From: Jarkko Hietaniemi <jhi@iki.fi>
Date: Sun, 3 Nov 2002 17:50:08 +0000 (+0200)
Subject: Re: [PATCH] UTF-8 enabling via locale (was: Re: Redhat 8 issue?)
X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=commitdiff_plain;h=61de9fb5aad39c2904a43125c7c70031be6bc679;p=p5sagit%2Fp5-mst-13.2.git

Re: [PATCH] UTF-8 enabling via locale (was: Re: Redhat 8 issue?)
Message-ID: <20021103155008.GA382682@lyta.hut.fi>

p4raw-id: //depot/perl@18165
---

diff --git a/lib/open.pm b/lib/open.pm
index 2dc1d21..007b667 100644
--- a/lib/open.pm
+++ b/lib/open.pm
@@ -27,6 +27,7 @@ sub _get_locale_encoding {
 	    } elsif ($ENV{LANG} =~ /^([^.]+)\.([^.]+)$/) {
 		($country_language, $locale_encoding) = ($1, $2);
 	    }
+	    # LANGUAGE affects only LC_MESSAGES only on glibc
 	} elsif (not $locale_encoding) {
 	    if ($ENV{LC_ALL} =~ /\butf-?8\b/i ||
 		$ENV{LANG}   =~ /\butf-?8\b/i) {
@@ -250,7 +251,7 @@ pragma.
 
 =back
 
-If your locale environment variables (LANGUAGE, LC_ALL, LC_CTYPE, LANG)
+If your locale environment variables (LC_ALL, LC_CTYPE, LANG)
 contain the strings 'UTF-8' or 'UTF8' (case-insensitive matching),
 the default encoding of your STDIN, STDOUT, and STDERR, and of
 B<any subsequent file open>, is UTF-8.
diff --git a/locale.c b/locale.c
index 0986614..c03451b 100644
--- a/locale.c
+++ b/locale.c
@@ -478,10 +478,15 @@ Perl_init_i18nl10n(pTHX_ int printwarn)
       /* Set PL_wantutf8 to TRUE if using PerlIO _and_
 	 any of the following are true:
 	 - nl_langinfo(CODESET) contains /^utf-?8/i
-	 - $ENV{LANGUAGE} contains /^utf-?8/i (only if using glibc)
-	 - $ENV{LC_CALL} contains /^utf-?8/i
+	 - $ENV{LC_ALL}   contains /^utf-?8/i
 	 - $ENV{LC_CTYPE} contains /^utf-?8/i
-	 - $ENV{LANG} 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_wantutf8 is true, perl.c:S_parse_body()
 	 will turn on the PerlIO :utf8 discipline on STDIN, STDOUT,
 	 STDERR, _and_ the default open discipline.
@@ -491,32 +496,26 @@ Perl_init_i18nl10n(pTHX_ int printwarn)
 #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)
+	      wantutf8 = (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)
+		   wantutf8 = (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)
+		   wantutf8 = (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)
+		   wantutf8 = (ibcmp(lc_all,   "UTF-8", 5) == 0 ||
+			       ibcmp(lc_all,   "UTF8",  4) == 0);
 #endif /* USE_LOCALE */
+	 }
 	 if (wantutf8)
 	      PL_wantutf8 = TRUE;
     }
diff --git a/pod/perl58delta.pod b/pod/perl58delta.pod
index 9b9e529..3bef17b 100644
--- a/pod/perl58delta.pod
+++ b/pod/perl58delta.pod
@@ -415,12 +415,12 @@ for more information about UTF-8.
 
 =item *
 
-If your environment variables (LC_ALL, LC_CTYPE, LANG, LANGUAGE) look
-like you want to use UTF-8 (any of the the variables match C</utf-?8/i>),
-your STDIN, STDOUT, STDERR handles and the default open layer
-(see L<open>) are marked as UTF-8.  (This feature, like other new
-features that combine Unicode and I/O, work only if you are using
-PerlIO, but that's the default.)
+If your environment variables (LC_ALL, LC_CTYPE, LANG) look like you
+want to use UTF-8 (any of the the variables match C</utf-?8/i>), your
+STDIN, STDOUT, STDERR handles and the default open layer (see L<open>)
+are marked as UTF-8.  (This feature, like other new features that
+combine Unicode and I/O, work only if you are using PerlIO, but that's
+the default.)
 
 Note that after this Perl really does assume that everything is UTF-8:
 for example if some input handle is not, Perl will probably very soon