-
Notifications
You must be signed in to change notification settings - Fork 0
/
markdown.js
1740 lines (1420 loc) · 52.5 KB
/
markdown.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
// Released under MIT license
// Copyright (c) 2009-2010 Dominic Baggott
// Copyright (c) 2009-2010 Ash Berlin
// Copyright (c) 2011 Christoph Dorn <[email protected]> (http://www.christophdorn.com)
// Date: 2013-09-15T16:12Z
(function(expose) {
var MarkdownHelpers = {};
// For Spidermonkey based engines
function mk_block_toSource() {
return "Markdown.mk_block( " +
uneval(this.toString()) +
", " +
uneval(this.trailing) +
", " +
uneval(this.lineNumber) +
" )";
}
// node
function mk_block_inspect() {
var util = require("util");
return "Markdown.mk_block( " +
util.inspect(this.toString()) +
", " +
util.inspect(this.trailing) +
", " +
util.inspect(this.lineNumber) +
" )";
}
MarkdownHelpers.mk_block = function(block, trail, line) {
// Be helpful for default case in tests.
if ( arguments.length === 1 )
trail = "\n\n";
// We actually need a String object, not a string primitive
/* jshint -W053 */
var s = new String(block);
s.trailing = trail;
// To make it clear its not just a string
s.inspect = mk_block_inspect;
s.toSource = mk_block_toSource;
if ( line !== undefined )
s.lineNumber = line;
return s;
};
var isArray = MarkdownHelpers.isArray = Array.isArray || function(obj) {
return Object.prototype.toString.call(obj) === "[object Array]";
};
// Don't mess with Array.prototype. Its not friendly
if ( Array.prototype.forEach ) {
MarkdownHelpers.forEach = function forEach( arr, cb, thisp ) {
return arr.forEach( cb, thisp );
};
}
else {
MarkdownHelpers.forEach = function forEach(arr, cb, thisp) {
for (var i = 0; i < arr.length; i++)
cb.call(thisp || arr, arr[i], i, arr);
};
}
MarkdownHelpers.isEmpty = function isEmpty( obj ) {
for ( var key in obj ) {
if ( hasOwnProperty.call( obj, key ) )
return false;
}
return true;
};
MarkdownHelpers.extract_attr = function extract_attr( jsonml ) {
return isArray(jsonml)
&& jsonml.length > 1
&& typeof jsonml[ 1 ] === "object"
&& !( isArray(jsonml[ 1 ]) )
? jsonml[ 1 ]
: undefined;
};
/**
* class Markdown
*
* Markdown processing in Javascript done right. We have very particular views
* on what constitutes 'right' which include:
*
* - produces well-formed HTML (this means that em and strong nesting is
* important)
*
* - has an intermediate representation to allow processing of parsed data (We
* in fact have two, both as [JsonML]: a markdown tree and an HTML tree).
*
* - is easily extensible to add new dialects without having to rewrite the
* entire parsing mechanics
*
* - has a good test suite
*
* This implementation fulfills all of these (except that the test suite could
* do with expanding to automatically run all the fixtures from other Markdown
* implementations.)
*
* ##### Intermediate Representation
*
* *TODO* Talk about this :) Its JsonML, but document the node names we use.
*
* [JsonML]: http://jsonml.org/ "JSON Markup Language"
**/
var Markdown = function(dialect) {
switch (typeof dialect) {
case "undefined":
this.dialect = Markdown.dialects.Gruber;
break;
case "object":
this.dialect = dialect;
break;
default:
if ( dialect in Markdown.dialects )
this.dialect = Markdown.dialects[dialect];
else
throw new Error("Unknown Markdown dialect '" + String(dialect) + "'");
break;
}
this.em_state = [];
this.strong_state = [];
this.debug_indent = "";
};
/**
* Markdown.dialects
*
* Namespace of built-in dialects.
**/
Markdown.dialects = {};
// Imported functions
var mk_block = Markdown.mk_block = MarkdownHelpers.mk_block,
isArray = MarkdownHelpers.isArray;
/**
* parse( markdown, [dialect] ) -> JsonML
* - markdown (String): markdown string to parse
* - dialect (String | Dialect): the dialect to use, defaults to gruber
*
* Parse `markdown` and return a markdown document as a Markdown.JsonML tree.
**/
Markdown.parse = function( source, dialect ) {
// dialect will default if undefined
var md = new Markdown( dialect );
return md.toTree( source );
};
function count_lines( str ) {
var n = 0,
i = -1;
while ( ( i = str.indexOf("\n", i + 1) ) !== -1 )
n++;
return n;
}
// Internal - split source into rough blocks
Markdown.prototype.split_blocks = function splitBlocks( input ) {
input = input.replace(/(\r\n|\n|\r)/g, "\n");
// [\s\S] matches _anything_ (newline or space)
// [^] is equivalent but doesn't work in IEs.
var re = /([\s\S]+?)($|\n#|\n(?:\s*\n|$)+)/g,
blocks = [],
m;
var line_no = 1;
if ( ( m = /^(\s*\n)/.exec(input) ) !== null ) {
// skip (but count) leading blank lines
line_no += count_lines( m[0] );
re.lastIndex = m[0].length;
}
while ( ( m = re.exec(input) ) !== null ) {
if (m[2] === "\n#") {
m[2] = "\n";
re.lastIndex--;
}
blocks.push( mk_block( m[1], m[2], line_no ) );
line_no += count_lines( m[0] );
}
return blocks;
};
/**
* Markdown#processBlock( block, next ) -> undefined | [ JsonML, ... ]
* - block (String): the block to process
* - next (Array): the following blocks
*
* Process `block` and return an array of JsonML nodes representing `block`.
*
* It does this by asking each block level function in the dialect to process
* the block until one can. Succesful handling is indicated by returning an
* array (with zero or more JsonML nodes), failure by a false value.
*
* Blocks handlers are responsible for calling [[Markdown#processInline]]
* themselves as appropriate.
*
* If the blocks were split incorrectly or adjacent blocks need collapsing you
* can adjust `next` in place using shift/splice etc.
*
* If any of this default behaviour is not right for the dialect, you can
* define a `__call__` method on the dialect that will get invoked to handle
* the block processing.
*/
Markdown.prototype.processBlock = function processBlock( block, next ) {
var cbs = this.dialect.block,
ord = cbs.__order__;
if ( "__call__" in cbs )
return cbs.__call__.call(this, block, next);
for ( var i = 0; i < ord.length; i++ ) {
//D:this.debug( "Testing", ord[i] );
var res = cbs[ ord[i] ].call( this, block, next );
if ( res ) {
//D:this.debug(" matched");
if ( !isArray(res) || ( res.length > 0 && !( isArray(res[0]) ) ) )
this.debug(ord[i], "didn't return a proper array");
//D:this.debug( "" );
return res;
}
}
// Uhoh! no match! Should we throw an error?
return [];
};
Markdown.prototype.processInline = function processInline( block ) {
return this.dialect.inline.__call__.call( this, String( block ) );
};
/**
* Markdown#toTree( source ) -> JsonML
* - source (String): markdown source to parse
*
* Parse `source` into a JsonML tree representing the markdown document.
**/
// custom_tree means set this.tree to `custom_tree` and restore old value on return
Markdown.prototype.toTree = function toTree( source, custom_root ) {
var blocks = source instanceof Array ? source : this.split_blocks( source );
// Make tree a member variable so its easier to mess with in extensions
var old_tree = this.tree;
try {
this.tree = custom_root || this.tree || [ "markdown" ];
blocks_loop:
while ( blocks.length ) {
var b = this.processBlock( blocks.shift(), blocks );
// Reference blocks and the like won't return any content
if ( !b.length )
continue blocks_loop;
this.tree.push.apply( this.tree, b );
}
return this.tree;
}
finally {
if ( custom_root )
this.tree = old_tree;
}
};
// Noop by default
Markdown.prototype.debug = function () {
var args = Array.prototype.slice.call( arguments);
args.unshift(this.debug_indent);
if ( typeof print !== "undefined" )
print.apply( print, args );
if ( typeof console !== "undefined" && typeof console.log !== "undefined" )
console.log.apply( null, args );
};
Markdown.prototype.loop_re_over_block = function( re, block, cb ) {
// Dont use /g regexps with this
var m,
b = block.valueOf();
while ( b.length && (m = re.exec(b) ) !== null ) {
b = b.substr( m[0].length );
cb.call(this, m);
}
return b;
};
// Build default order from insertion order.
Markdown.buildBlockOrder = function(d) {
var ord = [];
for ( var i in d ) {
if ( i === "__order__" || i === "__call__" )
continue;
ord.push( i );
}
d.__order__ = ord;
};
// Build patterns for inline matcher
Markdown.buildInlinePatterns = function(d) {
var patterns = [];
for ( var i in d ) {
// __foo__ is reserved and not a pattern
if ( i.match( /^__.*__$/) )
continue;
var l = i.replace( /([\\.*+?|()\[\]{}])/g, "\\$1" )
.replace( /\n/, "\\n" );
patterns.push( i.length === 1 ? l : "(?:" + l + ")" );
}
patterns = patterns.join("|");
d.__patterns__ = patterns;
//print("patterns:", uneval( patterns ) );
var fn = d.__call__;
d.__call__ = function(text, pattern) {
if ( pattern !== undefined )
return fn.call(this, text, pattern);
else
return fn.call(this, text, patterns);
};
};
var extract_attr = MarkdownHelpers.extract_attr;
/**
* renderJsonML( jsonml[, options] ) -> String
* - jsonml (Array): JsonML array to render to XML
* - options (Object): options
*
* Converts the given JsonML into well-formed XML.
*
* The options currently understood are:
*
* - root (Boolean): wether or not the root node should be included in the
* output, or just its children. The default `false` is to not include the
* root itself.
*/
Markdown.renderJsonML = function( jsonml, options ) {
options = options || {};
// include the root element in the rendered output?
options.root = options.root || false;
var content = [];
if ( options.root ) {
content.push( render_tree( jsonml ) );
}
else {
jsonml.shift(); // get rid of the tag
if ( jsonml.length && typeof jsonml[ 0 ] === "object" && !( jsonml[ 0 ] instanceof Array ) )
jsonml.shift(); // get rid of the attributes
while ( jsonml.length )
content.push( render_tree( jsonml.shift() ) );
}
return content.join( "\n\n" );
};
/**
* toHTMLTree( markdown, [dialect] ) -> JsonML
* toHTMLTree( md_tree ) -> JsonML
* - markdown (String): markdown string to parse
* - dialect (String | Dialect): the dialect to use, defaults to gruber
* - md_tree (Markdown.JsonML): parsed markdown tree
*
* Turn markdown into HTML, represented as a JsonML tree. If a string is given
* to this function, it is first parsed into a markdown tree by calling
* [[parse]].
**/
Markdown.toHTMLTree = function toHTMLTree( input, dialect , options ) {
// convert string input to an MD tree
if ( typeof input === "string" )
input = this.parse( input, dialect );
// Now convert the MD tree to an HTML tree
// remove references from the tree
var attrs = extract_attr( input ),
refs = {};
if ( attrs && attrs.references )
refs = attrs.references;
var html = convert_tree_to_html( input, refs , options );
merge_text_nodes( html );
return html;
};
/**
* toHTML( markdown, [dialect] ) -> String
* toHTML( md_tree ) -> String
* - markdown (String): markdown string to parse
* - md_tree (Markdown.JsonML): parsed markdown tree
*
* Take markdown (either as a string or as a JsonML tree) and run it through
* [[toHTMLTree]] then turn it into a well-formated HTML fragment.
**/
Markdown.toHTML = function toHTML( source , dialect , options ) {
var input = this.toHTMLTree( source , dialect , options );
return this.renderJsonML( input );
};
function escapeHTML( text ) {
return text.replace( /&/g, "&" )
.replace( /</g, "<" )
.replace( />/g, ">" )
.replace( /"/g, """ )
.replace( /'/g, "'" );
}
function render_tree( jsonml ) {
// basic case
if ( typeof jsonml === "string" )
return escapeHTML( jsonml );
var tag = jsonml.shift(),
attributes = {},
content = [];
if ( jsonml.length && typeof jsonml[ 0 ] === "object" && !( jsonml[ 0 ] instanceof Array ) )
attributes = jsonml.shift();
while ( jsonml.length )
content.push( render_tree( jsonml.shift() ) );
var tag_attrs = "";
for ( var a in attributes )
tag_attrs += " " + a + '="' + escapeHTML( attributes[ a ] ) + '"';
// be careful about adding whitespace here for inline elements
if ( tag === "img" || tag === "br" || tag === "hr" )
return "<"+ tag + tag_attrs + "/>";
else
return "<"+ tag + tag_attrs + ">" + content.join( "" ) + "</" + tag + ">";
}
function convert_tree_to_html( tree, references, options ) {
var i;
options = options || {};
// shallow clone
var jsonml = tree.slice( 0 );
if ( typeof options.preprocessTreeNode === "function" )
jsonml = options.preprocessTreeNode(jsonml, references);
// Clone attributes if they exist
var attrs = extract_attr( jsonml );
if ( attrs ) {
jsonml[ 1 ] = {};
for ( i in attrs ) {
jsonml[ 1 ][ i ] = attrs[ i ];
}
attrs = jsonml[ 1 ];
}
// basic case
if ( typeof jsonml === "string" )
return jsonml;
// convert this node
switch ( jsonml[ 0 ] ) {
case "header":
jsonml[ 0 ] = "h" + jsonml[ 1 ].level;
delete jsonml[ 1 ].level;
break;
case "bulletlist":
jsonml[ 0 ] = "ul";
break;
case "numberlist":
jsonml[ 0 ] = "ol";
break;
case "listitem":
jsonml[ 0 ] = "li";
break;
case "para":
jsonml[ 0 ] = "p";
break;
case "markdown":
jsonml[ 0 ] = "html";
if ( attrs )
delete attrs.references;
break;
case "code_block":
jsonml[ 0 ] = "pre";
i = attrs ? 2 : 1;
var code = [ "code" ];
code.push.apply( code, jsonml.splice( i, jsonml.length - i ) );
jsonml[ i ] = code;
break;
case "inlinecode":
jsonml[ 0 ] = "code";
break;
case "img":
jsonml[ 1 ].src = jsonml[ 1 ].href;
delete jsonml[ 1 ].href;
break;
case "linebreak":
jsonml[ 0 ] = "br";
break;
case "link":
jsonml[ 0 ] = "a";
break;
case "link_ref":
jsonml[ 0 ] = "a";
// grab this ref and clean up the attribute node
var ref = references[ attrs.ref ];
// if the reference exists, make the link
if ( ref ) {
delete attrs.ref;
// add in the href and title, if present
attrs.href = ref.href;
if ( ref.title )
attrs.title = ref.title;
// get rid of the unneeded original text
delete attrs.original;
}
// the reference doesn't exist, so revert to plain text
else {
return attrs.original;
}
break;
case "img_ref":
jsonml[ 0 ] = "img";
// grab this ref and clean up the attribute node
var ref = references[ attrs.ref ];
// if the reference exists, make the link
if ( ref ) {
delete attrs.ref;
// add in the href and title, if present
attrs.src = ref.href;
if ( ref.title )
attrs.title = ref.title;
// get rid of the unneeded original text
delete attrs.original;
}
// the reference doesn't exist, so revert to plain text
else {
return attrs.original;
}
break;
}
// convert all the children
i = 1;
// deal with the attribute node, if it exists
if ( attrs ) {
// if there are keys, skip over it
for ( var key in jsonml[ 1 ] ) {
i = 2;
break;
}
// if there aren't, remove it
if ( i === 1 )
jsonml.splice( i, 1 );
}
for ( ; i < jsonml.length; ++i ) {
jsonml[ i ] = convert_tree_to_html( jsonml[ i ], references, options );
}
return jsonml;
}
// merges adjacent text nodes into a single node
function merge_text_nodes( jsonml ) {
// skip the tag name and attribute hash
var i = extract_attr( jsonml ) ? 2 : 1;
while ( i < jsonml.length ) {
// if it's a string check the next item too
if ( typeof jsonml[ i ] === "string" ) {
if ( i + 1 < jsonml.length && typeof jsonml[ i + 1 ] === "string" ) {
// merge the second string into the first and remove it
jsonml[ i ] += jsonml.splice( i + 1, 1 )[ 0 ];
}
else {
++i;
}
}
// if it's not a string recurse
else {
merge_text_nodes( jsonml[ i ] );
++i;
}
}
};
var DialectHelpers = {};
DialectHelpers.inline_until_char = function( text, want ) {
var consumed = 0,
nodes = [];
while ( true ) {
if ( text.charAt( consumed ) === want ) {
// Found the character we were looking for
consumed++;
return [ consumed, nodes ];
}
if ( consumed >= text.length ) {
// No closing char found. Abort.
return null;
}
var res = this.dialect.inline.__oneElement__.call(this, text.substr( consumed ) );
consumed += res[ 0 ];
// Add any returned nodes.
nodes.push.apply( nodes, res.slice( 1 ) );
}
};
// Helper function to make sub-classing a dialect easier
DialectHelpers.subclassDialect = function( d ) {
function Block() {}
Block.prototype = d.block;
function Inline() {}
Inline.prototype = d.inline;
return { block: new Block(), inline: new Inline() };
};
var forEach = MarkdownHelpers.forEach,
extract_attr = MarkdownHelpers.extract_attr,
mk_block = MarkdownHelpers.mk_block,
isEmpty = MarkdownHelpers.isEmpty,
inline_until_char = DialectHelpers.inline_until_char;
/**
* Gruber dialect
*
* The default dialect that follows the rules set out by John Gruber's
* markdown.pl as closely as possible. Well actually we follow the behaviour of
* that script which in some places is not exactly what the syntax web page
* says.
**/
var Gruber = {
block: {
atxHeader: function atxHeader( block, next ) {
var m = block.match( /^(#{1,6})\s*(.*?)\s*#*\s*(?:\n|$)/ );
if ( !m )
return undefined;
var header = [ "header", { level: m[ 1 ].length } ];
Array.prototype.push.apply(header, this.processInline(m[ 2 ]));
if ( m[0].length < block.length )
next.unshift( mk_block( block.substr( m[0].length ), block.trailing, block.lineNumber + 2 ) );
return [ header ];
},
setextHeader: function setextHeader( block, next ) {
var m = block.match( /^(.*)\n([-=])\2\2+(?:\n|$)/ );
if ( !m )
return undefined;
var level = ( m[ 2 ] === "=" ) ? 1 : 2,
header = [ "header", { level : level }, m[ 1 ] ];
if ( m[0].length < block.length )
next.unshift( mk_block( block.substr( m[0].length ), block.trailing, block.lineNumber + 2 ) );
return [ header ];
},
code: function code( block, next ) {
// | Foo
// |bar
// should be a code block followed by a paragraph. Fun
//
// There might also be adjacent code block to merge.
var ret = [],
re = /^(?: {0,3}\t| {4})(.*)\n?/;
// 4 spaces + content
if ( !block.match( re ) )
return undefined;
block_search:
do {
// Now pull out the rest of the lines
var b = this.loop_re_over_block(
re, block.valueOf(), function( m ) { ret.push( m[1] ); } );
if ( b.length ) {
// Case alluded to in first comment. push it back on as a new block
next.unshift( mk_block(b, block.trailing) );
break block_search;
}
else if ( next.length ) {
// Check the next block - it might be code too
if ( !next[0].match( re ) )
break block_search;
// Pull how how many blanks lines follow - minus two to account for .join
ret.push ( block.trailing.replace(/[^\n]/g, "").substring(2) );
block = next.shift();
}
else {
break block_search;
}
} while ( true );
return [ [ "code_block", ret.join("\n") ] ];
},
horizRule: function horizRule( block, next ) {
// this needs to find any hr in the block to handle abutting blocks
var m = block.match( /^(?:([\s\S]*?)\n)?[ \t]*([-_*])(?:[ \t]*\2){2,}[ \t]*(?:\n([\s\S]*))?$/ );
if ( !m )
return undefined;
var jsonml = [ [ "hr" ] ];
// if there's a leading abutting block, process it
if ( m[ 1 ] ) {
var contained = mk_block( m[ 1 ], "", block.lineNumber );
jsonml.unshift.apply( jsonml, this.toTree( contained, [] ) );
}
// if there's a trailing abutting block, stick it into next
if ( m[ 3 ] )
next.unshift( mk_block( m[ 3 ], block.trailing, block.lineNumber + 1 ) );
return jsonml;
},
// There are two types of lists. Tight and loose. Tight lists have no whitespace
// between the items (and result in text just in the <li>) and loose lists,
// which have an empty line between list items, resulting in (one or more)
// paragraphs inside the <li>.
//
// There are all sorts weird edge cases about the original markdown.pl's
// handling of lists:
//
// * Nested lists are supposed to be indented by four chars per level. But
// if they aren't, you can get a nested list by indenting by less than
// four so long as the indent doesn't match an indent of an existing list
// item in the 'nest stack'.
//
// * The type of the list (bullet or number) is controlled just by the
// first item at the indent. Subsequent changes are ignored unless they
// are for nested lists
//
lists: (function( ) {
// Use a closure to hide a few variables.
var any_list = "[*+-]|\\d+\\.",
bullet_list = /[*+-]/,
// Capture leading indent as it matters for determining nested lists.
is_list_re = new RegExp( "^( {0,3})(" + any_list + ")[ \t]+" ),
indent_re = "(?: {0,3}\\t| {4})";
// TODO: Cache this regexp for certain depths.
// Create a regexp suitable for matching an li for a given stack depth
function regex_for_depth( depth ) {
return new RegExp(
// m[1] = indent, m[2] = list_type
"(?:^(" + indent_re + "{0," + depth + "} {0,3})(" + any_list + ")\\s+)|" +
// m[3] = cont
"(^" + indent_re + "{0," + (depth-1) + "}[ ]{0,4})"
);
}
function expand_tab( input ) {
return input.replace( / {0,3}\t/g, " " );
}
// Add inline content `inline` to `li`. inline comes from processInline
// so is an array of content
function add(li, loose, inline, nl) {
if ( loose ) {
li.push( [ "para" ].concat(inline) );
return;
}
// Hmmm, should this be any block level element or just paras?
var add_to = li[li.length -1] instanceof Array && li[li.length - 1][0] === "para"
? li[li.length -1]
: li;
// If there is already some content in this list, add the new line in
if ( nl && li.length > 1 )
inline.unshift(nl);
for ( var i = 0; i < inline.length; i++ ) {
var what = inline[i],
is_str = typeof what === "string";
if ( is_str && add_to.length > 1 && typeof add_to[add_to.length-1] === "string" )
add_to[ add_to.length-1 ] += what;
else
add_to.push( what );
}
}
// contained means have an indent greater than the current one. On
// *every* line in the block
function get_contained_blocks( depth, blocks ) {
var re = new RegExp( "^(" + indent_re + "{" + depth + "}.*?\\n?)*$" ),
replace = new RegExp("^" + indent_re + "{" + depth + "}", "gm"),
ret = [];
while ( blocks.length > 0 ) {
if ( re.exec( blocks[0] ) ) {
var b = blocks.shift(),
// Now remove that indent
x = b.replace( replace, "");
ret.push( mk_block( x, b.trailing, b.lineNumber ) );
}
else
break;
}
return ret;
}
// passed to stack.forEach to turn list items up the stack into paras
function paragraphify(s, i, stack) {
var list = s.list;
var last_li = list[list.length-1];
if ( last_li[1] instanceof Array && last_li[1][0] === "para" )
return;
if ( i + 1 === stack.length ) {
// Last stack frame
// Keep the same array, but replace the contents
last_li.push( ["para"].concat( last_li.splice(1, last_li.length - 1) ) );
}
else {
var sublist = last_li.pop();
last_li.push( ["para"].concat( last_li.splice(1, last_li.length - 1) ), sublist );
}
}
// The matcher function
return function( block, next ) {
var m = block.match( is_list_re );
if ( !m )
return undefined;
function make_list( m ) {
var list = bullet_list.exec( m[2] )
? ["bulletlist"]
: ["numberlist"];
stack.push( { list: list, indent: m[1] } );
return list;
}
var stack = [], // Stack of lists for nesting.
list = make_list( m ),
last_li,
loose = false,
ret = [ stack[0].list ],
i;
// Loop to search over block looking for inner block elements and loose lists
loose_search:
while ( true ) {
// Split into lines preserving new lines at end of line
var lines = block.split( /(?=\n)/ );
// We have to grab all lines for a li and call processInline on them
// once as there are some inline things that can span lines.
var li_accumulate = "", nl = "";
// Loop over the lines in this block looking for tight lists.
tight_search:
for ( var line_no = 0; line_no < lines.length; line_no++ ) {
nl = "";
var l = lines[line_no].replace(/^\n/, function(n) { nl = n; return ""; });
// TODO: really should cache this
var line_re = regex_for_depth( stack.length );
m = l.match( line_re );
//print( "line:", uneval(l), "\nline match:", uneval(m) );
// We have a list item
if ( m[1] !== undefined ) {
// Process the previous list item, if any
if ( li_accumulate.length ) {
add( last_li, loose, this.processInline( li_accumulate ), nl );
// Loose mode will have been dealt with. Reset it
loose = false;
li_accumulate = "";
}
m[1] = expand_tab( m[1] );
var wanted_depth = Math.floor(m[1].length/4)+1;
//print( "want:", wanted_depth, "stack:", stack.length);
if ( wanted_depth > stack.length ) {
// Deep enough for a nested list outright
//print ( "new nested list" );
list = make_list( m );
last_li.push( list );
last_li = list[1] = [ "listitem" ];
}
else {
// We aren't deep enough to be strictly a new level. This is
// where Md.pl goes nuts. If the indent matches a level in the
// stack, put it there, else put it one deeper then the
// wanted_depth deserves.
var found = false;
for ( i = 0; i < stack.length; i++ ) {
if ( stack[ i ].indent !== m[1] )
continue;
list = stack[ i ].list;
stack.splice( i+1, stack.length - (i+1) );
found = true;
break;
}
if (!found) {
//print("not found. l:", uneval(l));
wanted_depth++;
if ( wanted_depth <= stack.length ) {
stack.splice(wanted_depth, stack.length - wanted_depth);
//print("Desired depth now", wanted_depth, "stack:", stack.length);
list = stack[wanted_depth-1].list;
//print("list:", uneval(list) );
}
else {
//print ("made new stack for messy indent");
list = make_list(m);
last_li.push(list);
}
}
//print( uneval(list), "last", list === stack[stack.length-1].list );
last_li = [ "listitem" ];
list.push(last_li);
} // end depth of shenegains
nl = "";
}
// Add content
if ( l.length > m[0].length )
li_accumulate += nl + l.substr( m[0].length );
} // tight_search
if ( li_accumulate.length ) {
add( last_li, loose, this.processInline( li_accumulate ), nl );
// Loose mode will have been dealt with. Reset it
loose = false;
li_accumulate = "";