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: 1.21 $ =~ /\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
  16 use Encode::CN::HZ;
  17 # use Encode::CN::2022_CN;
  18
  19 1;
  20 __END__
  21
  22 =head1 NAME
  23
  24 Encode::CN - China-based Chinese Encodings
  25
  26 =head1 SYNOPSIS
  27
  28     use Encode qw/encode decode/;
  29     $euc_cn = encode("euc-cn", $utf8);   # loads Encode::CN implicitly
  30     $utf8   = decode("euc-cn", $euc_cn); # ditto
  31
  32 =head1 DESCRIPTION
  33
  34 This module implements China-based Chinese charset encodings.
  35 Encodings supported are as follows.
  36
  37   Canonical   Alias             Description
  38   --------------------------------------------------------------------
  39   euc-cn      /\beuc.*cn$/i     EUC (Extended Unix Character)
  40               /\bcn.*euc$/i
  41               /\bGB[-_ ]?2312(?:\D.*$|$)/i (see below)
  42   gb2312-raw                    The raw (low-bit) GB2312 character map
  43   gb12345-raw                   Traditional chinese counterpart to
  44                                 GB2312 (raw)
  45   iso-ir-165                    GB2312 + GB6345 + GB8565 + additions
  46   MacChineseSimp                GB2312 + Apple Additions
  47   cp936                         Code Page 936, also known as GBK
  48                                 (Extended GuoBiao)
  49   hz                            7-bit escaped GB2312 encoding
  50   --------------------------------------------------------------------
  51
  52 To find how to use this module in detail, see L<Encode>.
  53
  54 =head1 NOTES
  55
  56 Due to size concerns, C<GB 18030> (an extension to C<GBK>) is distributed
  57 separately on CPAN, under the name L<Encode::HanExtra>. That module
  58 also contains extra Taiwan-based encodings.
  59
  60 =head1 BUGS
  61
  62 When you see C<charset=gb2312> on mails and web pages, they really
  63 mean "euc-cn" encodings.  To fix that, gb2312 is aliased to euc-cn.  Use
  64 gb2312-raw when you really mean it.
  65
  66 ASCII part (0x00-0x7f) is preserved for all encodings, even though it
  67 conflicts with mappings by the Unicode Consortium.  See
  68
  69 L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
  70
  71 to find why it is implemented that way.
  72
  73 =head1 SEE ALSO
  74
  75 L<Encode>,L<Encode::CJKguide>
  76
  77 =cut