forked from samwillis/pagedown-bootstrap
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Markdown.Converter.js
1344 lines (1120 loc) · 50.7 KB
/
Markdown.Converter.js
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
var Markdown;
if (typeof exports === "object" && typeof require === "function") // we're in a CommonJS (e.g. Node.js) module
Markdown = exports;
else
Markdown = {};
// The following text is included for historical reasons, but should
// be taken with a pinch of salt; it's not all true anymore.
//
// Wherever possible, Showdown is a straight, line-by-line port
// of the Perl version of Markdown.
//
// This is not a normal parser design; it's basically just a
// series of string substitutions. It's hard to read and
// maintain this way, but keeping Showdown close to the original
// design makes it easier to port new features.
//
// More importantly, Showdown behaves like markdown.pl in most
// edge cases. So web applications can do client-side preview
// in Javascript, and then build identical HTML on the server.
//
// This port needs the new RegExp functionality of ECMA 262,
// 3rd Edition (i.e. Javascript 1.5). Most modern web browsers
// should do fine. Even with the new regular expression features,
// We do a lot of work to emulate Perl's regex functionality.
// The tricky changes in this file mostly have the "attacklab:"
// label. Major or self-explanatory changes don't.
//
// Smart diff tools like Araxis Merge will be able to match up
// this file with markdown.pl in a useful way. A little tweaking
// helps: in a copy of markdown.pl, replace "#" with "//" and
// replace "$text" with "text". Be sure to ignore whitespace
// and line endings.
//
//
// Usage:
//
// var text = "Markdown *rocks*.";
//
// var converter = new Markdown.Converter();
// var html = converter.makeHtml(text);
//
// alert(html);
//
// Note: move the sample code to the bottom of this
// file before uncommenting it.
//
(function () {
function identity(x) { return x; }
function returnFalse(x) { return false; }
function HookCollection() { }
HookCollection.prototype = {
chain: function (hookname, func) {
var original = this[hookname];
if (!original)
throw new Error("unknown hook " + hookname);
if (original === identity)
this[hookname] = func;
else
this[hookname] = function (x) { return func(original(x)); }
},
set: function (hookname, func) {
if (!this[hookname])
throw new Error("unknown hook " + hookname);
this[hookname] = func;
},
addNoop: function (hookname) {
this[hookname] = identity;
},
addFalse: function (hookname) {
this[hookname] = returnFalse;
}
};
Markdown.HookCollection = HookCollection;
// g_urls and g_titles allow arbitrary user-entered strings as keys. This
// caused an exception (and hence stopped the rendering) when the user entered
// e.g. [push] or [__proto__]. Adding a prefix to the actual key prevents this
// (since no builtin property starts with "s_"). See
// http://meta.stackoverflow.com/questions/64655/strange-wmd-bug
// (granted, switching from Array() to Object() alone would have left only __proto__
// to be a problem)
function SaveHash() { }
SaveHash.prototype = {
set: function (key, value) {
this["s_" + key] = value;
},
get: function (key) {
return this["s_" + key];
}
};
Markdown.Converter = function () {
var pluginHooks = this.hooks = new HookCollection();
pluginHooks.addNoop("plainLinkText"); // given a URL that was encountered by itself (without markup), should return the link text that's to be given to this link
pluginHooks.addNoop("preConversion"); // called with the orignal text as given to makeHtml. The result of this plugin hook is the actual markdown source that will be cooked
pluginHooks.addNoop("postConversion"); // called with the final cooked HTML code. The result of this plugin hook is the actual output of makeHtml
//
// Private state of the converter instance:
//
// Global hashes, used by various utility routines
var g_urls;
var g_titles;
var g_html_blocks;
// Used to track when we're inside an ordered or unordered list
// (see _ProcessListItems() for details):
var g_list_level;
this.makeHtml = function (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.
//
// This will only happen if makeHtml on the same converter instance is called from a plugin hook.
// Don't do that.
if (g_urls)
throw new Error("Recursive call to converter.makeHtml");
// Create the private state objects.
g_urls = new SaveHash();
g_titles = new SaveHash();
g_html_blocks = [];
g_list_level = 0;
text = pluginHooks.preConversion(text);
// attacklab: Replace ~ with ~T
// This lets us use tilde as an escape char to avoid md5 hashes
// The choice of character is arbitray; anything that isn't
// magic in Markdown will work.
text = text.replace(/~/g, "~T");
// attacklab: Replace $ with ~D
// RegExp interprets $ as a special character
// when it's in a replacement string
text = text.replace(/\$/g, "~D");
// Standardize line endings
text = text.replace(/\r\n/g, "\n"); // DOS to Unix
text = text.replace(/\r/g, "\n"); // Mac to Unix
// Make sure text begins and ends with a couple of newlines:
text = "\n\n" + text + "\n\n";
// Convert all tabs to spaces.
text = _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 = text.replace(/^[ \t]+$/mg, "");
// Turn block-level HTML blocks into hash entries
text = _HashHTMLBlocks(text);
// Strip link definitions, store in hashes.
text = _StripLinkDefinitions(text);
text = _RunBlockGamut(text);
text = _UnescapeSpecialChars(text);
// attacklab: Restore dollar signs
text = text.replace(/~D/g, "$$");
// attacklab: Restore tildes
text = text.replace(/~T/g, "~");
text = pluginHooks.postConversion(text);
g_html_blocks = g_titles = g_urls = null;
return text;
};
function _StripLinkDefinitions(text) {
//
// Strips link definitions from text, stores the URLs and titles in
// hash references.
//
// Link defs are in the form: ^[id]: url "optional title"
/*
text = text.replace(/
^[ ]{0,3}\[(.+)\]: // id = $1 attacklab: g_tab_width - 1
[ \t]*
\n? // maybe *one* newline
[ \t]*
<?(\S+?)>? // url = $2
(?=\s|$) // lookahead for whitespace instead of the lookbehind removed below
[ \t]*
\n? // maybe one newline
[ \t]*
( // (potential) title = $3
(\n*) // any lines skipped = $4 attacklab: lookbehind removed
[ \t]+
["(]
(.+?) // title = $5
[")]
[ \t]*
)? // title is optional
(?:\n+|$)
/gm, function(){...});
*/
text = text.replace(/^[ ]{0,3}\[(.+)\]:[ \t]*\n?[ \t]*<?(\S+?)>?(?=\s|$)[ \t]*\n?[ \t]*((\n*)["(](.+?)[")][ \t]*)?(?:\n+)/gm,
function (wholeMatch, m1, m2, m3, m4, m5) {
m1 = m1.toLowerCase();
g_urls.set(m1, _EncodeAmpsAndAngles(m2)); // Link IDs are case-insensitive
if (m4) {
// Oops, found blank lines, so it's not a title.
// Put back the parenthetical statement we stole.
return m3;
} else if (m5) {
g_titles.set(m1, m5.replace(/"/g, """));
}
// Completely remove the definition from the text
return "";
}
);
return text;
}
function _HashHTMLBlocks(text) {
// 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:
var block_tags_a = "p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del"
var 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>`.
// attacklab: This regex can be expensive when it fails.
/*
text = text.replace(/
( // save in $1
^ // start of line (with /m)
<($block_tags_a) // start tag = $2
\b // word break
// attacklab: hack around khtml/pcre bug...
[^\r]*?\n // any number of lines, minimally matching
</\2> // the matching end tag
[ \t]* // trailing spaces/tabs
(?=\n+) // followed by a newline
) // attacklab: there are sentinel newlines at end of document
/gm,function(){...}};
*/
text = text.replace(/^(<(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del)\b[^\r]*?\n<\/\2>[ \t]*(?=\n+))/gm, hashElement);
//
// Now match more liberally, simply from `\n<tag>` to `</tag>\n`
//
/*
text = text.replace(/
( // save in $1
^ // start of line (with /m)
<($block_tags_b) // start tag = $2
\b // word break
// attacklab: hack around khtml/pcre bug...
[^\r]*? // any number of lines, minimally matching
.*</\2> // the matching end tag
[ \t]* // trailing spaces/tabs
(?=\n+) // followed by a newline
) // attacklab: there are sentinel newlines at end of document
/gm,function(){...}};
*/
text = text.replace(/^(<(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math)\b[^\r]*?.*<\/\2>[ \t]*(?=\n+)\n)/gm, hashElement);
// Special case just for <hr />. It was easier to make a special case than
// to make the other regex more complicated.
/*
text = text.replace(/
\n // Starting after a blank line
[ ]{0,3}
( // save in $1
(<(hr) // start tag = $2
\b // word break
([^<>])*?
\/?>) // the matching end tag
[ \t]*
(?=\n{2,}) // followed by a blank line
)
/g,hashElement);
*/
text = text.replace(/\n[ ]{0,3}((<(hr)\b([^<>])*?\/?>)[ \t]*(?=\n{2,}))/g, hashElement);
// Special case for standalone HTML comments:
/*
text = text.replace(/
\n\n // Starting after a blank line
[ ]{0,3} // attacklab: g_tab_width - 1
( // save in $1
<!
(--(?:|(?:[^>-]|-[^>])(?:[^-]|-[^-])*)--) // see http://www.w3.org/TR/html-markup/syntax.html#comments and http://meta.stackoverflow.com/q/95256
>
[ \t]*
(?=\n{2,}) // followed by a blank line
)
/g,hashElement);
*/
text = text.replace(/\n\n[ ]{0,3}(<!(--(?:|(?:[^>-]|-[^>])(?:[^-]|-[^-])*)--)>[ \t]*(?=\n{2,}))/g, hashElement);
// PHP and ASP-style processor instructions (<?...?> and <%...%>)
/*
text = text.replace(/
(?:
\n\n // Starting after a blank line
)
( // save in $1
[ ]{0,3} // attacklab: g_tab_width - 1
(?:
<([?%]) // $2
[^\r]*?
\2>
)
[ \t]*
(?=\n{2,}) // followed by a blank line
)
/g,hashElement);
*/
text = text.replace(/(?:\n\n)([ ]{0,3}(?:<([?%])[^\r]*?\2>)[ \t]*(?=\n{2,}))/g, hashElement);
return text;
}
function hashElement(wholeMatch, m1) {
var blockText = m1;
// Undo double lines
blockText = blockText.replace(/^\n+/, "");
// strip trailing blank lines
blockText = blockText.replace(/\n+$/g, "");
// Replace the element text with a marker ("~KxK" where x is its key)
blockText = "\n\n~K" + (g_html_blocks.push(blockText) - 1) + "K\n\n";
return blockText;
}
function _RunBlockGamut(text, doNotUnhash) {
//
// These are all the transformations that form block-level
// tags like paragraphs, headers, and list items.
//
text = _DoHeaders(text);
// Do Horizontal Rules:
var replacement = "<hr />\n";
text = text.replace(/^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$/gm, replacement);
text = text.replace(/^[ ]{0,2}([ ]?-[ ]?){3,}[ \t]*$/gm, replacement);
text = text.replace(/^[ ]{0,2}([ ]?_[ ]?){3,}[ \t]*$/gm, replacement);
text = _DoLists(text);
text = _DoCodeBlocks(text);
text = _DoBlockQuotes(text);
// We already ran _HashHTMLBlocks() before, in Markdown(), but that
// was to escape raw HTML in the original Markdown source. This time,
// we're escaping the markup we've just created, so that we don't wrap
// <p> tags around block-level tags.
text = _HashHTMLBlocks(text);
text = _FormParagraphs(text, doNotUnhash);
return text;
}
function _RunSpanGamut(text) {
//
// These are all the transformations that occur *within* block-level
// tags like paragraphs, headers, and list items.
//
text = _DoCodeSpans(text);
text = _EscapeSpecialCharsWithinTagAttributes(text);
text = _EncodeBackslashEscapes(text);
// Process anchor and image tags. Images must come first,
// because ![foo][f] looks like an anchor.
text = _DoImages(text);
text = _DoAnchors(text);
// Make links out of things like `<http://example.com/>`
// Must come after _DoAnchors(), because you can use < and >
// delimiters in inline links like [this](<url>).
text = _DoAutoLinks(text);
text = text.replace(/~P/g, "://"); // put in place to prevent autolinking; reset now
text = _EncodeAmpsAndAngles(text);
text = _DoItalicsAndBold(text);
// Do hard breaks:
text = text.replace(/ +\n/g, " <br>\n");
return text;
}
function _EscapeSpecialCharsWithinTagAttributes(text) {
//
// Within tags -- meaning between < and > -- encode [\ ` * _] so they
// don't conflict with their use in Markdown for code, italics and strong.
//
// Build a regex to find HTML tags and comments. See Friedl's
// "Mastering Regular Expressions", 2nd Ed., pp. 200-201.
// SE: changed the comment part of the regex
var regex = /(<[a-z\/!$]("[^"]*"|'[^']*'|[^'">])*>|<!(--(?:|(?:[^>-]|-[^>])(?:[^-]|-[^-])*)--)>)/gi;
text = text.replace(regex, function (wholeMatch) {
var tag = wholeMatch.replace(/(.)<\/?code>(?=.)/g, "$1`");
tag = escapeCharacters(tag, wholeMatch.charAt(1) == "!" ? "\\`*_/" : "\\`*_"); // also escape slashes in comments to prevent autolinking there -- http://meta.stackoverflow.com/questions/95987
return tag;
});
return text;
}
function _DoAnchors(text) {
//
// Turn Markdown link shortcuts into XHTML <a> tags.
//
//
// First, handle reference-style links: [link text] [id]
//
/*
text = text.replace(/
( // wrap whole match in $1
\[
(
(?:
\[[^\]]*\] // allow brackets nested one level
|
[^\[] // or anything else
)*
)
\]
[ ]? // one optional space
(?:\n[ ]*)? // one optional newline followed by spaces
\[
(.*?) // id = $3
\]
)
()()()() // pad remaining backreferences
/g, writeAnchorTag);
*/
text = text.replace(/(\[((?:\[[^\]]*\]|[^\[\]])*)\][ ]?(?:\n[ ]*)?\[(.*?)\])()()()()/g, writeAnchorTag);
//
// Next, inline-style links: [link text](url "optional title")
//
/*
text = text.replace(/
( // wrap whole match in $1
\[
(
(?:
\[[^\]]*\] // allow brackets nested one level
|
[^\[\]] // or anything else
)*
)
\]
\( // literal paren
[ \t]*
() // no id, so leave $3 empty
<?( // href = $4
(?:
\([^)]*\) // allow one level of (correctly nested) parens (think MSDN)
|
[^()]
)*?
)>?
[ \t]*
( // $5
(['"]) // quote char = $6
(.*?) // Title = $7
\6 // matching quote
[ \t]* // ignore any spaces/tabs between closing quote and )
)? // title is optional
\)
)
/g, writeAnchorTag);
*/
text = text.replace(/(\[((?:\[[^\]]*\]|[^\[\]])*)\]\([ \t]*()<?((?:\([^)]*\)|[^()])*?)>?[ \t]*((['"])(.*?)\6[ \t]*)?\))/g, writeAnchorTag);
//
// Last, handle reference-style shortcuts: [link text]
// These must come last in case you've also got [link test][1]
// or [link test](/foo)
//
/*
text = text.replace(/
( // wrap whole match in $1
\[
([^\[\]]+) // link text = $2; can't contain '[' or ']'
\]
)
()()()()() // pad rest of backreferences
/g, writeAnchorTag);
*/
text = text.replace(/(\[([^\[\]]+)\])()()()()()/g, writeAnchorTag);
return text;
}
function writeAnchorTag(wholeMatch, m1, m2, m3, m4, m5, m6, m7) {
if (m7 == undefined) m7 = "";
var whole_match = m1;
var link_text = m2.replace(/:\/\//g, "~P"); // to prevent auto-linking withing the link. will be converted back after the auto-linker runs
var link_id = m3.toLowerCase();
var url = m4;
var title = m7;
if (url == "") {
if (link_id == "") {
// lower-case and turn embedded newlines into spaces
link_id = link_text.toLowerCase().replace(/ ?\n/g, " ");
}
url = "#" + link_id;
if (g_urls.get(link_id) != undefined) {
url = g_urls.get(link_id);
if (g_titles.get(link_id) != undefined) {
title = g_titles.get(link_id);
}
}
else {
if (whole_match.search(/\(\s*\)$/m) > -1) {
// Special case for explicit empty url
url = "";
} else {
return whole_match;
}
}
}
url = encodeProblemUrlChars(url);
url = escapeCharacters(url, "*_");
var result = "<a href=\"" + url + "\"";
if (title != "") {
title = attributeEncode(title);
title = escapeCharacters(title, "*_");
result += " title=\"" + title + "\"";
}
result += ">" + link_text + "</a>";
return result;
}
function _DoImages(text) {
//
// Turn Markdown image shortcuts into <img> tags.
//
//
// First, handle reference-style labeled images: ![alt text][id]
//
/*
text = text.replace(/
( // wrap whole match in $1
!\[
(.*?) // alt text = $2
\]
[ ]? // one optional space
(?:\n[ ]*)? // one optional newline followed by spaces
\[
(.*?) // id = $3
\]
)
()()()() // pad rest of backreferences
/g, writeImageTag);
*/
text = text.replace(/(!\[(.*?)\][ ]?(?:\n[ ]*)?\[(.*?)\])()()()()/g, writeImageTag);
//
// Next, handle inline images: ![alt text](url "optional title")
// Don't forget: encode * and _
/*
text = text.replace(/
( // wrap whole match in $1
!\[
(.*?) // alt text = $2
\]
\s? // One optional whitespace character
\( // literal paren
[ \t]*
() // no id, so leave $3 empty
<?(\S+?)>? // src url = $4
[ \t]*
( // $5
(['"]) // quote char = $6
(.*?) // title = $7
\6 // matching quote
[ \t]*
)? // title is optional
\)
)
/g, writeImageTag);
*/
text = text.replace(/(!\[(.*?)\]\s?\([ \t]*()<?(\S+?)>?[ \t]*((['"])(.*?)\6[ \t]*)?\))/g, writeImageTag);
return text;
}
function attributeEncode(text) {
// unconditionally replace angle brackets here -- what ends up in an attribute (e.g. alt or title)
// never makes sense to have verbatim HTML in it (and the sanitizer would totally break it)
return text.replace(/>/g, ">").replace(/</g, "<").replace(/"/g, """);
}
function writeImageTag(wholeMatch, m1, m2, m3, m4, m5, m6, m7) {
var whole_match = m1;
var alt_text = m2;
var link_id = m3.toLowerCase();
var url = m4;
var title = m7;
if (!title) title = "";
if (url == "") {
if (link_id == "") {
// lower-case and turn embedded newlines into spaces
link_id = alt_text.toLowerCase().replace(/ ?\n/g, " ");
}
url = "#" + link_id;
if (g_urls.get(link_id) != undefined) {
url = g_urls.get(link_id);
if (g_titles.get(link_id) != undefined) {
title = g_titles.get(link_id);
}
}
else {
return whole_match;
}
}
alt_text = escapeCharacters(attributeEncode(alt_text), "*_[]()");
url = escapeCharacters(url, "*_");
var result = "<img src=\"" + url + "\" alt=\"" + alt_text + "\"";
// attacklab: Markdown.pl adds empty title attributes to images.
// Replicate this bug.
//if (title != "") {
title = attributeEncode(title);
title = escapeCharacters(title, "*_");
result += " title=\"" + title + "\"";
//}
result += " />";
return result;
}
function _DoHeaders(text) {
// Setext-style headers:
// Header 1
// ========
//
// Header 2
// --------
//
text = text.replace(/^(.+)[ \t]*\n=+[ \t]*\n+/gm,
function (wholeMatch, m1) { return "<h1>" + _RunSpanGamut(m1) + "</h1>\n\n"; }
);
text = text.replace(/^(.+)[ \t]*\n-+[ \t]*\n+/gm,
function (matchFound, m1) { return "<h2>" + _RunSpanGamut(m1) + "</h2>\n\n"; }
);
// atx-style headers:
// # Header 1
// ## Header 2
// ## Header 2 with closing hashes ##
// ...
// ###### Header 6
//
/*
text = text.replace(/
^(\#{1,6}) // $1 = string of #'s
[ \t]*
(.+?) // $2 = Header text
[ \t]*
\#* // optional closing #'s (not counted)
\n+
/gm, function() {...});
*/
text = text.replace(/^(\#{1,6})[ \t]*(.+?)[ \t]*\#*\n+/gm,
function (wholeMatch, m1, m2) {
var h_level = m1.length;
return "<h" + h_level + ">" + _RunSpanGamut(m2) + "</h" + h_level + ">\n\n";
}
);
return text;
}
function _DoLists(text) {
//
// Form HTML ordered (numbered) and unordered (bulleted) lists.
//
// attacklab: add sentinel to hack around khtml/safari bug:
// http://bugs.webkit.org/show_bug.cgi?id=11231
text += "~0";
// Re-usable pattern to match any entirel ul or ol list:
/*
var whole_list = /
( // $1 = whole list
( // $2
[ ]{0,3} // attacklab: g_tab_width - 1
([*+-]|\d+[.]) // $3 = first list item marker
[ \t]+
)
[^\r]+?
( // $4
~0 // sentinel for workaround; should be $
|
\n{2,}
(?=\S)
(?! // Negative lookahead for another list item marker
[ \t]*
(?:[*+-]|\d+[.])[ \t]+
)
)
)
/g
*/
var whole_list = /^(([ ]{0,3}([*+-]|\d+[.])[ \t]+)[^\r]+?(~0|\n{2,}(?=\S)(?![ \t]*(?:[*+-]|\d+[.])[ \t]+)))/gm;
if (g_list_level) {
text = text.replace(whole_list, function (wholeMatch, m1, m2) {
var list = m1;
var list_type = (m2.search(/[*+-]/g) > -1) ? "ul" : "ol";
var result = _ProcessListItems(list, list_type);
// Trim any trailing whitespace, to put the closing `</$list_type>`
// up on the preceding line, to get it past the current stupid
// HTML block parser. This is a hack to work around the terrible
// hack that is the HTML block parser.
result = result.replace(/\s+$/, "");
result = "<" + list_type + ">" + result + "</" + list_type + ">\n";
return result;
});
} else {
whole_list = /(\n\n|^\n?)(([ ]{0,3}([*+-]|\d+[.])[ \t]+)[^\r]+?(~0|\n{2,}(?=\S)(?![ \t]*(?:[*+-]|\d+[.])[ \t]+)))/g;
text = text.replace(whole_list, function (wholeMatch, m1, m2, m3) {
var runup = m1;
var list = m2;
var list_type = (m3.search(/[*+-]/g) > -1) ? "ul" : "ol";
var result = _ProcessListItems(list, list_type);
result = runup + "<" + list_type + ">\n" + result + "</" + list_type + ">\n";
return result;
});
}
// attacklab: strip sentinel
text = text.replace(/~0/, "");
return text;
}
var _listItemMarkers = { ol: "\\d+[.]", ul: "[*+-]" };
function _ProcessListItems(list_str, list_type) {
//
// Process the contents of a single ordered or unordered list, splitting it
// into individual list items.
//
// list_type is either "ul" or "ol".
// The $g_list_level global keeps track of when we're inside a list.
// Each time we enter a list, we increment it; when we leave a list,
// we decrement. If it's zero, we're not in a list anymore.
//
// We do this because when we're not inside a list, we want to treat
// something like this:
//
// I recommend upgrading to version
// 8. Oops, now this line is treated
// as a sub-list.
//
// As a single paragraph, despite the fact that the second line starts
// with a digit-period-space sequence.
//
// Whereas when we're inside a list (or sub-list), that line will be
// treated as the start of a sub-list. What a kludge, huh? This is
// an aspect of Markdown's syntax that's hard to parse perfectly
// without resorting to mind-reading. Perhaps the solution is to
// change the syntax rules such that sub-lists must start with a
// starting cardinal number; e.g. "1." or "a.".
g_list_level++;
// trim trailing blank lines:
list_str = list_str.replace(/\n{2,}$/, "\n");
// attacklab: add sentinel to emulate \z
list_str += "~0";
// In the original attacklab showdown, list_type was not given to this function, and anything
// that matched /[*+-]|\d+[.]/ would just create the next <li>, causing this mismatch:
//
// Markdown rendered by WMD rendered by MarkdownSharp
// ------------------------------------------------------------------
// 1. first 1. first 1. first
// 2. second 2. second 2. second
// - third 3. third * third
//
// We changed this to behave identical to MarkdownSharp. This is the constructed RegEx,
// with {MARKER} being one of \d+[.] or [*+-], depending on list_type:
/*
list_str = list_str.replace(/
(^[ \t]*) // leading whitespace = $1
({MARKER}) [ \t]+ // list marker = $2
([^\r]+? // list item text = $3
(\n+)
)
(?=
(~0 | \2 ({MARKER}) [ \t]+)
)
/gm, function(){...});
*/
var marker = _listItemMarkers[list_type];
var re = new RegExp("(^[ \\t]*)(" + marker + ")[ \\t]+([^\\r]+?(\\n+))(?=(~0|\\1(" + marker + ")[ \\t]+))", "gm");
var last_item_had_a_double_newline = false;
list_str = list_str.replace(re,
function (wholeMatch, m1, m2, m3) {
var item = m3;
var leading_space = m1;
var ends_with_double_newline = /\n\n$/.test(item);
var contains_double_newline = ends_with_double_newline || item.search(/\n{2,}/) > -1;
if (contains_double_newline || last_item_had_a_double_newline) {
item = _RunBlockGamut(_Outdent(item), /* doNotUnhash = */true);
}
else {
// Recursion for sub-lists:
item = _DoLists(_Outdent(item));
item = item.replace(/\n$/, ""); // chomp(item)
item = _RunSpanGamut(item);
}
last_item_had_a_double_newline = ends_with_double_newline;
return "<li>" + item + "</li>\n";
}
);
// attacklab: strip sentinel
list_str = list_str.replace(/~0/g, "");
g_list_level--;
return list_str;
}
function _DoCodeBlocks(text) {
//
// Process Markdown `<pre><code>` blocks.
//
/*
text = text.replace(/
(?:\n\n|^)
( // $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{4}|\t) // Lines must start with a tab or a tab-width of spaces - attacklab: g_tab_width
.*\n+
)+
)
(\n*[ ]{0,3}[^ \t\n]|(?=~0)) // attacklab: g_tab_width
/g ,function(){...});
*/
// attacklab: sentinel workarounds for lack of \A and \Z, safari\khtml bug
text += "~0";
text = text.replace(/(?:\n\n|^)((?:(?:[ ]{4}|\t).*\n+)+)(\n*[ ]{0,3}[^ \t\n]|(?=~0))/g,
function (wholeMatch, m1, m2) {
var codeblock = m1;
var nextChar = m2;
codeblock = _EncodeCode(_Outdent(codeblock));
codeblock = _Detab(codeblock);
codeblock = codeblock.replace(/^\n+/g, ""); // trim leading newlines
codeblock = codeblock.replace(/\n+$/g, ""); // trim trailing whitespace
codeblock = '<pre class="prettyprint linenums"><code>' + codeblock + '\n</code></pre>';
return "\n\n" + codeblock + "\n\n" + nextChar;
}
);
// attacklab: strip sentinel
text = text.replace(/~0/, "");
return text;
}
function hashBlock(text) {
text = text.replace(/(^\n+|\n+$)/g, "");
return "\n\n~K" + (g_html_blocks.push(text) - 1) + "K\n\n";
}
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 = text.replace(/
(^|[^\\]) // Character before opening ` can't be a backslash
(`+) // $2 = Opening run of `
( // $3 = The code block
[^\r]*?
[^`] // attacklab: work around lack of lookbehind