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
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
|
// stmd.js - CommomMark in javascript
// Copyright (C) 2014 John MacFarlane
// License: BSD3.
// Basic usage:
//
// var stmd = require('stmd');
// var parser = new stmd.DocParser();
// var renderer = new stmd.HtmlRenderer();
// console.log(renderer.render(parser.parse('Hello *world*')));
(function(exports) {
// Some regexps used in inline parser:
var ESCAPABLE = '[!"#$%&\'()*+,./:;<=>?@[\\\\\\]^_`{|}~-]';
var ESCAPED_CHAR = '\\\\' + ESCAPABLE;
var IN_DOUBLE_QUOTES = '"(' + ESCAPED_CHAR + '|[^"\\x00])*"';
var IN_SINGLE_QUOTES = '\'(' + ESCAPED_CHAR + '|[^\'\\x00])*\'';
var IN_PARENS = '\\((' + ESCAPED_CHAR + '|[^)\\x00])*\\)';
var REG_CHAR = '[^\\\\()\\x00-\\x20]';
var IN_PARENS_NOSP = '\\((' + REG_CHAR + '|' + ESCAPED_CHAR + ')*\\)';
var TAGNAME = '[A-Za-z][A-Za-z0-9]*';
var BLOCKTAGNAME = '(?:article|header|aside|hgroup|iframe|blockquote|hr|body|li|map|button|object|canvas|ol|caption|output|col|p|colgroup|pre|dd|progress|div|section|dl|table|td|dt|tbody|embed|textarea|fieldset|tfoot|figcaption|th|figure|thead|footer|footer|tr|form|ul|h1|h2|h3|h4|h5|h6|video|script|style)';
var ATTRIBUTENAME = '[a-zA-Z_:][a-zA-Z0-9:._-]*';
var UNQUOTEDVALUE = "[^\"'=<>`\\x00-\\x20]+";
var SINGLEQUOTEDVALUE = "'[^']*'";
var DOUBLEQUOTEDVALUE = '"[^"]*"';
var ATTRIBUTEVALUE = "(?:" + UNQUOTEDVALUE + "|" + SINGLEQUOTEDVALUE + "|" + DOUBLEQUOTEDVALUE + ")";
var ATTRIBUTEVALUESPEC = "(?:" + "\\s*=" + "\\s*" + ATTRIBUTEVALUE + ")";
var ATTRIBUTE = "(?:" + "\\s+" + ATTRIBUTENAME + ATTRIBUTEVALUESPEC + "?)";
var OPENTAG = "<" + TAGNAME + ATTRIBUTE + "*" + "\\s*/?>";
var CLOSETAG = "</" + TAGNAME + "\\s*[>]";
var OPENBLOCKTAG = "<" + BLOCKTAGNAME + ATTRIBUTE + "*" + "\\s*/?>";
var CLOSEBLOCKTAG = "</" + BLOCKTAGNAME + "\\s*[>]";
var HTMLCOMMENT = "<!--([^-]+|[-][^-]+)*-->";
var PROCESSINGINSTRUCTION = "[<][?].*?[?][>]";
var DECLARATION = "<![A-Z]+" + "\\s+[^>]*>";
var CDATA = "<!\\[CDATA\\[([^\\]]+|\\][^\\]]|\\]\\][^>])*\\]\\]>";
var HTMLTAG = "(?:" + OPENTAG + "|" + CLOSETAG + "|" + HTMLCOMMENT + "|" +
PROCESSINGINSTRUCTION + "|" + DECLARATION + "|" + CDATA + ")";
var HTMLBLOCKOPEN = "<(?:" + BLOCKTAGNAME + "[\\s/>]" + "|" +
"/" + BLOCKTAGNAME + "[\\s>]" + "|" + "[?!])";
var reHtmlTag = new RegExp('^' + HTMLTAG, 'i');
var reHtmlBlockOpen = new RegExp('^' + HTMLBLOCKOPEN, 'i');
var reLinkTitle = new RegExp(
'^(?:"(' + ESCAPED_CHAR + '|[^"\\x00])*"' +
'|' +
'\'(' + ESCAPED_CHAR + '|[^\'\\x00])*\'' +
'|' +
'\\((' + ESCAPED_CHAR + '|[^)\\x00])*\\))');
var reLinkDestinationBraces = new RegExp(
'^(?:[<](?:[^<>\\n\\\\\\x00]' + '|' + ESCAPED_CHAR + '|' + '\\\\)*[>])');
var reLinkDestination = new RegExp(
'^(?:' + REG_CHAR + '+|' + ESCAPED_CHAR + '|' + IN_PARENS_NOSP + ')*');
var reEscapable = new RegExp(ESCAPABLE);
var reAllEscapedChar = new RegExp('\\\\(' + ESCAPABLE + ')', 'g');
var reEscapedChar = new RegExp('^\\\\(' + ESCAPABLE + ')');
var reAllTab = /\t/g;
var reHrule = /^(?:(?:\* *){3,}|(?:_ *){3,}|(?:- *){3,}) *$/;
// Matches a character with a special meaning in markdown,
// or a string of non-special characters. Note: we match
// clumps of _ or * or `, because they need to be handled in groups.
var reMain = /^(?:[_*`\n]+|[\[\]\\!<&*_]|(?: *[^\n `\[\]\\!<&*_]+)+|[ \n]+)/m;
// UTILITY FUNCTIONS
// Replace backslash escapes with literal characters.
var unescape = function(s) {
return s.replace(reAllEscapedChar, '$1');
};
// Returns true if string contains only space characters.
var isBlank = function(s) {
return /^\s*$/.test(s);
};
// Normalize reference label: collapse internal whitespace
// to single space, remove leading/trailing whitespace, case fold.
var normalizeReference = function(s) {
return s.trim()
.replace(/\s+/,' ')
.toUpperCase();
};
// Attempt to match a regex in string s at offset offset.
// Return index of match or null.
var matchAt = function(re, s, offset) {
var res = s.slice(offset).match(re);
if (res) {
return offset + res.index;
} else {
return null;
}
};
// Convert tabs to spaces on each line using a 4-space tab stop.
var detabLine = function(text) {
if (text.indexOf('\t') == -1) {
return text;
} else {
var lastStop = 0;
return text.replace(reAllTab, function(match, offset) {
var result = ' '.slice((offset - lastStop) % 4);
lastStop = offset + 1;
return result;
});
}
};
// INLINE PARSER
// These are methods of an InlineParser object, defined below.
// An InlineParser keeps track of a subject (a string to be
// parsed) and a position in that subject.
// If re matches at current position in the subject, advance
// position in subject and return the match; otherwise return null.
var match = function(re) {
var match = re.exec(this.subject.slice(this.pos));
if (match) {
this.pos += match.index + match[0].length;
return match[0];
} else {
return null;
}
};
// Returns the character at the current subject position, or null if
// there are no more characters.
var peek = function() {
return this.subject[this.pos] || null;
};
// Parse zero or more space characters, including at most one newline
var spnl = function() {
this.match(/^ *(?:\n *)?/);
return 1;
};
// All of the parsers below try to match something at the current position
// in the subject. If they succeed in matching anything, they
// return the inline matched, advancing the subject.
// Attempt to parse backticks, returning either a backtick code span or a
// literal sequence of backticks.
var parseBackticks = function() {
var startpos = this.pos;
var ticks = this.match(/^`+/);
if (!ticks) {
return 0;
}
var afterOpenTicks = this.pos;
var foundCode = false;
var match;
while (!foundCode && (match = this.match(/`+/m))) {
if (match == ticks) {
return [{ t: 'Code', c: this.subject.slice(afterOpenTicks,
this.pos - ticks.length)
.replace(/[ \n]+/g,' ')
.trim() }];
}
}
// If we got here, we didn't match a closing backtick sequence.
this.pos = afterOpenTicks;
return [{ t: 'Str', c: ticks }];
};
// Parse a backslash-escaped special character, adding either the escaped
// character, a hard line break (if the backslash is followed by a newline),
// or a literal backslash to the 'inlines' list.
var parseBackslash = function() {
var subj = this.subject,
pos = this.pos;
if (subj[pos] === '\\') {
if (subj[pos + 1] === '\n') {
this.pos = this.pos + 2;
return [{ t: 'Hardbreak' }];
} else if (reEscapable.test(subj[pos + 1])) {
this.pos = this.pos + 2;
return [{ t: 'Str', c: subj[pos + 1] }];
} else {
this.pos++;
return [{t: 'Str', c: '\\'}];
}
} else {
return null;
}
};
// Attempt to parse an autolink (URL or email in pointy brackets).
var parseAutolink = function() {
var m;
var dest;
if ((m = this.match(/^<([a-zA-Z0-9.!#$%&'*+\/=?^_`{|}~-]+@[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?(?:\.[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?)*)>/))) { // email autolink
dest = m.slice(1,-1);
return [{t: 'Link',
label: [{ t: 'Str', c: dest }],
destination: 'mailto:' + dest }];
} else if ((m = this.match(/^<(?:coap|doi|javascript|aaa|aaas|about|acap|cap|cid|crid|data|dav|dict|dns|file|ftp|geo|go|gopher|h323|http|https|iax|icap|im|imap|info|ipp|iris|iris.beep|iris.xpc|iris.xpcs|iris.lwz|ldap|mailto|mid|msrp|msrps|mtqp|mupdate|news|nfs|ni|nih|nntp|opaquelocktoken|pop|pres|rtsp|service|session|shttp|sieve|sip|sips|sms|snmp|soap.beep|soap.beeps|tag|tel|telnet|tftp|thismessage|tn3270|tip|tv|urn|vemmi|ws|wss|xcon|xcon-userid|xmlrpc.beep|xmlrpc.beeps|xmpp|z39.50r|z39.50s|adiumxtra|afp|afs|aim|apt|attachment|aw|beshare|bitcoin|bolo|callto|chrome|chrome-extension|com-eventbrite-attendee|content|cvs|dlna-playsingle|dlna-playcontainer|dtn|dvb|ed2k|facetime|feed|finger|fish|gg|git|gizmoproject|gtalk|hcp|icon|ipn|irc|irc6|ircs|itms|jar|jms|keyparc|lastfm|ldaps|magnet|maps|market|message|mms|ms-help|msnim|mumble|mvn|notes|oid|palm|paparazzi|platform|proxy|psyc|query|res|resource|rmi|rsync|rtmp|secondlife|sftp|sgn|skype|smb|soldat|spotify|ssh|steam|svn|teamspeak|things|udp|unreal|ut2004|ventrilo|view-source|webcal|wtai|wyciwyg|xfire|xri|ymsgr):[^<>\x00-\x20]*>/i))) {
dest = m.slice(1,-1);
return [{ t: 'Link',
label: [{ t: 'Str', c: dest }],
destination: dest }];
} else {
return null;
}
};
// Attempt to parse a raw HTML tag.
var parseHtmlTag = function() {
var m = this.match(reHtmlTag);
if (m) {
return [{ t: 'Html', c: m }];
} else {
return null;
}
};
// Scan a sequence of characters == c, and return information about
// the number of delimiters and whether they are positioned such that
// they can open and/or close emphasis or strong emphasis. A utility
// function for strong/emph parsing.
var scanDelims = function(c) {
var numdelims = 0;
var first_close_delims = 0;
var char_before, char_after;
var startpos = this.pos;
char_before = this.pos === 0 ? '\n' :
this.subject[this.pos - 1];
while (this.peek() === c) {
numdelims++;
this.pos++;
}
char_after = this.peek() || '\n';
var can_open = numdelims > 0 && numdelims <= 3 && !(/\s/.test(char_after));
var can_close = numdelims > 0 && numdelims <= 3 && !(/\s/.test(char_before));
if (c === '_') {
can_open = can_open && !((/[a-z0-9]/i).test(char_before));
can_close = can_close && !((/[a-z0-9]/i).test(char_after));
}
this.pos = startpos;
return { numdelims: numdelims,
can_open: can_open,
can_close: can_close };
};
// Attempt to parse emphasis or strong emphasis.
var parseEmphasis = function() {
var startpos = this.pos;
var c ;
var first_close = 0;
c = this.peek();
if (!(c === '*' || c === '_')) {
return null;
}
var numdelims;
var delimpos;
var inlines = [];
// Get opening delimiters.
res = this.scanDelims(c);
numdelims = res.numdelims;
if (numdelims === 0) {
this.pos = startpos;
return null;
}
if (numdelims >= 4 || !res.can_open) {
this.pos += numdelims;
return [{t: 'Str', c: this.subject.slice(startpos, startpos + numdelims)}];
}
this.pos += numdelims;
var next_inline;
var first = [];
var second = [];
var current = first;
var state = 0;
var can_close = false;
var can_open = false;
if (numdelims === 3) {
state = 1;
} else if (numdelims === 2) {
state = 2;
} else if (numdelims === 1) {
state = 3;
}
while (true) {
res = this.scanDelims(c);
if (res) {
numdelims = res.numdelims;
can_close = res.can_close;
can_open = res.can_open;
switch (state) {
case 1: // ***a
if (numdelims === 3 && can_close) {
this.pos += 3;
return [{t: 'Strong', c: [{t: 'Emph', c: first}]}];
} else if (numdelims === 2 && can_close) {
this.pos += 2;
current = second;
state = can_open ? 4 : 6;
continue;
} else if (numdelims === 1 && can_close) {
this.pos += 1;
current = second;
state = can_open ? 5 : 7;
continue;
}
break;
case 2: // **a
if (numdelims === 2 && can_close) {
this.pos += 2;
return [{t: 'Strong', c: first}];
} else if (numdelims === 1 && can_open) {
this.pos += 1;
current = second;
state = 8;
continue;
}
break;
case 3: // *a
if (numdelims === 1 && can_close) {
this.pos += 1;
return [{t: 'Emph', c: first}];
} else if (numdelims === 2 && can_open) {
this.pos += 2;
current = second;
state = 9;
continue;
}
break;
case 4: // ***a**b
if (numdelims === 3 && can_close) {
this.pos += 3;
return [{t: 'Strong',
c: [{t: 'Emph',
c: first.concat(
[{t: 'Str', c: c+c}],
second)}]}];
} else if (numdelims === 2 && can_close) {
this.pos += 2;
return [{t: 'Strong',
c: [{t: 'Str', c: c+c+c}].concat(
first,
[{t: 'Strong', c: second}])}];
} else if (numdelims === 1 && can_close) {
this.pos += 1;
return [{t: 'Emph',
c: [{t: 'Strong', c: first}].concat(second)}];
}
break;
case 5: // ***a*b
if (numdelims === 3 && can_close) {
this.pos += 3;
return [{t: 'Strong',
c: [{t: 'Emph',
c: first.concat(
[{t: 'Str', c: c}],
second)}]}];
} else if (numdelims === 2 && can_close) {
this.pos += 2;
return [{t: 'Strong',
c: [{t: 'Emph', c: first}].concat(second)}];
} else if (numdelims === 1 && can_close) {
this.pos += 1;
return [{t: 'Strong',
c: [{t: 'Str', c: c+c+c}].concat(
first,
[{t: 'Emph', c: second}])}];
}
break;
case 6: // ***a** b
if (numdelims === 3 && can_close) {
this.pos += 3;
return [{t: 'Strong',
c: [{t: 'Emph',
c: first.concat(
[{t: 'Str', c: c+c}],
second)}]}];
} else if (numdelims === 1 && can_close) {
this.pos += 1;
return [{t: 'Emph',
c: [{t: 'Strong', c: first}].concat(second)}];
}
break;
case 7: // ***a* b
if (numdelims === 3 && can_close) {
this.pos += 3;
return [{t: 'Strong',
c: [{t: 'Emph',
c: first.concat(
[{t: 'Str', c: c}],
second)}]}];
} else if (numdelims === 2 && can_close) {
this.pos += 2;
return [{t: 'Strong',
c: [{t: 'Emph', c: first}].concat(second)}];
}
break;
case 8: // **a *b
if (numdelims === 3 && can_close) {
this.pos += 3;
return [{t: 'Strong',
c: first.concat([{t: 'Emph',
c: second}])}];
} else if (numdelims === 2 && can_close) {
this.pos += 2;
return [{t: 'Strong',
c: first.concat(
[{t: 'Str', c: c}],
second)}];
} else if (numdelims === 1 && can_close) {
this.pos += 1;
first = first.concat([{t: 'Emph', c: second}]);
current = first;
state = 2;
continue;
}
break;
case 9: // *a **b
if (numdelims === 3 && can_close) {
this.pos += 3;
return [{t: 'Emph',
c: first.concat([{t: 'Strong',
c: second}])}];
} else if (numdelims === 2 && can_close) {
this.pos += 2;
first = first.concat([{t: 'Strong', c: second}]);
current = first;
state = 3;
continue;
} else if (numdelims === 1 && can_close) {
this.pos += 1;
return [{t: 'Emph',
c: first.concat(
[{t: 'Str', c: c+c}],
second)}];
}
break;
default:
break;
}
}
if ((next_inline = this.parseInline())) {
Array.prototype.push.apply(current, next_inline);
} else {
break;
}
}
switch (state) {
case 1: // ***a
return [{t: 'Str', c: c+c+c}].concat(first);
case 2: // **a
return [{t: 'Str', c: c+c}].concat(first);
case 3: // *a
return [{t: 'Str', c: c}].concat(first);
case 4: // ***a**b
case 6: // ***a** b
return [{t: 'Str', c: c+c+c}]
.concat(first,
[{t: 'Str', c: c+c}],
second);
case 5: // ***a*b
case 7: // ***a* b
return [{t: 'Str', c: c+c+c}]
.concat(first,
[{t: 'Str', c: c}],
second);
case 8: // **a *b
return [{t: 'Str', c: c+c}]
.concat(first,
[{t: 'Str', c: c}],
second);
case 9: // *a **b
return [{t: 'Str', c: c}]
.concat(first,
[{t: 'Str', c: c+c}],
second);
default:
console.log("Unknown state, parseEmphasis");
// shouldn't happen
}
};
// Attempt to parse link title (sans quotes), returning the string
// or null if no match.
var parseLinkTitle = function() {
var title = this.match(reLinkTitle);
if (title) {
// chop off quotes from title and unescape:
return unescape(title.substr(1, title.length - 2));
} else {
return null;
}
};
// Attempt to parse link destination, returning the string or
// null if no match.
var parseLinkDestination = function() {
var res = this.match(reLinkDestinationBraces);
if (res) { // chop off surrounding <..>:
return unescape(res.substr(1, res.length - 2));
} else {
res = this.match(reLinkDestination);
if (res !== null) {
return unescape(res);
} else {
return null;
}
}
};
// Attempt to parse a link label, returning number of characters parsed.
var parseLinkLabel = function() {
if (this.peek() != '[') {
return 0;
}
var startpos = this.pos;
var nest_level = 0;
if (this.label_nest_level > 0) {
// If we've already checked to the end of this subject
// for a label, even with a different starting [, we
// know we won't find one here and we can just return.
// This avoids lots of backtracking.
// Note: nest level 1 would be: [foo [bar]
// nest level 2 would be: [foo [bar [baz]
this.label_nest_level--;
return 0;
}
this.pos++; // advance past [
var c;
while ((c = this.peek()) && (c != ']' || nest_level > 0)) {
switch (c) {
case '`':
this.parseBackticks();
break;
case '<':
if (!(this.parseAutolink())) {
this.parseHtmlTag();
}
break;
case '[': // nested []
nest_level++;
this.pos++;
break;
case ']': // nested []
nest_level--;
this.pos++;
break;
case '\\':
this.parseBackslash();
break;
default:
this.parseString();
}
}
if (c === ']') {
this.label_nest_level = 0;
this.pos++; // advance past ]
return this.pos - startpos;
} else {
if (!c) {
this.label_nest_level = nest_level;
}
this.pos = startpos;
return 0;
}
};
// Parse raw link label, including surrounding [], and return
// inline contents. (Note: this is not a method of InlineParser.)
var parseRawLabel = function(s) {
// note: parse without a refmap; we don't want links to resolve
// in nested brackets!
return new InlineParser().parse(s.substr(1, s.length - 2), {});
};
// Attempt to parse a link. If successful, return the link.
var parseLink = function() {
var startpos = this.pos;
var reflabel;
var n;
var dest;
var title;
n = this.parseLinkLabel();
if (n === 0) {
return null;
}
var afterlabel = this.pos;
var rawlabel = this.subject.substr(startpos, n);
// if we got this far, we've parsed a label.
// Try to parse an explicit link: [label](url "title")
if (this.peek() == '(') {
this.pos++;
if (this.spnl() &&
((dest = this.parseLinkDestination()) !== null) &&
this.spnl() &&
// make sure there's a space before the title:
(/^\s/.test(this.subject[this.pos - 1]) &&
(title = this.parseLinkTitle() || '') || true) &&
this.spnl() &&
this.match(/^\)/)) {
return [{ t: 'Link',
destination: dest,
title: title,
label: parseRawLabel(rawlabel) }];
} else {
this.pos = startpos;
return null;
}
}
// If we're here, it wasn't an explicit link. Try to parse a reference link.
// first, see if there's another label
var savepos = this.pos;
this.spnl();
var beforelabel = this.pos;
n = this.parseLinkLabel();
if (n == 2) {
// empty second label
reflabel = rawlabel;
} else if (n > 0) {
reflabel = this.subject.slice(beforelabel, beforelabel + n);
} else {
this.pos = savepos;
reflabel = rawlabel;
}
// lookup rawlabel in refmap
var link = this.refmap[normalizeReference(reflabel)];
if (link) {
return [{t: 'Link',
destination: link.destination,
title: link.title,
label: parseRawLabel(rawlabel) }];
} else {
this.pos = startpos;
return null;
}
// Nothing worked, rewind:
this.pos = startpos;
return null;
};
// Attempt to parse an entity, return Entity object if successful.
var parseEntity = function() {
var m;
if ((m = this.match(/^&(?:#x[a-f0-9]{1,8}|#[0-9]{1,8}|[a-z][a-z0-9]{1,31});/i))) {
return [{ t: 'Entity', c: m }];
} else {
return null;
}
};
// Parse a run of ordinary characters, or a single character with
// a special meaning in markdown, as a plain string, adding to inlines.
var parseString = function() {
var m;
if ((m = this.match(reMain))) {
return [{ t: 'Str', c: m }];
} else {
return null;
}
};
// Parse a newline. If it was preceded by two spaces, return a hard
// line break; otherwise a soft line break.
var parseNewline = function() {
var m = this.match(/^ *\n/);
if (m) {
if (m.length > 2) {
return [{ t: 'Hardbreak' }];
} else if (m.length > 0) {
return [{ t: 'Softbreak' }];
}
}
return null;
};
// Attempt to parse an image. If the opening '!' is not followed
// by a link, return a literal '!'.
var parseImage = function() {
if (this.match(/^!/)) {
var link = this.parseLink();
if (link) {
link[0].t = 'Image';
return link;
} else {
return [{ t: 'Str', c: '!' }];
}
} else {
return null;
}
};
// Attempt to parse a link reference, modifying refmap.
var parseReference = function(s, refmap) {
this.subject = s;
this.pos = 0;
var rawlabel;
var dest;
var title;
var matchChars;
var startpos = this.pos;
var match;
// label:
matchChars = this.parseLinkLabel();
if (matchChars === 0) {
return 0;
} else {
rawlabel = this.subject.substr(0, matchChars);
}
// colon:
if (this.peek() === ':') {
this.pos++;
} else {
this.pos = startpos;
return 0;
}
// link url
this.spnl();
dest = this.parseLinkDestination();
if (dest === null || dest.length === 0) {
this.pos = startpos;
return 0;
}
var beforetitle = this.pos;
this.spnl();
title = this.parseLinkTitle();
if (title === null) {
title = '';
// rewind before spaces
this.pos = beforetitle;
}
// make sure we're at line end:
if (this.match(/^ *(?:\n|$)/) === null) {
this.pos = startpos;
return 0;
}
var normlabel = normalizeReference(rawlabel);
if (!refmap[normlabel]) {
refmap[normlabel] = { destination: dest, title: title };
}
return this.pos - startpos;
};
// Parse the next inline element in subject, advancing subject position
// and returning the inline parsed.
var parseInline = function() {
var startpos = this.pos;
/*
var memoized = this.memo[startpos];
if (memoized) {
this.pos = memoized.endpos;
return memoized.inline;
}
*/
var c = this.peek();
if (!c) {
return null;
}
var res;
switch(c) {
case '\n':
case ' ':
res = this.parseNewline();
break;
case '\\':
res = this.parseBackslash();
break;
case '`':
res = this.parseBackticks();
break;
case '*':
case '_':
res = this.parseEmphasis();
break;
case '[':
res = this.parseLink();
break;
case '!':
res = this.parseImage();
break;
case '<':
res = this.parseAutolink() || this.parseHtmlTag();
break;
case '&':
res = this.parseEntity();
break;
default:
res = this.parseString();
break;
}
if (res === null) {
this.pos += 1;
res = [{t: 'Str', c: c}];
}
/*
if (res) {
this.memo[startpos] = { inline: res,
endpos: this.pos };
}
*/
return res;
};
// Parse s as a list of inlines, using refmap to resolve references.
var parseInlines = function(s, refmap) {
this.subject = s;
this.pos = 0;
this.refmap = refmap || {};
// this.memo = {};
this.last_emphasis_closer = null;
var inlines = [];
var next_inline;
while ((next_inline = this.parseInline())) {
Array.prototype.push.apply(inlines, next_inline);
}
return inlines;
};
// The InlineParser object.
function InlineParser(){
return {
subject: '',
label_nest_level: 0, // used by parseLinkLabel method
last_emphasis_closer: null, // used by parseEmphasis method
pos: 0,
refmap: {},
// memo: {},
match: match,
peek: peek,
spnl: spnl,
parseBackticks: parseBackticks,
parseBackslash: parseBackslash,
parseAutolink: parseAutolink,
parseHtmlTag: parseHtmlTag,
scanDelims: scanDelims,
parseEmphasis: parseEmphasis,
parseLinkTitle: parseLinkTitle,
parseLinkDestination: parseLinkDestination,
parseLinkLabel: parseLinkLabel,
parseLink: parseLink,
parseEntity: parseEntity,
parseString: parseString,
parseNewline: parseNewline,
parseImage: parseImage,
parseReference: parseReference,
parseInline: parseInline,
parse: parseInlines
};
}
// DOC PARSER
// These are methods of a DocParser object, defined below.
var makeBlock = function(tag, start_line, start_column) {
return { t: tag,
open: true,
last_line_blank: false,
start_line: start_line,
start_column: start_column,
end_line: start_line,
children: [],
parent: null,
// string_content is formed by concatenating strings, in finalize:
string_content: "",
strings: [],
inline_content: []
};
};
// Returns true if parent block can contain child block.
var canContain = function(parent_type, child_type) {
return ( parent_type == 'Document' ||
parent_type == 'BlockQuote' ||
parent_type == 'ListItem' ||
(parent_type == 'List' && child_type == 'ListItem') );
};
// Returns true if block type can accept lines of text.
var acceptsLines = function(block_type) {
return ( block_type == 'Paragraph' ||
block_type == 'IndentedCode' ||
block_type == 'FencedCode' );
};
// Returns true if block ends with a blank line, descending if needed
// into lists and sublists.
var endsWithBlankLine = function(block) {
if (block.last_line_blank) {
return true;
}
if ((block.t == 'List' || block.t == 'ListItem') && block.children.length > 0) {
return endsWithBlankLine(block.children[block.children.length - 1]);
} else {
return false;
}
};
// Break out of all containing lists, resetting the tip of the
// document to the parent of the highest list, and finalizing
// all the lists. (This is used to implement the "two blank lines
// break of of all lists" feature.)
var breakOutOfLists = function(block, line_number) {
var b = block;
var last_list = null;
do {
if (b.t === 'List') {
last_list = b;
}
b = b.parent;
} while (b);
if (last_list) {
while (block != last_list) {
this.finalize(block, line_number);
block = block.parent;
}
this.finalize(last_list, line_number);
this.tip = last_list.parent;
}
};
// Add a line to the block at the tip. We assume the tip
// can accept lines -- that check should be done before calling this.
var addLine = function(ln, offset) {
var s = ln.slice(offset);
if (!(this.tip.open)) {
throw({ msg: "Attempted to add line (" + ln + ") to closed container." });
}
this.tip.strings.push(s);
};
// Add block of type tag as a child of the tip. If the tip can't
// accept children, close and finalize it and try its parent,
// and so on til we find a block that can accept children.
var addChild = function(tag, line_number, offset) {
while (!canContain(this.tip.t, tag)) {
this.finalize(this.tip, line_number);
}
var column_number = offset + 1; // offset 0 = column 1
var newBlock = makeBlock(tag, line_number, column_number);
this.tip.children.push(newBlock);
newBlock.parent = this.tip;
this.tip = newBlock;
return newBlock;
};
// Parse a list marker and return data on the marker (type,
// start, delimiter, bullet character, padding) or null.
var parseListMarker = function(ln, offset) {
var rest = ln.slice(offset);
var match;
var spaces_after_marker;
var data = {};
if (rest.match(reHrule)) {
return null;
}
if ((match = rest.match(/^[*+-]( +|$)/))) {
spaces_after_marker = match[1].length;
data.type = 'Bullet';
data.bullet_char = match[0][0];
} else if ((match = rest.match(/^(\d+)([.)])( +|$)/))) {
spaces_after_marker = match[3].length;
data.type = 'Ordered';
data.start = parseInt(match[1]);
data.delimiter = match[2];
} else {
return null;
}
var blank_item = match[0].length === rest.length;
if (spaces_after_marker >= 5 ||
spaces_after_marker < 1 ||
blank_item) {
data.padding = match[0].length - spaces_after_marker + 1;
} else {
data.padding = match[0].length;
}
return data;
};
// Returns true if the two list items are of the same type,
// with the same delimiter and bullet character. This is used
// in agglomerating list items into lists.
var listsMatch = function(list_data, item_data) {
return (list_data.type === item_data.type &&
list_data.delimiter === item_data.delimiter &&
list_data.bullet_char === item_data.bullet_char);
};
// Analyze a line of text and update the document appropriately.
// We parse markdown text by calling this on each line of input,
// then finalizing the document.
var incorporateLine = function(ln, line_number) {
var all_matched = true;
var last_child;
var first_nonspace;
var offset = 0;
var match;
var data;
var blank;
var indent;
var last_matched_container;
var i;
var CODE_INDENT = 4;
var container = this.doc;
var oldtip = this.tip;
// Convert tabs to spaces:
ln = detabLine(ln);
// For each containing block, try to parse the associated line start.
// Bail out on failure: container will point to the last matching block.
// Set all_matched to false if not all containers match.
while (container.children.length > 0) {
last_child = container.children[container.children.length - 1];
if (!last_child.open) {
break;
}
container = last_child;
match = matchAt(/[^ ]/, ln, offset);
if (match === null) {
first_nonspace = ln.length;
blank = true;
} else {
first_nonspace = match;
blank = false;
}
indent = first_nonspace - offset;
switch (container.t) {
case 'BlockQuote':
var matched = indent <= 3 && ln[first_nonspace] === '>';
if (matched) {
offset = first_nonspace + 1;
if (ln[offset] === ' ') {
offset++;
}
} else {
all_matched = false;
}
break;
case 'ListItem':
if (indent >= container.list_data.marker_offset +
container.list_data.padding) {
offset += container.list_data.marker_offset +
container.list_data.padding;
} else if (blank) {
offset = first_nonspace;
} else {
all_matched = false;
}
break;
case 'IndentedCode':
if (indent >= CODE_INDENT) {
offset += CODE_INDENT;
} else if (blank) {
offset = first_nonspace;
} else {
all_matched = false;
}
break;
case 'ATXHeader':
case 'SetextHeader':
case 'HorizontalRule':
// a header can never container > 1 line, so fail to match:
all_matched = false;
break;
case 'FencedCode':
// skip optional spaces of fence offset
i = container.fence_offset;
while (i > 0 && ln[offset] === ' ') {
offset++;
i--;
}
break;
case 'HtmlBlock':
if (blank) {
all_matched = false;
}
break;
case 'Paragraph':
if (blank) {
container.last_line_blank = true;
all_matched = false;
}
break;
default:
}
if (!all_matched) {
container = container.parent; // back up to last matching block
break;
}
}
last_matched_container = container;
// This function is used to finalize and close any unmatched
// blocks. We aren't ready to do this now, because we might
// have a lazy paragraph continuation, in which case we don't
// want to close unmatched blocks. So we store this closure for
// use later, when we have more information.
var closeUnmatchedBlocks = function(mythis) {
// finalize any blocks not matched
while (!already_done && oldtip != last_matched_container) {
mythis.finalize(oldtip, line_number);
oldtip = oldtip.parent;
}
var already_done = true;
};
// Check to see if we've hit 2nd blank line; if so break out of list:
if (blank && container.last_line_blank) {
this.breakOutOfLists(container, line_number);
}
// Unless last matched container is a code block, try new container starts,
// adding children to the last matched container:
while (container.t != 'FencedCode' &&
container.t != 'IndentedCode' &&
container.t != 'HtmlBlock' &&
// this is a little performance optimization:
matchAt(/^[ #`~*+_=<>0-9-]/,ln,offset) !== null) {
match = matchAt(/[^ ]/, ln, offset);
if (match === null) {
first_nonspace = ln.length;
blank = true;
} else {
first_nonspace = match;
blank = false;
}
indent = first_nonspace - offset;
if (indent >= CODE_INDENT) {
// indented code
if (this.tip.t != 'Paragraph' && !blank) {
offset += CODE_INDENT;
closeUnmatchedBlocks(this);
container = this.addChild('IndentedCode', line_number, offset);
} else { // indent > 4 in a lazy paragraph continuation
break;
}
} else if (ln[first_nonspace] === '>') {
// blockquote
offset = first_nonspace + 1;
// optional following space
if (ln[offset] === ' ') {
offset++;
}
closeUnmatchedBlocks(this);
container = this.addChild('BlockQuote', line_number, offset);
} else if ((match = ln.slice(first_nonspace).match(/^#{1,6}(?: +|$)/))) {
// ATX header
offset = first_nonspace + match[0].length;
closeUnmatchedBlocks(this);
container = this.addChild('ATXHeader', line_number, first_nonspace);
container.level = match[0].trim().length; // number of #s
// remove trailing ###s:
container.strings =
[ln.slice(offset).replace(/(?:(\\#) *#*| *#+) *$/,'$1')];
break;
} else if ((match = ln.slice(first_nonspace).match(/^`{3,}(?!.*`)|^~{3,}(?!.*~)/))) {
// fenced code block
var fence_length = match[0].length;
closeUnmatchedBlocks(this);
container = this.addChild('FencedCode', line_number, first_nonspace);
container.fence_length = fence_length;
container.fence_char = match[0][0];
container.fence_offset = first_nonspace - offset;
offset = first_nonspace + fence_length;
break;
} else if (matchAt(reHtmlBlockOpen, ln, first_nonspace) !== null) {
// html block
closeUnmatchedBlocks(this);
container = this.addChild('HtmlBlock', line_number, first_nonspace);
// note, we don't adjust offset because the tag is part of the text
break;
} else if (container.t == 'Paragraph' &&
container.strings.length === 1 &&
((match = ln.slice(first_nonspace).match(/^(?:=+|-+) *$/)))) {
// setext header line
closeUnmatchedBlocks(this);
container.t = 'SetextHeader'; // convert Paragraph to SetextHeader
container.level = match[0][0] === '=' ? 1 : 2;
offset = ln.length;
} else if (matchAt(reHrule, ln, first_nonspace) !== null) {
// hrule
closeUnmatchedBlocks(this);
container = this.addChild('HorizontalRule', line_number, first_nonspace);
offset = ln.length - 1;
break;
} else if ((data = parseListMarker(ln, first_nonspace))) {
// list item
closeUnmatchedBlocks(this);
data.marker_offset = indent;
offset = first_nonspace + data.padding;
// add the list if needed
if (container.t !== 'List' ||
!(listsMatch(container.list_data, data))) {
container = this.addChild('List', line_number, first_nonspace);
container.list_data = data;
}
// add the list item
container = this.addChild('ListItem', line_number, first_nonspace);
container.list_data = data;
} else {
break;
}
if (acceptsLines(container.t)) {
// if it's a line container, it can't contain other containers
break;
}
}
// What remains at the offset is a text line. Add the text to the
// appropriate container.
match = matchAt(/[^ ]/, ln, offset);
if (match === null) {
first_nonspace = ln.length;
blank = true;
} else {
first_nonspace = match;
blank = false;
}
indent = first_nonspace - offset;
// First check for a lazy paragraph continuation:
if (this.tip !== last_matched_container &&
!blank &&
this.tip.t == 'Paragraph' &&
this.tip.strings.length > 0) {
// lazy paragraph continuation
this.last_line_blank = false;
this.addLine(ln, offset);
} else { // not a lazy continuation
// finalize any blocks not matched
closeUnmatchedBlocks(this);
// Block quote lines are never blank as they start with >
// and we don't count blanks in fenced code for purposes of tight/loose
// lists or breaking out of lists. We also don't set last_line_blank
// on an empty list item.
container.last_line_blank = blank &&
!(container.t == 'BlockQuote' ||
container.t == 'FencedCode' ||
(container.t == 'ListItem' &&
container.children.length === 0 &&
container.start_line == line_number));
var cont = container;
while (cont.parent) {
cont.parent.last_line_blank = false;
cont = cont.parent;
}
switch (container.t) {
case 'IndentedCode':
case 'HtmlBlock':
this.addLine(ln, offset);
break;
case 'FencedCode':
// check for closing code fence:
match = (indent <= 3 &&
ln[first_nonspace] == container.fence_char &&
ln.slice(first_nonspace).match(/^(?:`{3,}|~{3,})(?= *$)/));
if (match && match[0].length >= container.fence_length) {
// don't add closing fence to container; instead, close it:
this.finalize(container, line_number);
} else {
this.addLine(ln, offset);
}
break;
case 'ATXHeader':
case 'SetextHeader':
case 'HorizontalRule':
// nothing to do; we already added the contents.
break;
default:
if (acceptsLines(container.t)) {
this.addLine(ln, first_nonspace);
} else if (blank) {
// do nothing
} else if (container.t != 'HorizontalRule' &&
container.t != 'SetextHeader') {
// create paragraph container for line
container = this.addChild('Paragraph', line_number, first_nonspace);
this.addLine(ln, first_nonspace);
} else {
console.log("Line " + line_number.toString() +
" with container type " + container.t +
" did not match any condition.");
}
}
}
};
// Finalize a block. Close it and do any necessary postprocessing,
// e.g. creating string_content from strings, setting the 'tight'
// or 'loose' status of a list, and parsing the beginnings
// of paragraphs for reference definitions. Reset the tip to the
// parent of the closed block.
var finalize = function(block, line_number) {
var pos;
// don't do anything if the block is already closed
if (!block.open) {
return 0;
}
block.open = false;
if (line_number > block.start_line) {
block.end_line = line_number - 1;
} else {
block.end_line = line_number;
}
switch (block.t) {
case 'Paragraph':
block.string_content = block.strings.join('\n').replace(/^ */m,'');
// try parsing the beginning as link reference definitions:
while (block.string_content[0] === '[' &&
(pos = this.inlineParser.parseReference(block.string_content,
this.refmap))) {
block.string_content = block.string_content.slice(pos);
if (isBlank(block.string_content)) {
block.t = 'ReferenceDef';
break;
}
}
break;
case 'ATXHeader':
case 'SetextHeader':
case 'HtmlBlock':
block.string_content = block.strings.join('\n');
break;
case 'IndentedCode':
block.string_content = block.strings.join('\n').replace(/(\n *)*$/,'\n');
break;
case 'FencedCode':
// first line becomes info string
block.info = unescape(block.strings[0].trim());
if (block.strings.length == 1) {
block.string_content = '';
} else {
block.string_content = block.strings.slice(1).join('\n') + '\n';
}
break;
case 'List':
block.tight = true; // tight by default
var numitems = block.children.length;
var i = 0;
while (i < numitems) {
var item = block.children[i];
// check for non-final list item ending with blank line:
var last_item = i == numitems - 1;
if (endsWithBlankLine(item) && !last_item) {
block.tight = false;
break;
}
// recurse into children of list item, to see if there are
// spaces between any of them:
var numsubitems = item.children.length;
var j = 0;
while (j < numsubitems) {
var subitem = item.children[j];
var last_subitem = j == numsubitems - 1;
if (endsWithBlankLine(subitem) && !(last_item && last_subitem)) {
block.tight = false;
break;
}
j++;
}
i++;
}
break;
default:
break;
}
this.tip = block.parent || this.top;
};
// Walk through a block & children recursively, parsing string content
// into inline content where appropriate.
var processInlines = function(block) {
switch(block.t) {
case 'Paragraph':
case 'SetextHeader':
case 'ATXHeader':
block.inline_content =
this.inlineParser.parse(block.string_content.trim(), this.refmap);
block.string_content = "";
break;
default:
break;
}
if (block.children) {
for (var i = 0; i < block.children.length; i++) {
this.processInlines(block.children[i]);
}
}
};
// The main parsing function. Returns a parsed document AST.
var parse = function(input) {
this.doc = makeBlock('Document', 1, 1);
this.tip = this.doc;
this.refmap = {};
var lines = input.replace(/\n$/,'').split(/\r\n|\n|\r/);
var len = lines.length;
for (var i = 0; i < len; i++) {
this.incorporateLine(lines[i], i+1);
}
while (this.tip) {
this.finalize(this.tip, len - 1);
}
this.processInlines(this.doc);
return this.doc;
};
// The DocParser object.
function DocParser(){
return {
doc: makeBlock('Document', 1, 1),
tip: this.doc,
refmap: {},
inlineParser: new InlineParser(),
breakOutOfLists: breakOutOfLists,
addLine: addLine,
addChild: addChild,
incorporateLine: incorporateLine,
finalize: finalize,
processInlines: processInlines,
parse: parse
};
}
// HTML RENDERER
// Helper function to produce content in a pair of HTML tags.
var inTags = function(tag, attribs, contents, selfclosing) {
var result = '<' + tag;
if (attribs) {
var i = 0;
var attrib;
while ((attrib = attribs[i]) !== undefined) {
result = result.concat(' ', attrib[0], '="', attrib[1], '"');
i++;
}
}
if (contents) {
result = result.concat('>', contents, '</', tag, '>');
} else if (selfclosing) {
result = result + ' />';
} else {
result = result.concat('></', tag, '>');
}
return result;
};
// Render an inline element as HTML.
var renderInline = function(inline) {
var attrs;
switch (inline.t) {
case 'Str':
return this.escape(inline.c);
case 'Softbreak':
return this.softbreak;
case 'Hardbreak':
return inTags('br',[],"",true) + '\n';
case 'Emph':
return inTags('em', [], this.renderInlines(inline.c));
case 'Strong':
return inTags('strong', [], this.renderInlines(inline.c));
case 'Html':
return inline.c;
case 'Entity':
return inline.c;
case 'Link':
attrs = [['href', this.escape(inline.destination, true)]];
if (inline.title) {
attrs.push(['title', this.escape(inline.title, true)]);
}
return inTags('a', attrs, this.renderInlines(inline.label));
case 'Image':
attrs = [['src', this.escape(inline.destination, true)],
['alt', this.escape(this.renderInlines(inline.label))]];
if (inline.title) {
attrs.push(['title', this.escape(inline.title, true)]);
}
return inTags('img', attrs, "", true);
case 'Code':
return inTags('code', [], this.escape(inline.c));
default:
console.log("Unknown inline type " + inline.t);
return "";
}
};
// Render a list of inlines.
var renderInlines = function(inlines) {
var result = '';
for (var i=0; i < inlines.length; i++) {
result = result + this.renderInline(inlines[i]);
}
return result;
};
// Render a single block element.
var renderBlock = function(block, in_tight_list) {
var tag;
var attr;
var info_words;
switch (block.t) {
case 'Document':
var whole_doc = this.renderBlocks(block.children);
return (whole_doc === '' ? '' : whole_doc + '\n');
case 'Paragraph':
if (in_tight_list) {
return this.renderInlines(block.inline_content);
} else {
return inTags('p', [], this.renderInlines(block.inline_content));
}
break;
case 'BlockQuote':
var filling = this.renderBlocks(block.children);
return inTags('blockquote', [], filling === '' ? this.innersep :
this.innersep + this.renderBlocks(block.children) + this.innersep);
case 'ListItem':
return inTags('li', [], this.renderBlocks(block.children, in_tight_list).trim());
case 'List':
tag = block.list_data.type == 'Bullet' ? 'ul' : 'ol';
attr = (!block.list_data.start || block.list_data.start == 1) ?
[] : [['start', block.list_data.start.toString()]];
return inTags(tag, attr, this.innersep +
this.renderBlocks(block.children, block.tight) +
this.innersep);
case 'ATXHeader':
case 'SetextHeader':
tag = 'h' + block.level;
return inTags(tag, [], this.renderInlines(block.inline_content));
case 'IndentedCode':
return inTags('pre', [],
inTags('code', [], this.escape(block.string_content)));
case 'FencedCode':
info_words = block.info.split(/ +/);
attr = info_words.length === 0 || info_words[0].length === 0 ?
[] : [['class','language-' +
this.escape(info_words[0],true)]];
return inTags('pre', [],
inTags('code', attr, this.escape(block.string_content)));
case 'HtmlBlock':
return block.string_content;
case 'ReferenceDef':
return "";
case 'HorizontalRule':
return inTags('hr',[],"",true);
default:
console.log("Unknown block type " + block.t);
return "";
}
};
// Render a list of block elements, separated by this.blocksep.
var renderBlocks = function(blocks, in_tight_list) {
var result = [];
for (var i=0; i < blocks.length; i++) {
if (blocks[i].t !== 'ReferenceDef') {
result.push(this.renderBlock(blocks[i], in_tight_list));
}
}
return result.join(this.blocksep);
};
// The HtmlRenderer object.
function HtmlRenderer(){
return {
// default options:
blocksep: '\n', // space between blocks
innersep: '\n', // space between block container tag and contents
softbreak: '\n', // by default, soft breaks are rendered as newlines in HTML
// set to "<br />" to make them hard breaks
// set to " " if you want to ignore line wrapping in source
escape: function(s, preserve_entities) {
if (preserve_entities) {
return s.replace(/[&](?![#](x[a-f0-9]{1,8}|[0-9]{1,8});|[a-z][a-z0-9]{1,31};)/gi,'&')
.replace(/[<]/g,'<')
.replace(/[>]/g,'>')
.replace(/["]/g,'"');
} else {
return s.replace(/[&]/g,'&')
.replace(/[<]/g,'<')
.replace(/[>]/g,'>')
.replace(/["]/g,'"');
}
},
renderInline: renderInline,
renderInlines: renderInlines,
renderBlock: renderBlock,
renderBlocks: renderBlocks,
render: renderBlock
};
}
exports.DocParser = DocParser;
exports.HtmlRenderer = HtmlRenderer;
})(typeof exports === 'undefined' ? this.stmd = {} : exports);
|