charset.c 10.2 KB
Newer Older
1
/*****************************************************************************
gbazin's avatar
   
gbazin committed
2
3
 * charset.c: Determine a canonical name for the current locale's character
 *            encoding.
4
5
 *****************************************************************************
 * Copyright (C) 2003 VideoLAN
6
 * $Id: charset.c,v 1.4 2003/10/11 21:08:40 hartman Exp $
7
8
9
10
 *
 * Authors: Derk-Jan Hartman <thedj at users.sf.net>
 *
 * vlc_current_charset() an adaption of mp_locale_charset():
Laurent Aimar's avatar
Laurent Aimar committed
11
12
13
 *
 *  Copyright (C) 2001-2003 The Mape Project
 *  Written by Karel Zak  <zakkr@zf.jcu.cz>.
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
 *
 * 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, USA.
 *****************************************************************************/

#include <stdlib.h>
Laurent Aimar's avatar
Laurent Aimar committed
31
32
#include <stdio.h>
#include <vlc/vlc.h>
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

#if !defined WIN32
# if HAVE_LANGINFO_CODESET
#  include <langinfo.h>
# else
#  if HAVE_SETLOCALE
#   include <locale.h>
#  endif
# endif
#elif defined WIN32
# include <windows.h>
#endif

#include "charset.h"

typedef struct VLCCharsetAlias
{
    char *psz_alias, *psz_name;
} VLCCharsetAlias;

/*
 * The libcharset load all from external text file, but it's strange and
 * slow solution, we rather use array(s) compiled into source. In the 
 * "good" libc this is not needful -- for example in linux.
 * 
 * Please, put to this funtion exotic aliases only. The libc 'iconv' knows
 * a lot of basic aliases (check it first by iconv -l).
 * 
 */

static const char* vlc_encoding_from_language( const char *l )
{
    /* check for language (and perhaps country) codes */
    if (strstr(l, "zh_TW")) return "Big5";
    if (strstr(l, "zh_HK")) return "Big5HKSCS";   /* no MIME charset */
    if (strstr(l, "zh")) return "GB2312";
    if (strstr(l, "th")) return "TIS-620";
    if (strstr(l, "ja")) return "EUC-JP";
    if (strstr(l, "ko")) return "EUC-KR";
    if (strstr(l, "ru")) return "KOI8-R";
    if (strstr(l, "uk")) return "KOI8-U";
    if (strstr(l, "pl") || strstr(l, "hr") ||
	strstr(l, "hu") || strstr(l, "cs") ||
	strstr(l, "sk") || strstr(l, "sl")) return "ISO-8859-2";
    if (strstr(l, "eo") || strstr(l, "mt")) return "ISO-8859-3";
    if (strstr(l, "lt") || strstr(l, "la")) return "ISO-8859-4";
    if (strstr(l, "bg") || strstr(l, "be") ||
        strstr(l, "mk") || strstr(l, "uk")) return "ISO-8859-5";
    if (strstr(l, "ar")) return "ISO-8859-6";
    if (strstr(l, "el")) return "ISO-8859-7";
    if (strstr(l, "he") || strstr(l, "iw")) return "ISO-8859-8";
    if (strstr(l, "tr")) return "ISO-8859-9";
    if (strstr(l, "th")) return "ISO-8859-11";
    if (strstr(l, "lv")) return "ISO-8859-13";
    if (strstr(l, "cy")) return "ISO-8859-14";
    if (strstr(l, "et")) return "ISO-8859-15"; /* all latin1 could be iso15 as well */
    if (strstr(l, "ro")) return "ISO-8859-2";   /* or ISO-8859-16 */
    if (strstr(l, "am") || strstr(l, "vi")) return "UTF-8";
    /* We don't know. This ain't working go to default. */
    return "ISO-8859-1";
}


static const char* vlc_charset_aliases( const char *psz_name )
{
    VLCCharsetAlias	*a;

#if defined WIN32
    VLCCharsetAlias aliases[] = 
    {
        { "CP936",	"GBK" },
        { "CP1361",	"JOHAB" },
        { "CP20127",	"ASCII" },
        { "CP20866",	"KOI8-R" },
        { "CP21866",	"KOI8-RU" },
        { "CP28591",	"ISO-8859-1" },
        { "CP28592",	"ISO-8859-2" },
        { "CP28593",	"ISO-8859-3" },
        { "CP28594",	"ISO-8859-4" },
        { "CP28595",	"ISO-8859-5" },
        { "CP28596",	"ISO-8859-6" },
        { "CP28597",	"ISO-8859-7" },
        { "CP28598",	"ISO-8859-8" },
        { "CP28599",	"ISO-8859-9" },
        { "CP28605",	"ISO-8859-15" },
        { NULL,		NULL }
    };
#elif SYS_AIX
    VLCCharsetAlias aliases[] =
    {
        { "IBM-850",	"CP850" },
        { "IBM-856",	"CP856" },
        { "IBM-921",	"ISO-8859-13" },
        { "IBM-922",	"CP922" },
        { "IBM-932",	"CP932" },
        { "IBM-943",	"CP943" },
        { "IBM-1046",	"CP1046" },
        { "IBM-1124",	"CP1124" },
        { "IBM-1129",	"CP1129" },
        { "IBM-1252",	"CP1252" },
        { "IBM-EUCCN",	"GB2312" },
        { "IBM-EUCJP",	"EUC-JP" },
        { "IBM-EUCKR",	"EUC-KR" },
        { "IBM-EUCTW",	"EUC-TW" },
        { NULL,	NULL }
    };
#elif SYS_HPUX 
    VLCCharsetAlias aliases[] =
    {
        { "ROMAN8",	"HP-ROMAN8" },
        { "ARABIC8",	"HP-ARABIC8" },
        { "GREEK8",	"HP-GREEK8" },
        { "HEBREW8",	"HP-HEBREW8" },
        { "TURKISH8",	"HP-TURKISH8" },
        { "KANA8",	"HP-KANA8" },
        { "HP15CN",	"GB2312" },
        { NULL, NULL }
    };
#elif SYS_IRIX
    VLCCharsetAlias aliases[] =
    {
        { "EUCCN",	"GB2312" },
        { NULL, NULL }
    };
#elif SYS_OSF 
    VLCCharsetAlias aliases[] =
    {
        { "KSC5601",	"CP949" },
        { "SDECKANJI",	"EUC-JP" },
        { "TACTIS",	"TIS-620" },
        { NULL, NULL }
    };
#elif SYS_SOLARIS
    VLCCharsetAlias aliases[] =
    {
        { "646",	"ASCII" },
        { "CNS11643",	"EUC-TW" },
        { "5601",	"EUC-KR" },
        { "JOHAP92",	"JOHAB" },
        { "PCK",	"SHIFT_JIS" },
        { "2533",	"TIS-620" },
        { NULL, NULL }
    };
#elif SYS_BSD
    VLCCharsetAlias aliases[] =
    {
        { "646", " ASCII" },
        { "EUCCN", "GB2312" },
        { NULL, NULL }
    };
#else
    VLCCharsetAlias aliases[] = {{NULL, NULL}};
#endif

    if( aliases )
    {
        for (a = aliases; a->psz_alias; a++)
            if (strcasecmp (a->psz_alias, psz_name) == 0)
                return a->psz_name;
    }
    
    /* we return original name beacuse iconv() probably will know
     * something better about name if we don't know it :-)
    */
    return psz_name;
}

/* Returns charset from "language_COUNTRY.charset@modifier" string */
gbazin's avatar
   
gbazin committed
201
static char *vlc_encoding_from_locale( char *psz_locale )
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
{
    char *psz_dot = strchr( psz_locale, '.' );

    if( psz_dot != NULL )
    {
        const char *psz_modifier;
        static char buf[2 + 10 + 1];

        psz_dot++;
        
        /* Look for the possible @... trailer and remove it, if any.  */
        psz_modifier = strchr( psz_dot, '@' );
        
        if( psz_modifier == NULL )
            return psz_dot;
217
        if( 0 < ( psz_modifier - psz_dot ) < sizeof( buf ))
218
219
220
221
222
223
224
        {
            memcpy( buf, psz_dot, psz_modifier - psz_dot );
            buf[ psz_modifier - psz_dot ] = '\0';
            return buf;
        }
    }
    /* try language mapping */
225
    return (char *)vlc_encoding_from_language( psz_locale );
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
}

vlc_bool_t vlc_current_charset( char **psz_charset )
{
    const char *psz_codeset;

#if !(defined WIN32 || defined OS2)

# if HAVE_LANGINFO_CODESET
    /* Most systems support nl_langinfo( CODESET ) nowadays.  */
    psz_codeset = nl_langinfo( CODESET );
# else
    /* On old systems which lack it, use setlocale or getenv.  */
    const char *psz_locale = NULL;

    /* But most old systems don't have a complete set of locales.  Some
     * (like SunOS 4 or DJGPP) have only the C locale.  Therefore we don't
     * use setlocale here; it would return "C" when it doesn't support the
     * locale name the user has set. Darwin's setlocale is broken.
     */
#  if HAVE_SETLOCALE && !SYS_DARWIN
    psz_locale = setlocale( LC_ALL, NULL );
#  endif
    if( psz_locale == NULL || psz_locale[0] == '\0' )
    {
        psz_locale = getenv( "LC_ALL" );
        if( psz_locale == NULL || psz_locale[0] == '\0' )
        {
            psz_locale = getenv( "LC_CTYPE" );
            if( psz_locale == NULL || psz_locale[0] == '\0')
                psz_locale = getenv( "LANG" );
        }
    }

    /* On some old systems, one used to set locale = "iso8859_1". On others,
     * you set it to "language_COUNTRY.charset". Darwin only has LANG :(
     */
263
    psz_codeset = vlc_encoding_from_locale( (char *)psz_locale );
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
# endif /* HAVE_LANGINFO_CODESET */

#elif defined WIN32

    static char buf[2 + 10 + 1];

    /* Woe32 has a function returning the locale's codepage as a number.  */
    sprintf( buf, "CP%u", GetACP() );
    psz_codeset = buf;

#elif defined OS2

    const char *psz_locale;
    static char buf[2 + 10 + 1];
    ULONG cp[3];
    ULONG cplen;

    /* Allow user to override the codeset, as set in the operating system,
     * with standard language environment variables.
     */
    psz_locale = getenv( "LC_ALL" );
    if( psz_locale == NULL || psz_locale[0] == '\0' )
    {
        psz+locale = getenv( "LC_CTYPE" );
        if( psz_locale == NULL || locale[0] == '\0' )
            locale = getenv( "LANG" );
    }
    if( psz_locale != NULL && psz_locale[0] != '\0' )
        psz_codeset = vlc_encoding_from_locale( psz_locale );
    else
    {
        /* OS/2 has a function returning the locale's codepage as a number.  */
        if( DosQueryCp( sizeof( cp ), cp, &cplen ) )
            psz_codeset = "";
        else
        {
            sprintf( buf, "CP%u", cp[0] );
            psz_codeset = buf;
        }
    }
#endif
    if( psz_codeset == NULL )
        /* The canonical name cannot be determined.  */
        psz_codeset = "";
    else
        psz_codeset = vlc_charset_aliases( psz_codeset );
    
    /* Don't return an empty string.  GNU libc and GNU libiconv interpret
     * the empty string as denoting "the locale's character encoding",
     * thus GNU libiconv would call this function a second time.  
     */
    if( psz_codeset[0] == '\0' )
    {
        /*
         * Last possibility is 'CHARSET' enviroment variable
         */
        if( !( psz_codeset = getenv( "CHARSET" ) ) )
            psz_codeset = "ISO-8859-1";
    }
    
    if( psz_charset )
325
        *psz_charset = strdup((char *)psz_codeset);
326
327

    if (strcasecmp(psz_codeset, "UTF8")==0 || strcasecmp(psz_codeset, "UTF-8")==0)
Laurent Aimar's avatar
Laurent Aimar committed
328
        return VLC_TRUE;
329
    
Laurent Aimar's avatar
Laurent Aimar committed
330
    return VLC_FALSE;
331
332
}