| 1 |
wakaba |
1.1 |
|
| 2 |
|
|
=head1 NAME |
| 3 |
|
|
|
| 4 |
|
|
Encode::SJIS::JIS --- Encoder/decoder of standard Shift JIS coding systems |
| 5 |
|
|
|
| 6 |
|
|
=head1 ENCODINGS |
| 7 |
|
|
|
| 8 |
|
|
=over 4 |
| 9 |
|
|
|
| 10 |
|
|
=cut |
| 11 |
|
|
|
| 12 |
|
|
package Encode::SJIS::JIS; |
| 13 |
|
|
use strict; |
| 14 |
|
|
our $VERSION=do{my @r=(q$Revision: 1.1 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
| 15 |
|
|
require Encode::SJIS; |
| 16 |
|
|
require Encode::Encoding; |
| 17 |
|
|
|
| 18 |
|
|
package Encode::SJIS::JIS::SJIS1997; |
| 19 |
|
|
use base 'Encode::SJIS'; |
| 20 |
|
|
__PACKAGE__->Define (qw!shift-jis-1997 shift_jis csshiftjis japanese-shift-jis!); |
| 21 |
|
|
|
| 22 |
|
|
=item shift-jis-1997 |
| 23 |
|
|
|
| 24 |
|
|
Shift coded representation defined by JIS X 0208:1997 Appendix 1. |
| 25 |
|
|
(Alias: shift_jis (IANA), csshiftjis (IANA), japanese-shift-jis (emacsen)) |
| 26 |
|
|
|
| 27 |
|
|
Note that although IANA registry [IANAREG] associates the name "MS_Kanji" |
| 28 |
|
|
as an alias of "Shift_JIS", in this module it is not used as |
| 29 |
|
|
a name of Shift coded representation of JIS X 0208, |
| 30 |
|
|
since it is more apropreate to associate the name with |
| 31 |
|
|
Microsoft-defined-Shift-JIS. (Microsoft's shift JIS is |
| 32 |
|
|
superset of JIS X 0208's shift JIS, even Microsoft's |
| 33 |
|
|
does NOT comform to JIS X 0208:1997.) |
| 34 |
|
|
|
| 35 |
|
|
=cut |
| 36 |
|
|
|
| 37 |
|
|
sub __2022__common ($) { |
| 38 |
|
|
my $C = Encode::SJIS->new_object; |
| 39 |
|
|
$C->{G0} = $Encode::Charset::CHARSET{G94}->{J}; ## JIS X 0201:1997 Latin |
| 40 |
|
|
$C->{G1} = $Encode::Charset::CHARSET{G94n}->{'B@'}; ## JIS X 0208:1997 |
| 41 |
|
|
$C->{G2} = $Encode::Charset::CHARSET{G94}->{I}; ## JIS X 0201:1997 Katakana |
| 42 |
|
|
$C->{G3} = $Encode::Charset::CHARSET{G94n}->{' @'}; ## undef |
| 43 |
|
|
$C; |
| 44 |
|
|
} |
| 45 |
|
|
sub __encode_map ($) { |
| 46 |
|
|
[qw/ucs_to_jisx0201_latin ucs_to_jisx0208_1997 ucs_to_jisx0201_katakana/]; |
| 47 |
|
|
} |
| 48 |
|
|
sub __decode_map ($) { |
| 49 |
|
|
[qw/jisx0201_latin_to_ucs jisx0208_1997_to_ucs jisx0201_katakana_to_ucs/]; |
| 50 |
|
|
} |
| 51 |
|
|
|
| 52 |
|
|
package Encode::SJIS::JIS::SJIS1997ASCII; |
| 53 |
|
|
use base 'Encode::SJIS::JIS::SJIS1997'; |
| 54 |
|
|
__PACKAGE__->Define (qw/shift-jis-1997-ascii/); |
| 55 |
|
|
|
| 56 |
|
|
=item shift-jis-1997-ascii |
| 57 |
|
|
|
| 58 |
|
|
Same as Shift_JISX0213 but ASCII (ISO/IEC 646 IRV) |
| 59 |
|
|
instead of JIS X 0201:1997 Latin character set. |
| 60 |
|
|
|
| 61 |
|
|
Note that this coding system does NOT comform to |
| 62 |
|
|
JIS X 0208:1997 Appendix 1. |
| 63 |
|
|
|
| 64 |
|
|
=cut |
| 65 |
|
|
|
| 66 |
|
|
sub __2022__common ($) { |
| 67 |
|
|
my $C = shift->SUPER::__2022__common; |
| 68 |
|
|
$C->{G0} = $Encode::Charset::CHARSET{G94}->{B}; ## ASCII |
| 69 |
|
|
$C; |
| 70 |
|
|
} |
| 71 |
|
|
sub __encode_map ($) { |
| 72 |
|
|
[qw/ucs_to_ascii ucs_to_jisx0208_1997 ucs_to_jisx0201_katakana/]; |
| 73 |
|
|
} |
| 74 |
|
|
sub __decode_map ($) { |
| 75 |
|
|
[qw/jisx0208_1997_to_ucs jisx0201_katakana_to_ucs/]; |
| 76 |
|
|
} |
| 77 |
|
|
|
| 78 |
|
|
package Encode::SJIS::JIS::SJIS2000plane1; |
| 79 |
|
|
use base 'Encode::SJIS'; |
| 80 |
|
|
__PACKAGE__->Define (qw!shift_jisx0213-plane1!); |
| 81 |
|
|
|
| 82 |
|
|
=item shift_jisx0213-plane1 |
| 83 |
|
|
|
| 84 |
|
|
Shift_JISX0213-plane1 coded representation defined by JIS X 0213:2000 |
| 85 |
|
|
Appendix 1 (i.e. implemention level 3). |
| 86 |
|
|
|
| 87 |
|
|
=cut |
| 88 |
|
|
|
| 89 |
|
|
sub __2022_encode ($) { |
| 90 |
|
|
my $C = shift->__2022__common; |
| 91 |
|
|
$C->{G3} = $Encode::Charset::CHARSET{G94n}->{' @'}; ## undef |
| 92 |
|
|
$C; |
| 93 |
|
|
} |
| 94 |
|
|
sub __encode_map ($) { |
| 95 |
|
|
[qw/ucs_to_jisx0201_latin ucs_to_jisx0213_2000_1 ucs_to_jisx0201_katakana/]; |
| 96 |
|
|
} |
| 97 |
|
|
|
| 98 |
|
|
1; |
| 99 |
|
|
__END__ |
| 100 |
|
|
|
| 101 |
|
|
=back |
| 102 |
|
|
|
| 103 |
|
|
Coding systems C<shift_jisx0213> and C<shift_jisx0213-ascii> |
| 104 |
|
|
are defined in Encode::SJIS. |
| 105 |
|
|
|
| 106 |
|
|
Shift JISes using alternative name (so mapped to HALFWIDTH |
| 107 |
|
|
or FULLWIDTH area of UCS) defined by JIS X 0208:1997 or |
| 108 |
|
|
JIS X 0213:2000 are not included in this module but in |
| 109 |
|
|
Encode::SJIS::JISCompatible. |
| 110 |
|
|
|
| 111 |
|
|
Shift JISes with JIS X 0208-1978, -1983, -1990 are not |
| 112 |
|
|
included in this module since these standards did not |
| 113 |
|
|
define them. They are defined in Encode::SJIS::* |
| 114 |
|
|
other than this module. |
| 115 |
|
|
|
| 116 |
|
|
=head1 SEE ALSO |
| 117 |
|
|
|
| 118 |
|
|
JIS X 0208:1997, "7-bit and 8-bit double byte coded Kanji |
| 119 |
|
|
set for information interchange", Japan Industrial Standards |
| 120 |
|
|
Committee (JISC) <http://www.jisc.go.jp/>, 1997. |
| 121 |
|
|
|
| 122 |
|
|
JIS X 0213:2000, "7-bit and 8-bit double byte coded extended Kanji |
| 123 |
|
|
sets for information interchange", Japan Industrial Standards |
| 124 |
|
|
Committee (JISC) <http://www.jisc.go.jp/>, 2000. |
| 125 |
|
|
|
| 126 |
|
|
Encode::SJIS |
| 127 |
|
|
|
| 128 |
|
|
[IANAREG] "CHARACTER SETS", IANA <http://www.iana.org/>, |
| 129 |
|
|
<http://www.iana.org/assignments/character-sets>. |
| 130 |
|
|
The charset registry for IETF <http://www.ietf.org/> standards. |
| 131 |
|
|
|
| 132 |
|
|
=head1 LICENSE |
| 133 |
|
|
|
| 134 |
|
|
Copyright 2002 Nanashi-san |
| 135 |
|
|
|
| 136 |
|
|
This library is free software; you can redistribute it |
| 137 |
|
|
and/or modify it under the same terms as Perl itself. |
| 138 |
|
|
|
| 139 |
|
|
=cut |
| 140 |
|
|
|
| 141 |
|
|
# $Date: 2002/10/12 07:27:01 $ |
| 142 |
|
|
### SJIS.pm ends here |