X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=ext%2FEncode%2FCN%2FCN.pm;h=be5a830fc511c0d9a80fa267fe704fa155255eeb;hb=a19d7498e238ac7c03cb96036dee4a734a2a0356;hp=51d90bb5ec3a1ffb59b5eb99c14b759c067c5bbb;hpb=071db25d4bd6237e4ead7e44b9c1420448a117ff;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/ext/Encode/CN/CN.pm b/ext/Encode/CN/CN.pm
index 51d90bb..be5a830 100644
--- a/ext/Encode/CN/CN.pm
+++ b/ext/Encode/CN/CN.pm
@@ -4,19 +4,20 @@ BEGIN {
 	die "Encode::CN not supported on EBCDIC\n";
     }
 }
-our $VERSION = do { my @r = (q$Revision: 0.97 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
+our $VERSION = do { my @r = (q$Revision: 2.0 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
 
 use Encode;
-use Encode::CN::HZ;
 use XSLoader;
-XSLoader::load('Encode::CN',$VERSION);
+XSLoader::load(__PACKAGE__,$VERSION);
 
 # Relocated from Encode.pm
-# CP936 doesn't have vendor-addon for GBK, so they're identical.
-Encode::define_alias( qr/^gbk$/i => '"cp936"');
+
+use Encode::CN::HZ;
+# use Encode::CN::2022_CN;
 
 1;
 __END__
+
 =head1 NAME
 
 Encode::CN - China-based Chinese Encodings
@@ -34,12 +35,14 @@ Encodings supported are as follows.
 
   Canonical   Alias		Description
   --------------------------------------------------------------------
-  euc-cn      /euc.*cn$/i	EUC (Extended Unix Character)
-	      /cn.*euc$/i
-  gb2312			The raw (low-bit) GB2312 character map
-  gb12345			Traditional chinese counterpart to 
+  euc-cn      /\beuc.*cn$/i	EUC (Extended Unix Character)
+	      /\bcn.*euc$/i
+              /\bGB[-_ ]?2312(?:\D.*$|$)/i (see below)
+  gb2312-raw			The raw (low-bit) GB2312 character map
+  gb12345-raw			Traditional chinese counterpart to 
 				GB2312 (raw)
   iso-ir-165			GB2312 + GB6345 + GB8565 + additions
+  MacChineseSimp                GB2312 + Apple Additions
   cp936				Code Page 936, also known as GBK 
 				(Extended GuoBiao)
   hz				7-bit escaped GB2312 encoding
@@ -55,12 +58,16 @@ also contains extra Taiwan-based encodings.
 
 =head1 BUGS
 
-ASCII part (0x00-0x7f) is preserved for all encodings, even though it
-conflicts with mappings by the Unicode Consortium.  See
+When you see C<charset=gb2312> on mails and web pages, they really
+mean C<euc-cn> encodings.  To fix that, C<gb2312> is aliased to C<euc-cn>.
+Use C<gb2312-raw> when you really mean it.
+
+The ASCII region (0x00-0x7f) is preserved for all encodings, even though
+this conflicts with mappings by the Unicode Consortium.  See
 
-F<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
+L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
 
-to find why it is implemented that way.
+to find out why it is implemented that way.
 
 =head1 SEE ALSO