[Summary view] [Print] [Text view]

   1  package Encode::CN;
   2  BEGIN {
   3      if ( ord("A") == 193 ) {
   4          die "Encode::CN not supported on EBCDIC\n";
   5      }
   6  }
   7  use strict;
   8  use warnings;
   9  use Encode;
  10  our $VERSION = do { my @r = ( q$Revision: 2.2 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
  11  use XSLoader;
  12  XSLoader::load( __PACKAGE__, $VERSION );
  13  
  14  # Relocated from Encode.pm
  15  
  16  use Encode::CN::HZ;
  17  
  18  # use Encode::CN::2022_CN;
  19  
  20  1;
  21  __END__
  22  
  23  =head1 NAME
  24  
  25  Encode::CN - China-based Chinese Encodings
  26  
  27  =head1 SYNOPSIS
  28  
  29      use Encode qw/encode decode/; 
  30      $euc_cn = encode("euc-cn", $utf8);   # loads Encode::CN implicitly
  31      $utf8   = decode("euc-cn", $euc_cn); # ditto
  32  
  33  =head1 DESCRIPTION
  34  
  35  This module implements China-based Chinese charset encodings.
  36  Encodings supported are as follows.
  37  
  38    Canonical   Alias        Description
  39    --------------------------------------------------------------------
  40    euc-cn      /\beuc.*cn$/i    EUC (Extended Unix Character)
  41            /\bcn.*euc$/i
  42                /\bGB[-_ ]?2312(?:\D.*$|$)/i (see below)
  43    gb2312-raw            The raw (low-bit) GB2312 character map
  44    gb12345-raw            Traditional chinese counterpart to 
  45                  GB2312 (raw)
  46    iso-ir-165            GB2312 + GB6345 + GB8565 + additions
  47    MacChineseSimp                GB2312 + Apple Additions
  48    cp936                Code Page 936, also known as GBK 
  49                  (Extended GuoBiao)
  50    hz                7-bit escaped GB2312 encoding
  51    --------------------------------------------------------------------
  52  
  53  To find how to use this module in detail, see L<Encode>.
  54  
  55  =head1 NOTES
  56  
  57  Due to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
  58  separately on CPAN, under the name L<Encode::HanExtra>. That module
  59  also contains extra Taiwan-based encodings.
  60  
  61  =head1 BUGS
  62  
  63  When you see C<charset=gb2312> on mails and web pages, they really
  64  mean C<euc-cn> encodings.  To fix that, C<gb2312> is aliased to C<euc-cn>.
  65  Use C<gb2312-raw> when you really mean it.
  66  
  67  The ASCII region (0x00-0x7f) is preserved for all encodings, even though
  68  this conflicts with mappings by the Unicode Consortium.  See
  69  
  70  L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
  71  
  72  to find out why it is implemented that way.
  73  
  74  =head1 SEE ALSO
  75  
  76  L<Encode>
  77  
  78  =cut