aboutsummaryrefslogblamecommitdiffstats
path: root/library/markdownify/markdownify.php
blob: 0d4429a01336e10d9ce17ab43170201ae874bef1 (plain) (tree)
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
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196















































































































































































































































































































































































































































































































































































































































































































                                                                                                                                                  



                                                                              












                                                                                
  



































                                                                                                                

                                                    
                                                                                                                                                          



                                                                                                              























                                                                                 
  





































































































































































































































































































































































































































                                                                                                                                                        
 
<?php
/**
 * Markdownify converts HTML Markup to [Markdown][1] (by [John Gruber][2]. It
 * also supports [Markdown Extra][3] by [Michel Fortin][4] via Markdownify_Extra.
 *
 * It all started as `html2text.php` - a port of [Aaron Swartz'][5] [`html2text.py`][6] - but
 * got a long way since. This is far more than a mere port now!
 * Starting with version 2.0.0 this is a complete rewrite and cannot be
 * compared to Aaron Swatz' `html2text.py` anylonger. I'm now using a HTML parser
 * (see `parsehtml.php` which I also wrote) which makes most of the evil
 * RegEx magic go away and additionally it gives a much cleaner class
 * structure. Also notably is the fact that I now try to prevent regressions by
 * utilizing testcases of Michel Fortin's [MDTest][7].
 *
 * [1]: http://daringfireball.com/projects/markdown
 * [2]: http://daringfireball.com/
 * [3]: http://www.michelf.com/projects/php-markdown/extra/
 * [4]: http://www.michelf.com/
 * [5]: http://www.aaronsw.com/
 * [6]: http://www.aaronsw.com/2002/html2text/
 * [7]: http://article.gmane.org/gmane.text.markdown.general/2540
 *
 * @version 2.0.0 alpha
 * @author Milian Wolff (<mail@milianw.de>, <http://milianw.de>)
 * @license LGPL, see LICENSE_LGPL.txt and the summary below
 * @copyright (C) 2007  Milian Wolff
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 */

/**
 * HTML Parser, see http://sf.net/projects/parseHTML
 */
require_once dirname(__FILE__).'/parsehtml/parsehtml.php';

/**
 * default configuration
 */
define('MDFY_LINKS_EACH_PARAGRAPH', false);
define('MDFY_BODYWIDTH', false);
define('MDFY_KEEPHTML', true);

/**
 * HTML to Markdown converter class
 */
class Markdownify {
  /**
   * html parser object
   *
   * @var parseHTML
   */
  var $parser;
  /**
   * markdown output
   *
   * @var string
   */
  var $output;
  /**
   * stack with tags which where not converted to html
   *
   * @var array<string>
   */
  var $notConverted = array();
  /**
   * skip conversion to markdown
   *
   * @var bool
   */
  var $skipConversion = false;
  /* options */
  /**
   * keep html tags which cannot be converted to markdown
   *
   * @var bool
   */
  var $keepHTML = false;
  /**
   * wrap output, set to 0 to skip wrapping
   *
   * @var int
   */
  var $bodyWidth = 0;
  /**
   * minimum body width
   *
   * @var int
   */
  var $minBodyWidth = 25;
  /**
   * display links after each paragraph
   *
   * @var bool
   */
  var $linksAfterEachParagraph = false;
  /**
   * constructor, set options, setup parser
   *
   * @param bool $linksAfterEachParagraph wether or not to flush stacked links after each paragraph
   *             defaults to false
   * @param int $bodyWidth wether or not to wrap the output to the given width
   *             defaults to false
   * @param bool $keepHTML wether to keep non markdownable HTML or to discard it
   *             defaults to true (HTML will be kept)
   * @return void
   */
  function Markdownify($linksAfterEachParagraph = MDFY_LINKS_EACH_PARAGRAPH, $bodyWidth = MDFY_BODYWIDTH, $keepHTML = MDFY_KEEPHTML) {
    $this->linksAfterEachParagraph = $linksAfterEachParagraph;
    $this->keepHTML = $keepHTML;

    if ($bodyWidth > $this->minBodyWidth) {
      $this->bodyWidth = intval($bodyWidth);
    } else {
      $this->bodyWidth = false;
    }

    $this->parser = new parseHTML;
    $this->parser->noTagsInCode = true;

    # we don't have to do this every time
    $search = array();
    $replace = array();
    foreach ($this->escapeInText as $s => $r) {
      array_push($search, '#(?<!\\\)'.$s.'#U');
      array_push($replace, $r);
    }
    $this->escapeInText = array(
      'search' => $search,
      'replace' => $replace
    );
  }
  /**
   * parse a HTML string
   *
   * @param string $html
   * @return string markdown formatted
   */
  function parseString($html) {
    $this->parser->html = $html;
    $this->parse();
    return $this->output;
  }
  /**
   * tags with elements which can be handled by markdown
   *
   * @var array<string>
   */
  var $isMarkdownable = array(
    'p' => array(),
    'ul' => array(),
    'ol' => array(),
    'li' => array(),
    'br' => array(),
    'blockquote' => array(),
    'code' => array(),
    'pre' => array(),
    'a' => array(
      'href' => 'required',
      'title' => 'optional',
    ),
    'strong' => array(),
    'b' => array(),
    'em' => array(),
    'i' => array(),
    'img' => array(
      'src' => 'required',
      'alt' => 'optional',
      'title' => 'optional',
    ),
    'h1' => array(),
    'h2' => array(),
    'h3' => array(),
    'h4' => array(),
    'h5' => array(),
    'h6' => array(),
    'hr' => array(),
  );
  /**
   * html tags to be ignored (contents will be parsed)
   *
   * @var array<string>
   */
  var $ignore = array(
    'html',
    'body',
  );
  /**
   * html tags to be dropped (contents will not be parsed!)
   *
   * @var array<string>
   */
  var $drop = array(
    'script',
    'head',
    'style',
    'form',
    'area',
    'object',
    'param',
    'iframe',
  );
  /**
   * Markdown indents which could be wrapped
   * @note: use strings in regex format
   *
   * @var array<string>
   */
  var $wrappableIndents = array(
    '\*   ', # ul
    '\d.  ', # ol
    '\d\d. ', # ol
    '> ', # blockquote
    '', # p
  );
  /**
   * list of chars which have to be escaped in normal text
   * @note: use strings in regex format
   *
   * @var array
   *
   * TODO: what's with block chars / sequences at the beginning of a block?
   */
  var $escapeInText = array(
    '([-*_])([ ]{0,2}\1){2,}' => '\\\\$0|', # hr
    '\*\*([^*\s]+)\*\*' => '\*\*$1\*\*', # strong
    '\*([^*\s]+)\*' => '\*$1\*', # em
    '__(?! |_)(.+)(?!<_| )__' => '\_\_$1\_\_', # em
    '_(?! |_)(.+)(?!<_| )_' => '\_$1\_', # em
    '`(.+)`' => '\`$1\`', # code
    '\[(.+)\](\s*\()' => '\[$1\]$2', # links: [text] (url) => [text\] (url)
    '\[(.+)\](\s*)\[(.*)\]' => '\[$1\]$2\[$3\]', # links: [text][id] => [text\][id\]
  );
  /**
   * wether last processed node was a block tag or not
   *
   * @var bool
   */
  var $lastWasBlockTag = false;
  /**
   * name of last closed tag
   *
   * @var string
   */
  var $lastClosedTag = '';
  /**
   * iterate through the nodes and decide what we
   * shall do with the current node
   *
   * @param void
   * @return void
   */
  function parse() {
    $this->output = '';
    # drop tags
    $this->parser->html = preg_replace('#<('.implode('|', $this->drop).')[^>]*>.*</\\1>#sU', '', $this->parser->html);
    while ($this->parser->nextNode()) {
      switch ($this->parser->nodeType) {
        case 'doctype':
          break;
        case 'pi':
        case 'comment':
          if ($this->keepHTML) {
            $this->flushLinebreaks();
            $this->out($this->parser->node);
            $this->setLineBreaks(2);
          }
          # else drop
          break;
        case 'text':
          $this->handleText();
          break;
        case 'tag':
          if (in_array($this->parser->tagName, $this->ignore)) {
            break;
          }
          if ($this->parser->isStartTag) {
            $this->flushLinebreaks();
          }
          if ($this->skipConversion) {
            $this->isMarkdownable(); # update notConverted
            $this->handleTagToText();
            continue;
          }
          if (!$this->parser->keepWhitespace && $this->parser->isBlockElement && $this->parser->isStartTag) {
            $this->parser->html = ltrim($this->parser->html);
          }
          if ($this->isMarkdownable()) {
            if ($this->parser->isBlockElement && $this->parser->isStartTag && !$this->lastWasBlockTag && !empty($this->output)) {
              if (!empty($this->buffer)) {
                $str =& $this->buffer[count($this->buffer) -1];
              } else {
                $str =& $this->output;
              }
              if (substr($str, -strlen($this->indent)-1) != "\n".$this->indent) {
                $str .= "\n".$this->indent;
              }
            }
            $func = 'handleTag_'.$this->parser->tagName;
            $this->$func();
            if ($this->linksAfterEachParagraph && $this->parser->isBlockElement && !$this->parser->isStartTag && empty($this->parser->openTags)) {
              $this->flushStacked();
            }
            if (!$this->parser->isStartTag) {
              $this->lastClosedTag = $this->parser->tagName;
            }
          } else {
            $this->handleTagToText();
            $this->lastClosedTag = '';
          }
          break;
        default:
          trigger_error('invalid node type', E_USER_ERROR);
          break;
      }
      $this->lastWasBlockTag = $this->parser->nodeType == 'tag' && $this->parser->isStartTag && $this->parser->isBlockElement;
    }
    if (!empty($this->buffer)) {
      trigger_error('buffer was not flushed, this is a bug. please report!', E_USER_WARNING);
      while (!empty($this->buffer)) {
        $this->out($this->unbuffer());
      }
    }
    ### cleanup
    $this->output = rtrim(str_replace('&amp;', '&', str_replace('&lt;', '<', str_replace('&gt;', '>', $this->output))));
    # end parsing, flush stacked tags
    $this->flushStacked();
    $this->stack = array();
  }
  /**
   * check if current tag can be converted to Markdown
   *
   * @param void
   * @return bool
   */
  function isMarkdownable() {
    if (!isset($this->isMarkdownable[$this->parser->tagName])) {
      # simply not markdownable
      return false;
    }
    if ($this->parser->isStartTag) {
      $return = true;
      if ($this->keepHTML) {
        $diff = array_diff(array_keys($this->parser->tagAttributes), array_keys($this->isMarkdownable[$this->parser->tagName]));
        if (!empty($diff)) {
          # non markdownable attributes given
          $return = false;
        }
      }
      if ($return) {
        foreach ($this->isMarkdownable[$this->parser->tagName] as $attr => $type) {
          if ($type == 'required' && !isset($this->parser->tagAttributes[$attr])) {
            # required markdown attribute not given
            $return = false;
            break;
          }
        }
      }
      if (!$return) {
        array_push($this->notConverted, $this->parser->tagName.'::'.implode('/', $this->parser->openTags));
      }
      return $return;
    } else {
      if (!empty($this->notConverted) && end($this->notConverted) === $this->parser->tagName.'::'.implode('/', $this->parser->openTags)) {
        array_pop($this->notConverted);
        return false;
      }
      return true;
    }
  }
  /**
   * output all stacked tags
   *
   * @param void
   * @return void
   */
  function flushStacked() {
    # links
    foreach ($this->stack as $tag => $a) {
      if (!empty($a)) {
        call_user_func(array(&$this, 'flushStacked_'.$tag));
      }
    }
  }
  /**
   * output link references (e.g. [1]: http://example.com "title");
   *
   * @param void
   * @return void
   */
  function flushStacked_a() {
    $out = false;
    foreach ($this->stack['a'] as $k => $tag) {
      if (!isset($tag['unstacked'])) {
        if (!$out) {
          $out = true;
          $this->out("\n\n", true);
        } else {
          $this->out("\n", true);
        }
        $this->out(' ['.$tag['linkID'].']: '.$tag['href'].(isset($tag['title']) ? ' "'.$tag['title'].'"' : ''), true);
        $tag['unstacked'] = true;
        $this->stack['a'][$k] = $tag;
      }
    }
  }
  /**
   * flush enqued linebreaks
   *
   * @param void
   * @return void
   */
  function flushLinebreaks() {
    if ($this->lineBreaks && !empty($this->output)) {
      $this->out(str_repeat("\n".$this->indent, $this->lineBreaks), true);
    }
    $this->lineBreaks = 0;
  }
  /**
   * handle non Markdownable tags
   *
   * @param void
   * @return void
   */
  function handleTagToText() {
    if (!$this->keepHTML) {
      if (!$this->parser->isStartTag && $this->parser->isBlockElement) {
        $this->setLineBreaks(2);
      }
    } else {
      # dont convert to markdown inside this tag
      /** TODO: markdown extra **/
      if (!$this->parser->isEmptyTag) {
        if ($this->parser->isStartTag) {
          if (!$this->skipConversion) {
            $this->skipConversion = $this->parser->tagName.'::'.implode('/', $this->parser->openTags);
          }
        } else {
          if ($this->skipConversion == $this->parser->tagName.'::'.implode('/', $this->parser->openTags)) {
            $this->skipConversion = false;
          }
        }
      }

      if ($this->parser->isBlockElement) {
        if ($this->parser->isStartTag) {
          if (in_array($this->parent(), array('ins', 'del'))) {
            # looks like ins or del are block elements now
            $this->out("\n", true);
            $this->indent('  ');
          }
          if ($this->parser->tagName != 'pre') {
            $this->out($this->parser->node."\n".$this->indent);
            if (!$this->parser->isEmptyTag) {
              $this->indent('  ');
            } else {
              $this->setLineBreaks(1);
            }
            $this->parser->html = ltrim($this->parser->html);
          } else {
            # don't indent inside <pre> tags
            $this->out($this->parser->node);
            static $indent;
            $indent =  $this->indent;
            $this->indent = '';
          }
        } else {
          if (!$this->parser->keepWhitespace) {
            $this->output = rtrim($this->output);
          }
          if ($this->parser->tagName != 'pre') {
            $this->indent('  ');
            $this->out("\n".$this->indent.$this->parser->node);
          } else {
            # reset indentation
            $this->out($this->parser->node);
            static $indent;
            $this->indent = $indent;
          }

          if (in_array($this->parent(), array('ins', 'del'))) {
            # ins or del was block element
            $this->out("\n");
            $this->indent('  ');
          }
          if ($this->parser->tagName == 'li') {
            $this->setLineBreaks(1);
          } else {
            $this->setLineBreaks(2);
          }
        }
      } else {
        $this->out($this->parser->node);
      }
      if (in_array($this->parser->tagName, array('code', 'pre'))) {
        if ($this->parser->isStartTag) {
          $this->buffer();
        } else {
          # add stuff so cleanup just reverses this
          $this->out(str_replace('&lt;', '&amp;lt;', str_replace('&gt;', '&amp;gt;', $this->unbuffer())));
        }
      }
    }
  }
  /**
   * handle plain text
   *
   * @param void
   * @return void
   */
  function handleText() {
    if ($this->hasParent('pre') && strpos($this->parser->node, "\n") !== false) {
      $this->parser->node = str_replace("\n", "\n".$this->indent, $this->parser->node);
    }
    if (!$this->hasParent('code') && !$this->hasParent('pre')) {
      # entity decode
      $this->parser->node = $this->decode($this->parser->node);
      if (!$this->skipConversion) {
        # escape some chars in normal Text
        $this->parser->node = preg_replace($this->escapeInText['search'], $this->escapeInText['replace'], $this->parser->node);
      }
    } else {
      $this->parser->node = str_replace(array('&quot;', '&apos'), array('"', '\''), $this->parser->node);
    }
    $this->out($this->parser->node);
    $this->lastClosedTag = '';
  }
  /**
   * handle <em> and <i> tags
   *
   * @param void
   * @return void
   */
  function handleTag_em() {
    $this->out('*', true);
  }
  function handleTag_i() {
    $this->handleTag_em();
  }
  /**
   * handle <strong> and <b> tags
   *
   * @param void
   * @return void
   */
  function handleTag_strong() {
    $this->out('**', true);
  }
  function handleTag_b() {
    $this->handleTag_strong();
  }
  /**
   * handle <h1> tags
   *
   * @param void
   * @return void
   */
  function handleTag_h1() {
    $this->handleHeader(1);
  }
  /**
   * handle <h2> tags
   *
   * @param void
   * @return void
   */
  function handleTag_h2() {
    $this->handleHeader(2);
  }
  /**
   * handle <h3> tags
   *
   * @param void
   * @return void
   */
  function handleTag_h3() {
    $this->handleHeader(3);
  }
  /**
   * handle <h4> tags
   *
   * @param void
   * @return void
   */
  function handleTag_h4() {
    $this->handleHeader(4);
  }
  /**
   * handle <h5> tags
   *
   * @param void
   * @return void
   */
  function handleTag_h5() {
    $this->handleHeader(5);
  }
  /**
   * handle <h6> tags
   *
   * @param void
   * @return void
   */
  function handleTag_h6() {
    $this->handleHeader(6);
  }
  /**
   * number of line breaks before next inline output
   */
  var $lineBreaks = 0;
  /**
   * handle header tags (<h1> - <h6>)
   *
   * @param int $level 1-6
   * @return void
   */
  function handleHeader($level) {
    if ($this->parser->isStartTag) {
      $this->out(str_repeat('#', $level).' ', true);
    } else {
      $this->setLineBreaks(2);
    }
  }
  /**
   * handle <p> tags
   *
   * @param void
   * @return void
   */
  function handleTag_p() {
    if (!$this->parser->isStartTag) {
      $this->setLineBreaks(2);
    }
  }
  /**
   * handle <a> tags
   *
   * @param void
   * @return void
   */
  function handleTag_a() {
    if ($this->parser->isStartTag) {
      $this->buffer();
      if (isset($this->parser->tagAttributes['title'])) {
        $this->parser->tagAttributes['title'] = $this->decode($this->parser->tagAttributes['title']);
      } else {
        $this->parser->tagAttributes['title'] = null;
      }
      $this->parser->tagAttributes['href'] = $this->decode(trim($this->parser->tagAttributes['href']));
      $this->stack();
    } else {
      $tag = $this->unstack();
      $buffer = $this->unbuffer();

      if (empty($tag['href']) && empty($tag['title'])) {
        # empty links... testcase mania, who would possibly do anything like that?!
        $this->out('['.$buffer.']()', true);
        return;
      }

      if ($buffer == $tag['href'] && empty($tag['title'])) {
        # <http://example.com>
        $this->out('<'.$buffer.'>', true);
        return;
      }

      $bufferDecoded = $this->decode(trim($buffer));
      if (substr($tag['href'], 0, 7) == 'mailto:' && 'mailto:'.$bufferDecoded == $tag['href']) {
        if (is_null($tag['title'])) {
          # <mail@example.com>
          $this->out('<'.$bufferDecoded.'>', true);
          return;
        }
        # [mail@example.com][1]
        # ...
        #  [1]: mailto:mail@example.com Title
        $tag['href'] = 'mailto:'.$bufferDecoded;
      }

      $this->out('['.$buffer.']('.$tag['href'].' "'.$tag['title'].'")', true);

/*
      # [This link][id]
      foreach ($this->stack['a'] as $tag2) {
        if ($tag2['href'] == $tag['href'] && $tag2['title'] === $tag['title']) {
          $tag['linkID'] = $tag2['linkID'];
          break;
        }
      }
      if (!isset($tag['linkID'])) {
        $tag['linkID'] = count($this->stack['a']) + 1;
        array_push($this->stack['a'], $tag);
      }

      $this->out('['.$buffer.']['.$tag['linkID'].']', true);
*/
    }
  }
  /**
   * handle <img /> tags
   *
   * @param void
   * @return void
   */
  function handleTag_img() {
    if (!$this->parser->isStartTag) {
      return; # just to be sure this is really an empty tag...
    }

    if (isset($this->parser->tagAttributes['title'])) {
      $this->parser->tagAttributes['title'] = $this->decode($this->parser->tagAttributes['title']);
    } else {
      $this->parser->tagAttributes['title'] = null;
    }
    if (isset($this->parser->tagAttributes['alt'])) {
      $this->parser->tagAttributes['alt'] = $this->decode($this->parser->tagAttributes['alt']);
    } else {
      $this->parser->tagAttributes['alt'] = null;
    }

    if (empty($this->parser->tagAttributes['src'])) {
      # support for "empty" images... dunno if this is really needed
      # but there are some testcases which do that...
      if (!empty($this->parser->tagAttributes['title'])) {
        $this->parser->tagAttributes['title'] = ' '.$this->parser->tagAttributes['title'].' ';
      }
      $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['title'].')', true);
      return;
    } else {
      $this->parser->tagAttributes['src'] = $this->decode($this->parser->tagAttributes['src']);
    }

// ![Alt text](/path/to/img.jpg "Optional title")
    if ($this->parser->tagAttributes['title'] != "")
      $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['src'].' "'.$this->parser->tagAttributes['title'].'")', true);
    else
      $this->out('!['.$this->parser->tagAttributes['alt'].']('.$this->parser->tagAttributes['src'].')', true);

/*
    # [This link][id]
    $link_id = false;
    if (!empty($this->stack['a'])) {
      foreach ($this->stack['a'] as $tag) {
        if ($tag['href'] == $this->parser->tagAttributes['src']
            && $tag['title'] === $this->parser->tagAttributes['title']) {
          $link_id = $tag['linkID'];
          break;
        }
      }
    } else {
      $this->stack['a'] = array();
    }
    if (!$link_id) {
      $link_id = count($this->stack['a']) + 1;
      $tag = array(
        'href' => $this->parser->tagAttributes['src'],
        'linkID' => $link_id,
        'title' => $this->parser->tagAttributes['title']
      );
      array_push($this->stack['a'], $tag);
    }

    $this->out('!['.$this->parser->tagAttributes['alt'].']['.$link_id.']', true);
*/
  }
  /**
   * handle <code> tags
   *
   * @param void
   * @return void
   */
  function handleTag_code() {
    if ($this->hasParent('pre')) {
      # ignore code blocks inside <pre>
      return;
    }
    if ($this->parser->isStartTag) {
      $this->buffer();
    } else {
      $buffer = $this->unbuffer();
      # use as many backticks as needed
      preg_match_all('#`+#', $buffer, $matches);
      if (!empty($matches[0])) {
        rsort($matches[0]);

        $ticks = '`';
        while (true) {
          if (!in_array($ticks, $matches[0])) {
            break;
          }
          $ticks .= '`';
        }
      } else {
        $ticks = '`';
      }
      if ($buffer[0] == '`' || substr($buffer, -1) == '`') {
        $buffer = ' '.$buffer.' ';
      }
      $this->out($ticks.$buffer.$ticks, true);
    }
  }
  /**
   * handle <pre> tags
   *
   * @param void
   * @return void
   */
  function handleTag_pre() {
    if ($this->keepHTML && $this->parser->isStartTag) {
      # check if a simple <code> follows
      if (!preg_match('#^\s*<code\s*>#Us', $this->parser->html)) {
        # this is no standard markdown code block
        $this->handleTagToText();
        return;
      }
    }
    $this->indent('    ');
    if (!$this->parser->isStartTag) {
      $this->setLineBreaks(2);
    } else {
      $this->parser->html = ltrim($this->parser->html);
    }
  }
  /**
   * handle <blockquote> tags
   *
   * @param void
   * @return void
   */
  function handleTag_blockquote() {
    $this->indent('> ');
  }
  /**
   * handle <ul> tags
   *
   * @param void
   * @return void
   */
  function handleTag_ul() {
    if ($this->parser->isStartTag) {
      $this->stack();
      if (!$this->keepHTML && $this->lastClosedTag == $this->parser->tagName) {
        $this->out("\n".$this->indent.'<!-- -->'."\n".$this->indent."\n".$this->indent);
      }
    } else {
      $this->unstack();
      if ($this->parent() != 'li' || preg_match('#^\s*(</li\s*>\s*<li\s*>\s*)?<(p|blockquote)\s*>#sU', $this->parser->html)) {
        # dont make Markdown add unneeded paragraphs
        $this->setLineBreaks(2);
      }
    }
  }
  /**
   * handle <ul> tags
   *
   * @param void
   * @return void
   */
  function handleTag_ol() {
    # same as above
    $this->parser->tagAttributes['num'] = 0;
    $this->handleTag_ul();
  }
  /**
   * handle <li> tags
   *
   * @param void
   * @return void
   */
  function handleTag_li() {
    if ($this->parent() == 'ol') {
      $parent =& $this->getStacked('ol');
      if ($this->parser->isStartTag) {
        $parent['num']++;
        $this->out($parent['num'].'.'.str_repeat(' ', 3 - strlen($parent['num'])), true);
      }
      $this->indent('    ', false);
    } else {
      if ($this->parser->isStartTag) {
        $this->out('*   ', true);
      }
      $this->indent('    ', false);
    }
    if (!$this->parser->isStartTag) {
      $this->setLineBreaks(1);
    }
  }
  /**
   * handle <hr /> tags
   *
   * @param void
   * @return void
   */
  function handleTag_hr() {
    if (!$this->parser->isStartTag) {
      return; # just to be sure this really is an empty tag
    }
    $this->out('* * *', true);
    $this->setLineBreaks(2);
  }
  /**
   * handle <br /> tags
   *
   * @param void
   * @return void
   */
  function handleTag_br() {
    $this->out("  \n".$this->indent, true);
    $this->parser->html = ltrim($this->parser->html);
  }
  /**
   * node stack, e.g. for <a> and <abbr> tags
   *
   * @var array<array>
   */
  var $stack = array();
  /**
   * add current node to the stack
   * this only stores the attributes
   *
   * @param void
   * @return void
   */
  function stack() {
    if (!isset($this->stack[$this->parser->tagName])) {
      $this->stack[$this->parser->tagName] = array();
    }
    array_push($this->stack[$this->parser->tagName], $this->parser->tagAttributes);
  }
  /**
   * remove current tag from stack
   *
   * @param void
   * @return array
   */
  function unstack() {
    if (!isset($this->stack[$this->parser->tagName]) || !is_array($this->stack[$this->parser->tagName])) {
      trigger_error('Trying to unstack from empty stack. This must not happen.', E_USER_ERROR);
    }
    return array_pop($this->stack[$this->parser->tagName]);
  }
  /**
   * get last stacked element of type $tagName
   *
   * @param string $tagName
   * @return array
   */
  function & getStacked($tagName) {
    // no end() so it can be referenced
    return $this->stack[$tagName][count($this->stack[$tagName])-1];
  }
  /**
   * set number of line breaks before next start tag
   *
   * @param int $number
   * @return void
   */
  function setLineBreaks($number) {
    if ($this->lineBreaks < $number) {
      $this->lineBreaks = $number;
    }
  }
  /**
   * stores current buffers
   *
   * @var array<string>
   */
  var $buffer = array();
  /**
   * buffer next parser output until unbuffer() is called
   *
   * @param void
   * @return void
   */
  function buffer() {
    array_push($this->buffer, '');
  }
  /**
   * end current buffer and return buffered output
   *
   * @param void
   * @return string
   */
  function unbuffer() {
    return array_pop($this->buffer);
  }
  /**
   * append string to the correct var, either
   * directly to $this->output or to the current
   * buffers
   *
   * @param string $put
   * @return void
   */
  function out($put, $nowrap = false) {
    if (empty($put)) {
      return;
    }
    if (!empty($this->buffer)) {
      $this->buffer[count($this->buffer) - 1] .= $put;
    } else {
      if ($this->bodyWidth && !$this->parser->keepWhitespace) { # wrap lines
        // get last line
        $pos = strrpos($this->output, "\n");
        if ($pos === false) {
          $line = $this->output;
        } else {
          $line = substr($this->output, $pos);
        }

        if ($nowrap) {
          if ($put[0] != "\n" && $this->strlen($line) + $this->strlen($put) > $this->bodyWidth) {
            $this->output .= "\n".$this->indent.$put;
          } else {
            $this->output .= $put;
          }
          return;
        } else {
          $put .= "\n"; # make sure we get all lines in the while below
          $lineLen = $this->strlen($line);
          while ($pos = strpos($put, "\n")) {
            $putLine = substr($put, 0, $pos+1);
            $put = substr($put, $pos+1);
            $putLen = $this->strlen($putLine);
            if ($lineLen + $putLen < $this->bodyWidth) {
              $this->output .= $putLine;
              $lineLen = $putLen;
            } else {
              $split = preg_split('#^(.{0,'.($this->bodyWidth - $lineLen).'})\b#', $putLine, 2, PREG_SPLIT_OFFSET_CAPTURE | PREG_SPLIT_DELIM_CAPTURE);
              $this->output .= rtrim($split[1][0])."\n".$this->indent.$this->wordwrap(ltrim($split[2][0]), $this->bodyWidth, "\n".$this->indent, false);
            }
          }
          $this->output = substr($this->output, 0, -1);
          return;
        }
      } else {
        $this->output .= $put;
      }
    }
  }
  /**
   * current indentation
   *
   * @var string
   */
  var $indent = '';
  /**
   * indent next output (start tag) or unindent (end tag)
   *
   * @param string $str indentation
   * @param bool $output add indendation to output
   * @return void
   */
  function indent($str, $output = true) {
    if ($this->parser->isStartTag) {
      $this->indent .= $str;
      if ($output) {
        $this->out($str, true);
      }
    } else {
      $this->indent = substr($this->indent, 0, -strlen($str));
    }
  }
  /**
   * decode email addresses
   *
   * @author derernst@gmx.ch <http://www.php.net/manual/en/function.html-entity-decode.php#68536>
   * @author Milian Wolff <http://milianw.de>
   */
  function decode($text, $quote_style = ENT_QUOTES) {
    if (version_compare(PHP_VERSION, '5', '>=')) {
      # UTF-8 is only supported in PHP 5.x.x and above
      $text = html_entity_decode($text, $quote_style, 'UTF-8');
    } else {
      if (function_exists('html_entity_decode')) {
        $text = html_entity_decode($text, $quote_style, 'ISO-8859-1');
      } else {
        static $trans_tbl;
        if (!isset($trans_tbl)) {
          $trans_tbl = array_flip(get_html_translation_table(HTML_ENTITIES, $quote_style));
        }
        $text = strtr($text, $trans_tbl);
      }
      $text = preg_replace_callback('~&#x([0-9a-f]+);~i', array(&$this, '_decode_hex'), $text);
      $text = preg_replace_callback('~&#(\d{2,5});~', array(&$this, '_decode_numeric'), $text);
    }
    return $text;
  }
  /**
   * callback for decode() which converts a hexadecimal entity to UTF-8
   *
   * @param array $matches
   * @return string UTF-8 encoded
   */
  function _decode_hex($matches) {
    return $this->unichr(hexdec($matches[1]));
  }
  /**
   * callback for decode() which converts a numerical entity to UTF-8
   *
   * @param array $matches
   * @return string UTF-8 encoded
   */
  function _decode_numeric($matches) {
    return $this->unichr($matches[1]);
  }
  /**
   * UTF-8 chr() which supports numeric entities
   *
   * @author grey - greywyvern - com <http://www.php.net/manual/en/function.chr.php#55978>
   * @param array $matches
   * @return string UTF-8 encoded
   */
  function unichr($dec) {
    if ($dec < 128) {
      $utf = chr($dec);
    } else if ($dec < 2048) {
      $utf = chr(192 + (($dec - ($dec % 64)) / 64));
      $utf .= chr(128 + ($dec % 64));
    } else {
      $utf = chr(224 + (($dec - ($dec % 4096)) / 4096));
      $utf .= chr(128 + ((($dec % 4096) - ($dec % 64)) / 64));
      $utf .= chr(128 + ($dec % 64));
    }
    return $utf;
  }
  /**
   * UTF-8 strlen()
   *
   * @param string $str
   * @return int
   *
   * @author dtorop 932 at hotmail dot com <http://www.php.net/manual/en/function.strlen.php#37975>
   * @author Milian Wolff <http://milianw.de>
   */
  function strlen($str) {
    if (function_exists('mb_strlen')) {
      return mb_strlen($str, 'UTF-8');
    } else {
      return preg_match_all('/[\x00-\x7F\xC0-\xFD]/', $str, $var_empty);
    }
  }
  /**
  * wordwrap for utf8 encoded strings
  *
  * @param string $str
  * @param integer $len
  * @param string $what
  * @return string
  */
  function wordwrap($str, $width, $break, $cut = false){
    if (!$cut) {
      $regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){1,'.$width.'}\b#';
    } else {
      $regexp = '#^(?:[\x00-\x7F]|[\xC0-\xFF][\x80-\xBF]+){'.$width.'}#';
    }
    $return = '';
    while (preg_match($regexp, $str, $matches)) {
      $string = $matches[0];
      $str = ltrim(substr($str, strlen($string)));
      if (!$cut && isset($str[0]) && in_array($str[0], array('.', '!', ';', ':', '?', ','))) {
        $string .= $str[0];
        $str = ltrim(substr($str, 1));
      }
      $return .= $string.$break;
    }
    return $return.ltrim($str);
  }
  /**
   * check if current node has a $tagName as parent (somewhere, not only the direct parent)
   *
   * @param string $tagName
   * @return bool
   */
  function hasParent($tagName) {
    return in_array($tagName, $this->parser->openTags);
  }
  /**
   * get tagName of direct parent tag
   *
   * @param void
   * @return string $tagName
   */
  function parent() {
    return end($this->parser->openTags);
  }
}