Upgrade to Encode 2.00.

[p5sagit/p5-mst-13.2.git] / ext / Encode / JP / JP.pm

diff --git a/ext/Encode/JP/JP.pm b/ext/Encode/JP/JP.pm
index 3091a99..696f928 100644 (file)
--- a/ext/Encode/JP/JP.pm
+++ b/ext/Encode/JP/JP.pm
@@ -5,23 +5,16 @@ BEGIN {
     }
 }
 use Encode;
-our $VERSION = do { my @r = (q$Revision: 0.94 $ =~ /\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 XSLoader;
-XSLoader::load('Encode::JP',$VERSION);
+XSLoader::load(__PACKAGE__,$VERSION);
 
-use Encode::JP::JIS;
-use Encode::JP::ISO_2022_JP;
-
-Encode::define_alias( qr/euc.*jp$/i     => '"euc-jp"' );
-Encode::define_alias( qr/jp.*euc/i      => '"euc-jp"' );
-Encode::define_alias( qr/ujis$/i        => '"euc-jp"' );
-Encode::define_alias( qr/shift.*jis$/i  => '"shiftjis"' );
-Encode::define_alias( qr/sjis$/i        => '"shiftjis"' );
-Encode::define_alias( qr/^jis$/i        => '"7bit-jis"' );
+use Encode::JP::JIS7;
 
 1;
 __END__
+
 =head1 NAME
 
 Encode::JP - Japanese Encodings
@@ -39,30 +32,63 @@ supported are as follows.
 
   Canonical   Alias            Description
   --------------------------------------------------------------------
-  euc-jp      /euc.*jp$/i      EUC (Extended Unix Character)
-              /jp.*euc/i   
-             /ujis$/i
-  shiftjis    /shift.*jis$/i   Shift JIS (aka MS Kanji)
-             /sjis$/i
-  7bit-jis    /^jis$/i         7bit JIS
-  iso-2022-jp                  ISO-2022-JP 
-                               (7bit JIS with all Halfwidth Kana 
-                                converted to Fullwidth)
-  macjapan      Mac Japan      (Shift JIS + Apple vendor mappings)
-  cp932         Code Page 932  (Shift JIS + Microsoft vendor mappings)
+  euc-jp      /\beuc.*jp$/i    EUC (Extended Unix Character)
+              /\bjp.*euc/i   
+             /\bujis$/i
+  shiftjis    /\bshift.*jis$/i Shift JIS (aka MS Kanji)
+             /\bsjis$/i
+  7bit-jis    /\bjis$/i                7bit JIS
+  iso-2022-jp                  ISO-2022-JP                  [RFC1468]
+                               = 7bit JIS with all Halfwidth Kana 
+                                 converted to Fullwidth
+  iso-2022-jp-1                        ISO-2022-JP-1                [RFC2237]
+                                = ISO-2022-JP with JIS X 0212-1990
+                                 support.  See below
+  MacJapanese                  Shift JIS + Apple vendor mappings
+  cp932                         Code Page 932  
+                                = Shift JIS + MS/IBM vendor mappings
+  jis0201-raw                   JIS0201, raw format
+  jis0208-raw                   JIS0201, raw format
+  jis0212-raw                   JIS0201, raw format
+  --------------------------------------------------------------------
 
 =head1 DESCRIPTION
 
-To find how to use this module in detail, see L<Encode>.
+To find out how to use this module in detail, see L<Encode>.
+
+=head1 Note on ISO-2022-JP(-1)?
+
+ISO-2022-JP-1 (RFC2237) is a superset of ISO-2022-JP (RFC1468) which
+adds support for JIS X 0212-1990.  That means you can use the same
+code to decode to utf8 but not vice versa.
+
+  $utf8 = decode('iso-2022-jp-1', $stream);
+
+and
+
+  $utf8 = decode('iso-2022-jp',   $stream);
+
+yield the same result but
+
+  $with_0212 = encode('iso-2022-jp-1', $utf8);
+
+is now different from
+
+  $without_0212 = encode('iso-2022-jp', $utf8 );
+
+In the latter case, characters that map to 0212 are first converted
+to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu' or
+'geta mark') then fed to the decoding engine.  U+FFFD is not used,
+in order to preserve text layout as much as possible.
 
 =head1 BUGS
 
-ASCII part (0x00-0x7f) is preserved for all encodings, even though it
-conflicts with mappings by the Unicode Consortium.  See
+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