1
/* Determine a canonical name for the current locale's character encoding.
3
Copyright (C) 2000-2001 Free Software Foundation, Inc.
5
This program is free software; you can redistribute it and/or modify it
6
under the terms of the GNU Library General Public License as published
7
by the Free Software Foundation; either version 2, or (at your option)
10
This program is distributed in the hope that it will be useful,
11
but WITHOUT ANY WARRANTY; without even the implied warranty of
12
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
13
Library General Public License for more details.
15
You should have received a copy of the GNU Library General Public
16
License along with this program; if not, write to the Free Software
17
Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
20
/* Written by Bruno Haible <haible@clisp.cons.org>. */
23
# include <gnulib/config.h>
25
# undef PACKAGE_VERSION
26
# undef PACKAGE_TARNAME
27
# undef PACKAGE_STRING
45
#if defined _WIN32 || defined __WIN32__
46
# undef WIN32 /* avoid warning on mingw32 */
51
# if HAVE_LANGINFO_CODESET
52
# include <langinfo.h>
59
# define WIN32_LEAN_AND_MEAN
63
#ifndef DIRECTORY_SEPARATOR
64
# define DIRECTORY_SEPARATOR '/'
68
# define ISSLASH(C) ((C) == DIRECTORY_SEPARATOR)
71
/* The following static variable is declared 'volatile' to avoid a
72
possible multithread problem in the function get_charset_aliases. If we
73
are running in a threaded environment, and if two threads initialize
74
'charset_aliases' simultaneously, both will produce the same value,
75
and everything will be ok if the two assignments to 'charset_aliases'
76
are atomic. But I don't know what will happen if the two assignments mix. */
78
# define volatile /* empty */
80
/* Pointer to the contents of the charset.alias file, if it has already been
81
read, else NULL. Its format is:
82
ALIAS_1 '\0' CANONICAL_1 '\0' ... ALIAS_n '\0' CANONICAL_n '\0' '\0' */
83
static char * volatile charset_aliases;
85
/* Return a pointer to the contents of the charset.alias file. */
87
get_charset_aliases ()
96
const char *dir = LIBDIR;
97
const char *base = "charset.alias";
100
/* Concatenate dir and base into freshly allocated file_name. */
102
size_t dir_len = strlen (dir);
103
size_t base_len = strlen (base);
104
int add_slash = (dir_len > 0 && !ISSLASH (dir[dir_len - 1]));
105
file_name = (char *) malloc (dir_len + add_slash + base_len + 1);
106
if (file_name != NULL)
108
memcpy (file_name, dir, dir_len);
110
file_name[dir_len] = DIRECTORY_SEPARATOR;
111
memcpy (file_name + dir_len + add_slash, base, base_len + 1);
115
if (file_name == NULL || (fp = fopen (file_name, "r")) == NULL)
116
/* Out of memory or file not found, treat it as empty. */
120
/* Parse the file's contents. */
124
char *res_ptr = NULL;
133
if (c == '\n' || c == ' ' || c == '\t')
137
/* Skip comment, to end of line. */
140
while (!(c == EOF || c == '\n'));
146
if (fscanf(fp, "%50s %50s", buf1, buf2) < 2)
152
res_size = l1 + 1 + l2 + 1;
153
res_ptr = malloc (res_size + 1);
157
res_size += l1 + 1 + l2 + 1;
158
res_ptr = realloc (res_ptr, res_size + 1);
166
strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1);
167
strcpy (res_ptr + res_size - (l2 + 1), buf2);
174
*(res_ptr + res_size) = '\0';
179
if (file_name != NULL)
184
/* To avoid the troubles of installing a separate file in the same
185
directory as the DLL and of retrieving the DLL's directory at
186
runtime, simply inline the aliases here. */
188
cp = "CP936" "\0" "GBK" "\0"
189
"CP1361" "\0" "JOHAB" "\0";
192
charset_aliases = cp;
198
/* Determine the current locale's character encoding, and canonicalize it
199
into one of the canonical names listed in config.charset.
200
The result must not be freed; it is statically allocated.
201
If the canonical name cannot be determined, the result is a non-canonical
215
# if HAVE_LANGINFO_CODESET
217
/* Most systems support nl_langinfo (CODESET) nowadays. */
218
codeset = nl_langinfo (CODESET);
222
/* On old systems which lack it, use setlocale or getenv. */
223
const char *locale = NULL;
225
/* But most old systems don't have a complete set of locales. Some
226
(like SunOS 4 or DJGPP) have only the C locale. Therefore we don't
227
use setlocale here; it would return "C" when it doesn't support the
228
locale name the user has set. */
229
# if HAVE_SETLOCALE && 0
230
locale = setlocale (LC_CTYPE, NULL);
232
if (locale == NULL || locale[0] == '\0')
234
locale = getenv ("LC_ALL");
235
if (locale == NULL || locale[0] == '\0')
237
locale = getenv ("LC_CTYPE");
238
if (locale == NULL || locale[0] == '\0')
239
locale = getenv ("LANG");
243
/* On some old systems, one used to set locale = "iso8859_1". On others,
244
you set it to "language_COUNTRY.charset". In any case, we resolve it
245
through the charset.alias file. */
252
static char buf[2 + 10 + 1];
254
/* Win32 has a function returning the locale's codepage as a number. */
255
sprintf (buf, "CP%u", GetACP ());
261
/* The canonical name cannot be determined. */
265
for (aliases = get_charset_aliases ();
267
aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1)
268
if (strcmp (codeset, aliases) == 0
269
|| (aliases[0] == '*' && aliases[1] == '\0'))
271
codeset = aliases + strlen (aliases) + 1;