X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=locale.c;h=9d522444ca620b38c8523b876a356fca4c12ac1c;hb=e8d7f3747c04a9bb10b98235d6cac8ff43bf8a54;hp=02d546df69861d519b10d7c91e6df920126fb08b;hpb=eb160463266f58ba83ae9bb9ae8bbdc8f0c3027b;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/locale.c b/locale.c
index 02d546d..9d52244 100644
--- a/locale.c
+++ b/locale.c
@@ -29,6 +29,8 @@
 #   include <langinfo.h>
 #endif
 
+#include "reentr.h"
+
 /*
  * Standardize the locale name from a string returned by 'setlocale'.
  *
@@ -471,41 +473,60 @@ Perl_init_i18nl10n(pTHX_ int printwarn)
 
 #endif /* USE_LOCALE */
 
+#ifdef USE_PERLIO
     {
-	 bool wantutf8 = FALSE;
+      /* Set PL_utf8locale to TRUE if using PerlIO _and_
+	 any of the following are true:
+	 - nl_langinfo(CODESET) contains /^utf-?8/i
+	 - $ENV{LC_ALL}   contains /^utf-?8/i
+	 - $ENV{LC_CTYPE} contains /^utf-?8/i
+	 - $ENV{LANG}     contains /^utf-?8/i
+	 The LC_ALL, LC_CTYPE, LANG obey the usual override
+	 hierarchy of locale environment variables.  (LANGUAGE
+	 affects only LC_MESSAGES only under glibc.) (If present,
+	 it overrides LC_MESSAGES for GNU gettext, and it also
+	 can have more than one locale, separated by spaces,
+	 in case you need to know.)
+	 If PL_utf8locale and PL_wantutf8 (set by -C) are true,
+	 perl.c:S_parse_body() will turn on the PerlIO :utf8 layer
+	 on STDIN, STDOUT, STDERR, _and_ the default open discipline.
+      */
+	 bool utf8locale = FALSE;
 	 char *codeset = NULL;
 #if defined(HAS_NL_LANGINFO) && defined(CODESET)
 	 codeset = nl_langinfo(CODESET);
 #endif
-	 if (codeset &&
-	     (ibcmp(codeset,  "UTF-8", 5) == 0 ||
-	      ibcmp(codeset,  "UTF8",  4) == 0))
-	      wantutf8 = TRUE;
+	 if (codeset)
+	      utf8locale = (ibcmp(codeset,  "UTF-8", 5) == 0 ||
+ 			    ibcmp(codeset,  "UTF8",  4) == 0);
 #if defined(USE_LOCALE)
-#ifdef __GLIBC__
-	 if (!wantutf8 && language &&
-	     (ibcmp(language, "UTF-8", 5) == 0 ||
-	      ibcmp(language, "UTF8",  4) == 0))
-	      wantutf8 = TRUE;
-#endif
-	 if (!wantutf8 && lc_all &&
-	     (ibcmp(lc_all,   "UTF-8", 5) == 0 ||
-	      ibcmp(lc_all,   "UTF8",  4) == 0))
-	      wantutf8 = TRUE;
+	 else { /* nl_langinfo(CODESET) is supposed to correctly
+		 * interpret the locale environment variables,
+		 * but just in case it fails, let's do this manually. */ 
+	      if (lang)
+		   utf8locale = (ibcmp(lang,     "UTF-8", 5) == 0 ||
+			         ibcmp(lang,     "UTF8",  4) == 0);
 #ifdef USE_LOCALE_CTYPE
-	 if (!wantutf8 && curctype &&
-	     (ibcmp(curctype,     "UTF-8", 5) == 0 ||
-	      ibcmp(curctype,     "UTF8",  4) == 0))
-	      wantutf8 = TRUE;
+	      if (curctype)
+		   utf8locale = (ibcmp(curctype,     "UTF-8", 5) == 0 ||
+			         ibcmp(curctype,     "UTF8",  4) == 0);
 #endif
-	 if (!wantutf8 && lang &&
-	     (ibcmp(lang,     "UTF-8", 5) == 0 ||
-	      ibcmp(lang,     "UTF8",  4) == 0))
-	      wantutf8 = TRUE;
+	      if (lc_all)
+		   utf8locale = (ibcmp(lc_all,   "UTF-8", 5) == 0 ||
+			         ibcmp(lc_all,   "UTF8",  4) == 0);
+	 }
 #endif /* USE_LOCALE */
-	 if (wantutf8)
-	      PL_wantutf8 = TRUE;
+	 if (utf8locale)
+	      PL_utf8locale = TRUE;
     }
+    /* Set PL_wantutf8 to $ENV{PERL_UTF8_LOCALE} if using PerlIO.
+       This is an alternative to using the -C command line switch
+       (the -C if present will override this). */
+    {
+	 char *p = PerlEnv_getenv("PERL_UTF8_LOCALE");
+	 PL_wantutf8 = p ? (bool) atoi(p) : FALSE;
+    }
+#endif
 
 #ifdef USE_LOCALE_CTYPE
     if (curctype != NULL)