5 |
|
|
6 |
=head1 ENCODINGS |
=head1 ENCODINGS |
7 |
|
|
8 |
This module defines only two basic version of shift JIS. |
This module defines encoding engine for Shift JIS coding systems. |
9 |
Other variants are defined in Encode::SJIS::* modules. |
This module only provides general en/decoding parts. Actual profiles |
10 |
|
for Shift JISes are included in Encode::SJIS::*. |
11 |
|
|
12 |
=over 4 |
=over 4 |
13 |
|
|
20 |
require Encode::Charset; |
require Encode::Charset; |
21 |
use base qw(Encode::Encoding); |
use base qw(Encode::Encoding); |
22 |
|
|
|
### --- Perl Encode module common functions |
|
|
|
|
|
sub encode ($$;$) { |
|
|
my ($obj, $str, $chk) = @_; |
|
|
$_[1] = '' if $chk; |
|
|
if (!defined $obj->{_encode_mapping} || $obj->{_encode_mapping}) { |
|
|
require Encode::Table; |
|
|
$str = Encode::Table::convert ($str, $obj->__encode_map, |
|
|
-autoload => defined $obj->{_encode_mapping_autoload} ? |
|
|
$obj->{_encode_mapping_autoload} : 1); |
|
|
} |
|
|
$str = &internal_to_sjis ($str, $obj->__2022_encode); |
|
|
$str; |
|
|
} |
|
|
|
|
|
sub decode ($$;$) { |
|
|
my ($obj, $str, $chk) = @_; |
|
|
$_[1] = '' if $chk; |
|
|
$str = &sjis_to_internal ($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; |
|
|
} |
|
|
|
|
|
### --- Encode::SJIS unique functions |
|
23 |
*new_object = \&Encode::Charset::new_object_sjis; |
*new_object = \&Encode::Charset::new_object_sjis; |
24 |
|
|
25 |
|
## Code extention escape sequence defined by ISO/IEC 2022 is |
26 |
|
## not supported in this version of this module. |
27 |
|
|
28 |
sub sjis_to_internal ($$) { |
sub sjis_to_internal ($$) { |
29 |
my ($s, $C) = @_; |
my ($s, $C) = @_; |
30 |
$C ||= &new_object; |
$C ||= &new_object; |
52 |
$f -= $f < 0xA0 ? 0x81 : 0xC1; $s -= 0x40 + ($s > 0x7F); |
$f -= $f < 0xA0 ? 0x81 : 0xC1; $s -= 0x40 + ($s > 0x7F); |
53 |
chr ($C->{G1}->{ucs} + $f * 188 + $s); |
chr ($C->{G1}->{ucs} + $f * 188 + $s); |
54 |
} else { ## [\xF0-\xFC]. |
} else { ## [\xF0-\xFC]. |
55 |
my ($f, $s) = unpack ('CC', $c2); |
my ($f, $s) = (ord substr ($c2, 0, 1), ord substr ($c2, 1, 1)); |
56 |
if ($C->{G3}->{Csjis_kuE}) { |
if ($C->{G3}->{Csjis_kuE}) { ## 94^2 set with first-byte->ku mapping |
57 |
$f = $s > 0x9E ? $C->{G3}->{Csjis_kuE}->{ $f }: |
my $F = $s > 0x9E ? $C->{G3}->{Csjis_kuE}->{ $f }: ## ku of even number |
58 |
$C->{G3}->{Csjis_kuO}->{ $f }; |
$C->{G3}->{Csjis_kuO}->{ $f }; ## ku of odd number |
59 |
$s -= ($s > 0x9E ? 0x9F : $s > 0x7F ? 0x41 : 0x40); |
if (defined $F) { |
60 |
chr ($C->{G3}->{ucs} + $f * 94 + $s); |
$s -= ($s > 0x9E ? 0x9F : $s > 0x7F ? 0x41 : 0x40); |
61 |
} else { |
chr ($C->{G3}->{ucs} + $F * 94 + $s); |
62 |
|
} else { ## Mapping is not defined |
63 |
|
$f -= 0xF0; $s -= 0x40 + ($s > 0x7F); |
64 |
|
chr ($Encode::Charset::CHARSET{G94n}->{"\x20\x40"}->{ucs} + $f * 188 + $s); |
65 |
|
} |
66 |
|
} elsif ($C->{G3}->{Csjis_ku}) { ## n^2 set with first-byte->ku mapping |
67 |
|
if (defined $C->{G3}->{Csjis_ku}->{ $f }) { |
68 |
|
$f = $C->{G3}->{Csjis_ku}->{ $f }; |
69 |
|
$s -= ($s > 0x9E ? 0x9F : $s > 0x7F ? 0x41 : 0x40); |
70 |
|
chr ($C->{G3}->{ucs} + $f * $C->{G3}->{chars} + $s); |
71 |
|
} else { ## Mapping is not defined |
72 |
|
$f -= 0xF0; $s -= 0x40 + ($s > 0x7F); |
73 |
|
chr ($Encode::Charset::CHARSET{G94n}->{"\x20\x40"}->{ucs} + $f * 188 + $s); |
74 |
|
} |
75 |
|
} else { ## 94^2 set without special mapping information |
76 |
$f -= 0xF0; $s -= 0x40 + ($s > 0x7F); |
$f -= 0xF0; $s -= 0x40 + ($s > 0x7F); |
77 |
chr ($C->{G3}->{ucs} + $f * 188 + $s); |
chr ($C->{G3}->{ucs} + $f * 188 + $s); |
78 |
} |
} |
92 |
$C ||= &new_object; |
$C ||= &new_object; |
93 |
|
|
94 |
my $r = ''; |
my $r = ''; |
95 |
for my $c (split //, $s) { |
my @c = split //, $s; |
96 |
my $cc = ord $c; |
for my $i (0..$#c) { |
97 |
|
my $c = $c[$i]; my $cc = ord $c; Encode::_utf8_off ($c); |
98 |
my $t; |
my $t; |
99 |
|
## CL = C0 control characters |
100 |
if ($cc <= 0x1F) { |
if ($cc <= 0x1F) { |
101 |
$t = $c if $C->{ $C->{CL} } eq $Encode::Charset::CHARSET{C0}->{"\x40"}; |
$t = $c if $C->{ $C->{CL} } eq $Encode::Charset::CHARSET{C0}->{"\x40"}; |
102 |
|
## 0x20 == SP and 0x7E == DEL |
103 |
} elsif ($cc == 0x20 || $cc == 0x7F) { |
} elsif ($cc == 0x20 || $cc == 0x7F) { |
|
Encode::_utf8_off ($c); |
|
104 |
$t = $c; |
$t = $c; |
105 |
|
## GL = G0 = ISO/IEC 646 graphic character set |
106 |
} elsif ($cc < 0x7F) { |
} elsif ($cc < 0x7F) { |
|
Encode::_utf8_off ($c); |
|
107 |
$t = $c if $C->{ $C->{GL} } eq $Encode::Charset::CHARSET{G94}->{"\x42"}; |
$t = $c if $C->{ $C->{GL} } eq $Encode::Charset::CHARSET{G94}->{"\x42"}; |
108 |
|
## 0x80 |
109 |
} elsif ($C->{option}->{C1invoke_to_right} && $cc == 0x80) { |
} elsif ($C->{option}->{C1invoke_to_right} && $cc == 0x80) { |
110 |
$t = "\x80" |
$t = "\x80" |
111 |
if $C->{ $C->{CR} } eq $Encode::Charset::CHARSET{C1}->{'64291991C1'}; |
if $C->{ $C->{CR} } eq $Encode::Charset::CHARSET{C1}->{'64291991C1'}; |
112 |
|
## ESC Fe = C1 control characters |
113 |
} elsif ($cc <= 0x9F) { |
} elsif ($cc <= 0x9F) { |
114 |
$t = "\x1B".pack 'C', ($cc - 0x40) |
$t = "\x1B".pack 'C', ($cc - 0x40) |
115 |
if $C->{ $C->{ESC_Fe} } eq $Encode::Charset::CHARSET{C1}->{'64291991C1'}; |
if $C->{ $C->{ESC_Fe} } eq $Encode::Charset::CHARSET{C1}->{'64291991C1'}; |
116 |
|
## G1 or G3 = 94^2 graphic character set from ISO-IR |
117 |
} elsif (0xE9F6C0 <= $cc && $cc <= 0xF06F80) { |
} elsif (0xE9F6C0 <= $cc && $cc <= 0xF06F80) { |
118 |
my $c = $cc - 0xE9F6C0; my $F = chr (($c / 8836)+0x30); |
my $c = $cc - 0xE9F6C0; my $F = chr (($c / 8836)+0x30); |
119 |
if ($C->{G1} eq $Encode::Charset::CHARSET{G94n}->{ $F }) { |
if ($C->{G1} eq $Encode::Charset::CHARSET{G94n}->{ $F }) { |
123 |
} elsif ($C->{G3} eq $Encode::Charset::CHARSET{G94n}->{ $F }) { |
} elsif ($C->{G3} eq $Encode::Charset::CHARSET{G94n}->{ $F }) { |
124 |
my ($c1, $c2) = ((($c % 8836) / 94)+0x21, ($c % 94)+0x21); |
my ($c1, $c2) = ((($c % 8836) / 94)+0x21, ($c % 94)+0x21); |
125 |
if ($C->{G3}->{Csjis_first}) { |
if ($C->{G3}->{Csjis_first}) { |
126 |
$t = pack ('CC', $C->{G3}->{Csjis_first}->{ ($c % 8836) / 94 }, |
my $fb = $C->{G3}->{Csjis_first}->{ ($c % 8836) / 94 }; |
127 |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)); |
$t = pack ('CC', $fb, $c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)) if $fb; |
128 |
} else { |
} else { |
129 |
$t = pack ('CC', ($c / 188) + 0xF0, |
$t = pack ('CC', ($c / 188) + 0xF0, |
130 |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)) |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)) |
131 |
if ($c / 188) + 0xF0 < 0xFD; |
if ($c / 188) + 0xF0 < 0xFD; |
132 |
} |
} |
133 |
} |
} |
134 |
|
## G1 = JIS X 0208-1990/:1997 |
135 |
} elsif (0xF49D7C <= $cc && $cc <= 0xF4BFFF) { |
} elsif (0xF49D7C <= $cc && $cc <= 0xF4BFFF) { |
136 |
my $c = $cc - 0xF49D7C; |
my $c = $cc - 0xF49D7C; |
137 |
if ($C->{G1} eq $Encode::Charset::CHARSET{G94n}->{'B@'}) { |
if ($C->{G1} eq $Encode::Charset::CHARSET{G94n}->{'B@'}) { |
139 |
$t = pack ('CC', (($c1 - 1) >> 1) + ($c1 < 0x5F ? 0x71 : 0xB1), |
$t = pack ('CC', (($c1 - 1) >> 1) + ($c1 < 0x5F ? 0x71 : 0xB1), |
140 |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)); |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)); |
141 |
} |
} |
142 |
|
## GL = G0 = ISO/IEC 646 graphic character set / GR = G2 = JIS X 0201 Katakana set |
143 |
} elsif (0xE90940 <= $cc && $cc <= 0xE92641) { |
} elsif (0xE90940 <= $cc && $cc <= 0xE92641) { |
144 |
my $c = $cc - 0xE90940; my $F = chr (($c / 94)+0x30); |
my $c = $cc - 0xE90940; my $F = chr (($c / 94)+0x30); |
145 |
if ($C->{ $C->{GL} } eq $Encode::Charset::CHARSET{G94}->{ $F }) { |
if ($C->{ $C->{GL} } eq $Encode::Charset::CHARSET{G94}->{ $F }) { |
147 |
} elsif ($C->{ $C->{GR} } eq $Encode::Charset::CHARSET{G94}->{ $F }) { |
} elsif ($C->{ $C->{GR} } eq $Encode::Charset::CHARSET{G94}->{ $F }) { |
148 |
$t = pack 'C', (($c % 94) + 0xA1) if ($c % 94) < 0x3F; |
$t = pack 'C', (($c % 94) + 0xA1) if ($c % 94) < 0x3F; |
149 |
} |
} |
150 |
|
## G1 / G3 = 94^2 graphic character set |
151 |
} elsif (0x70420000 <= $cc && $cc <= 0x7046F19B) { |
} elsif (0x70420000 <= $cc && $cc <= 0x7046F19B) { |
152 |
my $c = $cc % 0x10000; |
my $c = $cc % 0x10000; |
153 |
my $F0=$C->{option}->{private_set}->{G94n}->[($cc/0x10000)-0x7042]->[$c/8836]; |
my $F0=$C->{option}->{private_set}->{G94n}->[($cc/0x10000)-0x7042]->[$c/8836]; |
156 |
|| $C->{G3} eq $Encode::Charset::CHARSET{G94n}->{ $F1 }) { |
|| $C->{G3} eq $Encode::Charset::CHARSET{G94n}->{ $F1 }) { |
157 |
my ($c1, $c2) = ((($c % 8836) / 94)+0x21, ($c % 94)+0x21); |
my ($c1, $c2) = ((($c % 8836) / 94)+0x21, ($c % 94)+0x21); |
158 |
if ($C->{G3}->{Csjis_first}) { |
if ($C->{G3}->{Csjis_first}) { |
159 |
$t = pack ('CC', $C->{G3}->{Csjis_first}->{ ($c % 8836) / 94 }, |
my $fb = $C->{G3}->{Csjis_first}->{ ($c % 8836) / 94 }; |
160 |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)); |
$t = pack ('CC', $fb, $c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)) if $fb; |
161 |
} else { |
} else { |
162 |
$t = pack ('CC', ($c / 188) + 0xF0, |
$t = pack ('CC', ($c / 188) + 0xF0, |
163 |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)) |
$c2 + (($c1 & 1) ? ($c2 < 0x60 ? 0x1F : 0x20) : 0x7E)) |
164 |
if ($c / 188) + 0xF0 < 0xFD; |
if ($c / 188) + 0xF0 < 0xFD; |
165 |
} |
} |
166 |
} |
} |
167 |
|
## Non-ISO/IEC 2022 Coded Character Sets Mapping Area |
168 |
|
} elsif (0x71000000 <= $cc && $cc <= 0x71FFFFFF) { |
169 |
|
if ($C->{G3}->{ucs} <= $cc) { |
170 |
|
my $c = $cc - $C->{G3}->{ucs}; |
171 |
|
my $f = $C->{G3}->{Csjis_first}->{$c / $C->{G3}->{chars}}; |
172 |
|
if ($f) { |
173 |
|
my $s = $c % $C->{G3}->{chars}; |
174 |
|
$t = pack ('CC', $f, 0x40 + $s + ($s > 62)); |
175 |
|
} |
176 |
|
} |
177 |
|
## Other character sets are not supported now (and there is no plan to implement them). |
178 |
} |
} |
179 |
|
|
180 |
|
## Output the character itself |
181 |
if (defined $t) { |
if (defined $t) { |
182 |
$r .= $t; |
$r .= $t; |
183 |
|
## Output the character itself with mapping table of special code positions |
184 |
} elsif ($C->{GsmapR}->{ $c }) { |
} elsif ($C->{GsmapR}->{ $c }) { |
185 |
$r .= $C->{GsmapR}->{ $c }; |
$r .= $C->{GsmapR}->{ $c }; |
186 |
|
} elsif ($C->{option}->{fallback_from_ucs} =~ /quiet/) { |
187 |
|
return ($r, halfway => 1, converted_length => $i, |
188 |
|
warn => $C->{option}->{fallback_from_ucs} =~ /warn/ ? 1 : 0, |
189 |
|
reason => sprintf (q(U+%04X: There is no character mapped to), $cc)); |
190 |
|
} elsif ($C->{option}->{fallback_from_ucs} eq 'croak') { |
191 |
|
return ($r, halfway => 1, die => 1, |
192 |
|
reason => sprintf (q(U+%04X: There is no character mapped to), $cc)); |
193 |
|
## |
194 |
} else { |
} else { |
195 |
$r .= $C->{option}->{undef_char_sjis} || "\x3F"; |
## Try to output with fallback escape sequence (if specified) |
196 |
|
my $t = Encode::Charset->fallback_escape ($C, $c); |
197 |
|
if (defined $t) { |
198 |
|
my %D = (fallback => $C->{option}->{fallback_from_ucs}, reset => $C->{option}->{reset}); |
199 |
|
$C->{option}->{fallback_from_ucs} = 'croak'; |
200 |
|
eval q{$t = $C->{_encoder}->_encode_internal ($t, $C)} or undef $t; |
201 |
|
$C->{option}->{fallback_from_ucs} = $D{fallback}; |
202 |
|
} |
203 |
|
if (defined $t) { |
204 |
|
$r .= $t; |
205 |
|
} else { ## Replacement character specified in charset definition |
206 |
|
$r .= $C->{option}->{undef_char_sjis} || "\x3F"; |
207 |
|
} |
208 |
} |
} |
209 |
} |
} |
210 |
$r; |
$r; |
211 |
} |
} |
212 |
|
|
213 |
sub __clone ($) { |
sub page_to_internal ($$) { |
214 |
my $self = shift; |
my ($C, $s) = @_; |
215 |
bless {%$self}, ref $self; |
$s = pack ('U*', unpack ('C*', $s)); |
216 |
}; |
$s =~ s(\x1B\x24([EFGOPQ])([\x21-\x7E]+)\x0F)( |
217 |
|
my $page = {qw/E 1 F 2 G 3 O 4 P 5 Q 6/}->{$1}; |
218 |
__PACKAGE__->Define (qw!shift_jisx0213 japanese-shift-jisx0213 |
my $r = ''; |
219 |
shift-jisx0213 x-shift_jisx0213 shift-jis-3 shift-jis-2000 sjisx0213 |
for my $c (split //, $2) { |
220 |
sjis s-jis shift-jis x-sjis x_sjis x-sjis-jp shiftjis x-shiftjis |
$r .= chr ($Encode::Charset::CHARSET{G94}->{'CSpictogram_page_'.$page}->{ucs} + ord ($c) - 0x21); |
221 |
x-shift-jis shift.jis!); |
} |
222 |
|
$r; |
223 |
=item sjis |
)gex; |
224 |
|
$s; |
|
"Shift JIS" coding system. (Alias: shift-jis, shiftjis, |
|
|
shift.jis, x-shiftjis, x-shift-jis, s-jis, x-sjis, x_sjis, |
|
|
x-sjis-jp) |
|
|
|
|
|
Since this name is ambiguous (it can now refer all or any |
|
|
of shift JIS coding system family), this name should not |
|
|
be used to address specific coding system. In this module, |
|
|
this is considered as an alias name to the shift JIS with |
|
|
latest official definition, currently of JIS X 0213:2000 |
|
|
Appendix 1 (with implemention level 4). |
|
|
|
|
|
Note that the name "Shift_JIS" is not associated with |
|
|
this name, because IANA registry [IANAREG] assignes |
|
|
it to a shift JIS defined by JIS X 0208:1997. |
|
|
|
|
|
=item shift_jisx0213 |
|
|
|
|
|
Shift_JISX0213 coded representation, defined by |
|
|
JIS X 0213:2000 Appendix 1 (implemention level 4). |
|
|
(Alias: shift-jisx0213, x-shift_jisx0213, japanese-shift-jisx0213 (emacsen), |
|
|
shift-jis-3 (Yudit), shift-jis-2000, sjisx0213) |
|
|
|
|
|
=cut |
|
|
|
|
|
sub __2022__common ($) { |
|
|
my $C = Encode::SJIS->new_object; |
|
|
$C->{G0} = $Encode::Charset::CHARSET{G94}->{J}; ## JIS X 0201:1997 Latin |
|
|
$C->{G1} = $Encode::Charset::CHARSET{G94n}->{"\x4F"}; ## JIS X 0213:2000 plane 1 |
|
|
$C->{G2} = $Encode::Charset::CHARSET{G94}->{I}; ## JIS X 0201:1997 Katakana |
|
|
$C->{G3} = $Encode::Charset::CHARSET{G94n}->{"\x50"}; ## JIS X 0213:2000 plane 2 |
|
|
$C; |
|
|
} |
|
|
sub __2022_encode ($) { |
|
|
my $C = shift->__2022__common; |
|
|
$C; |
|
|
} |
|
|
sub __2022_decode ($) { |
|
|
my $C = shift->__2022__common; |
|
|
$C; |
|
|
} |
|
|
sub __encode_map ($) { |
|
|
[qw/ucs_to_jisx0201_latin ucs_to_jisx0213_2000_1 ucs_to_jisx0213_2000_2 ucs_to_jisx0201_katakana/]; |
|
|
} |
|
|
sub __decode_map ($) { |
|
|
[qw/jisx0201_latin_to_ucs jisx0213_2000_1_to_ucs jisx0213_2000_2_to_ucs jisx0201_katakana_to_ucs/]; |
|
225 |
} |
} |
226 |
|
|
227 |
package Encode::SJIS::X0213ASCII; |
sub _internal_to_page ($$$%) { |
228 |
use vars qw/@ISA/; |
my ($yourself, $C, $c, $option) = @_; |
229 |
push @ISA, 'Encode::SJIS'; |
my $cc = ord $c; |
230 |
__PACKAGE__->Define (qw/shift_jisx0213-ascii shift-jis-2000-ascii |
for my $page (1..6) { |
231 |
sjis-ascii shift-jis-ascii/); |
my $cs = $Encode::Charset::CHARSET{G94}->{'CSpictogram_page_'.$page}; |
232 |
|
if ($cs->{ucs} <= $cc && $cc < $cs->{ucs} + $cs->{chars} * $cs->{dimension}) { |
233 |
=item sjis-ascii |
return "\x1B\x24" . ([qw/_ E F G O P Q/]->[$page]) |
234 |
|
.pack ('C', 0x21 + $cc - $cs->{ucs}) . "\x0F"; |
235 |
Same as sjis but ASCII (ISO/IEC 646 IRV) instead of |
} |
236 |
JIS X 0201 Roman (or Latin) set. (Alias: shift-jis-ascii) |
} |
237 |
|
## $c is not a pictogram |
238 |
In spite of the history of shift JIS, ASCII is sometimes |
$option->{fallback_from_ucs} = $C->{option}->{fallback_from_ucs_2}; |
239 |
used instead of JIS X 0201 Roman set, because of compatibility |
$yourself->fallback_escape ($C, $c, %$option); |
|
with ASCII world. |
|
|
|
|
|
Note that this name is now an alias of shift_jisx0213-ascii, |
|
|
as sjis is of shift_jisx0213. |
|
|
|
|
|
=item shift_jisx0213-ascii |
|
|
|
|
|
Same as Shift_JISX0213 but ASCII (ISO/IEC 646 IRV) |
|
|
instead of JIS X 0201:1997 Latin character set. |
|
|
(Alias: shift-jis-2000-ascii) |
|
|
|
|
|
Note that this coding system does NOT comform to |
|
|
JIS X 0213:2000 Appendix 1. |
|
|
|
|
|
=cut |
|
|
|
|
|
sub __2022__common ($) { |
|
|
my $C = shift->SUPER::__2022__common; |
|
|
$C->{G0} = $Encode::Charset::CHARSET{G94}->{B}; ## ASCII |
|
|
$C; |
|
|
} |
|
|
sub __encode_map ($) { |
|
|
[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 jisx0213_2000_2_to_ucs jisx0201_katakana_to_ucs/]; |
|
240 |
} |
} |
241 |
|
|
|
1; |
|
|
__END__ |
|
|
|
|
242 |
=back |
=back |
243 |
|
|
244 |
=head1 SEE ALSO |
=head1 SEE ALSO |
251 |
sets for information interchange", Japan Industrial Standards |
sets for information interchange", Japan Industrial Standards |
252 |
Committee (JISC) <http://www.jisc.go.jp/>, 2000. |
Committee (JISC) <http://www.jisc.go.jp/>, 2000. |
253 |
|
|
254 |
Encode, perlunicode |
L<Encode::SJIS::JIS> |
255 |
|
|
256 |
|
L<Encode>, L<perlunicode> |
257 |
|
|
258 |
[IANAREG] "CHARACTER SETS", IANA <http://www.iana.org/>, |
L<Encode::Charset>, L<Encode::ISO2022> |
|
<http://www.iana.org/assignments/character-sets>. |
|
|
The charset registry for IETF <http://www.ietf.org/> standards. |
|
|
(Note that in this registry two shift JISes are registered, |
|
|
"Shift_JIS" and "Windows-31j". Former is JIS X 0208:1997's |
|
|
definition and later is the Windows standard character set.) |
|
259 |
|
|
260 |
=head1 LICENSE |
=head1 LICENSE |
261 |
|
|
262 |
Copyright 2002 Nanashi-san |
Copyright 2002 Nanashi-san <nanashi-san@nanashi.invalid> |
263 |
|
|
264 |
This library is free software; you can redistribute it |
This library is free software; you can redistribute it |
265 |
and/or modify it under the same terms as Perl itself. |
and/or modify it under the same terms as Perl itself. |
266 |
|
|
267 |
=cut |
=cut |
268 |
|
|
269 |
# $Date$ |
1; # $Date$ |
|
### SJIS.pm ends here |
|