Encode/ISO2022/EightBit.pm

=head1 NAME

Encode::ISO2022::Eight --- Encode and decode of 8-bit ISO/IEC 2022
based encodings (most of them are also known as EUCs)

=head1 ENCODINGS

=over 4

=cut

require 5.7.3;
use strict;
package Encode::ISO2022::EightBit;
use vars qw($VERSION);
$VERSION=do{my @r=(q$Revision: 1.5 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r};
use base qw(Encode::Encoding);
require Encode::ISO2022;

sub encode ($$;$) {
  my ($obj, $str, $chk) = @_;
  $_[1] = '' if $chk;
  if (!defined $obj->{_encode_mapping} || $obj->{_encode_mapping}) {
    require Encode::Table;
    $str = Encode::Table::convert ($str, $obj->__encode_map,
      -autoload => defined $obj->{_encode_mapping_autoload} ?
                   $obj->{_encode_mapping_autoload} : 1);
  }
  $str = &Encode::ISO2022::internal_to_iso2022 ($str, $obj->__2022_encode);
  $str;
}

sub decode ($$;$) {
  my ($obj, $str, $chk) = @_;
  $_[1] = '' if $chk;
  $str = &Encode::ISO2022::iso2022_to_internal ($str, $obj->__2022_decode);
  if (!defined $obj->{_decode_mapping} || $obj->{_decode_mapping}) {
    require Encode::Table;
    $str = Encode::Table::convert ($str, $obj->__decode_map,
      -autoload => defined $obj->{_decode_mapping_autoload} ?
                   $obj->{_decode_mapping_autoload} : 1);
  }
  $str;
}

## prototype for EUCs

sub __2022__common ($) {
  my $C = Encode::ISO2022->new_object;
  $C->{bit} = 8;
  $C->{option}->{designate_to}->{C0}->{default} = -1;
  $C->{option}->{designate_to}->{C0}->{"\x40"} = 0;
  $C->{option}->{designate_to}->{C1}->{default} = -1;
  $C->{option}->{designate_to}->{G94}->{default} = -1;
  $C->{option}->{designate_to}->{G94n}->{default} = -1;
  $C->{option}->{designate_to}->{G96}->{default} = -1;
  $C->{option}->{designate_to}->{G96n}->{default} = -1;
  $C->{option}->{Ginvoke_to_left} = [1,0,0,0];
  $C->{option}->{Ginvoke_by_single_shift} = [0,0,1,1];
  $C->{option}->{C1invoke_to_right} = 1;
  $C->{option}->{reset}->{Gdesignation} = 0;
  $C->{option}->{reset}->{Ginvoke} = 0;
  $C;
}
sub __2022_encode ($) {
  my $C = shift->__2022__common;
  $C;
}
sub __2022_decode ($) {
  my $C = shift->__2022__common;
  $C;
}
sub __encode_map ($) {
  [];
}
sub __decode_map ($) {
  [];
}

sub __clone ($) {
  my $self = shift;
  bless {%$self}, ref $self;
};

package Encode::ISO2022::EightBit::EUCJapanOldDefinition;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/ujis x-ujis euc-jp-1983 euc-japan-1983   deckanji/);

=item ujis

EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
with JIS X 0208 (JIS C 6226)-1983
(obsoleted definition of pre-1990 days).  (Alias: x-ujis,
euc-japan-1983, euc-jp-1983)

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{B};      ## JIS X 0208-1983
  $C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I};       ## JIS X 0201 Katakana
  $C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{' @'};   ## Gaiji (undefined)
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_jisx0208_1983 ucs_to_jisx0201_katakana/];
}
sub __decode_map ($) {
  [qw/jisx0208_1983_to_ucs jisx0201_katakana_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCJapan;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-japan euc-japan-1990 euc-japan-1997 euc-jp euc-jp-1990
  euc-jp-1997 euc-j eucjp euc_jp x-euc-jp
  x-eucjp eucjis euc-jis eucj Extended_UNIX_Code_Packed_Format_for_Japanese
  csEUCPkdFmtJapanese eujis
  japanese-iso-8bit cp51932 japanese_euc
      ajec eucjp-open  ibm-eucjp cp33722 33722  sdeckanji/);

=item euc-japan

EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
with JIS X 0208-1990.
(Alias: euc-japan-1990 (emacsen), euc-japan-1997, euc-jp (IANA), euc-jp-1990,
euc-jp-1997, eujis (locale),
euc-j, eucjp (locale), euc_jp, eucj, x-eucjp, x-euc-jp, eucjis, euc-jis,
extended_unix_code_packed_format_for_japanese (IANA),
cseucpkdfmtjapanese (IANA), japanese-iso-8bit (emacsen),
cp51932 (M$), japanese_euc)

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{'B@'};   ## JIS X 0208-1990
  $C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I};       ## JIS X 0201 Katakana
  $C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{D};      ## JIS X 0212-1990
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_jisx0208_1990 ucs_to_jisx0212_1990 ucs_to_jisx0201_katakana/];
}
sub __decode_map ($) {
  [qw/jisx0208_1990_to_ucs jisx0212_1990_to_ucs jisx0201_katakana_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCJapan1978;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-japan-1978 euc-jp-1978/);

=item euc-japan-1978

EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
with JIS X 0208 (JIS C 6226)-1978.  (Alias: euc-jp-1978)

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{'@'};    ## JIS X 0208-1978
  $C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I};       ## JIS X 0201 Katakana
  $C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{D};      ## JIS X 0212-1990
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_jisx0208_1978 ucs_to_jisx0212_1990 ucs_to_jisx0201_katakana/];
}
sub __decode_map ($) {
  [qw/jisx0208_1978_to_ucs jisx0212_1990_to_ucs jisx0201_katakana_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCJISX0213;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-jisx0213 x-euc-jisx0213 euc_jisx0213 eucjp0213
 euc-jp-3 euc-japan-2000 euc-jp-2000     x-euc-jisx0213-packed  deckanji2000/);

=item euc-jisx0213

EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
with JIS X 0213:2000, defined by JIS X 0213:2000.
(Alias: x-euc-jisx0213, euc_jisx0213, eucjp0213, euc-jp-3,
euc-japan-2000, euc-jp-2000)

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{O};      ## JIS X 0213:2000 plane 1
  $C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I};       ## JIS X 0201 Katakana
  $C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{P};      ## JIS X 0213:2000 plane 2
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_jisx0213_2000_1 ucs_to_jisx0213_2000_2 ucs_to_jisx0201_katakana/];
}
sub __decode_map ($) {
  [qw/jisx0213_2000_1_to_ucs jisx0212_0213_to_ucs jisx0201_katakana_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCJISX0213Plane1;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-jisx0213-plane1/);

=item euc-jisx0213-plane1

EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
with JIS X 0213:2000 plane 1, defined by JIS X 0213:2000

=cut

sub __2022__encode ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{"\x7E"}; ## empty
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_jisx0213_2000_1 ucs_to_jisx0201_katakana/];
}
sub __decode_map ($) {
  [qw/jisx0213_2000_1_to_ucs jisx0212_0213_to_ucs jisx0201_katakana_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCCHINA;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-china euc-cn euccn euc-gb
 cn-gb cn-gb-2312 chinese-iso-8bit ugb
 gb2312 csgb2312 x-euc-cn cp51936   ibm-euccn CP1383 1383/);

=item euc-china

EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese.
(Alias: euc-cn (emacsen), euccn, euc-gb, cn-gb (RFC 1922), cn-gb-2312 (RFC 1922),
chinese-iso-8bit (emacsen), ugb (locale), gb2312 (IANA), csgb2312 (IANA),
x-euc-cn, CP51936 (M$))

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{A};      ## GB 2312
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_gb2312_1980/];
}
sub __decode_map ($) {
  [qw/gb2312_1980_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCCHINA165;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/cn-gb-isoir165 iso-ir-165/);

=item cn-gb-isoir165

EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
with ISO-IR 165. (Alias: cn-gb-isoir165 (RFC 1922),
ISO-IR-165)

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{"\x45"}; ## ISO-IR 165
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_iso_ir_165/];
}
sub __decode_map ($) {
  [qw/iso_ir_165_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCcwnn;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-cwnn cwnn-iso-8bit/);

=item euc-cwnn

EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
with GB 2312, used by cwnn input system (Alias: cwnn-iso-8bit).
See <http://www.tomo.gr.jp/users/wnn/9912ml/msg00088.html>.

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{A};      ## GB 2312
  $C->{G2} = $Encode::ISO2022::CHARSET{G94}->{'0'};     # omron_udc_zh (sisheng)
        ## TODO: Implement by private set support
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_gb2312_1980 ucs_to_omron_udc_zh/];
}
sub __decode_map ($) {
  [qw/gb2312_1980_to_ucs omron_udc_zh_to_ucs/];
}

## cn-gb-12345, gb12345, euc-gb12345

package Encode::ISO2022::EightBit::EUCKorea;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-korea euc-kr euckr cp970 cp51949 ibm-euckr x-euc-kr
 cseuckr korean-iso-8bit/);

=item euc-korea

EUC (ISO/IEC 2022 based 8-bit encoding) for Korean
(Alias: euc-kr (IANA), euckr, cp970, cp51949 (M$), ibm-euckr,
x-euc-kr, cseuckr (IANA), korean-iso-8bit (emacsen))

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{C};      ## KS X 1001
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ksx1001_1992_katakana/];
}
sub __decode_map ($) {
  [qw/ksx1001_1992_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCTaiwan;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-taiwan euc-tw euctw x-euc-tw cns11643 cseuctw
    ibm-euctw cp964/);

=item euc-taiwan

EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
with CNS 11643.  (Alias: euc-tw, euctw, x-euc-tw, cseuctw, cns11643)

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{G};      ## plane 1
  #$C->{G2} =   ## BUG: does not support plane 2-16 yet
  $C->{G2} = $Encode::ISO2022::CHARSET{G94n}->{' `'};   # 3byte DRCS (temporary)
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_cns11643_1 ucs_to_cns11643_2 ucs_to_cns11643_3 ucs_to_cns11643_4 ucs_to_cns11643_5 ucs_to_cns11643_6 ucs_to_cns11643_7 ucs_to_cns11643_8 ucs_to_cns11643_9 ucs_to_cns11643_10 ucs_to_cns11643_11 ucs_to_cns11643_12 ucs_to_cns11643_13 ucs_to_cns11643_14 ucs_to_cns11643_15 ucs_to_cns11643_16/];
}
sub __decode_map ($) {
  [qw/cns11643_1_to_ucs cns11643_2_to_ucs cns11643_3_to_ucs cns11643_4_to_ucs cns11643_5_to_ucs cns11643_6_to_ucs cns11643_7_to_ucs cns11643_8_to_ucs cns11643_9_to_ucs cns11643_10_to_ucs cns11643_11_to_ucs cns11643_12_to_ucs cns11643_13_to_ucs cns11643_14_to_ucs cns11643_15_to_ucs cns11643_16_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCtwnn;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-twnn twnn-iso-8bit/);

=item euc-twnn

EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
with CNS 11643, used by twnn input system (Alias: twnn-iso-8bit)
See <http://www.tomo.gr.jp/users/wnn/9912ml/msg00088.html>.

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{G};      ## plane 1
  $C->{G2} = $Encode::ISO2022::CHARSET{G94}->{'0'};     # omron_udc_zh (sisheng)
        ## TODO: Implement by private set support
  $C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{H};      ## plane 2
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_cns11643_1 ucs_to_cns11643_2 ucs_to_omron_udc_zh/];
}
sub __decode_map ($) {
  [qw/cns11643_1_to_ucs cns11643_2_to_ucs omron_udc_zh_to_ucs/];
}

package Encode::ISO2022::EightBit::EUCKPS9566;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/euc-kps9566/);

=item euc-kps9566

EUC (ISO/IEC 2022 based 8-bit encoding) for Korean
with KPS 9566-97

=cut

sub __2022__common ($) {
  my $C = shift->SUPER::__2022__common;
  $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{N};      ## KPS 9566-97
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_kps9566_1997/];
}
sub __decode_map ($) {
  [qw/kps9566_1997_to_ucs/];
}

package Encode::ISO2022::EightBit::SS2;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/iso-2022-8bit-ss2/);

=item iso-2022-8bit-ss2

ISO/IEC 2022 based 8-bit encoding using SS2 for 96-charset

=cut

sub __2022__common ($) {
  my $C = Encode::ISO2022->new_object;
  $C->{option}->{designate_to}->{G96}->{default} = 2;
  $C->{option}->{designate_to}->{G96n}->{default} = 2;
  $C->{option}->{G94n_designate_long} = 1;
  $C->{option}->{Ginvoke_by_single_shift}->[2] = 1;
  $C->{option}->{Ginvoke_to_left}->[2] = 0;
  $C->{option}->{C1invoke_to_right} = 1;
  $C;
}

package Encode::ISO2022::EightBit::CompoundText;
use vars qw/@ISA/;
push @ISA, 'Encode::ISO2022::EightBit';
__PACKAGE__->Define (qw/compound-text compound_text 
 x-compound-text ctext x-ctext ct/);

=item compound-text

ISO/IEC 2022 based 8-bit encoding used in inter-client
communication of X Window System (Alias: ctext (emacsen), x-ctext (emacsen),
compound_text, x-compound-text, ct (loacle))

Strictly, x-ctext, extended compound text (X Compound Text
based encoding for unknown ISO/IEC 2022 based encoding) is a
different coding system from X Compound Text.  See
[mule-jp:7455] <mid:rsqsoa5s2hr.fsf@crane.jaist.ac.jp> and
[mule-jp:7457] <mid:rsq4smlky85.fsf@crane.jaist.ac.jp>.
Mule's ctext allows private final bytes and 96^n sets.

XFree86 extended compound text allows to use UTF-8
with ESC 02/05 04/06.  See
<http://cvsweb.xfree86.org/cvsweb/xc/doc/specs/CTEXT/ctext.tbl.ms>.

=cut

## TODO: separate mule ctext and xfree86 ctext

sub __2022__common ($) {
  my $C = Encode::ISO2022->new_object;
  $C->{option}->{designate_to}->{C0}->{default} = -1;
  $C->{option}->{designate_to}->{C1}->{default} = -1;
  $C->{option}->{designate_to}->{G94}->{I} = 1; ## JIS X 0201 Katakana
  $C->{option}->{designate_to}->{G96}->{default} = 1;
  $C->{option}->{designate_to}->{G96n}->{default} = -1;
  for my $t (qw/G94 G96 G94n/) {
    for (0x30..0x3F) {
      my $F = chr $_;
      #$C->{option}->{designate_to}->{$t}->{$F} = -1;
      $C->{option}->{designate_to}->{$t}->{'!'.$F} = -1;
      $C->{option}->{designate_to}->{$t}->{'"'.$F} = -1;
      $C->{option}->{designate_to}->{$t}->{'#'.$F} = -1;
      $C->{option}->{designate_to}->{$t}->{' '.$F} = -1;
    }
    for (0x40..0x7E) {
      $C->{option}->{designate_to}->{$t}->{' '.chr $_} = -1;
    }
  }
  $C->{option}->{G94n_designate_long} = 1;
  $C->{option}->{Ginvoke_to_left}->[1] = 0;
  $C->{option}->{C1invoke_to_right} = 1;
  $C->{option}->{reset}->{Ginvoke} = 0;
  $C->{option}->{use_revision} = 0;
  ## XFree86 extension
  $C->{option}->{designate_to}->{G94n}->{"\x42\x40"} = 0;       ## JIS X 0208-1990
  $C->{option}->{designate_to}->{coding_system}->{"\x40"} = 1;  ## ISO/IEC 2022
  $C->{option}->{designate_to}->{coding_system}->{"\x47"} = 1;  ## UTF-8
  $C;
}
sub __2022_decode ($) {
  my $C = shift->__2022__common;
  ## Emacsen's x-ctext
  $C->{G1} = $Encode::ISO2022::CHARSET{G96}->{A};       ## ISO/IEC 8859-1
  $C;
}
sub __encode_map ($) {
  [qw/ucs_to_ascii ucs_to_isoiec8859_1 ucs_to_isoiec8859_2 ucs_to_isoiec8859_3 ucs_to_isoiec8859_4 ucs_to_isoiec8859_5 ucs_to_isoiec8859_6 ucs_to_isoiec8859_7 ucs_to_isoiec8859_8 ucs_to_isoiec8859_9 ucs_to_gb2312_1980 ucs_to_jisx0208_1983 ucs_to_ksx1001_1992 ucs_to_jisx0212_1990 ucs_to_jisx0201_latin ucs_to_jisx0201_katakana/];
}
sub __decode_map ($) {
  [qw/isoiec8859_2_to_ucs isoiec8859_3_to_ucs isoiec8859_4_to_ucs isoiec8859_5_to_ucs isoiec8859_6_to_ucs isoiec8859_7_to_ucs isoiec8859_8_to_ucs isoiec8859_9_to_ucs gb2312_1980_to_ucs jisx0208_1983_to_ucs ksx1001_1992_to_ucs jisx0212_1990_to_ucs/];
}


1;
__END__

=back

=head1 LICENSE

Copyright 2002 Wakaba <w@suika.fam.cx>

This library is free software; you can redistribute it
and/or modify it under the same terms as Perl itself.

=cut

# $Date: 2002/10/12 07:27:01 $
### SevenBit.pm ends here
1	=head1 NAME
2
3	Encode::ISO2022::Eight --- Encode and decode of 8-bit ISO/IEC 2022
4	based encodings (most of them are also known as EUCs)
5
6	=head1 ENCODINGS
7
8	=over 4
9
10	=cut
11
12	require 5.7.3;
13	use strict;
14	package Encode::ISO2022::EightBit;
15	use vars qw($VERSION);
16	$VERSION=do{my @r=(q$Revision: 1.5 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r};
17	use base qw(Encode::Encoding);
18	require Encode::ISO2022;
19
20	sub encode ($$;$) {
21	my ($obj, $str, $chk) = @_;
22	$_[1] = '' if $chk;
23	if (!defined $obj->{_encode_mapping} \|\| $obj->{_encode_mapping}) {
24	require Encode::Table;
25	$str = Encode::Table::convert ($str, $obj->__encode_map,
26	-autoload => defined $obj->{_encode_mapping_autoload} ?
27	$obj->{_encode_mapping_autoload} : 1);
28	}
29	$str = &Encode::ISO2022::internal_to_iso2022 ($str, $obj->__2022_encode);
30	$str;
31	}
32
33	sub decode ($$;$) {
34	my ($obj, $str, $chk) = @_;
35	$_[1] = '' if $chk;
36	$str = &Encode::ISO2022::iso2022_to_internal ($str, $obj->__2022_decode);
37	if (!defined $obj->{_decode_mapping} \|\| $obj->{_decode_mapping}) {
38	require Encode::Table;
39	$str = Encode::Table::convert ($str, $obj->__decode_map,
40	-autoload => defined $obj->{_decode_mapping_autoload} ?
41	$obj->{_decode_mapping_autoload} : 1);
42	}
43	$str;
44	}
45
46	## prototype for EUCs
47
48	sub __2022__common ($) {
49	my $C = Encode::ISO2022->new_object;
50	$C->{bit} = 8;
51	$C->{option}->{designate_to}->{C0}->{default} = -1;
52	$C->{option}->{designate_to}->{C0}->{"\x40"} = 0;
53	$C->{option}->{designate_to}->{C1}->{default} = -1;
54	$C->{option}->{designate_to}->{G94}->{default} = -1;
55	$C->{option}->{designate_to}->{G94n}->{default} = -1;
56	$C->{option}->{designate_to}->{G96}->{default} = -1;
57	$C->{option}->{designate_to}->{G96n}->{default} = -1;
58	$C->{option}->{Ginvoke_to_left} = [1,0,0,0];
59	$C->{option}->{Ginvoke_by_single_shift} = [0,0,1,1];
60	$C->{option}->{C1invoke_to_right} = 1;
61	$C->{option}->{reset}->{Gdesignation} = 0;
62	$C->{option}->{reset}->{Ginvoke} = 0;
63	$C;
64	}
65	sub __2022_encode ($) {
66	my $C = shift->__2022__common;
67	$C;
68	}
69	sub __2022_decode ($) {
70	my $C = shift->__2022__common;
71	$C;
72	}
73	sub __encode_map ($) {
74	[];
75	}
76	sub __decode_map ($) {
77	[];
78	}
79
80	sub __clone ($) {
81	my $self = shift;
82	bless {%$self}, ref $self;
83	};
84
85	package Encode::ISO2022::EightBit::EUCJapanOldDefinition;
86	use vars qw/@ISA/;
87	push @ISA, 'Encode::ISO2022::EightBit';
88	__PACKAGE__->Define (qw/ujis x-ujis euc-jp-1983 euc-japan-1983 deckanji/);
89
90	=item ujis
91
92	EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
93	with JIS X 0208 (JIS C 6226)-1983
94	(obsoleted definition of pre-1990 days). (Alias: x-ujis,
95	euc-japan-1983, euc-jp-1983)
96
97	=cut
98
99	sub __2022__common ($) {
100	my $C = shift->SUPER::__2022__common;
101	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{B}; ## JIS X 0208-1983
102	$C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I}; ## JIS X 0201 Katakana
103	$C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{' @'}; ## Gaiji (undefined)
104	$C;
105	}
106	sub __encode_map ($) {
107	[qw/ucs_to_ascii ucs_to_jisx0208_1983 ucs_to_jisx0201_katakana/];
108	}
109	sub __decode_map ($) {
110	[qw/jisx0208_1983_to_ucs jisx0201_katakana_to_ucs/];
111	}
112
113	package Encode::ISO2022::EightBit::EUCJapan;
114	use vars qw/@ISA/;
115	push @ISA, 'Encode::ISO2022::EightBit';
116	__PACKAGE__->Define (qw/euc-japan euc-japan-1990 euc-japan-1997 euc-jp euc-jp-1990
117	euc-jp-1997 euc-j eucjp euc_jp x-euc-jp
118	x-eucjp eucjis euc-jis eucj Extended_UNIX_Code_Packed_Format_for_Japanese
119	csEUCPkdFmtJapanese eujis
120	japanese-iso-8bit cp51932 japanese_euc
121	ajec eucjp-open ibm-eucjp cp33722 33722 sdeckanji/);
122
123	=item euc-japan
124
125	EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
126	with JIS X 0208-1990.
127	(Alias: euc-japan-1990 (emacsen), euc-japan-1997, euc-jp (IANA), euc-jp-1990,
128	euc-jp-1997, eujis (locale),
129	euc-j, eucjp (locale), euc_jp, eucj, x-eucjp, x-euc-jp, eucjis, euc-jis,
130	extended_unix_code_packed_format_for_japanese (IANA),
131	cseucpkdfmtjapanese (IANA), japanese-iso-8bit (emacsen),
132	cp51932 (M$), japanese_euc)
133
134	=cut
135
136	sub __2022__common ($) {
137	my $C = shift->SUPER::__2022__common;
138	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{'B@'}; ## JIS X 0208-1990
139	$C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I}; ## JIS X 0201 Katakana
140	$C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{D}; ## JIS X 0212-1990
141	$C;
142	}
143	sub __encode_map ($) {
144	[qw/ucs_to_ascii ucs_to_jisx0208_1990 ucs_to_jisx0212_1990 ucs_to_jisx0201_katakana/];
145	}
146	sub __decode_map ($) {
147	[qw/jisx0208_1990_to_ucs jisx0212_1990_to_ucs jisx0201_katakana_to_ucs/];
148	}
149
150	package Encode::ISO2022::EightBit::EUCJapan1978;
151	use vars qw/@ISA/;
152	push @ISA, 'Encode::ISO2022::EightBit';
153	__PACKAGE__->Define (qw/euc-japan-1978 euc-jp-1978/);
154
155	=item euc-japan-1978
156
157	EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
158	with JIS X 0208 (JIS C 6226)-1978. (Alias: euc-jp-1978)
159
160	=cut
161
162	sub __2022__common ($) {
163	my $C = shift->SUPER::__2022__common;
164	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{'@'}; ## JIS X 0208-1978
165	$C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I}; ## JIS X 0201 Katakana
166	$C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{D}; ## JIS X 0212-1990
167	$C;
168	}
169	sub __encode_map ($) {
170	[qw/ucs_to_ascii ucs_to_jisx0208_1978 ucs_to_jisx0212_1990 ucs_to_jisx0201_katakana/];
171	}
172	sub __decode_map ($) {
173	[qw/jisx0208_1978_to_ucs jisx0212_1990_to_ucs jisx0201_katakana_to_ucs/];
174	}
175
176	package Encode::ISO2022::EightBit::EUCJISX0213;
177	use vars qw/@ISA/;
178	push @ISA, 'Encode::ISO2022::EightBit';
179	__PACKAGE__->Define (qw/euc-jisx0213 x-euc-jisx0213 euc_jisx0213 eucjp0213
180	euc-jp-3 euc-japan-2000 euc-jp-2000 x-euc-jisx0213-packed deckanji2000/);
181
182	=item euc-jisx0213
183
184	EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
185	with JIS X 0213:2000, defined by JIS X 0213:2000.
186	(Alias: x-euc-jisx0213, euc_jisx0213, eucjp0213, euc-jp-3,
187	euc-japan-2000, euc-jp-2000)
188
189	=cut
190
191	sub __2022__common ($) {
192	my $C = shift->SUPER::__2022__common;
193	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{O}; ## JIS X 0213:2000 plane 1
194	$C->{G2} = $Encode::ISO2022::CHARSET{G94}->{I}; ## JIS X 0201 Katakana
195	$C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{P}; ## JIS X 0213:2000 plane 2
196	$C;
197	}
198	sub __encode_map ($) {
199	[qw/ucs_to_ascii ucs_to_jisx0213_2000_1 ucs_to_jisx0213_2000_2 ucs_to_jisx0201_katakana/];
200	}
201	sub __decode_map ($) {
202	[qw/jisx0213_2000_1_to_ucs jisx0212_0213_to_ucs jisx0201_katakana_to_ucs/];
203	}
204
205	package Encode::ISO2022::EightBit::EUCJISX0213Plane1;
206	use vars qw/@ISA/;
207	push @ISA, 'Encode::ISO2022::EightBit';
208	__PACKAGE__->Define (qw/euc-jisx0213-plane1/);
209
210	=item euc-jisx0213-plane1
211
212	EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese
213	with JIS X 0213:2000 plane 1, defined by JIS X 0213:2000
214
215	=cut
216
217	sub __2022__encode ($) {
218	my $C = shift->SUPER::__2022__common;
219	$C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{"\x7E"}; ## empty
220	$C;
221	}
222	sub __encode_map ($) {
223	[qw/ucs_to_ascii ucs_to_jisx0213_2000_1 ucs_to_jisx0201_katakana/];
224	}
225	sub __decode_map ($) {
226	[qw/jisx0213_2000_1_to_ucs jisx0212_0213_to_ucs jisx0201_katakana_to_ucs/];
227	}
228
229	package Encode::ISO2022::EightBit::EUCCHINA;
230	use vars qw/@ISA/;
231	push @ISA, 'Encode::ISO2022::EightBit';
232	__PACKAGE__->Define (qw/euc-china euc-cn euccn euc-gb
233	cn-gb cn-gb-2312 chinese-iso-8bit ugb
234	gb2312 csgb2312 x-euc-cn cp51936 ibm-euccn CP1383 1383/);
235
236	=item euc-china
237
238	EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese.
239	(Alias: euc-cn (emacsen), euccn, euc-gb, cn-gb (RFC 1922), cn-gb-2312 (RFC 1922),
240	chinese-iso-8bit (emacsen), ugb (locale), gb2312 (IANA), csgb2312 (IANA),
241	x-euc-cn, CP51936 (M$))
242
243	=cut
244
245	sub __2022__common ($) {
246	my $C = shift->SUPER::__2022__common;
247	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{A}; ## GB 2312
248	$C;
249	}
250	sub __encode_map ($) {
251	[qw/ucs_to_ascii ucs_to_gb2312_1980/];
252	}
253	sub __decode_map ($) {
254	[qw/gb2312_1980_to_ucs/];
255	}
256
257	package Encode::ISO2022::EightBit::EUCCHINA165;
258	use vars qw/@ISA/;
259	push @ISA, 'Encode::ISO2022::EightBit';
260	__PACKAGE__->Define (qw/cn-gb-isoir165 iso-ir-165/);
261
262	=item cn-gb-isoir165
263
264	EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
265	with ISO-IR 165. (Alias: cn-gb-isoir165 (RFC 1922),
266	ISO-IR-165)
267
268	=cut
269
270	sub __2022__common ($) {
271	my $C = shift->SUPER::__2022__common;
272	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{"\x45"}; ## ISO-IR 165
273	$C;
274	}
275	sub __encode_map ($) {
276	[qw/ucs_to_ascii ucs_to_iso_ir_165/];
277	}
278	sub __decode_map ($) {
279	[qw/iso_ir_165_to_ucs/];
280	}
281
282	package Encode::ISO2022::EightBit::EUCcwnn;
283	use vars qw/@ISA/;
284	push @ISA, 'Encode::ISO2022::EightBit';
285	__PACKAGE__->Define (qw/euc-cwnn cwnn-iso-8bit/);
286
287	=item euc-cwnn
288
289	EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
290	with GB 2312, used by cwnn input system (Alias: cwnn-iso-8bit).
291	See <http://www.tomo.gr.jp/users/wnn/9912ml/msg00088.html>.
292
293	=cut
294
295	sub __2022__common ($) {
296	my $C = shift->SUPER::__2022__common;
297	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{A}; ## GB 2312
298	$C->{G2} = $Encode::ISO2022::CHARSET{G94}->{'0'}; # omron_udc_zh (sisheng)
299	## TODO: Implement by private set support
300	$C;
301	}
302	sub __encode_map ($) {
303	[qw/ucs_to_ascii ucs_to_gb2312_1980 ucs_to_omron_udc_zh/];
304	}
305	sub __decode_map ($) {
306	[qw/gb2312_1980_to_ucs omron_udc_zh_to_ucs/];
307	}
308
309	## cn-gb-12345, gb12345, euc-gb12345
310
311	package Encode::ISO2022::EightBit::EUCKorea;
312	use vars qw/@ISA/;
313	push @ISA, 'Encode::ISO2022::EightBit';
314	__PACKAGE__->Define (qw/euc-korea euc-kr euckr cp970 cp51949 ibm-euckr x-euc-kr
315	cseuckr korean-iso-8bit/);
316
317	=item euc-korea
318
319	EUC (ISO/IEC 2022 based 8-bit encoding) for Korean
320	(Alias: euc-kr (IANA), euckr, cp970, cp51949 (M$), ibm-euckr,
321	x-euc-kr, cseuckr (IANA), korean-iso-8bit (emacsen))
322
323	=cut
324
325	sub __2022__common ($) {
326	my $C = shift->SUPER::__2022__common;
327	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{C}; ## KS X 1001
328	$C;
329	}
330	sub __encode_map ($) {
331	[qw/ucs_to_ascii ksx1001_1992_katakana/];
332	}
333	sub __decode_map ($) {
334	[qw/ksx1001_1992_to_ucs/];
335	}
336
337	package Encode::ISO2022::EightBit::EUCTaiwan;
338	use vars qw/@ISA/;
339	push @ISA, 'Encode::ISO2022::EightBit';
340	__PACKAGE__->Define (qw/euc-taiwan euc-tw euctw x-euc-tw cns11643 cseuctw
341	ibm-euctw cp964/);
342
343	=item euc-taiwan
344
345	EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
346	with CNS 11643. (Alias: euc-tw, euctw, x-euc-tw, cseuctw, cns11643)
347
348	=cut
349
350	sub __2022__common ($) {
351	my $C = shift->SUPER::__2022__common;
352	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{G}; ## plane 1
353	#$C->{G2} = ## BUG: does not support plane 2-16 yet
354	$C->{G2} = $Encode::ISO2022::CHARSET{G94n}->{' `'}; # 3byte DRCS (temporary)
355	$C;
356	}
357	sub __encode_map ($) {
358	[qw/ucs_to_ascii ucs_to_cns11643_1 ucs_to_cns11643_2 ucs_to_cns11643_3 ucs_to_cns11643_4 ucs_to_cns11643_5 ucs_to_cns11643_6 ucs_to_cns11643_7 ucs_to_cns11643_8 ucs_to_cns11643_9 ucs_to_cns11643_10 ucs_to_cns11643_11 ucs_to_cns11643_12 ucs_to_cns11643_13 ucs_to_cns11643_14 ucs_to_cns11643_15 ucs_to_cns11643_16/];
359	}
360	sub __decode_map ($) {
361	[qw/cns11643_1_to_ucs cns11643_2_to_ucs cns11643_3_to_ucs cns11643_4_to_ucs cns11643_5_to_ucs cns11643_6_to_ucs cns11643_7_to_ucs cns11643_8_to_ucs cns11643_9_to_ucs cns11643_10_to_ucs cns11643_11_to_ucs cns11643_12_to_ucs cns11643_13_to_ucs cns11643_14_to_ucs cns11643_15_to_ucs cns11643_16_to_ucs/];
362	}
363
364	package Encode::ISO2022::EightBit::EUCtwnn;
365	use vars qw/@ISA/;
366	push @ISA, 'Encode::ISO2022::EightBit';
367	__PACKAGE__->Define (qw/euc-twnn twnn-iso-8bit/);
368
369	=item euc-twnn
370
371	EUC (ISO/IEC 2022 based 8-bit encoding) for Chinese
372	with CNS 11643, used by twnn input system (Alias: twnn-iso-8bit)
373	See <http://www.tomo.gr.jp/users/wnn/9912ml/msg00088.html>.
374
375	=cut
376
377	sub __2022__common ($) {
378	my $C = shift->SUPER::__2022__common;
379	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{G}; ## plane 1
380	$C->{G2} = $Encode::ISO2022::CHARSET{G94}->{'0'}; # omron_udc_zh (sisheng)
381	## TODO: Implement by private set support
382	$C->{G3} = $Encode::ISO2022::CHARSET{G94n}->{H}; ## plane 2
383	$C;
384	}
385	sub __encode_map ($) {
386	[qw/ucs_to_ascii ucs_to_cns11643_1 ucs_to_cns11643_2 ucs_to_omron_udc_zh/];
387	}
388	sub __decode_map ($) {
389	[qw/cns11643_1_to_ucs cns11643_2_to_ucs omron_udc_zh_to_ucs/];
390	}
391
392	package Encode::ISO2022::EightBit::EUCKPS9566;
393	use vars qw/@ISA/;
394	push @ISA, 'Encode::ISO2022::EightBit';
395	__PACKAGE__->Define (qw/euc-kps9566/);
396
397	=item euc-kps9566
398
399	EUC (ISO/IEC 2022 based 8-bit encoding) for Korean
400	with KPS 9566-97
401
402	=cut
403
404	sub __2022__common ($) {
405	my $C = shift->SUPER::__2022__common;
406	$C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{N}; ## KPS 9566-97
407	$C;
408	}
409	sub __encode_map ($) {
410	[qw/ucs_to_ascii ucs_to_kps9566_1997/];
411	}
412	sub __decode_map ($) {
413	[qw/kps9566_1997_to_ucs/];
414	}
415
416	package Encode::ISO2022::EightBit::SS2;
417	use vars qw/@ISA/;
418	push @ISA, 'Encode::ISO2022::EightBit';
419	__PACKAGE__->Define (qw/iso-2022-8bit-ss2/);
420
421	=item iso-2022-8bit-ss2
422
423	ISO/IEC 2022 based 8-bit encoding using SS2 for 96-charset
424
425	=cut
426
427	sub __2022__common ($) {
428	my $C = Encode::ISO2022->new_object;
429	$C->{option}->{designate_to}->{G96}->{default} = 2;
430	$C->{option}->{designate_to}->{G96n}->{default} = 2;
431	$C->{option}->{G94n_designate_long} = 1;
432	$C->{option}->{Ginvoke_by_single_shift}->[2] = 1;
433	$C->{option}->{Ginvoke_to_left}->[2] = 0;
434	$C->{option}->{C1invoke_to_right} = 1;
435	$C;
436	}
437
438	package Encode::ISO2022::EightBit::CompoundText;
439	use vars qw/@ISA/;
440	push @ISA, 'Encode::ISO2022::EightBit';
441	__PACKAGE__->Define (qw/compound-text compound_text
442	x-compound-text ctext x-ctext ct/);
443
444	=item compound-text
445
446	ISO/IEC 2022 based 8-bit encoding used in inter-client
447	communication of X Window System (Alias: ctext (emacsen), x-ctext (emacsen),
448	compound_text, x-compound-text, ct (loacle))
449
450	Strictly, x-ctext, extended compound text (X Compound Text
451	based encoding for unknown ISO/IEC 2022 based encoding) is a
452	different coding system from X Compound Text. See
453	[mule-jp:7455] <mid:rsqsoa5s2hr.fsf@crane.jaist.ac.jp> and
454	[mule-jp:7457] <mid:rsq4smlky85.fsf@crane.jaist.ac.jp>.
455	Mule's ctext allows private final bytes and 96^n sets.
456
457	XFree86 extended compound text allows to use UTF-8
458	with ESC 02/05 04/06. See
459	<http://cvsweb.xfree86.org/cvsweb/xc/doc/specs/CTEXT/ctext.tbl.ms>.
460
461	=cut
462
463	## TODO: separate mule ctext and xfree86 ctext
464
465	sub __2022__common ($) {
466	my $C = Encode::ISO2022->new_object;
467	$C->{option}->{designate_to}->{C0}->{default} = -1;
468	$C->{option}->{designate_to}->{C1}->{default} = -1;
469	$C->{option}->{designate_to}->{G94}->{I} = 1; ## JIS X 0201 Katakana
470	$C->{option}->{designate_to}->{G96}->{default} = 1;
471	$C->{option}->{designate_to}->{G96n}->{default} = -1;
472	for my $t (qw/G94 G96 G94n/) {
473	for (0x30..0x3F) {
474	my $F = chr $_;
475	#$C->{option}->{designate_to}->{$t}->{$F} = -1;
476	$C->{option}->{designate_to}->{$t}->{'!'.$F} = -1;
477	$C->{option}->{designate_to}->{$t}->{'"'.$F} = -1;
478	$C->{option}->{designate_to}->{$t}->{'#'.$F} = -1;
479	$C->{option}->{designate_to}->{$t}->{' '.$F} = -1;
480	}
481	for (0x40..0x7E) {
482	$C->{option}->{designate_to}->{$t}->{' '.chr $_} = -1;
483	}
484	}
485	$C->{option}->{G94n_designate_long} = 1;
486	$C->{option}->{Ginvoke_to_left}->[1] = 0;
487	$C->{option}->{C1invoke_to_right} = 1;
488	$C->{option}->{reset}->{Ginvoke} = 0;
489	$C->{option}->{use_revision} = 0;
490	## XFree86 extension
491	$C->{option}->{designate_to}->{G94n}->{"\x42\x40"} = 0; ## JIS X 0208-1990
492	$C->{option}->{designate_to}->{coding_system}->{"\x40"} = 1; ## ISO/IEC 2022
493	$C->{option}->{designate_to}->{coding_system}->{"\x47"} = 1; ## UTF-8
494	$C;
495	}
496	sub __2022_decode ($) {
497	my $C = shift->__2022__common;
498	## Emacsen's x-ctext
499	$C->{G1} = $Encode::ISO2022::CHARSET{G96}->{A}; ## ISO/IEC 8859-1
500	$C;
501	}
502	sub __encode_map ($) {
503	[qw/ucs_to_ascii ucs_to_isoiec8859_1 ucs_to_isoiec8859_2 ucs_to_isoiec8859_3 ucs_to_isoiec8859_4 ucs_to_isoiec8859_5 ucs_to_isoiec8859_6 ucs_to_isoiec8859_7 ucs_to_isoiec8859_8 ucs_to_isoiec8859_9 ucs_to_gb2312_1980 ucs_to_jisx0208_1983 ucs_to_ksx1001_1992 ucs_to_jisx0212_1990 ucs_to_jisx0201_latin ucs_to_jisx0201_katakana/];
504	}
505	sub __decode_map ($) {
506	[qw/isoiec8859_2_to_ucs isoiec8859_3_to_ucs isoiec8859_4_to_ucs isoiec8859_5_to_ucs isoiec8859_6_to_ucs isoiec8859_7_to_ucs isoiec8859_8_to_ucs isoiec8859_9_to_ucs gb2312_1980_to_ucs jisx0208_1983_to_ucs ksx1001_1992_to_ucs jisx0212_1990_to_ucs/];
507	}
508
509
510	1;
511	__END__
512
513	=back
514
515	=head1 LICENSE
516
517	Copyright 2002 Wakaba <w@suika.fam.cx>
518
519	This library is free software; you can redistribute it
520	and/or modify it under the same terms as Perl itself.
521
522	=cut
523
524	# $Date: 2002/10/12 07:27:01 $
525	### SevenBit.pm ends here