aboutsummaryrefslogtreecommitdiff
path: root/contexts/data/lib/closure-library/closure/goog/i18n/bidi.js
blob: 1af4e859c05fc6cae84b16276518e2762ae63c5c (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
// Copyright 2007 The Closure Library Authors. All Rights Reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//      http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS-IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.

/**
 * @fileoverview Utility functions for supporting Bidi issues.
 */


/**
 * Namespace for bidi supporting functions.
 */
goog.provide('goog.i18n.bidi');


/**
 * @define {boolean} FORCE_RTL forces the {@link goog.i18n.bidi.IS_RTL} constant
 * to say that the current locale is a RTL locale.  This should only be used
 * if you want to override the default behavior for deciding whether the
 * current locale is RTL or not.
 *
 * {@see goog.i18n.bidi.IS_RTL}
 */
goog.i18n.bidi.FORCE_RTL = false;


/**
 * Constant that defines whether or not the current locale is a RTL locale.
 * If {@link goog.i18n.bidi.FORCE_RTL} is not true, this constant will default
 * to check that {@link goog.LOCALE} is one of a few major RTL locales.
 *
 * <p>This is designed to be a maximally efficient compile-time constant. For
 * example, for the default goog.LOCALE, compiling
 * "if (goog.i18n.bidi.IS_RTL) alert('rtl') else {}" should produce no code. It
 * is this design consideration that limits the implementation to only
 * supporting a few major RTL locales, as opposed to the broader repertoire of
 * something like goog.i18n.bidi.isRtlLanguage.
 *
 * <p>Since this constant refers to the directionality of the locale, it is up
 * to the caller to determine if this constant should also be used for the
 * direction of the UI.
 *
 * {@see goog.LOCALE}
 *
 * @type {boolean}
 *
 * TODO(user): write a test that checks that this is a compile-time constant.
 */
goog.i18n.bidi.IS_RTL = goog.i18n.bidi.FORCE_RTL ||
    (goog.LOCALE.substring(0, 2).toLowerCase() == 'ar' ||
     goog.LOCALE.substring(0, 2).toLowerCase() == 'fa' ||
     goog.LOCALE.substring(0, 2).toLowerCase() == 'he' ||
     goog.LOCALE.substring(0, 2).toLowerCase() == 'iw' ||
     goog.LOCALE.substring(0, 2).toLowerCase() == 'ur' ||
     goog.LOCALE.substring(0, 2).toLowerCase() == 'yi') &&
    (goog.LOCALE.length == 2 ||
     goog.LOCALE.substring(2, 3) == '-' ||
     goog.LOCALE.substring(2, 3) == '_');


/**
 * Unicode formatting characters and directionality string constants.
 * @enum {string}
 */
goog.i18n.bidi.Format = {
  /** Unicode "Left-To-Right Embedding" (LRE) character. */
  LRE: '\u202A',
  /** Unicode "Right-To-Left Embedding" (RLE) character. */
  RLE: '\u202B',
  /** Unicode "Pop Directional Formatting" (PDF) character. */
  PDF: '\u202C',
  /** Unicode "Left-To-Right Mark" (LRM) character. */
  LRM: '\u200E',
  /** Unicode "Right-To-Left Mark" (RLM) character. */
  RLM: '\u200F'
};


/**
 * Directionality enum.
 * @enum {number}
 */
goog.i18n.bidi.Dir = {
  RTL: -1,
  UNKNOWN: 0,
  LTR: 1
};


/**
 * 'right' string constant.
 * @type {string}
 */
goog.i18n.bidi.RIGHT = 'right';


/**
 * 'left' string constant.
 * @type {string}
 */
goog.i18n.bidi.LEFT = 'left';


/**
 * 'left' if locale is RTL, 'right' if not.
 * @type {string}
 */
goog.i18n.bidi.I18N_RIGHT = goog.i18n.bidi.IS_RTL ? goog.i18n.bidi.LEFT :
    goog.i18n.bidi.RIGHT;


/**
 * 'right' if locale is RTL, 'left' if not.
 * @type {string}
 */
goog.i18n.bidi.I18N_LEFT = goog.i18n.bidi.IS_RTL ? goog.i18n.bidi.RIGHT :
    goog.i18n.bidi.LEFT;


/**
 * Convert a directionality given in various formats to a goog.i18n.bidi.Dir
 * constant. Useful for interaction with different standards of directionality
 * representation.
 *
 * @param {goog.i18n.bidi.Dir|number|boolean} givenDir Directionality given in
 *     one of the following formats:
 *     1. A goog.i18n.bidi.Dir constant.
 *     2. A number (positive = LRT, negative = RTL, 0 = unknown).
 *     3. A boolean (true = RTL, false = LTR).
 * @return {goog.i18n.bidi.Dir} A goog.i18n.bidi.Dir constant matching the given
 *     directionality.
 */
goog.i18n.bidi.toDir = function(givenDir) {
  if (typeof givenDir == 'number') {
    return givenDir > 0 ? goog.i18n.bidi.Dir.LTR :
        givenDir < 0 ? goog.i18n.bidi.Dir.RTL : goog.i18n.bidi.Dir.UNKNOWN;
  } else {
    return givenDir ? goog.i18n.bidi.Dir.RTL : goog.i18n.bidi.Dir.LTR;
  }
};


/**
 * A practical pattern to identify strong LTR characters. This pattern is not
 * theoretically correct according to the Unicode standard. It is simplified for
 * performance and small code size.
 * @type {string}
 * @private
 */
goog.i18n.bidi.ltrChars_ =
    'A-Za-z\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u02B8\u0300-\u0590\u0800-\u1FFF' +
    '\u2C00-\uFB1C\uFE00-\uFE6F\uFEFD-\uFFFF';


/**
 * A practical pattern to identify strong RTL character. This pattern is not
 * theoretically correct according to the Unicode standard. It is simplified
 * for performance and small code size.
 * @type {string}
 * @private
 */
goog.i18n.bidi.rtlChars_ = '\u0591-\u07FF\uFB1D-\uFDFF\uFE70-\uFEFC';


/**
 * Simplified regular expression for an HTML tag (opening or closing) or an HTML
 * escape. We might want to skip over such expressions when estimating the text
 * directionality.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.htmlSkipReg_ = /<[^>]*>|&[^;]+;/g;


/**
 * Returns the input text with spaces instead of HTML tags or HTML escapes, if
 * opt_isStripNeeded is true. Else returns the input as is.
 * Useful for text directionality estimation.
 * Note: the function should not be used in other contexts; it is not 100%
 * correct, but rather a good-enough implementation for directionality
 * estimation purposes.
 * @param {string} str The given string.
 * @param {boolean=} opt_isStripNeeded Whether to perform the stripping.
 *     Default: false (to retain consistency with calling functions).
 * @return {string} The given string cleaned of HTML tags / escapes.
 * @private
 */
goog.i18n.bidi.stripHtmlIfNeeded_ = function(str, opt_isStripNeeded) {
  return opt_isStripNeeded ? str.replace(goog.i18n.bidi.htmlSkipReg_, ' ') :
      str;
};


/**
 * Regular expression to check for RTL characters.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.rtlCharReg_ = new RegExp('[' + goog.i18n.bidi.rtlChars_ + ']');


/**
 * Regular expression to check for LTR characters.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.ltrCharReg_ = new RegExp('[' + goog.i18n.bidi.ltrChars_ + ']');


/**
 * Test whether the given string has any RTL characters in it.
 * @param {string} str The given string that need to be tested.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether the string contains RTL characters.
 */
goog.i18n.bidi.hasAnyRtl = function(str, opt_isHtml) {
  return goog.i18n.bidi.rtlCharReg_.test(goog.i18n.bidi.stripHtmlIfNeeded_(
      str, opt_isHtml));
};


/**
 * Test whether the given string has any RTL characters in it.
 * @param {string} str The given string that need to be tested.
 * @return {boolean} Whether the string contains RTL characters.
 * @deprecated Use hasAnyRtl.
 */
goog.i18n.bidi.hasRtlChar = goog.i18n.bidi.hasAnyRtl;


/**
 * Test whether the given string has any LTR characters in it.
 * @param {string} str The given string that need to be tested.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether the string contains LTR characters.
 */
goog.i18n.bidi.hasAnyLtr = function(str, opt_isHtml) {
  return goog.i18n.bidi.ltrCharReg_.test(goog.i18n.bidi.stripHtmlIfNeeded_(
      str, opt_isHtml));
};


/**
 * Regular expression pattern to check if the first character in the string
 * is LTR.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.ltrRe_ = new RegExp('^[' + goog.i18n.bidi.ltrChars_ + ']');


/**
 * Regular expression pattern to check if the first character in the string
 * is RTL.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.rtlRe_ = new RegExp('^[' + goog.i18n.bidi.rtlChars_ + ']');


/**
 * Check if the first character in the string is RTL or not.
 * @param {string} str The given string that need to be tested.
 * @return {boolean} Whether the first character in str is an RTL char.
 */
goog.i18n.bidi.isRtlChar = function(str) {
  return goog.i18n.bidi.rtlRe_.test(str);
};


/**
 * Check if the first character in the string is LTR or not.
 * @param {string} str The given string that need to be tested.
 * @return {boolean} Whether the first character in str is an LTR char.
 */
goog.i18n.bidi.isLtrChar = function(str) {
  return goog.i18n.bidi.ltrRe_.test(str);
};


/**
 * Check if the first character in the string is neutral or not.
 * @param {string} str The given string that need to be tested.
 * @return {boolean} Whether the first character in str is a neutral char.
 */
goog.i18n.bidi.isNeutralChar = function(str) {
  return !goog.i18n.bidi.isLtrChar(str) && !goog.i18n.bidi.isRtlChar(str);
};


/**
 * Regular expressions to check if a piece of text is of LTR directionality
 * on first character with strong directionality.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.ltrDirCheckRe_ = new RegExp(
    '^[^' + goog.i18n.bidi.rtlChars_ + ']*[' + goog.i18n.bidi.ltrChars_ + ']');


/**
 * Regular expressions to check if a piece of text is of RTL directionality
 * on first character with strong directionality.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.rtlDirCheckRe_ = new RegExp(
    '^[^' + goog.i18n.bidi.ltrChars_ + ']*[' + goog.i18n.bidi.rtlChars_ + ']');


/**
 * Check whether the first strongly directional character (if any) is RTL.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether RTL directionality is detected using the first
 *     strongly-directional character method.
 */
goog.i18n.bidi.startsWithRtl = function(str, opt_isHtml) {
  return goog.i18n.bidi.rtlDirCheckRe_.test(goog.i18n.bidi.stripHtmlIfNeeded_(
      str, opt_isHtml));
};


/**
 * Check whether the first strongly directional character (if any) is RTL.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether RTL directionality is detected using the first
 *     strongly-directional character method.
 * @deprecated Use startsWithRtl.
 */
goog.i18n.bidi.isRtlText = goog.i18n.bidi.startsWithRtl;


/**
 * Check whether the first strongly directional character (if any) is LTR.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether LTR directionality is detected using the first
 *     strongly-directional character method.
 */
goog.i18n.bidi.startsWithLtr = function(str, opt_isHtml) {
  return goog.i18n.bidi.ltrDirCheckRe_.test(goog.i18n.bidi.stripHtmlIfNeeded_(
      str, opt_isHtml));
};


/**
 * Check whether the first strongly directional character (if any) is LTR.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether LTR directionality is detected using the first
 *     strongly-directional character method.
 * @deprecated Use startsWithLtr.
 */
goog.i18n.bidi.isLtrText = goog.i18n.bidi.startsWithLtr;


/**
 * Regular expression to check if a string looks like something that must
 * always be LTR even in RTL text, e.g. a URL. When estimating the
 * directionality of text containing these, we treat these as weakly LTR,
 * like numbers.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.isRequiredLtrRe_ = /^http:\/\/.*/;


/**
 * Check whether the input string either contains no strongly directional
 * characters or looks like a url.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether neutral directionality is detected.
 */
goog.i18n.bidi.isNeutralText = function(str, opt_isHtml) {
  str = goog.i18n.bidi.stripHtmlIfNeeded_(str, opt_isHtml);
  return goog.i18n.bidi.isRequiredLtrRe_.test(str) ||
      !goog.i18n.bidi.hasAnyLtr(str) && !goog.i18n.bidi.hasAnyRtl(str);
};


/**
 * Regular expressions to check if the last strongly-directional character in a
 * piece of text is LTR.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.ltrExitDirCheckRe_ = new RegExp(
    '[' + goog.i18n.bidi.ltrChars_ + '][^' + goog.i18n.bidi.rtlChars_ + ']*$');


/**
 * Regular expressions to check if the last strongly-directional character in a
 * piece of text is RTL.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.rtlExitDirCheckRe_ = new RegExp(
    '[' + goog.i18n.bidi.rtlChars_ + '][^' + goog.i18n.bidi.ltrChars_ + ']*$');


/**
 * Check if the exit directionality a piece of text is LTR, i.e. if the last
 * strongly-directional character in the string is LTR.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether LTR exit directionality was detected.
 */
goog.i18n.bidi.endsWithLtr = function(str, opt_isHtml) {
  return goog.i18n.bidi.ltrExitDirCheckRe_.test(
      goog.i18n.bidi.stripHtmlIfNeeded_(str, opt_isHtml));
};


/**
 * Check if the exit directionality a piece of text is LTR, i.e. if the last
 * strongly-directional character in the string is LTR.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether LTR exit directionality was detected.
 * @deprecated Use endsWithLtr.
 */
goog.i18n.bidi.isLtrExitText = goog.i18n.bidi.endsWithLtr;


/**
 * Check if the exit directionality a piece of text is RTL, i.e. if the last
 * strongly-directional character in the string is RTL.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether RTL exit directionality was detected.
 */
goog.i18n.bidi.endsWithRtl = function(str, opt_isHtml) {
  return goog.i18n.bidi.rtlExitDirCheckRe_.test(
      goog.i18n.bidi.stripHtmlIfNeeded_(str, opt_isHtml));
};


/**
 * Check if the exit directionality a piece of text is RTL, i.e. if the last
 * strongly-directional character in the string is RTL.
 * @param {string} str String being checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether RTL exit directionality was detected.
 * @deprecated Use endsWithRtl.
 */
goog.i18n.bidi.isRtlExitText = goog.i18n.bidi.endsWithRtl;


/**
 * A regular expression for matching right-to-left language codes.
 * See {@link #isRtlLanguage} for the design.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.rtlLocalesRe_ = new RegExp(
    '^(ar|dv|he|iw|fa|nqo|ps|sd|ug|ur|yi|.*[-_](Arab|Hebr|Thaa|Nkoo|Tfng))' +
    '(?!.*[-_](Latn|Cyrl)($|-|_))($|-|_)',
    'i');


/**
 * Check if a BCP 47 / III language code indicates an RTL language, i.e. either:
 * - a language code explicitly specifying one of the right-to-left scripts,
 *   e.g. "az-Arab", or<p>
 * - a language code specifying one of the languages normally written in a
 *   right-to-left script, e.g. "fa" (Farsi), except ones explicitly specifying
 *   Latin or Cyrillic script (which are the usual LTR alternatives).<p>
 * The list of right-to-left scripts appears in the 100-199 range in
 * http://www.unicode.org/iso15924/iso15924-num.html, of which Arabic and
 * Hebrew are by far the most widely used. We also recognize Thaana, N'Ko, and
 * Tifinagh, which also have significant modern usage. The rest (Syriac,
 * Samaritan, Mandaic, etc.) seem to have extremely limited or no modern usage
 * and are not recognized to save on code size.
 * The languages usually written in a right-to-left script are taken as those
 * with Suppress-Script: Hebr|Arab|Thaa|Nkoo|Tfng  in
 * http://www.iana.org/assignments/language-subtag-registry,
 * as well as Sindhi (sd) and Uyghur (ug).
 * Other subtags of the language code, e.g. regions like EG (Egypt), are
 * ignored.
 * @param {string} lang BCP 47 (a.k.a III) language code.
 * @return {boolean} Whether the language code is an RTL language.
 */
goog.i18n.bidi.isRtlLanguage = function(lang) {
  return goog.i18n.bidi.rtlLocalesRe_.test(lang);
};


/**
 * Regular expression for bracket guard replacement in html.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.bracketGuardHtmlRe_ =
    /(\(.*?\)+)|(\[.*?\]+)|(\{.*?\}+)|(&lt;.*?(&gt;)+)/g;


/**
 * Regular expression for bracket guard replacement in text.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.bracketGuardTextRe_ =
    /(\(.*?\)+)|(\[.*?\]+)|(\{.*?\}+)|(<.*?>+)/g;


/**
 * Apply bracket guard using html span tag. This is to address the problem of
 * messy bracket display frequently happens in RTL layout.
 * @param {string} s The string that need to be processed.
 * @param {boolean=} opt_isRtlContext specifies default direction (usually
 *     direction of the UI).
 * @return {string} The processed string, with all bracket guarded.
 */
goog.i18n.bidi.guardBracketInHtml = function(s, opt_isRtlContext) {
  var useRtl = opt_isRtlContext === undefined ?
      goog.i18n.bidi.hasAnyRtl(s) : opt_isRtlContext;
  if (useRtl) {
    return s.replace(goog.i18n.bidi.bracketGuardHtmlRe_,
        '<span dir=rtl>$&</span>');
  }
  return s.replace(goog.i18n.bidi.bracketGuardHtmlRe_,
      '<span dir=ltr>$&</span>');
};


/**
 * Apply bracket guard using LRM and RLM. This is to address the problem of
 * messy bracket display frequently happens in RTL layout.
 * This version works for both plain text and html. But it does not work as
 * good as guardBracketInHtml in some cases.
 * @param {string} s The string that need to be processed.
 * @param {boolean=} opt_isRtlContext specifies default direction (usually
 *     direction of the UI).
 * @return {string} The processed string, with all bracket guarded.
 */
goog.i18n.bidi.guardBracketInText = function(s, opt_isRtlContext) {
  var useRtl = opt_isRtlContext === undefined ?
      goog.i18n.bidi.hasAnyRtl(s) : opt_isRtlContext;
  var mark = useRtl ? goog.i18n.bidi.Format.RLM : goog.i18n.bidi.Format.LRM;
  return s.replace(goog.i18n.bidi.bracketGuardTextRe_, mark + '$&' + mark);
};


/**
 * Enforce the html snippet in RTL directionality regardless overall context.
 * If the html piece was enclosed by tag, dir will be applied to existing
 * tag, otherwise a span tag will be added as wrapper. For this reason, if
 * html snippet start with with tag, this tag must enclose the whole piece. If
 * the tag already has a dir specified, this new one will override existing
 * one in behavior (tested on FF and IE).
 * @param {string} html The string that need to be processed.
 * @return {string} The processed string, with directionality enforced to RTL.
 */
goog.i18n.bidi.enforceRtlInHtml = function(html) {
  if (html.charAt(0) == '<') {
    return html.replace(/<\w+/, '$& dir=rtl');
  }
  // '\n' is important for FF so that it won't incorrectly merge span groups
  return '\n<span dir=rtl>' + html + '</span>';
};


/**
 * Enforce RTL on both end of the given text piece using unicode BiDi formatting
 * characters RLE and PDF.
 * @param {string} text The piece of text that need to be wrapped.
 * @return {string} The wrapped string after process.
 */
goog.i18n.bidi.enforceRtlInText = function(text) {
  return goog.i18n.bidi.Format.RLE + text + goog.i18n.bidi.Format.PDF;
};


/**
 * Enforce the html snippet in RTL directionality regardless overall context.
 * If the html piece was enclosed by tag, dir will be applied to existing
 * tag, otherwise a span tag will be added as wrapper. For this reason, if
 * html snippet start with with tag, this tag must enclose the whole piece. If
 * the tag already has a dir specified, this new one will override existing
 * one in behavior (tested on FF and IE).
 * @param {string} html The string that need to be processed.
 * @return {string} The processed string, with directionality enforced to RTL.
 */
goog.i18n.bidi.enforceLtrInHtml = function(html) {
  if (html.charAt(0) == '<') {
    return html.replace(/<\w+/, '$& dir=ltr');
  }
  // '\n' is important for FF so that it won't incorrectly merge span groups
  return '\n<span dir=ltr>' + html + '</span>';
};


/**
 * Enforce LTR on both end of the given text piece using unicode BiDi formatting
 * characters LRE and PDF.
 * @param {string} text The piece of text that need to be wrapped.
 * @return {string} The wrapped string after process.
 */
goog.i18n.bidi.enforceLtrInText = function(text) {
  return goog.i18n.bidi.Format.LRE + text + goog.i18n.bidi.Format.PDF;
};


/**
 * Regular expression to find dimensions such as "padding: .3 0.4ex 5px 6;"
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.dimensionsRe_ =
    /:\s*([.\d][.\w]*)\s+([.\d][.\w]*)\s+([.\d][.\w]*)\s+([.\d][.\w]*)/g;


/**
 * Regular expression for left.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.leftRe_ = /left/gi;


/**
 * Regular expression for right.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.rightRe_ = /right/gi;


/**
 * Placeholder regular expression for swapping.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.tempRe_ = /%%%%/g;


/**
 * Swap location parameters and 'left'/'right' in CSS specification. The
 * processed string will be suited for RTL layout. Though this function can
 * cover most cases, there are always exceptions. It is suggested to put
 * those exceptions in separate group of CSS string.
 * @param {string} cssStr CSS spefication string.
 * @return {string} Processed CSS specification string.
 */
goog.i18n.bidi.mirrorCSS = function(cssStr) {
  return cssStr.
      // reverse dimensions
      replace(goog.i18n.bidi.dimensionsRe_, ':$1 $4 $3 $2').
      replace(goog.i18n.bidi.leftRe_, '%%%%').          // swap left and right
      replace(goog.i18n.bidi.rightRe_, goog.i18n.bidi.LEFT).
      replace(goog.i18n.bidi.tempRe_, goog.i18n.bidi.RIGHT);
};


/**
 * Regular expression for hebrew double quote substitution, finding quote
 * directly after hebrew characters.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.doubleQuoteSubstituteRe_ = /([\u0591-\u05f2])"/g;


/**
 * Regular expression for hebrew single quote substitution, finding quote
 * directly after hebrew characters.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.singleQuoteSubstituteRe_ = /([\u0591-\u05f2])'/g;


/**
 * Replace the double and single quote directly after a Hebrew character with
 * GERESH and GERSHAYIM. In such case, most likely that's user intention.
 * @param {string} str String that need to be processed.
 * @return {string} Processed string with double/single quote replaced.
 */
goog.i18n.bidi.normalizeHebrewQuote = function(str) {
  return str.
      replace(goog.i18n.bidi.doubleQuoteSubstituteRe_, '$1\u05f4').
      replace(goog.i18n.bidi.singleQuoteSubstituteRe_, '$1\u05f3');
};


/**
 * Regular expression to split a string into "words" for directionality
 * estimation based on relative word counts.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.wordSeparatorRe_ = /\s+/;


/**
 * Regular expression to check if a string contains any numerals. Used to
 * differentiate between completely neutral strings and those containing
 * numbers, which are weakly LTR.
 * @type {RegExp}
 * @private
 */
goog.i18n.bidi.hasNumeralsRe_ = /\d/;


/**
 * This constant controls threshold of RTL directionality.
 * @type {number}
 * @private
 */
goog.i18n.bidi.rtlDetectionThreshold_ = 0.40;


/**
 * Estimates the directionality of a string based on relative word counts.
 * If the number of RTL words is above a certain percentage of the total number
 * of strongly directional words, returns RTL.
 * Otherwise, if any words are strongly or weakly LTR, returns LTR.
 * Otherwise, returns UNKNOWN, which is used to mean "neutral".
 * Numbers are counted as weakly LTR.
 * @param {string} str The string to be checked.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {goog.i18n.bidi.Dir} Estimated overall directionality of {@code str}.
 */
goog.i18n.bidi.estimateDirection = function(str, opt_isHtml) {
  var rtlCount = 0;
  var totalCount = 0;
  var hasWeaklyLtr = false;
  var tokens = goog.i18n.bidi.stripHtmlIfNeeded_(str, opt_isHtml).
      split(goog.i18n.bidi.wordSeparatorRe_);
  for (var i = 0; i < tokens.length; i++) {
    var token = tokens[i];
    if (goog.i18n.bidi.startsWithRtl(token)) {
      rtlCount++;
      totalCount++;
    } else if (goog.i18n.bidi.isRequiredLtrRe_.test(token)) {
      hasWeaklyLtr = true;
    } else if (goog.i18n.bidi.hasAnyLtr(token)) {
      totalCount++;
    } else if (goog.i18n.bidi.hasNumeralsRe_.test(token)) {
      hasWeaklyLtr = true;
    }
  }

  return totalCount == 0 ?
      (hasWeaklyLtr ? goog.i18n.bidi.Dir.LTR : goog.i18n.bidi.Dir.UNKNOWN) :
      (rtlCount / totalCount > goog.i18n.bidi.rtlDetectionThreshold_ ?
          goog.i18n.bidi.Dir.RTL : goog.i18n.bidi.Dir.LTR);
};


/**
 * Check the directionality of a piece of text, return true if the piece of
 * text should be laid out in RTL direction.
 * @param {string} str The piece of text that need to be detected.
 * @param {boolean=} opt_isHtml Whether str is HTML / HTML-escaped.
 *     Default: false.
 * @return {boolean} Whether this piece of text should be laid out in RTL.
 */
goog.i18n.bidi.detectRtlDirectionality = function(str, opt_isHtml) {
  return goog.i18n.bidi.estimateDirection(str, opt_isHtml) ==
      goog.i18n.bidi.Dir.RTL;
};


/**
 * Sets text input element's directionality and text alignment based on a
 * given directionality.
 * @param {Element} element Input field element to set directionality to.
 * @param {goog.i18n.bidi.Dir|number|boolean} dir Desired directionality, given
 *     in one of the following formats:
 *     1. A goog.i18n.bidi.Dir constant.
 *     2. A number (positive = LRT, negative = RTL, 0 = unknown).
 *     3. A boolean (true = RTL, false = LTR).
 */
goog.i18n.bidi.setElementDirAndAlign = function(element, dir) {
  if (element &&
      (dir = goog.i18n.bidi.toDir(dir)) != goog.i18n.bidi.Dir.UNKNOWN) {
    element.style.textAlign = dir == goog.i18n.bidi.Dir.RTL ? 'right' : 'left';
    element.dir = dir == goog.i18n.bidi.Dir.RTL ? 'rtl' : 'ltr';
  }
};