[Summary view] [Print] [Text view]

   1  package Encode::TW;
   2  BEGIN {
   3      if ( ord("A") == 193 ) {
   4          die "Encode::TW 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  1;
  15  __END__
  16  
  17  =head1 NAME
  18  
  19  Encode::TW - Taiwan-based Chinese Encodings
  20  
  21  =head1 SYNOPSIS
  22  
  23      use Encode qw/encode decode/; 
  24      $big5 = encode("big5", $utf8); # loads Encode::TW implicitly
  25      $utf8 = decode("big5", $big5); # ditto
  26  
  27  =head1 DESCRIPTION
  28  
  29  This module implements tradition Chinese charset encodings as used
  30  in Taiwan and Hong Kong.
  31  Encodings supported are as follows.
  32  
  33    Canonical   Alias        Description
  34    --------------------------------------------------------------------
  35    big5-eten   /\bbig-?5$/i    Big5 encoding (with ETen extensions)
  36            /\bbig5-?et(en)?$/i
  37            /\btca-?big5$/i
  38    big5-hkscs  /\bbig5-?hk(scs)?$/i
  39                /\bhk(scs)?-?big5$/i
  40                                  Big5 + Cantonese characters in Hong Kong
  41    MacChineseTrad        Big5 + Apple Vendor Mappings
  42    cp950                        Code Page 950 
  43                                  = Big5 + Microsoft vendor mappings
  44    --------------------------------------------------------------------
  45  
  46  To find out how to use this module in detail, see L<Encode>.
  47  
  48  =head1 NOTES
  49  
  50  Due to size concerns, C<EUC-TW> (Extended Unix Character), C<CCCII>
  51  (Chinese Character Code for Information Interchange), C<BIG5PLUS>
  52  (CMEX's Big5+) and C<BIG5EXT> (CMEX's Big5e) are distributed separately
  53  on CPAN, under the name L<Encode::HanExtra>. That module also contains
  54  extra China-based encodings.
  55  
  56  =head1 BUGS
  57  
  58  Since the original C<big5> encoding (1984) is not supported anywhere
  59  (glibc and DOS-based systems uses C<big5> to mean C<big5-eten>; Microsoft
  60  uses C<big5> to mean C<cp950>), a conscious decision was made to alias
  61  C<big5> to C<big5-eten>, which is the de facto superset of the original
  62  big5.
  63  
  64  The C<CNS11643> encoding files are not complete. For common C<CNS11643>
  65  manipulation, please use C<EUC-TW> in L<Encode::HanExtra>, which contains
  66  planes 1-7.
  67  
  68  The ASCII region (0x00-0x7f) is preserved for all encodings, even
  69  though this conflicts with mappings by the Unicode Consortium.  See
  70  
  71  L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
  72  
  73  to find out why it is implemented that way.
  74  
  75  =head1 SEE ALSO
  76  
  77  L<Encode>
  78  
  79  =cut