~case/dbns

ref: 85d3c74215baa48cb2fd97d3c85ff6060e7c42b1 dbns/src/utf8.h -rw-r--r-- 27.7 KiB
85d3c742Zerhyn SBC oopsie 3 years ago
                                                                                
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
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
// This is free and unencumbered software released into the public domain.
//
// Anyone is free to copy, modify, publish, use, compile, sell, or
// distribute this software, either in source code form or as a compiled
// binary, for any purpose, commercial or non-commercial, and by any
// means.
//
// In jurisdictions that recognize copyright laws, the author or authors
// of this software dedicate any and all copyright interest in the
// software to the public domain. We make this dedication for the benefit
// of the public at large and to the detriment of our heirs and
// successors. We intend this dedication to be an overt act of
// relinquishment in perpetuity of all present and future rights to this
// software under copyright law.
//
// 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 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.
//
// For more information, please refer to <http://unlicense.org/>

#ifndef SHEREDOM_UTF8_H_INCLUDED
#define SHEREDOM_UTF8_H_INCLUDED

#if defined(_MSC_VER)
#pragma warning(push)

// disable 'bytes padding added after construct' warning
#pragma warning(disable : 4820)
#endif

#include <stddef.h>
#include <stdlib.h>

#if defined(_MSC_VER)
#pragma warning(pop)
#endif

#if defined(_MSC_VER)
#define int32_t __int32
#define uint32_t __uint32
#else
#include <stdint.h>
#endif

#if defined(__clang__)
#pragma clang diagnostic push
#pragma clang diagnostic ignored "-Wold-style-cast"
#pragma clang diagnostic ignored "-Wcast-qual"
#endif

#ifdef __cplusplus
extern "C" {
#endif

#if defined(__clang__) || defined(__GNUC__)
#define utf8_nonnull __attribute__((nonnull))
#define utf8_pure __attribute__((pure))
#define utf8_restrict __restrict__
#define utf8_weak __attribute__((weak))
#elif defined(_MSC_VER)
#define utf8_nonnull
#define utf8_pure
#define utf8_restrict __restrict
#define utf8_weak __inline
#else
#error Non clang, non gcc, non MSVC compiler found!
#endif

// While ignoring the case of ASCII characters, return less
// than 0, 0, greater than 0 if src1 < src2, src1 == src2,
// src1 > src2 respectively.
utf8_nonnull utf8_pure utf8_weak int utf8casecmp(const void *src1,
                                                 const void *src2);

// Append the utf8 string src onto the utf8 string dst.
utf8_nonnull utf8_weak void *utf8cat(void *utf8_restrict dst,
                                     const void *utf8_restrict src);

// Find the first match of the utf8 codepoint chr in the utf8 string src.
utf8_nonnull utf8_pure utf8_weak void *utf8chr(const void *src, int32_t chr);

// Return less than 0, 0, greater than 0 if src1 < src2,
// src1 == src2, src1 > src2 respectively.
utf8_nonnull utf8_pure utf8_weak int utf8cmp(const void *src1,
                                             const void *src2);

// Copy the utf8 string src onto the memory allocated in dst.
utf8_nonnull utf8_weak void *utf8cpy(void *utf8_restrict dst,
                                     const void *utf8_restrict src);

// Number of utf8 codepoints in the utf8 string src that consists entirely
// of utf8 codepoints not from the utf8 string reject.
utf8_nonnull utf8_pure utf8_weak size_t utf8cspn(const void *src,
                                                 const void *reject);

// Duplicate the utf8 string src by getting its size, malloc'ing a new buffer
// copying over the data, and returning that. Or 0 if malloc failed.
utf8_nonnull utf8_weak void *utf8dup(const void *src);

// Number of utf8 codepoints in the utf8 string str,
// excluding the null terminating byte.
utf8_nonnull utf8_pure utf8_weak size_t utf8len(const void *str);

// While ignoring the case of ASCII characters, return less
// than 0, 0, greater than 0 if src1 < src2, src1 == src2,
// src1 > src2 respectively. Checking at most n
// bytes of each utf8 string.
utf8_nonnull utf8_pure utf8_weak int utf8ncasecmp(const void *src1,
                                                  const void *src2, size_t n);

// Append the utf8 string src onto the utf8 string dst,
// writing at most n+1 bytes. Can produce an invalid utf8
// string if n falls partway through a utf8 codepoint.
utf8_nonnull utf8_weak void *utf8ncat(void *utf8_restrict dst,
                                      const void *utf8_restrict src, size_t n);

// Return less than 0, 0, greater than 0 if src1 < src2,
// src1 == src2, src1 > src2 respectively. Checking at most n
// bytes of each utf8 string.
utf8_nonnull utf8_pure utf8_weak int utf8ncmp(const void *src1,
                                              const void *src2, size_t n);

// Copy the utf8 string src onto the memory allocated in dst.
// Copies at most n bytes. If there is no terminating null byte in
// the first n bytes of src, the string placed into dst will not be
// null-terminated. If the size (in bytes) of src is less than n,
// extra null terminating bytes are appended to dst such that at
// total of n bytes are written. Can produce an invalid utf8
// string if n falls partway through a utf8 codepoint.
utf8_nonnull utf8_weak void *utf8ncpy(void *utf8_restrict dst,
                                      const void *utf8_restrict src, size_t n);

// Locates the first occurence in the utf8 string str of any byte in the
// utf8 string accept, or 0 if no match was found.
utf8_nonnull utf8_pure utf8_weak void *utf8pbrk(const void *str,
                                                const void *accept);

// Find the last match of the utf8 codepoint chr in the utf8 string src.
utf8_nonnull utf8_pure utf8_weak void *utf8rchr(const void *src, int chr);

// Number of bytes in the utf8 string str,
// including the null terminating byte.
utf8_nonnull utf8_pure utf8_weak size_t utf8size(const void *str);

// Number of utf8 codepoints in the utf8 string src that consists entirely
// of utf8 codepoints from the utf8 string accept.
utf8_nonnull utf8_pure utf8_weak size_t utf8spn(const void *src,
                                                const void *accept);

// The position of the utf8 string needle in the utf8 string haystack.
utf8_nonnull utf8_pure utf8_weak void *utf8str(const void *haystack,
                                               const void *needle);

// The position of the utf8 string needle in the utf8 string haystack, case
// instensitive.
utf8_nonnull utf8_pure utf8_weak void *utf8casestr(const void *haystack,
                                                   const void *needle);

// Return 0 on success, or the position of the invalid
// utf8 codepoint on failure.
utf8_nonnull utf8_pure utf8_weak void *utf8valid(const void *str);

// Sets out_codepoint to the next utf8 codepoint in str, and returns the address
// of the utf8 codepoint after the current one in str.
utf8_nonnull utf8_weak void *utf8codepoint(const void *utf8_restrict str,
                                           int32_t *utf8_restrict out_codepoint);

// Returns the size of the given codepoint in bytes.
utf8_weak size_t utf8codepointsize(int32_t chr);

// Write a codepoint to the given string, and return the address to the next place
// after the written codepoint. Pass how many bytes left in the buffer to n. If there
// is not enough space for the codepoint, this function returns null.
utf8_nonnull utf8_weak void *utf8catcodepoint(void *utf8_restrict str, int32_t chr, size_t n);

// Returns 1 if the given character is lowercase, or 0 if it is not.
utf8_weak int utf8islower(int32_t chr);

// Returns 1 if the given character is uppercase, or 0 if it is not.
utf8_weak int utf8isupper(int32_t chr);

// Transform the given string into all lowercase codepoints.
utf8_nonnull utf8_weak void utf8lwr(void *utf8_restrict str);

// Transform the given string into all uppercase codepoints.
utf8_nonnull utf8_weak void utf8upr(void *utf8_restrict str);

#undef utf8_weak
#undef utf8_pure
#undef utf8_nonnull

int utf8casecmp(const void *src1, const void *src2) {
  const unsigned char *s1 = (const unsigned char *)src1;
  const unsigned char *s2 = (const unsigned char *)src2;

  while (('\0' != *s1) || ('\0' != *s2)) {
    unsigned char a = *s1;
    unsigned char b = *s2;

    if (('A' <= a) && ('Z' >= a)) {
      a |= 0x20; // make a lowercase
    }

    if (('A' <= b) && ('Z' >= b)) {
      b |= 0x20; // make b lowercase
    }

    if (a < b) {
      return -1;
    } else if (a > b) {
      return 1;
    }

    s1++;
    s2++;
  }

  // both utf8 strings matched
  return 0;
}

void *utf8cat(void *utf8_restrict dst, const void *utf8_restrict src) {
  char *d = (char *)dst;
  const char *s = (const char *)src;

  // find the null terminating byte in dst
  while ('\0' != *d) {
    d++;
  }

  // overwriting the null terminating byte in dst, append src byte-by-byte
  while ('\0' != *s) {
    *d++ = *s++;
  }

  // write out a new null terminating byte into dst
  *d = '\0';

  return dst;
}

void *utf8chr(const void *src, int32_t chr) {
  char c[5] = {'\0', '\0', '\0', '\0', '\0'};

  if (0 == chr) {
    // being asked to return position of null terminating byte, so
    // just run s to the end, and return!
    const char *s = (const char *)src;
    while ('\0' != *s) {
      s++;
    }
    return (void *)s;
  } else if (0 == ((int32_t)0xffffff80 & chr)) {
    // 1-byte/7-bit ascii
    // (0b0xxxxxxx)
    c[0] = (char)chr;
  } else if (0 == ((int32_t)0xfffff800 & chr)) {
    // 2-byte/11-bit utf8 code point
    // (0b110xxxxx 0b10xxxxxx)
    c[0] = 0xc0 | (char)(chr >> 6);
    c[1] = 0x80 | (char)(chr & 0x3f);
  } else if (0 == ((int32_t)0xffff0000 & chr)) {
    // 3-byte/16-bit utf8 code point
    // (0b1110xxxx 0b10xxxxxx 0b10xxxxxx)
    c[0] = 0xe0 | (char)(chr >> 12);
    c[1] = 0x80 | (char)((chr >> 6) & 0x3f);
    c[2] = 0x80 | (char)(chr & 0x3f);
  } else { // if (0 == ((int)0xffe00000 & chr)) {
    // 4-byte/21-bit utf8 code point
    // (0b11110xxx 0b10xxxxxx 0b10xxxxxx 0b10xxxxxx)
    c[0] = 0xf0 | (char)(chr >> 18);
    c[1] = 0x80 | (char)((chr >> 12) & 0x3f);
    c[2] = 0x80 | (char)((chr >> 6) & 0x3f);
    c[3] = 0x80 | (char)(chr & 0x3f);
  }

  // we've made c into a 2 utf8 codepoint string, one for the chr we are
  // seeking, another for the null terminating byte. Now use utf8str to
  // search
  return utf8str(src, c);
}

int utf8cmp(const void *src1, const void *src2) {
  const unsigned char *s1 = (const unsigned char *)src1;
  const unsigned char *s2 = (const unsigned char *)src2;

  while (('\0' != *s1) || ('\0' != *s2)) {
    if (*s1 < *s2) {
      return -1;
    } else if (*s1 > *s2) {
      return 1;
    }

    s1++;
    s2++;
  }

  // both utf8 strings matched
  return 0;
}

int utf8coll(const void *src1, const void *src2);

void *utf8cpy(void *utf8_restrict dst, const void *utf8_restrict src) {
  char *d = (char *)dst;
  const char *s = (const char *)src;

  // overwriting anything previously in dst, write byte-by-byte
  // from src
  while ('\0' != *s) {
    *d++ = *s++;
  }

  // append null terminating byte
  *d = '\0';

  return dst;
}

size_t utf8cspn(const void *src, const void *reject) {
  const char *s = (const char *)src;
  size_t chars = 0;

  while ('\0' != *s) {
    const char *r = (const char *)reject;
    size_t offset = 0;

    while ('\0' != *r) {
      // checking that if *r is the start of a utf8 codepoint
      // (it is not 0b10xxxxxx) and we have successfully matched
      // a previous character (0 < offset) - we found a match
      if ((0x80 != (0xc0 & *r)) && (0 < offset)) {
        return chars;
      } else {
        if (*r == s[offset]) {
          // part of a utf8 codepoint matched, so move our checking
          // onwards to the next byte
          offset++;
          r++;
        } else {
          // r could be in the middle of an unmatching utf8 code point,
          // so we need to march it on to the next character beginning,

          do {
            r++;
          } while (0x80 == (0xc0 & *r));

          // reset offset too as we found a mismatch
          offset = 0;
        }
      }
    }

    // the current utf8 codepoint in src did not match reject, but src
    // could have been partway through a utf8 codepoint, so we need to
    // march it onto the next utf8 codepoint starting byte
    do {
      s++;
    } while ((0x80 == (0xc0 & *s)));
    chars++;
  }

  return chars;
}

size_t utf8size(const void *str);

void *utf8dup(const void *src) {
  const char *s = (const char *)src;
  char *n = 0;

  // figure out how many bytes (including the terminator) we need to copy first
  size_t bytes = utf8size(src);

  n = (char *)malloc(bytes);

  if (0 == n) {
    // out of memory so we bail
    return 0;
  } else {
    bytes = 0;

    // copy src byte-by-byte into our new utf8 string
    while ('\0' != s[bytes]) {
      n[bytes] = s[bytes];
      bytes++;
    }

    // append null terminating byte
    n[bytes] = '\0';
    return n;
  }
}

void *utf8fry(const void *str);

size_t utf8len(const void *str) {
  const unsigned char *s = (const unsigned char *)str;
  size_t length = 0;

  while ('\0' != *s) {
    if (0xf0 == (0xf8 & *s)) {
      // 4-byte utf8 code point (began with 0b11110xxx)
      s += 4;
    } else if (0xe0 == (0xf0 & *s)) {
      // 3-byte utf8 code point (began with 0b1110xxxx)
      s += 3;
    } else if (0xc0 == (0xe0 & *s)) {
      // 2-byte utf8 code point (began with 0b110xxxxx)
      s += 2;
    } else { // if (0x00 == (0x80 & *s)) {
      // 1-byte ascii (began with 0b0xxxxxxx)
      s += 1;
    }

    // no matter the bytes we marched s forward by, it was
    // only 1 utf8 codepoint
    length++;
  }

  return length;
}

int utf8ncasecmp(const void *src1, const void *src2, size_t n) {
  const unsigned char *s1 = (const unsigned char *)src1;
  const unsigned char *s2 = (const unsigned char *)src2;

  while ((('\0' != *s1) || ('\0' != *s2)) && (0 != n--)) {
    unsigned char a = *s1;
    unsigned char b = *s2;

    if (('A' <= a) && ('Z' >= a)) {
      a |= 0x20; // make a lowercase
    }

    if (('A' <= b) && ('Z' >= b)) {
      b |= 0x20; // make b lowercase
    }

    if (a < b) {
      return -1;
    } else if (a > b) {
      return 1;
    }

    s1++;
    s2++;
  }

  // both utf8 strings matched
  return 0;
}

void *utf8ncat(void *utf8_restrict dst, const void *utf8_restrict src,
               size_t n) {
  char *d = (char *)dst;
  const char *s = (const char *)src;

  // find the null terminating byte in dst
  while ('\0' != *d) {
    d++;
  }

  // overwriting the null terminating byte in dst, append src byte-by-byte
  // stopping if we run out of space
  do {
    *d++ = *s++;
  } while (('\0' != *s) && (0 != --n));

  // write out a new null terminating byte into dst
  *d = '\0';

  return dst;
}

int utf8ncmp(const void *src1, const void *src2, size_t n) {
  const unsigned char *s1 = (const unsigned char *)src1;
  const unsigned char *s2 = (const unsigned char *)src2;

  while ((('\0' != *s1) || ('\0' != *s2)) && (0 != n--)) {
    if (*s1 < *s2) {
      return -1;
    } else if (*s1 > *s2) {
      return 1;
    }

    s1++;
    s2++;
  }

  // both utf8 strings matched
  return 0;
}

void *utf8ncpy(void *utf8_restrict dst, const void *utf8_restrict src,
               size_t n) {
  char *d = (char *)dst;
  const char *s = (const char *)src;

  // overwriting anything previously in dst, write byte-by-byte
  // from src
  do {
    *d++ = *s++;
  } while (('\0' != *s) && (0 != --n));

  // append null terminating byte
  while (0 != n) {
    *d++ = '\0';
    n--;
  }

  return dst;
}

void *utf8rchr(const void *src, int chr) {
  const char *s = (const char *)src;
  const char *match = 0;
  char c[5] = {'\0', '\0', '\0', '\0', '\0'};

  if (0 == chr) {
    // being asked to return position of null terminating byte, so
    // just run s to the end, and return!
    while ('\0' != *s) {
      s++;
    }
    return (void *)s;
  } else if (0 == ((int)0xffffff80 & chr)) {
    // 1-byte/7-bit ascii
    // (0b0xxxxxxx)
    c[0] = (char)chr;
  } else if (0 == ((int)0xfffff800 & chr)) {
    // 2-byte/11-bit utf8 code point
    // (0b110xxxxx 0b10xxxxxx)
    c[0] = 0xc0 | (char)(chr >> 6);
    c[1] = 0x80 | (char)(chr & 0x3f);
  } else if (0 == ((int)0xffff0000 & chr)) {
    // 3-byte/16-bit utf8 code point
    // (0b1110xxxx 0b10xxxxxx 0b10xxxxxx)
    c[0] = 0xe0 | (char)(chr >> 12);
    c[1] = 0x80 | (char)((chr >> 6) & 0x3f);
    c[2] = 0x80 | (char)(chr & 0x3f);
  } else { // if (0 == ((int)0xffe00000 & chr)) {
    // 4-byte/21-bit utf8 code point
    // (0b11110xxx 0b10xxxxxx 0b10xxxxxx 0b10xxxxxx)
    c[0] = 0xf0 | (char)(chr >> 18);
    c[1] = 0x80 | (char)((chr >> 12) & 0x3f);
    c[2] = 0x80 | (char)((chr >> 6) & 0x3f);
    c[3] = 0x80 | (char)(chr & 0x3f);
  }

  // we've created a 2 utf8 codepoint string in c that is
  // the utf8 character asked for by chr, and a null
  // terminating byte

  while ('\0' != *s) {
    size_t offset = 0;

    while (s[offset] == c[offset]) {
      offset++;
    }

    if ('\0' == c[offset]) {
      // we found a matching utf8 code point
      match = s;
      s += offset;
    } else {
      s += offset;

      // need to march s along to next utf8 codepoint start
      // (the next byte that doesn't match 0b10xxxxxx)
      if ('\0' != *s) {
        do {
          s++;
        } while (0x80 == (0xc0 & *s));
      }
    }
  }

  // return the last match we found (or 0 if no match was found)
  return (void *)match;
}

void *utf8pbrk(const void *str, const void *accept) {
  const char *s = (const char *)str;

  while ('\0' != *s) {
    const char *a = (const char *)accept;
    size_t offset = 0;

    while ('\0' != *a) {
      // checking that if *a is the start of a utf8 codepoint
      // (it is not 0b10xxxxxx) and we have successfully matched
      // a previous character (0 < offset) - we found a match
      if ((0x80 != (0xc0 & *a)) && (0 < offset)) {
        return (void *)s;
      } else {
        if (*a == s[offset]) {
          // part of a utf8 codepoint matched, so move our checking
          // onwards to the next byte
          offset++;
          a++;
        } else {
          // r could be in the middle of an unmatching utf8 code point,
          // so we need to march it on to the next character beginning,

          do {
            a++;
          } while (0x80 == (0xc0 & *a));

          // reset offset too as we found a mismatch
          offset = 0;
        }
      }
    }

    // we found a match on the last utf8 codepoint
    if (0 < offset) {
      return (void *)s;
    }

    // the current utf8 codepoint in src did not match accept, but src
    // could have been partway through a utf8 codepoint, so we need to
    // march it onto the next utf8 codepoint starting byte
    do {
      s++;
    } while ((0x80 == (0xc0 & *s)));
  }

  return 0;
}

size_t utf8size(const void *str) {
  const char *s = (const char *)str;
  size_t size = 0;
  while ('\0' != s[size]) {
    size++;
  }

  // we are including the null terminating byte in the size calculation
  size++;
  return size;
}

size_t utf8spn(const void *src, const void *accept) {
  const char *s = (const char *)src;
  size_t chars = 0;

  while ('\0' != *s) {
    const char *a = (const char *)accept;
    size_t offset = 0;

    while ('\0' != *a) {
      // checking that if *r is the start of a utf8 codepoint
      // (it is not 0b10xxxxxx) and we have successfully matched
      // a previous character (0 < offset) - we found a match
      if ((0x80 != (0xc0 & *a)) && (0 < offset)) {
        // found a match, so increment the number of utf8 codepoints
        // that have matched and stop checking whether any other utf8
        // codepoints in a match
        chars++;
        s += offset;
        break;
      } else {
        if (*a == s[offset]) {
          offset++;
          a++;
        } else {
          // a could be in the middle of an unmatching utf8 codepoint,
          // so we need to march it on to the next character beginning,
          do {
            a++;
          } while (0x80 == (0xc0 & *a));

          // reset offset too as we found a mismatch
          offset = 0;
        }
      }
    }

    // if a got to its terminating null byte, then we didn't find a match.
    // Return the current number of matched utf8 codepoints
    if ('\0' == *a) {
      return chars;
    }
  }

  return chars;
}

void *utf8str(const void *haystack, const void *needle) {
  const char *h = (const char *)haystack;

  // if needle has no utf8 codepoints before the null terminating
  // byte then return haystack
  if ('\0' == *((const char *)needle)) {
    return (void *)haystack;
  }

  while ('\0' != *h) {
    const char *maybeMatch = h;
    const char *n = (const char *)needle;

    while (*h == *n && (*h != '\0' && *n != '\0')) {
      n++;
      h++;
    }

    if ('\0' == *n) {
      // we found the whole utf8 string for needle in haystack at
      // maybeMatch, so return it
      return (void *)maybeMatch;
    } else {
      // h could be in the middle of an unmatching utf8 codepoint,
      // so we need to march it on to the next character beginning,
      if ('\0' != *h) {
        do {
          h++;
        } while (0x80 == (0xc0 & *h));
      }
    }
  }

  // no match
  return 0;
}

void *utf8casestr(const void *haystack, const void *needle) {
  const char *h = (const char *)haystack;

  // if needle has no utf8 codepoints before the null terminating
  // byte then return haystack
  if ('\0' == *((const char *)needle)) {
    return (void *)haystack;
  }

  while ('\0' != *h) {
    const char *maybeMatch = h;
    const char *n = (const char *)needle;

    for (; '\0' != *h && '\0' != *n;) {
      char a = *h;
      char b = *n;
      // not entirely correct, but good enough
      if (('A' <= a) && ('Z' >= a)) {
        a |= 0x20; // make a lowercase
      }

      if (('A' <= b) && ('Z' >= b)) {
        b |= 0x20; // make b lowercase
      }

      // if we find a mismatch, bail out!
      if (a != b) {
        break;
      }

      n++;
      h++;
    }

    if ('\0' == *n) {
      // we found the whole utf8 string for needle in haystack at
      // maybeMatch, so return it
      return (void *)maybeMatch;
    } else {
      // h could be in the middle of an unmatching utf8 codepoint,
      // so we need to march it on to the next character beginning,
      if ('\0' != *h) {
        do {
          h++;
        } while (0x80 == (0xc0 & *h));
      }
    }
  }

  // no match
  return 0;
}

void *utf8valid(const void *str) {
  const char *s = (const char *)str;

  while ('\0' != *s) {
    if (0xf0 == (0xf8 & *s)) {
      // ensure each of the 3 following bytes in this 4-byte
      // utf8 codepoint began with 0b10xxxxxx
      if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2])) ||
          (0x80 != (0xc0 & s[3]))) {
        return (void *)s;
      }

      // ensure that our utf8 codepoint ended after 4 bytes
      if (0x80 == (0xc0 & s[4])) {
        return (void *)s;
      }

      // ensure that the top 5 bits of this 4-byte utf8
      // codepoint were not 0, as then we could have used
      // one of the smaller encodings
      if ((0 == (0x07 & s[0])) && (0 == (0x30 & s[1]))) {
        return (void *)s;
      }

      // 4-byte utf8 code point (began with 0b11110xxx)
      s += 4;
    } else if (0xe0 == (0xf0 & *s)) {
      // ensure each of the 2 following bytes in this 3-byte
      // utf8 codepoint began with 0b10xxxxxx
      if ((0x80 != (0xc0 & s[1])) || (0x80 != (0xc0 & s[2]))) {
        return (void *)s;
      }

      // ensure that our utf8 codepoint ended after 3 bytes
      if (0x80 == (0xc0 & s[3])) {
        return (void *)s;
      }

      // ensure that the top 5 bits of this 3-byte utf8
      // codepoint were not 0, as then we could have used
      // one of the smaller encodings
      if ((0 == (0x0f & s[0])) && (0 == (0x20 & s[1]))) {
        return (void *)s;
      }

      // 3-byte utf8 code point (began with 0b1110xxxx)
      s += 3;
    } else if (0xc0 == (0xe0 & *s)) {
      // ensure the 1 following byte in this 2-byte
      // utf8 codepoint began with 0b10xxxxxx
      if (0x80 != (0xc0 & s[1])) {
        return (void *)s;
      }

      // ensure that our utf8 codepoint ended after 2 bytes
      if (0x80 == (0xc0 & s[2])) {
        return (void *)s;
      }

      // ensure that the top 4 bits of this 2-byte utf8
      // codepoint were not 0, as then we could have used
      // one of the smaller encodings
      if (0 == (0x1e & s[0])) {
        return (void *)s;
      }

      // 2-byte utf8 code point (began with 0b110xxxxx)
      s += 2;
    } else if (0x00 == (0x80 & *s)) {
      // 1-byte ascii (began with 0b0xxxxxxx)
      s += 1;
    } else {
      // we have an invalid 0b1xxxxxxx utf8 code point entry
      return (void *)s;
    }
  }

  return 0;
}

void *utf8codepoint(const void *utf8_restrict str,
                    int32_t *utf8_restrict out_codepoint) {
  const char *s = (const char *)str;

  if (0xf0 == (0xf8 & s[0])) {
    // 4 byte utf8 codepoint
    *out_codepoint = ((0x07 & s[0]) << 18) | ((0x3f & s[1]) << 12) |
                     ((0x3f & s[2]) << 6) | (0x3f & s[3]);
    s += 4;
  } else if (0xe0 == (0xf0 & s[0])) {
    // 3 byte utf8 codepoint
    *out_codepoint =
        ((0x0f & s[0]) << 12) | ((0x3f & s[1]) << 6) | (0x3f & s[2]);
    s += 3;
  } else if (0xc0 == (0xe0 & s[0])) {
    // 2 byte utf8 codepoint
    *out_codepoint = ((0x1f & s[0]) << 6) | (0x3f & s[1]);
    s += 2;
  } else {
    // 1 byte utf8 codepoint otherwise
    *out_codepoint = s[0];
    s += 1;
  }

  return (void *)s;
}

size_t utf8codepointsize(int32_t chr) {
  if (0 == ((int32_t)0xffffff80 & chr)) {
    return 1;
  } else if (0 == ((int32_t)0xfffff800 & chr)) {
    return 2;
  } else if (0 == ((int32_t)0xffff0000 & chr)) {
    return 3;
  } else { // if (0 == ((int)0xffe00000 & chr)) {
    return 4;
  }
}

void *utf8catcodepoint(void *utf8_restrict str, int32_t chr, size_t n) {
  char *s = (char *)str;

  if (0 == ((int32_t)0xffffff80 & chr)) {
    // 1-byte/7-bit ascii
    // (0b0xxxxxxx)
    if (n < 1) {
      return 0;
    }
    s[0] = (char)chr;
    s += 1;
  } else if (0 == ((int32_t)0xfffff800 & chr)) {
    // 2-byte/11-bit utf8 code point
    // (0b110xxxxx 0b10xxxxxx)
    if (n < 2) {
      return 0;
    }
    s[0] = 0xc0 | (char)(chr >> 6);
    s[1] = 0x80 | (char)(chr & 0x3f);
    s += 2;
  } else if (0 == ((int32_t)0xffff0000 & chr)) {
    // 3-byte/16-bit utf8 code point
    // (0b1110xxxx 0b10xxxxxx 0b10xxxxxx)
    if (n < 3) {
      return 0;
    }
    s[0] = 0xe0 | (char)(chr >> 12);
    s[1] = 0x80 | (char)((chr >> 6) & 0x3f);
    s[2] = 0x80 | (char)(chr & 0x3f);
    s += 3;
  } else { // if (0 == ((int)0xffe00000 & chr)) {
    // 4-byte/21-bit utf8 code point
    // (0b11110xxx 0b10xxxxxx 0b10xxxxxx 0b10xxxxxx)
    if (n < 4) {
      return 0;
    }
    s[0] = 0xf0 | (char)(chr >> 18);
    s[1] = 0x80 | (char)((chr >> 12) & 0x3f);
    s[2] = 0x80 | (char)((chr >> 6) & 0x3f);
    s[3] = 0x80 | (char)(chr & 0x3f);
    s += 4;
  }

  return s;
}

int utf8islower(int32_t chr)
{
  if (('A' <= chr) && ('Z' >= chr)) {
    return 0;
  }
  // Because we're not all-inclusive, assume everything else is lowercase
  return 1;
}

int utf8isupper(int32_t chr)
{
  if (('A' <= chr) && ('Z' >= chr)) {
    return 1;
  }
  return 0;
}

void utf8lwr(void *utf8_restrict str)
{
  void *p, *pn;
  int cp;

  p = (char *)str;
  pn = utf8codepoint(p, &cp);

  while (cp != 0) {
    if (('A' <= cp) && ('Z' >= cp)) {
      cp |= 0x20;
      utf8catcodepoint(p, cp, 1);
    }
    p = pn;
    pn = utf8codepoint(p, &cp);
  }
}

void utf8upr(void *utf8_restrict str)
{
  void *p, *pn;
  int cp;

  p = (char *)str;
  pn = utf8codepoint(p, &cp);

  while (cp != 0) {
    if (('a' <= cp) && ('z' >= cp)) {
      cp &= ~0x20;
      utf8catcodepoint(p, cp, 1);
    }
    p = pn;
    pn = utf8codepoint(p, &cp);
  }
}

#undef utf8_restrict

#ifdef __cplusplus
} // extern "C"
#endif

#if defined(__clang__)
#pragma clang diagnostic pop
#endif

#endif // SHEREDOM_UTF8_H_INCLUDED