summaryrefslogtreecommitdiff
path: root/utf8.c
blob: a42fae6469032f65c20d4a7262ea178b1dc7452a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
/*
    DeaDBeeF - ultimate music player for GNU/Linux systems with X11
    Copyright (C) 2009  Alexey Yakovenko

    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, see <http://www.gnu.org/licenses/>.

    utf8 code is based on Basic UTF-8 manipulation routines
    by Jeff Bezanson
    placed in the public domain Fall 2005
*/
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <stdarg.h>
#include <alloca.h>
#include "ctype.h"
#include "utf8.h"

static const uint32_t offsetsFromUTF8[6] = {
    0x00000000UL, 0x00003080UL, 0x000E2080UL,
    0x03C82080UL, 0xFA082080UL, 0x82082080UL
};

static const char trailingBytesForUTF8[256] = {
    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,
    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,
    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,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 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, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
};

/* conversions without error checking
   only works for valid UTF-8, i.e. no 5- or 6-byte sequences
   srcsz = source size in bytes, or -1 if 0-terminated
   sz = dest size in # of wide characters

   returns # characters converted
   dest will always be L'\0'-terminated, even if there isn't enough room
   for all the characters.
   if sz = srcsz+1 (i.e. 4*srcsz+4 bytes), there will always be enough space.
*/
int u8_toucs(uint32_t *dest, int32_t sz, const char *src, int32_t srcsz)
{
    uint32_t ch;
    const char *src_end = src + srcsz;
    int32_t nb;
    int32_t i=0;

    while (i < sz-1) {
        nb = trailingBytesForUTF8[(unsigned char)*src];
        if (srcsz == -1) {
            if (*src == 0)
                goto done_toucs;
        }
        else {
            if (src + nb >= src_end)
                goto done_toucs;
        }
        ch = 0;
        switch (nb) {
            /* these fall through deliberately */
        case 3: ch += (unsigned char)*src++; ch <<= 6;
        case 2: ch += (unsigned char)*src++; ch <<= 6;
        case 1: ch += (unsigned char)*src++; ch <<= 6;
        case 0: ch += (unsigned char)*src++;
        }
        ch -= offsetsFromUTF8[nb];
        dest[i++] = ch;
    }
 done_toucs:
    dest[i] = 0;
    return i;
}

/* srcsz = number of source characters, or -1 if 0-terminated
   sz = size of dest buffer in bytes

   returns # characters converted
   dest will only be '\0'-terminated if there is enough space. this is
   for consistency; imagine there are 2 bytes of space left, but the next
   character requires 3 bytes. in this case we could NUL-terminate, but in
   general we can't when there's insufficient space. therefore this function
   only NUL-terminates if all the characters fit, and there's space for
   the NUL as well.
   the destination string will never be bigger than the source string.
*/
int u8_toutf8(char *dest, int32_t sz, uint32_t *src, int32_t srcsz)
{
    uint32_t ch;
    int32_t i = 0;
    char *dest_end = dest + sz;

    while (srcsz<0 ? src[i]!=0 : i < srcsz) {
        ch = src[i];
        if (ch < 0x80) {
            if (dest >= dest_end)
                return i;
            *dest++ = (char)ch;
        }
        else if (ch < 0x800) {
            if (dest >= dest_end-1)
                return i;
            *dest++ = (ch>>6) | 0xC0;
            *dest++ = (ch & 0x3F) | 0x80;
        }
        else if (ch < 0x10000) {
            if (dest >= dest_end-2)
                return i;
            *dest++ = (ch>>12) | 0xE0;
            *dest++ = ((ch>>6) & 0x3F) | 0x80;
            *dest++ = (ch & 0x3F) | 0x80;
        }
        else if (ch < 0x200000) {
            if (dest >= dest_end-3)
                return i;
            *dest++ = (ch>>18) | 0xF0;
            *dest++ = ((ch>>12) & 0x3F) | 0x80;
            *dest++ = ((ch>>6) & 0x3F) | 0x80;
            *dest++ = (ch & 0x3F) | 0x80;
        }
        i++;
    }
    if (dest < dest_end)
        *dest = '\0';
    return i;
}

int u8_wc_toutf8(char *dest, wchar_t ch)
{
    if (ch < 0x80) {
        dest[0] = (char)ch;
        return 1;
    }
    if (ch < 0x800) {
        dest[0] = (ch>>6) | 0xC0;
        dest[1] = (ch & 0x3F) | 0x80;
        return 2;
    }
    if (ch < 0x10000) {
        dest[0] = (ch>>12) | 0xE0;
        dest[1] = ((ch>>6) & 0x3F) | 0x80;
        dest[2] = (ch & 0x3F) | 0x80;
        return 3;
    }
    if (ch < 0x200000) {
        dest[0] = (ch>>18) | 0xF0;
        dest[1] = ((ch>>12) & 0x3F) | 0x80;
        dest[2] = ((ch>>6) & 0x3F) | 0x80;
        dest[3] = (ch & 0x3F) | 0x80;
        return 4;
    }
    return 0;
}

/* charnum => byte offset */
int u8_offset(char *str, int32_t charnum)
{
    int32_t offs=0;

    while (charnum > 0 && str[offs]) {
        (void)(isutf(str[++offs]) || isutf(str[++offs]) ||
               isutf(str[++offs]) || ++offs);
        charnum--;
    }
    return offs;
}

/* byte offset => charnum */
int u8_charnum(char *s, int32_t offset)
{
    int32_t charnum = 0, offs=0;

    while (offs < offset && s[offs]) {
        (void)(isutf(s[++offs]) || isutf(s[++offs]) ||
               isutf(s[++offs]) || ++offs);
        charnum++;
    }
    return charnum;
}

/* number of characters */
int u8_strlen(char *s)
{
    int32_t count = 0;
    int32_t i = 0;

    while (u8_nextchar(s, &i) != 0)
        count++;

    return count;
}

/* reads the next utf-8 sequence out of a string, updating an index */
uint32_t u8_nextchar(const char *s, int32_t *i)
{
    uint32_t ch = 0;
    int32_t sz = 0;

    do {
        ch <<= 6;
        ch += (unsigned char)s[(*i)++];
        sz++;
    } while (s[*i] && !isutf(s[*i]));
    ch -= offsetsFromUTF8[sz-1];

    return ch;
}

void u8_inc(const char *s, int32_t *i)
{
    (void)(isutf(s[++(*i)]) || isutf(s[++(*i)]) ||
           isutf(s[++(*i)]) || ++(*i));
}

void u8_dec(const char *s, int32_t *i)
{
    (void)(isutf(s[--(*i)]) || isutf(s[--(*i)]) ||
           isutf(s[--(*i)]) || --(*i));
}

int octal_digit(char c)
{
    return (c >= '0' && c <= '7');
}

int hex_digit(char c)
{
    return ((c >= '0' && c <= '9') ||
            (c >= 'A' && c <= 'F') ||
            (c >= 'a' && c <= 'f'));
}

/* assumes that src points to the character after a backslash
   returns number of input characters processed */
int u8_read_escape_sequence(const char *str, uint32_t *dest)
{
    uint32_t ch;
    char digs[]="\0\0\0\0\0\0\0\0\0";
    int32_t dno=0, i=1;

    ch = (uint32_t)str[0];    /* take literal character */
    if (str[0] == 'n')
        ch = L'\n';
    else if (str[0] == 't')
        ch = L'\t';
    else if (str[0] == 'r')
        ch = L'\r';
    else if (str[0] == 'b')
        ch = L'\b';
    else if (str[0] == 'f')
        ch = L'\f';
    else if (str[0] == 'v')
        ch = L'\v';
    else if (str[0] == 'a')
        ch = L'\a';
    else if (octal_digit(str[0])) {
        i = 0;
        do {
            digs[dno++] = str[i++];
        } while (octal_digit(str[i]) && dno < 3);
        ch = strtol(digs, NULL, 8);
    }
    else if (str[0] == 'x') {
        while (hex_digit(str[i]) && dno < 2) {
            digs[dno++] = str[i++];
        }
        if (dno > 0)
            ch = strtol(digs, NULL, 16);
    }
    else if (str[0] == 'u') {
        while (hex_digit(str[i]) && dno < 4) {
            digs[dno++] = str[i++];
        }
        if (dno > 0)
            ch = strtol(digs, NULL, 16);
    }
    else if (str[0] == 'U') {
        while (hex_digit(str[i]) && dno < 8) {
            digs[dno++] = str[i++];
        }
        if (dno > 0)
            ch = strtol(digs, NULL, 16);
    }
    *dest = ch;

    return i;
}

// convert a string with literal \uxxxx or \Uxxxxxxxx characters to UTF-8
// example: u8_unescape(mybuf, 256, "hello\\u220e")
// note the double backslash is needed if called on a C string literal
int u8_unescape(char *buf, int32_t sz, const char *src)
{
    int32_t c=0, amt;
    uint32_t ch;
    char temp[4];

    while (*src && c < sz) {
        if (*src == '\\') {
            src++;
            amt = u8_read_escape_sequence(src, &ch);
        }
        else {
            ch = (uint32_t)*src;
            amt = 1;
        }
        src += amt;
        amt = u8_wc_toutf8(temp, ch);
        if (amt > sz-c)
            break;
        memcpy(&buf[c], temp, amt);
        c += amt;
    }
    if (c < sz)
        buf[c] = '\0';
    return c;
}

int u8_escape_wchar(char *buf, int32_t sz, uint32_t ch)
{
    if (ch == L'\n')
        return snprintf(buf, sz, "\\n");
    else if (ch == L'\t')
        return snprintf(buf, sz, "\\t");
    else if (ch == L'\r')
        return snprintf(buf, sz, "\\r");
    else if (ch == L'\b')
        return snprintf(buf, sz, "\\b");
    else if (ch == L'\f')
        return snprintf(buf, sz, "\\f");
    else if (ch == L'\v')
        return snprintf(buf, sz, "\\v");
    else if (ch == L'\a')
        return snprintf(buf, sz, "\\a");
    else if (ch == L'\\')
        return snprintf(buf, sz, "\\\\");
    else if (ch < 32 || ch == 0x7f)
        return snprintf(buf, sz, "\\x%hhX", (unsigned char)ch);
    else if (ch > 0xFFFF)
        return snprintf(buf, sz, "\\U%.8lX", (uint32_t)ch);
    else if (ch >= 0x80 && ch <= 0xFFFF)
        return snprintf(buf, sz, "\\u%.4hX", (unsigned short)ch);

    return snprintf(buf, sz, "%c", (char)ch);
}

int u8_escape(char *buf, int32_t sz, const char *src, int32_t escape_quotes)
{
    int32_t c=0, i=0, amt;

    while (src[i] && c < sz) {
        if (escape_quotes && src[i] == '"') {
            amt = snprintf(buf, sz - c, "\\\"");
            i++;
        }
        else {
            amt = u8_escape_wchar(buf, sz - c, u8_nextchar(src, &i));
        }
        c += amt;
        buf += amt;
    }
    if (c < sz)
        *buf = '\0';
    return c;
}

char *u8_strchr(char *s, uint32_t ch, int32_t *charn)
{
    int32_t i = 0, lasti=0;
    uint32_t c;

    *charn = 0;
    while (s[i]) {
        c = u8_nextchar(s, &i);
        if (c == ch) {
            return &s[lasti];
        }
        lasti = i;
        (*charn)++;
    }
    return NULL;
}

char *u8_memchr(char *s, uint32_t ch, size_t sz, int32_t *charn)
{
    int32_t i = 0, lasti=0;
    uint32_t c;
    int32_t csz;

    *charn = 0;
    while (i < sz) {
        c = csz = 0;
        do {
            c <<= 6;
            c += (unsigned char)s[i++];
            csz++;
        } while (i < sz && !isutf(s[i]));
        c -= offsetsFromUTF8[csz-1];

        if (c == ch) {
            return &s[lasti];
        }
        lasti = i;
        (*charn)++;
    }
    return NULL;
}

int u8_is_locale_utf8(char *locale)
{
    /* this code based on libutf8 */
    const char* cp = locale;

    for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++) {
        if (*cp == '.') {
            const char* encoding = ++cp;
            for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++)
                ;
            if ((cp-encoding == 5 && !strncmp(encoding, "UTF-8", 5))
                || (cp-encoding == 4 && !strncmp(encoding, "utf8", 4)))
                return 1; /* it's UTF-8 */
            break;
        }
    }
    return 0;
}

int u8_vprintf(char *fmt, va_list ap)
{
    int32_t cnt, sz=0;
    char *buf;
    uint32_t *wcs;

    sz = 512;
    buf = (char*)alloca(sz);
 try_print:
    cnt = vsnprintf(buf, sz, fmt, ap);
    if (cnt >= sz) {
        buf = (char*)alloca(cnt - sz + 1);
        sz = cnt + 1;
        goto try_print;
    }
    wcs = (uint32_t*)alloca((cnt+1) * sizeof(uint32_t));
    cnt = u8_toucs(wcs, cnt+1, buf, cnt);
    printf("%ls", (wchar_t*)wcs);
    return cnt;
}

int u8_printf(char *fmt, ...)
{
    int32_t cnt;
    va_list args;

    va_start(args, fmt);

    cnt = u8_vprintf(fmt, args);

    va_end(args);
    return cnt;
}

// adaptation of g_utf8_validate

#define UTF8_COMPUTE(Char, Mask, Len)                                         \
  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 = -1;

#define UTF8_LENGTH(Char)              \
  ((Char) < 0x80 ? 1 :                 \
   ((Char) < 0x800 ? 2 :               \
    ((Char) < 0x10000 ? 3 :            \
     ((Char) < 0x200000 ? 4 :          \
      ((Char) < 0x4000000 ? 5 : 6)))))


#define UTF8_GET(Result, Chars, Count, Mask, Len)                             \
  (Result) = (Chars)[0] & (Mask);                                             \
  for ((Count) = 1; (Count) < (Len); ++(Count))                               \
    {                                                                         \
      if (((Chars)[(Count)] & 0xc0) != 0x80)                                  \
        {                                                                     \
          (Result) = -1;                                                      \
          break;                                                              \
        }                                                                     \
      (Result) <<= 6;                                                         \
      (Result) |= ((Chars)[(Count)] & 0x3f);                                  \
    }

#define UNICODE_VALID(Char)                   \
    ((Char) < 0x110000 &&                     \
     (((Char) & 0xFFFFF800) != 0xD800) &&     \
     ((Char) < 0xFDD0 || (Char) > 0xFDEF) &&  \
     ((Char) & 0xFFFE) != 0xFFFE)


int u8_valid (const char  *str,
        int max_len,
        const char **end)
{

    const char *p;

    if (!str) {
        return 0;
    }

    if (end)
        *end = str;

    p = str;

    while ((max_len < 0 || (p - str) < max_len) && *p)
    {
        int i, mask = 0, len;
        int32_t result;
        unsigned char c = (unsigned char) *p;

        UTF8_COMPUTE (c, mask, len);

        if (len == -1)
            break;

        /* check that the expected number of bytes exists in str */
        if (max_len >= 0 &&
                ((max_len - (p - str)) < len))
            break;

        UTF8_GET (result, p, i, mask, len);

        if (UTF8_LENGTH (result) != len) /* Check for overlong UTF-8 */
            break;

        if (result == (int32_t)-1)
            break;

        if (!UNICODE_VALID (result))
            break;

        p += len;
    }

    if (end)
        *end = p;

    /* See that we covered the entire length if a length was
     * passed in, or that we ended on a nul if not
     */
    if (max_len >= 0 &&
            p != (str + max_len))
        return 0;
    else if (max_len < 0 &&
            *p != '\0')
        return 0;
    else
        return 1;
}

static const char lowerchars[] = "záéíñóúüäöåæøàçèéêабвгдеёжзийклмнорпстуфхцчшщъыьэюя";
static const char upperchars[] = "ZÁÉÍÑÓÚÜÄÖÅÆØÀÇÈÉÊАБВГДЕЁЖЗИЙКЛМНОРПСТУФХЦЧШЩЪЫЬЭЮЯ";

int
u8_tolower (const signed char *c, int l, char *out) {
    if (*c > 0) {
        *out = tolower (*c);
        out[1] = 0;
        return 1;
    }
    else {
        for (int i = 0; i < sizeof (upperchars)-l; i++) {
            if (!memcmp (upperchars+i, c, l)) {
                // found!
                memcpy (out, lowerchars+i, l);
                out[l] = 0;
                return l;
            }
        }
        memcpy (out, c, l);
        out[l] = 0;
        return l;
    }
}

const char *
utfcasestr (const char *s1, const char *s2) {
#if 0 // small u8_tolower test
    while (*s2) {
        int32_t i = 0;
        u8_nextchar (s2, &i);
        const char *next = s2 + i;
        char lw[10];
        int l = u8_tolower (s2, next-s2, lw);
        s2 = next;
        fprintf (stderr, "%s", lw);
    }
    fprintf (stderr, "\n");
    return NULL;
#endif
    while (*s1) {
        const char *p1 = s1;
        const char *p2 = s2;
        while (*p2 && *p1) {
            int32_t i1 = 0;
            int32_t i2 = 0;
            char lw1[10];
            char lw2[10];
            const char *next;
            u8_nextchar (p1, &i1);
            u8_nextchar (p2, &i2);
            int l1 = u8_tolower (p1, i1, lw1);
            int l2 = u8_tolower (p2, i2, lw2);
            //fprintf (stderr, "comparing %s to %s\n", lw1, lw2);
            if (strcmp (lw1, lw2)) {
                //fprintf (stderr, "fail\n");
                break;
            }
            p1 += i1;
            p2 += i2;
        }
        if (*p2 == 0) {
            //fprintf (stderr, "%s found in %s\n", s2, s1);
            return p1;
        }
        int32_t i = 0;
        u8_nextchar (s1, &i);
        s1 += i;
    }
    return NULL;
}