* encoding.c: include locale.h

  (rb_locale_charmap): new method Encoding.locale_charmap for
  nl_langinfo(CODESET).

* include/ruby/encoding.h (rb_locale_charmap): declared.

* main.c (main): call setlocale with LC_CTYPE.

* ruby.c (locale_encoding): use rb_locale_charmap.


git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@14380 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

5 files changed, 33 insertions, 26 deletions

diff --git a/ChangeLog b/ChangeLog
index 2979f11922..a9ebbfd403 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,15 @@
+Fri Dec 21 11:47:56 2007  Tanaka Akira  <akr@fsij.org>
+
+	* encoding.c: include locale.h
+	  (rb_locale_charmap): new method Encoding.locale_charmap for
+	  nl_langinfo(CODESET).
+
+	* include/ruby/encoding.h (rb_locale_charmap): declared.
+
+	* main.c (main): call setlocale with LC_CTYPE.
+
+	* ruby.c (locale_encoding): use rb_locale_charmap.
+
 Fri Dec 21 11:35:10 2007  Koichi Sasada  <ko1@atdot.net>
 
 	* vm.c, vm_dump.c: fix typo.  Reported by Yuki Mitsui.
diff --git a/encoding.c b/encoding.c
index a85cfdfdf5..1e130162be 100644
--- a/encoding.c
+++ b/encoding.c
@@ -14,6 +14,7 @@
 #include "ruby/encoding.h"
 #include "regenc.h"
 #include <ctype.h>
+#include <langinfo.h>
 
 static ID id_encoding, id_based_encoding;
 static VALUE rb_cEncoding;
@@ -703,6 +704,14 @@ rb_enc_set_default_external(VALUE encoding)
     default_external_index = rb_enc_to_index(rb_to_encoding(encoding));
 }
 
+VALUE
+rb_locale_charmap(VALUE klass)
+{
+    char *codeset;
+    codeset = nl_langinfo(CODESET);
+    return rb_str_new2(codeset);
+}
+
 static void
 set_encoding_const(const char *name, rb_encoding *enc)
 {
@@ -772,6 +781,7 @@ Init_Encoding(void)
     rb_define_singleton_method(rb_cEncoding, "_load", enc_load, 1);
 
     rb_define_singleton_method(rb_cEncoding, "default_external", get_default_external, 0);
+    rb_define_singleton_method(rb_cEncoding, "locale_charmap", rb_locale_charmap, 0);
 
     /* dummy for unsupported, statefull encoding */
     rb_enc_replicate("ISO-2022-JP", rb_enc_find(rb_enc_name(ONIG_ENCODING_ASCII)));
diff --git a/include/ruby/encoding.h b/include/ruby/encoding.h
index eb27dfb625..1c45abb4bb 100644
--- a/include/ruby/encoding.h
+++ b/include/ruby/encoding.h
@@ -117,5 +117,6 @@ rb_encoding *rb_default_encoding(void);
 rb_encoding *rb_default_external_encoding(void);
 VALUE rb_enc_default_external(void);
 void rb_enc_set_default_external(VALUE encoding);
+VALUE rb_locale_charmap(VALUE klass);
 
 #endif /* RUBY_ENCODING_H */
diff --git a/main.c b/main.c
index e9d1bada5f..691cfcdd5b 100644
--- a/main.c
+++ b/main.c
@@ -12,6 +12,7 @@
 
 #undef RUBY_EXPORT
 #include "ruby/ruby.h"
+#include <locale.h>
 
 RUBY_GLOBAL_SETUP
 
@@ -22,6 +23,7 @@ main(int argc, char **argv, char **envp)
     extern void ruby_set_debug_option(const char *);
     ruby_set_debug_option(getenv("RUBY_DEBUG"));
 #endif
+    setlocale(LC_CTYPE, "");
 
     ruby_sysinit(&argc, &argv);
     {
diff --git a/ruby.c b/ruby.c
index d3807146a9..f16ed424c8 100644
--- a/ruby.c
+++ b/ruby.c
@@ -138,32 +138,14 @@ usage(const char *name)
 static rb_encoding *
 locale_encoding(void)
 {
-    static const char *const langs[] = {"LC_ALL", "LC_CTYPE", "LANG",};
-    const char *lang, *at;
-    int i, len, idx = 0;
-    char buf[32];
-    rb_encoding *enc;
-
-    for (i = 0; i < sizeof(langs) / sizeof(langs[0]); ++i) {
-	if (!(lang = getenv(langs[i]))) continue;
-	if (!(lang = strchr(lang, '.'))) continue;
-	at = strchr(++lang, '@');
-	if ((len = (at ? at - lang : strlen(lang))) >= sizeof(buf) - 1) continue;
-	MEMCPY(buf, lang, char, len);
-	buf[len] = 0;
-	idx = rb_enc_find_index(buf);
-	if (idx < 0 && len > 3 &&
-	    (strncasecmp(buf, "euc", 3) == 0 ||
-	     strncasecmp(buf, "utf", 3) == 0) &&
-	    buf[3]) {
-	    MEMMOVE(buf + 4, buf + 3, char, len - 2);
-	    buf[3] = '-';
-	    idx = rb_enc_find_index(buf);
-	}
-	enc = rb_enc_from_index(idx);
-	if (enc) return enc;
-    }
-    return rb_default_encoding();
+    VALUE codeset = rb_locale_charmap(Qnil);
+    char *name = StringValueCStr(codeset);
+    int idx;
+
+    idx = rb_enc_find_index(name);
+    if (idx < 0)
+        return rb_default_encoding();
+    return rb_enc_from_index(idx);
 }
 
 extern VALUE rb_load_path;