summaryrefslogtreecommitdiff
path: root/framework/3rdParty/Markdown/MarkdownParser.php
blob: a7bcfb3dda792aa8739b11aaaa1bb01f7ae177e6 (plain)
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
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
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
<?php

#
# Markdown  -  A text-to-HTML conversion tool for web writers
#
# Copyright (c) 2004-2005 John Gruber
# <http://daringfireball.net/projects/markdown/>
#
# Copyright (c) 2004-2005 Michel Fortin - PHP Port
# <http://www.michelf.com/projects/php-markdown/>
#

/**
 * PHP5 version of the markdown parser.
 * Usage:
 * <code>
 * $markdown = new MarkdownParser;
 * echo $markdown->parse($text);
 * </code>
 */
class MarkdownParser
{
	private static $md_nested_brackets;
	private static $md_escape_table = array();
	private static $md_backslash_escape_table = array();
	private static $md_nested_brackets_depth = 6;

	protected $md_empty_element_suffix = " />";     # Change to ">" for HTML output
	protected $md_tab_width = 4;

	private $md_list_level = 0;
	private $md_urls = array();
	private $md_titles = array();
	private $md_html_blocks = array();

	public function __construct()
	{
		if(is_null(self::$md_nested_brackets))
			$this->initialize();
	}

	private function initialize()
	{
		self::$md_nested_brackets =
			str_repeat('(?>[^\[\]]+|\[', self::$md_nested_brackets_depth).
			str_repeat('\])*', self::$md_nested_brackets_depth);

		self::$md_escape_table = array(
			"\\" => md5("\\"),
			"`" => md5("`"),
			"*" => md5("*"),
			"_" => md5("_"),
			"{" => md5("{"),
			"}" => md5("}"),
			"[" => md5("["),
			"]" => md5("]"),
			"(" => md5("("),
			")" => md5(")"),
			">" => md5(">"),
			"#" => md5("#"),
			"+" => md5("+"),
			"-" => md5("-"),
			"." => md5("."),
			"!" => md5("!")
		);

		# Table of hash values for escaped characters:
		# Create an identical table but for escaped characters.
		foreach (self::$md_escape_table as $key => $char)
			self::$md_backslash_escape_table["\\$key"] = $char;
	}

	public function parse($text)
	{
	#
	# Main function. The order in which other subs are called here is
	# essential. Link and image substitutions need to happen before
	# _EscapeSpecialCharsWithinTagAttributes(), so that any *'s or _'s in the <a>
	# and <img> tags get encoded.
	#
		# Clear the hashes. If we don't clear these, you get conflicts
		# from other articles when generating a page which contains more than
		# one article (e.g. an index page that shows the N most recent
		# articles):
		$this->md_urls = array();
		$this->md_titles = array();
		$this->md_html_blocks = array();

		# Standardize line endings:
		#   DOS to Unix and Mac to Unix
		$text = str_replace(array("\r\n", "\r"), "\n", $text);

		# Make sure $text ends with a couple of newlines:
		$text .= "\n\n";

		# Convert all tabs to spaces.
		$text = $this->_Detab($text);

		# Strip any lines consisting only of spaces and tabs.
		# This makes subsequent regexen easier to write, because we can
		# match consecutive blank lines with /\n+/ instead of something
		# contorted like /[ \t]*\n+/ .
		$text = preg_replace('/^[ \t]+$/m', '', $text);

		# Turn block-level HTML blocks into hash entries
		$text = $this->_HashHTMLBlocks($text);

		# Strip link definitions, store in hashes.
		$text = $this->_StripLinkDefinitions($text);

		$text = $this->_RunBlockGamut($text);

		$text = $this->_UnescapeSpecialChars($text);

		return $text . "\n";
	}


	private function _StripLinkDefinitions($text) {
	#
	# Strips link definitions from text, stores the URLs and titles in
	# hash references.
	#
		$less_than_tab = $this->md_tab_width - 1;

		# Link defs are in the form: ^[id]: url "optional title"
		$text = preg_replace_callback('{
							^[ ]{0,'.$less_than_tab.'}\[(.+)\]:	# id = $1
							  [ \t]*
							  \n?				# maybe *one* newline
							  [ \t]*
							<?(\S+?)>?			# url = $2
							  [ \t]*
							  \n?				# maybe one newline
							  [ \t]*
							(?:
								(?<=\s)			# lookbehind for whitespace
								["(]
								(.+?)			# title = $3
								[")]
								[ \t]*
							)?	# title is optional
							(?:\n+|\Z)
			}xm',
			array($this,'_StripLinkDefinitions_callback'),
			$text);
		return $text;
	}

	private function _StripLinkDefinitions_callback($matches) {
		$link_id = strtolower($matches[1]);
		$this->md_urls[$link_id] = $this->_EncodeAmpsAndAngles($matches[2]);
		if (isset($matches[3]))
			$this->md_titles[$link_id] = str_replace('"', '&quot;', $matches[3]);
		return ''; # String that will replace the block
	}


	private function _HashHTMLBlocks($text) {
		$less_than_tab = $this->md_tab_width - 1;

		# Hashify HTML blocks:
		# We only want to do this for block-level HTML tags, such as headers,
		# lists, and tables. That's because we still want to wrap <p>s around
		# "paragraphs" that are wrapped in non-block-level tags, such as anchors,
		# phrase emphasis, and spans. The list of tags we're looking for is
		# hard-coded:
		$block_tags_a = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|'.
						'script|noscript|form|fieldset|iframe|math|ins|del';
		$block_tags_b = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|'.
						'script|noscript|form|fieldset|iframe|math';

		# First, look for nested blocks, e.g.:
		# 	<div>
		# 		<div>
		# 		tags for inner block must be indented.
		# 		</div>
		# 	</div>
		#
		# The outermost tags must start at the left margin for this to match, and
		# the inner nested divs must be indented.
		# We need to do this before the next, more liberal match, because the next
		# match will start at the first `<div>` and stop at the first `</div>`.
		$text = preg_replace_callback("{
					(						# save in $1
						^					# start of line  (with /m)
						<($block_tags_a)	# start tag = $2
						\\b					# word break
						(.*\\n)*?			# any number of lines, minimally matching
						</\\2>				# the matching end tag
						[ \\t]*				# trailing spaces/tabs
						(?=\\n+|\\Z)	# followed by a newline or end of document
					)
			}xm",
			array($this,'_HashHTMLBlocks_callback'),
			$text);

		#
		# Now match more liberally, simply from `\n<tag>` to `</tag>\n`
		#
		$text = preg_replace_callback("{
					(						# save in $1
						^					# start of line  (with /m)
						<($block_tags_b)	# start tag = $2
						\\b					# word break
						(.*\\n)*?			# any number of lines, minimally matching
						.*</\\2>				# the matching end tag
						[ \\t]*				# trailing spaces/tabs
						(?=\\n+|\\Z)	# followed by a newline or end of document
					)
			}xm",
			array($this,'_HashHTMLBlocks_callback'),
			$text);

		# Special case just for <hr />. It was easier to make a special case than
		# to make the other regex more complicated.
		$text = preg_replace_callback('{
					(?:
						(?<=\n\n)		# Starting after a blank line
						|				# or
						\A\n?			# the beginning of the doc
					)
					(						# save in $1
						[ ]{0,'.$less_than_tab.'}
						<(hr)				# start tag = $2
						\b					# word break
						([^<>])*?			#
						/?>					# the matching end tag
						[ \t]*
						(?=\n{2,}|\Z)		# followed by a blank line or end of document
					)
			}x',
			array($this,'_HashHTMLBlocks_callback'),
			$text);

		# Special case for standalone HTML comments:
		$text = preg_replace_callback('{
					(?:
						(?<=\n\n)		# Starting after a blank line
						|				# or
						\A\n?			# the beginning of the doc
					)
					(						# save in $1
						[ ]{0,'.$less_than_tab.'}
						(?s:
							<!
							(--.*?--\s*)+
							>
						)
						[ \t]*
						(?=\n{2,}|\Z)		# followed by a blank line or end of document
					)
				}x',
				array($this,'_HashHTMLBlocks_callback'),
				$text);

		return $text;
	}
	private function _HashHTMLBlocks_callback($matches) {
		$text = $matches[1];
		$key = md5($text);
		$this->md_html_blocks[$key] = $text;
		return "\n\n$key\n\n"; # String that will replace the block
	}


	private function _RunBlockGamut($text) {
	#
	# These are all the transformations that form block-level
	# tags like paragraphs, headers, and list items.
	#
		$text = $this->_DoHeaders($text);

		# Do Horizontal Rules:
		$text = preg_replace(
			array('{^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$}mx',
				  '{^[ ]{0,2}([ ]? -[ ]?){3,}[ \t]*$}mx',
				  '{^[ ]{0,2}([ ]? _[ ]?){3,}[ \t]*$}mx'),
			"\n<hr{$this->md_empty_element_suffix}\n",
			$text);

		$text = $this->_DoLists($text);
		$text = $this->_DoCodeBlocks($text);
		$text = $this->_DoBlockQuotes($text);

		# We already ran _HashHTMLBlocks() before, in Markdown(), but that
		# was to escape raw HTML in the original Markdown source. This time,
		# we're escaping the markup we've just created, so that we don't wrap
		# <p> tags around block-level tags.
		$text = $this->_HashHTMLBlocks($text);
		$text = $this->_FormParagraphs($text);

		return $text;
	}


	private function _RunSpanGamut($text) {
	#
	# These are all the transformations that occur *within* block-level
	# tags like paragraphs, headers, and list items.
	#

		$text = $this->_DoCodeSpans($text);

		$text = $this->_EscapeSpecialChars($text);

		# Process anchor and image tags. Images must come first,
		# because ![foo][f] looks like an anchor.
		$text = $this->_DoImages($text);
		$text = $this->_DoAnchors($text);

		# Make links out of things like `<http://example.com/>`
		# Must come after _DoAnchors(), because you can use < and >
		# delimiters in inline links like [this](<url>).
		$text = $this->_DoAutoLinks($text);
		$text = $this->_EncodeAmpsAndAngles($text);
		$text = $this->_DoItalicsAndBold($text);

		# Do hard breaks:
		$text = preg_replace('/ {2,}\n/', "<br{$this->md_empty_element_suffix}\n", $text);

		return $text;
	}


	private function _EscapeSpecialChars($text) {
		$tokens = $this->_TokenizeHTML($text);

		$text = '';   # rebuild $text from the tokens
	#	$in_pre = 0;  # Keep track of when we're inside <pre> or <code> tags.
	#	$tags_to_skip = "!<(/?)(?:pre|code|kbd|script|math)[\s>]!";

		foreach ($tokens as $cur_token) {
			if ($cur_token[0] == 'tag') {
				# Within tags, encode * and _ so they don't conflict
				# with their use in Markdown for italics and strong.
				# We're replacing each such character with its
				# corresponding MD5 checksum value; this is likely
				# overkill, but it should prevent us from colliding
				# with the escape values by accident.
				$cur_token[1] = str_replace(array('*', '_'),
					array(self::$md_escape_table['*'], self::$md_escape_table['_']),
					$cur_token[1]);
				$text .= $cur_token[1];
			} else {
				$t = $cur_token[1];
				$t = $this->_EncodeBackslashEscapes($t);
				$text .= $t;
			}
		}
		return $text;
	}


	private function _DoAnchors($text) {
	#
	# Turn Markdown link shortcuts into XHTML <a> tags.
	#
		#
		# First, handle reference-style links: [link text] [id]
		#
		$bracket = self::$md_nested_brackets;
		$text = preg_replace_callback("{
			(					# wrap whole match in $1
			  \\[
				({$bracket})	# link text = $2
			  \\]

			  [ ]?				# one optional space
			  (?:\\n[ ]*)?		# one optional newline followed by spaces

			  \\[
				(.*?)		# id = $3
			  \\]
			)
			}xs",
			array($this,'_DoAnchors_reference_callback'), $text);

		#
		# Next, inline-style links: [link text](url "optional title")
		#
		$text = preg_replace_callback("{
			(				# wrap whole match in $1
			  \\[
				({$bracket})	# link text = $2
			  \\]
			  \\(			# literal paren
				[ \\t]*
				<?(.*?)>?	# href = $3
				[ \\t]*
				(			# $4
				  (['\"])	# quote char = $5
				  (.*?)		# Title = $6
				  \\5		# matching quote
				)?			# title is optional
			  \\)
			)
			}xs",
			array($this,'_DoAnchors_inline_callback'), $text);

		return $text;
	}
	private function _DoAnchors_reference_callback($matches) {
		$whole_match = $matches[1];
		$link_text   = $matches[2];
		$link_id     = strtolower($matches[3]);

		if ($link_id == "") {
			$link_id = strtolower($link_text); # for shortcut links like [this][].
		}

		if (isset($this->md_urls[$link_id])) {
			$url = $this->md_urls[$link_id];
			# We've got to encode these to avoid conflicting with italics/bold.
			$url = str_replace(array('*', '_'),
							   array(self::$md_escape_table['*'], self::$md_escape_table['_']),
							   $url);
			$result = "<a href=\"$url\"";
			if ( isset( $this->md_titles[$link_id] ) ) {
				$title = $this->md_titles[$link_id];
				$title = str_replace(array('*',     '_'),
									 array(self::$md_escape_table['*'],
										   self::$md_escape_table['_']), $title);
				$result .=  " title=\"$title\"";
			}
			$result .= ">$link_text</a>";
		}
		else {
			$result = $whole_match;
		}
		return $result;
	}
	private function _DoAnchors_inline_callback($matches) {
		$whole_match	= $matches[1];
		$link_text		= $matches[2];
		$url			= $matches[3];
		$title			=& $matches[6];

		# We've got to encode these to avoid conflicting with italics/bold.
		$url = str_replace(array('*', '_'),
						   array(self::$md_escape_table['*'], self::$md_escape_table['_']),
						   $url);
		$result = "<a href=\"$url\"";
		if (isset($title)) {
			$title = str_replace('"', '&quot;', $title);
			$title = str_replace(array('*', '_'),
								 array(self::$md_escape_table['*'], self::$md_escape_table['_']),
								 $title);
			$result .=  " title=\"$title\"";
		}

		$result .= ">$link_text</a>";

		return $result;
	}


	private function _DoImages($text) {
	#
	# Turn Markdown image shortcuts into <img> tags.
	#
		#
		# First, handle reference-style labeled images: ![alt text][id]
		#
		$text = preg_replace_callback('{
			(				# wrap whole match in $1
			  !\[
				('.self::$md_nested_brackets.')		# alt text = $2
			  \]

			  [ ]?				# one optional space
			  (?:\n[ ]*)?		# one optional newline followed by spaces

			  \[
				(.*?)		# id = $3
			  \]

			)
			}xs',
			array($this,'_DoImages_reference_callback'), $text);

		#
		# Next, handle inline images:  ![alt text](url "optional title")
		# Don't forget: encode * and _

		$text = preg_replace_callback('{
			(				# wrap whole match in $1
			  !\[
				('.self::$md_nested_brackets.')		# alt text = $2
			  \]
			  \(			# literal paren
				[ \t]*
				<?(\S+?)>?	# src url = $3
				[ \t]*
				(			# $4
				  ([\'"])	# quote char = $5
				  (.*?)		# title = $6
				  \5		# matching quote
				  [ \t]*
				)?			# title is optional
			  \)
			)
			}xs',
			array($this,'_DoImages_inline_callback'), $text);

		return $text;
	}
	private function _DoImages_reference_callback($matches) {
		$whole_match = $matches[1];
		$alt_text    = $matches[2];
		$link_id     = strtolower($matches[3]);

		if ($link_id == "") {
			$link_id = strtolower($alt_text); # for shortcut links like ![this][].
		}

		$alt_text = str_replace('"', '&quot;', $alt_text);
		if (isset($this->md_urls[$link_id])) {
			$url = $this->md_urls[$link_id];
			# We've got to encode these to avoid conflicting with italics/bold.
			$url = str_replace(array('*', '_'),
							   array(self::$md_escape_table['*'], self::$md_escape_table['_']),
							   $url);
			$result = "<img src=\"$url\" alt=\"$alt_text\"";
			if (isset($this->md_titles[$link_id])) {
				$title = $this->md_titles[$link_id];
				$title = str_replace(array('*', '_'),
									 array(self::$md_escape_table['*'],
										   self::$md_escape_table['_']), $title);
				$result .=  " title=\"$title\"";
			}
			$result .= $this->md_empty_element_suffix;
		}
		else {
			# If there's no such link ID, leave intact:
			$result = $whole_match;
		}

		return $result;
	}
	private function _DoImages_inline_callback($matches) {
		$whole_match	= $matches[1];
		$alt_text		= $matches[2];
		$url			= $matches[3];
		$title			= '';
		if (isset($matches[6])) {
			$title		= $matches[6];
		}

		$alt_text = str_replace('"', '&quot;', $alt_text);
		$title    = str_replace('"', '&quot;', $title);
		# We've got to encode these to avoid conflicting with italics/bold.
		$url = str_replace(array('*', '_'),
						   array(self::$md_escape_table['*'], self::$md_escape_table['_']),
						   $url);
		$result = "<img src=\"$url\" alt=\"$alt_text\"";
		if (isset($title)) {
			$title = str_replace(array('*', '_'),
								 array(self::$md_escape_table['*'], self::$md_escape_table['_']),
								 $title);
			$result .=  " title=\"$title\""; # $title already quoted
		}
		$result .= $this->md_empty_element_suffix;

		return $result;
	}


	private function _DoHeaders($text) {
		# Setext-style headers:
		#	  Header 1
		#	  ========
		#
		#	  Header 2
		#	  --------
		#
		$text = preg_replace(
			array('{ ^(.+)[ \t]*\n=+[ \t]*\n+ }emx',
				  '{ ^(.+)[ \t]*\n-+[ \t]*\n+ }emx'),
			array("'<h1>'.\$this->_RunSpanGamut(\$this->_UnslashQuotes('\\1')).'</h1>\n\n'",
				  "'<h2>'.\$this->_RunSpanGamut(\$this->_UnslashQuotes('\\1')).'</h2>\n\n'"),
			$text);

		# atx-style headers:
		#	# Header 1
		#	## Header 2
		#	## Header 2 with closing hashes ##
		#	...
		#	###### Header 6
		#
		$text = preg_replace("{
				^(\\#{1,6})	# $1 = string of #'s
				[ \\t]*
				(.+?)		# $2 = Header text
				[ \\t]*
				\\#*			# optional closing #'s (not counted)
				\\n+
			}xme",
			"'<h'.strlen('\\1').'>'.\$this->_RunSpanGamut(\$this->_UnslashQuotes('\\2')).'</h'.strlen('\\1').'>\n\n'",
			$text);

		return $text;
	}


	private function _DoLists($text) {
	#
	# Form HTML ordered (numbered) and unordered (bulleted) lists.
	#
		$less_than_tab = $this->md_tab_width - 1;

		# Re-usable patterns to match list item bullets and number markers:
		$marker_ul  = '[*+-]';
		$marker_ol  = '\d+[.]';
		$marker_any = "(?:$marker_ul|$marker_ol)";

		$markers = array($marker_ul, $marker_ol);

		foreach ($markers as $marker) {
			# Re-usable pattern to match any entirel ul or ol list:
			$whole_list = '
				(								# $1 = whole list
				  (								# $2
					[ ]{0,'.$less_than_tab.'}
					('.$marker.')				# $3 = first list item marker
					[ \t]+
				  )
				  (?s:.+?)
				  (								# $4
					  \z
					|
					  \n{2,}
					  (?=\S)
					  (?!						# Negative lookahead for another list item marker
						[ \t]*
						'.$marker.'[ \t]+
					  )
				  )
				)
			'; // mx

			# We use a different prefix before nested lists than top-level lists.
			# See extended comment in _ProcessListItems().

			if ($this->md_list_level) {
				$text = preg_replace_callback('{
						^
						'.$whole_list.'
					}mx',
					array($this,'_DoLists_callback_top'), $text);
			}
			else {
				$text = preg_replace_callback('{
						(?:(?<=\n\n)|\A\n?)
						'.$whole_list.'
					}mx',
					array($this,'_DoLists_callback_nested'), $text);
			}
		}

		return $text;
	}
	private function _DoLists_callback_top($matches) {
		# Re-usable patterns to match list item bullets and number markers:
		$marker_ul  = '[*+-]';
		$marker_ol  = '\d+[.]';
		$marker_any = "(?:$marker_ul|$marker_ol)";

		$list = $matches[1];
		$list_type = preg_match("/$marker_ul/", $matches[3]) ? "ul" : "ol";

		$marker_any = ( $list_type == "ul" ? $marker_ul : $marker_ol );

		# Turn double returns into triple returns, so that we can make a
		# paragraph for the last item in a list, if necessary:
		$list = preg_replace("/\n{2,}/", "\n\n\n", $list);
		$result = $this->_ProcessListItems($list, $marker_any);

		# Trim any trailing whitespace, to put the closing `</$list_type>`
		# up on the preceding line, to get it past the current stupid
		# HTML block parser. This is a hack to work around the terrible
		# hack that is the HTML block parser.
		$result = rtrim($result);
		$result = "<$list_type>" . $result . "</$list_type>\n";
		return $result;
	}
	private function _DoLists_callback_nested($matches) {
		# Re-usable patterns to match list item bullets and number markers:
		$marker_ul  = '[*+-]';
		$marker_ol  = '\d+[.]';
		$marker_any = "(?:$marker_ul|$marker_ol)";

		$list = $matches[1];
		$list_type = preg_match("/$marker_ul/", $matches[3]) ? "ul" : "ol";

		$marker_any = ( $list_type == "ul" ? $marker_ul : $marker_ol );

		# Turn double returns into triple returns, so that we can make a
		# paragraph for the last item in a list, if necessary:
		$list = preg_replace("/\n{2,}/", "\n\n\n", $list);
		$result = $this->_ProcessListItems($list, $marker_any);
		$result = "<$list_type>\n" . $result . "</$list_type>\n";
		return $result;
	}


	private function _ProcessListItems($list_str, $marker_any) {
	#
	#	Process the contents of a single ordered or unordered list, splitting it
	#	into individual list items.
	#

		# The $md_list_level keeps track of when we're inside a list.
		# Each time we enter a list, we increment it; when we leave a list,
		# we decrement. If it's zero, we're not in a list anymore.
		#
		# We do this because when we're not inside a list, we want to treat
		# something like this:
		#
		#		I recommend upgrading to version
		#		8. Oops, now this line is treated
		#		as a sub-list.
		#
		# As a single paragraph, despite the fact that the second line starts
		# with a digit-period-space sequence.
		#
		# Whereas when we're inside a list (or sub-list), that line will be
		# treated as the start of a sub-list. What a kludge, huh? This is
		# an aspect of Markdown's syntax that's hard to parse perfectly
		# without resorting to mind-reading. Perhaps the solution is to
		# change the syntax rules such that sub-lists must start with a
		# starting cardinal number; e.g. "1." or "a.".

		$this->md_list_level++;

		# trim trailing blank lines:
		$list_str = preg_replace("/\n{2,}\\z/", "\n", $list_str);

		$list_str = preg_replace_callback('{
			(\n)?							# leading line = $1
			(^[ \t]*)						# leading whitespace = $2
			('.$marker_any.') [ \t]+		# list marker = $3
			((?s:.+?)						# list item text   = $4
			(\n{1,2}))
			(?= \n* (\z | \2 ('.$marker_any.') [ \t]+))
			}xm',
			array($this,'_ProcessListItems_callback'), $list_str);

		$this->md_list_level--;
		return $list_str;
	}
	private function _ProcessListItems_callback($matches) {
		$item = $matches[4];
		$leading_line =& $matches[1];
		$leading_space =& $matches[2];

		if ($leading_line || preg_match('/\n{2,}/', $item)) {
			$item = $this->_RunBlockGamut($this->_Outdent($item));
		}
		else {
			# Recursion for sub-lists:
			$item = $this->_DoLists($this->_Outdent($item));
			$item = preg_replace('/\n+$/', '', $item);
			$item = $this->_RunSpanGamut($item);
		}

		return "<li>" . $item . "</li>\n";
	}


	private function _DoCodeBlocks($text) {
	#
	#	Process Markdown `<pre><code>` blocks.
	#
		$text = preg_replace_callback('{
				(?:\n\n|\A)
				(	            # $1 = the code block -- one or more lines, starting with a space/tab
				  (?:
					(?:[ ]{'.$this->md_tab_width.'} | \t)  # Lines must start with a tab or a tab-width of spaces
					.*\n+
				  )+
				)
				((?=^[ ]{0,'.$this->md_tab_width.'}\S)|\Z)	# Lookahead for non-space at line-start, or end of doc
			}xm',
			array($this,'_DoCodeBlocks_callback'), $text);

		return $text;
	}
	private function _DoCodeBlocks_callback($matches) {
		$codeblock = $matches[1];

		$codeblock = $this->_EncodeCode($this->_Outdent($codeblock));
	//	$codeblock = _Detab($codeblock);
		# trim leading newlines and trailing whitespace
		$codeblock = preg_replace(array('/\A\n+/', '/\s+\z/'), '', $codeblock);

		$result = "\n\n<pre><code>" . $codeblock . "\n</code></pre>\n\n";

		return $result;
	}


	private function _DoCodeSpans($text) {
	#
	# 	*	Backtick quotes are used for <code></code> spans.
	#
	# 	*	You can use multiple backticks as the delimiters if you want to
	# 		include literal backticks in the code span. So, this input:
	#
	#		  Just type ``foo `bar` baz`` at the prompt.
	#
	#	  	Will translate to:
	#
	#		  <p>Just type <code>foo `bar` baz</code> at the prompt.</p>
	#
	#		There's no arbitrary limit to the number of backticks you
	#		can use as delimters. If you need three consecutive backticks
	#		in your code, use four for delimiters, etc.
	#
	#	*	You can use spaces to get literal backticks at the edges:
	#
	#		  ... type `` `bar` `` ...
	#
	#	  	Turns to:
	#
	#		  ... type <code>`bar`</code> ...
	#
		$text = preg_replace_callback('@
				(?<!\\\)	# Character before opening ` can\'t be a backslash
				(`+)		# $1 = Opening run of `
				(.+?)		# $2 = The code block
				(?<!`)
				\1			# Matching closer
				(?!`)
			@xs',
			array($this,'_DoCodeSpans_callback'), $text);

		return $text;
	}
	private function _DoCodeSpans_callback($matches) {
		$c = $matches[2];
		$c = preg_replace('/^[ \t]*/', '', $c); # leading whitespace
		$c = preg_replace('/[ \t]*$/', '', $c); # trailing whitespace
		$c = $this->_EncodeCode($c);
		return "<code>$c</code>";
	}


	private function _EncodeCode($_) {
	#
	# Encode/escape certain characters inside Markdown code runs.
	# The point is that in code, these characters are literals,
	# and lose their special Markdown meanings.
	#
		# Encode all ampersands; HTML entities are not
		# entities within a Markdown code span.
		$_ = str_replace('&', '&amp;', $_);

		# Do the angle bracket song and dance:
		$_ = str_replace(array('<',    '>'),
						 array('&lt;', '&gt;'), $_);

		# Now, escape characters that are magic in Markdown:
		$_ = str_replace(array_keys(self::$md_escape_table),
						 array_values(self::$md_escape_table), $_);

		return $_;
	}


	private function _DoItalicsAndBold($text) {
		# <strong> must go first:
		$text = preg_replace('{
				(						# $1: Marker
					(?<!\*\*) \*\* |	#     (not preceded by two chars of
					(?<!__)   __		#      the same marker)
				)
				(?=\S) 					# Not followed by whitespace
				(?!\1)					#   or two others marker chars.
				(						# $2: Content
					(?:
						[^*_]+?			# Anthing not em markers.
					|
										# Balence any regular emphasis inside.
						([*_]) (?=\S) .+? (?<=\S) \3	# $3: em char (* or _)
					|
						(?! \1 ) .		# Allow unbalenced * and _.
					)+?
				)
				(?<=\S) \1				# End mark not preceded by whitespace.
			}sx',
			'<strong>\2</strong>', $text);
		# Then <em>:
		$text = preg_replace(
			'{ ( (?<!\*)\* | (?<!_)_ ) (?=\S) (?! \1) (.+?) (?<=\S) \1 }sx',
			'<em>\2</em>', $text);

		return $text;
	}


	private function _DoBlockQuotes($text) {
		$text = preg_replace_callback('/
			  (								# Wrap whole match in $1
				(
				  ^[ \t]*>[ \t]?			# ">" at the start of a line
					.+\n					# rest of the first line
				  (.+\n)*					# subsequent consecutive lines
				  \n*						# blanks
				)+
			  )
			/xm',
			array($this,'_DoBlockQuotes_callback'), $text);

		return $text;
	}
	private function _DoBlockQuotes_callback($matches) {
		$bq = $matches[1];
		# trim one level of quoting - trim whitespace-only lines
		$bq = preg_replace(array('/^[ \t]*>[ \t]?/m', '/^[ \t]+$/m'), '', $bq);
		$bq = $this->_RunBlockGamut($bq);		# recurse

		$bq = preg_replace('/^/m', "  ", $bq);
		# These leading spaces screw with <pre> content, so we need to fix that:
		$bq = preg_replace_callback('{(\s*<pre>.+?</pre>)}sx',
									array($this,'_DoBlockQuotes_callback2'), $bq);

		return "<blockquote>\n$bq\n</blockquote>\n\n";
	}
	private function _DoBlockQuotes_callback2($matches) {
		$pre = $matches[1];
		$pre = preg_replace('/^  /m', '', $pre);
		return $pre;
	}


	private function _FormParagraphs($text) {
	#
	#	Params:
	#		$text - string to process with html <p> tags
	#
		# Strip leading and trailing lines:
		$text = preg_replace(array('/\A\n+/', '/\n+\z/'), '', $text);

		$grafs = preg_split('/\n{2,}/', $text, -1, PREG_SPLIT_NO_EMPTY);

		#
		# Wrap <p> tags.
		#
		foreach ($grafs as $key => $value) {
			if (!isset( $this->md_html_blocks[$value] )) {
				$value = $this->_RunSpanGamut($value);
				$value = preg_replace('/^([ \t]*)/', '<p>', $value);
				$value .= "</p>";
				$grafs[$key] = $value;
			}
		}

		#
		# Unhashify HTML blocks
		#
		foreach ($grafs as $key => $value) {
			if (isset( $this->md_html_blocks[$value] )) {
				$grafs[$key] = $this->md_html_blocks[$value];
			}
		}

		return implode("\n\n", $grafs);
	}


	private function _EncodeAmpsAndAngles($text) {
	# Smart processing for ampersands and angle brackets that need to be encoded.

		# Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
		#   http://bumppo.net/projects/amputator/
		$text = preg_replace('/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/',
							 '&amp;', $text);;

		# Encode naked <'s
		$text = preg_replace('{<(?![a-z/?\$!])}i', '&lt;', $text);

		return $text;
	}


	private function _EncodeBackslashEscapes($text) {
	#
	#	Parameter:  String.
	#	Returns:    The string, with after processing the following backslash
	#				escape sequences.
	#
		# Must process escaped backslashes first.
		return str_replace(array_keys(self::$md_backslash_escape_table),
						   array_values(self::$md_backslash_escape_table), $text);
	}


	private function _DoAutoLinks($text) {
		$text = preg_replace("!<((https?|ftp):[^'\">\\s]+)>!",
							 '<a href="\1">\1</a>', $text);

		# Email addresses: <address@domain.foo>
		$text = preg_replace('{
			<
			(?:mailto:)?
			(
				[-.\w]+
				\@
				[-a-z0-9]+(\.[-a-z0-9]+)*\.[a-z]+
			)
			>
			}exi',
			"\$this->_EncodeEmailAddress(\$this->_UnescapeSpecialChars(\$this->_UnslashQuotes('\\1')))",
			$text);

		return $text;
	}


	private function _EncodeEmailAddress($addr) {
	#
	#	Input: an email address, e.g. "foo@example.com"
	#
	#	Output: the email address as a mailto link, with each character
	#		of the address encoded as either a decimal or hex entity, in
	#		the hopes of foiling most address harvesting spam bots. E.g.:
	#
	#	  <a href="&#x6D;&#97;&#105;&#108;&#x74;&#111;:&#102;&#111;&#111;&#64;&#101;
	#		x&#x61;&#109;&#x70;&#108;&#x65;&#x2E;&#99;&#111;&#109;">&#102;&#111;&#111;
	#		&#64;&#101;x&#x61;&#109;&#x70;&#108;&#x65;&#x2E;&#99;&#111;&#109;</a>
	#
	#	Based by a filter by Matthew Wickline, posted to the BBEdit-Talk
	#	mailing list: <http://tinyurl.com/yu7ue>
	#
		$addr = "mailto:" . $addr;
		$length = strlen($addr);

		# leave ':' alone (to spot mailto: later)
		$addr = preg_replace_callback('/([^\:])/',
									  array($this,'_EncodeEmailAddress_callback'), $addr);

		$addr = "<a href=\"$addr\">$addr</a>";
		# strip the mailto: from the visible part
		$addr = preg_replace('/">.+?:/', '">', $addr);

		return $addr;
	}
	private function _EncodeEmailAddress_callback($matches) {
		$char = $matches[1];
		$r = rand(0, 100);
		# roughly 10% raw, 45% hex, 45% dec
		# '@' *must* be encoded. I insist.
		if ($r > 90 && $char != '@') return $char;
		if ($r < 45) return '&#x'.dechex(ord($char)).';';
		return '&#'.ord($char).';';
	}


	private function _UnescapeSpecialChars($text) {
	#
	# Swap back in all the special characters we've hidden.
	#
		return str_replace(array_values(self::$md_escape_table),
						   array_keys(self::$md_escape_table), $text);
	}


	# _TokenizeHTML is shared between PHP Markdown and PHP SmartyPants.
	# We only define it if it is not already defined.

	private function _TokenizeHTML($str) {
	#
	#   Parameter:  String containing HTML markup.
	#   Returns:    An array of the tokens comprising the input
	#               string. Each token is either a tag (possibly with nested,
	#               tags contained therein, such as <a href="<MTFoo>">, or a
	#               run of text between tags. Each element of the array is a
	#               two-element array; the first is either 'tag' or 'text';
	#               the second is the actual value.
	#
	#
	#   Regular expression derived from the _tokenize() subroutine in
	#   Brad Choate's MTRegex plugin.
	#   <http://www.bradchoate.com/past/mtregex.php>
	#
		$index = 0;
		$tokens = array();

		$match = '(?s:<!(?:--.*?--\s*)+>)|'.	# comment
				 '(?s:<\?.*?\?>)|'.				# processing instruction
												# regular tags
				 '(?:<[/!$]?[-a-zA-Z0-9:]+\b(?>[^"\'>]+|"[^"]*"|\'[^\']*\')*>)';

		$parts = preg_split("{($match)}", $str, -1, PREG_SPLIT_DELIM_CAPTURE);

		foreach ($parts as $part) {
			if (++$index % 2 && $part != '')
				$tokens[] = array('text', $part);
			else
				$tokens[] = array('tag', $part);
		}

		return $tokens;
	}

	private function _Outdent($text) {
	#
	# Remove one level of line-leading tabs or spaces
	#
		return preg_replace("/^(\\t|[ ]{1,".$this->md_tab_width."})/m", "", $text);
	}


	private function _Detab($text) {
	#
	# Replace tabs with the appropriate amount of space.
	#
		# For each line we separate the line in blocks delemited by
		# tab characters. Then we reconstruct every line by adding the
		# appropriate number of space between each blocks.

		$lines = explode("\n", $text);
		$text = "";

		foreach ($lines as $line) {
			# Split in blocks.
			$blocks = explode("\t", $line);
			# Add each blocks to the line.
			$line = $blocks[0];
			unset($blocks[0]); # Do not add first block twice.
			foreach ($blocks as $block) {
				# Calculate amount of space, insert spaces, insert block.
				$amount = $this->md_tab_width - strlen($line) % $this->md_tab_width;
				$line .= str_repeat(" ", $amount) . $block;
			}
			$text .= "$line\n";
		}
		return $text;
	}


	private function _UnslashQuotes($text) {
	#
	#	This function is useful to remove automaticaly slashed double quotes
	#	when using preg_replace and evaluating an expression.
	#	Parameter:  String.
	#	Returns:    The string with any slash-double-quote (\") sequence replaced
	#				by a single double quote.
	#
		return str_replace('\"', '"', $text);
	}
}

/*

PHP Markdown
============

Description
-----------

This is a PHP translation of the original Markdown formatter written in
Perl by John Gruber.

Markdown is a text-to-HTML filter; it translates an easy-to-read /
easy-to-write structured text format into HTML. Markdown's text format
is most similar to that of plain text email, and supports features such
as headers, *emphasis*, code blocks, blockquotes, and links.

Markdown's syntax is designed not as a generic markup language, but
specifically to serve as a front-end to (X)HTML. You can use span-level
HTML tags anywhere in a Markdown document, and you can use block level
HTML tags (like <div> and <table> as well).

For more information about Markdown's syntax, see:

<http://daringfireball.net/projects/markdown/>


Bugs
----

To file bug reports please send email to:

<michel.fortin@michelf.com>

Please include with your report: (1) the example input; (2) the output you
expected; (3) the output Markdown actually produced.


Version History
---------------

See the readme file for detailed release notes for this version.

1.0.1c - 9 Dec 2005

1.0.1b - 6 Jun 2005

1.0.1a - 15 Apr 2005

1.0.1 - 16 Dec 2004

1.0 - 21 Aug 2004


Author & Contributors
---------------------

Original Perl version by John Gruber
<http://daringfireball.net/>

PHP port and other contributions by Michel Fortin
<http://www.michelf.com/>


Copyright and License
---------------------

Copyright (c) 2004-2005 Michel Fortin
<http://www.michelf.com/>
All rights reserved.

Copyright (c) 2003-2004 John Gruber
<http://daringfireball.net/>
All rights reserved.

Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:

*	Redistributions of source code must retain the above copyright notice,
	this list of conditions and the following disclaimer.

*	Redistributions in binary form must reproduce the above copyright
	notice, this list of conditions and the following disclaimer in the
	documentation and/or other materials provided with the distribution.

*	Neither the name "Markdown" nor the names of its contributors may
	be used to endorse or promote products derived from this software
	without specific prior written permission.

This software is provided by the copyright holders and contributors "as
is" and any express or implied warranties, including, but not limited
to, the implied warranties of merchantability and fitness for a
particular purpose are disclaimed. In no event shall the copyright owner
or contributors be liable for any direct, indirect, incidental, special,
exemplary, or consequential damages (including, but not limited to,
procurement of substitute goods or services; loss of use, data, or
profits; or business interruption) however caused and on any theory of
liability, whether in contract, strict liability, or tort (including
negligence or otherwise) arising in any way out of the use of this
software, even if advised of the possibility of such damage.

*/
?>