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
|
// ---------------------------------------------------------------------------80
// ICQ plugin for Miranda Instant Messenger
// ________________________________________
//
// Copyright © 2000,2001 Richard Hughes, Roland Rabien, Tristan Van de Vreede
// Copyright © 2001,2002 Jon Keating, Richard Hughes
// Copyright © 2002,2003,2004 Martin berg, Sam Kothari, Robert Rainwater
// Copyright © 2004,2005,2006 Joe Kucera
//
// 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., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
//
// -----------------------------------------------------------------------------
//
// File name : $Source: /cvsroot/miranda/miranda/protocols/IcqOscarJ/i18n.c,v $
// Revision : $Revision: 3184 $
// Last change on : $Date: 2006-06-20 12:40:26 +0200 (Tue, 20 Jun 2006) $
// Last change by : $Author: jokusoftware $
//
// DESCRIPTION:
//
// Contains helper functions to convert text messages between different
// character sets.
//
// -----------------------------------------------------------------------------
#include "icqoscar.h"
static BOOL bHasCP_UTF8 = FALSE;
void InitI18N(void)
{
CPINFO CPInfo;
bHasCP_UTF8 = GetCPInfo(CP_UTF8, &CPInfo);
}
// Returns true if the buffer only contains 7-bit characters.
BOOL IsUSASCII(const unsigned char* pBuffer, int nSize)
{
BOOL bResult = TRUE;
int nIndex;
for (nIndex = 0; nIndex < nSize; nIndex++)
{
if (pBuffer[nIndex] > 0x7F)
{
bResult = FALSE;
break;
}
}
return bResult;
}
// Returns true if the unicode buffer only contains 7-bit characters.
BOOL IsUnicodeAscii(const wchar_t* pBuffer, int nSize)
{
BOOL bResult = TRUE;
int nIndex;
for (nIndex = 0; nIndex < nSize; nIndex++)
{
if (pBuffer[nIndex] > 0x7F)
{
bResult = FALSE;
break;
}
}
return bResult;
}
// Scans a string encoded in UTF-8 to verify that it contains
// only valid sequences. It will return 1 if the string contains
// only legitimate encoding sequences; otherwise it will return 0;
// From 'Secure Programming Cookbook', John Viega & Matt Messier, 2003
int UTF8_IsValid(const unsigned char* pszInput)
{
int nb, i;
const unsigned char* c = pszInput;
for (c = pszInput; *c; c += (nb + 1))
{
if (!(*c & 0x80))
nb = 0;
else if ((*c & 0xc0) == 0x80) return 0;
else if ((*c & 0xe0) == 0xc0) nb = 1;
else if ((*c & 0xf0) == 0xe0) nb = 2;
else if ((*c & 0xf8) == 0xf0) nb = 3;
else if ((*c & 0xfc) == 0xf8) nb = 4;
else if ((*c & 0xfe) == 0xfc) nb = 5;
for (i = 1; i<=nb; i++) // we this forward, do not cross end of string
if ((*(c + i) & 0xc0) != 0x80)
return 0;
}
return 1;
}
// returns ansi string in all cases
char* detect_decode_utf8(const char *from)
{
char* temp = NULL;
if (IsUSASCII(from, strlennull(from)) || !UTF8_IsValid(from) || !utf8_decode(from, &temp)) return (char*)from;
SAFE_FREE((char**)&from);
return temp;
}
/*
* The following UTF8 routines are
*
* Copyright (C) 2001 Peter Harris <peter.harris@hummingbird.com>
* Copyright (C) 2001 Edmund Grimley Evans <edmundo@rano.org>
*
* under a GPL license
*
* --------------------------------------------------------------
* Convert a string between UTF-8 and the locale's charset.
* Invalid bytes are replaced by '#', and characters that are
* not available in the target encoding are replaced by '?'.
*
* If the locale's charset is not set explicitly then it is
* obtained using nl_langinfo(CODESET), where available, the
* environment variable CHARSET, or assumed to be US-ASCII.
*
* Return value of conversion functions:
*
* -1 : memory allocation failed
* 0 : data was converted exactly
* 1 : valid data was converted approximately (using '?')
* 2 : input was invalid (but still converted, using '#')
* 3 : unknown encoding (but still converted, using '?')
*/
/*
* Convert a string between UTF-8 and the locale's charset.
*/
unsigned char *make_utf8_string(const wchar_t *unicode)
{
int size = 0;
int index = 0;
int out_index = 0;
unsigned char* out;
unsigned short c;
/* first calculate the size of the target string */
c = unicode[index++];
while (c)
{
if (c < 0x0080)
size += 1;
else if (c < 0x0800)
size += 2;
else
size += 3;
c = unicode[index++];
}
out = (unsigned char*)SAFE_MALLOC(size + 1);
if (out == NULL)
return NULL;
index = 0;
c = unicode[index++];
while (c)
{
if (c < 0x080)
{
out[out_index++] = (unsigned char)c;
}
else if (c < 0x800)
{
out[out_index++] = 0xc0 | (c >> 6);
out[out_index++] = 0x80 | (c & 0x3f);
}
else
{
out[out_index++] = 0xe0 | (c >> 12);
out[out_index++] = 0x80 | ((c >> 6) & 0x3f);
out[out_index++] = 0x80 | (c & 0x3f);
}
c = unicode[index++];
}
out[out_index] = 0x00;
return out;
}
wchar_t *make_unicode_string(const unsigned char *utf8)
{
int size = 0, index = 0, out_index = 0;
wchar_t *out;
unsigned char c;
/* first calculate the size of the target string */
c = utf8[index++];
while (c)
{
if ((c & 0x80) == 0)
{
index += 0;
}
else if ((c & 0xe0) == 0xe0)
{
index += 2;
}
else
{
index += 1;
}
size += 1;
c = utf8[index++];
}
out = (wchar_t*)SAFE_MALLOC((size + 1) * sizeof(wchar_t));
if (out == NULL)
return NULL;
index = 0;
c = utf8[index++];
while (c)
{
if((c & 0x80) == 0)
{
out[out_index++] = c;
}
else if((c & 0xe0) == 0xe0)
{
out[out_index] = (c & 0x1F) << 12;
c = utf8[index++];
out[out_index] |= (c & 0x3F) << 6;
c = utf8[index++];
out[out_index++] |= (c & 0x3F);
}
else
{
out[out_index] = (c & 0x3F) << 6;
c = utf8[index++];
out[out_index++] |= (c & 0x3F);
}
c = utf8[index++];
}
out[out_index] = 0;
return out;
}
int utf8_encode(const char *from, char **to)
{
wchar_t *unicode;
int wchars, err;
wchars = MultiByteToWideChar(CP_ACP, MB_PRECOMPOSED, from,
strlennull(from), NULL, 0);
if (wchars == 0)
{
fprintf(stderr, "Unicode translation error %d\n", GetLastError());
return -1;
}
unicode = (wchar_t*)_alloca((wchars + 1) * sizeof(unsigned short));
unicode[wchars] = 0;
err = MultiByteToWideChar(CP_ACP, MB_PRECOMPOSED, from,
strlennull(from), unicode, wchars);
if(err != wchars)
{
fprintf(stderr, "Unicode translation error %d\n", GetLastError());
return -1;
}
/* On NT-based windows systems, we could use WideCharToMultiByte(), but
* MS doesn't actually have a consistent API across win32.
*/
*to = make_utf8_string(unicode);
return 0;
}
char *ansi_to_utf8(const char *szAnsi)
{
char *szUtf;
if (strlennull(szAnsi))
{
utf8_encode(szAnsi, &szUtf);
return szUtf;
}
else
return null_strdup("");
}
char *ansi_to_utf8_codepage(const char *szAnsi, WORD wCp)
{
wchar_t *unicode;
int wchars = strlennull(szAnsi);
unicode = (wchar_t*)_alloca((wchars + 1) * sizeof(wchar_t));
ZeroMemory(unicode, (wchars + 1)*sizeof(wchar_t));
MultiByteToWideChar(wCp, MB_PRECOMPOSED, szAnsi, wchars, unicode, wchars);
return make_utf8_string(unicode);
}
// Returns 0 on error, 1 on success
int utf8_decode(const char *from, char **to)
{
int nResult = 0;
_ASSERTE(!(*to)); // You passed a non-zero pointer, make sure it doesnt point to unfreed memory
// Validate the string
if (!UTF8_IsValid(from))
return 0;
// Use the native conversion routines when available
if (bHasCP_UTF8)
{
WCHAR *wszTemp = NULL;
int inlen = strlennull(from);
wszTemp = (WCHAR *)_alloca(sizeof(WCHAR) * (inlen + 1));
// Convert the UTF-8 string to UCS
if (MultiByteToWideChar(CP_UTF8, 0, from, -1, wszTemp, inlen + 1))
{
// Convert the UCS string to local ANSI codepage
*to = (char*)SAFE_MALLOC(inlen+1);
if (WideCharToMultiByte(CP_ACP, 0, wszTemp, -1, *to, inlen+1, NULL, NULL))
{
nResult = 1;
}
else
{
SAFE_FREE(&(*to));
}
}
}
else
{
wchar_t *unicode;
int chars;
int err;
unicode = make_unicode_string(from);
if(unicode == NULL)
{
fprintf(stderr, "Out of memory processing string from UTF8 to UNICODE16\n");
return 0;
}
chars = WideCharToMultiByte(CP_ACP, WC_COMPOSITECHECK, unicode, -1, NULL, 0, NULL, NULL);
if(chars == 0)
{
fprintf(stderr, "Unicode translation error %d\n", GetLastError());
SAFE_FREE(&unicode);
return 0;
}
*to = (char*)SAFE_MALLOC((chars + 1)*sizeof(unsigned char));
if(*to == NULL)
{
fprintf(stderr, "Out of memory processing string to local charset\n");
SAFE_FREE(&unicode);
return 0;
}
err = WideCharToMultiByte(CP_ACP, WC_COMPOSITECHECK, unicode, -1, *to, chars, NULL, NULL);
if (err != chars)
{
fprintf(stderr, "Unicode translation error %d\n", GetLastError());
SAFE_FREE(&unicode);
SAFE_FREE(to);
return 0;
}
SAFE_FREE(&unicode);
nResult = 1;
}
return nResult;
}
// Returns 0 on error, 1 on success
int utf8_decode_static(const char *from, char *to, int to_size)
{
int nResult = 0;
_ASSERTE(to); // You passed a zero pointer
// Validate the string
if (!UTF8_IsValid(from))
return 0;
// Use the native conversion routines when available
if (bHasCP_UTF8)
{
WCHAR *wszTemp = NULL;
int inlen = strlennull(from);
wszTemp = (WCHAR *)_alloca(sizeof(WCHAR) * (inlen + 1));
// Convert the UTF-8 string to UCS
if (MultiByteToWideChar(CP_UTF8, 0, from, -1, wszTemp, inlen + 1))
{
// Convert the UCS string to local ANSI codepage
if (WideCharToMultiByte(CP_ACP, 0, wszTemp, -1, to, to_size, NULL, NULL))
{
nResult = 1;
}
}
}
else
{
wchar_t *unicode = make_unicode_string(from);
if (unicode == NULL)
{
fprintf(stderr, "Out of memory processing string from UTF8 to UNICODE16\n");
return 0;
}
WideCharToMultiByte(CP_ACP, WC_COMPOSITECHECK, unicode, -1, to, to_size, NULL, NULL);
SAFE_FREE(&unicode);
nResult = 1;
}
return nResult;
}
|