*** empty log message ***

[gnulib.git] / lib / localcharset.c

diff --git a/lib/localcharset.c b/lib/localcharset.c
index 932473c..61f8f3e 100644 (file)
--- 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
@@ -37,12 +37,22 @@
 # include <stdlib.h>
 #endif
 
-#if HAVE_LANGINFO_CODESET
-# include <langinfo.h>
-#else
-# if HAVE_SETLOCALE
-#  include <locale.h>
+#if defined _WIN32 || defined __WIN32__
+# undef WIN32   /* avoid warning on mingw32 */
+# define WIN32
+#endif
+
+#ifndef WIN32
+# if HAVE_LANGINFO_CODESET
+#  include <langinfo.h>
+# else
+#  if HAVE_SETLOCALE
+#   include <locale.h>
+#  endif
 # endif
+#else /* WIN32 */
+# define WIN32_LEAN_AND_MEAN
+# include <windows.h>
 #endif
 
 #ifndef DIRECTORY_SEPARATOR
@@ -59,20 +69,24 @@
    '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
       FILE *fp;
       const char *dir = LIBDIR;
       const char *base = "charset.alias";
@@ -157,9 +171,20 @@ get_charset_aliases ()
            }
        }
 
-      charset_aliases = cp;
       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;
     }
 
   return cp;
@@ -169,7 +194,7 @@ 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
@@ -180,19 +205,25 @@ 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
+#  endif
   if (locale == NULL || locale[0] == '\0')
     {
       locale = getenv ("LC_ALL");
@@ -209,20 +240,32 @@ 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 && 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;
-         }
-    }
+  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;
 }