X-Git-Url: https://perl5.git.perl.org/perl5.git/blobdiff_plain/be3c0a43e1e6b1244032726df02a3ab450a3c4be..8006bbc377c15cd3d89b49736744acd8c1396f24:/locale.c

diff --git a/locale.c b/locale.c
index 22e9030..6f5f016 100644
--- a/locale.c
+++ b/locale.c
@@ -1,6 +1,7 @@
 /*    locale.c
  *
- *    Copyright (c) 2001-2002, Larry Wall
+ *    Copyright (C) 1993, 1994, 1995, 1996, 1997, 1998, 1999,
+ *    2000, 2001, 2002, 2003, by Larry Wall and others
  *
  *    You may distribute under the terms of either the GNU General Public
  *    License or the Artistic License, as specified in the README file.
@@ -25,6 +26,12 @@
 #  include <locale.h>
 #endif
 
+#ifdef I_LANGINFO
+#   include <langinfo.h>
+#endif
+
+#include "reentr.h"
+
 /*
  * Standardize the locale name from a string returned by 'setlocale'.
  *
@@ -212,7 +219,7 @@ Perl_new_collate(pTHX_ char *newcoll)
 	  SSize_t mult = fb - fa;
 	  if (mult < 1)
 	      Perl_croak(aTHX_ "strxfrm() gets absurd");
-	  PL_collxfrm_base = (fa > mult) ? (fa - mult) : 0;
+	  PL_collxfrm_base = (fa > (Size_t)mult) ? (fa - mult) : 0;
 	  PL_collxfrm_mult = mult;
 	}
     }
@@ -462,10 +469,66 @@ Perl_init_i18nl10n(pTHX_ int printwarn)
 #ifdef USE_LOCALE_NUMERIC
     new_numeric(curnum);
 #endif /* USE_LOCALE_NUMERIC */
+
     }
 
 #endif /* USE_LOCALE */
 
+#ifdef USE_PERLIO
+    {
+      /* 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_unicode (set by -C or by $ENV{PERL_UNICODE})
+         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)
+	      utf8locale = (ibcmp(codeset,  "UTF-8", 5) == 0 ||
+ 			    ibcmp(codeset,  "UTF8",  4) == 0);
+#if defined(USE_LOCALE)
+	 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 (curctype)
+		   utf8locale = (ibcmp(curctype,     "UTF-8", 5) == 0 ||
+			         ibcmp(curctype,     "UTF8",  4) == 0);
+#endif
+	      if (lc_all)
+		   utf8locale = (ibcmp(lc_all,   "UTF-8", 5) == 0 ||
+			         ibcmp(lc_all,   "UTF8",  4) == 0);
+	 }
+#endif /* USE_LOCALE */
+	 if (utf8locale)
+	      PL_utf8locale = TRUE;
+    }
+    /* Set PL_unicode to $ENV{PERL_UNICODE} 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_UNICODE");
+	 PL_unicode = p ? parse_unicode_opts(&p) : 0;
+    }
+#endif
+
 #ifdef USE_LOCALE_CTYPE
     if (curctype != NULL)
 	Safefree(curctype);
@@ -520,7 +583,7 @@ Perl_mem_collxfrm(pTHX_ const char *s, STRLEN len, STRLEN *xlen)
 	    xused = strxfrm(xbuf + xout, s + xin, xAlloc - xout);
 	    if (xused == -1)
 		goto bad;
-	    if (xused < xAlloc - xout)
+	    if ((STRLEN)xused < xAlloc - xout)
 		break;
 	    xAlloc = (2 * xAlloc) + 1;
 	    Renew(xbuf, xAlloc, char);