Parent Directory
|
Revision Log
2002-09-16 Wakaba <w@suika.fam.cx> * EightBit.pm: New module. * JIS.pm: New module. * SevenBit.pm: Don't invoke G1 to GR when encoding.
| 1 | wakaba | 1.1 | =head1 NAME |
| 2 | |||
| 3 | Encode::ISO2022::SevenBit --- Encode and decode of 7-bit ISO/IEC 2022 | ||
| 4 | based encodings | ||
| 5 | |||
| 6 | =head1 ENCODINGS | ||
| 7 | |||
| 8 | =over 4 | ||
| 9 | |||
| 10 | =cut | ||
| 11 | |||
| 12 | require 5.7.3; | ||
| 13 | use strict; | ||
| 14 | package Encode::ISO2022::SevenBit; | ||
| 15 | use vars qw($VERSION); | ||
| 16 | wakaba | 1.4 | $VERSION=do{my @r=(q$Revision: 1.3 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 17 | wakaba | 1.1 | use base qw(Encode::Encoding); |
| 18 | wakaba | 1.3 | __PACKAGE__->Define (qw/iso-2022-7bit iso-2022-7 jis junet jis7/); |
| 19 | wakaba | 1.1 | require Encode::ISO2022; |
| 20 | |||
| 21 | sub encode ($$;$) { | ||
| 22 | my ($obj, $str, $chk) = @_; | ||
| 23 | $_[1] = '' if $chk; | ||
| 24 | $str = &Encode::ISO2022::internal_to_iso2022 ($str, $obj->__2022_encode); | ||
| 25 | return $str; | ||
| 26 | } | ||
| 27 | |||
| 28 | sub decode ($$;$) { | ||
| 29 | my ($obj, $str, $chk) = @_; | ||
| 30 | $_[1] = '' if $chk; | ||
| 31 | return &Encode::ISO2022::iso2022_to_internal ($str, $obj->__2022_decode); | ||
| 32 | } | ||
| 33 | |||
| 34 | =item iso-2022-7bit | ||
| 35 | |||
| 36 | ISO/IEC 2022 based 7-bit encoding using only G0 | ||
| 37 | wakaba | 1.3 | (Alias: junet, jis, jis7, iso-2022-7) |
| 38 | wakaba | 1.1 | |
| 39 | =cut | ||
| 40 | |||
| 41 | sub __2022__common ($) { | ||
| 42 | my $C = Encode::ISO2022->new_object; | ||
| 43 | $C->{bit} = 7; | ||
| 44 | $C->{option}->{designate_to}->{G96}->{default} = 0; | ||
| 45 | $C->{option}->{designate_to}->{G96n}->{default} = 0; | ||
| 46 | $C; | ||
| 47 | } | ||
| 48 | sub __2022_encode ($) { | ||
| 49 | my $C = shift->__2022__common; | ||
| 50 | wakaba | 1.4 | $C->{GR} = undef; |
| 51 | wakaba | 1.1 | $C->{G1} = $Encode::ISO2022::CHARSET{G96}->{"\x7E"}; ## empty set |
| 52 | $C; | ||
| 53 | } | ||
| 54 | sub __2022_decode ($) { | ||
| 55 | my $C = shift->__2022__common; | ||
| 56 | |||
| 57 | $C; | ||
| 58 | } | ||
| 59 | |||
| 60 | package Encode::ISO2022::SevenBit::JP; | ||
| 61 | use vars qw/@ISA/; | ||
| 62 | push @ISA, 'Encode::ISO2022::SevenBit'; | ||
| 63 | wakaba | 1.2 | __PACKAGE__->Define (qw/iso-2022-jp junet-code japanese-iso-7bit csiso2022jp |
| 64 | cp50220 iso2022jp/); | ||
| 65 | wakaba | 1.1 | |
| 66 | =item iso-2022-jp | ||
| 67 | |||
| 68 | ISO/IEC 2022 based 7-bit encoding for Japanese. | ||
| 69 | Defined by Junet no tebiki, RFC 1468 and JIS X 0208:1997 Appendix 2. | ||
| 70 | wakaba | 1.2 | (Alias: junet-code, japanese-iso-7bit (emacsen), csISO2022JP (IANA), |
| 71 | CP50220 (M$)) | ||
| 72 | wakaba | 1.1 | |
| 73 | =cut | ||
| 74 | |||
| 75 | sub __2022__common ($) { | ||
| 76 | my $C = Encode::ISO2022->new_object; | ||
| 77 | $C->{bit} = 7; | ||
| 78 | $C->{option}->{designate_to}->{C0}->{default} = -1; | ||
| 79 | $C->{option}->{designate_to}->{C0}->{"\x40"} = 0; | ||
| 80 | $C->{option}->{designate_to}->{C1}->{default} = -1; | ||
| 81 | $C->{option}->{designate_to}->{G94}->{default} = -1; | ||
| 82 | $C->{option}->{designate_to}->{G94n}->{default} = -1; | ||
| 83 | $C->{option}->{designate_to}->{G96}->{default} = -1; | ||
| 84 | $C->{option}->{designate_to}->{G96n}->{default} = -1; | ||
| 85 | $C->{option}->{designate_to}->{G94}->{"\x4A"} = 0; ## JIS X 0201 roman | ||
| 86 | $C->{option}->{designate_to}->{G94n}->{"\x40"} = 0; ## JIS X 0208-1978 | ||
| 87 | $C->{option}->{designate_to}->{G94n}->{"\x42"} = 0; ## JIS X 0208-1983 | ||
| 88 | $C->{option}->{designate_to}->{G94n}->{"\x42\x40"} = 0; ## JIS X 0208-1990 | ||
| 89 | $C->{option}->{use_revision} = 0; | ||
| 90 | $C; | ||
| 91 | } | ||
| 92 | sub __2022_encode ($) { | ||
| 93 | my $C = shift->__2022__common; | ||
| 94 | wakaba | 1.4 | $C->{GR} = undef; |
| 95 | wakaba | 1.1 | $C->{C1} = $Encode::ISO2022::CHARSET{C1}->{"\x7E"}; ## empty set |
| 96 | $C->{G1} = $Encode::ISO2022::CHARSET{G96}->{"\x7E"}; ## empty set | ||
| 97 | $C; | ||
| 98 | } | ||
| 99 | |||
| 100 | package Encode::ISO2022::SevenBit::JP1978IRV; | ||
| 101 | use vars qw/@ISA/; | ||
| 102 | push @ISA, 'Encode::ISO2022::SevenBit::JP'; | ||
| 103 | wakaba | 1.2 | __PACKAGE__->Define (qw/iso-2022-jp-1978-irv japanese-iso-7bit-1978-irv old-jis |
| 104 | x-obsoleted-iso-2022-jp/); | ||
| 105 | wakaba | 1.1 | |
| 106 | =item iso-2022-jp-1978-irv | ||
| 107 | |||
| 108 | ISO/IEC 2022 based 7-bit encoding for Japanese. | ||
| 109 | (Alias: japanese-iso-7bit-1978-irv (emacsen), old-jis (emacsen)) | ||
| 110 | |||
| 111 | =cut | ||
| 112 | |||
| 113 | sub __2022_encode ($) { | ||
| 114 | my $C = shift->__2022__common; | ||
| 115 | wakaba | 1.4 | $C->{GR} = undef; |
| 116 | wakaba | 1.1 | $C->{option}->{designate_to}->{G94}->{"\x4A"} = -1; ## JIS X 0201 roman |
| 117 | $C->{option}->{designate_to}->{G94n}->{"\x42"} = -1; ## JIS X 0208-1983 | ||
| 118 | $C->{option}->{designate_to}->{G94n}->{"\x42\x40"} = -1; ## JIS X 0208-1990 | ||
| 119 | $C; | ||
| 120 | } | ||
| 121 | |||
| 122 | package Encode::ISO2022::SevenBit::JP1; | ||
| 123 | use vars qw/@ISA/; | ||
| 124 | push @ISA, 'Encode::ISO2022::SevenBit::JP'; | ||
| 125 | __PACKAGE__->Define (qw/iso-2022-jp-1/); | ||
| 126 | |||
| 127 | =item iso-2022-jp-1 | ||
| 128 | |||
| 129 | ISO/IEC 2022 based 7-bit encoding for Japanese, | ||
| 130 | defined by RFC 2237 | ||
| 131 | |||
| 132 | =cut | ||
| 133 | |||
| 134 | sub __2022__common ($) { | ||
| 135 | my $C = shift->SUPER::__2022__common; | ||
| 136 | $C->{option}->{designate_to}->{G94n}->{"\x44"} = 0; ## JIS X 0212-1990 | ||
| 137 | $C->{option}->{designate_to}->{G94n}->{"\x42\x40"} = -1; ## JIS X 0208-1990 | ||
| 138 | $C; | ||
| 139 | } | ||
| 140 | |||
| 141 | package Encode::ISO2022::SevenBit::JP3; | ||
| 142 | use vars qw/@ISA/; | ||
| 143 | push @ISA, 'Encode::ISO2022::SevenBit::JP'; | ||
| 144 | __PACKAGE__->Define (qw/iso-2022-jp-3 x-iso-2022-jp-3 iso-2022-jp-3-compatible iso-2022-jp-3-strict/); | ||
| 145 | |||
| 146 | =item iso-2022-jp-3 | ||
| 147 | |||
| 148 | ISO/IEC 2022 based 7-bit encoding for Japanese, | ||
| 149 | defined by JIS X 0213:2000 Appendix 2. | ||
| 150 | (Alias: x-iso-2022-jp-3) | ||
| 151 | |||
| 152 | =item iso-2022-jp-3-compatible | ||
| 153 | |||
| 154 | ISO/IEC 2022 based 7-bit encoding for Japanese | ||
| 155 | |||
| 156 | =item iso-2022-jp-3-strict | ||
| 157 | |||
| 158 | ISO/IEC 2022 based 7-bit encoding for Japanese. | ||
| 159 | A subset of iso-2022-jp-3. | ||
| 160 | |||
| 161 | =cut | ||
| 162 | |||
| 163 | sub __2022__common ($) { | ||
| 164 | my $C = shift->SUPER::__2022__common; | ||
| 165 | $C->{option}->{designate_to}->{G94}->{"\x4A"} = -1; ## JIS X 0201 roman | ||
| 166 | $C->{option}->{designate_to}->{G94n}->{"\x40"} = -1; ## JIS X 0208-1978 | ||
| 167 | $C->{option}->{designate_to}->{G94n}->{"\x42"} = 0; ## restricted JIS X 0213:2000 plane 1 | ||
| 168 | $C->{option}->{designate_to}->{G94n}->{"\x42\x40"} = -1; ## JIS X 0208-1990 | ||
| 169 | $C->{option}->{designate_to}->{G94n}->{"\x4F"} = 0; ## JIS X 0213:2000 plane 1 | ||
| 170 | $C->{option}->{designate_to}->{G94n}->{"\x50"} = 0; ## JIS X 0213:2000 plane 2 | ||
| 171 | $C; | ||
| 172 | } | ||
| 173 | |||
| 174 | package Encode::ISO2022::SevenBit::JP3Plane1; | ||
| 175 | use vars qw/@ISA/; | ||
| 176 | push @ISA, 'Encode::ISO2022::SevenBit::JP3'; | ||
| 177 | __PACKAGE__->Define (qw/iso-2022-jp-3-plane1/); | ||
| 178 | |||
| 179 | =item iso-2022-jp-3-plane1 | ||
| 180 | |||
| 181 | ISO/IEC 2022 based 7-bit encoding for Japanese, | ||
| 182 | defined by JIS X 0213:2000 Appendix 2. | ||
| 183 | |||
| 184 | =cut | ||
| 185 | |||
| 186 | sub __2022__common ($) { | ||
| 187 | my $C = shift->SUPER::__2022__common; | ||
| 188 | $C->{option}->{designate_to}->{G94n}->{"\x50"} = -1; ## JIS X 0213:2000 plane 2 | ||
| 189 | $C; | ||
| 190 | } | ||
| 191 | |||
| 192 | package Encode::ISO2022::SevenBit::SS2; | ||
| 193 | use vars qw/@ISA/; | ||
| 194 | push @ISA, 'Encode::ISO2022::SevenBit'; | ||
| 195 | wakaba | 1.3 | __PACKAGE__->Define (qw/iso-2022-7bit-ss2 x-iso-2022-jp-2 iso-2022-ss2-7 |
| 196 | jis_encoding csjisencoding/); | ||
| 197 | wakaba | 1.1 | |
| 198 | =item iso-2022-7bit-ss2 | ||
| 199 | |||
| 200 | ISO/IEC 2022 based 7-bit encoding using SS2 for 96-charset | ||
| 201 | wakaba | 1.3 | (Alias: x-iso-2022-jp-2, iso-2022-ss2-7 (emacsen)) |
| 202 | wakaba | 1.1 | |
| 203 | =cut | ||
| 204 | |||
| 205 | sub __2022__common ($) { | ||
| 206 | my $C = shift->SUPER::__2022__common; | ||
| 207 | $C->{option}->{designate_to}->{G96}->{default} = 2; | ||
| 208 | $C->{option}->{designate_to}->{G96n}->{default} = 2; | ||
| 209 | $C->{option}->{Ginvoke_by_single_shift}->[2] = 1; | ||
| 210 | $C; | ||
| 211 | } | ||
| 212 | |||
| 213 | package Encode::ISO2022::SevenBit::JP2; | ||
| 214 | use vars qw/@ISA/; | ||
| 215 | push @ISA, 'Encode::ISO2022::SevenBit::SS2'; | ||
| 216 | wakaba | 1.2 | __PACKAGE__->Define (qw/iso-2022-jp-2 csiso2022jp2/); |
| 217 | wakaba | 1.1 | |
| 218 | =item iso-2022-jp-2 | ||
| 219 | |||
| 220 | ISO/IEC 2022 based 7-bit multilingual encoding, defined by | ||
| 221 | wakaba | 1.2 | RFC 1554. A subset of iso-2022-7bit-ss2. (Alias: csISO2022JP2 (IANA)) |
| 222 | wakaba | 1.1 | |
| 223 | =cut | ||
| 224 | |||
| 225 | sub __2022__common ($) { | ||
| 226 | my $C = shift->SUPER::__2022__common; | ||
| 227 | $C->{option}->{designate_to}->{C0}->{default} = -1; | ||
| 228 | $C->{option}->{designate_to}->{C0}->{"\x40"} = 0; | ||
| 229 | $C->{option}->{designate_to}->{C1}->{default} = -1; | ||
| 230 | $C->{C1} = $Encode::ISO2022::CHARSET{C1}->{"\x47"}; ## Minimum C1 | ||
| 231 | $C->{option}->{designate_to}->{C1}->{"\x47"} = 1; | ||
| 232 | $C->{option}->{designate_to}->{G94}->{default} = -1; | ||
| 233 | $C->{option}->{designate_to}->{G94n}->{default} = -1; | ||
| 234 | $C->{option}->{designate_to}->{G96}->{default} = -1; | ||
| 235 | $C->{option}->{designate_to}->{G96n}->{default} = -1; | ||
| 236 | $C->{option}->{designate_to}->{G94}->{"\x4A"} = 0; ## JIS X 0201 roman | ||
| 237 | for ("\x40", "\x41", "\x42", "\x43") { | ||
| 238 | $C->{option}->{designate_to}->{G94n}->{ $_ } = 0; | ||
| 239 | } | ||
| 240 | for ("\x41", "\x46") { | ||
| 241 | $C->{option}->{designate_to}->{G96}->{ $_ } = 2; | ||
| 242 | } | ||
| 243 | $C; | ||
| 244 | } | ||
| 245 | sub __2022_encode ($) { | ||
| 246 | my $C = shift->__2022__common; | ||
| 247 | wakaba | 1.4 | $C->{GR} = undef; |
| 248 | wakaba | 1.1 | $C->{C1} = $Encode::ISO2022::CHARSET{C1}->{"\x7E"}; ## empty set |
| 249 | $C->{G1} = $Encode::ISO2022::CHARSET{G96}->{"\x7E"}; ## empty set | ||
| 250 | $C; | ||
| 251 | } | ||
| 252 | |||
| 253 | package Encode::ISO2022::SevenBit::Lock; | ||
| 254 | use vars qw/@ISA/; | ||
| 255 | push @ISA, 'Encode::ISO2022::SevenBit'; | ||
| 256 | __PACKAGE__->Define (qw/iso-2022-7bit-lock/); | ||
| 257 | |||
| 258 | =item iso-2022-7bit-lock | ||
| 259 | |||
| 260 | ISO/IEC 2022 based 7-bit encoding using G1 and locking-shift for 96-charset | ||
| 261 | |||
| 262 | =cut | ||
| 263 | |||
| 264 | sub __2022__common ($) { | ||
| 265 | my $C = shift->SUPER::__2022__common; | ||
| 266 | $C->{option}->{designate_to}->{G96}->{default} = 1; | ||
| 267 | $C->{option}->{designate_to}->{G96n}->{default} = 1; | ||
| 268 | $C; | ||
| 269 | } | ||
| 270 | |||
| 271 | wakaba | 1.3 | package Encode::ISO2022::SevenBit::INT; |
| 272 | use vars qw/@ISA/; | ||
| 273 | push @ISA, 'Encode::ISO2022::SevenBit'; | ||
| 274 | __PACKAGE__->Define (qw/iso-2022-int iso-2022-int-* iso-2022-int-2/); | ||
| 275 | |||
| 276 | =item iso-2022-int | ||
| 277 | |||
| 278 | ISO/IEC 2022 based 7-bit encoding using G1 and locking-shift for | ||
| 279 | KS X 1001 and 96-charset. See draft-ohta-text-encoding. | ||
| 280 | (Alias: iso-2022-int-*) | ||
| 281 | |||
| 282 | =cut | ||
| 283 | |||
| 284 | sub __2022__common ($) { | ||
| 285 | my $C = shift->SUPER::__2022__common; | ||
| 286 | $C->{option}->{designate_to}->{G96}->{default} = 1; | ||
| 287 | $C->{option}->{designate_to}->{G96n}->{default} = 1; | ||
| 288 | $C->{option}->{designate_to}->{G94n}->{"\x43"} = 1; ## KS X 1001 | ||
| 289 | $C; | ||
| 290 | } | ||
| 291 | sub __2022_encode ($) { | ||
| 292 | my $C = shift->__2022__common; | ||
| 293 | wakaba | 1.4 | $C->{GR} = undef; |
| 294 | wakaba | 1.3 | $C->{C1} = $Encode::ISO2022::CHARSET{C1}->{"\x7E"}; ## empty set |
| 295 | $C->{G1} = $Encode::ISO2022::CHARSET{G96}->{"\x7E"}; ## empty set | ||
| 296 | $C; | ||
| 297 | } | ||
| 298 | sub __2022_decode ($) { | ||
| 299 | my $C = shift->__2022__common; | ||
| 300 | $C->{G1} = $Encode::ISO2022::CHARSET{G94n}->{"\x43"}; ## KS X 1001 | ||
| 301 | $C; | ||
| 302 | } | ||
| 303 | |||
| 304 | wakaba | 1.1 | package Encode::ISO2022::SevenBit::KR; |
| 305 | use vars qw/@ISA/; | ||
| 306 | push @ISA, 'Encode::ISO2022::SevenBit'; | ||
| 307 | wakaba | 1.2 | __PACKAGE__->Define (qw/iso-2022-kr korean-iso-7bit csiso2022kr cp50225 kr2022/); |
| 308 | wakaba | 1.1 | |
| 309 | =item iso-2022-kr | ||
| 310 | |||
| 311 | An ISO/IEC 2022 based 7-bit encoding for Korean, | ||
| 312 | wakaba | 1.2 | defined by RFC 1557 (Alias: korean-iso-7bit (emacsen), |
| 313 | csISO2022KR (IANA), CP50225 (M$), KR2022) | ||
| 314 | wakaba | 1.1 | |
| 315 | =cut | ||
| 316 | |||
| 317 | sub __2022__common ($) { | ||
| 318 | my $C = shift->SUPER::__2022__common; | ||