-
Notifications
You must be signed in to change notification settings - Fork 24
/
Copy pathHtmlParser.cpp
1184 lines (1052 loc) · 28.5 KB
/
HtmlParser.cpp
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
#include "HtmlParser.h"
#include <memory.h>
#include <string.h>
#include <ctype.h>
#include <assert.h>
//HtmlParser类，用于解析HTML文本
//by liigo, @2010-2013
#ifndef WIN32
#include <strings.h>
#define stricmp strcasecmp
#endif
using namespace liigo;
const char* strnchr(const char* pStr, int len, char c)
{
if(pStr == NULL || len <= 0)
return NULL;
const char *p = pStr;
while(1)
{
if(*p == c) return p;
p++;
if((p - pStr) == len) break;
}
return NULL;
}
inline bool matchchar(char c1, char c2, bool bCaseSensitive)
{
return bCaseSensitive ? (c1 == c2) : (tolower(c1) == tolower(c2));
}
const char* findFirstUnquotedChar(const char* pStr, char endchar)
{
char c;
const char* p = pStr;
bool inQuote1 = false, inQuote2 = false; //'inQuote1', "inQuote2"
while(c = *p)
{
if(c == '\'')
{
inQuote1 = !inQuote1;
}
else if(c == '\"')
{
inQuote2 = !inQuote2;
}
if(!inQuote1 && !inQuote2)
{
if(c == endchar) return p;
}
p++;
}
return NULL;
}
const char* findFirstUnquotedChars(const char* pStr, char* endchars, int nchars, bool bCaseSensitive)
{
char c;
const char* p = pStr;
bool inQuote1 = false, inQuote2 = false; //'inQuote1', "inQuote2"
while(c = *p)
{
if(c == '\'')
{
inQuote1 = !inQuote1;
}
else if(c == '\"')
{
inQuote2 = !inQuote2;
}
if(!inQuote1 && !inQuote2)
{
for(int i = 0; i < nchars; i++)
{
if(matchchar(c, endchars[i], bCaseSensitive))
return p;
}
}
p++;
}
return NULL;
}
// return true if pStr1 starts with pStr2. pStr1 not NULL, pStr2 not NULL, lenStr2 > 0.
static bool strStartWith(const char* pStr1, const char* pStr2, int lenStr2, bool bCaseSensitive)
{
for(int i = 0; i < lenStr2; i++)
{
if(pStr1[i] == '\0') return false;
if(!matchchar(pStr1[i], pStr2[i], bCaseSensitive))
return false;
}
return true;
}
const char* findFirstUnquotedStr(const char* pSourceStr, const char* pDestStr, bool bCaseSensitive)
{
if(pDestStr == NULL || *pDestStr == '\0') return NULL;
char c;
const char* p = pSourceStr;
bool inQuote1 = false, inQuote2 = false; //'inQuote1', "inQuote2"
int lenDestStr = strlen(pDestStr);
while(c = *p)
{
if(c == '\'')
{
inQuote1 = !inQuote1;
}
else if(c == '\"')
{
inQuote2 = !inQuote2;
}
if(!inQuote1 && !inQuote2)
{
if(strStartWith(p, pDestStr, lenDestStr, bCaseSensitive))
return p;
}
p++;
}
return NULL;
}
const char* findFirstStr(const char* pSourceStr, const char* pDestStr, bool bCaseSensitive)
{
if(pDestStr == NULL || *pDestStr == '\0') return NULL;
char c;
const char* p = pSourceStr;
int lenDestStr = strlen(pDestStr);
while(c = *p)
{
if(strStartWith(p, pDestStr, lenDestStr, bCaseSensitive))
return p;
p++;
}
return NULL;
}
//nDest and nChar can by -1
size_t copyStr(char* pDest, size_t nDest, const char* pSrc, size_t nChar)
{
if(pDest == NULL || nDest == 0)
return 0;
if(pSrc == NULL)
{
pDest[0] = '\0';
return 0;
}
if(nChar == (size_t)-1)
nChar = strlen(pSrc);
if(nChar > nDest)
nChar = nDest;
memcpy(pDest, pSrc, nChar * sizeof(char));
pDest[nChar] = '\0';
return nChar;
}
int copyStrUtill(char* pDest, size_t nDest, const char* pSrc, char endchar, bool ignoreEndCharInQuoted)
{
if(nDest == 0) return 0;
pDest[0] = '\0';
const char* pSearched = (ignoreEndCharInQuoted ? findFirstUnquotedChar(pSrc,endchar) : strchr(pSrc, endchar));
if(pSearched <= pSrc) return 0;
return copyStr(pDest, nDest, pSrc, pSearched - pSrc);
}
//nChar can be -1
char* duplicateStr(const char* pSrc, size_t nChar, const char* pPrefix = NULL)
{
if(nChar == (size_t)-1)
nChar = strlen(pSrc);
int lenPrefix = pPrefix ? strlen(pPrefix) : 0;
char* pNew = (char*) malloc( (lenPrefix + nChar + 1) * sizeof(char) );
if(lenPrefix > 0)
{
copyStr(pNew, -1, pPrefix, lenPrefix);
copyStr(pNew + lenPrefix, -1, pSrc, nChar);
} else {
copyStr(pNew, -1, pSrc, nChar);
}
return pNew;
}
char* duplicateStrUtill(const char* pSrc, char endchar, bool ignoreEndCharInQuoted)
{
const char* pSearched = (ignoreEndCharInQuoted ? findFirstUnquotedChar(pSrc,endchar) : strchr(pSrc, endchar));;
if(pSearched <= pSrc) return NULL;
int n = pSearched - pSrc;
return duplicateStr(pSrc, n);
}
void freeDuplicatedStr(char* p)
{
if(p) free(p);
}
void skipSpaceChars(char*& p)
{
if(p)
{
while(isspace(*p)) p++;
}
}
inline const char* nextUnqotedSpaceChar(const char* p)
{
return findFirstUnquotedChars(p, " \n\r\t\f", 5, true);
}
char* duplicateStrAndUnquote(const char* str, size_t nChar, const char* prefix = NULL)
{
if( nChar > 1 && (str[0] == '\"' && str[nChar-1] == '\"') || (str[0] == '\'' && str[nChar-1] == '\'') )
{
str++; nChar-=2;
}
return duplicateStr(str, nChar, prefix);
}
//-----------------------------------------------------------------------------
// TagName & TagType
struct N2T { const char* name; HtmlTagType type; };
static HtmlTagType identifyHtmlTagInTable(const char* szTagName, N2T* table, int count)
{
for(int i = 0; i < count; i++)
{
N2T* p = table + i;
if(stricmp(p->name, szTagName) == 0)
return p->type;
}
return TAG_UNKNOWN;
}
//出于解析需要必须识别的HtmlTagType
static HtmlTagType identifyHtmlTag_Internal(const char* szTagName)
{
static N2T n2tTable[] =
{
{ "SCRIPT", TAG_SCRIPT },
{ "STYLE", TAG_STYLE },
{ "TEXTAREA", TAG_TEXTAREA },
};
return identifyHtmlTagInTable(szTagName, n2tTable, sizeof(n2tTable)/sizeof(n2tTable[0]));
}
//[virtual]
HtmlTagType HtmlParser::onIdentifyHtmlTag(const char* szTagName, HtmlNodeType nodeType)
{
//默认仅识别涉及HTML基本结构和信息的有限几个TAG
//交给用户自行扩展以便识别更多或更少
if(nodeType != NODE_START_TAG)
return TAG_UNKNOWN;
static N2T n2tTable[] =
{
{ "A", TAG_A },
{ "IMG", TAG_IMG },
{ "META", TAG_META },
{ "BODY", TAG_BODY },
{ "TITLE", TAG_TITLE },
{ "FRAME", TAG_FRAME },
{ "IFRAME", TAG_IFRAME },
};
return identifyHtmlTagInTable(szTagName, n2tTable, sizeof(n2tTable)/sizeof(n2tTable[0]));
}
HtmlNode* HtmlParser::appendHtmlNode()
{
static char staticHtmlNodeTemplate[sizeof(HtmlNode)] = {0};
size_t offset = m_HtmlNodes.appendData(staticHtmlNodeTemplate, sizeof(HtmlNode));
HtmlNode* pNode = (HtmlNode*) m_HtmlNodes.getOffsetData(offset);
pNode->type = NODE_UNKNOWN;
return pNode;
}
static void setNodeAttributeText(HtmlNode* pNode, const char* pStart)
{
while(isspace(*pStart)) pStart++;
if(pStart[0] == '>') return; //no attribute text
if(pStart[0] == '/' && pStart[1] == '>')
{
pNode->flags |= FLAG_SELF_CLOSING_TAG; //自封闭标签
return; //no attribute text
}
char* attributeText = duplicateStrUtill(pStart, '>', true);
if(attributeText)
{
int len = strlen(attributeText);
if(attributeText[len-1] == '/') //去掉最后可能会有的'/'字符, 如这种情况: <img src="..." />
{
attributeText[len-1] = '\0';
pNode->flags |= FLAG_SELF_CLOSING_TAG; //自封闭标签
}
pNode->text = attributeText;
pNode->flags |= FLAG_NEED_FREE_TEXT; //标记需释放文本
}
}
static const char* s_LF = "\n"; //Unix,Linux
static const char* s_CR = "\r"; //Mac
static const char* s_CRLF = "\r\n"; //Windows
// pNode != NULL, pStart != NULL, len > 0
static void setNodeText(HtmlNode* pNode, const char* pStart, int len)
{
//由于空行文本比较常见，每个行首标签的前面都可能有一个空行文本
//此处优化直接返回常量文本，以减少不必要的内存分配
//因为没有设定FLAG_NEED_FREE_TEXT标记，freeHtmlNode(pNode)里不会释放这类常量文本
if(len == 1 && pStart[0] == '\n') { pNode->text = (char*)s_LF; return; }
if(pStart[0] == '\r')
{
if(len == 1) { pNode->text = (char*)s_CR; return; }
if(len == 2 && pStart[1] == '\n') { pNode->text = (char*)s_CRLF; return; }
}
char* text = duplicateStr(pStart, len); //TODO: 将来优化到尽量少复制文本
if(text)
{
pNode->text = text;
pNode->flags |= FLAG_NEED_FREE_TEXT; //标记需释放文本
}
}
void HtmlParser::parseHtml(const char* szHtml, bool parseAttributes)
{
cleanHtmlNodes();
if(szHtml == NULL || *szHtml == '\0')
{
HtmlNode* pNode = appendHtmlNode();
pNode->type = NODE_NULL;
return; //额外添加一个NODE_NULL节点
}
char* p = (char*) szHtml;
char* s = (char*) szHtml;
HtmlNode* pNode = NULL;
char c;
bool bInQuote1 = false; //between ' and '
bool bInQuote2 = false; //between " and "
bool bInScript = false; //between <scripte> and </script>
bool bInStyle = false; //between <style> and </style>
bool bInTextArea = false; //between <textarea> and </textarea>
bool bInsideTag = false; //between < and >
while( c = *p )
{
if(bInsideTag)
{
//在 < 和 > 之间，跳过单引号或双引号内的任何文本（包括<和>）
if(c == '\'')
{
bInQuote1 = !bInQuote1;
p++; continue;
}
else if(c == '\"')
{
bInQuote2 = !bInQuote2;
p++; continue;
}
if(bInQuote1 || bInQuote2)
{
p++; continue;
}
}
if(bInScript)
{
//跳过<script>和</script>之间的任何文本
const char* pEndScript = findFirstStr(p, "</script>", false);
if(pEndScript)
{
bInScript = false;
p = (char*)pEndScript;
c = *p;
}
else
goto onerror; //error: no </script>
}
else if(bInStyle)
{
//跳过<style>和</style>之间的任何文本
const char* pEndStyle = findFirstStr(p, "</style>", false);
if(pEndStyle)
{
bInStyle = false;
p = (char*)pEndStyle;
c = *p;
}
else
goto onerror; //error: no </style>
}
else if(bInTextArea)
{
//跳过<textarea>和</textarea>之间的任何文本
const char* pEndTextArea = findFirstStr(p, "</textarea>", false);
if(pEndTextArea)
{
bInTextArea = false;
p = (char*)pEndTextArea;
c = *p;
}
else
goto onerror; //error: no </textarea>
}
if(c == '<') // <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
{
if(p > s)
{
//Add Content Node
pNode = appendHtmlNode();
pNode->type = NODE_CONTENT;
setNodeText(pNode, s, p - s);
if(onNodeReady(pNode) == false) goto onuserend;
}
//处理HTML注释或CDATA
if(p[1] == '!')
{
if(p[2] == '-' && p[3] == '-')
{
//注释: <!-- ... -->
const char* pEndRemarks = findFirstStr(p + 4, "-->", true);
if(pEndRemarks)
{
//Add Remarks Node
pNode = appendHtmlNode();
pNode->type = NODE_REMARKS;
setNodeText(pNode, p + 4, pEndRemarks - (p + 4));
if(onNodeReady(pNode) == false) goto onuserend;
s = p = (char*)pEndRemarks + 3;
bInsideTag = bInQuote1 = bInQuote2 = false;
continue;
}
//else: no -->, not very bad, try continue parsing
}
else if(p[2] == '[' && strStartWith(p+3, "CDATA[", 5, false))
{
//CDATA: <![CDATA[ ... ]]>
const char* pEndCData = findFirstStr(p + 9, "]]>", true);
if(pEndCData)
{
//Add Content Node with CDATA flag
pNode = appendHtmlNode();
pNode->type = NODE_CONTENT;
setNodeText(pNode, p + 9, pEndCData - (p + 9));
pNode->flags |= FLAG_CDATA_BLOCK; //标记CDATA, used by outputHtml() and dumpHtml()
if(onNodeReady(pNode) == false) goto onuserend;
s = p = (char*)pEndCData + 3;
bInsideTag = bInQuote1 = bInQuote2 = false;
continue;
}
//else: no ]]>, not very bad, try contiune parsing
}
}
s = p + 1;
bInsideTag = true; bInQuote1 = bInQuote2 = false;
}
else if(c == '>') // >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>
{
if(p > s)
{
//创建新节点(HtmlNode)，得到节点类型(NodeType)和名称(TagName)
pNode = appendHtmlNode();
while(isspace(*s)) s++;
pNode->type = (*s == '/' ? NODE_END_TAG : NODE_START_TAG);
if(*s == '/') s++;
//这里得到的tagName可能包含一部分属性文本，需在下面修正
//tagName也可能是这种情况 a href="///////////////// （即缓冲区被填满,最后一个/是属性值中的字符）
copyStrUtill(pNode->tagName, MAX_HTML_TAG_LENGTH, s, '>', true);
int tagNameLen = strlen(pNode->tagName);
if(tagNameLen < MAX_HTML_TAG_LENGTH && pNode->tagName[tagNameLen-1] == '/')
{
//处理自封闭的标签, 如<br/>, 删除tagName中可能会有的'/'字符
//自封闭的结点的type设置为NODE_START_TAG应该可以接受(否则要引入新的节点类型NODE_STARTCLOSE_TAG)
pNode->flags |= FLAG_SELF_CLOSING_TAG; //used by outputHtml() and dumpHtml()
pNode->tagName[tagNameLen-1] = '\0';
tagNameLen--;
}
//修正节点名称，提取属性文本(存入pNode->text)
int i;
for(i = 0; i < tagNameLen; i++)
{
if(isspace(pNode->tagName[i]) //第一个空白字符后面跟的是属性文本
|| pNode->tagName[i] == '=') //扩展支持这种格式: <tagName=value>, 等效于<tagName tagName=value>
{
char* attributes = (pNode->tagName[i] == '=' ? s : s + i + 1);
setNodeAttributeText(pNode, attributes); //此处也处理了自封闭标签
pNode->tagName[i] = '\0';
break;
}
}
if(i == tagNameLen)
{
//parse error, tag name is too long, MAX_HTML_TAG_LENGTH is too small
}
//识别节点类型(HtmlTagType) - 内部处理
pNode->tagType = identifyHtmlTag_Internal(pNode->tagName); //内部识别SCRIPT,STYLE
if(pNode->tagType == TAG_STYLE)
bInStyle = (pNode->type == NODE_START_TAG);
else if(pNode->tagType == TAG_SCRIPT)
bInScript = (pNode->type == NODE_START_TAG);
else if(pNode->tagType == TAG_TEXTAREA)
bInTextArea = (pNode->type == NODE_START_TAG);
//识别节点类型(HtmlTagType) - 用户处理
if(pNode->tagType == TAG_UNKNOWN)
pNode->tagType = onIdentifyHtmlTag(pNode->tagName, pNode->type);
//解析节点属性
if(pNode->type == NODE_START_TAG && parseAttributes && pNode->text)
onParseAttributes(pNode);
if(onNodeReady(pNode) == false) goto onuserend;
}
s = p + 1;
bInsideTag = bInQuote1 = bInQuote2 = false;
}
p++;
}
if(p > s)
{
//Add Content Node
pNode = appendHtmlNode();
pNode->type = NODE_CONTENT;
setNodeText(pNode, s, strlen(s));
if(onNodeReady(pNode) == false) goto onuserend;
}
goto endnodes;
return;
onerror:
pNode = appendHtmlNode();
pNode->type = NODE_CONTENT;
setNodeText(pNode, s, strlen(s));
goto endnodes;
return;
onuserend:
goto endnodes;
return;
endnodes:
//确保在所有节点最后额外添加一个NODE_NULL节点
pNode = appendHtmlNode();
pNode->type = NODE_NULL;
#ifdef _DEBUG
//dumpHtmlNodes(); //just for test
#endif
}
int HtmlParser::getHtmlNodeCount()
{
//不包括最后一个额外添加的NODE_NULL节点，参见parseHtml()
return (int)(m_HtmlNodes.getDataSize() / sizeof(HtmlNode)) - 1;
}
HtmlNode* HtmlParser::getHtmlNode(int index)
{
assert(index >= 0 && index <= getHtmlNodeCount());
return (HtmlNode*)m_HtmlNodes.getData() + index;
}
void HtmlParser::cleanHtmlNodes()
{
for(int i = 0, count = getHtmlNodeCount(); i < count; i++)
{
HtmlNode* pNode = getHtmlNode(i);
cleanHtmlNode(pNode);
}
m_HtmlNodes.clean();
}
void HtmlParser::cleanHtmlNode(HtmlNode* pNode)
{
if(pNode == NULL) return;
if(pNode->text && (pNode->flags & FLAG_NEED_FREE_TEXT))
{
freeDuplicatedStr(pNode->text);
}
pNode->text = NULL;
if(pNode->attributes)
{
for(int attributeIndex = 0; attributeIndex < pNode->attributeCount; attributeIndex++)
{
HtmlAttribute* pAttribute = (HtmlAttribute*) getAttribute(pNode, attributeIndex);
if(pAttribute->name && (pAttribute->flags & FLAG_NEED_FREE_NAME))
freeDuplicatedStr(pAttribute->name);
if(pAttribute->value && (pAttribute->flags & FLAG_NEED_FREE_VALUE))
freeDuplicatedStr(pAttribute->value);
pAttribute->name = NULL;
pAttribute->value = NULL;
pAttribute->flags = 0;
}
delete(pNode->attributes); //see: HtmlParser.parseAttributes()
pNode->attributes = NULL;
}
pNode->attributeCount = 0;
}
bool HtmlParser::cloneHtmlNode(const HtmlNode* pSrcNode, HtmlNode* pDestNode)
{
if(pDestNode == NULL)
return false;
memcpy(pDestNode, pSrcNode, sizeof(HtmlNode)); //先浅拷贝，后面是深拷贝
if(pSrcNode->text)
{
pDestNode->text = duplicateStr(pSrcNode->text, -1);
pDestNode->flags |= FLAG_NEED_FREE_TEXT;
}
if(pSrcNode->attributes)
{
pDestNode->attributes = new MemBuffer(*pSrcNode->attributes);
HtmlAttribute* pAttributes = (HtmlAttribute*) pDestNode->attributes->getData();
for(int i = 0; i < pSrcNode->attributeCount; ++i)
{
HtmlAttribute* pAttribute = pAttributes + i;
if(pAttribute->name)
{
pAttribute->name = duplicateStr(pAttribute->name, -1);
pAttribute->flags |= FLAG_NEED_FREE_NAME;
}
if(pAttribute->value)
{
pAttribute->value = duplicateStr(pAttribute->value, -1);
pAttribute->flags |= FLAG_NEED_FREE_VALUE;
}
}
}
return true;
}
//[virtual]
void HtmlParser::onParseAttributes(HtmlNode* pNode)
{
if(pNode->tagType != TAG_UNKNOWN)
parseAttributes(pNode);
}
void HtmlParser::parseExtraAttributes(const char* szAttributesText, HtmlNode* pTargetNode, const char* szNamePrefix)
{
assert(pTargetNode);
const char* p = szAttributesText;
const char* ps = NULL;
MemBuffer mem;
bool inQuote1 = false, inQuote2 = false;
char c;
while(c = *p)
{
if(c == '\'')
inQuote1 = !inQuote1;
else if(c == '\"')
inQuote2 = !inQuote2;
bool notInQuote = (!inQuote1 && !inQuote2);
if(notInQuote && (c == '\"' || c == '\'') && !isspace(p[1]))
{
//处理属性值引号后面没有空白分隔符的情况：a="v1"b=v2 （这种错误写法不少见，应兼容之）
if(ps)
{
mem.appendPointer(duplicateStrAndUnquote(ps, p - ps + 1));
ps = NULL;
}
p++;
continue;
}
if(notInQuote && (c == '=' || isspace(c)))
{
if(ps)
{
mem.appendPointer(duplicateStrAndUnquote(ps, p - ps));
ps = NULL;
}
if(c == '=')
mem.appendPointer(NULL);
}
else
{
if(ps == NULL)
ps = p;
}
p++;
}
if(ps)
mem.appendPointer(duplicateStrAndUnquote(ps, p - ps));
mem.appendPointer(NULL);
mem.appendPointer(NULL);
char** pp = (char**) mem.getData();
//下面把解析出来的属性值存入pTargetNode->attributes
MemBuffer* attributes = pTargetNode->attributes;
if(attributes == NULL)
{
attributes = new MemBuffer();
pTargetNode->attributes = attributes;
}
for(int i = 0, n = mem.getDataSize() / sizeof(char*) - 2; i < n; i++)
{
if(!szNamePrefix)
{
attributes->appendPointer(pp[i]); //attribute name
} else {
char* newAttributeName = duplicateStr(pp[i], -1, szNamePrefix);
attributes->appendPointer(newAttributeName); //attribute name
freeDuplicatedStr(pp[i]);
}
if(pp[i+1] == NULL)
{
attributes->appendPointer(pp[i+2]); //attribute value
i += 2;
}
else
attributes->appendPointer(NULL); //attribute vlalue
//标记需free属性名称和属性值文本
//TODO: 将来优化到尽量少复制文本
attributes->appendInt((size_t)(FLAG_NEED_FREE_NAME | FLAG_NEED_FREE_VALUE)); //attribute flags
}
attributes->shrink();
pTargetNode->attributeCount = attributes->getDataSize() / sizeof(HtmlAttribute);
}
void HtmlParser::parseAttributes(HtmlNode* pNode)
{
if(pNode == NULL || pNode->attributeCount > 0 || pNode->text == NULL)
return;
if(pNode->tagName[0] == '!' && stricmp(pNode->tagName+1, "DOCTYPE") == 0)
return; //don't parse <!DOCTYPE ...>'s text: not name=value syntax
HtmlParser::parseExtraAttributes(pNode->text, pNode, NULL);
}
const HtmlAttribute* HtmlParser::getAttribute(const HtmlNode* pNode, size_t index)
{
return ((HtmlAttribute*) pNode->attributes->getData()) + index;
}
const HtmlAttribute* HtmlParser::getAttribute(const HtmlNode* pNode, const char* szAttributeName)
{
if(pNode == NULL || pNode->attributeCount <= 0)
return NULL;
for(int i = 0; i < pNode->attributeCount; i++)
{
const HtmlAttribute* attribute = getAttribute(pNode, i);
if(stricmp(attribute->name, szAttributeName) == 0)
return attribute;
}
return NULL;
}
const char* HtmlParser::getAttributeStringValue(const HtmlNode* pNode, const char* szAttributeName, const char* szDefaultValue /*= NULL*/)
{
const HtmlAttribute* pAttribute = getAttribute(pNode, szAttributeName);
if(pAttribute)
return pAttribute->value;
else
return szDefaultValue;
}
int HtmlParser::getAttributeIntValue(const HtmlNode* pNode, const char* szAttributeName, int defaultValue /*= 0*/)
{
const HtmlAttribute* pAttribute = getAttribute(pNode, szAttributeName);
if(pAttribute && pAttribute->value)
return atoi(pAttribute->value);
else
return defaultValue;
}
void HtmlParser::dumpHtmlNodes(FILE* f)
{
fprintf(f, "\r\n-------- begin HtmlParser.dumpHtmlNodes() --------\r\n");
for(int i = 0, count = getHtmlNodeCount(); i < count; i++)
{
HtmlNode* pNode = getHtmlNode(i);
dumpHtmlNode(pNode, i, f);
}
fprintf(f, "-------- end of HtmlParser.dumpHtmlNodes() --------\r\n");
}
void HtmlParser::dumpHtmlNode(const HtmlNode* pNode, int nodeIndex, FILE* f)
{
assert(pNode);
char buffer[256] = {0};
switch(pNode->type)
{
case NODE_CONTENT:
sprintf(buffer, "%2d) type: NODE_CONTENT", nodeIndex);
break;
case NODE_START_TAG:
sprintf(buffer, "%2d) type: NODE_START_TAG, tagName: %s (%d)", nodeIndex, pNode->tagName, pNode->tagType);
break;
case NODE_END_TAG:
sprintf(buffer, "%2d) type: NODE_END_TAG, tagName: %s (%d)", nodeIndex, pNode->tagName, pNode->tagType);
break;
case NODE_REMARKS:
sprintf(buffer, "%2d) type: NODE_REMARKS", nodeIndex);
break;
case NODE_UNKNOWN:
default:
sprintf(buffer, "%2d) type: UNKNOWN NODE (type = %d)", nodeIndex, pNode->type);
break;
}
fprintf(f, "%s", buffer);
if(pNode->text)
fprintf(f, ", text: %s", pNode->text);
if(pNode->flags & FLAG_SELF_CLOSING_TAG)
fprintf(f, ", flags: />"); //自封闭
if(pNode->flags & FLAG_CDATA_BLOCK)
fprintf(f, ", flags: CDATA"); //CDATA
fprintf(f, "\r\n");
if(pNode->attributeCount > 0)
{
fprintf(f, " attributes: ");
for(int i = 0; i < pNode->attributeCount; i++)
{
const HtmlAttribute* pAttribute = getAttribute(pNode, i);
if(pAttribute->value)
fprintf(f, "%s = \"%s\"", pAttribute->name, pAttribute->value);
else
fprintf(f, "%s", pAttribute->name);
if(i < pNode->attributeCount - 1)
{
fprintf(f, ", ");
}
}
fprintf(f, "\r\n");
}
}
void HtmlParser::outputHtml(MemBuffer& buffer, bool keepBufferData)
{
if(!keepBufferData) buffer.empty();
for(int nodeIndex = 0, count = getHtmlNodeCount(); nodeIndex < count; nodeIndex++)
{
HtmlNode* pNode = getHtmlNode(nodeIndex);
outputHtmlNode(buffer, pNode);
}
}
void HtmlParser::outputHtmlNode(MemBuffer& buffer, const HtmlNode* pNode)
{
int attributeIndex = 0;
if(pNode == NULL)
return;
switch(pNode->type)
{
case NODE_CONTENT:
if(pNode->flags & FLAG_CDATA_BLOCK)
{
buffer.appendText("<![CDATA[", 9);
buffer.appendText(pNode->text);
buffer.appendText("]]>", 3);
}
else
buffer.appendText(pNode->text);
break;
case NODE_START_TAG:
buffer.appendChar('<');
buffer.appendText(pNode->tagName);
if(pNode->attributeCount > 0)
buffer.appendChar(' ');
for(attributeIndex = 0; attributeIndex < pNode->attributeCount; attributeIndex++)
{
const HtmlAttribute* pAttribute = getAttribute(pNode, attributeIndex);
buffer.appendText(pAttribute->name);
if(pAttribute->value)
{
bool hasQuoteChar = (strchr(pAttribute->value, '\"') != NULL);
buffer.appendChar('=');
buffer.appendChar(hasQuoteChar ? '\'' : '\"');
buffer.appendText(pAttribute->value);
buffer.appendChar(hasQuoteChar ? '\'' : '\"');
}
if(attributeIndex < pNode->attributeCount - 1)
buffer.appendChar(' ');
}
if(pNode->attributeCount == 0 && pNode->text) //比如 <!DOCTYPE ...>
{
buffer.appendChar(' ');
buffer.appendText(pNode->text);
}
if(pNode->flags & FLAG_SELF_CLOSING_TAG)
buffer.appendText(" /"); //自封闭
buffer.appendChar('>');
break;
case NODE_END_TAG:
buffer.appendText("</");
buffer.appendText(pNode->tagName);
buffer.appendChar('>');
break;
case NODE_REMARKS:
buffer.appendText("<!--");
buffer.appendText(pNode->text);
buffer.appendText("-->");
break;
case NODE_UNKNOWN:
default:
fprintf(stderr, "HtmlParser.outputHtmlNode(): NODE_UNKNOWN\n");
break;
} //end switch
}
//-----------------------------------------------------------------------------
// class MemBuffer
MemBuffer::MemBuffer(size_t nBufferSize) : m_pBuffer(NULL), m_nDataSize(0), m_nBufferSize(0)
{
if(nBufferSize == (size_t)-1)
nBufferSize = MEM_DEFAULT_BUFFER_SIZE;
if(nBufferSize > 0)
require(nBufferSize);
}
MemBuffer::MemBuffer(const MemBuffer& other) : m_pBuffer(NULL), m_nDataSize(0), m_nBufferSize(0)
{
*this = other; // invoke operator=()
}
MemBuffer::~MemBuffer()
{
clean();
}
const MemBuffer& MemBuffer::operator= (const MemBuffer& other)
{
if(&other != this)
{
resetDataSize(0);
appendData(other.getData(), other.getDataSize());
}
return *this;
}
void MemBuffer::clean()
{
if(m_pBuffer) free(m_pBuffer);
m_pBuffer = NULL;
m_nDataSize = m_nBufferSize = 0;
}
void* MemBuffer::detach(bool bShrink)
{
if(bShrink) shrink();
void* pReturn = m_pBuffer;
//数据长度为0时返回NULL,内部释放m_pBuffer
if(m_pBuffer && m_nDataSize == 0)
{
free(m_pBuffer);
pReturn = NULL;
}
m_pBuffer = NULL;
m_nDataSize = m_nBufferSize = 0;
return pReturn;
}
void* MemBuffer::require(size_t size)