1 |
wakaba |
1.1 |
package Message::Charset::Info; |
2 |
|
|
use strict; |
3 |
wakaba |
1.4 |
our $VERSION=do{my @r=(q$Revision: 1.3 $=~/\d+/g);sprintf "%d."."%02d" x $#r,@r}; |
4 |
wakaba |
1.1 |
|
5 |
|
|
sub UNREGISTERED_CHARSET_NAME () { 0b1 } |
6 |
wakaba |
1.4 |
## Names for non-standard encodings/implementations for Perl encodings |
7 |
wakaba |
1.1 |
sub REGISTERED_CHARSET_NAME () { 0b10 } |
8 |
wakaba |
1.4 |
## Names for standard encodings for Perl encodings |
9 |
|
|
sub PRIMARY_CHARSET_NAME () { 0b100 } |
10 |
wakaba |
1.1 |
## "Name:" field for IANA names |
11 |
wakaba |
1.4 |
## Canonical name for Perl encodings |
12 |
|
|
sub PREFERRED_CHARSET_NAME () { 0b1000 } |
13 |
wakaba |
1.1 |
## "preferred MIME name" for IANA names |
14 |
|
|
|
15 |
wakaba |
1.4 |
sub FALLBACK_ENCODING_IMPL () { 0b10000 } |
16 |
|
|
## For Perl encodings: Not a name of the encoding, the encoding |
17 |
|
|
## for the name might be useful as a fallback when the correct |
18 |
|
|
## encoding is not supported. |
19 |
|
|
sub NONCONFORMING_ENCODING_IMPL () { FALLBACK_ENCODING_IMPL } |
20 |
|
|
## For Perl encodings: Not a conforming implementation of the encoding, |
21 |
|
|
## though it seems that the intention was to implement that encoding. |
22 |
|
|
sub ERROR_REPORTING_ENCODING_IMPL () { 0b100000 } |
23 |
|
|
## For Perl encodings: Support error reporting via |manakai_onerror| |
24 |
|
|
## handler. |
25 |
|
|
|
26 |
wakaba |
1.2 |
## iana_status |
27 |
|
|
sub STATUS_COMMON () { 0b1 } |
28 |
|
|
sub STATUS_LIMITED_USE () { 0b10 } |
29 |
|
|
sub STATUS_OBSOLETE () { 0b100 } |
30 |
|
|
|
31 |
wakaba |
1.1 |
## iana_names |
32 |
|
|
## is_html_ascii_superset: "superset of US-ASCII (specifically, ANSI_X3.4-1968) |
33 |
|
|
## for bytes in the range 0x09 - 0x0D, 0x20, 0x21, 0x22, 0x26, 0x27, |
34 |
|
|
## 0x2C - 0x3F, 0x41 - 0x5A, and 0x61 - 0x7A" [HTML5] |
35 |
|
|
## is_ebcdic_based |
36 |
|
|
|
37 |
|
|
## ISSUE: Shift_JIS is a superset of US-ASCII? ISO-2022-JP is? |
38 |
|
|
## ISSUE: 0x5F (_) should be added to the range? |
39 |
|
|
|
40 |
|
|
my $Charset; |
41 |
|
|
|
42 |
|
|
our $IANACharset; |
43 |
|
|
|
44 |
|
|
$Charset->{'us-ascii'} |
45 |
|
|
= $IANACharset->{'ansi_x3.4-1968'} |
46 |
|
|
= $IANACharset->{'iso-ir-6'} |
47 |
|
|
= $IANACharset->{'ansi_x3.4-1986'} |
48 |
|
|
= $IANACharset->{'iso_646.irv:1991'} |
49 |
|
|
= $IANACharset->{'ascii'} |
50 |
|
|
= $IANACharset->{'iso646-us'} |
51 |
|
|
= $IANACharset->{'us-ascii'} |
52 |
|
|
= $IANACharset->{'us'} |
53 |
|
|
= $IANACharset->{'ibm367'} |
54 |
|
|
= $IANACharset->{'cp367'} |
55 |
|
|
= $IANACharset->{'csascii'} |
56 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
57 |
wakaba |
1.1 |
iana_names => { |
58 |
wakaba |
1.4 |
'ansi_x3.4-1968' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
59 |
wakaba |
1.1 |
'iso-ir-6' => REGISTERED_CHARSET_NAME, |
60 |
|
|
'ansi_x3.4-1986' => REGISTERED_CHARSET_NAME, |
61 |
|
|
'iso_646.irv:1991' => REGISTERED_CHARSET_NAME, |
62 |
|
|
'ascii' => REGISTERED_CHARSET_NAME, |
63 |
|
|
'iso646-us' => REGISTERED_CHARSET_NAME, |
64 |
wakaba |
1.4 |
'us-ascii' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
65 |
wakaba |
1.1 |
'us' => REGISTERED_CHARSET_NAME, |
66 |
|
|
'ibm367' => REGISTERED_CHARSET_NAME, |
67 |
|
|
'cp367' => REGISTERED_CHARSET_NAME, |
68 |
|
|
'csascii' => REGISTERED_CHARSET_NAME, |
69 |
|
|
}, |
70 |
|
|
is_html_ascii_superset => 1, |
71 |
wakaba |
1.4 |
}); |
72 |
wakaba |
1.1 |
|
73 |
|
|
$Charset->{'iso-8859-1'} |
74 |
|
|
= $IANACharset->{'iso_8859-1:1987'} |
75 |
|
|
= $IANACharset->{'iso-ir-100'} |
76 |
|
|
= $IANACharset->{'iso_8859-1'} |
77 |
|
|
= $IANACharset->{'iso-8859-1'} |
78 |
|
|
= $IANACharset->{'latin1'} |
79 |
|
|
= $IANACharset->{'l1'} |
80 |
|
|
= $IANACharset->{'ibm819'} |
81 |
|
|
= $IANACharset->{'cp819'} |
82 |
|
|
= $IANACharset->{'csisolatin1'} |
83 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
84 |
wakaba |
1.1 |
iana_names => { |
85 |
wakaba |
1.4 |
'iso_8859-1:1987' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
86 |
wakaba |
1.1 |
'iso-ir-100' => REGISTERED_CHARSET_NAME, |
87 |
|
|
'iso_8859-1' => REGISTERED_CHARSET_NAME, |
88 |
wakaba |
1.4 |
'iso-8859-1' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
89 |
wakaba |
1.1 |
'latin1' => REGISTERED_CHARSET_NAME, |
90 |
|
|
'l1' => REGISTERED_CHARSET_NAME, |
91 |
|
|
'ibm819' => REGISTERED_CHARSET_NAME, |
92 |
|
|
'cp819' => REGISTERED_CHARSET_NAME, |
93 |
|
|
'csisolatin1' => REGISTERED_CHARSET_NAME, |
94 |
|
|
}, |
95 |
|
|
is_html_ascii_superset => 1, |
96 |
wakaba |
1.4 |
}); |
97 |
wakaba |
1.1 |
|
98 |
wakaba |
1.2 |
$Charset->{'iso-8859-2'} |
99 |
|
|
= $IANACharset->{'iso_8859-2:1987'} |
100 |
|
|
= $IANACharset->{'iso-ir-101'} |
101 |
|
|
= $IANACharset->{'iso_8859-2'} |
102 |
|
|
= $IANACharset->{'iso-8859-2'} |
103 |
|
|
= $IANACharset->{'latin2'} |
104 |
|
|
= $IANACharset->{'l2'} |
105 |
|
|
= $IANACharset->{'csisolatin2'} |
106 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
107 |
wakaba |
1.2 |
iana_names => { |
108 |
wakaba |
1.4 |
'iso_8859-2:1987' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
109 |
wakaba |
1.2 |
'iso-ir-101' => REGISTERED_CHARSET_NAME, |
110 |
|
|
'iso_8859-2' => REGISTERED_CHARSET_NAME, |
111 |
wakaba |
1.4 |
'iso-8859-2' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
112 |
wakaba |
1.2 |
'latin2' => REGISTERED_CHARSET_NAME, |
113 |
|
|
'l2' => REGISTERED_CHARSET_NAME, |
114 |
|
|
'csisolatin2' => REGISTERED_CHARSET_NAME, |
115 |
|
|
}, |
116 |
|
|
is_html_ascii_superset => 1, |
117 |
wakaba |
1.4 |
}); |
118 |
wakaba |
1.2 |
|
119 |
|
|
$Charset->{'iso-8859-3'} |
120 |
|
|
= $IANACharset->{'iso_8859-3:1988'} |
121 |
|
|
= $IANACharset->{'iso-ir-109'} |
122 |
|
|
= $IANACharset->{'iso_8859-3'} |
123 |
|
|
= $IANACharset->{'iso-8859-3'} |
124 |
|
|
= $IANACharset->{'latin3'} |
125 |
|
|
= $IANACharset->{'l3'} |
126 |
|
|
= $IANACharset->{'csisolatin3'} |
127 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
128 |
wakaba |
1.2 |
iana_names => { |
129 |
wakaba |
1.4 |
'iso_8859-3:1988' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
130 |
wakaba |
1.2 |
'iso-ir-109' => REGISTERED_CHARSET_NAME, |
131 |
|
|
'iso_8859-3' => REGISTERED_CHARSET_NAME, |
132 |
wakaba |
1.4 |
'iso-8859-3' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
133 |
wakaba |
1.2 |
'latin3' => REGISTERED_CHARSET_NAME, |
134 |
|
|
'l3' => REGISTERED_CHARSET_NAME, |
135 |
|
|
'csisolatin3' => REGISTERED_CHARSET_NAME, |
136 |
|
|
}, |
137 |
|
|
is_html_ascii_superset => 1, |
138 |
wakaba |
1.4 |
}); |
139 |
wakaba |
1.2 |
|
140 |
|
|
$Charset->{'iso-8859-4'} |
141 |
|
|
= $IANACharset->{'iso_8859-4:1988'} |
142 |
|
|
= $IANACharset->{'iso-ir-110'} |
143 |
|
|
= $IANACharset->{'iso_8859-4'} |
144 |
|
|
= $IANACharset->{'iso-8859-4'} |
145 |
|
|
= $IANACharset->{'latin4'} |
146 |
|
|
= $IANACharset->{'l4'} |
147 |
|
|
= $IANACharset->{'csisolatin4'} |
148 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
149 |
wakaba |
1.2 |
iana_names => { |
150 |
wakaba |
1.4 |
'iso_8859-4:1988' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
151 |
wakaba |
1.2 |
'iso-ir-110' => REGISTERED_CHARSET_NAME, |
152 |
|
|
'iso_8859-4' => REGISTERED_CHARSET_NAME, |
153 |
wakaba |
1.4 |
'iso-8859-4' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
154 |
wakaba |
1.2 |
'latin4' => REGISTERED_CHARSET_NAME, |
155 |
|
|
'l4' => REGISTERED_CHARSET_NAME, |
156 |
|
|
'csisolatin4' => REGISTERED_CHARSET_NAME, |
157 |
|
|
}, |
158 |
|
|
is_html_ascii_superset => 1, |
159 |
wakaba |
1.4 |
}); |
160 |
wakaba |
1.2 |
|
161 |
|
|
$Charset->{'iso-8859-5'} |
162 |
|
|
= $IANACharset->{'iso_8859-5:1988'} |
163 |
|
|
= $IANACharset->{'iso-ir-144'} |
164 |
|
|
= $IANACharset->{'iso_8859-5'} |
165 |
|
|
= $IANACharset->{'iso-8859-5'} |
166 |
|
|
= $IANACharset->{'cyrillic'} |
167 |
|
|
= $IANACharset->{'csisolatincyrillic'} |
168 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
169 |
wakaba |
1.2 |
iana_names => { |
170 |
wakaba |
1.4 |
'iso_8859-5:1988' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
171 |
wakaba |
1.2 |
'iso-ir-144' => REGISTERED_CHARSET_NAME, |
172 |
|
|
'iso_8859-5' => REGISTERED_CHARSET_NAME, |
173 |
wakaba |
1.4 |
'iso-8859-5' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
174 |
wakaba |
1.2 |
'cyrillic' => REGISTERED_CHARSET_NAME, |
175 |
|
|
'csisolatincyrillic' => REGISTERED_CHARSET_NAME, |
176 |
|
|
}, |
177 |
|
|
is_html_ascii_superset => 1, |
178 |
wakaba |
1.4 |
}); |
179 |
wakaba |
1.2 |
|
180 |
|
|
$Charset->{'iso-8859-6'} |
181 |
|
|
= $IANACharset->{'iso_8859-6:1987'} |
182 |
|
|
= $IANACharset->{'iso-ir-127'} |
183 |
|
|
= $IANACharset->{'iso_8859-6'} |
184 |
|
|
= $IANACharset->{'iso-8859-6'} |
185 |
|
|
= $IANACharset->{'ecma-114'} |
186 |
|
|
= $IANACharset->{'asmo-708'} |
187 |
|
|
= $IANACharset->{'arabic'} |
188 |
|
|
= $IANACharset->{'csisolatinarabic'} |
189 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
190 |
wakaba |
1.2 |
iana_names => { |
191 |
wakaba |
1.4 |
'iso_8859-6:1987' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
192 |
wakaba |
1.2 |
'iso-ir-127' => REGISTERED_CHARSET_NAME, |
193 |
|
|
'iso_8859-6' => REGISTERED_CHARSET_NAME, |
194 |
wakaba |
1.4 |
'iso-8859-6' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
195 |
wakaba |
1.2 |
'ecma-114' => REGISTERED_CHARSET_NAME, |
196 |
|
|
'asmo-708' => REGISTERED_CHARSET_NAME, |
197 |
|
|
'arabic' => REGISTERED_CHARSET_NAME, |
198 |
|
|
'csisolatinarabic' => REGISTERED_CHARSET_NAME, |
199 |
|
|
}, |
200 |
|
|
is_html_ascii_superset => 1, |
201 |
|
|
## NOTE: 3/0..3/9 have different semantics from U+0030..0039, |
202 |
|
|
## but have same character names (maybe). |
203 |
wakaba |
1.3 |
## NOTE: According to RFC 2046, charset left-hand half of "iso-8859-6" |
204 |
|
|
## is same as "us-ascii". |
205 |
wakaba |
1.4 |
}); |
206 |
wakaba |
1.2 |
|
207 |
|
|
$Charset->{'iso-8859-7'} |
208 |
|
|
= $IANACharset->{'iso_8859-7:1987'} |
209 |
|
|
= $IANACharset->{'iso-ir-126'} |
210 |
|
|
= $IANACharset->{'iso_8859-7'} |
211 |
|
|
= $IANACharset->{'iso-8859-7'} |
212 |
|
|
= $IANACharset->{'elot_928'} |
213 |
|
|
= $IANACharset->{'ecma-118'} |
214 |
|
|
= $IANACharset->{'greek'} |
215 |
|
|
= $IANACharset->{'greek8'} |
216 |
|
|
= $IANACharset->{'csisolatingreek'} |
217 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
218 |
wakaba |
1.2 |
iana_names => { |
219 |
wakaba |
1.4 |
'iso_8859-7:1987' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
220 |
wakaba |
1.2 |
'iso-ir-126' => REGISTERED_CHARSET_NAME, |
221 |
|
|
'iso_8859-7' => REGISTERED_CHARSET_NAME, |
222 |
wakaba |
1.4 |
'iso-8859-7' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
223 |
wakaba |
1.2 |
'elot_928' => REGISTERED_CHARSET_NAME, |
224 |
|
|
'ecma-118' => REGISTERED_CHARSET_NAME, |
225 |
|
|
'greek' => REGISTERED_CHARSET_NAME, |
226 |
|
|
'greek8' => REGISTERED_CHARSET_NAME, |
227 |
|
|
'csisolatingreek' => REGISTERED_CHARSET_NAME, |
228 |
|
|
}, |
229 |
|
|
is_html_ascii_superset => 1, |
230 |
wakaba |
1.4 |
}); |
231 |
wakaba |
1.2 |
|
232 |
|
|
$Charset->{'iso-8859-8'} |
233 |
|
|
= $IANACharset->{'iso_8859-8:1988'} |
234 |
|
|
= $IANACharset->{'iso-ir-138'} |
235 |
|
|
= $IANACharset->{'iso_8859-8'} |
236 |
|
|
= $IANACharset->{'iso-8859-8'} |
237 |
|
|
= $IANACharset->{'hebrew'} |
238 |
|
|
= $IANACharset->{'csisolatinhebrew'} |
239 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
240 |
wakaba |
1.2 |
iana_names => { |
241 |
wakaba |
1.4 |
'iso_8859-8:1988' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
242 |
wakaba |
1.2 |
'iso-ir-138' => REGISTERED_CHARSET_NAME, |
243 |
|
|
'iso_8859-8' => REGISTERED_CHARSET_NAME, |
244 |
wakaba |
1.4 |
'iso-8859-8' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
245 |
wakaba |
1.2 |
'hebrew' => REGISTERED_CHARSET_NAME, |
246 |
|
|
'csisolatinhebrew' => REGISTERED_CHARSET_NAME, |
247 |
|
|
}, |
248 |
|
|
is_html_ascii_superset => 1, |
249 |
wakaba |
1.4 |
}); |
250 |
wakaba |
1.2 |
|
251 |
|
|
$Charset->{'iso-8859-9'} |
252 |
|
|
= $IANACharset->{'iso_8859-9:1989'} |
253 |
|
|
= $IANACharset->{'iso-ir-148'} |
254 |
|
|
= $IANACharset->{'iso_8859-9'} |
255 |
|
|
= $IANACharset->{'iso-8859-9'} |
256 |
|
|
= $IANACharset->{'latin5'} |
257 |
|
|
= $IANACharset->{'l5'} |
258 |
|
|
= $IANACharset->{'csisolatin5'} |
259 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
260 |
wakaba |
1.2 |
iana_names => { |
261 |
wakaba |
1.4 |
'iso_8859-9:1989' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
262 |
wakaba |
1.2 |
'iso-ir-148' => REGISTERED_CHARSET_NAME, |
263 |
|
|
'iso_8859-9' => REGISTERED_CHARSET_NAME, |
264 |
wakaba |
1.4 |
'iso-8859-9' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
265 |
wakaba |
1.2 |
'latin5' => REGISTERED_CHARSET_NAME, |
266 |
|
|
'l5' => REGISTERED_CHARSET_NAME, |
267 |
|
|
'csisolatin5' => REGISTERED_CHARSET_NAME, |
268 |
|
|
}, |
269 |
|
|
is_html_ascii_superset => 1, |
270 |
wakaba |
1.4 |
}); |
271 |
wakaba |
1.2 |
|
272 |
|
|
$Charset->{'iso-8859-10'} |
273 |
|
|
= $IANACharset->{'iso-8859-10'} |
274 |
|
|
= $IANACharset->{'iso-ir-157'} |
275 |
|
|
= $IANACharset->{'l6'} |
276 |
|
|
= $IANACharset->{'iso_8859-10:1992'} |
277 |
|
|
= $IANACharset->{'csisolatin6'} |
278 |
|
|
= $IANACharset->{'latin6'} |
279 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
280 |
wakaba |
1.2 |
iana_names => { |
281 |
wakaba |
1.4 |
'iso-8859-10' => PRIMARY_CHARSET_NAME | PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
282 |
wakaba |
1.2 |
'iso-ir-157' => REGISTERED_CHARSET_NAME, |
283 |
|
|
'l6' => REGISTERED_CHARSET_NAME, |
284 |
|
|
'iso_8859-10:1992' => REGISTERED_CHARSET_NAME, |
285 |
|
|
'csisolatin6' => REGISTERED_CHARSET_NAME, |
286 |
|
|
'latin6' => REGISTERED_CHARSET_NAME, |
287 |
|
|
}, |
288 |
|
|
is_html_ascii_superset => 1, |
289 |
wakaba |
1.4 |
}); |
290 |
wakaba |
1.2 |
|
291 |
|
|
$Charset->{'iso_6937-2-add'} |
292 |
|
|
= $IANACharset->{'iso_6937-2-add'} |
293 |
|
|
= $IANACharset->{'iso-ir-142'} |
294 |
|
|
= $IANACharset->{'csisotextcomm'} |
295 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
296 |
wakaba |
1.2 |
iana_names => { |
297 |
wakaba |
1.4 |
'iso_6937-2-add' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
298 |
wakaba |
1.2 |
'iso-ir-142' => REGISTERED_CHARSET_NAME, |
299 |
|
|
'csisotextcomm' => REGISTERED_CHARSET_NAME, |
300 |
|
|
}, |
301 |
|
|
is_html_ascii_superset => 1, |
302 |
wakaba |
1.4 |
}); |
303 |
wakaba |
1.2 |
|
304 |
|
|
$Charset->{'jis_x0201'} |
305 |
|
|
= $IANACharset->{'jis_x0201'} |
306 |
|
|
= $IANACharset->{'x0201'} |
307 |
|
|
= $IANACharset->{'cshalfwidthkatakana'} |
308 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
309 |
wakaba |
1.2 |
iana_names => { |
310 |
wakaba |
1.4 |
'jis_x0201' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
311 |
wakaba |
1.2 |
'x0201' => REGISTERED_CHARSET_NAME, |
312 |
|
|
'cshalfwidthkatakana' => REGISTERED_CHARSET_NAME, |
313 |
|
|
}, |
314 |
|
|
is_html_ascii_superset => 1, |
315 |
wakaba |
1.4 |
}); |
316 |
wakaba |
1.2 |
|
317 |
|
|
$Charset->{'jis_encoding'} |
318 |
|
|
= $IANACharset->{'jis_encoding'} |
319 |
|
|
= $IANACharset->{'csjisencoding'} |
320 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
321 |
wakaba |
1.2 |
iana_names => { |
322 |
wakaba |
1.4 |
'jis_encoding' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
323 |
wakaba |
1.2 |
'csjisencoding' => REGISTERED_CHARSET_NAME, |
324 |
|
|
}, |
325 |
|
|
## NOTE: What is this? |
326 |
wakaba |
1.4 |
}); |
327 |
wakaba |
1.1 |
|
328 |
|
|
$Charset->{'shift_jis'} |
329 |
|
|
= $IANACharset->{'shift_jis'} |
330 |
|
|
= $IANACharset->{'ms_kanji'} |
331 |
|
|
= $IANACharset->{'csshiftjis'} |
332 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
333 |
wakaba |
1.1 |
iana_names => { |
334 |
wakaba |
1.4 |
'shift_jis' => PREFERRED_CHARSET_NAME | PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
335 |
wakaba |
1.1 |
'ms_kanji' => REGISTERED_CHARSET_NAME, |
336 |
|
|
'csshiftjis' => REGISTERED_CHARSET_NAME, |
337 |
|
|
}, |
338 |
wakaba |
1.2 |
mime_text_suitable => 1, |
339 |
wakaba |
1.4 |
}); |
340 |
wakaba |
1.1 |
|
341 |
wakaba |
1.3 |
$Charset->{'x-sjis'} |
342 |
|
|
= $IANACharset->{'x-sjis'} |
343 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
344 |
wakaba |
1.3 |
iana_names => { |
345 |
|
|
'x-sjis' => UNREGISTERED_CHARSET_NAME, |
346 |
|
|
}, |
347 |
|
|
mime_text_suitable => 1, |
348 |
wakaba |
1.4 |
}); |
349 |
wakaba |
1.3 |
|
350 |
wakaba |
1.1 |
$Charset->{'euc-jp'} |
351 |
|
|
= $IANACharset->{'extended_unix_code_packed_format_for_japanese'} |
352 |
|
|
= $IANACharset->{'cseucpkdfmtjapanese'} |
353 |
|
|
= $IANACharset->{'euc-jp'} |
354 |
wakaba |
1.3 |
= $IANACharset->{'x-euc-jp'} |
355 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
356 |
wakaba |
1.1 |
iana_names => { |
357 |
wakaba |
1.4 |
'extended_unix_code_packed_format_for_japanese' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
358 |
wakaba |
1.1 |
'cseucpkdfmtjapanese' => REGISTERED_CHARSET_NAME, |
359 |
wakaba |
1.4 |
'euc-jp' => PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
360 |
wakaba |
1.1 |
}, |
361 |
|
|
is_html_ascii_superset => 1, |
362 |
wakaba |
1.3 |
mime_text_suitable => 1, |
363 |
wakaba |
1.4 |
}); |
364 |
wakaba |
1.3 |
|
365 |
|
|
$Charset->{'x-euc-jp'} |
366 |
|
|
= $IANACharset->{'x-euc-jp'} |
367 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
368 |
wakaba |
1.3 |
iana_names => { |
369 |
|
|
'x-euc-jp' => UNREGISTERED_CHARSET_NAME, |
370 |
|
|
}, |
371 |
|
|
is_html_ascii_superset => 1, |
372 |
|
|
mime_text_suitable => 1, |
373 |
wakaba |
1.4 |
}); |
374 |
wakaba |
1.1 |
|
375 |
wakaba |
1.2 |
$Charset->{'extended_unix_code_fixed_width_for_japanese'} |
376 |
|
|
= $IANACharset->{'extended_unix_code_fixed_width_for_japanese'} |
377 |
|
|
= $IANACharset->{'cseucfixwidjapanese'} |
378 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
379 |
wakaba |
1.2 |
iana_names => { |
380 |
wakaba |
1.4 |
'extended_unix_code_fixed_width_for_japanese' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
381 |
wakaba |
1.2 |
'cseucfixwidjapanese' => REGISTERED_CHARSET_NAME, |
382 |
|
|
}, |
383 |
wakaba |
1.4 |
}); |
384 |
wakaba |
1.2 |
|
385 |
wakaba |
1.1 |
## TODO: ... |
386 |
|
|
|
387 |
wakaba |
1.2 |
$Charset->{'euc-kr'} |
388 |
|
|
= $IANACharset->{'euc-kr'} |
389 |
|
|
= $IANACharset->{'cseuckr'} |
390 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
391 |
wakaba |
1.2 |
iana_names => { |
392 |
wakaba |
1.4 |
'euc-kr' => PRIMARY_CHARSET_NAME | PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
393 |
wakaba |
1.2 |
'cseuckr' => REGISTERED_CHARSET_NAME, |
394 |
|
|
}, |
395 |
|
|
is_html_ascii_superset => 1, |
396 |
wakaba |
1.4 |
}); |
397 |
wakaba |
1.2 |
|
398 |
wakaba |
1.1 |
$Charset->{'iso-2022-jp'} |
399 |
|
|
= $IANACharset->{'iso-2022-jp'} |
400 |
|
|
= $IANACharset->{'csiso2022jp'} |
401 |
wakaba |
1.3 |
= $IANACharset->{'iso2022jp'} |
402 |
|
|
= $IANACharset->{'junet-code'} |
403 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
404 |
wakaba |
1.1 |
iana_names => { |
405 |
wakaba |
1.4 |
'iso-2022-jp' => PREFERRED_CHARSET_NAME | PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
406 |
wakaba |
1.1 |
'csiso2022jp' => REGISTERED_CHARSET_NAME, |
407 |
wakaba |
1.3 |
'iso2022jp' => UNREGISTERED_CHARSET_NAME, |
408 |
|
|
'junet-code' => UNREGISTERED_CHARSET_NAME, |
409 |
wakaba |
1.1 |
}, |
410 |
wakaba |
1.2 |
mime_text_suitable => 1, |
411 |
wakaba |
1.4 |
}); |
412 |
wakaba |
1.2 |
|
413 |
|
|
$Charset->{'iso-2022-jp-2'} |
414 |
|
|
= $IANACharset->{'iso-2022-jp-2'} |
415 |
|
|
= $IANACharset->{'csiso2022jp2'} |
416 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
417 |
wakaba |
1.2 |
iana_names => { |
418 |
wakaba |
1.4 |
'iso-2022-jp-2' => PREFERRED_CHARSET_NAME | PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
419 |
wakaba |
1.2 |
'csiso2022jp2' => REGISTERED_CHARSET_NAME, |
420 |
|
|
}, |
421 |
|
|
mime_text_suitable => 1, |
422 |
wakaba |
1.4 |
}); |
423 |
wakaba |
1.1 |
|
424 |
|
|
## TODO: ... |
425 |
|
|
|
426 |
|
|
$Charset->{'utf-8'} |
427 |
|
|
= $IANACharset->{'utf-8'} |
428 |
wakaba |
1.3 |
= $IANACharset->{'x-utf-8'} |
429 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
430 |
wakaba |
1.1 |
iana_names => { |
431 |
wakaba |
1.4 |
'utf-8' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
432 |
wakaba |
1.3 |
'x-utf-8' => UNREGISTERED_CHARSET_NAME, |
433 |
wakaba |
1.1 |
}, |
434 |
|
|
is_html_ascii_superset => 1, |
435 |
wakaba |
1.3 |
mime_text_suitable => 1, |
436 |
wakaba |
1.4 |
}); |
437 |
wakaba |
1.3 |
|
438 |
|
|
$Charset->{'utf-8n'} |
439 |
|
|
= $IANACharset->{'utf-8n'} |
440 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
441 |
wakaba |
1.3 |
iana_names => { |
442 |
|
|
'utf-8n' => UNREGISTERED_CHARSET_NAME, |
443 |
|
|
}, |
444 |
|
|
is_html_ascii_superset => 1, |
445 |
|
|
mime_text_suitable => 1, |
446 |
wakaba |
1.4 |
}); |
447 |
wakaba |
1.1 |
|
448 |
|
|
## TODO: ... |
449 |
|
|
|
450 |
wakaba |
1.2 |
$Charset->{'gbk'} |
451 |
|
|
= $IANACharset->{'gbk'} |
452 |
|
|
= $IANACharset->{'cp936'} |
453 |
|
|
= $IANACharset->{'ms936'} |
454 |
|
|
= $IANACharset->{'windows-936'} |
455 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
456 |
wakaba |
1.2 |
iana_names => { |
457 |
wakaba |
1.4 |
'gbk' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
458 |
wakaba |
1.2 |
'cp936' => REGISTERED_CHARSET_NAME, |
459 |
|
|
'ms936' => REGISTERED_CHARSET_NAME, |
460 |
|
|
'windows-936' => REGISTERED_CHARSET_NAME, |
461 |
|
|
}, |
462 |
|
|
iana_status => STATUS_COMMON | STATUS_OBSOLETE, |
463 |
|
|
mime_text_suitable => 1, |
464 |
wakaba |
1.4 |
}); |
465 |
wakaba |
1.2 |
|
466 |
|
|
$Charset->{'gb18030'} |
467 |
|
|
= $IANACharset->{'gb18030'} |
468 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
469 |
wakaba |
1.2 |
iana_names => { |
470 |
wakaba |
1.4 |
'gb18030' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
471 |
wakaba |
1.2 |
}, |
472 |
|
|
iana_status => STATUS_COMMON, |
473 |
|
|
mime_text_suitable => 1, |
474 |
wakaba |
1.4 |
}); |
475 |
wakaba |
1.2 |
|
476 |
|
|
## TODO: ... |
477 |
|
|
|
478 |
wakaba |
1.1 |
$Charset->{'utf-16be'} |
479 |
|
|
= $IANACharset->{'utf-16be'} |
480 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
481 |
wakaba |
1.1 |
iana_names => { |
482 |
wakaba |
1.4 |
'utf-16be' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
483 |
wakaba |
1.1 |
}, |
484 |
wakaba |
1.4 |
}); |
485 |
wakaba |
1.1 |
|
486 |
|
|
$Charset->{'utf-16le'} |
487 |
|
|
= $IANACharset->{'utf-16le'} |
488 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
489 |
wakaba |
1.1 |
iana_names => { |
490 |
wakaba |
1.4 |
'utf-16le' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
491 |
wakaba |
1.1 |
}, |
492 |
wakaba |
1.4 |
}); |
493 |
wakaba |
1.1 |
|
494 |
|
|
$Charset->{'utf-16'} |
495 |
|
|
= $IANACharset->{'utf-16'} |
496 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
497 |
wakaba |
1.1 |
iana_names => { |
498 |
wakaba |
1.4 |
'utf-16' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
499 |
wakaba |
1.1 |
}, |
500 |
wakaba |
1.4 |
}); |
501 |
wakaba |
1.1 |
|
502 |
|
|
## TODO: ... |
503 |
|
|
|
504 |
wakaba |
1.2 |
$Charset->{'windows-31j'} |
505 |
|
|
= $IANACharset->{'windows-31j'} |
506 |
|
|
= $IANACharset->{'cswindows31j'} |
507 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
508 |
wakaba |
1.2 |
iana_names => { |
509 |
wakaba |
1.4 |
'windows-31j' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
510 |
wakaba |
1.2 |
'cswindows31j' => REGISTERED_CHARSET_NAME, |
511 |
|
|
}, |
512 |
|
|
iana_status => STATUS_LIMITED_USE, # maybe |
513 |
|
|
mime_text_suitable => 1, |
514 |
wakaba |
1.4 |
}); |
515 |
wakaba |
1.2 |
|
516 |
|
|
$Charset->{'gb2312'} |
517 |
|
|
= $IANACharset->{'gb2312'} |
518 |
|
|
= $IANACharset->{'csgb2312'} |
519 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
520 |
wakaba |
1.2 |
iana_names => { |
521 |
wakaba |
1.4 |
'gb2312' => PRIMARY_CHARSET_NAME | PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
522 |
wakaba |
1.2 |
'csgb2312' => REGISTERED_CHARSET_NAME, |
523 |
|
|
}, |
524 |
|
|
is_html_ascii_superset => 1, |
525 |
|
|
mime_text_suitable => 1, |
526 |
wakaba |
1.4 |
}); |
527 |
wakaba |
1.2 |
|
528 |
|
|
$Charset->{'big5'} |
529 |
|
|
= $IANACharset->{'big5'} |
530 |
|
|
= $IANACharset->{'csbig5'} |
531 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
532 |
wakaba |
1.2 |
iana_names => { |
533 |
wakaba |
1.4 |
'big5' => PRIMARY_CHARSET_NAME | PREFERRED_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
534 |
wakaba |
1.2 |
'csbig5' => REGISTERED_CHARSET_NAME, |
535 |
|
|
}, |
536 |
|
|
mime_text_suitable => 1, |
537 |
wakaba |
1.4 |
}); |
538 |
wakaba |
1.2 |
|
539 |
|
|
## TODO: ... |
540 |
|
|
|
541 |
|
|
$Charset->{'big5-hkscs'} |
542 |
|
|
= $IANACharset->{'big5-hkscs'} |
543 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
544 |
wakaba |
1.2 |
iana_names => { |
545 |
wakaba |
1.4 |
'big5-hkscs' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
546 |
wakaba |
1.2 |
}, |
547 |
|
|
mime_text_suitable => 1, |
548 |
wakaba |
1.4 |
}); |
549 |
wakaba |
1.2 |
|
550 |
|
|
## TODO: ... |
551 |
|
|
|
552 |
wakaba |
1.1 |
$Charset->{'windows-1252'} |
553 |
|
|
= $IANACharset->{'windows-1252'} |
554 |
wakaba |
1.4 |
= __PACKAGE__->new ({ |
555 |
wakaba |
1.1 |
iana_names => { |
556 |
wakaba |
1.4 |
'windows-1252' => PRIMARY_CHARSET_NAME | REGISTERED_CHARSET_NAME, |
557 |
wakaba |
1.1 |
}, |
558 |
|
|
is_html_ascii_superset => 1, |
559 |
wakaba |
1.4 |
}); |
560 |
wakaba |
1.1 |
|
561 |
|
|
## TODO: ... |
562 |
|
|
|
563 |
wakaba |
1.4 |
sub new ($$) { |
564 |
|
|
return bless $_[1], $_[0]; |
565 |
|
|
} # new |
566 |
|
|
|
567 |
|
|
## NOTE: A class method |
568 |
|
|
sub get_by_iana_name ($$) { |
569 |
|
|
my $name = $_[1]; |
570 |
|
|
$name =~ tr/A-Z/a-z/; ## ASCII case-insensitive |
571 |
|
|
unless ($IANACharset->{$name}) { |
572 |
|
|
$IANACharset->{$name} = __PACKAGE__->new ({ |
573 |
|
|
iana_names => { |
574 |
|
|
$name => UNREGISTERED_CHARSET_NAME, |
575 |
|
|
}, |
576 |
|
|
}); |
577 |
|
|
} |
578 |
|
|
return $IANACharset->{$name}; |
579 |
|
|
} # get_by_iana_name |
580 |
|
|
|
581 |
|
|
sub get_perl_encoding ($;%) { |
582 |
|
|
my ($self, %opt) = @_; |
583 |
|
|
|
584 |
|
|
require Encode; |
585 |
|
|
|
586 |
|
|
if ($opt{allow_error_reporting}) { |
587 |
|
|
for my $perl_name (keys %{$self->{perl_names} or {}}) { |
588 |
|
|
my $perl_status = $self->{perl_names}->{$perl_name}; |
589 |
|
|
next unless $perl_status & ERROR_REPORTING_ENCODING_IMPL; |
590 |
|
|
next unless $perl_status & FALLBACK_ENCODING_IMPL; |
591 |
|
|
|
592 |
|
|
my $e = Encode::find_encoding ($perl_name); |
593 |
|
|
if ($e) { |
594 |
|
|
return ($e, $perl_status); |
595 |
|
|
} |
596 |
|
|
} |
597 |
|
|
} |
598 |
|
|
|
599 |
|
|
for my $perl_name (keys %{$self->{perl_names} or {}}) { |
600 |
|
|
my $perl_status = $self->{perl_names}->{$perl_name}; |
601 |
|
|
next if $perl_status & ERROR_REPORTING_ENCODING_IMPL; |
602 |
|
|
next if $perl_status & FALLBACK_ENCODING_IMPL; |
603 |
|
|
|
604 |
|
|
my $e = Encode::find_encoding ($perl_name); |
605 |
|
|
if ($e) { |
606 |
|
|
return ($e, $perl_status); |
607 |
|
|
} |
608 |
|
|
} |
609 |
|
|
|
610 |
|
|
if ($opt{allow_fallback}) { |
611 |
|
|
for my $perl_name (keys %{$self->{perl_names} or {}}) { |
612 |
|
|
my $perl_status = $self->{perl_names}->{$perl_name}; |
613 |
|
|
next unless $perl_status & FALLBACK_ENCODING_IMPL; |
614 |
|
|
|
615 |
|
|
my $e = Encode::find_encoding ($perl_name); |
616 |
|
|
if ($e) { |
617 |
|
|
return ($e, $perl_status); |
618 |
|
|
} |
619 |
|
|
} |
620 |
|
|
|
621 |
|
|
for my $iana_name (keys %{$self->{iana_names} or {}}) { |
622 |
|
|
my $e = Encode::find_encoding ($iana_name); |
623 |
|
|
if ($e) { |
624 |
|
|
return ($e, FALLBACK_ENCODING_IMPL); |
625 |
|
|
} |
626 |
|
|
} |
627 |
|
|
} |
628 |
|
|
|
629 |
|
|
return (undef, 0); |
630 |
|
|
} # get_perl_encoding |
631 |
|
|
|
632 |
|
|
sub get_iana_name ($) { |
633 |
|
|
my $self = shift; |
634 |
|
|
|
635 |
|
|
my $primary; |
636 |
|
|
my $other; |
637 |
|
|
for my $iana_name (keys %{$self->{iana_names} or {}}) { |
638 |
|
|
my $name_status = $self->{iana_names}->{$iana_name}; |
639 |
|
|
if ($name_status & PREFERRED_CHARSET_NAME) { |
640 |
|
|
return $iana_name; |
641 |
|
|
} elsif ($name_status & PRIMARY_CHARSET_NAME) { |
642 |
|
|
$primary = $iana_name; |
643 |
|
|
} elsif ($name_status & REGISTERED_CHARSET_NAME) { |
644 |
|
|
$other = $iana_name; |
645 |
|
|
} else { |
646 |
|
|
$other ||= $iana_name; |
647 |
|
|
} |
648 |
|
|
} |
649 |
|
|
|
650 |
|
|
return $primary || $other; |
651 |
|
|
} # get_iana_name |
652 |
|
|
|
653 |
|
|
## NOTE: A non-method function |
654 |
wakaba |
1.3 |
sub is_syntactically_valid_iana_charset_name ($) { |
655 |
wakaba |
1.1 |
my $name = shift; |
656 |
|
|
return $name =~ /\A[\x20-\x7E]{1,40}\z/; |
657 |
|
|
} # is_suntactically_valid_iana_charset_name |
658 |
|
|
|
659 |
|
|
1; |
660 |
wakaba |
1.4 |
## $Date: 2007/12/22 06:29:32 $ |
661 |
wakaba |
1.1 |
|