ext/Encode/CN/CN.pm

   1 package Encode::CN;
   2 our $VERSION = do { my @r = (q$Revision: 0.96 $ =~ /\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 # Relocated from Encode.pm
  10 # CP936 doesn't have vendor-addon for GBK, so they're identical.
  11 Encode::define_alias( qr/^gbk$/i => '"cp936"');
  12
  13 1;
  14 __END__
  15 =head1 NAME
  16
  17 Encode::CN - China-based Chinese Encodings
  18
  19 =head1 SYNOPSIS
  20
  21     use Encode qw/encode decode/;
  22     $euc_cn = encode("euc-cn", $utf8);   # loads Encode::CN implicitly
  23     $utf8   = decode("euc-cn", $euc_cn); # ditto
  24
  25 =head1 DESCRIPTION
  26
  27 This module implements China-based Chinese charset encodings.
  28 Encodings supported are as follows.
  29
  30   Canonical   Alias             Description
  31   --------------------------------------------------------------------
  32   euc-cn      /euc.*cn$/i       EUC (Extended Unix Character)
  33               /cn.*euc$/i
  34   gb2312                        The raw (low-bit) GB2312 character map
  35   gb12345                       Traditional chinese counterpart to
  36                                 GB2312 (raw)
  37   iso-ir-165                    GB2312 + GB6345 + GB8565 + additions
  38   cp936                         Code Page 936, also known as GBK
  39                                 (Extended GuoBiao)
  40   hz                            7-bit escaped GB2312 encoding
  41   --------------------------------------------------------------------
  42
  43 To find how to use this module in detail, see L<Encode>.
  44
  45 =head1 NOTES
  46
  47 Due to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
  48 separately on CPAN, under the name L<Encode::HanExtra>. That module
  49 also contains extra Taiwan-based encodings.
  50
  51 =head1 BUGS
  52
  53 ASCII part (0x00-0x7f) is preserved for all encodings, even though it
  54 conflicts with mappings by the Unicode Consortium.  See
  55
  56 F<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
  57
  58 to find why it is implemented that way.
  59
  60 =head1 SEE ALSO
  61
  62 L<Encode>
  63
  64 =cut