ext/Encode/CN/CN.pm

   1 package Encode::CN;
   2 BEGIN {
   3     if (ord("A") == 193) {
   4         die "Encode::CN not supported on EBCDIC\n";
   5     }
   6 }
   7 our $VERSION = do { my @r = (q$Revision: 0.97 $ =~ /\d+/g); sprintf "%d."."%02d" x $#r, @r };
   8
   9 use Encode;
  10 use Encode::CN::HZ;
  11 use XSLoader;
  12 XSLoader::load('Encode::CN',$VERSION);
  13
  14 # Relocated from Encode.pm
  15 # CP936 doesn't have vendor-addon for GBK, so they're identical.
  16 Encode::define_alias( qr/^gbk$/i => '"cp936"');
  17
  18 1;
  19 __END__
  20 =head1 NAME
  21
  22 Encode::CN - China-based Chinese Encodings
  23
  24 =head1 SYNOPSIS
  25
  26     use Encode qw/encode decode/;
  27     $euc_cn = encode("euc-cn", $utf8);   # loads Encode::CN implicitly
  28     $utf8   = decode("euc-cn", $euc_cn); # ditto
  29
  30 =head1 DESCRIPTION
  31
  32 This module implements China-based Chinese charset encodings.
  33 Encodings supported are as follows.
  34
  35   Canonical   Alias             Description
  36   --------------------------------------------------------------------
  37   euc-cn      /euc.*cn$/i       EUC (Extended Unix Character)
  38               /cn.*euc$/i
  39   gb2312                        The raw (low-bit) GB2312 character map
  40   gb12345                       Traditional chinese counterpart to
  41                                 GB2312 (raw)
  42   iso-ir-165                    GB2312 + GB6345 + GB8565 + additions
  43   cp936                         Code Page 936, also known as GBK
  44                                 (Extended GuoBiao)
  45   hz                            7-bit escaped GB2312 encoding
  46   --------------------------------------------------------------------
  47
  48 To find how to use this module in detail, see L<Encode>.
  49
  50 =head1 NOTES
  51
  52 Due to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
  53 separately on CPAN, under the name L<Encode::HanExtra>. That module
  54 also contains extra Taiwan-based encodings.
  55
  56 =head1 BUGS
  57
  58 ASCII part (0x00-0x7f) is preserved for all encodings, even though it
  59 conflicts with mappings by the Unicode Consortium.  See
  60
  61 F<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
  62
  63 to find why it is implemented that way.
  64
  65 =head1 SEE ALSO
  66
  67 L<Encode>
  68
  69 =cut