X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Flocalcharset.c;h=bc5587bf6015ca1a45070736eb9630e2accaa7e4;hb=fcfc4f43bfd05d1739e78c6850b58de4175b62a4;hp=461320823d8a827489b2d5c753a297c9c028523f;hpb=fac1a01e39ca1cddd2dd5d5d672136e3d78c766b;p=gnulib.git diff --git a/lib/localcharset.c b/lib/localcharset.c index 461320823..bc5587bf6 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) 2000-2002 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 @@ -37,16 +37,50 @@ # 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 + +#if defined __EMX__ +/* Assume EMX program runs on OS/2, even if compiled under DOS. */ +# define OS2 +#endif + +#if !defined WIN32 +# if HAVE_LANGINFO_CODESET +# include +# else +# if HAVE_SETLOCALE +# include +# endif # endif +#elif defined WIN32 +# define WIN32_LEAN_AND_MEAN +# include +#endif +#if defined OS2 +# define INCL_DOS +# include +#endif + +#if defined _WIN32 || defined __WIN32__ || defined __EMX__ || defined __DJGPP__ + /* Win32, OS/2, DOS */ +# define ISSLASH(C) ((C) == '/' || (C) == '\\') +#endif + +#ifndef DIRECTORY_SEPARATOR +# define DIRECTORY_SEPARATOR '/' #endif -char *xmalloc (); -char *xrealloc (); +#ifndef ISSLASH +# define ISSLASH(C) ((C) == DIRECTORY_SEPARATOR) +#endif + +#ifdef HAVE_GETC_UNLOCKED +# undef getc +# define getc getc_unlocked +#endif /* The following static variable is declared 'volatile' to avoid a possible multithread problem in the function get_charset_aliases. If we @@ -54,25 +88,46 @@ char *xrealloc (); '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. */ +#if __STDC__ != 1 +# define volatile /* empty */ +#endif /* 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' */ -static char * volatile charset_aliases; +static const char * volatile charset_aliases; /* Return a pointer to the contents of the charset.alias file. */ static const char * get_charset_aliases () { - char *cp; + const char *cp; cp = charset_aliases; if (cp == NULL) { +#if !defined 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 { @@ -102,19 +157,25 @@ get_charset_aliases () continue; } ungetc (c, fp); - if (fscanf(fp, "%50s %50s", buf1, buf2) < 2) + if (fscanf (fp, "%50s %50s", buf1, buf2) < 2) break; l1 = strlen (buf1); l2 = strlen (buf2); if (res_size == 0) { res_size = l1 + 1 + l2 + 1; - res_ptr = xmalloc (res_size + 1); + res_ptr = (char *) malloc (res_size + 1); } else { res_size += l1 + 1 + l2 + 1; - res_ptr = xrealloc (res_ptr, res_size + 1); + res_ptr = (char *) 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); @@ -129,6 +190,21 @@ get_charset_aliases () } } + if (file_name != NULL) + free (file_name); + +#else + + /* 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. */ + +# if defined WIN32 + cp = "CP936" "\0" "GBK" "\0" + "CP1361" "\0" "JOHAB" "\0"; +# endif +#endif + charset_aliases = cp; } @@ -139,7 +215,7 @@ 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 @@ -150,26 +226,32 @@ locale_charset () const char *codeset; const char *aliases; -#if HAVE_LANGINFO_CODESET +#if !(defined WIN32 || defined OS2) + +# 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"); } } @@ -179,20 +261,85 @@ locale_charset () through the charset.alias file. */ codeset = locale; -#endif +# endif + +#elif defined 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; + +#elif defined OS2 - if (codeset != NULL) + const char *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. */ + locale = getenv ("LC_ALL"); + if (locale == NULL || locale[0] == '\0') { - /* 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; - } + locale = getenv ("LC_CTYPE"); + if (locale == NULL || locale[0] == '\0') + locale = getenv ("LANG"); + } + if (locale != NULL && locale[0] != '\0') + { + /* If the locale name contains an encoding after the dot, return it. */ + const char *dot = strchr (locale, '.'); + + if (dot != NULL) + { + const char *modifier; + + dot++; + /* Look for the possible @... trailer and remove it, if any. */ + modifier = strchr (dot, '@'); + if (modifier == NULL) + return dot; + if (modifier - dot < sizeof (buf)) + { + memcpy (buf, dot, modifier - dot); + buf [modifier - dot] = '\0'; + return buf; + } + } + + /* Resolve through the charset.alias file. */ + codeset = locale; + } + else + { + /* OS/2 has a function returning the locale's codepage as a number. */ + if (DosQueryCp (sizeof (cp), cp, &cplen)) + codeset = ""; + else + { + sprintf (buf, "CP%u", cp[0]); + codeset = buf; + } } +#endif + + 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; }