X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Flocalcharset.c;h=1ff46052d757089ce020dbd65afaef7c3b7923ef;hb=cc7f5298d74867d113d32db1ddfb5f3667cbaeff;hp=fa6f8a34ae89e2f589f86efb379c288b40d046a7;hpb=506c68800b8e428247472e39568cefc477409684;p=gnulib.git diff --git a/lib/localcharset.c b/lib/localcharset.c index fa6f8a34a..1ff46052d 100644 --- a/lib/localcharset.c +++ b/lib/localcharset.c @@ -1,59 +1,84 @@ /* Determine a canonical name for the current locale's character encoding. - Copyright (C) 2000-2001 Free Software Foundation, Inc. + Copyright (C) 2000-2006, 2008-2009 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 - by the Free Software Foundation; either version 2, or (at your option) + 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, 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 - Library General Public License for more details. + 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 Library General Public - License along with this program; if not, write to the Free Software - Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, - USA. */ + 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */ -/* Written by Bruno Haible . */ +/* Written by Bruno Haible . */ -#ifdef HAVE_CONFIG_H -# include -#endif +#include -#if HAVE_STDDEF_H -# include -#endif +/* Specification. */ +#include "localcharset.h" +#include #include -#if HAVE_STRING_H -# include -#else -# include -#endif -#if HAVE_STDLIB_H -# include +#include +#include + +#if defined __APPLE__ && defined __MACH__ && HAVE_LANGINFO_CODESET +# define DARWIN7 /* Darwin 7 or newer, i.e. MacOS X 10.3 or newer */ #endif #if defined _WIN32 || defined __WIN32__ -# undef WIN32 /* avoid warning on mingw32 */ -# define WIN32 +# define WIN32_NATIVE #endif -#ifndef WIN32 +#if defined __EMX__ +/* Assume EMX program runs on OS/2, even if compiled under DOS. */ +# ifndef OS2 +# define OS2 +# endif +#endif + +#if !defined WIN32_NATIVE # if HAVE_LANGINFO_CODESET # include # else -# if HAVE_SETLOCALE +# if 0 /* see comment below */ # include # endif # endif -#else /* WIN32 */ +# ifdef __CYGWIN__ +# define WIN32_LEAN_AND_MEAN +# include +# endif +#elif defined WIN32_NATIVE # define WIN32_LEAN_AND_MEAN # include #endif +#if defined OS2 +# define INCL_DOS +# include +#endif + +#if ENABLE_RELOCATABLE +# include "relocatable.h" +#else +# define relocate(pathname) (pathname) +#endif + +/* Get LIBDIR. */ +#ifndef LIBDIR +# include "configmake.h" +#endif + +#if defined _WIN32 || defined __WIN32__ || defined __CYGWIN__ || defined __EMX__ || defined __DJGPP__ + /* Win32, Cygwin, OS/2, DOS */ +# define ISSLASH(C) ((C) == '/' || (C) == '\\') +#endif #ifndef DIRECTORY_SEPARATOR # define DIRECTORY_SEPARATOR '/' @@ -63,32 +88,46 @@ # define ISSLASH(C) ((C) == DIRECTORY_SEPARATOR) #endif +#if HAVE_DECL_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 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 () +get_charset_aliases (void) { - char *cp; + const char *cp; cp = charset_aliases; if (cp == NULL) { -#ifndef WIN32 +#if !(defined DARWIN7 || defined VMS || defined WIN32_NATIVE || defined __CYGWIN__) FILE *fp; - const char *dir = LIBDIR; + const char *dir; const char *base = "charset.alias"; char *file_name; + /* Make it possible to override the charset.alias location. This is + necessary for running the testsuite before "make install". */ + dir = getenv ("CHARSETALIASDIR"); + if (dir == NULL || dir[0] == '\0') + dir = relocate (LIBDIR); + /* Concatenate dir and base into freshly allocated file_name. */ { size_t dir_len = strlen (dir); @@ -110,15 +149,17 @@ get_charset_aliases () else { /* Parse the file's contents. */ - int c; - char buf1[50+1]; - char buf2[50+1]; char *res_ptr = NULL; size_t res_size = 0; - size_t l1, l2; for (;;) { + int c; + char buf1[50+1]; + char buf2[50+1]; + size_t l1, l2; + char *old_res_ptr; + c = getc (fp); if (c == EOF) break; @@ -135,24 +176,27 @@ 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); + old_res_ptr = res_ptr; 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) { /* Out of memory. */ res_size = 0; + if (old_res_ptr != NULL) + free (old_res_ptr); break; } strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1); @@ -171,14 +215,95 @@ get_charset_aliases () if (file_name != NULL) free (file_name); -#else /* WIN32 */ +#else + +# if defined DARWIN7 + /* To avoid the trouble of installing a file that is shared by many + GNU packages -- many packaging systems have problems with this --, + simply inline the aliases here. */ + cp = "ISO8859-1" "\0" "ISO-8859-1" "\0" + "ISO8859-2" "\0" "ISO-8859-2" "\0" + "ISO8859-4" "\0" "ISO-8859-4" "\0" + "ISO8859-5" "\0" "ISO-8859-5" "\0" + "ISO8859-7" "\0" "ISO-8859-7" "\0" + "ISO8859-9" "\0" "ISO-8859-9" "\0" + "ISO8859-13" "\0" "ISO-8859-13" "\0" + "ISO8859-15" "\0" "ISO-8859-15" "\0" + "KOI8-R" "\0" "KOI8-R" "\0" + "KOI8-U" "\0" "KOI8-U" "\0" + "CP866" "\0" "CP866" "\0" + "CP949" "\0" "CP949" "\0" + "CP1131" "\0" "CP1131" "\0" + "CP1251" "\0" "CP1251" "\0" + "eucCN" "\0" "GB2312" "\0" + "GB2312" "\0" "GB2312" "\0" + "eucJP" "\0" "EUC-JP" "\0" + "eucKR" "\0" "EUC-KR" "\0" + "Big5" "\0" "BIG5" "\0" + "Big5HKSCS" "\0" "BIG5-HKSCS" "\0" + "GBK" "\0" "GBK" "\0" + "GB18030" "\0" "GB18030" "\0" + "SJIS" "\0" "SHIFT_JIS" "\0" + "ARMSCII-8" "\0" "ARMSCII-8" "\0" + "PT154" "\0" "PT154" "\0" + /*"ISCII-DEV" "\0" "?" "\0"*/ + "*" "\0" "UTF-8" "\0"; +# endif + +# if defined VMS + /* To avoid the troubles of an extra file charset.alias_vms in the + sources of many GNU packages, simply inline the aliases here. */ + /* The list of encodings is taken from the OpenVMS 7.3-1 documentation + "Compaq C Run-Time Library Reference Manual for OpenVMS systems" + section 10.7 "Handling Different Character Sets". */ + cp = "ISO8859-1" "\0" "ISO-8859-1" "\0" + "ISO8859-2" "\0" "ISO-8859-2" "\0" + "ISO8859-5" "\0" "ISO-8859-5" "\0" + "ISO8859-7" "\0" "ISO-8859-7" "\0" + "ISO8859-8" "\0" "ISO-8859-8" "\0" + "ISO8859-9" "\0" "ISO-8859-9" "\0" + /* Japanese */ + "eucJP" "\0" "EUC-JP" "\0" + "SJIS" "\0" "SHIFT_JIS" "\0" + "DECKANJI" "\0" "DEC-KANJI" "\0" + "SDECKANJI" "\0" "EUC-JP" "\0" + /* Chinese */ + "eucTW" "\0" "EUC-TW" "\0" + "DECHANYU" "\0" "DEC-HANYU" "\0" + "DECHANZI" "\0" "GB2312" "\0" + /* Korean */ + "DECKOREAN" "\0" "EUC-KR" "\0"; +# endif +# if defined WIN32_NATIVE || defined __CYGWIN__ /* 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"; + "CP1361" "\0" "JOHAB" "\0" + "CP20127" "\0" "ASCII" "\0" + "CP20866" "\0" "KOI8-R" "\0" + "CP20936" "\0" "GB2312" "\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" + "CP38598" "\0" "ISO-8859-8" "\0" + "CP51932" "\0" "EUC-JP" "\0" + "CP51936" "\0" "GB2312" "\0" + "CP51949" "\0" "EUC-KR" "\0" + "CP51950" "\0" "EUC-TW" "\0" + "CP54936" "\0" "GB18030" "\0" + "CP65001" "\0" "UTF-8" "\0"; +# endif #endif charset_aliases = cp; @@ -197,18 +322,65 @@ get_charset_aliases () STATIC #endif const char * -locale_charset () +locale_charset (void) { const char *codeset; const char *aliases; -#ifndef WIN32 +#if !(defined WIN32_NATIVE || defined OS2) # if HAVE_LANGINFO_CODESET /* Most systems support nl_langinfo (CODESET) nowadays. */ codeset = nl_langinfo (CODESET); +# ifdef __CYGWIN__ + /* Cygwin 2006 does not have locales. nl_langinfo (CODESET) always + returns "US-ASCII". As long as this is not fixed, return the suffix + of the locale name from the environment variables (if present) or + the codepage as a number. */ + if (codeset != NULL && strcmp (codeset, "US-ASCII") == 0) + { + const char *locale; + static char buf[2 + 10 + 1]; + + locale = getenv ("LC_ALL"); + if (locale == NULL || locale[0] == '\0') + { + 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; + } + } + } + + /* Woe32 has a function returning the locale's codepage as a number. */ + sprintf (buf, "CP%u", GetACP ()); + codeset = buf; + } +# endif + # else /* On old systems which lack it, use setlocale or getenv. */ @@ -218,7 +390,7 @@ locale_charset () (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 +# if 0 locale = setlocale (LC_CTYPE, NULL); # endif if (locale == NULL || locale[0] == '\0') @@ -239,31 +411,89 @@ locale_charset () # endif -#else /* WIN32 */ +#elif defined WIN32_NATIVE 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; +#elif defined OS2 + + 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') + { + 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 = ""; - else if (codeset[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; - } - } + + /* 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; }