summaryrefslogtreecommitdiffstats
path: root/gfx/harfbuzz/src/hb-ot-tag.cc
blob: 547f9573d05fba649ffe5a483a7d2e93ad6103bb (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
/*
 * Copyright © 2009  Red Hat, Inc.
 * Copyright © 2011  Google, Inc.
 *
 *  This is part of HarfBuzz, a text shaping library.
 *
 * Permission is hereby granted, without written agreement and without
 * license or royalty fees, to use, copy, modify, and distribute this
 * software and its documentation for any purpose, provided that the
 * above copyright notice and the following two paragraphs appear in
 * all copies of this software.
 *
 * IN NO EVENT SHALL THE COPYRIGHT HOLDER BE LIABLE TO ANY PARTY FOR
 * DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES
 * ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS DOCUMENTATION, EVEN
 * IF THE COPYRIGHT HOLDER HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH
 * DAMAGE.
 *
 * THE COPYRIGHT HOLDER SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING,
 * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
 * FITNESS FOR A PARTICULAR PURPOSE.  THE SOFTWARE PROVIDED HEREUNDER IS
 * ON AN "AS IS" BASIS, AND THE COPYRIGHT HOLDER HAS NO OBLIGATION TO
 * PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
 *
 * Red Hat Author(s): Behdad Esfahbod
 * Google Author(s): Behdad Esfahbod, Roozbeh Pournader
 */

#include "hb.hh"

#ifndef HB_NO_OT_TAG


/* hb_script_t */

static hb_tag_t
hb_ot_old_tag_from_script (hb_script_t script)
{
  /* This seems to be accurate as of end of 2012. */

  switch ((hb_tag_t) script)
  {
    case HB_SCRIPT_INVALID:		return HB_OT_TAG_DEFAULT_SCRIPT;
    case HB_SCRIPT_MATH:		return HB_OT_TAG_MATH_SCRIPT;

    /* KATAKANA and HIRAGANA both map to 'kana' */
    case HB_SCRIPT_HIRAGANA:		return HB_TAG('k','a','n','a');

    /* Spaces at the end are preserved, unlike ISO 15924 */
    case HB_SCRIPT_LAO:			return HB_TAG('l','a','o',' ');
    case HB_SCRIPT_YI:			return HB_TAG('y','i',' ',' ');
    /* Unicode-5.0 additions */
    case HB_SCRIPT_NKO:			return HB_TAG('n','k','o',' ');
    /* Unicode-5.1 additions */
    case HB_SCRIPT_VAI:			return HB_TAG('v','a','i',' ');
  }

  /* Else, just change first char to lowercase and return */
  return ((hb_tag_t) script) | 0x20000000u;
}

static hb_script_t
hb_ot_old_tag_to_script (hb_tag_t tag)
{
  if (unlikely (tag == HB_OT_TAG_DEFAULT_SCRIPT))
    return HB_SCRIPT_INVALID;
  if (unlikely (tag == HB_OT_TAG_MATH_SCRIPT))
    return HB_SCRIPT_MATH;

  /* This side of the conversion is fully algorithmic. */

  /* Any spaces at the end of the tag are replaced by repeating the last
   * letter.  Eg 'nko ' -> 'Nkoo' */
  if (unlikely ((tag & 0x0000FF00u) == 0x00002000u))
    tag |= (tag >> 8) & 0x0000FF00u; /* Copy second letter to third */
  if (unlikely ((tag & 0x000000FFu) == 0x00000020u))
    tag |= (tag >> 8) & 0x000000FFu; /* Copy third letter to fourth */

  /* Change first char to uppercase and return */
  return (hb_script_t) (tag & ~0x20000000u);
}

static hb_tag_t
hb_ot_new_tag_from_script (hb_script_t script)
{
  switch ((hb_tag_t) script) {
    case HB_SCRIPT_BENGALI:		return HB_TAG('b','n','g','2');
    case HB_SCRIPT_DEVANAGARI:		return HB_TAG('d','e','v','2');
    case HB_SCRIPT_GUJARATI:		return HB_TAG('g','j','r','2');
    case HB_SCRIPT_GURMUKHI:		return HB_TAG('g','u','r','2');
    case HB_SCRIPT_KANNADA:		return HB_TAG('k','n','d','2');
    case HB_SCRIPT_MALAYALAM:		return HB_TAG('m','l','m','2');
    case HB_SCRIPT_ORIYA:		return HB_TAG('o','r','y','2');
    case HB_SCRIPT_TAMIL:		return HB_TAG('t','m','l','2');
    case HB_SCRIPT_TELUGU:		return HB_TAG('t','e','l','2');
    case HB_SCRIPT_MYANMAR:		return HB_TAG('m','y','m','2');
  }

  return HB_OT_TAG_DEFAULT_SCRIPT;
}

static hb_script_t
hb_ot_new_tag_to_script (hb_tag_t tag)
{
  switch (tag) {
    case HB_TAG('b','n','g','2'):	return HB_SCRIPT_BENGALI;
    case HB_TAG('d','e','v','2'):	return HB_SCRIPT_DEVANAGARI;
    case HB_TAG('g','j','r','2'):	return HB_SCRIPT_GUJARATI;
    case HB_TAG('g','u','r','2'):	return HB_SCRIPT_GURMUKHI;
    case HB_TAG('k','n','d','2'):	return HB_SCRIPT_KANNADA;
    case HB_TAG('m','l','m','2'):	return HB_SCRIPT_MALAYALAM;
    case HB_TAG('o','r','y','2'):	return HB_SCRIPT_ORIYA;
    case HB_TAG('t','m','l','2'):	return HB_SCRIPT_TAMIL;
    case HB_TAG('t','e','l','2'):	return HB_SCRIPT_TELUGU;
    case HB_TAG('m','y','m','2'):	return HB_SCRIPT_MYANMAR;
  }

  return HB_SCRIPT_UNKNOWN;
}

#ifndef HB_DISABLE_DEPRECATED
/**
 * hb_ot_tags_from_script:
 * @script: an #hb_script_t to convert.
 * @script_tag_1: (out): output #hb_tag_t.
 * @script_tag_2: (out): output #hb_tag_t.
 *
 * Converts an #hb_script_t to script tags.
 *
 * Since: 0.6.0
 * Deprecated: 2.0.0: use hb_ot_tags_from_script_and_language() instead
 **/
void
hb_ot_tags_from_script (hb_script_t  script,
			hb_tag_t    *script_tag_1,
			hb_tag_t    *script_tag_2)
{
  unsigned int count = 2;
  hb_tag_t tags[2];
  hb_ot_tags_from_script_and_language (script, HB_LANGUAGE_INVALID, &count, tags, nullptr, nullptr);
  *script_tag_1 = count > 0 ? tags[0] : HB_OT_TAG_DEFAULT_SCRIPT;
  *script_tag_2 = count > 1 ? tags[1] : HB_OT_TAG_DEFAULT_SCRIPT;
}
#endif

/*
 * Complete list at:
 * https://docs.microsoft.com/en-us/typography/opentype/spec/scripttags
 *
 * Most of the script tags are the same as the ISO 15924 tag but lowercased.
 * So we just do that, and handle the exceptional cases in a switch.
 */

static void
hb_ot_all_tags_from_script (hb_script_t   script,
			    unsigned int *count /* IN/OUT */,
			    hb_tag_t     *tags /* OUT */)
{
  unsigned int i = 0;

  hb_tag_t new_tag = hb_ot_new_tag_from_script (script);
  if (unlikely (new_tag != HB_OT_TAG_DEFAULT_SCRIPT))
  {
    /* HB_SCRIPT_MYANMAR maps to 'mym2', but there is no 'mym3'. */
    if (new_tag != HB_TAG('m','y','m','2'))
      tags[i++] = new_tag | '3';
    if (*count > i)
      tags[i++] = new_tag;
  }

  if (*count > i)
  {
    hb_tag_t old_tag = hb_ot_old_tag_from_script (script);
    if (old_tag != HB_OT_TAG_DEFAULT_SCRIPT)
      tags[i++] = old_tag;
  }

  *count = i;
}

/**
 * hb_ot_tag_to_script:
 * @tag: a script tag
 *
 * Converts a script tag to an #hb_script_t.
 *
 * Return value: The #hb_script_t corresponding to @tag.
 *
 **/
hb_script_t
hb_ot_tag_to_script (hb_tag_t tag)
{
  unsigned char digit = tag & 0x000000FFu;
  if (unlikely (digit == '2' || digit == '3'))
    return hb_ot_new_tag_to_script (tag & 0xFFFFFF32);

  return hb_ot_old_tag_to_script (tag);
}


/* hb_language_t */

static inline bool
subtag_matches (const char *lang_str,
		const char *limit,
		const char *subtag,
		unsigned    subtag_len)
{
  if (likely ((unsigned) (limit - lang_str) < subtag_len))
    return false;

  do {
    const char *s = strstr (lang_str, subtag);
    if (!s || s >= limit)
      return false;
    if (!ISALNUM (s[subtag_len]))
      return true;
    lang_str = s + subtag_len;
  } while (true);
}

static bool
lang_matches (const char *lang_str,
	      const char *limit,
	      const char *spec,
	      unsigned    spec_len)
{
  /* Same as hb_language_matches(); duplicated. */

  if (likely ((unsigned) (limit - lang_str) < spec_len))
    return false;

  return strncmp (lang_str, spec, spec_len) == 0 &&
	 (lang_str[spec_len] == '\0' || lang_str[spec_len] == '-');
}

struct LangTag
{
  hb_tag_t language;
  hb_tag_t tag;

  int cmp (hb_tag_t a) const
  {
    return a < this->language ? -1 : a > this->language ? +1 : 0;
  }
  int cmp (const LangTag *that) const
  { return cmp (that->language); }
};

#include "hb-ot-tag-table.hh"

/* The corresponding languages IDs for the following IDs are unclear,
 * overlap, or are architecturally weird. Needs more research. */

/*{"??",	{HB_TAG('B','C','R',' ')}},*/	/* Bible Cree */
/*{"zh?",	{HB_TAG('C','H','N',' ')}},*/	/* Chinese (seen in Microsoft fonts) */
/*{"ar-Syrc?",	{HB_TAG('G','A','R',' ')}},*/	/* Garshuni */
/*{"??",	{HB_TAG('N','G','R',' ')}},*/	/* Nagari */
/*{"??",	{HB_TAG('Y','I','C',' ')}},*/	/* Yi Classic */
/*{"zh?",	{HB_TAG('Z','H','P',' ')}},*/	/* Chinese Phonetic */

#ifndef HB_DISABLE_DEPRECATED
/**
 * hb_ot_tag_from_language:
 * @language: an #hb_language_t to convert.
 *
 * Converts an #hb_language_t to an #hb_tag_t.
 *
 * Since: 0.6.0
 * Deprecated: 2.0.0: use hb_ot_tags_from_script_and_language() instead
 **/
hb_tag_t
hb_ot_tag_from_language (hb_language_t language)
{
  unsigned int count = 1;
  hb_tag_t tags[1];
  hb_ot_tags_from_script_and_language (HB_SCRIPT_UNKNOWN, language, nullptr, nullptr, &count, tags);
  return count > 0 ? tags[0] : HB_OT_TAG_DEFAULT_LANGUAGE;
}
#endif

static void
hb_ot_tags_from_language (const char   *lang_str,
			  const char   *limit,
			  unsigned int *count,
			  hb_tag_t     *tags)
{

#ifndef HB_NO_LANGUAGE_LONG
  /* Check for matches of multiple subtags. */
  if (hb_ot_tags_from_complex_language (lang_str, limit, count, tags))
    return;
#endif

  /* Find a language matching in the first component. */
#ifndef HB_NO_LANGUAGE_LONG
  const char *s; s = strchr (lang_str, '-');
#endif
  {
#ifndef HB_NO_LANGUAGE_LONG
    if (s && limit - lang_str >= 6)
    {
      const char *extlang_end = strchr (s + 1, '-');
      /* If there is an extended language tag, use it. */
      if (3 == (extlang_end ? extlang_end - s - 1 : strlen (s + 1)) &&
	  ISALPHA (s[1]))
	lang_str = s + 1;
    }
#endif
    const LangTag *ot_languages = nullptr;
    unsigned ot_languages_len = 0;
    const char *dash = strchr (lang_str, '-');
    unsigned first_len = dash ? dash - lang_str : limit - lang_str;
    if (first_len == 2)
    {
      ot_languages = ot_languages2;
      ot_languages_len = ARRAY_LENGTH (ot_languages2);
    }
#ifndef HB_NO_LANGUAGE_LONG
    else if (first_len == 3)
    {
      ot_languages = ot_languages3;
      ot_languages_len = ARRAY_LENGTH (ot_languages3);
    }
#endif

    hb_tag_t lang_tag = hb_tag_from_string (lang_str, first_len);

    static hb_atomic_int_t last_tag_idx; /* Poor man's cache. */
    unsigned tag_idx = last_tag_idx;

    if (likely (tag_idx < ot_languages_len && ot_languages[tag_idx].language == lang_tag) ||
	hb_sorted_array (ot_languages, ot_languages_len).bfind (lang_tag, &tag_idx))
    {
      last_tag_idx = tag_idx;
      unsigned int i;
      while (tag_idx != 0 &&
	     ot_languages[tag_idx].language == ot_languages[tag_idx - 1].language)
	tag_idx--;
      for (i = 0;
	   i < *count &&
	   tag_idx + i < ot_languages_len &&
	   ot_languages[tag_idx + i].tag != HB_TAG_NONE &&
	   ot_languages[tag_idx + i].language == ot_languages[tag_idx].language;
	   i++)
	tags[i] = ot_languages[tag_idx + i].tag;
      *count = i;
      return;
    }
  }

#ifndef HB_NO_LANGUAGE_LONG
  if (!s)
    s = lang_str + strlen (lang_str);
  if (s - lang_str == 3) {
    /* Assume it's ISO-639-3 and upper-case and use it. */
    tags[0] = hb_tag_from_string (lang_str, s - lang_str) & ~0x20202000u;
    *count = 1;
    return;
  }
#endif

  *count = 0;
}

static bool
parse_private_use_subtag (const char     *private_use_subtag,
			  unsigned int   *count,
			  hb_tag_t       *tags,
			  const char     *prefix,
			  unsigned char (*normalize) (unsigned char))
{
#ifdef HB_NO_LANGUAGE_PRIVATE_SUBTAG
  return false;
#endif

  if (!(private_use_subtag && count && tags && *count)) return false;

  const char *s = strstr (private_use_subtag, prefix);
  if (!s) return false;

  char tag[4];
  int i;
  s += strlen (prefix);
  if (s[0] == '-') {
    s += 1;
    char c;
    for (i = 0; i < 8 && ISHEX (s[i]); i++)
    {
      c = FROMHEX (s[i]);
      if (i % 2 == 0)
	tag[i / 2] = c << 4;
      else
	tag[i / 2] += c;
    }
    if (i != 8) return false;
  } else {
    for (i = 0; i < 4 && ISALNUM (s[i]); i++)
      tag[i] = normalize (s[i]);
    if (!i) return false;

    for (; i < 4; i++)
      tag[i] = ' ';
  }
  tags[0] = HB_TAG (tag[0], tag[1], tag[2], tag[3]);
  if ((tags[0] & 0xDFDFDFDF) == HB_OT_TAG_DEFAULT_SCRIPT)
    tags[0] ^= ~0xDFDFDFDF;
  *count = 1;
  return true;
}

/**
 * hb_ot_tags_from_script_and_language:
 * @script: an #hb_script_t to convert.
 * @language: an #hb_language_t to convert.
 * @script_count: (inout) (optional): maximum number of script tags to retrieve (IN)
 * and actual number of script tags retrieved (OUT)
 * @script_tags: (out) (optional): array of size at least @script_count to store the
 * script tag results
 * @language_count: (inout) (optional): maximum number of language tags to retrieve
 * (IN) and actual number of language tags retrieved (OUT)
 * @language_tags: (out) (optional): array of size at least @language_count to store
 * the language tag results
 *
 * Converts an #hb_script_t and an #hb_language_t to script and language tags.
 *
 * Since: 2.0.0
 **/
void
hb_ot_tags_from_script_and_language (hb_script_t   script,
				     hb_language_t language,
				     unsigned int *script_count /* IN/OUT */,
				     hb_tag_t     *script_tags /* OUT */,
				     unsigned int *language_count /* IN/OUT */,
				     hb_tag_t     *language_tags /* OUT */)
{
  bool needs_script = true;

  if (language == HB_LANGUAGE_INVALID)
  {
    if (language_count && language_tags && *language_count)
      *language_count = 0;
  }
  else
  {
    const char *lang_str, *s, *limit, *private_use_subtag;
    bool needs_language;

    lang_str = hb_language_to_string (language);
    limit = nullptr;
    private_use_subtag = nullptr;
    if (lang_str[0] == 'x' && lang_str[1] == '-')
    {
      private_use_subtag = lang_str;
    } else {
      for (s = lang_str + 1; *s; s++)
      {
	if (s[-1] == '-' && s[1] == '-')
	{
	  if (s[0] == 'x')
	  {
	    private_use_subtag = s;
	    if (!limit)
	      limit = s - 1;
	    break;
	  } else if (!limit)
	  {
	    limit = s - 1;
	  }
	}
      }
      if (!limit)
	limit = s;
    }

    needs_script = !parse_private_use_subtag (private_use_subtag, script_count, script_tags, "-hbsc", TOLOWER);
    needs_language = !parse_private_use_subtag (private_use_subtag, language_count, language_tags, "-hbot", TOUPPER);

    if (needs_language && language_count && language_tags && *language_count)
      hb_ot_tags_from_language (lang_str, limit, language_count, language_tags);
  }

  if (needs_script && script_count && script_tags && *script_count)
    hb_ot_all_tags_from_script (script, script_count, script_tags);
}

/**
 * hb_ot_tag_to_language:
 * @tag: an language tag
 *
 * Converts a language tag to an #hb_language_t.
 *
 * Return value: (transfer none) (nullable):
 * The #hb_language_t corresponding to @tag.
 *
 * Since: 0.9.2
 **/
hb_language_t
hb_ot_tag_to_language (hb_tag_t tag)
{
  unsigned int i;

  if (tag == HB_OT_TAG_DEFAULT_LANGUAGE)
    return nullptr;

#ifndef HB_NO_LANGUAGE_LONG
  {
    hb_language_t disambiguated_tag = hb_ot_ambiguous_tag_to_language (tag);
    if (disambiguated_tag != HB_LANGUAGE_INVALID)
      return disambiguated_tag;
  }
#endif

  char buf[4];
  for (i = 0; i < ARRAY_LENGTH (ot_languages2); i++)
    if (ot_languages2[i].tag == tag)
    {
      hb_tag_to_string (ot_languages2[i].language, buf);
      return hb_language_from_string (buf, 2);
    }
#ifndef HB_NO_LANGUAGE_LONG
  for (i = 0; i < ARRAY_LENGTH (ot_languages3); i++)
    if (ot_languages3[i].tag == tag)
    {
      hb_tag_to_string (ot_languages3[i].language, buf);
      return hb_language_from_string (buf, 3);
    }
#endif

  /* Return a custom language in the form of "x-hbot-AABBCCDD".
   * If it's three letters long, also guess it's ISO 639-3 and lower-case and
   * prepend it (if it's not a registered tag, the private use subtags will
   * ensure that calling hb_ot_tag_from_language on the result will still return
   * the same tag as the original tag).
   */
  {
    char buf[20];
    char *str = buf;
    if (ISALPHA (tag >> 24)
	&& ISALPHA ((tag >> 16) & 0xFF)
	&& ISALPHA ((tag >> 8) & 0xFF)
	&& (tag & 0xFF) == ' ')
    {
      buf[0] = TOLOWER (tag >> 24);
      buf[1] = TOLOWER ((tag >> 16) & 0xFF);
      buf[2] = TOLOWER ((tag >> 8) & 0xFF);
      buf[3] = '-';
      str += 4;
    }
    snprintf (str, 16, "x-hbot-%08x", tag);
    return hb_language_from_string (&*buf, -1);
  }
}

/**
 * hb_ot_tags_to_script_and_language:
 * @script_tag: a script tag
 * @language_tag: a language tag
 * @script: (out) (optional): the #hb_script_t corresponding to @script_tag.
 * @language: (out) (optional): the #hb_language_t corresponding to @script_tag and
 * @language_tag.
 *
 * Converts a script tag and a language tag to an #hb_script_t and an
 * #hb_language_t.
 *
 * Since: 2.0.0
 **/
void
hb_ot_tags_to_script_and_language (hb_tag_t       script_tag,
				   hb_tag_t       language_tag,
				   hb_script_t   *script /* OUT */,
				   hb_language_t *language /* OUT */)
{
  hb_script_t script_out = hb_ot_tag_to_script (script_tag);
  if (script)
    *script = script_out;
  if (language)
  {
    unsigned int script_count = 1;
    hb_tag_t primary_script_tag[1];
    hb_ot_tags_from_script_and_language (script_out,
					 HB_LANGUAGE_INVALID,
					 &script_count,
					 primary_script_tag,
					 nullptr, nullptr);
    *language = hb_ot_tag_to_language (language_tag);
    if (script_count == 0 || primary_script_tag[0] != script_tag)
    {
      unsigned char *buf;
      const char *lang_str = hb_language_to_string (*language);
      size_t len = strlen (lang_str);
      buf = (unsigned char *) hb_malloc (len + 16);
      if (unlikely (!buf))
      {
	*language = nullptr;
      }
      else
      {
	int shift;
	hb_memcpy (buf, lang_str, len);
	if (lang_str[0] != 'x' || lang_str[1] != '-') {
	  buf[len++] = '-';
	  buf[len++] = 'x';
	}
	buf[len++] = '-';
	buf[len++] = 'h';
	buf[len++] = 'b';
	buf[len++] = 's';
	buf[len++] = 'c';
	buf[len++] = '-';
	for (shift = 28; shift >= 0; shift -= 4)
	  buf[len++] = TOHEX (script_tag >> shift);
	*language = hb_language_from_string ((char *) buf, len);
	hb_free (buf);
      }
    }
  }
}

#ifdef MAIN
static inline void
test_langs_sorted ()
{
  for (unsigned int i = 1; i < ARRAY_LENGTH (ot_languages2); i++)
  {
    int c = ot_languages2[i].cmp (&ot_languages2[i - 1]);
    if (c > 0)
    {
      fprintf (stderr, "ot_languages2 not sorted at index %u: %08x %d %08x\n",
	       i, ot_languages2[i-1].language, c, ot_languages2[i].language);
      abort();
    }
  }
#ifndef HB_NO_LANGUAGE_LONG
  for (unsigned int i = 1; i < ARRAY_LENGTH (ot_languages3); i++)
  {
    int c = ot_languages3[i].cmp (&ot_languages3[i - 1]);
    if (c > 0)
    {
      fprintf (stderr, "ot_languages3 not sorted at index %u: %08x %d %08x\n",
	       i, ot_languages3[i-1].language, c, ot_languages3[i].language);
      abort();
    }
  }
#endif
}

int
main ()
{
  test_langs_sorted ();
  return 0;
}

#endif


#endif