[Summary view] [Print] [Text view]

   1  package Encode::JP;
   2  BEGIN {
   3      if ( ord("A") == 193 ) {
   4          die "Encode::JP not supported on EBCDIC\n";
   5      }
   6  }
   7  use strict;
   8  use warnings;
   9  use Encode;
  10  our $VERSION = do { my @r = ( q$Revision: 2.3 $ =~ /\d+/g ); sprintf "%d." . "%02d" x $#r, @r };
  11  
  12  use XSLoader;
  13  XSLoader::load( __PACKAGE__, $VERSION );
  14  
  15  use Encode::JP::JIS7;
  16  
  17  1;
  18  __END__
  19  
  20  =head1 NAME
  21  
  22  Encode::JP - Japanese Encodings
  23  
  24  =head1 SYNOPSIS
  25  
  26      use Encode qw/encode decode/; 
  27      $euc_jp = encode("euc-jp", $utf8);   # loads Encode::JP implicitly
  28      $utf8   = decode("euc-jp", $euc_jp); # ditto
  29  
  30  =head1 ABSTRACT
  31  
  32  This module implements Japanese charset encodings.  Encodings
  33  supported are as follows.
  34  
  35    Canonical   Alias        Description
  36    --------------------------------------------------------------------
  37    euc-jp      /\beuc.*jp$/i    EUC (Extended Unix Character)
  38                /\bjp.*euc/i   
  39            /\bujis$/i
  40    shiftjis    /\bshift.*jis$/i    Shift JIS (aka MS Kanji)
  41            /\bsjis$/i
  42    7bit-jis    /\bjis$/i        7bit JIS
  43    iso-2022-jp            ISO-2022-JP                  [RFC1468]
  44                  = 7bit JIS with all Halfwidth Kana 
  45                    converted to Fullwidth
  46    iso-2022-jp-1            ISO-2022-JP-1                [RFC2237]
  47                                  = ISO-2022-JP with JIS X 0212-1990
  48                    support.  See below
  49    MacJapanese                    Shift JIS + Apple vendor mappings
  50    cp932       /\bwindows-31j$/i Code Page 932
  51                                  = Shift JIS + MS/IBM vendor mappings
  52    jis0201-raw                   JIS0201, raw format
  53    jis0208-raw                   JIS0201, raw format
  54    jis0212-raw                   JIS0201, raw format
  55    --------------------------------------------------------------------
  56  
  57  =head1 DESCRIPTION
  58  
  59  To find out how to use this module in detail, see L<Encode>.
  60  
  61  =head1 Note on ISO-2022-JP(-1)?
  62  
  63  ISO-2022-JP-1 (RFC2237) is a superset of ISO-2022-JP (RFC1468) which
  64  adds support for JIS X 0212-1990.  That means you can use the same
  65  code to decode to utf8 but not vice versa.
  66  
  67    $utf8 = decode('iso-2022-jp-1', $stream);
  68  
  69  and
  70  
  71    $utf8 = decode('iso-2022-jp',   $stream);
  72  
  73  yield the same result but
  74  
  75    $with_0212 = encode('iso-2022-jp-1', $utf8);
  76  
  77  is now different from
  78  
  79    $without_0212 = encode('iso-2022-jp', $utf8 );
  80  
  81  In the latter case, characters that map to 0212 are first converted
  82  to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu' or
  83  'geta mark') then fed to the decoding engine.  U+FFFD is not used,
  84  in order to preserve text layout as much as possible.
  85  
  86  =head1 BUGS
  87  
  88  The ASCII region (0x00-0x7f) is preserved for all encodings, even
  89  though this conflicts with mappings by the Unicode Consortium.  See
  90  
  91  L<http://www.debian.or.jp/~kubota/unicode-symbols.html.en>
  92  
  93  to find out why it is implemented that way.
  94  
  95  =head1 SEE ALSO
  96  
  97  L<Encode>
  98  
  99  =cut