ext/Encode/CN/CN.pm

   1 package Encode::CN;
   2 our $VERSION = do { my @r = (q$Revision: 0.95 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
   3
   4 use Encode;
   5 use Encode::CN::HZ;
   6 use XSLoader;
   7 XSLoader::load('Encode::CN',$VERSION);
   8
   9 Encode::define_alias( qr/euc.*cn$/i     => '"euc-cn"' );
  10 Encode::define_alias( qr/cn.*euc/i      => '"euc-cn"' );
  11
  12 # Relocated from Encode.pm
  13 # CP936 doesn't have vendor-addon for GBK, so they're identical.
  14 Encode::define_alias( qr/^gbk$/i => '"cp936"');
  15
  16 1;
  17 __END__
  18 =head1 NAME
  19
  20 Encode::CN - China-based Chinese Encodings
  21
  22 =head1 SYNOPSIS
  23
  24     use Encode qw/encode decode/;
  25     $euc_cn = encode("euc-cn", $utf8);   # loads Encode::CN implicitly
  26     $utf8   = decode("euc-cn", $euc_cn); # ditto
  27
  28 =head1 DESCRIPTION
  29
  30 This module implements China-based Chinese charset encodings.
  31 Encodings supported are as follows.
  32
  33   Canonical   Alias             Description
  34   --------------------------------------------------------------------
  35   euc-cn      /euc.*cn$/i       EUC (Extended Unix Character)
  36               /cn.*euc$/i
  37   gb2312                        The raw (low-bit) GB2312 character map
  38   gb12345                       Traditional chinese counterpart to
  39                                 GB2312 (raw)
  40   iso-ir-165                    GB2312 + GB6345 + GB8565 + additions
  41   cp936                         Code Page 936, also known as GBK
  42                                 (Extended GuoBiao)
  43   hz                            7-bit escaped GB2312 encoding
  44
  45 To find how to use this module in detail, see L<Encode>.
  46
  47 =head1 NOTES
  48
  49 Due to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
  50 separately on CPAN, under the name L<Encode::HanExtra>. That module
  51 also contains extra Taiwan-based encodings.
  52
  53 =head1 BUGS
  54
  55 ASCII part (0x00-0x7f) is preserved for all encodings, even though it
  56 conflicts with mappings by the Unicode Consortium.  See
  57
  58 F<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
  59
  60 to find why it is implemented that way.
  61
  62 =head1 SEE ALSO
  63
  64 L<Encode>
  65
  66 =cut