Parent Directory
|
Revision Log
2002-11-08 Wakaba <w@suika.fam.cx> * JIS.esr: New files. * JIS.pm: Removed. * Makefile: Updated.
| 1 | wakaba | 1.1 | =head1 NAME |
| 2 | |||
| 3 | C<Encode::ISO2022::JIS> --- Encode and decode of ISO/IEC 2022 | ||
| 4 | based encodings defined by JIS (Japan Industrial Standard), | ||
| 5 | other than RFC 1468 coded representation, C<ISO-2022-JP-3> | ||
| 6 | coded representations and C<EUC-JISX0213> coded representations | ||
| 7 | |||
| 8 | =head1 ENCODINGS | ||
| 9 | |||
| 10 | =over 4 | ||
| 11 | |||
| 12 | =cut | ||
| 13 | |||
| 14 | require 5.7.3; | ||
| 15 | use strict; | ||
| 16 | package Encode::ISO2022::JIS; | ||
| 17 | use vars qw($VERSION); | ||
| 18 | wakaba | 1.7 | $VERSION=do{my @r=(q$Revision: 1.6 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 19 | wakaba | 1.1 | use base qw(Encode::Encoding); |
| 20 | require Encode::ISO2022; | ||
| 21 | |||
| 22 | sub encode ($$;$) { | ||
| 23 | my ($obj, $str, $chk) = @_; | ||
| 24 | $_[1] = '' if $chk; | ||
| 25 | $str = &Encode::ISO2022::internal_to_iso2022 ($str, $obj->__2022_encode); | ||
| 26 | return $str; | ||
| 27 | } | ||
| 28 | |||
| 29 | sub decode ($$;$) { | ||
| 30 | my ($obj, $str, $chk) = @_; | ||
| 31 | $_[1] = '' if $chk; | ||
| 32 | return &Encode::ISO2022::iso2022_to_internal ($str, $obj->__2022_decode); | ||
| 33 | } | ||
| 34 | |||
| 35 | sub __2022__common ($) { | ||
| 36 | my $C = Encode::ISO2022->new_object; | ||
| 37 | $C->{option}->{designate_to}->{C0}->{default} = -1; | ||
| 38 | $C->{option}->{designate_to}->{C1}->{default} = -1; | ||
| 39 | $C->{option}->{designate_to}->{G94}->{default} = -1; | ||
| 40 | $C->{option}->{designate_to}->{G94}->{B} = -1; | ||
| 41 | $C->{option}->{designate_to}->{G94n}->{default} = -1; | ||
| 42 | $C->{option}->{designate_to}->{G96}->{default} = -1; | ||
| 43 | $C->{option}->{designate_to}->{G96n}->{default} = -1; | ||
| 44 | $C->{G1} = $Encode::ISO2022::CHARSET{G94}->{"\x7E"}; ## empty | ||
| 45 | $C->{option}->{reset}->{Gdesignation} = 0; | ||
| 46 | $C->{option}->{reset}->{Ginvoke} = 0; | ||
| 47 | $C->{option}->{undef_char} = ["\x22\x2E", ## GETA MARK | ||
| 48 | {type => 'G94n', charset => 'B', revision => '@'}]; | ||
| 49 | $C; | ||
| 50 | } | ||
| 51 | sub __2022_encode ($) { | ||
| 52 | my $C = shift->__2022__common; | ||
| 53 | $C; | ||
| 54 | } | ||
| 55 | sub __2022_decode ($) { | ||
| 56 | my $C = shift->__2022__common; | ||
| 57 | $C; | ||
| 58 | } | ||
| 59 | |||
| 60 | wakaba | 1.5 | sub __clone ($) { |
| 61 | my $self = shift; | ||
| 62 | bless {%$self}, ref $self; | ||
| 63 | }; | ||
| 64 | |||
| 65 | wakaba | 1.2 | package Encode::ISO2022::JIS::JISX0201Latin7; |
| 66 | wakaba | 1.1 | use vars qw/@ISA/; |
| 67 | push @ISA, 'Encode::ISO2022::JIS'; | ||
| 68 | __PACKAGE__->Define (qw/jisx0201-1997-latin-7bit JIS_C6220-1969-ro | ||
| 69 | wakaba | 1.4 | iso-ir-14 ir14 jp ISO646-JP 646-jp csISO14JISC6220ro/); |
| 70 | wakaba | 1.1 | |
| 71 | =item jisx0201-1997-latin-7bit | ||
| 72 | |||
| 73 | JIS X 0201:1997 6.1 7-bit code for Latin. | ||
| 74 | (Alias: C<JIS_C6220-1969-ro> (RFC 1345), C<iso-ir-14> (RFC 1345), | ||
| 75 | wakaba | 1.4 | C<ir14>, C<jp> (RFC 1345), C<ISO646-JP> (RFC 1345), C<646-jp>, |
| 76 | C<csISO14JISC6220ro> (IANA)) | ||
| 77 | wakaba | 1.1 | |
| 78 | =cut | ||
| 79 | |||
| 80 | sub __2022__common ($) { | ||
| 81 | my $C = shift->SUPER::__2022__common; | ||
| 82 | $C->{bit} = 7; | ||
| 83 | $C->{G0} = $Encode::ISO2022::CHARSET{G94}->{J}; ## JIS X 0201:1997 Latin set | ||
| 84 | wakaba | 1.4 | $C->{G1} = $C->{G0}; $C->{G2} = $C->{G1}; ## RFC 1345 (not in JIS) |
| 85 | $C->{G3} = $C->{G1}; | ||
| 86 | wakaba | 1.1 | $C->{option}->{undef_char} = ["\x3F", {type => 'G94', charset => 'J'}]; |
| 87 | $C; | ||
| 88 | } | ||
| 89 | |||
| 90 | wakaba | 1.2 | package Encode::ISO2022::JIS::JISX0201Katakana7; |
| 91 | wakaba | 1.1 | use vars qw/@ISA/; |
| 92 | push @ISA, 'Encode::ISO2022::JIS'; | ||
| 93 | __PACKAGE__->Define (qw/jisx0201-1997-katakana-7bit JIS_C6220-1969-jp JIS_C6220-1969 | ||
| 94 | wakaba | 1.4 | iso-ir-13 ir13 katakana x0201-7 csISO13JISC6220jp/); |
| 95 | wakaba | 1.1 | |
| 96 | =item jisx0201-1997-katakana-7bit | ||
| 97 | |||
| 98 | JIS X 0201:1997 6.2 7-bit code for Katakana | ||
| 99 | (Alias: JIS_C6220-1969-jp (RFC 1345), JIS_C6220-1969 (RFC 1345), | ||
| 100 | wakaba | 1.4 | iso-ir-13 (RFC 1345), ir13, katakana (RFC 1345), x0201-7 (RFC 1345), |
| 101 | wakaba | 1.1 | csISO13JISC6220jp (IANA)) |
| 102 | |||
| 103 | =cut | ||
| 104 | |||
| 105 | sub __2022__common ($) { | ||
| 106 | my $C = shift->SUPER::__2022__common; | ||
| 107 | $C->{bit} = 7; | ||
| 108 | $C->{G0} = $Encode::ISO2022::CHARSET{G94}->{I}; ## JIS X 0201:1997 Katakana set | ||
| 109 | wakaba | 1.4 | $C->{G1} = $C->{G0}; $C->{G2} = $C->{G1}; ## RFC 1345 (not in JIS) |
| 110 | $C->{G3} = $C->{G1}; | ||
| 111 | wakaba | 1.1 | $C->{option}->{undef_char} = ["\x25", {type => 'G94', charset => 'I'}]; |
| 112 | $C; | ||
| 113 | } | ||
| 114 | |||
| 115 | wakaba | 1.2 | package Encode::ISO2022::JIS::JISX0201LatinKatakana7; |
| 116 | wakaba | 1.1 | use vars qw/@ISA/; |
| 117 | push @ISA, 'Encode::ISO2022::JIS'; | ||
| 118 | __PACKAGE__->Define (qw/jisx0201-1997-latin-katakana-7bit | ||
| 119 | JIS_X0201 X0201 csHalfWidthKatakana/); | ||
| 120 | |||
| 121 | =item jisx0201-1997-latin-katakana-7bit | ||
| 122 | |||
| 123 | JIS X 0201:1997 6.3 7-bit code for Latin and Katakana | ||
| 124 | (Alias: JIS_X0201 (RFC 1345), X0201 (RFC 1345), csHalfWidthKatakana (IANA)) | ||
| 125 | |||
| 126 | =cut | ||
| 127 | |||
| 128 | sub __2022__common ($) { | ||
| 129 | my $C = shift->SUPER::__2022__common; | ||
| 130 | $C->{bit} = 7; | ||
| 131 | $C->{G0} = $Encode::ISO2022::CHARSET{G94}->{J}; ## JIS X 0201:1997 Latin set | ||
| 132 | $C->{G1} = $Encode::ISO2022::CHARSET{G94}->{I}; ## JIS X 0201:1997 Katakana set | ||
| 133 | $C->{option}->{Ginvoke_to_left} = [1,1,1,1]; | ||
| 134 | $C->{option}->{reset}->{Ginvoke} = 1; | ||
| 135 | ## JIS X 0201:1997 does not specify this limitation. | ||
| 136 | $C->{option}->{undef_char} = ["\x3F", {type => 'G94', charset => 'J'}]; | ||
| 137 | $C; | ||
| 138 | } | ||
| 139 | sub __2022_encode ($) { | ||
| 140 | my $C = shift->__2022__common; | ||
| 141 | $C->{GR} = undef; | ||
| 142 | $C; | ||
| 143 | } | ||
| 144 | |||
| 145 | wakaba | 1.2 | package Encode::ISO2022::JIS::JISX0201LatinKatakana8; |
| 146 | wakaba | 1.1 | use vars qw/@ISA/; |
| 147 | push @ISA, 'Encode::ISO2022::JIS'; | ||
| 148 | wakaba | 1.6 | __PACKAGE__->Define (qw/jisx0201-1997-latin-latin-8bit kana8/); |
| 149 | wakaba | 1.1 | |
| 150 | =item jisx0201-1997-latin-katakana-8bit | ||
| 151 | |||
| 152 | JIS X 0208:1997 7.4 8-bit code for Latin and Katakana | ||
| 153 | |||
| 154 | =cut | ||
| 155 | |||
| 156 | sub __2022__common ($) { | ||
| 157 | my $C = shift->SUPER::__2022__common; | ||
| 158 | $C->{bit} = 8; | ||
| 159 | $C->{G0} = $Encode::ISO2022::CHARSET{G94}->{J}; ## JIS X 0201:1997 Latin set | ||
| 160 | $C->{G1} = $Encode::ISO2022::CHARSET{G94}->{I}; ## JIS X 0201:1997 Katakana set | ||
| 161 | $C->{option}->{undef_char} = ["\x3F", {type => 'G94', charset => 'J'}]; | ||
| 162 | wakaba | 1.2 | $C->{option}->{C1invoke_to_right} = 1; |
| 163 | wakaba | 1.1 | $C; |
| 164 | } | ||
| 165 | |||
| 166 | wakaba | 1.2 | package Encode::ISO2022::JIS::JISX0208Kanji7; |
| 167 | wakaba | 1.1 | use vars qw/@ISA/; |
| 168 | push @ISA, 'Encode::ISO2022::JIS'; | ||
| 169 | __PACKAGE__->Define (qw/jisx0208-1997-kanji-7bit/); | ||
| 170 | |||
| 171 | =item jisx0208-1997-kanji-7bit | ||
| 172 | |||
| 173 | JIS X 0208:1997 7.1.1 7-bit code for Kanji | ||
| 174 | |||
| 175 | =cut | ||
| 176 | |||
| 177 | sub __2022__common ($) { | ||
| 178 | my $C = shift->SUPER::__2022__common; | ||
| 179 | $C->{bit} = 7; | ||
| 180 | $C->{G0} = $Encode::ISO2022::CHARSET{G94n}->{'B@'}; ## JIS X 0208:1997 | ||
| 181 | $C; | ||
| 182 | } | ||
| 183 | |||
| 184 | wakaba | 1.2 | package Encode::ISO2022::JIS::JISX0208Kanji8; |
| 185 | wakaba | 1.1 | use vars qw/@ISA/; |
| 186 | push @ISA, 'Encode::ISO2022::JIS'; | ||
| 187 | __PACKAGE__->Define (qw/jisx0208-1997-kanji-8bit/); | ||
| 188 | |||
| 189 | =item jisx0208-1997-kanji-8bit | ||
| 190 | |||
| 191 | JIS X 0208:1997 7.1.2 8-bit code for Kanji | ||
| 192 | |||
| 193 | =cut | ||
| 194 | |||
| 195 | sub __2022__common ($) { | ||
| 196 | my $C = shift->SUPER::__2022__common; | ||
| 197 | $C->{bit} = 8; | ||
| 198 | $C->{G0} = $Encode::ISO2022::CHARSET{G94n}->{'B@'}; ## JIS X 0208:1997 | ||
| 199 | $C->{G1} = $Encode::ISO2022::CHARSET{G94}->{"\x7E"}; ## empty | ||
| 200 | $C->{option}->{C1invoke_to_right} = 1; | ||
| 201 | $C; | ||
| 202 | } | ||
| 203 | |||
| 204 | wakaba | 1.2 | package Encode::ISO2022::JIS::JISX0208IRVKanji7; |
| 205 | wakaba | 1.1 | use vars qw/@ISA/; |
| 206 | push @ISA, 'Encode::ISO2022::JIS'; | ||
| 207 | __PACKAGE__->Define (qw/jisx0208-1997-irv-kanji-7bit/); | ||
| 208 | |||
| 209 | =item jisx0208-1997-irv-kanji-7bit | ||
| 210 | |||
| 211 | JIS X 0208:1997 7.2.1 7-bit code for IRV and Kanji | ||
| 212 | |||
| 213 | =cut | ||
| 214 | |||
| 215 | sub __2022__common ($) { | ||
| 216 | my $C = shift->SUPER::__2022__common; | ||
| 217 | $C->{bit} = 7; | ||
| 218 | $C->{G0} = $Encode::ISO2022::CHARSET{G94}->{B}; ## ISO/IEC 646 IRV | ||
| 219 |