent);
    } else if (!gotDot) {
      // Clamp values outside of integer range.
      if (sign > 0) {
        aToken.mInteger = Math.min(intPart, Number.MAX_SAFE_INTEGER);
      } else {
        aToken.mInteger = Math.max(-intPart, Number.MIN_SAFE_INTEGER);
      }
      aToken.mIntegerValid = true;
    }

    let ident = aToken.mIdent;

    // Check for Dimension and Percentage tokens.
    if (c >= 0) {
      if (StartsIdent(c, this.Peek(1))) {
        if (this.GatherText(IS_IDCHAR, ident)) {
          type = eCSSToken_Dimension;
        }
      } else if (c == PERCENT_SIGN) {
        this.Advance();
        type = eCSSToken_Percentage;
        value = value / 100.0;
        aToken.mIntegerValid = false;
      }
    }
    aToken.mNumber = value;
    aToken.mType = type;
    return true;
  },

  /**
   * Scan a string constant ('foo' or "foo").  Will always produce
   * either a String or a Bad_String token; the latter occurs when the
   * close quote is missing.  Always returns true (for convenience in Next()).
   */
  ScanString: function (aToken) {
    let aStop = this.Peek();
    aToken.mType = eCSSToken_String;
    aToken.mSymbol = aStop; // Remember how it's quoted.
    this.Advance();

    for (;;) {
      this.GatherText(IS_STRING, aToken.mIdent);

      let ch = this.Peek();
      if (ch == -1) {
        this.AddEOFCharacters(aStop == QUOTATION_MARK ?
                              eEOFCharacters_DoubleQuote :
                              eEOFCharacters_SingleQuote);
        break; // EOF ends a string token with no error.
      }
      if (ch == aStop) {
        this.Advance();
        break;
      }
      // Both " and ' are excluded from IS_STRING.
      if (ch == QUOTATION_MARK || ch == APOSTROPHE) {
        aToken.mIdent.push(ch);
        this.Advance();
        continue;
      }

      aToken.mType = eCSSToken_Bad_String;
      break;
    }
    return true;
  },

  /**
   * Scan a unicode-range token.  These match the regular expression
   *
   *     u\+[0-9a-f?]{1,6}(-[0-9a-f]{1,6})?
   *
   * However, some such tokens are "invalid".  There are three valid forms:
   *
   *     u+[0-9a-f]{x}              1 <= x <= 6
   *     u+[0-9a-f]{x}\?{y}         1 <= x+y <= 6
   *     u+[0-9a-f]{x}-[0-9a-f]{y}  1 <= x <= 6, 1 <= y <= 6
   *
   * All unicode-range tokens have their text recorded in mIdent; valid ones
   * are also decoded into mInteger and mInteger2, and mIntegerValid is set.
   * Note that this does not validate the numeric range, only the syntactic
   * form.
   */
  ScanURange: function (aResult) {
    let intro1 = this.Peek();
    let intro2 = this.Peek(1);
    let ch = this.Peek(2);

    aResult.mIdent.push(intro1);
    aResult.mIdent.push(intro2);
    this.Advance(2);

    let valid = true;
    let haveQues = false;
    let low = 0;
    let high = 0;
    let i = 0;

    do {
      aResult.mIdent.push(ch);
      if (IsHexDigit(ch)) {
        if (haveQues) {
          valid = false; // All question marks should be at the end.
        }
        low = low * 16 + HexDigitValue(ch);
        high = high * 16 + HexDigitValue(ch);
      } else {
        haveQues = true;
        low = low * 16 + 0x0;
        high = high * 16 + 0xF;
      }

      i++;
      this.Advance();
      ch = this.Peek();
    } while (i < 6 && (IsHexDigit(ch) || ch == QUESTION_MARK));

    if (ch == HYPHEN_MINUS && IsHexDigit(this.Peek(1))) {
      if (haveQues) {
        valid = false;
      }

      aResult.mIdent.push(ch);
      this.Advance();
      ch = this.Peek();
      high = 0;
      i = 0;
      do {
        aResult.mIdent.push(ch);
        high = high * 16 + HexDigitValue(ch);

        i++;
        this.Advance();
        ch = this.Peek();
      } while (i < 6 && IsHexDigit(ch));
    }

    aResult.mInteger = low;
    aResult.mInteger2 = high;
    aResult.mIntegerValid = valid;
    aResult.mType = eCSSToken_URange;
    return true;
  },

  SetEOFCharacters: function (aEOFCharacters) {
    this.mEOFCharacters = aEOFCharacters;
  },

  AddEOFCharacters: function (aEOFCharacters) {
    this.mEOFCharacters = this.mEOFCharacters | aEOFCharacters;
  },

  AppendImpliedEOFCharacters: function (aEOFCharacters, aResult) {
    // First, ignore eEOFCharacters_DropBackslash.
    let c = aEOFCharacters >> 1;

    // All of the remaining EOFCharacters bits represent appended characters,
    // and the bits are in the order that they need appending.
    for (let p of kImpliedEOFCharacters) {
      if (c & 1) {
        aResult.push(p);
      }
      c >>= 1;
    }
  },

  /**
   * Consume the part of an URL token after the initial 'url('.  Caller
   * is assumed to have consumed 'url(' already.  Will always produce
   * either an URL or a Bad_URL token.
   *
   * Exposed for use by nsCSSParser::ParseMozDocumentRule, which applies
   * the special lexical rules for URL tokens in a nonstandard context.
   */
  NextURL: function (aToken) {
    this.SkipWhitespace();

    // aToken.mIdent may be "url" at this point; clear that out
    aToken.mIdent.length = 0;

    let hasString = false;
    let ch = this.Peek();
    // Do we have a string?
    if (ch == QUOTATION_MARK || ch == APOSTROPHE) {
      this.ScanString(aToken);
      if (aToken.mType == eCSSToken_Bad_String) {
        aToken.mType = eCSSToken_Bad_URL;
        return;
      }
      hasString = true;
    } else {
      // Otherwise, this is the start of a non-quoted url (which may be empty).
      aToken.mSymbol = 0;
      this.GatherText(IS_URL_CHAR, aToken.mIdent);
    }

    // Consume trailing whitespace and then look for a close parenthesis.
    this.SkipWhitespace();
    ch = this.Peek();
    // ch can be less than zero indicating EOF
    if (ch < 0 || ch == RIGHT_PARENTHESIS) {
      this.Advance();
      aToken.mType = eCSSToken_URL;
      if (ch < 0) {
        this.AddEOFCharacters(eEOFCharacters_CloseParen);
      }
    } else {
      aToken.mType = eCSSToken_Bad_URL;
      if (!hasString) {
        // Consume until before the next right parenthesis, which follows
        // how <bad-url-token> is consumed in CSS Syntax 3 spec.
        // Note that, we only do this when "url(" is not followed by a
        // string, because in the spec, "url(" followed by a string is
        // handled as a url function rather than a <url-token>, so the
        // rest of content before ")" should be consumed in balance,
        // which will be done by the parser.
        // The closing ")" is not consumed here. It is left to the parser
        // so that the parser can handle both cases.
        do {
          if (IsVertSpace(ch)) {
            this.AdvanceLine();
          } else {
            this.Advance();
          }
          ch = this.Peek();
        } while (ch >= 0 && ch != RIGHT_PARENTHESIS);
      }
    }
  },

  /**
   * Primary scanner entry point.  Consume one token and fill in
   * |aToken| accordingly.  Will skip over any number of comments first,
   * and will also skip over rather than return whitespace and comment
   * tokens, depending on the value of |aSkip|.
   *
   * Returns true if it successfully consumed a token, false if EOF has
   * been reached.  Will always advance the current read position by at
   * least one character unless called when already at EOF.
   */
  Next: function (aToken, aSkip) {
    let ch;

    // do this here so we don't have to do it in dozens of other places
    aToken.mIdent = [];
    aToken.mType = eCSSToken_Symbol;

    this.mTokenOffset = this.mOffset;
    this.mTokenLineOffset = this.mLineOffset;
    this.mTokenLineNumber = this.mLineNumber;

    ch = this.Peek();
    if (IsWhitespace(ch)) {
      this.SkipWhitespace();
      aToken.mType = eCSSToken_Whitespace;
      return true;
    }
    if (ch == SOLIDUS && // !IsSVGMode() &&
        this.Peek(1) == ASTERISK) {
      this.SkipComment();
      aToken.mType = eCSSToken_Comment;
      return true;
    }

    // EOF
    if (ch < 0) {
      return false;
    }

    // 'u' could be UNICODE-RANGE or an identifier-family token
    if (ch == LATIN_SMALL_LETTER_U || ch == LATIN_CAPITAL_LETTER_U) {
      let c2 = this.Peek(1);
      let c3 = this.Peek(2);
      if (c2 == PLUS_SIGN && (IsHexDigit(c3) || c3 == QUESTION_MARK)) {
        return this.ScanURange(aToken);
      }
      return this.ScanIdent(aToken);
    }

    // identifier family
    if (IsIdentStart(ch)) {
      return this.ScanIdent(aToken);
    }

    // number family
    if (IsDigit(ch)) {
      return this.ScanNumber(aToken);
    }

    if (ch == FULL_STOP && IsDigit(this.Peek(1))) {
      return this.ScanNumber(aToken);
    }

    if (ch == PLUS_SIGN) {
      let c2 = this.Peek(1);
      if (IsDigit(c2) || (c2 == FULL_STOP && IsDigit(this.Peek(2)))) {
        return this.ScanNumber(aToken);
      }
    }

    // HYPHEN_MINUS can start an identifier-family token, a number-family token,
    // or an HTML-comment
    if (ch == HYPHEN_MINUS) {
      let c2 = this.Peek(1);
      let c3 = this.Peek(2);
      if (IsIdentStart(c2) || (c2 == HYPHEN_MINUS && c3 != GREATER_THAN_SIGN)) {
        return this.ScanIdent(aToken);
      }
      if (IsDigit(c2) || (c2 == FULL_STOP && IsDigit(c3))) {
        return this.ScanNumber(aToken);
      }
      if (c2 == HYPHEN_MINUS && c3 == GREATER_THAN_SIGN) {
        this.Advance(3);
        aToken.mType = eCSSToken_HTMLComment;
        aToken.mIdent = stringToCodes("-->");
        return true;
      }
    }

    // the other HTML-comment token
    if (ch == LESS_THAN_SIGN &&
        this.Peek(1) == EXCLAMATION_MARK &&
        this.Peek(2) == HYPHEN_MINUS &&
        this.Peek(3) == HYPHEN_MINUS) {
      this.Advance(4);
      aToken.mType = eCSSToken_HTMLComment;
      aToken.mIdent = stringToCodes("<!--");
      return true;
    }

    // AT_KEYWORD
    if (ch == COMMERCIAL_AT) {
      return this.ScanAtKeyword(aToken);
    }

    // HASH
    if (ch == NUMBER_SIGN) {
      return this.ScanHash(aToken);
    }

    // STRING
    if (ch == QUOTATION_MARK || ch == APOSTROPHE) {
      return this.ScanString(aToken);
    }

    // Match operators: ~= |= ^= $= *=
    let opType = MatchOperatorType(ch);
    if (opType != eCSSToken_Symbol && this.Peek(1) == EQUALS_SIGN) {
      aToken.mType = opType;
      this.Advance(2);
      return true;
    }

    // Otherwise, a symbol (DELIM).
    aToken.mSymbol = ch;
    this.Advance();
    return true;
  },
};

/**
 * Create and return a new CSS lexer, conforming to the @see CSSLexer
 * webidl interface.
 *
 * @param {String} input the CSS text to lex
 * @return {CSSLexer} the new lexer
 */
function getCSSLexer(input) {
  return new Scanner(input);
}

exports.getCSSLexer = getCSSLexer;