/[suikacvs]/markup/html/whatpm/Whatpm/Charset/DecodeHandle.pm
Suika

Contents of /markup/html/whatpm/Whatpm/Charset/DecodeHandle.pm

Parent Directory Parent Directory | Revision Log Revision Log

Revision 1.3 - (hide annotations) (download)
Sat May 17 12:29:24 2008 UTC (16 years, 5 months ago) by wakaba
Branch: MAIN
Changes since 1.2: +40 -18 lines 
++ whatpm/Whatpm/ChangeLog	17 May 2008 12:28:47 -0000
	* HTML.pm.src (parse_byte_string): Use streaming decoder
	rather than converting the whole byte string and then parsing.
	Propagate errors in character encoding layer.
	(get_next_token): Precise error reporting for |bare stago| error.

2008-05-17  Wakaba  <wakaba@suika.fam.cx>

++ whatpm/Whatpm/Charset/ChangeLog	17 May 2008 12:29:09 -0000
2008-05-17  Wakaba  <wakaba@suika.fam.cx>

	* DecodeHandle.pm (ByteBuffer): New class.
1 wakaba 1.1 package Whatpm::Charset::DecodeHandle;
2     use strict;
3    
4     my $XML_AUTO_CHARSET = q<http://suika.fam.cx/www/2006/03/xml-entity/>;
5     my $IANA_CHARSET = q<urn:x-suika-fam-cx:charset:>;
6     my $PERL_CHARSET = q<http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.>;
7     my $XML_CHARSET = q<http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.>;
8    
9     ## ->create_decode_handle ($charset_uri, $byte_stream, $onerror)
10     sub create_decode_handle ($$$;$) {
11     my $csdef = $Whatpm::Charset::CharsetDef->{$_[1]};
12     my $obj = {
13     character_queue => [],
14     filehandle => $_[2],
15     charset => $_[1],
16     byte_buffer => '',
17     onerror => $_[3] || sub {},
18     };
19     if ($csdef->{uri}->{$XML_AUTO_CHARSET} or
20     $obj->{charset} eq $XML_AUTO_CHARSET) {
21     my $b = ''; # UTF-8 w/o BOM
22     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
23 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
24 wakaba 1.1 if (read $obj->{filehandle}, $b, 256) {
25     no warnings "substr";
26     no warnings "uninitialized";
27     if (substr ($b, 0, 1) eq "<") {
28     if (substr ($b, 1, 1) eq "?") { # ASCII8
29     if ($b =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
30     encoding\s*=\s*["']([^"']*)/x) {
31 wakaba 1.2 $obj->{input_encoding} = $1;
32 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
33     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
34     if (not $csdef->{ascii8} or $csdef->{bom_required}) {
35     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
36     charset_uri => $uri,
37     charset_name => $obj->{input_encoding});
38     }
39     } else {
40     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
41 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
42 wakaba 1.1 }
43     if (defined $csdef->{no_bom_variant}) {
44     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant}};
45     }
46     } elsif (substr ($b, 1, 1) eq "\x00") {
47     if (substr ($b, 2, 2) eq "?\x00") { # ASCII16LE
48     my $c = $b; $c =~ tr/\x00//d;
49     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
50     encoding\s*=\s*["']([^"']*)/x) {
51 wakaba 1.2 $obj->{input_encoding} = $1;
52 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
53     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
54     if (not $csdef->{ascii16} or $csdef->{ascii16be} or
55     $csdef->{bom_required}) {
56     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
57     charset_uri => $uri,
58     charset_name => $obj->{input_encoding});
59     }
60     } else {
61     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
62 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
63 wakaba 1.1 }
64     if (defined $csdef->{no_bom_variant16le}) {
65     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant16le}};
66     }
67     } elsif (substr ($b, 2, 2) eq "\x00\x00") { # ASCII32Endian4321
68     my $c = $b; $c =~ tr/\x00//d;
69     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
70     encoding\s*=\s*["']([^"']*)/x) {
71 wakaba 1.2 $obj->{input_encoding} = $1;
72 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
73     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
74     if (not $csdef->{ascii32} or
75     $csdef->{ascii32endian1234} or
76     $csdef->{ascii32endian2143} or
77     $csdef->{ascii32endian3412} or
78     $csdef->{bom_required}) {
79     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
80     charset_uri => $uri,
81     charset_name => $obj->{input_encoding});
82     }
83     } else {
84     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
85 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
86 wakaba 1.1 }
87     if (defined $csdef->{no_bom_variant32endian4321}) {
88     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian4321}};
89     }
90     }
91     }
92     } elsif (substr ($b, 0, 3) eq "\xEF\xBB\xBF") { # UTF8
93     $obj->{has_bom} = 1;
94     substr ($b, 0, 3) = '';
95     my $c = $b;
96     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
97     encoding\s*=\s*["']([^"']*)/x) {
98 wakaba 1.2 $obj->{input_encoding} = $1;
99 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
100     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
101     if (not $csdef->{utf8_encoding_scheme} or
102     not $csdef->{bom_allowed}) {
103     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
104     charset_uri => $uri,
105     charset_name => $obj->{input_encoding});
106     }
107     } else {
108     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
109 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
110 wakaba 1.1 }
111     if (defined $csdef->{no_bom_variant}) {
112     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant}};
113     }
114     } elsif (substr ($b, 0, 2) eq "\x00<") {
115     if (substr ($b, 2, 2) eq "\x00?") { # ASCII16BE
116     my $c = $b; $c =~ tr/\x00//d;
117     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
118     encoding\s*=\s*["']([^"']*)/x) {
119 wakaba 1.2 $obj->{input_encoding} = $1;
120 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
121     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
122     if (not $csdef->{ascii16} or $csdef->{ascii16le} or
123     $csdef->{bom_required}) {
124     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
125     charset_uri => $uri,
126     charset_name => $obj->{input_encoding});
127     }
128     } else {
129     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
130 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
131 wakaba 1.1 }
132     if (defined $csdef->{no_bom_variant16be}) {
133     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant16be}};
134     }
135     } elsif (substr ($b, 2, 2) eq "\x00\x00") { # ASCII32Endian3412
136     my $c = $b; $c =~ tr/\x00//d;
137     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
138     encoding\s*=\s*["']([^"']*)/x) {
139 wakaba 1.2 $obj->{input_encoding} = $1;
140 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
141     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
142     if (not $csdef->{ascii32} or
143     $csdef->{ascii32endian1234} or
144     $csdef->{ascii32endian2143} or
145     $csdef->{ascii32endian4321} or
146     $csdef->{bom_required}) {
147     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
148     charset_uri => $uri,
149     charset_name => $obj->{input_encoding});
150     }
151     } else {
152     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
153 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
154 wakaba 1.1 }
155     if (defined $csdef->{no_bom_variant32endian3412}) {
156     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian3412}};
157     }
158     }
159     } elsif (substr ($b, 0, 2) eq "\xFE\xFF") {
160     if (substr ($b, 2, 2) eq "\x00<") { # ASCII16BE
161     $obj->{has_bom} = 1;
162     substr ($b, 0, 2) = '';
163     my $c = $b; $c =~ tr/\x00//d;
164     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
165     encoding\s*=\s*["']([^"']*)/x) {
166 wakaba 1.2 $obj->{input_encoding} = $1;
167 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
168     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
169     if (not $csdef->{ascii16} or
170     $csdef->{ascii16le} or
171     not $csdef->{bom_allowed}) {
172     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
173     charset_uri => $uri,
174     charset_name => $obj->{input_encoding});
175     }
176     } else {
177     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16be'};
178 wakaba 1.2 $obj->{input_encoding} = 'UTF-16';
179 wakaba 1.1 }
180     if (defined $csdef->{no_bom_variant16be}) {
181     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant16be}};
182     }
183     } elsif (substr ($b, 2, 2) eq "\x00\x00") { # ASCII32Endian3412
184     $obj->{has_bom} = 1;
185     substr ($b, 0, 4) = '';
186     my $c = $b; $c =~ tr/\x00//d;
187     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
188     encoding\s*=\s*["']([^"']*)/x) {
189 wakaba 1.2 $obj->{input_encoding} = $1;
190 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
191     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
192     if (not $csdef->{ascii32} or
193     $csdef->{ascii32endian1234} or
194     $csdef->{ascii32endian2143} or
195     $csdef->{ascii32endian4321} or
196     not $csdef->{bom_allowed}) {
197     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
198     charset_uri => $uri,
199     charset_name => $obj->{input_encoding});
200     }
201     } else {
202     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16be'};
203 wakaba 1.2 $obj->{input_encoding} = 'UTF-16';
204 wakaba 1.1 $obj->{byte_buffer} .= "\x00\x00";
205     }
206     if (defined $csdef->{no_bom_variant32endian3412}) {
207     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian3412}};
208     }
209     } else {
210     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16be'};
211 wakaba 1.2 $obj->{input_encoding} = 'UTF-16';
212 wakaba 1.1 substr ($b, 0, 2) = '';
213     $obj->{has_bom} = 1;
214     }
215     } elsif (substr ($b, 0, 2) eq "\xFF\xFE") {
216     if (substr ($b, 2, 2) eq "<\x00") { # ASCII16LE
217     $obj->{has_bom} = 1;
218     substr ($b, 0, 2) = '';
219     my $c = $b; $c =~ tr/\x00//d;
220     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
221     encoding\s*=\s*["']([^"']*)/x) {
222 wakaba 1.2 $obj->{input_encoding} = $1;
223 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
224     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
225     if (not $csdef->{ascii16} or
226     $csdef->{ascii16be} or
227     not $csdef->{bom_allowed}) {
228     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
229     charset_uri => $uri,
230     charset_name => $obj->{input_encoding});
231     }
232     } else {
233     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16le'};
234 wakaba 1.2 $obj->{input_encoding} = 'UTF-16';
235 wakaba 1.1 }
236     if (defined $csdef->{no_bom_variant16le}) {
237     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant16le}};
238     }
239     } elsif (substr ($b, 2, 2) eq "\x00\x00") { # ASCII32Endian4321
240     $obj->{has_bom} = 1;
241     substr ($b, 0, 4) = '';
242     my $c = $b; $c =~ tr/\x00//d;
243     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
244     encoding\s*=\s*["']([^"']*)/x) {
245 wakaba 1.2 $obj->{input_encoding} = $1;
246 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
247     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
248     if (not $csdef->{ascii32} or
249     $csdef->{ascii32endian1234} or
250     $csdef->{ascii32endian2143} or
251     $csdef->{ascii32endian3412} or
252     not $csdef->{bom_allowed}) {
253     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
254     charset_uri => $uri,
255     charset_name => $obj->{input_encoding});
256     }
257     } else {
258     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16le'};
259 wakaba 1.2 $obj->{input_encoding} = 'UTF-16';
260 wakaba 1.1 $obj->{byte_buffer} .= "\x00\x00";
261     }
262     if (defined $csdef->{no_bom_variant32endian4321}) {
263     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian4321}};
264     }
265     } else {
266     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16le'};
267 wakaba 1.2 $obj->{input_encoding} = 'UTF-16';
268 wakaba 1.1 substr ($b, 0, 2) = '';
269     $obj->{has_bom} = 1;
270     }
271     } elsif (substr ($b, 0, 2) eq "\x00\x00") {
272     if (substr ($b, 2, 2) eq "\x00<") { # ASCII32Endian1234
273     my $c = $b; $c =~ tr/\x00//d;
274     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
275     encoding\s*=\s*["']([^"']*)/x) {
276 wakaba 1.2 $obj->{input_encoding} = $1;
277 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
278     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
279     if (not $csdef->{ascii32} or
280     $csdef->{ascii32endian2143} or
281     $csdef->{ascii32endian3412} or
282     $csdef->{ascii32endian4321} or
283     $csdef->{bom_required}) {
284     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
285     charset_uri => $uri,
286     charset_name => $obj->{input_encoding});
287     }
288     } else {
289     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
290 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
291 wakaba 1.1 }
292     if (defined $csdef->{no_bom_variant32endian1234}) {
293     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian1234}};
294     }
295     } elsif (substr ($b, 2, 2) eq "<\x00") { # ASCII32Endian2143
296     my $c = $b; $c =~ tr/\x00//d;
297     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
298     encoding\s*=\s*["']([^"']*)/x) {
299 wakaba 1.2 $obj->{input_encoding} = $1;
300 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
301     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
302     if (not $csdef->{ascii32} or
303     $csdef->{ascii32endian1234} or
304     $csdef->{ascii32endian3412} or
305     $csdef->{ascii32endian4321} or
306     $csdef->{bom_required}) {
307     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
308     charset_uri => $uri,
309     charset_name => $obj->{input_encoding});
310     }
311     } else {
312     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
313 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
314 wakaba 1.1 }
315     if (defined $csdef->{no_bom_variant32endian2143}) {
316     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian2143}};
317     }
318     } elsif (substr ($b, 2, 2) eq "\xFE\xFF") { # ASCII32Endian1234
319     $obj->{has_bom} = 1;
320     substr ($b, 0, 4) = '';
321     my $c = $b; $c =~ tr/\x00//d;
322     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
323     encoding\s*=\s*["']([^"']*)/x) {
324 wakaba 1.2 $obj->{input_encoding} = $1;
325 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
326     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
327     if (not $csdef->{ascii32} or
328     $csdef->{ascii32endian2143} or
329     $csdef->{ascii32endian3412} or
330     $csdef->{ascii32endian4321} or
331     $csdef->{bom_required}) {
332     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
333     charset_uri => $uri,
334     charset_name => $obj->{input_encoding});
335     }
336     } else {
337     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
338 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
339 wakaba 1.1 $obj->{has_bom} = 0;
340     $obj->{byte_buffer} .= "\x00\x00\xFE\xFF";
341     }
342     if (defined $csdef->{no_bom_variant32endian1234}) {
343     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian1234}};
344     }
345     } elsif (substr ($b, 2, 2) eq "\xFF\xFE") { # ASCII32Endian2143
346     $obj->{has_bom} = 1;
347     substr ($b, 0, 4) = '';
348     my $c = $b; $c =~ tr/\x00//d;
349     if ($c =~ /^<\?xml\s+(?:version\s*=\s*["'][^"']*["']\s*)?
350     encoding\s*=\s*["']([^"']*)/x) {
351 wakaba 1.2 $obj->{input_encoding} = $1;
352 wakaba 1.1 my $uri = name_to_uri (undef, 'xml', $obj->{input_encoding});
353     $csdef = $Whatpm::Charset::CharsetDef->{$uri};
354     if (not $csdef->{ascii32} or
355     $csdef->{ascii32endian1234} or
356     $csdef->{ascii32endian3412} or
357     $csdef->{ascii32endian4321} or
358     $csdef->{bom_required}) {
359     $obj->{onerror}->(undef, 'charset-name-mismatch-error',
360     charset_uri => $uri,
361     charset_name => $obj->{input_encoding});
362     }
363     } else {
364     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'};
365 wakaba 1.2 $obj->{input_encoding} = 'UTF-8';
366 wakaba 1.1 $obj->{has_bom} = 0;
367     $obj->{byte_buffer} .= "\x00\x00\xFF\xFE";
368     }
369     if (defined $csdef->{no_bom_variant32endian2143}) {
370     $csdef = $Whatpm::Charset::CharsetDef->{$csdef->{no_bom_variant32endian2143}};
371     }
372     }
373     # \x4C\x6F\xA7\x94 EBCDIC
374     } # buffer
375     $obj->{byte_buffer} .= $b;
376     } # read
377     } elsif ($csdef->{uri}->{$XML_CHARSET.'utf-8'}) {
378     ## BOM is optional.
379     my $b = '';
380     if (read $obj->{filehandle}, $b, 3) {
381     if ($b eq "\xEF\xBB\xBF") {
382     $obj->{has_bom} = 1;
383     } else {
384     $obj->{byte_buffer} .= $b;
385     }
386     }
387     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-8'}; # UTF-8 w/o BOM
388     } elsif ($csdef->{uri}->{$XML_CHARSET.'utf-16'}) {
389     ## BOM is mandated.
390     my $b = '';
391     if (read $obj->{filehandle}, $b, 2) {
392     if ($b eq "\xFE\xFF") {
393     $obj->{has_bom} = 1; # UTF-16BE w/o BOM
394     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16be'};
395     } elsif ($b eq "\xFF\xFE") {
396     $obj->{has_bom} = 1; # UTF-16LE w/o BOM
397     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16le'};
398     } else {
399     $obj->{onerror}->(undef, 'no-bom-error', charset_uri => $obj->{charset});
400     $obj->{has_bom} = 0;
401     $obj->{byte_buffer} .= $b; # UTF-16BE w/o BOM
402     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16be'};
403     }
404     } else {
405     $obj->{onerror}->(undef, 'no-bom-error', charset_uri => $obj->{charset});
406     $obj->{has_bom} = 0; # UTF-16BE w/o BOM
407     $csdef = $Whatpm::Charset::CharsetDef->{$PERL_CHARSET.'utf-16be'};
408     }
409     }
410    
411     if ($csdef->{uri}->{$XML_CHARSET.'iso-2022-jp'}) {
412     $obj->{state_2440} = 'gl-jis-1997-swapped';
413     $obj->{state_2442} = 'gl-jis-1997';
414     $obj->{state} = 'state_2842';
415     require Encode::GLJIS1997Swapped;
416     require Encode::GLJIS1997;
417     if (Encode::find_encoding ($obj->{state_2440}) and
418     Encode::find_encoding ($obj->{state_2442})) {
419     return bless $obj, 'Whatpm::Charset::DecodeHandle::ISO2022JP';
420     }
421     } elsif ($csdef->{uri}->{$IANA_CHARSET.'iso-2022-jp'}) {
422     $obj->{state_2440} = 'gl-jis-1978';
423     $obj->{state_2442} = 'gl-jis-1983';
424     $obj->{state} = 'state_2842';
425     require Encode::GLJIS1978;
426     require Encode::GLJIS1983;
427     if (Encode::find_encoding ($obj->{state_2440}) and
428     Encode::find_encoding ($obj->{state_2442})) {
429     return bless $obj, 'Whatpm::Charset::DecodeHandle::ISO2022JP';
430     }
431     } elsif (defined $csdef->{perl_name}->[0]) {
432     if ($csdef->{uri}->{$XML_CHARSET.'euc-jp'} or
433     $csdef->{uri}->{$IANA_CHARSET.'euc-jp'}) {
434     $obj->{perl_encoding_name} = $csdef->{perl_name}->[0];
435     require Encode::EUCJP1997;
436     if (Encode::find_encoding ($obj->{perl_encoding_name})) {
437     return bless $obj, 'Whatpm::Charset::DecodeHandle::EUCJP';
438     }
439     } elsif ($csdef->{uri}->{$XML_CHARSET.'shift_jis'} or
440     $csdef->{uri}->{$IANA_CHARSET.'shift_jis'}) {
441     $obj->{perl_encoding_name} = $csdef->{perl_name}->[0];
442     require Encode::ShiftJIS1997;
443     if (Encode::find_encoding ($obj->{perl_encoding_name})) {
444     return bless $obj, 'Whatpm::Charset::DecodeHandle::ShiftJIS';
445     }
446     } elsif ($csdef->{is_block_safe}) {
447     $obj->{perl_encoding_name} = $csdef->{perl_name}->[0];
448     require Encode;
449     if (Encode::find_encoding ($obj->{perl_encoding_name})) {
450     return bless $obj, 'Whatpm::Charset::DecodeHandle::Encode';
451     }
452     }
453     }
454    
455     $obj->{onerror}->(undef, 'charset-not-supported-error',
456     charset_uri => $obj->{charset});
457     return undef;
458     } # create_decode_handle
459    
460     sub name_to_uri ($$$) {
461     my $domain = $_[1];
462     my $name = lc $_[2];
463    
464     if ($domain eq 'ietf') {
465     return $IANA_CHARSET . $name;
466     } elsif ($domain eq 'xml') {
467     if ({
468     'utf-8' => 1,
469     'utf-16' => 1,
470     'iso-10646-ucs-2' => 1,
471     'iso-10646-ucs-4' => 1,
472     'iso-8859-1' => 1,
473     'iso-8859-2' => 1,
474     'iso-8859-3' => 1,
475     'iso-8859-4' => 1,
476     'iso-8859-5' => 1,
477     'iso-8859-6' => 1,
478     'iso-8859-7' => 1,
479     'iso-8859-8' => 1,
480     'iso-8859-9' => 1,
481     'iso-8859-10' => 1,
482     'iso-8859-11' => 1,
483     'iso-8859-13' => 1,
484     'iso-8859-14' => 1,
485     'iso-8859-15' => 1,
486     'iso-8859-16' => 1,
487     'iso-2022-jp' => 1,
488     'shift_jis' => 1,
489     'euc-jp' => 1,
490     }->{$name}) {
491     return $XML_CHARSET . $name;
492     }
493    
494     my $uri = $IANA_CHARSET . $name;
495     return $uri if $Whatpm::Charset::CharsetDef->{$uri};
496    
497     return $XML_CHARSET . $name;
498     } else {
499     return undef;
500     }
501     } # name_to_uri
502    
503     sub uri_to_name ($$$) {
504     my (undef, $domain, $uri) = @_;
505 wakaba 1.2
506     if ($domain eq 'xml') {
507     my $v = $Whatpm::Charset::CharsetDef->{$uri}->{xml_name};
508     return $v if defined $v;
509    
510     if (substr ($uri, 0, length $XML_CHARSET) eq $XML_CHARSET) {
511     return substr ($uri, length $XML_CHARSET);
512     }
513    
514     $domain = 'ietf'; ## TODO: XML encoding name has smaller range
515     }
516    
517     if ($domain eq 'ietf') {
518     my $v = $Whatpm::Charset::CharsetDef->{$uri}->{iana_name};
519     return $v->[0] if defined $v;
520    
521     if (substr ($uri, 0, length $IANA_CHARSET) eq $IANA_CHARSET) {
522 wakaba 1.1 return substr ($uri, length $IANA_CHARSET);
523     }
524     }
525    
526     return undef;
527     } # uri_to_name
528    
529 wakaba 1.3 require IO::Handle;
530    
531     package Whatpm::Charset::DecodeHandle::ByteBuffer;
532    
533     sub new ($$) {
534     my $self = bless {
535     buffer => '',
536     }, shift;
537     $self->{filehandle} = shift;
538     return $self;
539     } # new
540    
541     sub read {
542     my $self = shift;
543     my $pos = length $self->{buffer};
544     my $r = $self->{filehandle}->read ($self->{buffer}, $_[1], $pos);
545     substr ($_[0], $_[2]) = substr ($self->{buffer}, $pos);
546     return $r;
547     } # read
548    
549     sub close { $_[0]->{filehandle}->close }
550    
551 wakaba 1.1 package Whatpm::Charset::DecodeHandle::Encode;
552    
553     sub charset ($) { $_[0]->{charset} }
554    
555 wakaba 1.3 sub close ($) { $_[0]->{filehandle}->close }
556 wakaba 1.1
557     sub getc ($) {
558     my $self = $_[0];
559     return shift @{$self->{character_queue}} if @{$self->{character_queue}};
560    
561     my $error;
562     if ($self->{continue}) {
563 wakaba 1.3 if ($self->{filehandle}->read ($self->{byte_buffer}, 256,
564     length $self->{byte_buffer})) {
565 wakaba 1.1 #
566     } else {
567     $error = 1;
568     }
569     $self->{continue} = 0;
570     } elsif (512 > length $self->{byte_buffer}) {
571 wakaba 1.3 $self->{filehandle}->read ($self->{byte_buffer}, 256,
572     length $self->{byte_buffer});
573 wakaba 1.1 }
574    
575     my $r;
576     unless ($error) {
577     my $string = Encode::decode ($self->{perl_encoding_name},
578     $self->{byte_buffer},
579     Encode::FB_QUIET ());
580     if (length $string) {
581     push @{$self->{character_queue}}, split //, $string;
582     $r = shift @{$self->{character_queue}};
583     if (length $self->{byte_buffer}) {
584     $self->{continue} = 1;
585     }
586     } else {
587     if (length $self->{byte_buffer}) {
588     $error = 1;
589     } else {
590     $r = undef;
591     }
592     }
593     }
594    
595     if ($error) {
596     $r = substr $self->{byte_buffer}, 0, 1, '';
597     $self->{onerror}->($self, 'illegal-octets-error', octets => \$r);
598     }
599    
600     return $r;
601     } # getc
602    
603     sub has_bom ($) { $_[0]->{has_bom} }
604    
605 wakaba 1.2 sub input_encoding ($) {
606     my $v = $_[0]->{input_encoding};
607     return $v if defined $v;
608    
609     my $uri = $_[0]->{charset};
610     if (defined $uri) {
611     return Whatpm::Charset::DecodeHandle->uri_to_name (xml => $uri);
612     }
613    
614     return undef;
615     } # input_encoding
616 wakaba 1.1
617     sub onerror ($;$) {
618     if (@_ > 1) {
619     $_[0]->{onerror} = $_[1];
620     }
621    
622     return $_[0]->{onerror};
623     } # onerror
624    
625     sub ungetc ($$) {
626     unshift @{$_[0]->{character_queue}}, chr int ($_[1] or 0);
627     } # ungetc
628    
629     package Whatpm::Charset::DecodeHandle::EUCJP;
630     push our @ISA, 'Whatpm::Charset::DecodeHandle::Encode';
631    
632     sub getc ($) {
633     my $self = $_[0];
634     return shift @{$self->{character_queue}} if @{$self->{character_queue}};
635    
636     my $error;
637     if ($self->{continue}) {
638 wakaba 1.3 if ($self->{filehandle}->read ($self->{byte_buffer}, 256,
639     length $self->{byte_buffer})) {
640 wakaba 1.1 #
641     } else {
642     $error = 1;
643     }
644     $self->{continue} = 0;
645     } elsif (512 > length $self->{byte_buffer}) {
646 wakaba 1.3 $self->{filehandle}->read ($self->{byte_buffer}, 256,
647     length $self->{byte_buffer});
648 wakaba 1.1 }
649    
650     my $r;
651     unless ($error) {
652     my $string = Encode::decode ($self->{perl_encoding_name},
653     $self->{byte_buffer},
654     Encode::FB_QUIET ());
655     if (length $string) {
656     push @{$self->{character_queue}}, split //, $string;
657     $r = shift @{$self->{character_queue}};
658     if (length $self->{byte_buffer}) {
659     $self->{continue} = 1;
660     }
661     } else {
662     if (length $self->{byte_buffer}) {
663     $error = 1;
664     } else {
665     $r = undef;
666     }
667     }
668     }
669    
670     if ($error) {
671     $r = substr $self->{byte_buffer}, 0, 1, '';
672     my $etype = 'illegal-octets-error';
673     if ($r =~ /^[\xA1-\xFE]/) {
674     if ($self->{byte_buffer} =~ s/^([\xA1-\xFE])//) {
675     $r .= $1;
676     $etype = 'unassigned-code-point-error';
677     }
678     } elsif ($r eq "\x8F") {
679     if ($self->{byte_buffer} =~ s/^([\xA1-\xFE][\xA1-\xFE]?)//) {
680     $r .= $1;
681     $etype = 'unassigned-code-point-error' if length $1 == 2;
682     }
683     } elsif ($r eq "\x8E") {
684     if ($self->{byte_buffer} =~ s/^([\xA1-\xFE])//) {
685     $r .= $1;
686     $etype = 'unassigned-code-point-error';
687     }
688     } elsif ($r eq "\xA0" or $r eq "\xFF") {
689     $etype = 'unassigned-code-point-error';
690     }
691     $self->{onerror}->($self, $etype, octets => \$r);
692     }
693    
694     return $r;
695     } # getc
696    
697     package Whatpm::Charset::DecodeHandle::ISO2022JP;
698     push our @ISA, 'Whatpm::Charset::DecodeHandle::Encode';
699    
700     sub getc ($) {
701     my $self = $_[0];
702     return shift @{$self->{character_queue}} if @{$self->{character_queue}};
703    
704     my $r;
705     A: {
706     my $error;
707     if ($self->{continue}) {
708 wakaba 1.3 if ($self->{filehandle}->read ($self->{byte_buffer}, 256,
709     length $self->{byte_buffer})) {
710 wakaba 1.1 #
711     } else {
712     $error = 1;
713     }
714     $self->{continue} = 0;
715     } elsif (512 > length $self->{byte_buffer}) {
716 wakaba 1.3 $self->{filehandle}->read ($self->{byte_buffer}, 256,
717     length $self->{byte_buffer});
718 wakaba 1.1 }
719    
720     unless ($error) {
721     if ($self->{byte_buffer} =~ s/^\x1B(\x24[\x40\x42]|\x28[\x42\x4A])//) {
722     $self->{state} = {
723     "\x24\x40" => 'state_2440',
724     "\x24\x42" => 'state_2442',
725     "\x28\x42" => 'state_2842',
726     "\x28\x4A" => 'state_284A',
727     }->{$1};
728     redo A;
729     } elsif ($self->{state} eq 'state_2842') { # IRV
730     if ($self->{byte_buffer} =~ s/^([\x00-\x0D\x10-\x1A\x1C-\x7F]+)//) {
731     push @{$self->{character_queue}}, split //, $1;
732     $r = shift @{$self->{character_queue}};
733     } else {
734     if (length $self->{byte_buffer}) {
735     $error = 1;
736     } else {
737     $r = undef;
738     }
739     }
740     } elsif ($self->{state} eq 'state_284A') { # 0201
741     if ($self->{byte_buffer} =~ s/^([\x00-\x0D\x10-\x1A\x1C-\x7F]+)//) {
742     my $v = $1;
743     $v =~ tr/\x5C\x7E/\xA5\x{203E}/;
744     push @{$self->{character_queue}}, split //, $v;
745     $r = shift @{$self->{character_queue}};
746     } else {
747     if (length $self->{byte_buffer}) {
748     $error = 1;
749     } else {
750     $r = undef;
751     $self->{onerror}->($self, 'invalid-state-error',
752     state => $self->{state});
753     }
754     }
755     } elsif ($self->{state} eq 'state_2442') { # 1983
756     my $v = Encode::decode ($self->{state_2442},
757     $self->{byte_buffer},
758     Encode::FB_QUIET ());
759     if (length $v) {
760     push @{$self->{character_queue}}, split //, $v;
761     $r = shift @{$self->{character_queue}};
762     } else {
763     if (length $self->{byte_buffer}) {
764     $error = 1;
765     } else {
766     $r = undef;
767     $self->{onerror}->($self, 'invalid-state-error',
768     state => $self->{state});
769     }
770     }
771     } elsif ($self->{state} eq 'state_2440') { # 1978
772     my $v = Encode::decode ($self->{state_2440},
773     $self->{byte_buffer},
774     Encode::FB_QUIET ());
775     if (length $v) {
776     push @{$self->{character_queue}}, split //, $v;
777     $r = shift @{$self->{character_queue}};
778     } else {
779     if (length $self->{byte_buffer}) {
780     $error = 1;
781     } else {
782     $r = undef;
783     $self->{onerror}->($self, 'invalid-state-error',
784     state => $self->{state});
785     }
786     }
787     } else {
788     $error = 1;
789     }
790     }
791    
792     if ($error) {
793     $r = substr $self->{byte_buffer}, 0, 1, '';
794     my $etype = 'illegal-octets-error';
795     if (($self->{state} eq 'state_2442' or
796     $self->{state} eq 'state_2440') and
797     $r =~ /^[\x21-\x7E]/ and
798     $self->{byte_buffer} =~ s/^([\x21-\x7E])//) {
799     $r .= $1;
800     $etype = 'unassigned-code-point-error';
801     } elsif ($r eq "\x1B" and
802     $self->{byte_buffer} =~ s/^\(H//) { # Old 0201
803     $r .= "(H";
804     $self->{state} = 'state_284A';
805     }
806     $self->{onerror}->($self, $etype, octets => \$r);
807     }
808     } # A
809    
810     return $r;
811     } # getc
812    
813     package Whatpm::Charset::DecodeHandle::ShiftJIS;
814     push our @ISA, 'Whatpm::Charset::DecodeHandle::Encode';
815    
816     sub getc ($) {
817     my $self = $_[0];
818     return shift @{$self->{character_queue}} if @{$self->{character_queue}};
819    
820     my $error;
821     if ($self->{continue}) {
822 wakaba 1.3 if ($self->{filehandle}->read ($self->{byte_buffer}, 256,
823     length $self->{byte_buffer})) {
824 wakaba 1.1 #
825     } else {
826     $error = 1;
827     }
828     $self->{continue} = 0;
829     } elsif (512 > length $self->{byte_buffer}) {
830 wakaba 1.3 $self->{filehandle}->read ($self->{byte_buffer}, 256,
831     length $self->{byte_buffer});
832 wakaba 1.1 }
833    
834     my $r;
835     unless ($error) {
836     my $string = Encode::decode ($self->{perl_encoding_name},
837     $self->{byte_buffer},
838     Encode::FB_QUIET ());
839     if (length $string) {
840     push @{$self->{character_queue}}, split //, $string;
841     $r = shift @{$self->{character_queue}};
842     if (length $self->{byte_buffer}) {
843     $self->{continue} = 1;
844     }
845     } else {
846     if (length $self->{byte_buffer}) {
847     $error = 1;
848     } else {
849     $r = undef;
850     }
851     }
852     }
853    
854     if ($error) {
855     $r = substr $self->{byte_buffer}, 0, 1, '';
856     my $etype = 'illegal-octets-error';
857     if ($r =~ /^[\x81-\x9F\xE0-\xEF]/) {
858     if ($self->{byte_buffer} =~ s/(.)//s) {
859     $r .= $1; # not limited to \x40-\xFC - \x7F
860     $etype = 'unassigned-code-point-error';
861     }
862     } elsif ($r =~ /^[\x80\xA0\xF0-\xFF]/) {
863     $etype = 'unassigned-code-point-error';
864     }
865     $self->{onerror}->($self, $etype, octets => \$r);
866     }
867    
868     return $r;
869     } # getc
870    
871     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:us-ascii'} =
872     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:us'} =
873     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:iso646-us'} =
874     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:cp367'} =
875     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:ibm367'} =
876     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:ansi_x3.4-1986'} =
877     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:ansi_x3.4-1968'} =
878     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:iso-ir-6'} =
879     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:csascii'} =
880     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:iso_646.irv:1991'} =
881     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:ascii'} = {ascii8 =>
882     '1',
883     is_block_safe =>
884     '1',
885     ietf_name =>
886     ['ansi_x3.4-1968',
887     'ansi_x3.4-1986',
888     'ascii',
889     'cp367',
890     'csascii',
891     'ibm367',
892     'iso-ir-6',
893     'iso646-us',
894     'iso_646.irv:1991',
895     'us',
896     'us-ascii',
897     'us-ascii'],
898     mime_name =>
899     'us-ascii',
900     perl_name =>
901     ['ascii',
902     'iso-646-us',
903     'us-ascii'],
904     utf8_encoding_scheme =>
905     '1',
906     'uri',
907     {'urn:x-suika-fam-cx:charset:ansi_x3.4-1968',
908     '1',
909     'urn:x-suika-fam-cx:charset:ansi_x3.4-1986',
910     '1',
911     'urn:x-suika-fam-cx:charset:ascii',
912     '1',
913     'urn:x-suika-fam-cx:charset:cp367',
914     '1',
915     'urn:x-suika-fam-cx:charset:csascii',
916     '1',
917     'urn:x-suika-fam-cx:charset:ibm367',
918     '1',
919     'urn:x-suika-fam-cx:charset:iso-ir-6',
920     '1',
921     'urn:x-suika-fam-cx:charset:iso646-us',
922     '1',
923     'urn:x-suika-fam-cx:charset:iso_646.irv:1991',
924     '1',
925     'urn:x-suika-fam-cx:charset:us',
926     '1',
927     'urn:x-suika-fam-cx:charset:us-ascii',
928     '1'},
929 wakaba 1.2 };
930    
931 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ascii-ctrl'} = {perl_name =>
932     ['ascii-ctrl'],
933     'uri',
934     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ascii-ctrl',
935     '1'}};
936     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.null'} = {perl_name =>
937     ['null'],
938     'uri',
939     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.null',
940     '1'}};
941     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.utf-8'} = {ascii8 =>
942     '1',
943     bom_allowed =>
944     '1',
945     no_bom_variant =>
946     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf8',
947     utf8_encoding_scheme =>
948     '1',
949     'uri',
950     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.utf-8',
951     '1'},
952 wakaba 1.2 xml_name => 'UTF-8',
953     };
954    
955 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/UTF-8.RFC2279'} = {ascii8 =>
956     '1',
957     bom_allowed =>
958     '1',
959     no_bom_variant =>
960     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf8',
961     utf8_encoding_scheme =>
962     '1',
963     'uri',
964     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/UTF-8.RFC2279',
965     '1'}};
966     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-8'} = {
967     ascii8 => 1,
968     is_block_safe =>
969     '1',
970     perl_name =>
971     ['utf-8'],
972     utf8_encoding_scheme =>
973     '1',
974     'uri',
975     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-8',
976     '1'}};
977     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:utf-8'} = {
978     ascii8 => 1,
979     bom_allowed =>
980     '1',
981     no_bom_variant =>
982     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-8',
983     ietf_name =>
984     ['utf-8'],
985     mime_name =>
986     'utf-8',
987     utf8_encoding_scheme =>
988     '1',
989     'uri',
990     {'urn:x-suika-fam-cx:charset:utf-8',
991     '1'},
992 wakaba 1.2 };
993    
994 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf8'} = {ascii8 =>
995     '1',
996     is_block_safe =>
997     '1',
998     perl_name =>
999     ['utf8'],
1000     utf8_encoding_scheme =>
1001     '1',
1002     'uri',
1003     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf8',
1004     '1'}};
1005     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.utf-16'} = {
1006     ascii16 => 1,
1007     bom_allowed =>
1008     '1',
1009     bom_required =>
1010     '1',
1011     no_bom_variant =>
1012     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le',
1013     no_bom_variant16be =>
1014     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16be',
1015     no_bom_variant16le =>
1016     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le',
1017     perl_name =>
1018     ['utf-16'],
1019     'uri',
1020     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.utf-16',
1021     '1'},
1022 wakaba 1.2 xml_name => 'UTF-16',
1023     };
1024    
1025 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:utf-16'} = {
1026     ascii16 => 1,
1027     bom_allowed =>
1028     '1',
1029     no_bom_variant =>
1030     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le',
1031     no_bom_variant16be =>
1032     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16be',
1033     no_bom_variant16le =>
1034     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le',
1035     ietf_name =>
1036     ['utf-16'],
1037     mime_name =>
1038     'utf-16',
1039     'uri',
1040     {'urn:x-suika-fam-cx:charset:utf-16',
1041     '1'},
1042 wakaba 1.2 };
1043    
1044 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:utf-16be'} = {
1045     ascii16 => 1,
1046     ascii16be => 1,
1047     bom_allowed =>
1048     '1',
1049     no_bom_variant =>
1050     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16be',
1051     no_bom_variant16be =>
1052     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16be',
1053     ietf_name =>
1054     ['utf-16be'],
1055     mime_name =>
1056     'utf-16be',
1057     'uri',
1058     {'urn:x-suika-fam-cx:charset:utf-16be',
1059     '1'},
1060 wakaba 1.2 };
1061    
1062 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:utf-16le'} = {
1063     ascii16 => 1,
1064     ascii16le => 1,
1065     bom_allowed =>
1066     '1',
1067     no_bom_variant =>
1068     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le',
1069     no_bom_variant16le =>
1070     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le',
1071     ietf_name =>
1072     ['utf-16le'],
1073     mime_name =>
1074     'utf-16le',
1075     'uri',
1076     {'urn:x-suika-fam-cx:charset:utf-16le',
1077     '1'},
1078 wakaba 1.2 };
1079    
1080 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16be'} = {
1081     ascii16 => 1,
1082     ascii16be => 1,
1083     is_block_safe =>
1084     '1',
1085     perl_name =>
1086     ['utf-16be'],
1087     'uri',
1088     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16be',
1089     '1'}};
1090     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le'} = {
1091     ascii16 => 1,
1092     ascii16le => 1,
1093     is_block_safe =>
1094     '1',
1095     perl_name =>
1096     ['utf-16le'],
1097     'uri',
1098     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-16le',
1099     '1'}};
1100     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-10646-ucs-2'} = $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:iso-10646-ucs-2'} = {
1101     ascii16 => 1,
1102     bom_allowed =>
1103     '1',
1104     no_bom_variant =>
1105     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ucs-2le',
1106     no_bom_variant16be =>
1107     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ucs-2be',
1108     no_bom_variant16le =>
1109     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ucs-2le',
1110     ietf_name =>
1111     ['csunicode',
1112     'iso-10646-ucs-2'],
1113     mime_name =>
1114     'iso-10646-ucs-2',
1115     'uri',
1116     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-10646-ucs-2',
1117     '1',
1118     'urn:x-suika-fam-cx:charset:iso-10646-ucs-2',
1119     '1'},
1120 wakaba 1.2 xml_name => 'ISO-10646-UCS-2',
1121     };
1122    
1123 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ucs-2be'} = {
1124     ascii16 => 1,
1125     ascii16be => 1,
1126     is_block_safe =>
1127     '1',
1128     perl_name =>
1129     ['ucs-2be'],
1130     'uri',
1131     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ucs-2be',
1132     '1'}};
1133     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ucs-2le'} = {
1134     ascii16 => 1,
1135     ascii16le => 1,
1136     is_block_safe =>
1137     '1',
1138     perl_name =>
1139     ['ucs-2le'],
1140     'uri',
1141     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.ucs-2le',
1142     '1'}};
1143     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-10646-ucs-4'} = $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:iso-10646-ucs-4'} = {
1144     ascii32 => 1,
1145     bom_allowed =>
1146     '1',
1147     no_bom_variant =>
1148     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-32le',
1149     no_bom_variant32endian1234 =>
1150     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-32be',
1151     no_bom_variant32endian4321 =>
1152     'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-32le',
1153     ietf_name =>
1154     ['csucs4',
1155     'iso-10646-ucs-4'],
1156     mime_name =>
1157     'iso-10646-ucs-4',
1158     'uri',
1159     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-10646-ucs-4',
1160     '1',
1161     'urn:x-suika-fam-cx:charset:iso-10646-ucs-4',
1162     '1'},
1163 wakaba 1.2 xml_name => 'ISO-10646-UCS-4',
1164     };
1165    
1166 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-32be'} = {
1167     ascii32 => 1,
1168     ascii32endian1234 => 1,
1169     is_block_safe =>
1170     '1',
1171     perl_name =>
1172     ['ucs-4be',
1173     'utf-32be'],
1174     'uri',
1175     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-32be',
1176     '1'}};
1177     $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-32le'} = {
1178     ascii32 => 1,
1179     ascii32endian4321 => 1,
1180     is_block_safe =>
1181     '1',
1182     perl_name =>
1183     ['ucs-4le',
1184     'utf-32le'],
1185     'uri',
1186     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.utf-32le',
1187     '1'}};
1188     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:iso_8859-1:1987'} = $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-1'} = {ascii8 =>
1189     '1',
1190     is_block_safe =>
1191     '1',
1192     ietf_name =>
1193     ['cp819',
1194     'csisolatin1',
1195     'ibm819',
1196     'iso-8859-1',
1197     'iso-8859-1',
1198     'iso-ir-100',
1199     'iso_8859-1',
1200     'iso_8859-1:1987',
1201     'l1',
1202     'latin1'],
1203     mime_name =>
1204     'iso-8859-1',
1205     perl_name =>
1206     ['iso-8859-1',
1207     'latin1'],
1208     'uri',
1209     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-1',
1210     '1',
1211     'urn:x-suika-fam-cx:charset:iso_8859-1:1987',
1212     '1'},
1213 wakaba 1.2 xml_name => 'ISO-8859-1',
1214     };
1215    
1216 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-2'} = {ascii8 =>
1217     '1',
1218     is_block_safe =>
1219     '1',
1220     'uri',
1221     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-2',
1222     '1'},
1223 wakaba 1.2 xml_name => 'ISO-8859-2',
1224     };
1225    
1226 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-3'} = {ascii8 =>
1227     '1',
1228     is_block_safe =>
1229     '1',
1230     'uri',
1231     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-3',
1232     '1'},
1233 wakaba 1.2 xml_name => 'ISO-8859-3',
1234     };
1235    
1236 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-4'} = {ascii8 =>
1237     '1',
1238     is_block_safe =>
1239     '1',
1240     'uri',
1241     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-4',
1242     '1'},
1243 wakaba 1.2 xml_name => 'ISO-8859-4',
1244     };
1245    
1246 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-5'} = {ascii8 =>
1247     '1',
1248     is_block_safe =>
1249     '1',
1250     'uri',
1251     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-5',
1252     '1'},
1253 wakaba 1.2 xml_name => 'ISO-8859-5',
1254     };
1255    
1256 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-6'} = {ascii8 =>
1257     '1',
1258     is_block_safe =>
1259     '1',
1260     'uri',
1261     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-6',
1262     '1'},
1263 wakaba 1.2 xml_name => 'ISO-8859-6',
1264     };
1265    
1266 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-7'} = {ascii8 =>
1267     '1',
1268     is_block_safe =>
1269     '1',
1270     'uri',
1271     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-7',
1272     '1'},
1273 wakaba 1.2 xml_name => 'ISO-8859-7',
1274     };
1275    
1276 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-8'} = {ascii8 =>
1277     '1',
1278     is_block_safe =>
1279     '1',
1280     'uri',
1281     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-8',
1282     '1'},
1283 wakaba 1.2 xml_name => 'ISO-8859-8',
1284     };
1285    
1286 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-9'} = {ascii8 =>
1287     '1',
1288     is_block_safe =>
1289     '1',
1290     'uri',
1291     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-9',
1292     '1'},
1293 wakaba 1.2 xml_name => 'ISO-8859-9',
1294     };
1295    
1296 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-10'} = {ascii8 =>
1297     '1',
1298     is_block_safe =>
1299     '1',
1300     'uri',
1301     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-10',
1302     '1'},
1303 wakaba 1.2 xml_name => 'ISO-8859-10',
1304     };
1305    
1306 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-11'} = {ascii8 =>
1307     '1',
1308     is_block_safe =>
1309     '1',
1310     'uri',
1311     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-11',
1312     '1'},
1313 wakaba 1.2 xml_name => 'ISO-8859-11',
1314     };
1315    
1316 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-13'} = {ascii8 =>
1317     '1',
1318     is_block_safe =>
1319     '1',
1320     'uri',
1321     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-13',
1322     '1'},
1323 wakaba 1.2 xml_name => 'ISO-8859-13',
1324     };
1325    
1326 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-14'} = {ascii8 =>
1327     '1',
1328     is_block_safe =>
1329     '1',
1330     'uri',
1331     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-14',
1332     '1'},
1333 wakaba 1.2 xml_name => 'ISO-8859-14',
1334     };
1335    
1336 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-15'} = {ascii8 =>
1337     '1',
1338     is_block_safe =>
1339     '1',
1340     'uri',
1341     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-15',
1342     '1'},
1343 wakaba 1.2 xml_name => 'ISO-8859-15',
1344     };
1345    
1346 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-16'} = {ascii8 =>
1347     '1',
1348     is_block_safe =>
1349     '1',
1350     'uri',
1351     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-8859-16',
1352     '1'},
1353 wakaba 1.2 xml_name => 'ISO-8859-16',
1354     };
1355    
1356 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-2022-jp'} = {ascii8 =>
1357     '1',
1358     'uri',
1359     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.iso-2022-jp',
1360     '1'},
1361 wakaba 1.2 xml_name => 'ISO-2022-JP',
1362     };
1363    
1364 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:iso-2022-jp'} = {ascii8 =>
1365     '1',
1366     ietf_name =>
1367     ['csiso2022jp',
1368     'iso-2022-jp',
1369     'iso-2022-jp'],
1370     mime_name =>
1371     'iso-2022-jp',
1372     'uri',
1373     {'urn:x-suika-fam-cx:charset:iso-2022-jp',
1374     '1'},
1375 wakaba 1.2 };
1376    
1377 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.iso-2022-jp'} = {ascii8 =>
1378     '1',
1379     perl_name =>
1380     ['iso-2022-jp'],
1381     'uri',
1382     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.iso-2022-jp',
1383     '1'}};
1384     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:shift_jis'} = $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.shift_jis'} = {ascii8 =>
1385     '1',
1386     is_block_safe =>
1387     '1',
1388     ietf_name =>
1389     ['csshiftjis',
1390     'ms_kanji',
1391     'shift_jis',
1392     'shift_jis'],
1393     mime_name =>
1394     'shift_jis',
1395     perl_name =>
1396     ['shift-jis-1997'],
1397     'uri',
1398     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.shift_jis',
1399     '1',
1400     'urn:x-suika-fam-cx:charset:shift_jis',
1401     '1'},
1402 wakaba 1.2 xml_name => 'Shift_JIS',
1403     };
1404    
1405 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.shiftjis'} = {ascii8 =>
1406     '1',
1407     is_block_safe =>
1408     '1',
1409     perl_name =>
1410     ['shiftjis',
1411     'sjis'],
1412     'uri',
1413     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.shiftjis',
1414     '1'}};
1415     $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:euc-jp'} = $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.euc-jp'} = $Whatpm::Charset::CharsetDef->{'urn:x-suika-fam-cx:charset:extended_unix_code_packed_format_for_japanese'} = {ascii8 =>
1416     '1',
1417     is_block_safe =>
1418     '1',
1419     ietf_name =>
1420     ['cseucpkdfmtjapanese',
1421     'euc-jp',
1422     'euc-jp',
1423     'extended_unix_code_packed_format_for_japanese'],
1424     mime_name =>
1425     'euc-jp',
1426     perl_name =>
1427     ['euc-jp-1997'],
1428     'uri',
1429     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/XML.euc-jp',
1430     '1',
1431     'urn:x-suika-fam-cx:charset:euc-jp',
1432     '1',
1433     'urn:x-suika-fam-cx:charset:extended_unix_code_packed_format_for_japanese',
1434     '1'},
1435 wakaba 1.2 xml_name => 'EUC-JP',
1436     };
1437    
1438 wakaba 1.1 $Whatpm::Charset::CharsetDef->{'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.euc-jp'} = {ascii8 =>
1439     '1',
1440     is_block_safe =>
1441     '1',
1442     perl_name =>
1443     ['euc-jp',
1444     'ujis'],
1445     'uri',
1446     {'http://suika.fam.cx/~wakaba/archive/2004/dis/Charset/Perl.euc-jp',
1447     '1'}};
1448    
1449     1;
1450 wakaba 1.3 ## $Date: 2007/07/15 16:51:14 $
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24