summaryrefslogtreecommitdiff
path: root/src/lib/eina/eina_unicode.c
blob: a1993de697cd92f82bdaacc50dfe437d2865cc9e (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
/* EINA - EFL data type library
 * Copyright (C) 2010 Tom Hacohen,
 *		Brett Nash
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library;
 * if not, see <http://www.gnu.org/licenses/>.
 */

#ifdef HAVE_CONFIG_H
# include "config.h"
#endif

#include "eina_config.h"
#include "eina_private.h"
#include <string.h>

/* undefs EINA_ARG_NONULL() so NULL checks are not compiled out! */
#include "eina_safety_checks.h"
#include "eina_unicode.h"

/* FIXME: check if sizeof(wchar_t) == sizeof(Eina_Unicode) if so,
 * probably better to use the standard functions */

/* Maybe I'm too tired, but this is the only thing that actually worked. */
const Eina_Unicode _EINA_UNICODE_EMPTY_STRING[1] = {0};
EAPI const Eina_Unicode *EINA_UNICODE_EMPTY_STRING = _EINA_UNICODE_EMPTY_STRING;
EAPI int
eina_unicode_strcmp(const Eina_Unicode *a, const Eina_Unicode *b)
{
   EINA_SAFETY_ON_NULL_RETURN_VAL(a, -1);
   EINA_SAFETY_ON_NULL_RETURN_VAL(b, -1);

   for (; *a && *a == *b; a++, b++)
      ;
   if (*a == *b)
      return 0;
   else if (*a < *b)
      return -1;
   else
      return 1;
}

EAPI Eina_Unicode *
eina_unicode_strcpy(Eina_Unicode *dest, const Eina_Unicode *source)
{
   Eina_Unicode *ret = dest;

   EINA_SAFETY_ON_NULL_RETURN_VAL(dest, NULL);
   EINA_SAFETY_ON_NULL_RETURN_VAL(source, NULL);

   while (*source)
      *dest++ = *source++;
   *dest = 0;
   return ret;
}

EAPI Eina_Unicode *
eina_unicode_strncpy(Eina_Unicode *dest, const Eina_Unicode *source, size_t n)
{
   Eina_Unicode *ret = dest;

   EINA_SAFETY_ON_NULL_RETURN_VAL(dest, NULL);
   EINA_SAFETY_ON_NULL_RETURN_VAL(source, NULL);

   for ( ; n && *source ; n--)
      *dest++ = *source++;
   for (; n; n--)
      *dest++ = 0;
   return ret;
}

EAPI size_t
eina_unicode_strlen(const Eina_Unicode *ustr)
{
   const Eina_Unicode *end;

   EINA_SAFETY_ON_NULL_RETURN_VAL(ustr, 0);

   for (end = ustr; *end; end++)
      ;
   return end - ustr;
}

EAPI size_t
eina_unicode_strnlen(const Eina_Unicode *ustr, int n)
{
   const Eina_Unicode *end;
   const Eina_Unicode *last = ustr + n; /* technically not portable ;-) */

   EINA_SAFETY_ON_NULL_RETURN_VAL(ustr, 0);

   for (end = ustr; end < last && *end; end++)
      ;
   return end - ustr;
}




EAPI Eina_Unicode *
eina_unicode_strndup(const Eina_Unicode *text, size_t n)
{
   Eina_Unicode *ustr;

   EINA_SAFETY_ON_NULL_RETURN_VAL(text, NULL);

   ustr = malloc((n + 1) * sizeof(Eina_Unicode));
   memcpy(ustr, text, n * sizeof(Eina_Unicode));
   ustr[n] = 0;
   return ustr;
}

EAPI Eina_Unicode *
eina_unicode_strdup(const Eina_Unicode *text)
{
   size_t len;

   EINA_SAFETY_ON_NULL_RETURN_VAL(text, NULL);

   len = eina_unicode_strlen(text);
   return eina_unicode_strndup(text, len);
}

EAPI Eina_Unicode *
eina_unicode_strstr(const Eina_Unicode *haystack, const Eina_Unicode *needle)
{
   const Eina_Unicode *i, *j;

   EINA_SAFETY_ON_NULL_RETURN_VAL(haystack, NULL);
   EINA_SAFETY_ON_NULL_RETURN_VAL(needle, NULL);

   for (i = haystack; *i; i++)
     {
        haystack = i; /* set this location as the base position */
        for (j = needle; *j && *i && *j == *i; j++, i++)
           ;

        if (!*j) /*if we got to the end of j this means we got a full match */
          {
             return (Eina_Unicode *)haystack; /* return the new base position */
          }
     }

   return NULL;
}

EAPI Eina_Unicode *
eina_unicode_escape(const Eina_Unicode *str)
{
   Eina_Unicode *s2, *d;
   const Eina_Unicode *s;

   EINA_SAFETY_ON_NULL_RETURN_VAL(str, NULL);

   s2 = malloc((eina_unicode_strlen(str) * 2) + 1);
   if (!s2)
      return NULL;

   for (s = str, d = s2; *s != 0; s++, d++)
     {
        if ((*s == ' ') || (*s == '\\') || (*s == '\''))
          {
             *d = '\\';
             d++;
          }

        *d = *s;
     }
   *d = 0;
   return s2;
}

/* UTF-8 Handling */

#define EINA_UNICODE_UTF8_BYTES_PER_CHAR 6
/* The replacement range that will be used for bad utf8 chars. */
#define ERROR_REPLACEMENT_BASE  0xDC80
#define ERROR_REPLACEMENT_END   0xDCFF
#define IS_INVALID_BYTE(x)      ((x == 192) || (x == 193) || (x >= 245))
#define IS_CONTINUATION_BYTE(x) ((x & 0xC0) == 0x80)

EAPI Eina_Unicode
eina_unicode_utf8_get_next(const char *buf, int *iindex)
{
   int ind;
   Eina_Unicode r;
   unsigned char d;

   EINA_SAFETY_ON_NULL_RETURN_VAL(buf, 0);
   EINA_SAFETY_ON_NULL_RETURN_VAL(iindex, 0);

   ind = *iindex;

   /* if this char is the null terminator, exit */
   if ((d = buf[ind++]) == 0) return 0;

   if ((d & 0x80) == 0)
     { // 1 byte (7bit) - 0xxxxxxx
        *iindex = ind;
        return d;
     }
   if ((d & 0xe0) == 0xc0)
     { // 2 byte (11bit) - 110xxxxx 10xxxxxx
        r  = (d & 0x1f) << 6;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f);
        if (r <= 0x7F) goto error;
        *iindex = ind;
        return r;
     }
   if ((d & 0xf0) == 0xe0)
     { // 3 byte (16bit) - 1110xxxx 10xxxxxx 10xxxxxx
        r  = (d & 0x0f) << 12;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 6;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f);
        if (r <= 0x7FF) goto error;
        *iindex = ind;
        return r;
     }
   if ((d & 0xf8) == 0xf0)
     { // 4 byte (21bit) - 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
        r  = (d & 0x07) << 18;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 12;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 6;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f);
        if (r <= 0xFFFF) goto error;
        *iindex = ind;
        return r;
     }
   if ((d & 0xfc) == 0xf8)
     { // 5 byte (26bit) - 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
        r  = (d & 0x03) << 24;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 18;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 12;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 6;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f);
        if (r <= 0x1FFFFF) goto error;
        *iindex = ind;
        return r;
     }
   if ((d & 0xfe) == 0xfc)
     { // 6 byte (31bit) - 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
        r  = (d & 0x01) << 30;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 24;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 18;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 12;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f) << 6;
        if (((d = buf[ind++]) == 0) || IS_INVALID_BYTE(d) ||
            !IS_CONTINUATION_BYTE(d)) goto error;
        r |= (d & 0x3f);
        if (r <= 0x3FFFFFF) goto error;
        *iindex = ind;
        return r;
     }

/* Gets here where there was an error and we want to replace the char
 * we just use the invalid unicode codepoints 8 lower bits represent
 * the original char */
error:
   d = buf[*iindex];
   (*iindex)++;
   return ERROR_REPLACEMENT_BASE | d;
}

EAPI Eina_Unicode
eina_unicode_utf8_get_prev(const char *buf, int *iindex)
{
   int r, ind;

   EINA_SAFETY_ON_NULL_RETURN_VAL(buf, 0);
   EINA_SAFETY_ON_NULL_RETURN_VAL(iindex, 0);

   ind = *iindex;
   /* First obtain the codepoint at iindex */
   r = eina_unicode_utf8_get_next(buf, &ind);

   /* although when ind == 0 there's no previous char, we still want to get
    * the current char */
   if (*iindex <= 0)
     return r;

   /* Next advance iindex to previous codepoint */
   ind = *iindex;
   ind--;
   while ((ind > 0) && ((buf[ind] & 0xc0) == 0x80))
     ind--;

   *iindex = ind;
   return r;
}

EAPI int
eina_unicode_utf8_get_len(const char *buf)
{
   /* returns the number of utf8 characters (not bytes) in the string */
   int i = 0, len = 0;

   EINA_SAFETY_ON_NULL_RETURN_VAL(buf, 0);

   while (eina_unicode_utf8_get_next(buf, &i))
        len++;

   return len;
}

EAPI Eina_Unicode *
eina_unicode_utf8_to_unicode(const char *utf, int *_len)
{
   /* FIXME: Should optimize! */
   int len, i;
   int ind;
   Eina_Unicode *buf, *uind;

   EINA_SAFETY_ON_NULL_RETURN_VAL(utf, NULL);

   len = eina_unicode_utf8_get_len(utf);
   if (_len)
      *_len = len;
   buf = (Eina_Unicode *) calloc(sizeof(Eina_Unicode), (len + 1));
   if (!buf) return buf;

   for (i = 0, ind = 0, uind = buf ; i < len ; i++, uind++)
     {
        *uind = eina_unicode_utf8_get_next(utf, &ind);
     }

   return buf;
}

EAPI char *
eina_unicode_unicode_to_utf8(const Eina_Unicode *uni, int *_len)
{
   char *buf;
   const Eina_Unicode *uind;
   char *ind;
   int ulen, len;

   EINA_SAFETY_ON_NULL_RETURN_VAL(uni, NULL);

   ulen = eina_unicode_strlen(uni);
   buf = (char *) calloc(ulen + 1, EINA_UNICODE_UTF8_BYTES_PER_CHAR);

   len = 0;
   for (uind = uni, ind = buf ; *uind ; uind++)
     {
        if (*uind <= 0x7F) /* 1 byte char */
          {
             *ind++ = *uind;
             len += 1;
          }
        else if (*uind <= 0x7FF) /* 2 byte char */
          {
             *ind++ = 0xC0 | (unsigned char) (*uind >> 6);
             *ind++ = 0x80 | (unsigned char) (*uind & 0x3F);
             len += 2;
          }
        else if (*uind <= 0xFFFF) /* 3 byte char */
          {
             /* If it's a special replacement codepoint */
             if (*uind >= ERROR_REPLACEMENT_BASE &&
                 *uind <= ERROR_REPLACEMENT_END)
               {
                  *ind++ = *uind & 0xFF;
                  len += 1;
               }
             else
               {
                  *ind++ = 0xE0 | (unsigned char) (*uind >> 12);
                  *ind++ = 0x80 | (unsigned char) ((*uind >> 6) & 0x3F);
                  *ind++ = 0x80 | (unsigned char) (*uind & 0x3F);
                  len += 3;
               }
          }
        else if (*uind <= 0x1FFFFF) /* 4 byte char */
          {
             *ind++ = 0xF0 | (unsigned char) ((*uind >> 18) & 0x07);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 12) & 0x3F);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 6) & 0x3F);
             *ind++ = 0x80 | (unsigned char) (*uind & 0x3F);
             len += 4;
          }
        else if (*uind <= 0x3FFFFFF) /* 5 byte char */
          {
             *ind++ = 0xF8 | (unsigned char) ((*uind >> 24) & 0x03);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 18) & 0x3F);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 12) & 0x3F);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 6) & 0x3F);
             *ind++ = 0x80 | (unsigned char) (*uind & 0x3F);
             len += 5;
          }
        else if (*uind <= 0x7FFFFFFF) /* 6 byte char */
          {
             *ind++ = 0xFC | (unsigned char) ((*uind >> 30) & 0x01);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 24) & 0x3F);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 18) & 0x3F);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 12) & 0x3F);
             *ind++ = 0x80 | (unsigned char) ((*uind >> 6) & 0x3F);
             *ind++ = 0x80 | (unsigned char) (*uind & 0x3F);
             len += 6;
          }
        else /* error */
          {
             /* Do something */
          }
     }
   buf = realloc(buf, len + 1);
   buf[len] = '\0';
   if (_len)
      *_len = len;
   return buf;
}