locale.c: Add is_locale_utf8()

Previous commits have added the infrastructure to be able to determine
if a locale is UTF-8.  This will prove useful, and this commit adds
a function to encapsulate this information, and uses it in a couple of
places, with more to come in future commits.

This uses as a final fallback, mbtowc(), supposed to be available in
C99.  Future commits will add heuristics when that function isn't
available or is known to be unreliable on a particular system.

embed.fnc

@@ -3334,6 +3334,7 @@ So	|const char *|toggle_locale_i|const unsigned switch_cat_index	\
 So	|void	|restore_toggled_locale_i|const unsigned cat_index	\
                                 |NULLOK const char * original_locale    \
 				|const line_t caller_line
+S	|bool	|is_locale_utf8	|NN const char * locale
 #    if defined(USE_POSIX_2008_LOCALE)
 S	|const char*|emulate_setlocale_i|const unsigned int index	\
 				    |NULLOK const char* new_locale	\

embed.h

@@ -1706,6 +1706,7 @@
 #define category_name		S_category_name
 #define get_category_index	S_get_category_index
 #define is_codeset_name_UTF8	S_is_codeset_name_UTF8
+#define is_locale_utf8(a)	S_is_locale_utf8(aTHX_ a)
 #define new_LC_ALL(a)		S_new_LC_ALL(aTHX_ a)
 #define new_collate(a)		S_new_collate(aTHX_ a)
 #define new_ctype(a)		S_new_ctype(aTHX_ a)

locale.c

@@ -1846,7 +1846,7 @@ S_new_ctype(pTHX_ const char *newctype)
         PL_warn_locale = NULL;
     }
 
-    PL_in_utf8_CTYPE_locale = _is_cur_LC_category_utf8(LC_CTYPE);
+    PL_in_utf8_CTYPE_locale = is_locale_utf8(newctype);
 
     /* A UTF-8 locale gets standard rules.  But note that code still has to
      * handle this specially because of the three problematic code points */
@@ -2213,7 +2213,7 @@ S_new_collate(pTHX_ const char *newcoll)
             goto is_standard_collation;
         }
 
-        PL_in_utf8_COLLATE_locale = _is_cur_LC_category_utf8(LC_COLLATE);
+        PL_in_utf8_COLLATE_locale = is_locale_utf8(newcoll);
         PL_strxfrm_NUL_replacement = '\0';
         PL_strxfrm_max_cp = 0;
 
@@ -5770,7 +5770,39 @@ S_is_codeset_name_UTF8(const char * name)
             && (len == 4 || name[3] == '-'));
 }
 
-#endif
+STATIC bool
+S_is_locale_utf8(pTHX_ const char * locale)
+{
+    /* Returns TRUE if the locale 'locale' is UTF-8; FALSE otherwise.  It uses
+     * my_langinfo() */
+
+#  if ! defined(USE_LOCALE_CTYPE)                                             \
+   ||   defined(EBCDIC) /* There aren't any real UTF-8 locales at this time */
+
+    PERL_UNUSED_ARG(locale);
+
+    return FALSE;
+
+#  else
+
+    const char * scratch_buffer = NULL;
+    const char * codeset = my_langinfo_c(CODESET, LC_CTYPE, locale,
+                                         &scratch_buffer, NULL);
+    bool retval = is_codeset_name_UTF8(codeset);
+
+    PERL_ARGS_ASSERT_IS_LOCALE_UTF8;
+
+    DEBUG_Lv(PerlIO_printf(Perl_debug_log,
+                           "found codeset=%s, is_utf8=%d\n", codeset, retval));
+
+    Safefree(scratch_buffer);
+    return retval;
+
+#  endif
+
+}
+
+#endif  /* USE_LOCALE */
 
 bool
 Perl__is_in_locale_category(pTHX_ const bool compiling, const int category)

proto.h

@@ -5635,6 +5635,9 @@ STATIC unsigned int	S_get_category_index(const int category, const char * locale
 STATIC bool	S_is_codeset_name_UTF8(const char * name);
 #define PERL_ARGS_ASSERT_IS_CODESET_NAME_UTF8	\
 	assert(name)
+STATIC bool	S_is_locale_utf8(pTHX_ const char * locale);
+#define PERL_ARGS_ASSERT_IS_LOCALE_UTF8	\
+	assert(locale)
 STATIC void	S_new_LC_ALL(pTHX_ const char* unused);
 #define PERL_ARGS_ASSERT_NEW_LC_ALL
 STATIC void	S_new_collate(pTHX_ const char* newcoll);