X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Flocalcharset.c;h=dad97308c79a6e50cfd7bc2ce1946caa0dd11e92;hb=0439822fa6b678aa4be450d5cb14b288f5c6cf0a;hp=936d93d84caa2c8d12fa5db130d69d75d2c468a8;hpb=aafdd4ac07b3b5aaa4c0eabd756833baec861a59;p=gnulib.git diff --git a/lib/localcharset.c b/lib/localcharset.c index 936d93d84..dad97308c 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 @@ -17,12 +17,15 @@ Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. */ -/* Written by Bruno Haible . */ +/* Written by Bruno Haible . */ #ifdef HAVE_CONFIG_H # include #endif +/* Specification. */ +#include "localcharset.h" + #if HAVE_STDDEF_H # include #endif @@ -42,7 +45,12 @@ # define WIN32 #endif -#ifndef WIN32 +#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 @@ -50,10 +58,19 @@ # include # endif # endif -#else /* WIN32 */ +#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 '/' @@ -63,27 +80,40 @@ # define ISSLASH(C) ((C) == DIRECTORY_SEPARATOR) #endif +#ifdef HAVE_GETC_UNLOCKED +# undef getc +# define getc getc_unlocked +#endif + +#ifdef __cplusplus +/* When compiling with "gcc -x c++", produce a function with C linkage. */ +extern "C" const char * locale_charset (void); +#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. */ +#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) { -#ifndef WIN32 +#if !defined WIN32 FILE *fp; const char *dir = LIBDIR; const char *base = "charset.alias"; @@ -135,19 +165,19 @@ 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 = malloc (res_size + 1); + res_ptr = (char *) malloc (res_size + 1); } else { res_size += l1 + 1 + l2 + 1; - res_ptr = realloc (res_ptr, res_size + 1); + res_ptr = (char *) realloc (res_ptr, res_size + 1); } if (res_ptr == NULL) { @@ -171,14 +201,29 @@ get_charset_aliases () if (file_name != NULL) free (file_name); -#else /* WIN32 */ +#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"; + "CP1361" "\0" "JOHAB" "\0" + "CP20127" "\0" "ASCII" "\0" + "CP20866" "\0" "KOI8-R" "\0" + "CP21866" "\0" "KOI8-RU" "\0" + "CP28591" "\0" "ISO-8859-1" "\0" + "CP28592" "\0" "ISO-8859-2" "\0" + "CP28593" "\0" "ISO-8859-3" "\0" + "CP28594" "\0" "ISO-8859-4" "\0" + "CP28595" "\0" "ISO-8859-5" "\0" + "CP28596" "\0" "ISO-8859-6" "\0" + "CP28597" "\0" "ISO-8859-7" "\0" + "CP28598" "\0" "ISO-8859-8" "\0" + "CP28599" "\0" "ISO-8859-9" "\0" + "CP28605" "\0" "ISO-8859-15" "\0"; +# endif #endif charset_aliases = cp; @@ -191,7 +236,7 @@ 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 @@ -202,7 +247,7 @@ locale_charset () const char *codeset; const char *aliases; -#ifndef WIN32 +#if !(defined WIN32 || defined OS2) # if HAVE_LANGINFO_CODESET @@ -211,10 +256,14 @@ locale_charset () # 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 || locale[0] == '\0') @@ -235,28 +284,89 @@ locale_charset () # endif -#else /* WIN32 */ +#elif defined WIN32 static char buf[2 + 10 + 1]; - /* Win32 has a function returning the locale's codepage as a number. */ + /* Woe32 has a function returning the locale's codepage as a number. */ sprintf (buf, "CP%u", GetACP ()); codeset = buf; -#endif +#elif defined OS2 + + const char *locale; + static char buf[2 + 10 + 1]; + ULONG cp[3]; + ULONG cplen; - if (codeset != NULL && codeset[0] != '\0') + /* 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; + } + + /* 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 (codeset[0] == '\0') + codeset = "ASCII"; return codeset; }