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
|
/*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version 2
* of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software Foundation,
* Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
*
* The Original Code is Copyright (C) 2011 Blender Foundation.
* Code from gutf8.c Copyright (C) 1999 Tom Tromey
* Copyright (C) 2000 Red Hat, Inc.
* All rights reserved.
*/
/** \file
* \ingroup bli
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <wchar.h>
#include <wctype.h>
#include <wcwidth.h>
#include "BLI_utildefines.h"
#include "BLI_string_utf8.h" /* own include */
#ifdef WIN32
# include "utfconv.h"
#endif
#ifdef __GNUC__
# pragma GCC diagnostic error "-Wsign-conversion"
#endif
// #define DEBUG_STRSIZE
/* array copied from glib's gutf8.c, */
/* NOTE: last two values (0xfe and 0xff) are forbidden in utf-8,
* so they are considered 1 byte length too. */
static const size_t utf8_skip_data[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,
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,
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, 5, 5, 5, 5, 6, 6, 1, 1,
};
/* from libswish3, originally called u8_isvalid(),
* modified to return the index of the bad character (byte index not utf).
* http://svn.swish-e.org/libswish3/trunk/src/libswish3/utf8.c r3044 - campbell */
/* based on the valid_utf8 routine from the PCRE library by Philip Hazel
*
* length is in bytes, since without knowing whether the string is valid
* it's hard to know how many characters there are! */
/**
* Find first utf-8 invalid byte in given \a str, of \a length bytes.
*
* \return the offset of the first invalid byte.
*/
ptrdiff_t BLI_str_utf8_invalid_byte(const char *str, size_t length)
{
const unsigned char *p, *perr, *pend = (const unsigned char *)str + length;
unsigned char c;
int ab;
for (p = (const unsigned char *)str; p < pend; p++, length--) {
c = *p;
perr = p; /* Erroneous char is always the first of an invalid utf8 sequence... */
if (ELEM(c, 0xfe, 0xff, 0x00)) {
/* Those three values are not allowed in utf8 string. */
goto utf8_error;
}
if (c < 128) {
continue;
}
if ((c & 0xc0) != 0xc0) {
goto utf8_error;
}
/* Note that since we always increase p (and decrease length) by one byte in main loop,
* we only add/subtract extra utf8 bytes in code below
* (ab number, aka number of bytes remaining in the utf8 sequence after the initial one). */
ab = (int)utf8_skip_data[c] - 1;
if (length <= ab) {
goto utf8_error;
}
/* Check top bits in the second byte */
p++;
length--;
if ((*p & 0xc0) != 0x80) {
goto utf8_error;
}
/* Check for overlong sequences for each different length */
switch (ab) {
case 1:
/* Check for xx00 000x */
if ((c & 0x3e) == 0) {
goto utf8_error;
}
continue; /* We know there aren't any more bytes to check */
case 2:
/* Check for 1110 0000, xx0x xxxx */
if (c == 0xe0 && (*p & 0x20) == 0) {
goto utf8_error;
}
/* Some special cases, see section 5 of utf-8 decoder stress-test by Markus Kuhn
* (https://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt). */
/* From section 5.1 (and 5.2) */
if (c == 0xed) {
if (*p == 0xa0 && *(p + 1) == 0x80) {
goto utf8_error;
}
if (*p == 0xad && *(p + 1) == 0xbf) {
goto utf8_error;
}
if (*p == 0xae && *(p + 1) == 0x80) {
goto utf8_error;
}
if (*p == 0xaf && *(p + 1) == 0xbf) {
goto utf8_error;
}
if (*p == 0xb0 && *(p + 1) == 0x80) {
goto utf8_error;
}
if (*p == 0xbe && *(p + 1) == 0x80) {
goto utf8_error;
}
if (*p == 0xbf && *(p + 1) == 0xbf) {
goto utf8_error;
}
}
/* From section 5.3 */
if (c == 0xef) {
if (*p == 0xbf && *(p + 1) == 0xbe) {
goto utf8_error;
}
if (*p == 0xbf && *(p + 1) == 0xbf) {
goto utf8_error;
}
}
break;
case 3:
/* Check for 1111 0000, xx00 xxxx */
if (c == 0xf0 && (*p & 0x30) == 0) {
goto utf8_error;
}
break;
case 4:
/* Check for 1111 1000, xx00 0xxx */
if (c == 0xf8 && (*p & 0x38) == 0) {
goto utf8_error;
}
break;
case 5:
/* Check for 1111 1100, xx00 00xx */
if (c == 0xfc && (*p & 0x3c) == 0) {
goto utf8_error;
}
break;
}
/* Check for valid bytes after the 2nd, if any; all must start 10 */
while (--ab > 0) {
p++;
length--;
if ((*p & 0xc0) != 0x80) {
goto utf8_error;
}
}
}
return -1;
utf8_error:
return ((const char *)perr - (const char *)str);
}
/**
* Remove any invalid utf-8 byte (taking into account multi-bytes sequence of course).
*
* \return number of stripped bytes.
*/
int BLI_str_utf8_invalid_strip(char *str, size_t length)
{
ptrdiff_t bad_char;
int tot = 0;
BLI_assert(str[length] == '\0');
while ((bad_char = BLI_str_utf8_invalid_byte(str, length)) != -1) {
str += bad_char;
length -= (size_t)(bad_char + 1);
if (length == 0) {
/* last character bad, strip it */
*str = '\0';
tot++;
break;
}
/* strip, keep looking */
memmove(str, str + 1, length + 1); /* +1 for NULL char! */
tot++;
}
return tot;
}
/** Compatible with #BLI_strncpy, but ensure no partial UTF8 chars. */
#define BLI_STR_UTF8_CPY(dst, src, maxncpy) \
{ \
size_t utf8_size; \
while (*src != '\0' && (utf8_size = utf8_skip_data[*src]) < maxncpy) { \
maxncpy -= utf8_size; \
switch (utf8_size) { \
case 6: \
*dst++ = *src++; \
ATTR_FALLTHROUGH; \
case 5: \
*dst++ = *src++; \
ATTR_FALLTHROUGH; \
case 4: \
*dst++ = *src++; \
ATTR_FALLTHROUGH; \
case 3: \
*dst++ = *src++; \
ATTR_FALLTHROUGH; \
case 2: \
*dst++ = *src++; \
ATTR_FALLTHROUGH; \
case 1: \
*dst++ = *src++; \
} \
} \
*dst = '\0'; \
} \
(void)0
char *BLI_strncpy_utf8(char *__restrict dst, const char *__restrict src, size_t maxncpy)
{
char *r_dst = dst;
BLI_assert(maxncpy != 0);
#ifdef DEBUG_STRSIZE
memset(dst, 0xff, sizeof(*dst) * maxncpy);
#endif
/* NOTE: currently we don't attempt to deal with invalid utf8 chars. */
BLI_STR_UTF8_CPY(dst, src, maxncpy);
return r_dst;
}
size_t BLI_strncpy_utf8_rlen(char *__restrict dst, const char *__restrict src, size_t maxncpy)
{
char *r_dst = dst;
BLI_assert(maxncpy != 0);
#ifdef DEBUG_STRSIZE
memset(dst, 0xff, sizeof(*dst) * maxncpy);
#endif
/* NOTE: currently we don't attempt to deal with invalid utf8 chars. */
BLI_STR_UTF8_CPY(dst, src, maxncpy);
return (size_t)(dst - r_dst);
}
#undef BLI_STR_UTF8_CPY
/* --------------------------------------------------------------------------*/
/* wchar_t / utf8 functions */
size_t BLI_strncpy_wchar_as_utf8(char *__restrict dst,
const wchar_t *__restrict src,
const size_t maxncpy)
{
const size_t maxlen = maxncpy - 1;
/* 6 is max utf8 length of an unicode char. */
const int64_t maxlen_secured = (int64_t)maxlen - 6;
size_t len = 0;
BLI_assert(maxncpy != 0);
#ifdef DEBUG_STRSIZE
memset(dst, 0xff, sizeof(*dst) * maxncpy);
#endif
while (*src && len <= maxlen_secured) {
len += BLI_str_utf8_from_unicode((uint)*src++, dst + len);
}
/* We have to be more careful for the last six bytes,
* to avoid buffer overflow in case utf8-encoded char would be too long for our dst buffer. */
while (*src) {
char t[6];
size_t l = BLI_str_utf8_from_unicode((uint)*src++, t);
BLI_assert(l <= 6);
if (len + l > maxlen) {
break;
}
memcpy(dst + len, t, l);
len += l;
}
dst[len] = '\0';
return len;
}
/* wchar len in utf8 */
size_t BLI_wstrlen_utf8(const wchar_t *src)
{
size_t len = 0;
while (*src) {
len += BLI_str_utf8_from_unicode((uint)*src++, NULL);
}
return len;
}
size_t BLI_strlen_utf8_ex(const char *strc, size_t *r_len_bytes)
{
size_t len;
const char *strc_orig = strc;
for (len = 0; *strc; len++) {
strc += BLI_str_utf8_size_safe(strc);
}
*r_len_bytes = (size_t)(strc - strc_orig);
return len;
}
size_t BLI_strlen_utf8(const char *strc)
{
size_t len_bytes;
return BLI_strlen_utf8_ex(strc, &len_bytes);
}
size_t BLI_strnlen_utf8_ex(const char *strc, const size_t maxlen, size_t *r_len_bytes)
{
size_t len = 0;
const char *strc_orig = strc;
const char *strc_end = strc + maxlen;
while (true) {
size_t step = (size_t)BLI_str_utf8_size_safe(strc);
if (!*strc || strc + step > strc_end) {
break;
}
strc += step;
len++;
}
*r_len_bytes = (size_t)(strc - strc_orig);
return len;
}
/**
* \param strc: the string to measure the length.
* \param maxlen: the string length (in bytes)
* \return the unicode length (not in bytes!)
*/
size_t BLI_strnlen_utf8(const char *strc, const size_t maxlen)
{
size_t len_bytes;
return BLI_strnlen_utf8_ex(strc, maxlen, &len_bytes);
}
size_t BLI_strncpy_wchar_from_utf8(wchar_t *__restrict dst_w,
const char *__restrict src_c,
const size_t maxncpy)
{
#ifdef WIN32
return conv_utf_8_to_16(src_c, dst_w, maxncpy);
#else
return BLI_str_utf8_as_utf32((char32_t *)dst_w, src_c, maxncpy);
#endif
}
/* end wchar_t / utf8 functions */
/* --------------------------------------------------------------------------*/
/* count columns that character/string occupies, based on wcwidth.c */
int BLI_wcwidth(char32_t ucs)
{
return mk_wcwidth(ucs);
}
int BLI_wcswidth(const char32_t *pwcs, size_t n)
{
return mk_wcswidth(pwcs, n);
}
int BLI_str_utf8_char_width(const char *p)
{
uint unicode = BLI_str_utf8_as_unicode(p);
if (unicode == BLI_UTF8_ERR) {
return -1;
}
return BLI_wcwidth((char32_t)unicode);
}
int BLI_str_utf8_char_width_safe(const char *p)
{
int columns;
uint unicode = BLI_str_utf8_as_unicode(p);
if (unicode == BLI_UTF8_ERR) {
return 1;
}
columns = BLI_wcwidth((char32_t)unicode);
return (columns < 0) ? 1 : columns;
}
/* --------------------------------------------------------------------------*/
/* copied from glib's gutf8.c, added 'Err' arg */
/* NOTE(campbell): glib uses uint for unicode, best we do the same,
* though we don't typedef it. */
#define UTF8_COMPUTE(Char, Mask, Len, Err) \
if (Char < 128) { \
Len = 1; \
Mask = 0x7f; \
} \
else if ((Char & 0xe0) == 0xc0) { \
Len = 2; \
Mask = 0x1f; \
} \
else if ((Char & 0xf0) == 0xe0) { \
Len = 3; \
Mask = 0x0f; \
} \
else if ((Char & 0xf8) == 0xf0) { \
Len = 4; \
Mask = 0x07; \
} \
else if ((Char & 0xfc) == 0xf8) { \
Len = 5; \
Mask = 0x03; \
} \
else if ((Char & 0xfe) == 0xfc) { \
Len = 6; \
Mask = 0x01; \
} \
else { \
Len = Err; /* -1 is the typical error value or 1 to skip */ \
} \
(void)0
/* same as glib define but added an 'Err' arg */
#define UTF8_GET(Result, Chars, Count, Mask, Len, Err) \
(Result) = (Chars)[0] & (Mask); \
for ((Count) = 1; (Count) < (Len); ++(Count)) { \
if (((Chars)[(Count)] & 0xc0) != 0x80) { \
(Result) = Err; \
break; \
} \
(Result) <<= 6; \
(Result) |= ((Chars)[(Count)] & 0x3f); \
} \
(void)0
/* uses glib functions but not from glib */
/* gets the size of a single utf8 char */
int BLI_str_utf8_size(const char *p)
{
int mask = 0, len;
const unsigned char c = (unsigned char)*p;
UTF8_COMPUTE(c, mask, len, -1);
(void)mask; /* quiet warning */
return len;
}
/* use when we want to skip errors */
int BLI_str_utf8_size_safe(const char *p)
{
int mask = 0, len;
const unsigned char c = (unsigned char)*p;
UTF8_COMPUTE(c, mask, len, 1);
(void)mask; /* quiet warning */
return len;
}
/* was g_utf8_get_char */
/**
* BLI_str_utf8_as_unicode:
* \param p: a pointer to Unicode character encoded as UTF-8
*
* Converts a sequence of bytes encoded as UTF-8 to a Unicode character.
* If \a p does not point to a valid UTF-8 encoded character, results are
* undefined. If you are not sure that the bytes are complete
* valid Unicode characters, you should use g_utf8_get_char_validated()
* instead.
*
* Return value: the resulting character
*/
uint BLI_str_utf8_as_unicode(const char *p)
{
int i, len;
uint mask = 0;
uint result;
const unsigned char c = (unsigned char)*p;
UTF8_COMPUTE(c, mask, len, -1);
if (UNLIKELY(len == -1)) {
return BLI_UTF8_ERR;
}
UTF8_GET(result, p, i, mask, len, BLI_UTF8_ERR);
return result;
}
/**
* UTF8 decoding that steps over the index (unless an error is encountered).
*
* \param p: The text to step over.
* \param p_len: The length of `p`.
* \param index: Index of `p` to step over.
* \return the code-point or #BLI_UTF8_ERR if there is a decoding error.
*
* \note The behavior for clipped text (where `p_len` limits decoding trailing bytes)
* must have the same behavior is encountering a nil byte,
* so functions that only use the first part of a string has matching behavior to functions
* that null terminate the text.
*/
uint BLI_str_utf8_as_unicode_step_or_error(const char *__restrict p,
const size_t p_len,
size_t *__restrict index)
{
int i, len;
uint mask = 0;
uint result;
const unsigned char c = (unsigned char)*(p += *index);
BLI_assert(*index < p_len);
BLI_assert(c != '\0');
UTF8_COMPUTE(c, mask, len, -1);
if (UNLIKELY(len == -1) || (*index + (size_t)len > p_len)) {
return BLI_UTF8_ERR;
}
UTF8_GET(result, p, i, mask, len, BLI_UTF8_ERR);
if (UNLIKELY(result == BLI_UTF8_ERR)) {
return BLI_UTF8_ERR;
}
*index += (size_t)len;
BLI_assert(*index <= p_len);
return result;
}
/**
* UTF8 decoding that steps over the index (unless an error is encountered).
*
* \param p: The text to step over.
* \param p_len: The length of `p`.
* \param index: Index of `p` to step over.
* \return the code-point `(p + *index)` if there is a decoding error.
*
* \note Falls back to `LATIN1` for text drawing.
*/
uint BLI_str_utf8_as_unicode_step(const char *__restrict p,
const size_t p_len,
size_t *__restrict index)
{
uint result = BLI_str_utf8_as_unicode_step_or_error(p, p_len, index);
if (UNLIKELY(result == BLI_UTF8_ERR)) {
result = (uint)p[*index];
*index += 1;
}
BLI_assert(*index <= p_len);
return result;
}
/* was g_unichar_to_utf8 */
/**
* BLI_str_utf8_from_unicode:
* \param c: a Unicode character code
* \param outbuf: output buffer, must have at least 6 bytes of space.
* If %NULL, the length will be computed and returned
* and nothing will be written to outbuf.
*
* Converts a single character to UTF-8.
*
* \return number of bytes written
*/
size_t BLI_str_utf8_from_unicode(uint c, char *outbuf)
{
/* If this gets modified, also update the copy in g_string_insert_unichar() */
uint len = 0;
uint first;
uint i;
if (c < 0x80) {
first = 0;
len = 1;
}
else if (c < 0x800) {
first = 0xc0;
len = 2;
}
else if (c < 0x10000) {
first = 0xe0;
len = 3;
}
else if (c < 0x200000) {
first = 0xf0;
len = 4;
}
else if (c < 0x4000000) {
first = 0xf8;
len = 5;
}
else {
first = 0xfc;
len = 6;
}
if (outbuf) {
for (i = len - 1; i > 0; i--) {
outbuf[i] = (c & 0x3f) | 0x80;
c >>= 6;
}
outbuf[0] = c | first;
}
return len;
}
size_t BLI_str_utf8_as_utf32(char32_t *__restrict dst_w,
const char *__restrict src_c,
const size_t maxncpy)
{
const size_t maxlen = maxncpy - 1;
size_t len = 0;
BLI_assert(maxncpy != 0);
#ifdef DEBUG_STRSIZE
memset(dst_w, 0xff, sizeof(*dst_w) * maxncpy);
#endif
const size_t src_c_len = strlen(src_c);
const char *src_c_end = src_c + src_c_len;
size_t index = 0;
while (*src_c && len != maxlen) {
const uint unicode = BLI_str_utf8_as_unicode_step_or_error(src_c, src_c_len, &index);
if (unicode != BLI_UTF8_ERR) {
*dst_w = unicode;
}
else {
*dst_w = '?';
const char *src_c_next = BLI_str_find_next_char_utf8(src_c + index, src_c_end);
if (src_c_next != NULL) {
index = (size_t)(src_c_next - src_c);
}
else {
index += 1;
}
}
dst_w++;
len++;
}
*dst_w = 0;
return len;
}
size_t BLI_str_utf32_as_utf8(char *__restrict dst,
const char32_t *__restrict src,
const size_t maxncpy)
{
const size_t maxlen = maxncpy - 1;
/* 6 is max utf8 length of an unicode char. */
const int64_t maxlen_secured = (int64_t)maxlen - 6;
size_t len = 0;
BLI_assert(maxncpy != 0);
#ifdef DEBUG_STRSIZE
memset(dst, 0xff, sizeof(*dst) * maxncpy);
#endif
while (*src && len <= maxlen_secured) {
len += BLI_str_utf8_from_unicode((uint)*src++, dst + len);
}
/* We have to be more careful for the last six bytes,
* to avoid buffer overflow in case utf8-encoded char would be too long for our dst buffer. */
while (*src) {
char t[6];
size_t l = BLI_str_utf8_from_unicode((uint)*src++, t);
BLI_assert(l <= 6);
if (len + l > maxlen) {
break;
}
memcpy(dst + len, t, l);
len += l;
}
dst[len] = '\0';
return len;
}
/* utf32 len in utf8 */
size_t BLI_str_utf32_as_utf8_len(const char32_t *src)
{
size_t len = 0;
while (*src) {
len += BLI_str_utf8_from_unicode((uint)*src++, NULL);
}
return len;
}
/* was g_utf8_find_prev_char */
/**
* BLI_str_find_prev_char_utf8:
* \param str: pointer to the beginning of a UTF-8 encoded string
* \param p: pointer to some position within \a str
*
* Given a position \a p with a UTF-8 encoded string \a str, find the start
* of the previous UTF-8 character starting before. \a p Returns %NULL if no
* UTF-8 characters are present in \a str before \a p
*
* \a p does not have to be at the beginning of a UTF-8 character. No check
* is made to see if the character found is actually valid other than
* it starts with an appropriate byte.
*
* Return value: a pointer to the found character or %NULL.
*/
char *BLI_str_find_prev_char_utf8(const char *str, const char *p)
{
for (--p; p >= str; p--) {
if ((*p & 0xc0) != 0x80) {
return (char *)p;
}
}
return NULL;
}
/* was g_utf8_find_next_char */
/**
* BLI_str_find_next_char_utf8:
* \param p: a pointer to a position within a UTF-8 encoded string
* \param end: a pointer to the byte following the end of the string,
* or %NULL to indicate that the string is nul-terminated.
*
* Finds the start of the next UTF-8 character in the string after \a p
*
* \a p does not have to be at the beginning of a UTF-8 character. No check
* is made to see if the character found is actually valid other than
* it starts with an appropriate byte.
*
* Return value: a pointer to the found character or %NULL
*/
char *BLI_str_find_next_char_utf8(const char *p, const char *end)
{
if (*p) {
if (end) {
BLI_assert(end >= p);
for (++p; p < end && (*p & 0xc0) == 0x80; p++) {
/* do nothing */
}
}
else {
for (++p; (*p & 0xc0) == 0x80; p++) {
/* do nothing */
}
}
}
return (p == end) ? NULL : (char *)p;
}
/* was g_utf8_prev_char */
/**
* BLI_str_prev_char_utf8:
* \param p: a pointer to a position within a UTF-8 encoded string
*
* Finds the previous UTF-8 character in the string before \a p
*
* \a p does not have to be at the beginning of a UTF-8 character. No check
* is made to see if the character found is actually valid other than
* it starts with an appropriate byte. If \a p might be the first
* character of the string, you must use g_utf8_find_prev_char() instead.
*
* Return value: a pointer to the found character.
*/
char *BLI_str_prev_char_utf8(const char *p)
{
while (1) {
p--;
if ((*p & 0xc0) != 0x80) {
return (char *)p;
}
}
}
/* end glib copy */
size_t BLI_str_partition_utf8(const char *str,
const uint delim[],
const char **sep,
const char **suf)
{
return BLI_str_partition_ex_utf8(str, NULL, delim, sep, suf, false);
}
size_t BLI_str_rpartition_utf8(const char *str,
const uint delim[],
const char **sep,
const char **suf)
{
return BLI_str_partition_ex_utf8(str, NULL, delim, sep, suf, true);
}
size_t BLI_str_partition_ex_utf8(const char *str,
const char *end,
const uint delim[],
const char **sep,
const char **suf,
const bool from_right)
{
const uint *d;
const size_t str_len = end ? (size_t)(end - str) : strlen(str);
size_t index;
/* Note that here, we assume end points to a valid utf8 char! */
BLI_assert(end == NULL || (end >= str && (BLI_str_utf8_as_unicode(end) != BLI_UTF8_ERR)));
*suf = (char *)(str + str_len);
for (*sep = (char *)(from_right ? BLI_str_find_prev_char_utf8(str, str + str_len) : str),
index = 0;
*sep >= str && (!end || *sep < end) && **sep != '\0';
*sep = (char *)(from_right ? BLI_str_find_prev_char_utf8(str, *sep) : str + index)) {
size_t index_ofs = 0;
const uint c = BLI_str_utf8_as_unicode_step_or_error(*sep, (size_t)(end - *sep), &index_ofs);
index += index_ofs;
if (c == BLI_UTF8_ERR) {
*suf = *sep = NULL;
break;
}
for (d = delim; *d != '\0'; d++) {
if (*d == c) {
/* *suf is already correct in case from_right is true. */
if (!from_right) {
*suf = (char *)(str + index);
}
return (size_t)(*sep - str);
}
}
*suf = *sep; /* Useful in 'from_right' case! */
}
*suf = *sep = NULL;
return str_len;
}
/* -------------------------------------------------------------------- */
/** \name Offset Conversion in Strings
* \{ */
int BLI_str_utf8_offset_to_index(const char *str, int offset)
{
int index = 0, pos = 0;
while (pos != offset) {
pos += BLI_str_utf8_size(str + pos);
index++;
}
return index;
}
int BLI_str_utf8_offset_from_index(const char *str, int index)
{
int offset = 0, pos = 0;
while (pos != index) {
offset += BLI_str_utf8_size(str + offset);
pos++;
}
return offset;
}
int BLI_str_utf8_offset_to_column(const char *str, int offset)
{
int column = 0, pos = 0;
while (pos < offset) {
column += BLI_str_utf8_char_width_safe(str + pos);
pos += BLI_str_utf8_size_safe(str + pos);
}
return column;
}
int BLI_str_utf8_offset_from_column(const char *str, int column)
{
int offset = 0, pos = 0, col;
while (*(str + offset) && pos < column) {
col = BLI_str_utf8_char_width_safe(str + offset);
if (pos + col > column) {
break;
}
offset += BLI_str_utf8_size_safe(str + offset);
pos += col;
}
return offset;
}
/** \} */
|