forked from twitter-archive/twitter-text-js
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtwitter-text.js
783 lines (654 loc) · 28.2 KB
/
twitter-text.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
if (!window.twttr) {
window.twttr = {};
}
(function() {
twttr.txt = {};
twttr.txt.regexen = {};
var HTML_ENTITIES = {
'&': '&',
'>': '>',
'<': '<',
'"': '"',
"'": '''
};
// HTML escaping
twttr.txt.htmlEscape = function(text) {
return text && text.replace(/[&"'><]/g, function(character) {
return HTML_ENTITIES[character];
});
};
// Builds a RegExp
function regexSupplant(regex, flags) {
flags = flags || "";
if (typeof regex !== "string") {
if (regex.global && flags.indexOf("g") < 0) {
flags += "g";
}
if (regex.ignoreCase && flags.indexOf("i") < 0) {
flags += "i";
}
if (regex.multiline && flags.indexOf("m") < 0) {
flags += "m";
}
regex = regex.source;
}
return new RegExp(regex.replace(/#\{(\w+)\}/g, function(match, name) {
var newRegex = twttr.txt.regexen[name] || "";
if (typeof newRegex !== "string") {
newRegex = newRegex.source;
}
return newRegex;
}), flags);
}
// simple string interpolation
function stringSupplant(str, values) {
return str.replace(/#\{(\w+)\}/g, function(match, name) {
return values[name] || "";
});
}
function addCharsToCharClass(charClass, start, end) {
var s = String.fromCharCode(start);
if (end !== start) {
s += "-" + String.fromCharCode(end);
}
charClass.push(s);
return charClass;
}
// Space is more than %20, U+3000 for example is the full-width space used with Kanji. Provide a short-hand
// to access both the list of characters and a pattern suitible for use with String#split
// Taken from: ActiveSupport::Multibyte::Handlers::UTF8Handler::UNICODE_WHITESPACE
var fromCode = String.fromCharCode;
var UNICODE_SPACES = [
fromCode(0x0020), // White_Space # Zs SPACE
fromCode(0x0085), // White_Space # Cc <control-0085>
fromCode(0x00A0), // White_Space # Zs NO-BREAK SPACE
fromCode(0x1680), // White_Space # Zs OGHAM SPACE MARK
fromCode(0x180E), // White_Space # Zs MONGOLIAN VOWEL SEPARATOR
fromCode(0x2028), // White_Space # Zl LINE SEPARATOR
fromCode(0x2029), // White_Space # Zp PARAGRAPH SEPARATOR
fromCode(0x202F), // White_Space # Zs NARROW NO-BREAK SPACE
fromCode(0x205F), // White_Space # Zs MEDIUM MATHEMATICAL SPACE
fromCode(0x3000) // White_Space # Zs IDEOGRAPHIC SPACE
];
addCharsToCharClass(UNICODE_SPACES, 0x009, 0x00D); // White_Space # Cc [5] <control-0009>..<control-000D>
addCharsToCharClass(UNICODE_SPACES, 0x2000, 0x200A); // White_Space # Zs [11] EN QUAD..HAIR SPACE
twttr.txt.regexen.spaces_group = regexSupplant(UNICODE_SPACES.join(""));
twttr.txt.regexen.spaces = regexSupplant("[" + UNICODE_SPACES.join("") + "]");
twttr.txt.regexen.punct = /\!'#%&'\(\)*\+,\\\-\.\/:;<=>\?@\[\]\^_{|}~/;
twttr.txt.regexen.atSigns = /[@＠]/;
twttr.txt.regexen.extractMentions = regexSupplant(/(^|[^a-zA-Z0-9_])(#{atSigns})([a-zA-Z0-9_]{1,20})(?=(.|$))/g);
twttr.txt.regexen.extractReply = regexSupplant(/^(?:#{spaces})*#{atSigns}([a-zA-Z0-9_]{1,20})/);
twttr.txt.regexen.listName = /[a-zA-Z][a-zA-Z0-9_\-\u0080-\u00ff]{0,24}/;
var nonLatinHashtagChars = [];
// Cyrillic
addCharsToCharClass(nonLatinHashtagChars, 0x0400, 0x04ff); // Cyrillic
addCharsToCharClass(nonLatinHashtagChars, 0x0500, 0x0527); // Cyrillic Supplement
// Hangul (Korean)
addCharsToCharClass(nonLatinHashtagChars, 0x1100, 0x11ff); // Hangul Jamo
addCharsToCharClass(nonLatinHashtagChars, 0x3130, 0x3185); // Hangul Compatibility Jamo
addCharsToCharClass(nonLatinHashtagChars, 0xA960, 0xA97F); // Hangul Jamo Extended-A
addCharsToCharClass(nonLatinHashtagChars, 0xAC00, 0xD7AF); // Hangul Syllables
addCharsToCharClass(nonLatinHashtagChars, 0xD7B0, 0xD7FF); // Hangul Jamo Extended-B
// Japanese and Chinese
addCharsToCharClass(nonLatinHashtagChars, 0x30A1, 0x30FA); // Katakana (full-width)
addCharsToCharClass(nonLatinHashtagChars, 0x30FC, 0x30FC); // Katakana Chouon (full-width)
addCharsToCharClass(nonLatinHashtagChars, 0xFF66, 0xFF9F); // Katakana (half-width)
addCharsToCharClass(nonLatinHashtagChars, 0xFF70, 0xFF70); // Katakana Chouon (half-width)
addCharsToCharClass(nonLatinHashtagChars, 0xFF10, 0xFF19); // \
addCharsToCharClass(nonLatinHashtagChars, 0xFF21, 0xFF3A); // - Latin (full-width)
addCharsToCharClass(nonLatinHashtagChars, 0xFF41, 0xFF5A); // /
addCharsToCharClass(nonLatinHashtagChars, 0x3041, 0x3096); // Hiragana
addCharsToCharClass(nonLatinHashtagChars, 0x3400, 0x4DBF); // Kanji (CJK Extension A)
addCharsToCharClass(nonLatinHashtagChars, 0x4E00, 0x9FFF); // Kanji (Unified)
// -- Disabled as it breaks the Regex.
//addCharsToCharClass(nonLatinHashtagChars, 0x20000, 0x2A6DF); // Kanji (CJK Extension B)
addCharsToCharClass(nonLatinHashtagChars, 0x2A700, 0x2B73F); // Kanji (CJK Extension C)
addCharsToCharClass(nonLatinHashtagChars, 0x2B740, 0x2B81F); // Kanji (CJK Extension D)
addCharsToCharClass(nonLatinHashtagChars, 0x2F800, 0x2FA1F); // Kanji (CJK supplement)
addCharsToCharClass(nonLatinHashtagChars, 0x3005, 0x3005); // Kanji (CJK iteration mark)
twttr.txt.regexen.nonLatinHashtagChars = regexSupplant(nonLatinHashtagChars.join(""));
// Latin accented characters (subtracted 0xD7 from the range, it's a confusable multiplication sign. Looks like "x")
twttr.txt.regexen.latinAccentChars = regexSupplant("ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþ\\303\\277");
twttr.txt.regexen.endScreenNameMatch = regexSupplant(/^(?:#{atSigns}|[#{latinAccentChars}]|:\/\/)/);
// A hashtag must contain characters, numbers and underscores, but not all numbers.
twttr.txt.regexen.hashtagBoundary = regexSupplant(/(?:^|$|#{spaces}|「|」|。|、|\.|!|！|\?|？|,)/);
twttr.txt.regexen.hashtagAlpha = regexSupplant(/[a-z_#{latinAccentChars}#{nonLatinHashtagChars}]/i);
twttr.txt.regexen.hashtagAlphaNumeric = regexSupplant(/[a-z0-9_#{latinAccentChars}#{nonLatinHashtagChars}]/i);
twttr.txt.regexen.autoLinkHashtags = regexSupplant(/(#{hashtagBoundary})(#|＃)(#{hashtagAlphaNumeric}*#{hashtagAlpha}#{hashtagAlphaNumeric}*)/gi);
twttr.txt.regexen.autoLinkUsernamesOrLists = /(^|[^a-zA-Z0-9_]|RT:?)([@＠]+)([a-zA-Z0-9_]{1,20})(\/[a-zA-Z][a-zA-Z0-9_\-]{0,24})?/g;
twttr.txt.regexen.autoLinkEmoticon = /(8\-\#|8\-E|\+\-\(|\`\@|\`O|\<\|:~\(|\}:o\{|:\-\[|\>o\<|X\-\/|\[:-\]\-I\-|\/\/\/\/Ö\\\\\\\\|\(\|:\|\/\)|∑:\*\)|\( \| \))/g;
// URL related hash regex collection
twttr.txt.regexen.invalidDomainChars = stringSupplant("\u00A0#{punct}#{spaces_group}", twttr.txt.regexen);
twttr.txt.regexen.validPrecedingChars = regexSupplant(/(?:[^-\/"':!=A-Za-z0-9_@＠]|^|\:)/);
twttr.txt.regexen.validSubdomain = regexSupplant(/(?:[^#{invalidDomainChars}](?:[_-]|[^#{invalidDomainChars}])*)?[^#{invalidDomainChars}]\./);
twttr.txt.regexen.validDomainName = regexSupplant(/(?:[^#{invalidDomainChars}](?:[-]|[^#{invalidDomainChars}])*)?[^#{invalidDomainChars}]/);
twttr.txt.regexen.validDomain = regexSupplant(/(#{validSubdomain})*#{validDomainName}\.(?:xn--[a-z0-9]{2,}|[a-z]{2,})(?::[0-9]+)?/i);
twttr.txt.regexen.validGeneralUrlPathChars = /[a-z0-9!\*';:=\+\$\/%#\[\]\-_,~|\.]/i;
// Allow URL paths to contain balanced parens
// 1. Used in Wikipedia URLs like /Primer_(film)
// 2. Used in IIS sessions like /S(dfd346)/
twttr.txt.regexen.wikipediaDisambiguation = regexSupplant(/(?:\(#{validGeneralUrlPathChars}+\))/i);
// Allow @ in a url, but only in the middle. Catch things like http://example.com/@user
twttr.txt.regexen.validUrlPathChars = regexSupplant(/(?:#{wikipediaDisambiguation}|@#{validGeneralUrlPathChars}+\/|[\.,]?#{validGeneralUrlPathChars})/i);
// Valid end-of-path chracters (so /foo. does not gobble the period).
// 1. Allow =&# for empty URL parameters and other URL-join artifacts
twttr.txt.regexen.validUrlPathEndingChars = regexSupplant(/(?:[\+\-a-z0-9=_#\/]|#{wikipediaDisambiguation})/i);
twttr.txt.regexen.validUrlQueryChars = /[a-z0-9!\*'\(\);:&=\+\$\/%#\[\]\-_\.,~|]/i;
twttr.txt.regexen.validUrlQueryEndingChars = /[a-z0-9_&=#\/]/i;
twttr.txt.regexen.extractUrl = regexSupplant(
'(' + // $1 total match
'(#{validPrecedingChars})' + // $2 Preceeding chracter
'(' + // $3 URL
'(https?:\\/\\/)' + // $4 Protocol
'(#{validDomain})' + // $5 Domain(s) and optional post number
'(\\/' + // $6 URL Path
'(?:' +
'#{validUrlPathChars}+#{validUrlPathEndingChars}|' +
'#{validUrlPathChars}+#{validUrlPathEndingChars}?|' +
'#{validUrlPathEndingChars}' +
')?' +
')?' +
'(\\?#{validUrlQueryChars}*#{validUrlQueryEndingChars})?' + // $7 Query String
')' +
')'
, "gi");
// These URL validation pattern strings are based on the ABNF from RFC 3986
twttr.txt.regexen.validateUrlUnreserved = /[a-z0-9\-._~]/i;
twttr.txt.regexen.validateUrlPctEncoded = /(?:%[0-9a-f]{2})/i;
twttr.txt.regexen.validateUrlSubDelims = /[!$&'()*+,;=]/i;
twttr.txt.regexen.validateUrlPchar = regexSupplant('(?:' +
'#{validateUrlUnreserved}|' +
'#{validateUrlPctEncoded}|' +
'#{validateUrlSubDelims}|' +
':|@' +
')', 'i');
twttr.txt.regexen.validateUrlScheme = /(?:[a-z][a-z0-9+\-.]*)/i;
twttr.txt.regexen.validateUrlUserinfo = regexSupplant('(?:' +
'#{validateUrlUnreserved}|' +
'#{validateUrlPctEncoded}|' +
'#{validateUrlSubDelims}|' +
':' +
')*', 'i');
twttr.txt.regexen.validateUrlDecOctet = /(?:[0-9]|(?:[1-9][0-9])|(?:1[0-9]{2})|(?:2[0-4][0-9])|(?:25[0-5]))/i;
twttr.txt.regexen.validateUrlIpv4 = regexSupplant(/(?:#{validateUrlDecOctet}(?:\.#{validateUrlDecOctet}){3})/i);
// Punting on real IPv6 validation for now
twttr.txt.regexen.validateUrlIpv6 = /(?:\[[a-f0-9:\.]+\])/i;
// Also punting on IPvFuture for now
twttr.txt.regexen.validateUrlIp = regexSupplant('(?:' +
'#{validateUrlIpv4}|' +
'#{validateUrlIpv6}' +
')', 'i');
// This is more strict than the rfc specifies
twttr.txt.regexen.validateUrlSubDomainSegment = /(?:[a-z0-9](?:[a-z0-9_\-]*[a-z0-9])?)/i;
twttr.txt.regexen.validateUrlDomainSegment = /(?:[a-z0-9](?:[a-z0-9\-]*[a-z0-9])?)/i;
twttr.txt.regexen.validateUrlDomainTld = /(?:[a-z](?:[a-z0-9\-]*[a-z0-9])?)/i;
twttr.txt.regexen.validateUrlDomain = regexSupplant(/(?:(?:#{validateUrlSubDomainSegment]}\.)*(?:#{validateUrlDomainSegment]}\.)#{validateUrlDomainTld})/i);
twttr.txt.regexen.validateUrlHost = regexSupplant('(?:' +
'#{validateUrlIp}|' +
'#{validateUrlDomain}' +
')', 'i');
// Unencoded internationalized domains - this doesn't check for invalid UTF-8 sequences
twttr.txt.regexen.validateUrlUnicodeSubDomainSegment = /(?:(?:[a-z0-9]|[^\u0000-\u007f])(?:(?:[a-z0-9_\-]|[^\u0000-\u007f])*(?:[a-z0-9]|[^\u0000-\u007f]))?)/i;
twttr.txt.regexen.validateUrlUnicodeDomainSegment = /(?:(?:[a-z0-9]|[^\u0000-\u007f])(?:(?:[a-z0-9\-]|[^\u0000-\u007f])*(?:[a-z0-9]|[^\u0000-\u007f]))?)/i;
twttr.txt.regexen.validateUrlUnicodeDomainTld = /(?:(?:[a-z]|[^\u0000-\u007f])(?:(?:[a-z0-9\-]|[^\u0000-\u007f])*(?:[a-z0-9]|[^\u0000-\u007f]))?)/i;
twttr.txt.regexen.validateUrlUnicodeDomain = regexSupplant(/(?:(?:#{validateUrlUnicodeSubDomainSegment}\.)*(?:#{validateUrlUnicodeDomainSegment}\.)#{validateUrlUnicodeDomainTld})/i);
twttr.txt.regexen.validateUrlUnicodeHost = regexSupplant('(?:' +
'#{validateUrlIp}|' +
'#{validateUrlUnicodeDomain}' +
')', 'i');
twttr.txt.regexen.validateUrlPort = /[0-9]{1,5}/;
twttr.txt.regexen.validateUrlUnicodeAuthority = regexSupplant(
'(?:(#{validateUrlUserinfo})@)?' + // $1 userinfo
'(#{validateUrlUnicodeHost})' + // $2 host
'(?::(#{validateUrlPort}))?' //$3 port
, "i");
twttr.txt.regexen.validateUrlAuthority = regexSupplant(
'(?:(#{validateUrlUserinfo})@)?' + // $1 userinfo
'(#{validateUrlHost})' + // $2 host
'(?::(#{validateUrlPort}))?' // $3 port
, "i");
twttr.txt.regexen.validateUrlPath = regexSupplant(/(\/#{validateUrlPchar}*)*/i);
twttr.txt.regexen.validateUrlQuery = regexSupplant(/(#{validateUrlPchar}|\/|\?)*/i);
twttr.txt.regexen.validateUrlFragment = regexSupplant(/(#{validateUrlPchar}|\/|\?)*/i);
// Modified version of RFC 3986 Appendix B
twttr.txt.regexen.validateUrlUnencoded = regexSupplant(
'^' + // Full URL
'(?:' +
'([^:/?#]+):' + // $1 Scheme
')' +
'(?://' +
'([^/?#]*)' + // $2 Authority
')' +
'([^?#]*)' + // $3 Path
'(?:' +
'\\?([^#]*)' + // $4 Query
')?' +
'(?:' +
'#(.*)' + // $5 Fragment
')?$'
, "i");
// Default CSS class for auto-linked URLs
var DEFAULT_URL_CLASS = "tweet-url";
// Default CSS class for auto-linked lists (along with the url class)
var DEFAULT_LIST_CLASS = "list-slug";
// Default CSS class for auto-linked usernames (along with the url class)
var DEFAULT_USERNAME_CLASS = "username";
// Default CSS class for auto-linked hashtags (along with the url class)
var DEFAULT_HASHTAG_CLASS = "hashtag";
// HTML attribute for robot nofollow behavior (default)
var HTML_ATTR_NO_FOLLOW = " rel=\"nofollow\"";
// Simple object cloning function for simple objects
function clone(o) {
var r = {};
for (var k in o) {
if (o.hasOwnProperty(k)) {
r[k] = o[k];
}
}
return r;
}
twttr.txt.autoLink = function(text, options) {
options = clone(options || {});
return twttr.txt.autoLinkUsernamesOrLists(
twttr.txt.autoLinkUrlsCustom(
twttr.txt.autoLinkHashtags(text, options),
options),
options);
};
twttr.txt.autoLinkUsernamesOrLists = function(text, options) {
options = clone(options || {});
options.urlClass = options.urlClass || DEFAULT_URL_CLASS;
options.listClass = options.listClass || DEFAULT_LIST_CLASS;
options.usernameClass = options.usernameClass || DEFAULT_USERNAME_CLASS;
options.usernameUrlBase = options.usernameUrlBase || "http://twitter.com/";
options.listUrlBase = options.listUrlBase || "http://twitter.com/";
if (!options.suppressNoFollow) {
var extraHtml = HTML_ATTR_NO_FOLLOW;
}
var newText = "",
splitText = twttr.txt.splitTags(text);
for (var index = 0; index < splitText.length; index++) {
var chunk = splitText[index];
if (index !== 0) {
newText += ((index % 2 === 0) ? ">" : "<");
}
if (index % 4 !== 0) {
newText += chunk;
} else {
newText += chunk.replace(twttr.txt.regexen.autoLinkUsernamesOrLists, function(match, before, at, user, slashListname, offset, chunk) {
var after = chunk.slice(offset + match.length);
var d = {
before: before,
at: at,
user: twttr.txt.htmlEscape(user),
slashListname: twttr.txt.htmlEscape(slashListname),
extraHtml: extraHtml,
preChunk: "",
chunk: twttr.txt.htmlEscape(chunk),
postChunk: ""
};
for (var k in options) {
if (options.hasOwnProperty(k)) {
d[k] = options[k];
}
}
if (slashListname && !options.suppressLists) {
// the link is a list
var list = d.chunk = stringSupplant("#{user}#{slashListname}", d);
d.list = twttr.txt.htmlEscape(list.toLowerCase());
return stringSupplant("#{before}#{at}<a class=\"#{urlClass} #{listClass}\" href=\"#{listUrlBase}#{list}\"#{extraHtml}>#{chunk}</a>", d);
} else {
if (after && after.match(twttr.txt.regexen.endScreenNameMatch)) {
// Followed by something that means we don't autolink
return match;
} else {
// this is a screen name
d.chunk = twttr.txt.htmlEscape(user);
d.dataScreenName = !options.suppressDataScreenName ? stringSupplant("data-screen-name=\"#{chunk}\" ", d) : "";
return stringSupplant("#{before}#{at}<a class=\"#{urlClass} #{usernameClass}\" #{dataScreenName}href=\"#{usernameUrlBase}#{chunk}\"#{extraHtml}>#{preChunk}#{chunk}#{postChunk}</a>", d);
}
}
});
}
}
return newText;
};
twttr.txt.autoLinkHashtags = function(text, options) {
options = clone(options || {});
options.urlClass = options.urlClass || DEFAULT_URL_CLASS;
options.hashtagClass = options.hashtagClass || DEFAULT_HASHTAG_CLASS;
options.hashtagUrlBase = options.hashtagUrlBase || "http://twitter.com/search?q=%23";
if (!options.suppressNoFollow) {
var extraHtml = HTML_ATTR_NO_FOLLOW;
}
return text.replace(twttr.txt.regexen.autoLinkHashtags, function(match, before, hash, text) {
var d = {
before: before,
hash: twttr.txt.htmlEscape(hash),
preText: "",
text: twttr.txt.htmlEscape(text),
postText: "",
extraHtml: extraHtml
};
for (var k in options) {
if (options.hasOwnProperty(k)) {
d[k] = options[k];
}
}
return stringSupplant("#{before}<a href=\"#{hashtagUrlBase}#{text}\" title=\"##{text}\" class=\"#{urlClass} #{hashtagClass}\"#{extraHtml}>#{hash}#{preText}#{text}#{postText}</a>", d);
});
};
twttr.txt.autoLinkUrlsCustom = function(text, options) {
options = clone(options || {});
if (!options.suppressNoFollow) {
options.rel = "nofollow";
}
if (options.urlClass) {
options["class"] = options.urlClass;
delete options.urlClass;
}
delete options.suppressNoFollow;
delete options.suppressDataScreenName;
return text.replace(twttr.txt.regexen.extractUrl, function(match, all, before, url, protocol, domain, path, queryString) {
var tldComponents;
if (protocol) {
var htmlAttrs = "";
for (var k in options) {
htmlAttrs += stringSupplant(" #{k}=\"#{v}\" ", {k: k, v: options[k].toString().replace(/"/, """).replace(/</, "<").replace(/>/, ">")});
}
var d = {
before: before,
htmlAttrs: htmlAttrs,
url: twttr.txt.htmlEscape(url)
};
return stringSupplant("#{before}<a href=\"#{url}\"#{htmlAttrs}>#{url}</a>", d);
} else {
return all;
}
});
};
twttr.txt.extractMentions = function(text) {
var screenNamesOnly = [],
screenNamesWithIndices = twttr.txt.extractMentionsWithIndices(text);
for (var i = 0; i < screenNamesWithIndices.length; i++) {
var screenName = screenNamesWithIndices[i].screenName;
screenNamesOnly.push(screenName);
}
return screenNamesOnly;
};
twttr.txt.extractMentionsWithIndices = function(text) {
if (!text) {
return [];
}
var possibleScreenNames = [],
position = 0;
text.replace(twttr.txt.regexen.extractMentions, function(match, before, atSign, screenName, after) {
if (!after.match(twttr.txt.regexen.endScreenNameMatch)) {
var startPosition = text.indexOf(atSign + screenName, position);
position = startPosition + screenName.length + 1;
possibleScreenNames.push({
screenName: screenName,
indices: [startPosition, position]
});
}
});
return possibleScreenNames;
};
twttr.txt.extractReplies = function(text) {
if (!text) {
return null;
}
var possibleScreenName = text.match(twttr.txt.regexen.extractReply);
if (!possibleScreenName) {
return null;
}
return possibleScreenName[1];
};
twttr.txt.extractUrls = function(text) {
var urlsOnly = [],
urlsWithIndices = twttr.txt.extractUrlsWithIndices(text);
for (var i = 0; i < urlsWithIndices.length; i++) {
urlsOnly.push(urlsWithIndices[i].url);
}
return urlsOnly;
};
twttr.txt.extractUrlsWithIndices = function(text) {
if (!text) {
return [];
}
var urls = [],
position = 0;
text.replace(twttr.txt.regexen.extractUrl, function(match, all, before, url, protocol, domain, path, query) {
var tldComponents;
if (protocol) {
var startPosition = text.indexOf(url, position),
position = startPosition + url.length;
urls.push({
url: url,
indices: [startPosition, position]
});
}
});
return urls;
};
twttr.txt.extractHashtags = function(text) {
var hashtagsOnly = [],
hashtagsWithIndices = twttr.txt.extractHashtagsWithIndices(text);
for (var i = 0; i < hashtagsWithIndices.length; i++) {
hashtagsOnly.push(hashtagsWithIndices[i].hashtag);
}
return hashtagsOnly;
};
twttr.txt.extractHashtagsWithIndices = function(text) {
if (!text) {
return [];
}
var tags = [],
position = 0;
text.replace(twttr.txt.regexen.autoLinkHashtags, function(match, before, hash, hashText) {
var startPosition = text.indexOf(hash + hashText, position);
position = startPosition + hashText.length + 1;
tags.push({
hashtag: hashText,
indices: [startPosition, position]
});
});
return tags;
};
// this essentially does text.split(/<|>/)
// except that won't work in IE, where empty strings are ommitted
// so "<>".split(/<|>/) => [] in IE, but is ["", "", ""] in all others
// but "<<".split("<") => ["", "", ""]
twttr.txt.splitTags = function(text) {
var firstSplits = text.split("<"),
secondSplits,
allSplits = [],
split;
for (var i = 0; i < firstSplits.length; i += 1) {
split = firstSplits[i];
if (!split) {
allSplits.push("");
} else {
secondSplits = split.split(">");
for (var j = 0; j < secondSplits.length; j += 1) {
allSplits.push(secondSplits[j]);
}
}
}
return allSplits;
};
twttr.txt.hitHighlight = function(text, hits, options) {
var defaultHighlightTag = "em";
hits = hits || [];
options = options || {};
if (hits.length === 0) {
return text;
}
var tagName = options.tag || defaultHighlightTag,
tags = ["<" + tagName + ">", "</" + tagName + ">"],
chunks = twttr.txt.splitTags(text),
split,
i,
j,
result = "",
chunkIndex = 0,
chunk = chunks[0],
prevChunksLen = 0,
chunkCursor = 0,
startInChunk = false,
chunkChars = chunk,
flatHits = [],
index,
hit,
tag,
placed,
hitSpot;
for (i = 0; i < hits.length; i += 1) {
for (j = 0; j < hits[i].length; j += 1) {
flatHits.push(hits[i][j]);
}
}
for (index = 0; index < flatHits.length; index += 1) {
hit = flatHits[index];
tag = tags[index % 2];
placed = false;
while (chunk != null && hit >= prevChunksLen + chunk.length) {
result += chunkChars.slice(chunkCursor);
if (startInChunk && hit === prevChunksLen + chunkChars.length) {
result += tag;
placed = true;
}
if (chunks[chunkIndex + 1]) {
result += "<" + chunks[chunkIndex + 1] + ">";
}
prevChunksLen += chunkChars.length;
chunkCursor = 0;
chunkIndex += 2;
chunk = chunks[chunkIndex];
chunkChars = chunk;
startInChunk = false;
}
if (!placed && chunk != null) {
hitSpot = hit - prevChunksLen;
result += chunkChars.slice(chunkCursor, hitSpot) + tag;
chunkCursor = hitSpot;
if (index % 2 === 0) {
startInChunk = true;
} else {
startInChunk = false;
}
} else if(!placed) {
placed = true;
result += tag;
}
}
if (chunk != null) {
if (chunkCursor < chunkChars.length) {
result += chunkChars.slice(chunkCursor);
}
for (index = chunkIndex + 1; index < chunks.length; index += 1) {
result += (index % 2 === 0 ? chunks[index] : "<" + chunks[index] + ">");
}
}
return result;
};
var MAX_LENGTH = 140;
// Characters not allowed in Tweets
var INVALID_CHARACTERS = [
// BOM
fromCode(0xFFFE),
fromCode(0xFEFF),
// Special
fromCode(0xFFFF),
// Directional Change
fromCode(0x202A),
fromCode(0x202B),
fromCode(0x202C),
fromCode(0x202D),
fromCode(0x202E)
];
// Check the text for any reason that it may not be valid as a Tweet. This is meant as a pre-validation
// before posting to api.twitter.com. There are several server-side reasons for Tweets to fail but this pre-validation
// will allow quicker feedback.
//
// Returns false if this text is valid. Otherwise one of the following strings will be returned:
//
// "too_long": if the text is too long
// "empty": if the text is nil or empty
// "invalid_characters": if the text contains non-Unicode or any of the disallowed Unicode characters
twttr.txt.isInvalidTweet = function(text) {
if (!text) {
return "empty";
}
if (text.length > MAX_LENGTH) {
return "too_long";
}
for (var i = 0; i < INVALID_CHARACTERS.length; i++) {
if (text.indexOf(INVALID_CHARACTERS[i]) >= 0) {
return "invalid_characters";
}
}
return false;
};
twttr.txt.isValidTweetText = function(text) {
return !twttr.txt.isInvalidTweet(text);
};
twttr.txt.isValidUsername = function(username) {
if (!username) {
return false;
}
var extracted = twttr.txt.extractMentions(username);
// Should extract the username minus the @ sign, hence the .slice(1)
return extracted.length === 1 && extracted[0] === username.slice(1);
};
var VALID_LIST_RE = regexSupplant(/^#{autoLinkUsernamesOrLists}$/);
twttr.txt.isValidList = function(usernameList) {
var match = usernameList.match(VALID_LIST_RE);
// Must have matched and had nothing before or after
return !!(match && match[1] == "" && match[4]);
};
twttr.txt.isValidHashtag = function(hashtag) {
if (!hashtag) {
return false;
}
var extracted = twttr.txt.extractHashtags(hashtag);
// Should extract the hashtag minus the # sign, hence the .slice(1)
return extracted.length === 1 && extracted[0] === hashtag.slice(1);
};
twttr.txt.isValidUrl = function(url, unicodeDomains) {
if (unicodeDomains == null) {
unicodeDomains = true;
}
if (!url) {
return false;
}
var urlParts = url.match(twttr.txt.regexen.validateUrlUnencoded);
if (!urlParts || urlParts[0] !== url) {
return false;
}
var scheme = urlParts[1],
authority = urlParts[2],
path = urlParts[3],
query = urlParts[4],
fragment = urlParts[5];
if (!(
isValidMatch(scheme, twttr.txt.regexen.validateUrlScheme) && scheme.match(/^https?$/i) &&
isValidMatch(path, twttr.txt.regexen.validateUrlPath) &&
isValidMatch(query, twttr.txt.regexen.validateUrlQuery, true) &&
isValidMatch(fragment, twttr.txt.regexen.validateUrlFragment, true)
)) {
return false;
}
return (unicodeDomains && isValidMatch(authority, twttr.txt.regexen.validateUrlUnicodeAuthority)) ||
(!unicodeDomains && isValidMatch(authority, twttr.txt.regexen.validateUrlAuthority));
};
function isValidMatch(string, regex, optional) {
if (!optional) {
// RegExp["$&"] is the text of the last match
// blank strings are ok, but are falsy, so we check stringiness instead of truthiness
return ((typeof string === "string") && string.match(regex) && RegExp["$&"] === string);
}
// RegExp["$&"] is the text of the last match
return (!string || (string.match(regex) && RegExp["$&"] === string));
}
}());