X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Flocalcharset.c;h=575372dca4472404c5f0c7a76ba0ced72fe9c184;hb=468e57cb4025983239ff40bb1c05b7d8e4328185;hp=86f43b58896712244f64b08f94ec7125bff2fe76;hpb=8aecbf69e84c78c3dd989b8d25368a1f2a7e6e0e;p=gnulib.git diff --git a/lib/localcharset.c b/lib/localcharset.c index 86f43b588..575372dca 100644 --- a/lib/localcharset.c +++ b/lib/localcharset.c @@ -1,6 +1,6 @@ /* Determine a canonical name for the current locale's character encoding. - Copyright (C) 2000 Free Software Foundation, Inc. + Copyright (C) 2000-2001 Free Software Foundation, Inc. This program is free software; you can redistribute it and/or modify it under the terms of the GNU Library General Public License as published @@ -37,17 +37,38 @@ # include #endif -#if HAVE_LANGINFO_CODESET -# include -#else -# if HAVE_SETLOCALE -# include +#if defined _WIN32 || defined __WIN32__ +# undef WIN32 /* avoid warning on mingw32 */ +# define WIN32 +#endif + +#ifndef WIN32 +# if HAVE_LANGINFO_CODESET +# include +# else +# if HAVE_SETLOCALE +# include +# endif # endif +#else /* WIN32 */ +# define WIN32_LEAN_AND_MEAN +# include +#endif + +#ifndef DIRECTORY_SEPARATOR +# define DIRECTORY_SEPARATOR '/' #endif -char *xmalloc (); -char *xrealloc (); +#ifndef ISSLASH +# define ISSLASH(C) ((C) == DIRECTORY_SEPARATOR) +#endif +/* The following static variable is declared 'volatile' to avoid a + possible multithread problem in the function get_charset_aliases. If we + are running in a threaded environment, and if two threads initialize + 'charset_aliases' simultaneously, both will produce the same value, + and everything will be ok if the two assignments to 'charset_aliases' + are atomic. But I don't know what will happen if the two assignments mix. */ /* Pointer to the contents of the charset.alias file, if it has already been read, else NULL. Its format is: ALIAS_1 '\0' CANONICAL_1 '\0' ... ALIAS_n '\0' CANONICAL_n '\0' '\0' */ @@ -62,11 +83,29 @@ get_charset_aliases () cp = charset_aliases; if (cp == NULL) { +#ifndef WIN32 FILE *fp; + const char *dir = LIBDIR; + const char *base = "charset.alias"; + char *file_name; - fp = fopen (LIBDIR "/" "charset.alias", "r"); - if (fp == NULL) - /* File not found, treat it as empty. */ + /* Concatenate dir and base into freshly allocated file_name. */ + { + size_t dir_len = strlen (dir); + size_t base_len = strlen (base); + int add_slash = (dir_len > 0 && !ISSLASH (dir[dir_len - 1])); + file_name = (char *) malloc (dir_len + add_slash + base_len + 1); + if (file_name != NULL) + { + memcpy (file_name, dir, dir_len); + if (add_slash) + file_name[dir_len] = DIRECTORY_SEPARATOR; + memcpy (file_name + dir_len + add_slash, base, base_len + 1); + } + } + + if (file_name == NULL || (fp = fopen (file_name, "r")) == NULL) + /* Out of memory or file not found, treat it as empty. */ cp = ""; else { @@ -103,12 +142,18 @@ get_charset_aliases () if (res_size == 0) { res_size = l1 + 1 + l2 + 1; - res_ptr = xmalloc (res_size + 1); + res_ptr = malloc (res_size + 1); } else { res_size += l1 + 1 + l2 + 1; - res_ptr = xrealloc (res_ptr, res_size + 1); + res_ptr = realloc (res_ptr, res_size + 1); + } + if (res_ptr == NULL) + { + /* Out of memory. */ + res_size = 0; + break; } strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1); strcpy (res_ptr + res_size - (l2 + 1), buf2); @@ -123,6 +168,19 @@ get_charset_aliases () } } + if (file_name != NULL) + free (file_name); + +#else /* WIN32 */ + + /* To avoid the troubles of installing a separate file in the same + directory as the DLL and of retrieving the DLL's directory at + runtime, simply inline the aliases here. */ + + cp = "CP936" "\0" "GBK" "\0" + "CP1361" "\0" "JOHAB" "\0"; +#endif + charset_aliases = cp; } @@ -133,7 +191,7 @@ get_charset_aliases () into one of the canonical names listed in config.charset. The result must not be freed; it is statically allocated. If the canonical name cannot be determined, the result is a non-canonical - name or NULL. */ + name. */ #ifdef STATIC STATIC @@ -144,26 +202,32 @@ locale_charset () const char *codeset; const char *aliases; -#if HAVE_LANGINFO_CODESET +#ifndef WIN32 + +# if HAVE_LANGINFO_CODESET /* Most systems support nl_langinfo (CODESET) nowadays. */ codeset = nl_langinfo (CODESET); -#else +# else - /* On old systems which lack it, use setlocale and getenv. */ + /* On old systems which lack it, use setlocale or getenv. */ const char *locale = NULL; -# if HAVE_SETLOCALE + /* 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. */ +# if HAVE_SETLOCALE && 0 locale = setlocale (LC_CTYPE, NULL); -# endif - if (locale == NULL) +# endif + if (locale == NULL || locale[0] == '\0') { locale = getenv ("LC_ALL"); - if (locale == NULL) + if (locale == NULL || locale[0] == '\0') { locale = getenv ("LC_CTYPE"); - if (locale == NULL) + if (locale == NULL || locale[0] == '\0') locale = getenv ("LANG"); } } @@ -173,20 +237,32 @@ locale_charset () through the charset.alias file. */ codeset = locale; +# endif + +#else /* WIN32 */ + + static char buf[2 + 10 + 1]; + + /* Win32 has a function returning the locale's codepage as a number. */ + sprintf (buf, "CP%u", GetACP ()); + codeset = buf; + #endif - if (codeset != NULL) - { - /* Resolve alias. */ - for (aliases = get_charset_aliases (); - *aliases != '\0'; - aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1) - if (!strcmp (codeset, aliases)) - { - codeset = aliases + strlen (aliases) + 1; - break; - } - } + if (codeset == NULL) + /* The canonical name cannot be determined. */ + codeset = ""; + + /* Resolve alias. */ + for (aliases = get_charset_aliases (); + *aliases != '\0'; + aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1) + if (strcmp (codeset, aliases) == 0 + || (aliases[0] == '*' && aliases[1] == '\0')) + { + codeset = aliases + strlen (aliases) + 1; + break; + } return codeset; }