File: utf8proc.c

package info (click to toggle)
bibledit 5.0.764-1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 230,136 kB
  • sloc: xml: 863,336; ansic: 164,208; cpp: 81,648; sh: 4,684; makefile: 406; php: 69
file content (642 lines) | stat: -rw-r--r-- 23,903 bytes parent folder | download | duplicates (2)
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
/* -*- mode: c; c-basic-offset: 2; tab-width: 2; indent-tabs-mode: nil -*- */
/*
 *  Copyright (c) 2009 Public Software Group e. V., Berlin, Germany
 *
 *  Permission is hereby granted, free of charge, to any person obtaining a
 *  copy of this software and associated documentation files (the "Software"),
 *  to deal in the Software without restriction, including without limitation
 *  the rights to use, copy, modify, merge, publish, distribute, sublicense,
 *  and/or sell copies of the Software, and to permit persons to whom the
 *  Software is furnished to do so, subject to the following conditions:
 *
 *  The above copyright notice and this permission notice shall be included in
 *  all copies or substantial portions of the Software.
 *
 *  THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 *  IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 *  FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 *  AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 *  LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 *  FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
 *  DEALINGS IN THE SOFTWARE.
 */

/*
 *  This library contains derived data from a modified version of the
 *  Unicode data files.
 *
 *  The original data files are available at
 *  http://www.unicode.org/Public/UNIDATA/
 *
 *  Please notice the copyright statement in the file "utf8proc_data.c".
 */


/*
 *  File name:    utf8proc.c
 *
 *  Description:
 *  Implementation of libutf8proc.
 */


#include "utf8proc.h"
#include "utf8proc_data.c"


UTF8PROC_DLLEXPORT const utf8proc_int8_t utf8proc_utf8class[256] = {
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
  3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,
  4, 4, 4, 4, 4, 4, 4, 4, 0, 0, 0, 0, 0, 0, 0, 0 };

#define UTF8PROC_HANGUL_SBASE 0xAC00
#define UTF8PROC_HANGUL_LBASE 0x1100
#define UTF8PROC_HANGUL_VBASE 0x1161
#define UTF8PROC_HANGUL_TBASE 0x11A7
#define UTF8PROC_HANGUL_LCOUNT 19
#define UTF8PROC_HANGUL_VCOUNT 21
#define UTF8PROC_HANGUL_TCOUNT 28
#define UTF8PROC_HANGUL_NCOUNT 588
#define UTF8PROC_HANGUL_SCOUNT 11172
/* END is exclusive */
#define UTF8PROC_HANGUL_L_START  0x1100
#define UTF8PROC_HANGUL_L_END    0x115A
#define UTF8PROC_HANGUL_L_FILLER 0x115F
#define UTF8PROC_HANGUL_V_START  0x1160
#define UTF8PROC_HANGUL_V_END    0x11A3
#define UTF8PROC_HANGUL_T_START  0x11A8
#define UTF8PROC_HANGUL_T_END    0x11FA
#define UTF8PROC_HANGUL_S_START  0xAC00
#define UTF8PROC_HANGUL_S_END    0xD7A4

/* Should follow semantic-versioning rules (semver.org) based on API
   compatibility.  (Note that the shared-library version number will
   be different, being based on ABI compatibility.): */
#define STRINGIZEx(x) #x
#define STRINGIZE(x) STRINGIZEx(x)
UTF8PROC_DLLEXPORT const char *utf8proc_version(void) {
  return STRINGIZE(UTF8PROC_VERSION_MAJOR) "." STRINGIZE(UTF8PROC_VERSION_MINOR) "." STRINGIZE(UTF8PROC_VERSION_PATCH) "";
}

UTF8PROC_DLLEXPORT const char *utf8proc_errmsg(utf8proc_ssize_t errcode) {
  switch (errcode) {
    case UTF8PROC_ERROR_NOMEM:
    return "Memory for processing UTF-8 data could not be allocated.";
    case UTF8PROC_ERROR_OVERFLOW:
    return "UTF-8 string is too long to be processed.";
    case UTF8PROC_ERROR_INVALIDUTF8:
    return "Invalid UTF-8 string";
    case UTF8PROC_ERROR_NOTASSIGNED:
    return "Unassigned Unicode code point found in UTF-8 string.";
    case UTF8PROC_ERROR_INVALIDOPTS:
    return "Invalid options for UTF-8 processing chosen.";
    default:
    return "An unknown error occurred while processing UTF-8 data.";
  }
}

#define utf_cont(ch)  (((ch) & 0xc0) == 0x80)
UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_iterate(
  const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_int32_t *dst
) {
  utf8proc_uint32_t uc;
  const utf8proc_uint8_t *end;

  *dst = -1;
  if (!strlen) return 0;
  end = str + ((strlen < 0) ? 4 : strlen);
  uc = *str++;
  if (uc < 0x80) {
    *dst = uc;
    return 1;
  }
  // Must be between 0xc2 and 0xf4 inclusive to be valid
  if ((uc - 0xc2) > (0xf4-0xc2)) return UTF8PROC_ERROR_INVALIDUTF8;
  if (uc < 0xe0) {         // 2-byte sequence
     // Must have valid continuation character
     if (!utf_cont(*str)) return UTF8PROC_ERROR_INVALIDUTF8;
     *dst = ((uc & 0x1f)<<6) | (*str & 0x3f);
     return 2;
  }
  if (uc < 0xf0) {        // 3-byte sequence
     if ((str + 1 >= end) || !utf_cont(*str) || !utf_cont(str[1]))
        return UTF8PROC_ERROR_INVALIDUTF8;
     // Check for surrogate chars
     if (uc == 0xed && *str > 0x9f)
         return UTF8PROC_ERROR_INVALIDUTF8;
     uc = ((uc & 0xf)<<12) | ((*str & 0x3f)<<6) | (str[1] & 0x3f);
     if (uc < 0x800)
         return UTF8PROC_ERROR_INVALIDUTF8;
     *dst = uc;
     return 3;
  }
  // 4-byte sequence
  // Must have 3 valid continuation characters
  if ((str + 2 >= end) || !utf_cont(*str) || !utf_cont(str[1]) || !utf_cont(str[2]))
     return UTF8PROC_ERROR_INVALIDUTF8;
  // Make sure in correct range (0x10000 - 0x10ffff)
  if (uc == 0xf0) {
    if (*str < 0x90) return UTF8PROC_ERROR_INVALIDUTF8;
  } else if (uc == 0xf4) {
    if (*str > 0x8f) return UTF8PROC_ERROR_INVALIDUTF8;
  }
  *dst = ((uc & 7)<<18) | ((*str & 0x3f)<<12) | ((str[1] & 0x3f)<<6) | (str[2] & 0x3f);
  return 4;
}

UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_codepoint_valid(utf8proc_int32_t uc) {
    return (((utf8proc_uint32_t)uc)-0xd800 > 0x07ff) && ((utf8proc_uint32_t)uc < 0x110000);
}

UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
  if (uc < 0x00) {
    return 0;
  } else if (uc < 0x80) {
    dst[0] = uc;
    return 1;
  } else if (uc < 0x800) {
    dst[0] = 0xC0 + (uc >> 6);
    dst[1] = 0x80 + (uc & 0x3F);
    return 2;
  // Note: we allow encoding 0xd800-0xdfff here, so as not to change
  // the API, however, these are actually invalid in UTF-8
  } else if (uc < 0x10000) {
    dst[0] = 0xE0 + (uc >> 12);
    dst[1] = 0x80 + ((uc >> 6) & 0x3F);
    dst[2] = 0x80 + (uc & 0x3F);
    return 3;
  } else if (uc < 0x110000) {
    dst[0] = 0xF0 + (uc >> 18);
    dst[1] = 0x80 + ((uc >> 12) & 0x3F);
    dst[2] = 0x80 + ((uc >> 6) & 0x3F);
    dst[3] = 0x80 + (uc & 0x3F);
    return 4;
  } else return 0;
}

/* internal "unsafe" version that does not check whether uc is in range */
static utf8proc_ssize_t unsafe_encode_char(utf8proc_int32_t uc, utf8proc_uint8_t *dst) {
   if (uc < 0x00) {
      return 0;
   } else if (uc < 0x80) {
      dst[0] = uc;
      return 1;
   } else if (uc < 0x800) {
      dst[0] = 0xC0 + (uc >> 6);
      dst[1] = 0x80 + (uc & 0x3F);
      return 2;
   } else if (uc == 0xFFFF) {
       dst[0] = 0xFF;
       return 1;
   } else if (uc == 0xFFFE) {
       dst[0] = 0xFE;
       return 1;
   } else if (uc < 0x10000) {
      dst[0] = 0xE0 + (uc >> 12);
      dst[1] = 0x80 + ((uc >> 6) & 0x3F);
      dst[2] = 0x80 + (uc & 0x3F);
      return 3;
   } else if (uc < 0x110000) {
      dst[0] = 0xF0 + (uc >> 18);
      dst[1] = 0x80 + ((uc >> 12) & 0x3F);
      dst[2] = 0x80 + ((uc >> 6) & 0x3F);
      dst[3] = 0x80 + (uc & 0x3F);
      return 4;
   } else return 0;
}

/* internal "unsafe" version that does not check whether uc is in range */
static const utf8proc_property_t *unsafe_get_property(utf8proc_int32_t uc) {
  /* ASSERT: uc >= 0 && uc < 0x110000 */
  return utf8proc_properties + (
    utf8proc_stage2table[
      utf8proc_stage1table[uc >> 8] + (uc & 0xFF)
    ]
  );
}

UTF8PROC_DLLEXPORT const utf8proc_property_t *utf8proc_get_property(utf8proc_int32_t uc) {
  return uc < 0 || uc >= 0x110000 ? utf8proc_properties : unsafe_get_property(uc);
}

/* return whether there is a grapheme break between boundclasses lbc and tbc */
static utf8proc_bool grapheme_break(int lbc, int tbc) {
  return 
    (lbc == UTF8PROC_BOUNDCLASS_START) ? true :
    (lbc == UTF8PROC_BOUNDCLASS_CR &&
     tbc == UTF8PROC_BOUNDCLASS_LF) ? false :
    (lbc >= UTF8PROC_BOUNDCLASS_CR && lbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true :
    (tbc >= UTF8PROC_BOUNDCLASS_CR && tbc <= UTF8PROC_BOUNDCLASS_CONTROL) ? true :
    (tbc == UTF8PROC_BOUNDCLASS_EXTEND) ? false :
    (lbc == UTF8PROC_BOUNDCLASS_L &&
     (tbc == UTF8PROC_BOUNDCLASS_L ||
      tbc == UTF8PROC_BOUNDCLASS_V ||
      tbc == UTF8PROC_BOUNDCLASS_LV ||
      tbc == UTF8PROC_BOUNDCLASS_LVT)) ? false :
    ((lbc == UTF8PROC_BOUNDCLASS_LV ||
      lbc == UTF8PROC_BOUNDCLASS_V) &&
     (tbc == UTF8PROC_BOUNDCLASS_V ||
      tbc == UTF8PROC_BOUNDCLASS_T)) ? false :
    ((lbc == UTF8PROC_BOUNDCLASS_LVT ||
      lbc == UTF8PROC_BOUNDCLASS_T) &&
     tbc == UTF8PROC_BOUNDCLASS_T) ? false :
    (lbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR &&
     tbc == UTF8PROC_BOUNDCLASS_REGIONAL_INDICATOR) ? false :
    (tbc != UTF8PROC_BOUNDCLASS_SPACINGMARK);
}

/* return whether there is a grapheme break between codepoints c1 and c2 */
UTF8PROC_DLLEXPORT utf8proc_bool utf8proc_grapheme_break(utf8proc_int32_t c1, utf8proc_int32_t c2) {
  return grapheme_break(utf8proc_get_property(c1)->boundclass,
                        utf8proc_get_property(c2)->boundclass);
}

UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_tolower(utf8proc_int32_t c)
{
  utf8proc_int32_t cl = utf8proc_get_property(c)->lowercase_mapping;
  return cl >= 0 ? cl : c;
}

UTF8PROC_DLLEXPORT utf8proc_int32_t utf8proc_toupper(utf8proc_int32_t c)
{
  utf8proc_int32_t cu = utf8proc_get_property(c)->uppercase_mapping;
  return cu >= 0 ? cu : c;
}

/* return a character width analogous to wcwidth (except portable and
   hopefully less buggy than most system wcwidth functions). */
UTF8PROC_DLLEXPORT int utf8proc_charwidth(utf8proc_int32_t c) {
  return utf8proc_get_property(c)->charwidth;
}

UTF8PROC_DLLEXPORT utf8proc_category_t utf8proc_category(utf8proc_int32_t c) {
  return utf8proc_get_property(c)->category;
}

UTF8PROC_DLLEXPORT const char *utf8proc_category_string(utf8proc_int32_t c) {
  static const char s[][3] = {"Cn","Lu","Ll","Lt","Lm","Lo","Mn","Mc","Me","Nd","Nl","No","Pc","Pd","Ps","Pe","Pi","Pf","Po","Sm","Sc","Sk","So","Zs","Zl","Zp","Cc","Cf","Cs","Co"};
  return s[utf8proc_category(c)];
}

#define utf8proc_decompose_lump(replacement_uc) \
  return utf8proc_decompose_char((replacement_uc), dst, bufsize, \
  options & ~UTF8PROC_LUMP, last_boundclass)

UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose_char(utf8proc_int32_t uc, utf8proc_int32_t *dst, utf8proc_ssize_t bufsize, utf8proc_option_t options, int *last_boundclass) {
  const utf8proc_property_t *property;
  utf8proc_propval_t category;
  utf8proc_int32_t hangul_sindex;
  if (uc < 0 || uc >= 0x110000) return UTF8PROC_ERROR_NOTASSIGNED;
  property = unsafe_get_property(uc);
  category = property->category;
  hangul_sindex = uc - UTF8PROC_HANGUL_SBASE;
  if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
    if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT) {
      utf8proc_int32_t hangul_tindex;
      if (bufsize >= 1) {
        dst[0] = UTF8PROC_HANGUL_LBASE +
          hangul_sindex / UTF8PROC_HANGUL_NCOUNT;
        if (bufsize >= 2) dst[1] = UTF8PROC_HANGUL_VBASE +
          (hangul_sindex % UTF8PROC_HANGUL_NCOUNT) / UTF8PROC_HANGUL_TCOUNT;
      }
      hangul_tindex = hangul_sindex % UTF8PROC_HANGUL_TCOUNT;
      if (!hangul_tindex) return 2;
      if (bufsize >= 3) dst[2] = UTF8PROC_HANGUL_TBASE + hangul_tindex;
      return 3;
    }
  }
  if (options & UTF8PROC_REJECTNA) {
    if (!category) return UTF8PROC_ERROR_NOTASSIGNED;
  }
  if (options & UTF8PROC_IGNORE) {
    if (property->ignorable) return 0;
  }
  if (options & UTF8PROC_LUMP) {
    if (category == UTF8PROC_CATEGORY_ZS) utf8proc_decompose_lump(0x0020);
    if (uc == 0x2018 || uc == 0x2019 || uc == 0x02BC || uc == 0x02C8)
      utf8proc_decompose_lump(0x0027);
    if (category == UTF8PROC_CATEGORY_PD || uc == 0x2212)
      utf8proc_decompose_lump(0x002D);
    if (uc == 0x2044 || uc == 0x2215) utf8proc_decompose_lump(0x002F);
    if (uc == 0x2236) utf8proc_decompose_lump(0x003A);
    if (uc == 0x2039 || uc == 0x2329 || uc == 0x3008)
      utf8proc_decompose_lump(0x003C);
    if (uc == 0x203A || uc == 0x232A || uc == 0x3009)
      utf8proc_decompose_lump(0x003E);
    if (uc == 0x2216) utf8proc_decompose_lump(0x005C);
    if (uc == 0x02C4 || uc == 0x02C6 || uc == 0x2038 || uc == 0x2303)
      utf8proc_decompose_lump(0x005E);
    if (category == UTF8PROC_CATEGORY_PC || uc == 0x02CD)
      utf8proc_decompose_lump(0x005F);
    if (uc == 0x02CB) utf8proc_decompose_lump(0x0060);
    if (uc == 0x2223) utf8proc_decompose_lump(0x007C);
    if (uc == 0x223C) utf8proc_decompose_lump(0x007E);
    if ((options & UTF8PROC_NLF2LS) && (options & UTF8PROC_NLF2PS)) {
      if (category == UTF8PROC_CATEGORY_ZL ||
          category == UTF8PROC_CATEGORY_ZP)
        utf8proc_decompose_lump(0x000A);
    }
  }
  if (options & UTF8PROC_STRIPMARK) {
    if (category == UTF8PROC_CATEGORY_MN ||
      category == UTF8PROC_CATEGORY_MC ||
      category == UTF8PROC_CATEGORY_ME) return 0;
  }
  if (options & UTF8PROC_CASEFOLD) {
    if (property->casefold_mapping) {
      const utf8proc_int32_t *casefold_entry;
      utf8proc_ssize_t written = 0;
      for (casefold_entry = property->casefold_mapping;
          *casefold_entry >= 0; casefold_entry++) {
        written += utf8proc_decompose_char(*casefold_entry, dst+written,
          (bufsize > written) ? (bufsize - written) : 0, options,
          last_boundclass);
        if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
      }
      return written;
    }
  }
  if (options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) {
    if (property->decomp_mapping &&
        (!property->decomp_type || (options & UTF8PROC_COMPAT))) {
      const utf8proc_int32_t *decomp_entry;
      utf8proc_ssize_t written = 0;
      for (decomp_entry = property->decomp_mapping;
          *decomp_entry >= 0; decomp_entry++) {
        written += utf8proc_decompose_char(*decomp_entry, dst+written,
          (bufsize > written) ? (bufsize - written) : 0, options,
        last_boundclass);
        if (written < 0) return UTF8PROC_ERROR_OVERFLOW;
      }
      return written;
    }
  }
  if (options & UTF8PROC_CHARBOUND) {
    utf8proc_bool boundary;
    int tbc = property->boundclass;
    boundary = grapheme_break(*last_boundclass, tbc);
    *last_boundclass = tbc;
    if (boundary) {
      if (bufsize >= 1) dst[0] = 0xFFFF;
      if (bufsize >= 2) dst[1] = uc;
      return 2;
    }
  }
  if (bufsize >= 1) *dst = uc;
  return 1;
}

UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_decompose(
  const utf8proc_uint8_t *str, utf8proc_ssize_t strlen,
  utf8proc_int32_t *buffer, utf8proc_ssize_t bufsize, utf8proc_option_t options
) {
  /* strlen will be ignored, if UTF8PROC_NULLTERM is set in options */
  utf8proc_ssize_t wpos = 0;
  if ((options & UTF8PROC_COMPOSE) && (options & UTF8PROC_DECOMPOSE))
    return UTF8PROC_ERROR_INVALIDOPTS;
  if ((options & UTF8PROC_STRIPMARK) &&
      !(options & UTF8PROC_COMPOSE) && !(options & UTF8PROC_DECOMPOSE))
    return UTF8PROC_ERROR_INVALIDOPTS;
  {
    utf8proc_int32_t uc;
    utf8proc_ssize_t rpos = 0;
    utf8proc_ssize_t decomp_result;
    int boundclass = UTF8PROC_BOUNDCLASS_START;
    while (1) {
      if (options & UTF8PROC_NULLTERM) {
        rpos += utf8proc_iterate(str + rpos, -1, &uc);
        /* checking of return value is not necessary,
           as 'uc' is < 0 in case of error */
        if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
        if (rpos < 0) return UTF8PROC_ERROR_OVERFLOW;
        if (uc == 0) break;
      } else {
        if (rpos >= strlen) break;
        rpos += utf8proc_iterate(str + rpos, strlen - rpos, &uc);
        if (uc < 0) return UTF8PROC_ERROR_INVALIDUTF8;
      }
      decomp_result = utf8proc_decompose_char(
        uc, buffer + wpos, (bufsize > wpos) ? (bufsize - wpos) : 0, options,
        &boundclass
      );
      if (decomp_result < 0) return decomp_result;
      wpos += decomp_result;
      /* prohibiting integer overflows due to too long strings: */
      if (wpos < 0 || wpos > (utf8proc_ssize_t)(SSIZE_MAX/sizeof(utf8proc_int32_t)/2))
        return UTF8PROC_ERROR_OVERFLOW;
    }
  }
  if ((options & (UTF8PROC_COMPOSE|UTF8PROC_DECOMPOSE)) && bufsize >= wpos) {
    utf8proc_ssize_t pos = 0;
    while (pos < wpos-1) {
      utf8proc_int32_t uc1, uc2;
      const utf8proc_property_t *property1, *property2;
      uc1 = buffer[pos];
      uc2 = buffer[pos+1];
      property1 = unsafe_get_property(uc1);
      property2 = unsafe_get_property(uc2);
      if (property1->combining_class > property2->combining_class &&
          property2->combining_class > 0) {
        buffer[pos] = uc2;
        buffer[pos+1] = uc1;
        if (pos > 0) pos--; else pos++;
      } else {
        pos++;
      }
    }
  }
  return wpos;
}

UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_reencode(utf8proc_int32_t *buffer, utf8proc_ssize_t length, utf8proc_option_t options) {
  /* UTF8PROC_NULLTERM option will be ignored, 'length' is never ignored
     ASSERT: 'buffer' has one spare byte of free space at the end! */
  if (options & (UTF8PROC_NLF2LS | UTF8PROC_NLF2PS | UTF8PROC_STRIPCC)) {
    utf8proc_ssize_t rpos;
    utf8proc_ssize_t wpos = 0;
    utf8proc_int32_t uc;
    for (rpos = 0; rpos < length; rpos++) {
      uc = buffer[rpos];
      if (uc == 0x000D && rpos < length-1 && buffer[rpos+1] == 0x000A) rpos++;
      if (uc == 0x000A || uc == 0x000D || uc == 0x0085 ||
          ((options & UTF8PROC_STRIPCC) && (uc == 0x000B || uc == 0x000C))) {
        if (options & UTF8PROC_NLF2LS) {
          if (options & UTF8PROC_NLF2PS) {
            buffer[wpos++] = 0x000A;
          } else {
            buffer[wpos++] = 0x2028;
          }
        } else {
          if (options & UTF8PROC_NLF2PS) {
            buffer[wpos++] = 0x2029;
          } else {
            buffer[wpos++] = 0x0020;
          }
        }
      } else if ((options & UTF8PROC_STRIPCC) &&
          (uc < 0x0020 || (uc >= 0x007F && uc < 0x00A0))) {
        if (uc == 0x0009) buffer[wpos++] = 0x0020;
      } else {
        buffer[wpos++] = uc;
      }
    }
    length = wpos;
  }
  if (options & UTF8PROC_COMPOSE) {
    utf8proc_int32_t *starter = NULL;
    utf8proc_int32_t current_char;
    const utf8proc_property_t *starter_property = NULL, *current_property;
    utf8proc_propval_t max_combining_class = -1;
    utf8proc_ssize_t rpos;
    utf8proc_ssize_t wpos = 0;
    utf8proc_int32_t composition;
    for (rpos = 0; rpos < length; rpos++) {
      current_char = buffer[rpos];
      current_property = unsafe_get_property(current_char);
      if (starter && current_property->combining_class > max_combining_class) {
        /* combination perhaps possible */
        utf8proc_int32_t hangul_lindex;
        utf8proc_int32_t hangul_sindex;
        hangul_lindex = *starter - UTF8PROC_HANGUL_LBASE;
        if (hangul_lindex >= 0 && hangul_lindex < UTF8PROC_HANGUL_LCOUNT) {
          utf8proc_int32_t hangul_vindex;
          hangul_vindex = current_char - UTF8PROC_HANGUL_VBASE;
          if (hangul_vindex >= 0 && hangul_vindex < UTF8PROC_HANGUL_VCOUNT) {
            *starter = UTF8PROC_HANGUL_SBASE +
              (hangul_lindex * UTF8PROC_HANGUL_VCOUNT + hangul_vindex) *
              UTF8PROC_HANGUL_TCOUNT;
            starter_property = NULL;
            continue;
          }
        }
        hangul_sindex = *starter - UTF8PROC_HANGUL_SBASE;
        if (hangul_sindex >= 0 && hangul_sindex < UTF8PROC_HANGUL_SCOUNT &&
            (hangul_sindex % UTF8PROC_HANGUL_TCOUNT) == 0) {
          utf8proc_int32_t hangul_tindex;
          hangul_tindex = current_char - UTF8PROC_HANGUL_TBASE;
          if (hangul_tindex >= 0 && hangul_tindex < UTF8PROC_HANGUL_TCOUNT) {
            *starter += hangul_tindex;
            starter_property = NULL;
            continue;
          }
        }
        if (!starter_property) {
          starter_property = unsafe_get_property(*starter);
        }
        if (starter_property->comb1st_index >= 0 &&
            current_property->comb2nd_index >= 0) {
          composition = utf8proc_combinations[
            starter_property->comb1st_index +
            current_property->comb2nd_index
          ];
          if (composition >= 0 && (!(options & UTF8PROC_STABLE) ||
              !(unsafe_get_property(composition)->comp_exclusion))) {
            *starter = composition;
            starter_property = NULL;
            continue;
          }
        }
      }
      buffer[wpos] = current_char;
      if (current_property->combining_class) {
        if (current_property->combining_class > max_combining_class) {
          max_combining_class = current_property->combining_class;
        }
      } else {
        starter = buffer + wpos;
        starter_property = NULL;
        max_combining_class = -1;
      }
      wpos++;
    }
    length = wpos;
  }
  {
    utf8proc_ssize_t rpos, wpos = 0;
    utf8proc_int32_t uc;
    if (options & UTF8PROC_CHARBOUND) {
        for (rpos = 0; rpos < length; rpos++) {
            uc = buffer[rpos];
            wpos += unsafe_encode_char(uc, ((utf8proc_uint8_t *)buffer) + wpos);
        }
    } else {
        for (rpos = 0; rpos < length; rpos++) {
            uc = buffer[rpos];
            wpos += utf8proc_encode_char(uc, ((utf8proc_uint8_t *)buffer) + wpos);
        }
    }
    ((utf8proc_uint8_t *)buffer)[wpos] = 0;
    return wpos;
  }
}

UTF8PROC_DLLEXPORT utf8proc_ssize_t utf8proc_map(
  const utf8proc_uint8_t *str, utf8proc_ssize_t strlen, utf8proc_uint8_t **dstptr, utf8proc_option_t options
) {
  utf8proc_int32_t *buffer;
  utf8proc_ssize_t result;
  *dstptr = NULL;
  result = utf8proc_decompose(str, strlen, NULL, 0, options);
  if (result < 0) return result;
  buffer = (utf8proc_int32_t *) malloc(result * sizeof(utf8proc_int32_t) + 1);
  if (!buffer) return UTF8PROC_ERROR_NOMEM;
  result = utf8proc_decompose(str, strlen, buffer, result, options);
  if (result < 0) {
    free(buffer);
    return result;
  }
  result = utf8proc_reencode(buffer, result, options);
  if (result < 0) {
    free(buffer);
    return result;
  }
  {
    utf8proc_int32_t *newptr;
    newptr = (utf8proc_int32_t *) realloc(buffer, (size_t)result+1);
    if (newptr) buffer = newptr;
  }
  *dstptr = (utf8proc_uint8_t *)buffer;
  return result;
}

UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFD(const utf8proc_uint8_t *str) {
  utf8proc_uint8_t *retval;
  utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
    UTF8PROC_DECOMPOSE);
  return retval;
}

UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFC(const utf8proc_uint8_t *str) {
  utf8proc_uint8_t *retval;
  utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
    UTF8PROC_COMPOSE);
  return retval;
}

UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKD(const utf8proc_uint8_t *str) {
  utf8proc_uint8_t *retval;
  utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
    UTF8PROC_DECOMPOSE | UTF8PROC_COMPAT);
  return retval;
}

UTF8PROC_DLLEXPORT utf8proc_uint8_t *utf8proc_NFKC(const utf8proc_uint8_t *str) {
  utf8proc_uint8_t *retval;
  utf8proc_map(str, 0, &retval, UTF8PROC_NULLTERM | UTF8PROC_STABLE |
    UTF8PROC_COMPOSE | UTF8PROC_COMPAT);
  return retval;
}