]> git.saurik.com Git - wxWidgets.git/blob - src/html/htmlpars.cpp
better learn the operators...
[wxWidgets.git] / src / html / htmlpars.cpp
1 /////////////////////////////////////////////////////////////////////////////
2 // Name: htmlpars.cpp
3 // Purpose: wxHtmlParser class (generic parser)
4 // Author: Vaclav Slavik
5 // RCS-ID: $Id$
6 // Copyright: (c) 1999 Vaclav Slavik
7 // Licence: wxWindows Licence
8 /////////////////////////////////////////////////////////////////////////////
9
10
11 #ifdef __GNUG__
12 #pragma implementation
13 #endif
14
15 #include "wx/wxprec.h"
16
17 #include "wx/defs.h"
18 #if wxUSE_HTML && wxUSE_STREAMS
19
20 #ifdef __BORDLANDC__
21 #pragma hdrstop
22 #endif
23
24 #ifndef WXPRECOMP
25 #include "wx/log.h"
26 #include "wx/intl.h"
27 #endif
28
29 #include "wx/tokenzr.h"
30 #include "wx/wfstream.h"
31 #include "wx/url.h"
32 #include "wx/fontmap.h"
33 #include "wx/html/htmldefs.h"
34 #include "wx/html/htmlpars.h"
35 #include "wx/dynarray.h"
36 #include "wx/arrimpl.cpp"
37
38 //-----------------------------------------------------------------------------
39 // wxHtmlParser helpers
40 //-----------------------------------------------------------------------------
41
42 class wxHtmlTextPiece
43 {
44 public:
45 wxHtmlTextPiece(int pos, int lng) : m_pos(pos), m_lng(lng) {}
46 int m_pos, m_lng;
47 };
48
49 WX_DECLARE_OBJARRAY(wxHtmlTextPiece, wxHtmlTextPieces);
50 WX_DEFINE_OBJARRAY(wxHtmlTextPieces);
51
52 class wxHtmlParserState
53 {
54 public:
55 wxHtmlTag *m_curTag;
56 wxHtmlTag *m_tags;
57 wxHtmlTextPieces *m_textPieces;
58 int m_curTextPiece;
59 wxString m_source;
60 wxHtmlParserState *m_nextState;
61 };
62
63 //-----------------------------------------------------------------------------
64 // wxHtmlParser
65 //-----------------------------------------------------------------------------
66
67 IMPLEMENT_ABSTRACT_CLASS(wxHtmlParser,wxObject)
68
69 wxHtmlParser::wxHtmlParser()
70 : wxObject(), m_HandlersHash(wxKEY_STRING),
71 m_FS(NULL), m_HandlersStack(NULL)
72 {
73 m_entitiesParser = new wxHtmlEntitiesParser;
74 m_Tags = NULL;
75 m_CurTag = NULL;
76 m_TextPieces = NULL;
77 m_CurTextPiece = 0;
78 m_SavedStates = NULL;
79 }
80
81 wxHtmlParser::~wxHtmlParser()
82 {
83 while (RestoreState()) {}
84 DestroyDOMTree();
85
86 delete m_HandlersStack;
87 m_HandlersHash.Clear();
88 m_HandlersList.DeleteContents(TRUE);
89 m_HandlersList.Clear();
90 delete m_entitiesParser;
91 }
92
93 wxObject* wxHtmlParser::Parse(const wxString& source)
94 {
95 wxObject *result;
96
97 InitParser(source);
98 DoParsing();
99 result = GetProduct();
100 DoneParser();
101 return result;
102 }
103
104 void wxHtmlParser::InitParser(const wxString& source)
105 {
106 SetSource(source);
107 }
108
109 void wxHtmlParser::DoneParser()
110 {
111 DestroyDOMTree();
112 }
113
114 void wxHtmlParser::SetSource(const wxString& src)
115 {
116 DestroyDOMTree();
117 m_Source = src;
118 CreateDOMTree();
119 m_CurTag = NULL;
120 m_CurTextPiece = 0;
121 }
122
123 void wxHtmlParser::CreateDOMTree()
124 {
125 wxHtmlTagsCache cache(m_Source);
126 m_TextPieces = new wxHtmlTextPieces;
127 CreateDOMSubTree(NULL, 0, m_Source.Length(), &cache);
128 m_CurTextPiece = 0;
129 }
130
131 void wxHtmlParser::CreateDOMSubTree(wxHtmlTag *cur,
132 int begin_pos, int end_pos,
133 wxHtmlTagsCache *cache)
134 {
135 if (end_pos <= begin_pos) return;
136
137 wxChar c;
138 int i = begin_pos;
139 int textBeginning = begin_pos;
140
141 while (i < end_pos)
142 {
143 c = m_Source.GetChar(i);
144
145 if (c == wxT('<'))
146 {
147 // add text to m_TextPieces:
148 if (i - textBeginning > 0)
149 m_TextPieces->Add(
150 wxHtmlTextPiece(textBeginning, i - textBeginning));
151
152 // if it is a comment, skip it:
153 if (i < end_pos-6 && m_Source.GetChar(i+1) == wxT('!') &&
154 m_Source.GetChar(i+2) == wxT('-') &&
155 m_Source.GetChar(i+3) == wxT('-'))
156 {
157 // Comments begin with "<!--" and end with "--[ \t\r\n]*>"
158 // according to HTML 4.0
159 int dashes = 0;
160 i += 4;
161 while (i < end_pos)
162 {
163 c = m_Source.GetChar(i++);
164 if ((c == wxT(' ') || c == wxT('\n') ||
165 c == wxT('\r') || c == wxT('\t')) && dashes >= 2) {}
166 else if (c == wxT('>') && dashes >= 2)
167 {
168 textBeginning = i;
169 break;
170 }
171 else if (c == wxT('-'))
172 dashes++;
173 else
174 dashes = 0;
175 }
176 }
177
178 // add another tag to the tree:
179 else if (i < end_pos-1 && m_Source.GetChar(i+1) != wxT('/'))
180 {
181 wxHtmlTag *chd;
182 if (cur)
183 chd = new wxHtmlTag(cur, m_Source,
184 i, end_pos, cache, m_entitiesParser);
185 else
186 {
187 chd = new wxHtmlTag(NULL, m_Source,
188 i, end_pos, cache, m_entitiesParser);
189 if (!m_Tags)
190 {
191 // if this is the first tag to be created make the root
192 // m_Tags point to it:
193 m_Tags = chd;
194 }
195 else
196 {
197 // if there is already a root tag add this tag as
198 // the last sibling:
199 chd->m_Prev = m_Tags->GetLastSibling();
200 chd->m_Prev->m_Next = chd;
201 }
202 }
203
204 if (chd->HasEnding())
205 {
206 CreateDOMSubTree(chd,
207 chd->GetBeginPos(), chd->GetEndPos1(),
208 cache);
209 i = chd->GetEndPos2();
210 }
211 else
212 i = chd->GetBeginPos();
213 textBeginning = i;
214 }
215
216 // ... or skip ending tag:
217 else
218 {
219 while (i < end_pos && m_Source.GetChar(i) != wxT('>')) i++;
220 textBeginning = i+1;
221 }
222 }
223 else i++;
224 }
225
226 // add remaining text to m_TextPieces:
227 if (end_pos - textBeginning > 0)
228 m_TextPieces->Add(
229 wxHtmlTextPiece(textBeginning, end_pos - textBeginning));
230 }
231
232 void wxHtmlParser::DestroyDOMTree()
233 {
234 wxHtmlTag *t1, *t2;
235 t1 = m_Tags;
236 while (t1)
237 {
238 t2 = t1->GetNextSibling();
239 delete t1;
240 t1 = t2;
241 }
242 m_Tags = m_CurTag = NULL;
243
244 delete m_TextPieces;
245 m_TextPieces = NULL;
246 }
247
248 void wxHtmlParser::DoParsing()
249 {
250 m_CurTag = m_Tags;
251 m_CurTextPiece = 0;
252 DoParsing(0, m_Source.Length());
253 }
254
255 void wxHtmlParser::DoParsing(int begin_pos, int end_pos)
256 {
257 if (end_pos <= begin_pos) return;
258
259 wxHtmlTextPieces& pieces = *m_TextPieces;
260 size_t piecesCnt = pieces.GetCount();
261
262 while (begin_pos < end_pos)
263 {
264 while (m_CurTag && m_CurTag->GetBeginPos() < begin_pos)
265 m_CurTag = m_CurTag->GetNextTag();
266 while (m_CurTextPiece < piecesCnt &&
267 pieces[m_CurTextPiece].m_pos < begin_pos)
268 m_CurTextPiece++;
269
270 if (m_CurTextPiece < piecesCnt &&
271 (!m_CurTag ||
272 pieces[m_CurTextPiece].m_pos < m_CurTag->GetBeginPos()))
273 {
274 // Add text:
275 AddText(GetEntitiesParser()->Parse(
276 m_Source.Mid(pieces[m_CurTextPiece].m_pos,
277 pieces[m_CurTextPiece].m_lng)));
278 begin_pos = pieces[m_CurTextPiece].m_pos +
279 pieces[m_CurTextPiece].m_lng;
280 m_CurTextPiece++;
281 }
282 else if (m_CurTag)
283 {
284 // Add tag:
285 if (m_CurTag)
286 {
287 if (m_CurTag->HasEnding())
288 begin_pos = m_CurTag->GetEndPos2();
289 else
290 begin_pos = m_CurTag->GetBeginPos();
291 }
292 wxHtmlTag *t = m_CurTag;
293 m_CurTag = m_CurTag->GetNextTag();
294 AddTag(*t);
295 }
296 else break;
297 }
298 }
299
300 void wxHtmlParser::AddTag(const wxHtmlTag& tag)
301 {
302 wxHtmlTagHandler *h;
303 bool inner = FALSE;
304
305 h = (wxHtmlTagHandler*) m_HandlersHash.Get(tag.GetName());
306 if (h)
307 inner = h->HandleTag(tag);
308 if (!inner)
309 {
310 if (tag.HasEnding())
311 DoParsing(tag.GetBeginPos(), tag.GetEndPos1());
312 }
313 }
314
315 void wxHtmlParser::AddTagHandler(wxHtmlTagHandler *handler)
316 {
317 wxString s(handler->GetSupportedTags());
318 wxStringTokenizer tokenizer(s, wxT(", "));
319
320 while (tokenizer.HasMoreTokens())
321 m_HandlersHash.Put(tokenizer.NextToken(), handler);
322
323 if (m_HandlersList.IndexOf(handler) == wxNOT_FOUND)
324 m_HandlersList.Append(handler);
325
326 handler->SetParser(this);
327 }
328
329 void wxHtmlParser::PushTagHandler(wxHtmlTagHandler *handler, wxString tags)
330 {
331 wxStringTokenizer tokenizer(tags, wxT(", "));
332 wxString key;
333
334 if (m_HandlersStack == NULL)
335 {
336 m_HandlersStack = new wxList;
337 m_HandlersStack->DeleteContents(TRUE);
338 }
339
340 m_HandlersStack->Insert(new wxHashTable(m_HandlersHash));
341
342 while (tokenizer.HasMoreTokens())
343 {
344 key = tokenizer.NextToken();
345 m_HandlersHash.Delete(key);
346 m_HandlersHash.Put(key, handler);
347 }
348 }
349
350 void wxHtmlParser::PopTagHandler()
351 {
352 wxNode *first;
353
354 if (m_HandlersStack == NULL ||
355 (first = m_HandlersStack->GetFirst()) == NULL)
356 {
357 wxLogWarning(_("Warning: attempt to remove HTML tag handler from empty stack."));
358 return;
359 }
360 m_HandlersHash = *((wxHashTable*) first->GetData());
361 m_HandlersStack->DeleteNode(first);
362 }
363
364 void wxHtmlParser::SetSourceAndSaveState(const wxString& src)
365 {
366 wxHtmlParserState *s = new wxHtmlParserState;
367
368 s->m_curTag = m_CurTag;
369 s->m_tags = m_Tags;
370 s->m_textPieces = m_TextPieces;
371 s->m_curTextPiece = m_CurTextPiece;
372 s->m_source = m_Source;
373
374 s->m_nextState = m_SavedStates;
375 m_SavedStates = s;
376
377 m_CurTag = NULL;
378 m_Tags = NULL;
379 m_TextPieces = NULL;
380 m_CurTextPiece = 0;
381 m_Source = wxEmptyString;
382
383 SetSource(src);
384 }
385
386 bool wxHtmlParser::RestoreState()
387 {
388 if (!m_SavedStates) return FALSE;
389
390 DestroyDOMTree();
391
392 wxHtmlParserState *s = m_SavedStates;
393 m_SavedStates = s->m_nextState;
394
395 m_CurTag = s->m_curTag;
396 m_Tags = s->m_tags;
397 m_TextPieces = s->m_textPieces;
398 m_CurTextPiece = s->m_curTextPiece;
399 m_Source = s->m_source;
400
401 delete s;
402 return TRUE;
403 }
404
405 //-----------------------------------------------------------------------------
406 // wxHtmlTagHandler
407 //-----------------------------------------------------------------------------
408
409 IMPLEMENT_ABSTRACT_CLASS(wxHtmlTagHandler,wxObject)
410
411
412 //-----------------------------------------------------------------------------
413 // wxHtmlEntitiesParser
414 //-----------------------------------------------------------------------------
415
416 IMPLEMENT_DYNAMIC_CLASS(wxHtmlEntitiesParser,wxObject)
417
418 wxHtmlEntitiesParser::wxHtmlEntitiesParser()
419 #if wxUSE_WCHAR_T && !wxUSE_UNICODE
420 : m_conv(NULL), m_encoding(wxFONTENCODING_SYSTEM)
421 #endif
422 {
423 }
424
425 wxHtmlEntitiesParser::~wxHtmlEntitiesParser()
426 {
427 #if wxUSE_WCHAR_T && !wxUSE_UNICODE
428 delete m_conv;
429 #endif
430 }
431
432 void wxHtmlEntitiesParser::SetEncoding(wxFontEncoding encoding)
433 {
434 #if wxUSE_WCHAR_T && !wxUSE_UNICODE
435 if (encoding == m_encoding) return;
436 delete m_conv;
437 m_conv = NULL;
438 m_encoding = encoding;
439 if (m_encoding != wxFONTENCODING_SYSTEM)
440 m_conv = new wxCSConv(wxFontMapper::GetEncodingName(m_encoding));
441 #else
442 (void) encoding;
443 #endif
444 }
445
446 wxString wxHtmlEntitiesParser::Parse(const wxString& input)
447 {
448 const wxChar *c, *last;
449 const wxChar *in_str = input.c_str();
450 wxString output;
451
452 for (c = in_str, last = in_str; *c != wxT('\0'); c++)
453 {
454 if (*c == wxT('&'))
455 {
456 if (c - last > 0)
457 output.append(last, c - last);
458 if (++c == wxT('\0')) break;
459 wxString entity;
460 const wxChar *ent_s = c;
461 for (; (*c >= wxT('a') && *c <= wxT('z')) ||
462 (*c >= wxT('A') && *c <= wxT('Z')) ||
463 (*c >= wxT('0') && *c <= wxT('9')) ||
464 *c == wxT('_') || *c == wxT('#'); c++) {}
465 entity.append(ent_s, c - ent_s);
466 if (*c != wxT(';')) c--;
467 last = c+1;
468 output << GetEntityChar(entity);
469 }
470 }
471 if (*last != wxT('\0'))
472 output.append(last);
473 return output;
474 }
475
476 struct wxHtmlEntityInfo
477 {
478 const wxChar *name;
479 unsigned code;
480 };
481
482 static int LINKAGEMODE compar_entity(const void *key, const void *item)
483 {
484 return wxStrcmp((wxChar*)key, ((wxHtmlEntityInfo*)item)->name);
485 }
486
487 wxChar wxHtmlEntitiesParser::GetCharForCode(unsigned code)
488 {
489 #if wxUSE_UNICODE
490 return (wxChar)code;
491 #elif wxUSE_WCHAR_T
492 char buf[2];
493 wchar_t wbuf[2];
494 wbuf[0] = (wchar_t)code;
495 wbuf[1] = 0;
496 wxMBConv *conv = m_conv ? m_conv : &wxConvLocal;
497 if (conv->WC2MB(buf, wbuf, 2) == (size_t)-1)
498 return '?';
499 return buf[0];
500 #else
501 return (code < 256) ? (wxChar)code : '?';
502 #endif
503 }
504
505 wxChar wxHtmlEntitiesParser::GetEntityChar(const wxString& entity)
506 {
507 unsigned code = 0;
508
509 if (entity[0] == wxT('#'))
510 {
511 const wxChar *ent_s = entity.c_str();
512 const wxChar *format;
513
514 if (ent_s[1] == wxT('x') || ent_s[1] == wxT('X'))
515 {
516 format = wxT("%x");
517 ent_s++;
518 }
519 else
520 format = wxT("%u");
521 ent_s++;
522
523 if (wxSscanf(ent_s, format, &code) != 1)
524 code = 0;
525 }
526 else
527 {
528 static wxHtmlEntityInfo substitutions[] = {
529 { wxT("AElig"),198 },
530 { wxT("Aacute"),193 },
531 { wxT("Acirc"),194 },
532 { wxT("Agrave"),192 },
533 { wxT("Alpha"),913 },
534 { wxT("Aring"),197 },
535 { wxT("Atilde"),195 },
536 { wxT("Auml"),196 },
537 { wxT("Beta"),914 },
538 { wxT("Ccedil"),199 },
539 { wxT("Chi"),935 },
540 { wxT("Dagger"),8225 },
541 { wxT("Delta"),916 },
542 { wxT("ETH"),208 },
543 { wxT("Eacute"),201 },
544 { wxT("Ecirc"),202 },
545 { wxT("Egrave"),200 },
546 { wxT("Epsilon"),917 },
547 { wxT("Eta"),919 },
548 { wxT("Euml"),203 },
549 { wxT("Gamma"),915 },
550 { wxT("Iacute"),205 },
551 { wxT("Icirc"),206 },
552 { wxT("Igrave"),204 },
553 { wxT("Iota"),921 },
554 { wxT("Iuml"),207 },
555 { wxT("Kappa"),922 },
556 { wxT("Lambda"),923 },
557 { wxT("Mu"),924 },
558 { wxT("Ntilde"),209 },
559 { wxT("Nu"),925 },
560 { wxT("OElig"),338 },
561 { wxT("Oacute"),211 },
562 { wxT("Ocirc"),212 },
563 { wxT("Ograve"),210 },
564 { wxT("Omega"),937 },
565 { wxT("Omicron"),927 },
566 { wxT("Oslash"),216 },
567 { wxT("Otilde"),213 },
568 { wxT("Ouml"),214 },
569 { wxT("Phi"),934 },
570 { wxT("Pi"),928 },
571 { wxT("Prime"),8243 },
572 { wxT("Psi"),936 },
573 { wxT("Rho"),929 },
574 { wxT("Scaron"),352 },
575 { wxT("Sigma"),931 },
576 { wxT("THORN"),222 },
577 { wxT("Tau"),932 },
578 { wxT("Theta"),920 },
579 { wxT("Uacute"),218 },
580 { wxT("Ucirc"),219 },
581 { wxT("Ugrave"),217 },
582 { wxT("Upsilon"),933 },
583 { wxT("Uuml"),220 },
584 { wxT("Xi"),926 },
585 { wxT("Yacute"),221 },
586 { wxT("Yuml"),376 },
587 { wxT("Zeta"),918 },
588 { wxT("aacute"),225 },
589 { wxT("acirc"),226 },
590 { wxT("acute"),180 },
591 { wxT("aelig"),230 },
592 { wxT("agrave"),224 },
593 { wxT("alefsym"),8501 },
594 { wxT("alpha"),945 },
595 { wxT("amp"),38 },
596 { wxT("and"),8743 },
597 { wxT("ang"),8736 },
598 { wxT("aring"),229 },
599 { wxT("asymp"),8776 },
600 { wxT("atilde"),227 },
601 { wxT("auml"),228 },
602 { wxT("bdquo"),8222 },
603 { wxT("beta"),946 },
604 { wxT("brvbar"),166 },
605 { wxT("bull"),8226 },
606 { wxT("cap"),8745 },
607 { wxT("ccedil"),231 },
608 { wxT("cedil"),184 },
609 { wxT("cent"),162 },
610 { wxT("chi"),967 },
611 { wxT("circ"),710 },
612 { wxT("clubs"),9827 },
613 { wxT("cong"),8773 },
614 { wxT("copy"),169 },
615 { wxT("crarr"),8629 },
616 { wxT("cup"),8746 },
617 { wxT("curren"),164 },
618 { wxT("dArr"),8659 },
619 { wxT("dagger"),8224 },
620 { wxT("darr"),8595 },
621 { wxT("deg"),176 },
622 { wxT("delta"),948 },
623 { wxT("diams"),9830 },
624 { wxT("divide"),247 },
625 { wxT("eacute"),233 },
626 { wxT("ecirc"),234 },
627 { wxT("egrave"),232 },
628 { wxT("empty"),8709 },
629 { wxT("emsp"),8195 },
630 { wxT("ensp"),8194 },
631 { wxT("epsilon"),949 },
632 { wxT("equiv"),8801 },
633 { wxT("eta"),951 },
634 { wxT("eth"),240 },
635 { wxT("euml"),235 },
636 { wxT("euro"),8364 },
637 { wxT("exist"),8707 },
638 { wxT("fnof"),402 },
639 { wxT("forall"),8704 },
640 { wxT("frac12"),189 },
641 { wxT("frac14"),188 },
642 { wxT("frac34"),190 },
643 { wxT("frasl"),8260 },
644 { wxT("gamma"),947 },
645 { wxT("ge"),8805 },
646 { wxT("gt"),62 },
647 { wxT("hArr"),8660 },
648 { wxT("harr"),8596 },
649 { wxT("hearts"),9829 },
650 { wxT("hellip"),8230 },
651 { wxT("iacute"),237 },
652 { wxT("icirc"),238 },
653 { wxT("iexcl"),161 },
654 { wxT("igrave"),236 },
655 { wxT("image"),8465 },
656 { wxT("infin"),8734 },
657 { wxT("int"),8747 },
658 { wxT("iota"),953 },
659 { wxT("iquest"),191 },
660 { wxT("isin"),8712 },
661 { wxT("iuml"),239 },
662 { wxT("kappa"),954 },
663 { wxT("lArr"),8656 },
664 { wxT("lambda"),955 },
665 { wxT("lang"),9001 },
666 { wxT("laquo"),171 },
667 { wxT("larr"),8592 },
668 { wxT("lceil"),8968 },
669 { wxT("ldquo"),8220 },
670 { wxT("le"),8804 },
671 { wxT("lfloor"),8970 },
672 { wxT("lowast"),8727 },
673 { wxT("loz"),9674 },
674 { wxT("lrm"),8206 },
675 { wxT("lsaquo"),8249 },
676 { wxT("lsquo"),8216 },
677 { wxT("lt"),60 },
678 { wxT("macr"),175 },
679 { wxT("mdash"),8212 },
680 { wxT("micro"),181 },
681 { wxT("middot"),183 },
682 { wxT("minus"),8722 },
683 { wxT("mu"),956 },
684 { wxT("nabla"),8711 },
685 { wxT("nbsp"),160 },
686 { wxT("ndash"),8211 },
687 { wxT("ne"),8800 },
688 { wxT("ni"),8715 },
689 { wxT("not"),172 },
690 { wxT("notin"),8713 },
691 { wxT("nsub"),8836 },
692 { wxT("ntilde"),241 },
693 { wxT("nu"),957 },
694 { wxT("oacute"),243 },
695 { wxT("ocirc"),244 },
696 { wxT("oelig"),339 },
697 { wxT("ograve"),242 },
698 { wxT("oline"),8254 },
699 { wxT("omega"),969 },
700 { wxT("omicron"),959 },
701 { wxT("oplus"),8853 },
702 { wxT("or"),8744 },
703 { wxT("ordf"),170 },
704 { wxT("ordm"),186 },
705 { wxT("oslash"),248 },
706 { wxT("otilde"),245 },
707 { wxT("otimes"),8855 },
708 { wxT("ouml"),246 },
709 { wxT("para"),182 },
710 { wxT("part"),8706 },
711 { wxT("permil"),8240 },
712 { wxT("perp"),8869 },
713 { wxT("phi"),966 },
714 { wxT("pi"),960 },
715 { wxT("piv"),982 },
716 { wxT("plusmn"),177 },
717 { wxT("pound"),163 },
718 { wxT("prime"),8242 },
719 { wxT("prod"),8719 },
720 { wxT("prop"),8733 },
721 { wxT("psi"),968 },
722 { wxT("quot"),34 },
723 { wxT("rArr"),8658 },
724 { wxT("radic"),8730 },
725 { wxT("rang"),9002 },
726 { wxT("raquo"),187 },
727 { wxT("rarr"),8594 },
728 { wxT("rceil"),8969 },
729 { wxT("rdquo"),8221 },
730 { wxT("real"),8476 },
731 { wxT("reg"),174 },
732 { wxT("rfloor"),8971 },
733 { wxT("rho"),961 },
734 { wxT("rlm"),8207 },
735 { wxT("rsaquo"),8250 },
736 { wxT("rsquo"),8217 },
737 { wxT("sbquo"),8218 },
738 { wxT("scaron"),353 },
739 { wxT("sdot"),8901 },
740 { wxT("sect"),167 },
741 { wxT("shy"),173 },
742 { wxT("sigma"),963 },
743 { wxT("sigmaf"),962 },
744 { wxT("sim"),8764 },
745 { wxT("spades"),9824 },
746 { wxT("sub"),8834 },
747 { wxT("sube"),8838 },
748 { wxT("sum"),8721 },
749 { wxT("sup"),8835 },
750 { wxT("sup1"),185 },
751 { wxT("sup2"),178 },
752 { wxT("sup3"),179 },
753 { wxT("supe"),8839 },
754 { wxT("szlig"),223 },
755 { wxT("tau"),964 },
756 { wxT("there4"),8756 },
757 { wxT("theta"),952 },
758 { wxT("thetasym"),977 },
759 { wxT("thinsp"),8201 },
760 { wxT("thorn"),254 },
761 { wxT("tilde"),732 },
762 { wxT("times"),215 },
763 { wxT("trade"),8482 },
764 { wxT("uArr"),8657 },
765 { wxT("uacute"),250 },
766 { wxT("uarr"),8593 },
767 { wxT("ucirc"),251 },
768 { wxT("ugrave"),249 },
769 { wxT("uml"),168 },
770 { wxT("upsih"),978 },
771 { wxT("upsilon"),965 },
772 { wxT("uuml"),252 },
773 { wxT("weierp"),8472 },
774 { wxT("xi"),958 },
775 { wxT("yacute"),253 },
776 { wxT("yen"),165 },
777 { wxT("yuml"),255 },
778 { wxT("zeta"),950 },
779 { wxT("zwj"),8205 },
780 { wxT("zwnj"),8204 },
781 {NULL, 0}};
782 static size_t substitutions_cnt = 0;
783
784 if (substitutions_cnt == 0)
785 while (substitutions[substitutions_cnt].code != 0)
786 substitutions_cnt++;
787
788 wxHtmlEntityInfo *info;
789 info = (wxHtmlEntityInfo*) bsearch(entity.c_str(), substitutions,
790 substitutions_cnt,
791 sizeof(wxHtmlEntityInfo),
792 compar_entity);
793 if (info)
794 code = info->code;
795 }
796
797 if (code == 0)
798 return wxT('?');
799 else
800 return GetCharForCode(code);
801 }
802
803 #endif