summaryrefslogtreecommitdiff
path: root/src/static_libs/liblinebreak/linebreak.c
blob: f9ff9a1f14ce280bcecdbc3e2d10311cb3a90178 (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
/* vim: set tabstop=4 shiftwidth=4: */

/*
 * Line breaking in a Unicode sequence.  Designed to be used in a
 * generic text renderer.
 *
 * Copyright (C) 2008-2010 Wu Yongwei <wuyongwei at gmail dot com>
 *
 * This software is provided 'as-is', without any express or implied
 * warranty.  In no event will the author be held liable for any damages
 * arising from the use of this software.
 *
 * Permission is granted to anyone to use this software for any purpose,
 * including commercial applications, and to alter it and redistribute
 * it freely, subject to the following restrictions:
 *
 * 1. The origin of this software must not be misrepresented; you must
 *    not claim that you wrote the original software.  If you use this
 *    software in a product, an acknowledgement in the product
 *    documentation would be appreciated but is not required.
 * 2. Altered source versions must be plainly marked as such, and must
 *    not be misrepresented as being the original software.
 * 3. This notice may not be removed or altered from any source
 *    distribution.
 *
 * The main reference is Unicode Standard Annex 14 (UAX #14):
 *		<URL:http://www.unicode.org/reports/tr14/>
 *
 * When this library was designed, this annex was at Revision 19, for
 * Unicode 5.0.0:
 *		<URL:http://www.unicode.org/reports/tr14/tr14-19.html>
 *
 * This library has been updated according to Revision 24, for
 * Unicode 5.2.0:
 *		<URL:http://www.unicode.org/reports/tr14/tr14-24.html>
 *
 * The Unicode Terms of Use are available at
 *		<URL:http://www.unicode.org/copyright.html>
 */

/**
 * @file	linebreak.c
 *
 * Implementation of the line breaking algorithm as described in Unicode
 * Standard Annex 14.
 *
 * @version	2.0, 2010/01/03
 * @author	Wu Yongwei
 */

#include <assert.h>
#include <stddef.h>
#include <string.h>
#include "linebreak.h"
#include "linebreakdef.h"

/**
 * Size of the second-level index to the line breaking properties.
 */
#define LINEBREAK_INDEX_SIZE 40

/**
 * Version number of the library.
 */
const int linebreak_version = LINEBREAK_VERSION;

/**
 * Enumeration of break actions.  They are used in the break action
 * pair table below.
 */
enum BreakAction
{
	DIR_BRK,		/**< Direct break opportunity */
	IND_BRK,		/**< Indirect break opportunity */
	CMI_BRK,		/**< Indirect break opportunity for combining marks */
	CMP_BRK,		/**< Prohibited break for combining marks */
	PRH_BRK			/**< Prohibited break */
};

/**
 * Break action pair table.  This is a direct mapping of Table 2 of
 * Unicode Standard Annex 14, Revision 24.
 */
static enum BreakAction baTable[LBP_JT][LBP_JT] = {
	{	/* OP */
		PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, CMP_BRK,
		PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK, PRH_BRK },
	{	/* CL */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, PRH_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* CP */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, PRH_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* QU */
		PRH_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK,
		IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK },
	{	/* GL */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK,
		IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK },
	{	/* NS */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* EX */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* SY */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* IS */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, IND_BRK, IND_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* PR */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, IND_BRK, IND_BRK, IND_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK },
	{	/* PO */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, IND_BRK, IND_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* NU */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* AL */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, IND_BRK, IND_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* ID */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* IN */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* HY */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, DIR_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* BA */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, DIR_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* BB */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK,
		IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK },
	{	/* B2 */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, IND_BRK, IND_BRK, DIR_BRK, PRH_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* ZW */
		DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, PRH_BRK, DIR_BRK,
		DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* CM */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, DIR_BRK, IND_BRK, IND_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK },
	{	/* WJ */
		IND_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK,
		IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK },
	{	/* H2 */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, IND_BRK, IND_BRK },
	{	/* H3 */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, IND_BRK },
	{	/* JL */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, IND_BRK, IND_BRK, IND_BRK, IND_BRK, DIR_BRK },
	{	/* JV */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, IND_BRK, IND_BRK },
	{	/* JT */
		DIR_BRK, PRH_BRK, PRH_BRK, IND_BRK, IND_BRK, IND_BRK, PRH_BRK,
		PRH_BRK, PRH_BRK, DIR_BRK, IND_BRK, DIR_BRK, DIR_BRK, DIR_BRK,
		IND_BRK, IND_BRK, IND_BRK, DIR_BRK, DIR_BRK, PRH_BRK, CMI_BRK,
		PRH_BRK, DIR_BRK, DIR_BRK, DIR_BRK, DIR_BRK, IND_BRK }
};

/**
 * Struct for the second-level index to the line breaking properties.
 */
struct LineBreakPropertiesIndex
{
	utf32_t end;					/**< End coding point */
	struct LineBreakProperties *lbp;/**< Pointer to line breaking properties */
};

/**
 * Second-level index to the line breaking properties.
 */
static struct LineBreakPropertiesIndex lb_prop_index[LINEBREAK_INDEX_SIZE] =
{
	{ 0xFFFFFFFF, lb_prop_default }
};

/**
 * Initializes the second-level index to the line breaking properties.
 * If it is not called, the performance of #get_char_lb_class_lang (and
 * thus the main functionality) can be pretty bad, especially for big
 * code points like those of Chinese.
 */
void init_linebreak(void)
{
	size_t i;
	size_t iPropDefault;
	size_t len;
	size_t step;

	len = 0;
	while (lb_prop_default[len].prop != LBP_Undefined)
		++len;
	step = len / LINEBREAK_INDEX_SIZE;
	iPropDefault = 0;
	for (i = 0; i < LINEBREAK_INDEX_SIZE; ++i)
	{
		lb_prop_index[i].lbp = lb_prop_default + iPropDefault;
		iPropDefault += step;
		lb_prop_index[i].end = lb_prop_default[iPropDefault].start - 1;
	}
	lb_prop_index[--i].end = 0xFFFFFFFF;
}

/**
 * Gets the language-specific line breaking properties.
 *
 * @param lang	language of the text
 * @return		pointer to the language-specific line breaking
 *				properties array if found; \c NULL otherwise
 */
static struct LineBreakProperties *get_lb_prop_lang(const char *lang)
{
	struct LineBreakPropertiesLang *lbplIter;
	if (lang != NULL)
	{
		for (lbplIter = lb_prop_lang_map; lbplIter->lang != NULL; ++lbplIter)
		{
			if (strncmp(lang, lbplIter->lang, lbplIter->namelen) == 0)
			{
				return lbplIter->lbp;
			}
		}
	}
	return NULL;
}

/**
 * Gets the line breaking class of a character from a line breaking
 * properties array.
 *
 * @param ch	character to check
 * @param lbp	pointer to the line breaking properties array
 * @return		the line breaking class if found; \c LBP_XX otherwise
 */
static enum LineBreakClass get_char_lb_class(
		utf32_t ch,
		struct LineBreakProperties *lbp)
{
	while (lbp->prop != LBP_Undefined && ch >= lbp->start)
	{
		if (ch <= lbp->end)
			return lbp->prop;
		++lbp;
	}
	return LBP_XX;
}

/**
 * Gets the line breaking class of a character from the default line
 * breaking properties array.
 *
 * @param ch	character to check
 * @return		the line breaking class if found; \c LBP_XX otherwise
 */
static enum LineBreakClass get_char_lb_class_default(
		utf32_t ch)
{
	size_t i = 0;
	while (ch > lb_prop_index[i].end)
		++i;
	assert(i < LINEBREAK_INDEX_SIZE);
	return get_char_lb_class(ch, lb_prop_index[i].lbp);
}

/**
 * Gets the line breaking class of a character for a specific
 * language.  This function will check the language-specific data first,
 * and then the default data if there is no language-specific property
 * available for the character.
 *
 * @param ch		character to check
 * @param lbpLang	pointer to the language-specific line breaking
 *					properties array
 * @return			the line breaking class if found; \c LBP_XX
 *					otherwise
 */
static enum LineBreakClass get_char_lb_class_lang(
		utf32_t ch,
		struct LineBreakProperties *lbpLang)
{
	enum LineBreakClass lbcResult;

	/* Find the language-specific line breaking class for a character */
	if (lbpLang)
	{
		lbcResult = get_char_lb_class(ch, lbpLang);
		if (lbcResult != LBP_XX)
			return lbcResult;
	}

	/* Find the generic language-specific line breaking class, if no
	 * language context is provided, or language-specific data are not
	 * available for the specific character in the specified language */
	return get_char_lb_class_default(ch);
}

/**
 * Resolves the line breaking class for certain ambiguous or complicated
 * characters.  They are treated in a simplistic way in this
 * implementation.
 *
 * @param lbc	line breaking class to resolve
 * @param lang	language of the text
 * @return		the resolved line breaking class
 */
static enum LineBreakClass resolve_lb_class(
		enum LineBreakClass lbc,
		const char *lang)
{
	switch (lbc)
	{
	case LBP_AI:
		if (lang != NULL &&
				(strncmp(lang, "zh", 2) == 0 ||	/* Chinese */
				 strncmp(lang, "ja", 2) == 0 ||	/* Japanese */
				 strncmp(lang, "ko", 2) == 0))	/* Korean */
		{
			return LBP_ID;
		}
		/* Fall through */
	case LBP_SA:
	case LBP_SG:
	case LBP_XX:
		return LBP_AL;
	default:
		return lbc;
	}
}

/**
 * Gets the next Unicode character in a UTF-8 sequence.  The index will
 * be advanced to the next complete character, unless the end of string
 * is reached in the middle of a UTF-8 sequence.
 *
 * @param[in]     s		input UTF-8 string
 * @param[in]     len	length of the string in bytes
 * @param[in,out] ip	pointer to the index
 * @return				the Unicode character beginning at the index; or
 *						#EOS if end of input is encountered
 */
utf32_t lb_get_next_char_utf8(
		const utf8_t *s,
		size_t len,
		size_t *ip)
{
	utf8_t ch;
	utf32_t res;

	assert(*ip <= len);
	if (*ip == len)
		return EOS;
	ch = s[*ip];

	if (ch < 0xC2 || ch > 0xF4)
	{	/* One-byte sequence, tail (should not occur), or invalid */
		*ip += 1;
		return ch;
	}
	else if (ch < 0xE0)
	{	/* Two-byte sequence */
		if (*ip + 2 > len)
			return EOS;
		res = ((ch & 0x1F) << 6) + (s[*ip + 1] & 0x3F);
		*ip += 2;
		return res;
	}
	else if (ch < 0xF0)
	{	/* Three-byte sequence */
		if (*ip + 3 > len)
			return EOS;
		res = ((ch & 0x0F) << 12) +
			  ((s[*ip + 1] & 0x3F) << 6) +
			  ((s[*ip + 2] & 0x3F));
		*ip += 3;
		return res;
	}
	else
	{	/* Four-byte sequence */
		if (*ip + 4 > len)
			return EOS;
		res = ((ch & 0x07) << 18) +
			  ((s[*ip + 1] & 0x3F) << 12) +
			  ((s[*ip + 2] & 0x3F) << 6) +
			  ((s[*ip + 3] & 0x3F));
		*ip += 4;
		return res;
	}
}

/**
 * Gets the next Unicode character in a UTF-16 sequence.  The index will
 * be advanced to the next complete character, unless the end of string
 * is reached in the middle of a UTF-16 surrogate pair.
 *
 * @param[in]     s		input UTF-16 string
 * @param[in]     len	length of the string in words
 * @param[in,out] ip	pointer to the index
 * @return				the Unicode character beginning at the index; or
 *						#EOS if end of input is encountered
 */
utf32_t lb_get_next_char_utf16(
		const utf16_t *s,
		size_t len,
		size_t *ip)
{
	utf16_t ch;

	assert(*ip <= len);
	if (*ip == len)
		return EOS;
	ch = s[(*ip)++];

	if (ch < 0xD800 || ch > 0xDBFF)
	{	/* If the character is not a high surrogate */
		return ch;
	}
	if (*ip == len)
	{	/* If the input ends here (an error) */
		--(*ip);
		return EOS;
	}
	if (s[*ip] < 0xDC00 || s[*ip] > 0xDFFF)
	{	/* If the next character is not the low surrogate (an error) */
		return ch;
	}
	/* Return the constructed character and advance the index again */
	return (((utf32_t)ch & 0x3FF) << 10) + (s[(*ip)++] & 0x3FF) + 0x10000;
}

/**
 * Gets the next Unicode character in a UTF-32 sequence.  The index will
 * be advanced to the next character.
 *
 * @param[in]     s		input UTF-32 string
 * @param[in]     len	length of the string in dwords
 * @param[in,out] ip	pointer to the index
 * @return				the Unicode character beginning at the index; or
 *						#EOS if end of input is encountered
 */
utf32_t lb_get_next_char_utf32(
		const utf32_t *s,
		size_t len,
		size_t *ip)
{
	assert(*ip <= len);
	if (*ip == len)
		return EOS;
	return s[(*ip)++];
}

/**
 * Sets the line breaking information for a generic input string.
 *
 * @param[in]  s			input string
 * @param[in]  len			length of the input
 * @param[in]  lang			language of the input
 * @param[out] brks			pointer to the output breaking data,
 *							containing #LINEBREAK_MUSTBREAK,
 *							#LINEBREAK_ALLOWBREAK, #LINEBREAK_NOBREAK,
 *							or #LINEBREAK_INSIDEACHAR
 * @param[in] get_next_char	function to get the next UTF-32 character
 */
void set_linebreaks(
		const void *s,
		size_t len,
		const char *lang,
		char *brks,
		get_next_char_t get_next_char)
{
	utf32_t ch;
	enum LineBreakClass lbcCur;
	enum LineBreakClass lbcNew;
	enum LineBreakClass lbcLast;
	struct LineBreakProperties *lbpLang;
	size_t posCur = 0;
	size_t posLast = 0;

	--posLast;	/* To be ++'d later */
	ch = get_next_char(s, len, &posCur);
	if (ch == EOS)
		return;
	lbpLang = get_lb_prop_lang(lang);
	lbcCur = resolve_lb_class(get_char_lb_class_lang(ch, lbpLang), lang);
	lbcNew = LBP_Undefined;

nextline:

	/* Special treatment for the first character */
	switch (lbcCur)
	{
	case LBP_LF:
	case LBP_NL:
		lbcCur = LBP_BK;
		break;
	case LBP_CB:
		lbcCur = LBP_BA;
		break;
	case LBP_SP:
		lbcCur = LBP_WJ;
		break;
	default:
		break;
	}

	/* Process a line till an explicit break or end of string */
	for (;;)
	{
		for (++posLast; posLast < posCur - 1; ++posLast)
		{
			brks[posLast] = LINEBREAK_INSIDEACHAR;
		}
		assert(posLast == posCur - 1);
		lbcLast = lbcNew;
		ch = get_next_char(s, len, &posCur);
		if (ch == EOS)
			break;
		lbcNew = get_char_lb_class_lang(ch, lbpLang);
		if (lbcCur == LBP_BK || (lbcCur == LBP_CR && lbcNew != LBP_LF))
		{
			brks[posLast] = LINEBREAK_MUSTBREAK;
			lbcCur = resolve_lb_class(lbcNew, lang);
			goto nextline;
		}

		switch (lbcNew)
		{
		case LBP_SP:
			brks[posLast] = LINEBREAK_NOBREAK;
			continue;
		case LBP_BK:
		case LBP_LF:
		case LBP_NL:
			brks[posLast] = LINEBREAK_NOBREAK;
			lbcCur = LBP_BK;
			continue;
		case LBP_CR:
			brks[posLast] = LINEBREAK_NOBREAK;
			lbcCur = LBP_CR;
			continue;
		case LBP_CB:
			brks[posLast] = LINEBREAK_ALLOWBREAK;
			lbcCur = LBP_BA;
			continue;
		default:
			break;
		}

		lbcNew = resolve_lb_class(lbcNew, lang);

		assert(lbcCur <= LBP_JT);
		assert(lbcNew <= LBP_JT);
		switch (baTable[lbcCur - 1][lbcNew - 1])
		{
		case DIR_BRK:
			brks[posLast] = LINEBREAK_ALLOWBREAK;
			break;
		case CMI_BRK:
		case IND_BRK:
			if (lbcLast == LBP_SP)
			{
				brks[posLast] = LINEBREAK_ALLOWBREAK;
			}
			else
			{
				brks[posLast] = LINEBREAK_NOBREAK;
			}
			break;
		case CMP_BRK:
			brks[posLast] = LINEBREAK_NOBREAK;
			if (lbcLast != LBP_SP)
				continue;
			break;
		case PRH_BRK:
			brks[posLast] = LINEBREAK_NOBREAK;
			break;
		}

		lbcCur = lbcNew;
	}

	assert(posLast == posCur - 1 && posCur <= len);
	/* Break after the last character */
	brks[posLast] = LINEBREAK_MUSTBREAK;
	/* When the input contains incomplete sequences */
	while (posCur < len)
	{
		brks[posCur++] = LINEBREAK_INSIDEACHAR;
	}
}

/**
 * Sets the line breaking information for a UTF-8 input string.
 *
 * @param[in]  s	input UTF-8 string
 * @param[in]  len	length of the input
 * @param[in]  lang	language of the input
 * @param[out] brks	pointer to the output breaking data, containing
 *					#LINEBREAK_MUSTBREAK, #LINEBREAK_ALLOWBREAK,
 *					#LINEBREAK_NOBREAK, or #LINEBREAK_INSIDEACHAR
 */
void set_linebreaks_utf8(
		const utf8_t *s,
		size_t len,
		const char *lang,
		char *brks)
{
	set_linebreaks(s, len, lang, brks,
				   (get_next_char_t)lb_get_next_char_utf8);
}

/**
 * Sets the line breaking information for a UTF-16 input string.
 *
 * @param[in]  s	input UTF-16 string
 * @param[in]  len	length of the input
 * @param[in]  lang	language of the input
 * @param[out] brks	pointer to the output breaking data, containing
 *					#LINEBREAK_MUSTBREAK, #LINEBREAK_ALLOWBREAK,
 *					#LINEBREAK_NOBREAK, or #LINEBREAK_INSIDEACHAR
 */
void set_linebreaks_utf16(
		const utf16_t *s,
		size_t len,
		const char *lang,
		char *brks)
{
	set_linebreaks(s, len, lang, brks,
				   (get_next_char_t)lb_get_next_char_utf16);
}

/**
 * Sets the line breaking information for a UTF-32 input string.
 *
 * @param[in]  s	input UTF-32 string
 * @param[in]  len	length of the input
 * @param[in]  lang	language of the input
 * @param[out] brks	pointer to the output breaking data, containing
 *					#LINEBREAK_MUSTBREAK, #LINEBREAK_ALLOWBREAK,
 *					#LINEBREAK_NOBREAK, or #LINEBREAK_INSIDEACHAR
 */
void set_linebreaks_utf32(
		const utf32_t *s,
		size_t len,
		const char *lang,
		char *brks)
{
	set_linebreaks(s, len, lang, brks,
				   (get_next_char_t)lb_get_next_char_utf32);
}

/**
 * Tells whether a line break can occur between two Unicode characters.
 * This is a wrapper function to expose a simple interface.  Generally
 * speaking, it is better to use #set_linebreaks_utf32 instead, since
 * complicated cases involving combining marks, spaces, etc. cannot be
 * correctly processed.
 *
 * @param char1 the first Unicode character
 * @param char2 the second Unicode character
 * @param lang  language of the input
 * @return      one of #LINEBREAK_MUSTBREAK, #LINEBREAK_ALLOWBREAK,
 *				#LINEBREAK_NOBREAK, or #LINEBREAK_INSIDEACHAR
 */
int is_line_breakable(
		utf32_t char1,
		utf32_t char2,
		const char* lang)
{
	utf32_t s[2];
	char brks[2];
	s[0] = char1;
	s[1] = char2;
	set_linebreaks_utf32(s, 2, lang, brks);
	return brks[0];
}