File: html.C

package info (click to toggle)
html2text 1.3.2a-3
  • links: PTS
  • area: main
  • in suites: etch, etch-m68k
  • size: 736 kB
  • ctags: 1,694
  • sloc: cpp: 9,311; yacc: 828; sh: 209; makefile: 144
file content (645 lines) | stat: -rw-r--r-- 16,628 bytes parent folder | download | duplicates (7)
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

 /***************************************************************************/

/*
 * Portions Copyright (c) 1999 GMRS Software GmbH
 * Carl-von-Linde-Str. 38, D-85716 Unterschleissheim, http://www.gmrs.de
 * All rights reserved.
 *
 * Author: Arno Unkrig <arno@unkrig.de>
 */
 
/* This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License in the file COPYING for more details.
 */

 /***************************************************************************/
 
/*
 * Changes to version 1.2.2 were made by Martin Bayer <mbayer@zedat.fu-berlin.de>
 * Dates and reasons of modifications:
 * Fre Jun  8 17:43:02 CEST 2001: new method
 * Wed Jul  2 22:07:12 CEST 2003: ported to g++ 3.3
 */

 /***************************************************************************/


#include <stdlib.h>
#include <stdarg.h>
#include <iostream>

#include "html.h"
#include "HTMLParser.h"
#include "cmp_nocase.h"

/* ------------------------------------------------------------------------- */

/*
 * Define some helpers.
 */

#define define_foreach(T, args, action) \
void foreach args { \
  for (T::const_iterator i = l.begin(); i != l.end(); ++i) { \
    action; \
  } \
}

#define pack(T) \
define_foreach(list<auto_ptr<T> >, ( \
  const list<auto_ptr<T> > &l, \
  ostream                  &os, \
  ostream_manipulator      separator \
), (*i)->unparse(os, separator))

static pack(Element)
static pack(TableCell)
static pack(TableRow)
static pack(ListItem)
static pack(Option)
static pack(DefinitionListItem)
static pack(Script)
static pack(Style)

#undef pack

/*
 * Special helper for "const auto_ptr<list<TagAttribute> > &".
 */
static ostream &operator<<(ostream &os, const auto_ptr<list<TagAttribute> > &a)
{
  if (a.get()) {
    const list<TagAttribute> &al(*a);
    list<TagAttribute>::const_iterator i;
    for (i = al.begin(); i != al.end(); ++i) {
      os << " " << (*i).first << "=\"" << (*i).second << "\"";
    }
  }
  return os;
}

/* ------------------------------------------------------------------------- */

/*
 * Brothers of "endl".
 */
static ostream &none(ostream &os) { return os; }

/* ------------------------------------------------------------------------- */

/*
 * Some C++ compilers (e.g. EGCS 2.91.66) have problems if all virtual
 * methods of a class are inline or pure virtual, so we define the virtual
 * "Element::~Element()", which is the only virtual method, non-inline,
 * although it is empty.
 */
Element::~Element()
{
}

/* ------------------------------------------------------------------------- */

void
Document::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<HTML" << attributes << ">" << separator;
  head.unparse(os, separator);
  body.unparse(os, separator);
  os << "</HTML>" << separator;
}

void
Head::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<HEAD>" << separator;
  if (title.get()) {
    os << "<TITLE>" << separator;
    title->unparse(os, separator);
    os << "</TITLE>" << separator;
  }
  if (isindex_attributes.get()) {
    os << "<ISINDEX"<< isindex_attributes << ">" << std::endl;
  }
  if (base_attributes.get()) os << "<BASE" << base_attributes << ">" << std::endl;
  foreach(scripts, os, separator);
  foreach(styles, os, separator);
  if (meta_attributes.get()) os << "<META" << meta_attributes << ">" << std::endl;
  if (link_attributes.get()) os << "<LINK" << link_attributes << ">" << std::endl;
  os << "</HEAD>" << separator;
}

void
Script::unparse(ostream &os, ostream_manipulator separator) const
{
  os
    << "<SCRIPT" << attributes << ">" << separator
    << text
    << "</SCRIPT>" << separator;
}

void
Style::unparse(ostream &os, ostream_manipulator separator) const
{
  os
    << "<STYLE" << attributes << ">" << separator
    << text
    << "</STYLE>" << separator;
}

void
Body::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<BODY" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</BODY>" << separator;
}

void
PCData::unparse(ostream &os, ostream_manipulator separator) const
{
  for (string::size_type j = 0; j < text.length(); ++j) {
    char c = text[j];
    switch (((int) c) & 255) {
    case LATIN1_nbsp: os << "&nbsp;"; break;
    case '&':         os << "&amp;";  break;
    case '<':         os << "&lt;";   break;
    case '>':         os << "&gt;";   break;
    case '"':         os << "&quot;"; break;
    default:
      if (c & 0x80) {
        os << "&#" << (((int) c) & 255) << ";";
      } else {
        os << c;
      }
      break;
    }
  }

  os << separator;
}

void
Heading::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<H" << level << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</H" << level << ">" << separator;
}

void
Paragraph::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<P" << attributes << ">" << separator;
  if (texts.get()) foreach(*texts, os, separator);
  os << "</P>" << separator;
}

void
Image::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<IMG" << attributes << ">" << separator;
}

void
Applet::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<APPLET" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</APPLET>" << separator;
}

void
Param::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<PARAM" << attributes << ">" << separator;
}

void
Division::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<DIV" << attributes << ">" << separator;
  if (body_content.get()) foreach(*body_content, os, separator);
  os << "</DIV>" << separator;
}

void
Center::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<CENTER>" << separator;
  if (body_content.get()) foreach(*body_content, os, separator);
  os << "</CENTER>" << separator;
}

void
BlockQuote::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<BLOCKQUOTE>" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</BLOCKQUOTE>" << separator;
}

void
Address::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<ADDRESS>" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</ADDRESS>" << separator;
}

void
Form::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<FORM" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</FORM>" << separator;
}

void
Preformatted::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<PRE" << attributes << ">" << separator;
  if (texts.get()) { foreach(*texts, os, none); os << separator; }
  os << "</PRE>" << separator;
}

void
HorizontalRule::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<HR" << attributes << ">" << separator;
}

void
Input::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<INPUT" << attributes << ">" << separator;
}

void
Option::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<OPTION" << attributes << ">" << separator;
  if (pcdata.get()) pcdata->unparse(os, separator);
  os << "</OPTION>" << std::endl;
}

void
Select::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<SELECT" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</SELECT>" << std::endl;
}

void
TextArea::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<TEXTAREA" << attributes << ">" << separator;
  if (pcdata.get()) pcdata->unparse(os, separator);
  os << "</TEXTAREA>" << std::endl;
}

/* ------------------------------------------------------------------------- */

void
OrderedList::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<OL" << attributes << ">" << separator;
  if (items.get()) foreach(*items, os, separator);
  os << "</OL>" << separator;
}

void
UnorderedList::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<UL" << attributes << ">" << separator;
  if (items.get()) foreach(*items, os, separator);
  os << "</UL>" << separator;
}

void
Dir::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<DIR" << attributes << ">" << separator;
  if (items.get()) foreach(*items, os, separator);
  os << "</DIR>" << separator;
}

void
Menu::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<MENU" << attributes << ">" << separator;
  if (items.get()) foreach(*items, os, separator);
  os << "</MENU>" << separator;
}

void
ListNormalItem::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<LI" <<attributes << ">" << separator;
  if (flow.get()) foreach(*flow, os, separator);
  os << "</LI>" << separator;
}

void
ListBlockItem::unparse(ostream &os, ostream_manipulator separator) const
{
  if (block.get()) block->unparse(os, separator);
}

/* ------------------------------------------------------------------------- */

void
DefinitionList::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<DL" << attributes << ">" << separator;
  if (items.get()) foreach(*items, os, separator);
  os << "</DL>" << separator;
}

void
TermName::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<DT>" << separator;
  if (flow.get()) foreach(*flow, os, separator);
  os << "</DT>" << separator;
}

void
TermDefinition::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<DD>" << separator;
  if (flow.get()) foreach(*flow, os, separator);
  os << "</DD>" << separator;
}

/* ------------------------------------------------------------------------- */

void
Table::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<TABLE" << attributes << ">" << separator;
  if (caption.get()) caption->unparse(os, separator);
  if (rows.get()) foreach(*rows, os, separator);
  os << "</TABLE>" << separator;
}

void
NoBreak::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<NOBR>" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</NOBR>" << separator;
}

void
Font::unparse(ostream &os, ostream_manipulator separator) const
{
  const char *tag = (
    attribute == HTMLParser::TT     ? "TT" :
    attribute == HTMLParser::I      ? "I" :
    attribute == HTMLParser::B      ? "B" :
    attribute == HTMLParser::U      ? "U" :
    attribute == HTMLParser::STRIKE ? "STRIKE" :
    attribute == HTMLParser::BIG    ? "BIG" :
    attribute == HTMLParser::SMALL  ? "SMALL" :
    attribute == HTMLParser::SUB    ? "SUB" :
    attribute == HTMLParser::SUP    ? "SUP" :
    "???"
  );

  os << "<" << tag << ">" << separator;
  if (texts.get()) foreach(*texts, os, separator);
  os << "</" << tag << ">" << separator;
}

void
Phrase::unparse(ostream &os, ostream_manipulator separator) const
{
  const char *tag = (
    attribute == HTMLParser::EM     ? "EM" :
    attribute == HTMLParser::STRONG ? "STRONG" :
    attribute == HTMLParser::DFN    ? "DFN" :
    attribute == HTMLParser::CODE   ? "CODE" :
    attribute == HTMLParser::SAMP   ? "SAMP" :
    attribute == HTMLParser::KBD    ? "KBD" :
    attribute == HTMLParser::VAR    ? "VAR" :
    attribute == HTMLParser::CITE   ? "CITE" :
    "???"
  );

  os << "<" << tag << ">" << separator;
  if (texts.get()) foreach(*texts, os, separator);
  os << "</" << tag << ">" << separator;
}

void
Anchor::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<A" << attributes << ">" << separator;
  if (texts.get()) foreach(*texts, os, separator);
  os << "</A>" << separator;
}

void
BaseFont::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<BASEFONT" << attributes << ">" << separator;
}

void
LineBreak::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<BR" << attributes << ">" << separator;
}

void
Map::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<MAP" << attributes << ">" << separator;
  if (areas.get()) {
    const list<auto_ptr<list<TagAttribute> > >           &al(*areas);
    list<auto_ptr<list<TagAttribute> > >::const_iterator i;
    for (i = al.begin(); i != al.end(); ++i) {
      os << "<AREA" << *i << ">" << separator;
    }
  }
  os << "</MAP>" << separator;
}

void
Font2::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<FONT" << attributes << ">" << separator;
  if (elements.get()) foreach(*elements, os, separator);
  os << "</FONT>" << separator;
}

void
TableRow::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<TR" << attributes << ">" << separator;
  if (cells.get()) foreach(*cells, os, separator);
  os << "</TR>" << separator;
}

void
TableCell::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<TD" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</TD>" << separator;
}

void
TableHeadingCell::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<TH" << attributes << ">" << separator;
  if (content.get()) foreach(*content, os, separator);
  os << "</TH>" << separator;
}

void
Caption::unparse(ostream &os, ostream_manipulator separator) const
{
  os << "<CAPTION" << attributes << ">" << separator;
  if (texts.get()) foreach(*texts, os, separator);
  os << "</CAPTION>" << separator;
}

/* ------------------------------------------------------------------------- */

string
get_attribute(
  const list<TagAttribute> *as,
  const char               *name,
  const char               *dflt
)
{
  if (as) {
    list<TagAttribute>::const_iterator i;
    for (i = as->begin(); i != as->end(); ++i) {
      if (cmp_nocase((*i).first, name) == 0) return string((*i).second);
    }
  }
  return string(dflt);
}

// *exists is set to false if attribute *name does not exist - Johannes Geiger

string
get_attribute(
  const list<TagAttribute> *as,
  const char               *name,
  bool                     *exists
)
{
  *exists = true;
  if (as) {
    list<TagAttribute>::const_iterator i;
    for (i = as->begin(); i != as->end(); ++i) {
      if (cmp_nocase((*i).first, name) == 0) return string((*i).second);
    }
  }
  *exists = false;
  return string("");
}


int
get_attribute(
  const list<TagAttribute> *as,
  const char               *name,
  int                      dflt
)
{
  if (as) {
    list<TagAttribute>::const_iterator i;
    for (i = as->begin(); i != as->end(); ++i) {
      if (cmp_nocase((*i).first, name) == 0) return atoi((*i).second.c_str());
    }
  }
  return dflt;
}

int
get_attribute(
  const list<TagAttribute> *as,
  const char               *name,
  int                      dflt,
  const char               *s1,
  int                      v1,
  ...
)
{
  if (as) {
    list<TagAttribute>::const_iterator i;
    for (i = as->begin(); i != as->end(); ++i) {
      if (cmp_nocase((*i).first, name) == 0) {
        const char *s = s1;
        int        v = v1;

        va_list va;
        va_start(va, v1);
        for (;;) {
          if (cmp_nocase(s, (*i).second) == 0) break;
          s = va_arg(va, const char *);
          if (!s) { v = dflt; break; }
          v = va_arg(va, int);
        }
        va_end(va);
        return v;
      }
    }
  }
  return dflt;
}

int
get_attribute(
  const list<TagAttribute> *as,
  const char               *name,   // Attribute name
  const char               *dflt1,  // If attribute not specified
  int                      dflt2,   // If string value does not match s1, ...
  const char               *s1,
  int                      v1,
  ...
)
{
  if (as) {
    list<TagAttribute>::const_iterator i;
    for (i = as->begin(); i != as->end(); ++i) {
      if (cmp_nocase((*i).first, name) == 0) {
	dflt1 = (*i).second.c_str();
        break;
      }
    }
  }

  if (!dflt1) return dflt2;

  const char *s = s1;
  int        v = v1;

  va_list va;
  va_start(va, v1);
  for (;;) {
    if (cmp_nocase(s, dflt1) == 0) break;
    s = va_arg(va, const char *);
    if (!s) break;
    v = va_arg(va, int);
  }
  va_end(va);

  return s ? v : dflt2;
}

/* ------------------------------------------------------------------------- */