forked from tapir-dream/HTMLTokenizer
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathHTMLTokenizer.js
1415 lines (1305 loc) · 38.8 KB
/
HTMLTokenizer.js
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
function HTMLTokenizer(reader) {
var HTMLTokeEnum = {
StartTag: 0,
EndTag: 1,
Comment: 2,
Character: 3,
Doctype: 4,
};
var TokenStateEnum = {
DataState: 0,
TagOpenState: 1,
EndTagOpenState: 2,
TagNameState: 3,
CommentStartState: 4,
CommentStartDashState: 5,
CommentState: 6,
CommentEndDashState: 7,
CommentEndState: 8,
BeforeAttributeNameState: 9,
AttributeNameState: 10,
AfterAttributeNameState: 11,
BeforeAttributeValueState: 12,
AttributeValueDoubleQuotedState: 13,
AttributeValueSingleQuotedState: 14,
AttributeValueUnquotedState: 15,
AfterAttributeValueQuotedState: 16,
RCDATAState: 17,
RAWTEXTState: 18,
ScriptDataState: 19,
RCDATALessThanSignState: 20,
RCDATAEndTagOpenState: 21,
RCDATAEndTagNameState: 22,
RAWTEXTLessThanSignState: 23,
RAWTEXTEndTagOpenState: 24,
RAWTEXTEndTagNameState: 25,
ScriptDataLessThanSignState: 26,
ScriptDataEndTagOpenState: 27,
ScriptDataEndTagNameState: 28,
DOCTYPEState: 29,
BeforeDOCTYPENameState: 30,
DOCTYPENameState: 31,
AfterDOCTYPENameState: 32,
AfterDOCTYPEPublicKeywordState: 33,
BeforeDOCTYPEPublicIdentifierState: 34,
DOCTYPEPublicIdentifierDoubleQuotedState: 35,
DOCTYPEPublicIdentifierSingleQuotedState: 36,
AfterDOCTYPEPublicIdentifierState: 37,
BetweenDOCTYPEPublicAndSystemIdentifiersState: 38,
AfterDOCTYPESystemKeywordState: 38,
BeforeDOCTYPESystemIdentifierState: 40,
DOCTYPESystemIdentifierDoubleQuotedState: 41,
DOCTYPESystemIdentifierSingleQuotedState: 42,
AfterDOCTYPESystemIdentifierState: 43,
BogusDOCTYPEState: 44
};
var TagToState = {
title: TokenStateEnum.RCDATAState,
textarea: TokenStateEnum.RCDATAState,
pre: TokenStateEnum.RCDATAState,
style: TokenStateEnum.RAWTEXTState,
xmp: TokenStateEnum.RAWTEXTState,
iframe: TokenStateEnum.RAWTEXTState,
noembed: TokenStateEnum.RAWTEXTState,
noframes: TokenStateEnum.RAWTEXTState,
noscript: TokenStateEnum.RAWTEXTState,
script: TokenStateEnum.ScriptDataState
};
var IgnoreClosedTags = {
area: true,
base: true,
basefont: true,
br: true,
col: true,
frame: true,
hr: true,
img: true,
input: true,
isindex: true,
link: true,
meta: true,
param: true
};
var SelectClosedTags = {
body: true,
colgroup: true,
dd: true,
dt: true,
head: true,
html: true,
li: true,
option: true,
p: true,
tbody: true,
td: true,
tfoot: true,
th: true,
thead: true,
tr: true
};
var cTokenState = TokenStateEnum.DataState;
var nextToken = function(reader, tokenDataList) {
var word = '';
var tl = 0;
var al = 0;
var td;
var tmpBuffer = '';
var tmpTagName = '';
var doctypeData = {name: '', pid: '', sid: ''};
while(!reader.isInputEnd()) {
var c = reader.nextChar();
switch(cTokenState) {
case TokenStateEnum.DataState:
if ('<' === c) {
var tbuf = reader.offsetChar(1)
if (!reader.isWordChar(tbuf)) {
word += c;
continue;
}
cTokenState = TokenStateEnum.TagOpenState;
if (word !== '') {
tokenDataList.push({
token: HTMLTokeEnum.Character,
value: word,
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber()
});
}
return true;
} else {
word += c;
}
break;
case TokenStateEnum.TagOpenState:
if (reader.isWordChar()) {
// 表明注释或doctype开始
if ('!' === c) {
tmpBuffer = '';
// 预读7个字符来判断是否为doctype
for (var i = 0; i < 7; ++i) {
tmpBuffer += reader.nextChar();
}
if ('doctype' === tmpBuffer.toLowerCase()) { //doctype
cTokenState = TokenStateEnum.DOCTYPEState;
} else { //注释
// 将字符回退7个矫正位置
for (var i = 0; i < 7; ++i) {
reader.prevChar();
}
// 预读两个字符来确定是注释
if (reader.offsetChar(1) === '-' && reader.offsetChar(2) === '-') {
cTokenState = TokenStateEnum.CommentStartState;
} else {
cTokenState = TokenStateEnum.TagNameState;
// 吃一个字符矫正位置
reader.prevChar();
}
}
} else {
cTokenState = TokenStateEnum.TagNameState;
// 吃一个字符矫正位置
reader.prevChar();
}
}
break;
case TokenStateEnum.TagNameState:
//TODO:是否需要补充 HTML Tag name 名字规则
if (reader.isSpaceChar() || reader.isTabChar() || reader.isNewLine()) {
cTokenState = TokenStateEnum.BeforeAttributeNameState;
// 将tag name内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.StartTag,
value: word.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber(),
attributes: []
});
return true;
} else if ('>' === c) {
// 说明tag无属性直接结束了
// 将tag name内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.StartTag,
value: word.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber(),
attributes: []
});
// 此处判断是否今日DataState之外的其他状态
// 处理 style/textarea/pre等 Tag 状态问题
td = tokenDataList[tokenDataList.length - 1];
if (td.value in TagToState) {
cTokenState = TagToState[td.value];
} else {
cTokenState = TokenStateEnum.DataState;
}
return true;
} else if ('/' === c) {
cTokenState = TokenStateEnum.EndTagOpenState;
} else {
word += c;
}
break;
case TokenStateEnum.BeforeAttributeNameState:
//TODO:是否需要补充 HTML Tag Attribute name 名字规则
if ('>' === c) {
// 此处判断是否今日DataState之外的其他状态
// 处理 style/textarea/pre等 Tag 状态问题
td = tokenDataList[tokenDataList.length - 1];
if (td.value in TagToState) {
cTokenState = TagToState[td.value];
} else {
cTokenState = TokenStateEnum.DataState;
}
return true;
} else if (reader.isWordChar() && '/' != c) {
word += c;
cTokenState = TokenStateEnum.AttributeNameState;
} else {
continue;
}
break;
case TokenStateEnum.AttributeNameState:
//TODO:是否需要补充 HTML Tag Attribute name 名字规则
if ('=' === c || reader.isSpaceChar() || reader.isTabChar() || reader.isNewLine()) {
cTokenState = TokenStateEnum.BeforeAttributeValueState;
// 将attribut name内容填入结构体
tl = tokenDataList.length - 1;
tokenDataList[tl].attributes.push({
name: word.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber(),
value: ''
});
word = '';
} else if ('>' === c) {
// 仅有属性名无属性值情况
cTokenState = TokenStateEnum.DataState;
tl = tokenDataList.length - 1;
tokenDataList[tl].attributes.push({
name: word.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber(),
value: ''
});
return true;
} else {
word += c;
}
break;
case TokenStateEnum.BeforeAttributeValueState:
oc = reader.offsetChar(-1);
// 如果前一个字符是 = 则说明从这个字符起，这个char为 attribute value 值
if (oc == '=') {
// 判断当前字符 是否为 引号
if (reader.isSingleQuotes()) {
cTokenState = TokenStateEnum.AttributeValueSingleQuotedState;
} else if (reader.isDoubleQuotes()) {
cTokenState = TokenStateEnum.AttributeValueDoubleQuotedState;
} else {
// 不是 引号则 进入没加引号状态
cTokenState = TokenStateEnum.AttributeValueUnquotedState;
// 回退一个字符矫正位置
reader.prevChar();
}
} else if ('=' === c) {
// 自身为 = 则状态未变
cTokenState = TokenStateEnum.BeforeAttributeValueState;
} else if ('>' === c) {
// 如果直接遇到 > 字符，则说明标记闭合
// 此处判断是否今日DataState之外的其他状态
// 处理 style/textarea/pre等 Tag 状态问题
td = tokenDataList[tokenDataList.length - 1];
if (td.value in TagToState) {
cTokenState = TagToState[td.value];
} else {
cTokenState = TokenStateEnum.DataState;
}
} else if (reader.isWordChar()) {
// 最后如果自身不是 = 字符 说明不是 attribute value 而是一个新的属性名
// 回退一个字符矫正位置
reader.prevChar();
cTokenState = TokenStateEnum.AttributeNameState;
}
break;
case TokenStateEnum.AttributeValueUnquotedState:
// 直到有字符位置
if (reader.isWordChar() && c != '>') {
word += c;
} else if (word.length > 0 &&
(reader.isSpaceChar() || reader.isTabChar()) || reader.isNewLine()
|| c == '>') {
// 否则是value后有空格情况或者直接闭合情况
cTokenState = TokenStateEnum.AfterAttributeValueQuotedState;
// 将attribut value内容填入结构体
tl = tokenDataList.length - 1;
al = tokenDataList[tl].attributes.length - 1;
tokenDataList[tl].attributes[al].quotes = '';
tokenDataList[tl].attributes[al].value = word;
tokenDataList[tl].attributes[al].cchar = reader.getCharNumber() - 1;
tokenDataList[tl].attributes[al].cline = reader.getLineNumber();
word = '';
// 回退一个字符矫正位置
reader.prevChar();
}
break;
case TokenStateEnum.AttributeValueDoubleQuotedState:
if (reader.isDoubleQuotes()) {
cTokenState = TokenStateEnum.AfterAttributeValueQuotedState;
// 将attribut value内容填入结构体
tl = tokenDataList.length - 1;
al = tokenDataList[tl].attributes.length - 1;
tokenDataList[tl].attributes[al].quotes = '\"';
tokenDataList[tl].attributes[al].value = word;
tokenDataList[tl].attributes[al].cchar = reader.getCharNumber() - 1;
tokenDataList[tl].attributes[al].cline = reader.getLineNumber();
word = '';
} else {
word += c;
}
break;
case TokenStateEnum.AttributeValueSingleQuotedState:
if (reader.isSingleQuotes()) {
// 将attribut value内容填入结构体
cTokenState = TokenStateEnum.AfterAttributeValueQuotedState;
tl = tokenDataList.length - 1;
al = tokenDataList[tl].attributes.length - 1;
tokenDataList[tl].attributes[al].quotes = '\'';
tokenDataList[tl].attributes[al].value = word;
tokenDataList[tl].attributes[al].cchar = reader.getCharNumber() - 1;
tokenDataList[tl].attributes[al].cline = reader.getLineNumber();
word = '';
} else {
word += c;
}
break;
case TokenStateEnum.AfterAttributeValueQuotedState:
if ('>' === c) {
// 此处判断是否今日DataState之外的其他状态
// 处理 style/textarea/pre等 Tag 状态问题
td = tokenDataList[tokenDataList.length - 1];
if (td.value in TagToState) {
cTokenState = TagToState[td.value];
} else {
cTokenState = TokenStateEnum.DataState;
}
return true;
} else {
cTokenState = TokenStateEnum.BeforeAttributeNameState;
}
break;
case TokenStateEnum.EndTagOpenState:
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将tag name内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.EndTag,
value: word.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber()
});
return true;
} else {
word += c;
}
break;
case TokenStateEnum.RCDATAState:
if ('<' === c) {
// 标签可能闭合了，将可能字符串存入临时缓冲
tmpBuffer += c;
cTokenState = TokenStateEnum.RCDATALessThanSignState;
} else {
// 当做普通字符累加
word += c;
}
break;
case TokenStateEnum.RCDATALessThanSignState:
if ('/' === c) {
tmpBuffer += c;
cTokenState = TokenStateEnum.RCDATAEndTagOpenState;
} else {
cTokenState = TokenStateEnum.RCDATAState;
// 它是普通文本，把它放入 word 内并补足上一状态的 < 字符
// 并且清空 tmpBuffer
word += '<' + c;
tmpBuffer = '';
}
break;
case TokenStateEnum.RCDATAEndTagOpenState:
tmpBuffer += c;
tmpTagName += c;
if (!reader.isWordChar() || '>' === reader.offsetChar(1)) {
cTokenState = TokenStateEnum.RCDATAEndTagNameState;
}
break;
case TokenStateEnum.RCDATAEndTagNameState:
td = tokenDataList[tokenDataList.length - 1];
// 开始标签如果与预取解释标签名一致
// 就认为这个标签闭合了
if (td.value === tmpTagName) {
// 此处需要存入两个 Token
// 一个是 RCDATA 值 Token
// 另一个是闭合 tag 的 Token
if (word != '') {
tokenDataList.push({
token: HTMLTokeEnum.Character,
value: word,
needEscape: true,
cchar: reader.getCharNumber() - tmpTagName.length - 3,
cline: reader.getLineNumber()
});
}
tokenDataList.push({
token: HTMLTokeEnum.EndTag,
value: tmpTagName.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber()
});
cTokenState = TokenStateEnum.DataState;
return true;
} else {
tmpBuffer += c;
// 如果没校验成功配对闭合，则累加 word 值和缓存值
// 并清空缓存内容
word += tmpBuffer;
tmpBuffer = '';
tmpTagName = '';
cTokenState = TokenStateEnum.RCDATAState;
}
break;
case TokenStateEnum.RAWTEXTState:
if ('<' === c) {
// 标签可能闭合了，将可能字符串存入临时缓冲
tmpBuffer += c;
cTokenState = TokenStateEnum.RAWTEXTLessThanSignState;
} else {
// 当做普通字符累加
word += c;
}
break;
case TokenStateEnum.RAWTEXTLessThanSignState:
if ('/' === c) {
tmpBuffer += c;
cTokenState = TokenStateEnum.RAWTEXTEndTagOpenState;
} else {
cTokenState = TokenStateEnum.RAWTEXTState;
// 它是普通文本，把它放入 word 内并补足上一状态的 < 字符
// 并且清空 tmpBuffer
word += '<' + c;
tmpBuffer = '';
}
break;
case TokenStateEnum.RAWTEXTEndTagOpenState:
tmpBuffer += c;
tmpTagName += c;
if (!reader.isWordChar() || '>' === reader.offsetChar(1)) {
cTokenState = TokenStateEnum.RAWTEXTEndTagNameState;
}
break;
case TokenStateEnum.RAWTEXTEndTagNameState:
td = tokenDataList[tokenDataList.length - 1];
// 开始标签如果与预取解释标签名一致
// 就认为这个标签闭合了
if (td.value === tmpTagName) {
// 此处需要存入两个 Token
// 一个是 RCDATA 值 Token
// 另一个是闭合 tag 的 Token
if (word != '') {
tokenDataList.push({
token: HTMLTokeEnum.Character,
value: word,
needEscape: false,
cchar: reader.getCharNumber() - tmpTagName.length - 3,
cline: reader.getLineNumber()
});
}
tokenDataList.push({
token: HTMLTokeEnum.EndTag,
value: tmpTagName.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber()
});
cTokenState = TokenStateEnum.DataState;
return true;
} else {
tmpBuffer += c;
// 如果没校验成功配对闭合，则累加 word 值和缓存值
// 并清空缓存内容
word += tmpBuffer;
tmpBuffer = '';
tmpTagName = '';
cTokenState = TokenStateEnum.RAWTEXTState;
}
break;
case TokenStateEnum.ScriptDataState:
if ('<' === c) {
// 标签可能闭合了，将可能字符串存入临时缓冲
tmpBuffer += c;
cTokenState = TokenStateEnum.ScriptDataLessThanSignState;
} else {
// 当做普通字符累加
word += c;
}
break;
case TokenStateEnum.ScriptDataLessThanSignState:
if ('/' === c) {
tmpBuffer += c;
cTokenState = TokenStateEnum.ScriptDataEndTagOpenState;
} else {
cTokenState = TokenStateEnum.ScriptDataState;
// 它是普通文本，把它放入 word 内并补足上一状态的 < 字符
// 并且清空 tmpBuffer
word += '<' + c;
tmpBuffer = '';
}
break;
case TokenStateEnum.ScriptDataEndTagOpenState:
tmpBuffer += c;
tmpTagName += c;
if (!reader.isWordChar() || '>' === reader.offsetChar(1)) {
cTokenState = TokenStateEnum.ScriptDataEndTagNameState;
}
break;
case TokenStateEnum.ScriptDataEndTagNameState:
td = tokenDataList[tokenDataList.length - 1];
// 开始标签如果与预取解释标签名一致
// 就认为这个标签闭合了
if (td.value === tmpTagName) {
// 此处需要存入两个 Token
// 一个是 RCDATA 值 Token
// 另一个是闭合 tag 的 Token
if (word != '') {
tokenDataList.push({
token: HTMLTokeEnum.Character,
value: word,
needEscape: false,
cchar: reader.getCharNumber() - tmpTagName.length - 3,
cline: reader.getLineNumber()
});
}
tokenDataList.push({
token: HTMLTokeEnum.EndTag,
value: tmpTagName.toLowerCase(),
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber()
});
cTokenState = TokenStateEnum.DataState;
return true;
} else {
tmpBuffer += c;
// 如果没校验成功配对闭合，则累加 word 值和缓存值
// 并清空缓存内容
word += tmpBuffer;
tmpBuffer = '';
tmpTagName = '';
cTokenState = TokenStateEnum.ScriptDataState;
}
break;
// ========注释标签解析===========
case TokenStateEnum.CommentStartState:
if ('-' === c) {
cTokenState = TokenStateEnum.CommentStartDashState;
}
break;
case TokenStateEnum.CommentStartDashState:
if ('-' === c) {
cTokenState = TokenStateEnum.CommentState;
}
break;
case TokenStateEnum.CommentState:
if ('-' === c && '-' == reader.offsetChar(1)) {
cTokenState = TokenStateEnum.CommentEndDashState;
} else {
// 注释文字处理
// 一个个字符保存起来
word += c;
}
break;
case TokenStateEnum.CommentEndDashState:
if ('-' === c && '>' == reader.offsetChar(1)) {
cTokenState = TokenStateEnum.CommentEndState;
}
break;
case TokenStateEnum.CommentEndState:
cTokenState = TokenStateEnum.DataState;
// 将注释内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Comment,
value: word,
cchar: reader.getCharNumber() - word.length - 3,
cline: reader.getLineNumber()
});
return true;
break;
// ========注释标签解析完毕==========
// ========DocType解析==========
case TokenStateEnum.DOCTYPEState:
if (!reader.isWordChar()) {
cTokenState = TokenStateEnum.BeforeDOCTYPENameState;
continue;
}
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将Doctype内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Doctype,
name: doctypeData.name,
pid: doctypeData.pid,
sid: doctypeData.sid,
cchar: reader.getCharNumber(),
cline: reader.getLineNumber()
});
continue;
}
// parser error in DOCTYPEState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
break;
case TokenStateEnum.BeforeDOCTYPENameState:
if (reader.isSpaceChar()) {
continue;
}
if (reader.isWordChar()) {
cTokenState = TokenStateEnum.DOCTYPENameState;
// 回退一个字符
reader.prevChar();
continue;
}
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将Doctype内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Doctype,
name: doctypeData.name,
pid: doctypeData.pid,
sid: doctypeData.sid,
cchar: reader.getCharNumber(),
cline: reader.getLineNumber()
});
continue;
}
break;
case TokenStateEnum.DOCTYPENameState:
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将Doctype内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Doctype,
name: doctypeData.name,
pid: doctypeData.pid,
sid: doctypeData.sid,
cchar: reader.getCharNumber(),
cline: reader.getLineNumber()
});
continue;
}
if (reader.isWordChar()) {
doctypeData.name += c;
continue;
} else {
cTokenState = TokenStateEnum.AfterDOCTYPENameState;
}
break;
case TokenStateEnum.AfterDOCTYPENameState:
if (!reader.isWordChar()) {
continue;
}
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将Doctype内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Doctype,
name: doctypeData.name,
pid: doctypeData.pid,
sid: doctypeData.sid,
cchar: reader.getCharNumber(),
cline: reader.getLineNumber()
});
continue;
}
tmpBuffer = '';
tmpBuffer += c;
// 向后预读5个字符来判断是否为 public
for (var i = 0; i < 5; ++i) {
tmpBuffer += reader.nextChar();
}
if ('public' === tmpBuffer.toLowerCase()) {
cTokenState = TokenStateEnum.AfterDOCTYPEPublicKeywordState;
continue;
}
if ('system' === tmpBuffer.toLowerCase()) {
cTokenState = TokenStateEnum.AfterDOCTYPESystemKeywordState;
continue;
}
// 不是 pid 也不是 sid 就去 BogusDOCTYPEState 吧……
cTokenState = TokenStateEnum.BogusDOCTYPEState;
// 回退 5 个字符
for (var i = 0; i < 5; ++i) {
reader.prevChar();
}
break;
// pid 解析
case TokenStateEnum.AfterDOCTYPEPublicKeywordState:
if (!reader.isWordChar()) {
cTokenState = TokenStateEnum.BeforeDOCTYPEPublicIdentifierState;
continue;
}
if ('>' === c) {
// Parse error in AfterDOCTYPEPublicKeywordState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
}
break;
case TokenStateEnum.BeforeDOCTYPEPublicIdentifierState:
if (reader.isSingleQuotes()) {
cTokenState = TokenStateEnum.DOCTYPEPublicIdentifierSingleQuotedState;
continue;
}
if (reader.isDoubleQuotes()) {
cTokenState = TokenStateEnum.DOCTYPEPublicIdentifierDoubleQuotedState;
continue;
}
if ('>' === c) {
// Parse error in AfterDOCTYPEPublicKeywordState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
}
break;
case TokenStateEnum.DOCTYPEPublicIdentifierDoubleQuotedState:
if ('>' === c) {
// Parse error in DOCTYPEPublicIdentifierDoubleQuotedState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
}
if (reader.isDoubleQuotes()) {
cTokenState = TokenStateEnum.AfterDOCTYPEPublicIdentifierState;
continue;
}
if (reader.isWordChar()) {
doctypeData.pid += c;
}
break;
case TokenStateEnum.DOCTYPEPublicIdentifierSingleQuotedState:
if ('>' === c) {
// Parse error in DOCTYPEPublicIdentifierSingleQuotedState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
}
if (reader.isSingleQuotes()) {
cTokenState = TokenStateEnum.AfterDOCTYPEPublicIdentifierState;
continue;
}
if (reader.isWordChar()) {
doctypeData.pid += c;
}
break;
case TokenStateEnum.AfterDOCTYPEPublicIdentifierState:
if (!reader.isWordChar()) {
cTokenState = TokenStateEnum.BetweenDOCTYPEPublicAndSystemIdentifiersState;
continue;
}
// Parse error in AfterDOCTYPEPublicIdentifierState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
break;
case TokenStateEnum.BetweenDOCTYPEPublicAndSystemIdentifiersState:
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将Doctype内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Doctype,
name: doctypeData.name,
pid: doctypeData.pid,
sid: doctypeData.sid,
cchar: reader.getCharNumber(),
cline: reader.getLineNumber()
});
continue;
}
if (reader.isSingleQuotes()) {
cTokenState = TokenStateEnum.DOCTYPESystemIdentifierSingleQuotedState;
continue;
}
if (reader.isDoubleQuotes()) {
cTokenState = TokenStateEnum.DOCTYPESystemIdentifierDoubleQuotedState;
continue;
}
break;
// sid 解析
case TokenStateEnum.AfterDOCTYPESystemKeywordState:
if (!reader.isWordChar()) {
cTokenState = TokenStateEnum.BeforeDOCTYPESystemKeywordState;
continue;
}
if ('>' === c) {
// Parse error in AfterDOCTYPESystemKeywordState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
}
break;
case TokenStateEnum.BeforeDOCTYPESystemIdentifierState:
if (reader.isSingleQuotes()) {
cTokenState = TokenStateEnum.DOCTYPESystemIdentifierSingleQuotedState;
continue;
}
if (reader.isDoubleQuotes()) {
cTokenState = TokenStateEnum.DOCTYPESystemIdentifierDoubleQuotedState;
continue;
}
// Parse error in BeforeDOCTYPESystemIdentifierState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
break;
case TokenStateEnum.DOCTYPESystemIdentifierDoubleQuotedState:
if ('>' === c) {
// Parse error in DOCTYPESystemIdentifierDoubleQuotedState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
}
if (reader.isDoubleQuotes()) {
cTokenState = TokenStateEnum.AfterDOCTYPESystemIdentifierState;
continue;
}
if (reader.isWordChar()) {
doctypeData.sid += c;
}
break;
case TokenStateEnum.DOCTYPESystemIdentifierSingleQuotedState:
if ('>' === c) {
// Parse error in DOCTYPESystemIdentifierSingleQuotedState.
cTokenState = TokenStateEnum.BogusDOCTYPEState;
}
if (reader.isSingleQuotes()) {
cTokenState = TokenStateEnum.AfterDOCTYPESystemIdentifierState;
continue;
}
if (reader.isWordChar()) {
doctypeData.sid += c;
}
break;
case TokenStateEnum.AfterDOCTYPESystemIdentifierState:
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将Doctype内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Doctype,
name: doctypeData.name,
pid: doctypeData.pid,
sid: doctypeData.sid,
cchar: reader.getCharNumber(),
cline: reader.getLineNumber()
});
continue;
}
// Parse error in AfterDOCTYPESystemIdentifierState.'
cTokenState = TokenStateEnum.BogusDOCTYPEState;
break;
case TokenStateEnum.BogusDOCTYPEState:
if ('>' === c) {
cTokenState = TokenStateEnum.DataState;
// 将Doctype内容填入结构体
tokenDataList.push({
token: HTMLTokeEnum.Doctype,
name: doctypeData.name,
pid: doctypeData.pid,
sid: doctypeData.sid,
cchar: reader.getCharNumber(),
cline: reader.getLineNumber()
});
continue;
}
break;
// ========DocType解析完毕==========
}
}
// 纯字符扫尾
if (tokenDataList.length == 0 && word != '') {
tokenDataList.push({
token: HTMLTokeEnum.Character,
value: word,
needEscape: false,
cchar: 1,
cline: 1
});
return false;
}
// 结尾文本标记扫尾
if (word !== '') {
tokenDataList.push({
token: HTMLTokeEnum.Character,
value: word,
cchar: reader.getCharNumber() - 1,
cline: reader.getLineNumber()
});
return false;
}
return false;
};
var scanner = function() {
// tokenDataList 每项结构
// {name: HTMLTokeEnum.StartTag, value: 'a', attriubtes: [{attrName: attrValue}, {attrName: attrValue}]};
cTokenState = TokenStateEnum.DataState;
var tokenDataList =[];
while(nextToken(reader, tokenDataList)) {}
return tokenDataList;
};
var toHTML = function(tdl) {
if (!tdl) {
return false;
}
var html = '';
var c = tdl.length;
if (c == 0) {
return '';
}
for (var i = 0; i < c; ++i) {
var data = tdl[i];
var token = data.token;
var quotes;
switch (token) {
case HTMLTokeEnum.StartTag:
html += '<' + data.value;
for (var j = 0, len = data.attributes.length; j < len; ++j) {
var attr = data.attributes[j];
if (!attr.value) {
html += ' ' + attr.name;
} else {
quotes = attr.quotes || '"';
html += ' ' + attr.name + '=' + quotes + attr.value + quotes;
}
}
if (IgnoreClosedTags[data.value]) {
html += ' />';
} else {
html += '>';
}
break;
case HTMLTokeEnum.EndTag:
html += '</' + data.value + '>';
break;
case HTMLTokeEnum.Comment:
// 暂时不要输出注释了
//html += '<!\-\-' + data.value + '\-\->';
break;
case HTMLTokeEnum.Doctype: