summaryrefslogtreecommitdiffstats
path: root/src/common/utf8.cpp
blob: 56609634c085de44dd23eef2c0ac0000f00e8041 (plain) (blame)
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
/*
  Basic UTF-8 manipulation routines
  by Jeff Bezanson
  placed in the public domain Fall 2005

  This code is designed to provide the utilities you need to manipulate
  UTF-8 as an internal string encoding. These functions do not perform the
  error checking normally needed when handling UTF-8 data, so if you happen
  to be from the Unicode Consortium you will want to flay me alive.
  I do this because error checking can be performed at the boundaries (I/O),
  with these routines reserved for higher performance on data known to be
  valid.
*/

#ifdef _WIN32
#include <windows.h>
#undef min
#undef max
#endif

#include <cstdlib>
#include <cstring>
#include <algorithm>

#include "common/common_types.h"
#include "common/utf8.h"

// is start of UTF sequence
inline bool isutf(char c) {
    return (c & 0xC0) != 0x80;
}

static const u32 offsetsFromUTF8[6] = {
  0x00000000UL, 0x00003080UL, 0x000E2080UL,
  0x03C82080UL, 0xFA082080UL, 0x82082080UL
};

static const u8 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,
};

/* returns length of next utf-8 sequence */
int u8_seqlen(const char *s)
{
  return trailingBytesForUTF8[(unsigned int)(unsigned char)s[0]] + 1;
}

/* 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(u32 *dest, int sz, const char *src, int srcsz)
{
  u32 ch;
  const char *src_end = src + srcsz;
  int nb;
  int 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, int sz, u32 *src, int srcsz)
{
  u32 ch;
  int 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 < 0x110000) {
      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, u32 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 < 0x110000) {
    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(const char *str, int charnum)
{
  int 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(const char *s, int offset)
{
  int 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(const char *s)
{
  int count = 0;
  int i = 0;

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

  return count;
}

/* reads the next utf-8 sequence out of a string, updating an index */
u32 u8_nextchar(const char *s, int *i)
{
  u32 ch = 0;
  int 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, int *i)
{
  (void)(isutf(s[++(*i)]) || isutf(s[++(*i)]) ||
       isutf(s[++(*i)]) || ++(*i));
}

void u8_dec(const char *s, int *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, u32 *dest)
{
  u32 ch;
  char digs[9]="\0\0\0\0\0\0\0\0";
  int dno=0, i=1;

  ch = (u32)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, nullptr, 8);
  }
  else if (str[0] == 'x') {
    while (hex_digit(str[i]) && dno < 2) {
      digs[dno++] = str[i++];
    }
    if (dno > 0)
      ch = strtol(digs, nullptr, 16);
  }
  else if (str[0] == 'u') {
    while (hex_digit(str[i]) && dno < 4) {
      digs[dno++] = str[i++];
    }
    if (dno > 0)
      ch = strtol(digs, nullptr, 16);
  }
  else if (str[0] == 'U') {
    while (hex_digit(str[i]) && dno < 8) {
      digs[dno++] = str[i++];
    }
    if (dno > 0)
      ch = strtol(digs, nullptr, 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, int sz, char *src)
{
  int c=0, amt;
  u32 ch;
  char temp[4];

  while (*src && c < sz) {
    if (*src == '\\') {
      src++;
      amt = u8_read_escape_sequence(src, &ch);
    }
    else {
      ch = (u32)*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;
}

const char *u8_strchr(const char *s, u32 ch, int *charn)
{
  int i = 0, lasti=0;
  u32 c;

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

const char *u8_memchr(const char *s, u32 ch, size_t sz, int *charn)
{
  u32 i = 0, lasti=0;
  u32 c;
  int 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 nullptr;
}

int u8_is_locale_utf8(const 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 UTF8StringNonASCIICount(const char *utf8string) {
    UTF8 utf(utf8string);
    int count = 0;
    while (!utf.end()) {
        int c = utf.next();
        if (c > 127)
            ++count;
    }
    return count;
}

bool UTF8StringHasNonASCII(const char *utf8string) {
    return UTF8StringNonASCIICount(utf8string) > 0;
}

#ifdef _WIN32

std::string ConvertWStringToUTF8(const wchar_t *wstr) {
    int len = (int)wcslen(wstr);
    int size = (int)WideCharToMultiByte(CP_UTF8, 0, wstr, len, 0, 0, nullptr, nullptr);
    std::string s;
    s.resize(size);
    if (size > 0) {
        WideCharToMultiByte(CP_UTF8, 0, wstr, len, &s[0], size, nullptr, nullptr);
    }
    return s;
}

std::string ConvertWStringToUTF8(const std::wstring &wstr) {
    int len = (int)wstr.size();
    int size = (int)WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(), len, 0, 0, nullptr, nullptr);
    std::string s;
    s.resize(size);
    if (size > 0) {
        WideCharToMultiByte(CP_UTF8, 0, wstr.c_str(), len, &s[0], size, nullptr, nullptr);
    }
    return s;
}

void ConvertUTF8ToWString(wchar_t *dest, size_t destSize, const std::string &source) {
    int len = (int)source.size();
    int size = (int)MultiByteToWideChar(CP_UTF8, 0, source.c_str(), len, nullptr, 0);
    MultiByteToWideChar(CP_UTF8, 0, source.c_str(), len, dest, std::min((int)destSize, size));
}

std::wstring ConvertUTF8ToWString(const std::string &source) {
    int len = (int)source.size();
    int size = (int)MultiByteToWideChar(CP_UTF8, 0, source.c_str(), len, nullptr, 0);
    std::wstring str;
    str.resize(size);
    if (size > 0) {
        MultiByteToWideChar(CP_UTF8, 0, source.c_str(), len, &str[0], size);
    }
    return str;
}

#endif