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