/[suikacvs]/markup/html/whatpm/Whatpm/_NamedEntityList.pm
Suika

Contents of /markup/html/whatpm/Whatpm/_NamedEntityList.pm

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.2 - (hide annotations) (download)
Sat Mar 1 00:42:53 2008 UTC (18 years, 7 months ago) by wakaba
Branch: MAIN
Changes since 1.1: +2 -2 lines
++ whatpm/t/ChangeLog	1 Mar 2008 00:26:59 -0000
2008-03-01  Wakaba  <wakaba@suika.fam.cx>

	* tokenizer-test-1.test: Updated (HTML5 recision 1286).

	* content-model-2.dat: Updated (HTML5 revision 1275).

++ whatpm/Whatpm/ChangeLog	1 Mar 2008 00:19:36 -0000
2008-03-01  Wakaba  <wakaba@suika.fam.cx>

	* _NamedEntityList.pm: Updated (HTML5 revision 1286).

	* HTML.pm.src: |charset| in |content| attribute is
	case-insensitive (HTML5 revision 1270).

++ whatpm/Whatpm/HTML/ChangeLog	1 Mar 2008 00:07:44 -0000
2008-03-01  Wakaba  <wakaba@suika.fam.cx>

	* Serializer.pm (get_inner_html): Escape NBSP (HTML5 revision
	1277).

++ whatpm/Whatpm/ContentChecker/ChangeLog	29 Feb 2008 23:29:54 -0000
2008-03-01  Wakaba  <wakaba@suika.fam.cx>

	* HTML.pm: Sectioning root category added.  |blockquote|
	is no longer a sectioning content.

1 wakaba 1.1 $Whatpm::HTML::EntityChar = {
2     "AElig" => "\306",
3     "AMP" => "&",
4     "AMP;" => "&",
5     "Aacute" => "\301",
6     "Aacute;" => "\301",
7     "Acirc" => "\302",
8     "Acirc;" => "\302",
9     "Agrave" => "\300",
10     "Agrave;" => "\300",
11     "Alpha;" => "\x{391}",
12     "Aring" => "\305",
13     "Aring;" => "\305",
14     "Atilde" => "\303",
15     "Atilde;" => "\303",
16     "Auml" => "\304",
17     "Auml;" => "\304",
18     "Beta;" => "\x{392}",
19     "COPY" => "\251",
20     "COPY;" => "\251",
21     "Ccedil" => "\307",
22     "Ccedil;" => "\307",
23     "Chi;" => "\x{3a7}",
24     "Dagger;" => "\x{2021}",
25     "Delta;" => "\x{394}",
26     "ETH" => "\320",
27     "ETH;" => "\320",
28     "Eacute" => "\311",
29     "Eacute;" => "\311",
30     "Ecirc" => "\312",
31     "Ecirc;" => "\312",
32     "Egrave" => "\310",
33     "Egrave;" => "\310",
34     "Epsilon;" => "\x{395}",
35     "Eta;" => "\x{397}",
36     "Euml" => "\313",
37     "Euml;" => "\313",
38     "GT" => ">",
39     "GT;" => ">",
40     "Gamma;" => "\x{393}",
41     "Iacute" => "\315",
42     "Iacute;" => "\315",
43     "Icirc" => "\316",
44     "Icirc;" => "\316",
45     "Igrave" => "\314",
46     "Igrave;" => "\314",
47     "Iota;" => "\x{399}",
48     "Iuml" => "\317",
49     "Iuml;" => "\317",
50     "Kappa;" => "\x{39a}",
51     "LT" => "<",
52     "LT;" => "<",
53     "Lambda;" => "\x{39b}",
54     "Mu;" => "\x{39c}",
55     "Ntilde" => "\321",
56     "Ntilde;" => "\321",
57     "Nu;" => "\x{39d}",
58     "OElig;" => "\x{152}",
59     "Oacute" => "\323",
60     "Oacute;" => "\323",
61     "Ocirc" => "\324",
62     "Ocirc;" => "\324",
63     "Ograve" => "\322",
64     "Ograve;" => "\322",
65     "Omega;" => "\x{3a9}",
66     "Omicron;" => "\x{39f}",
67     "Oslash" => "\330",
68     "Oslash;" => "\330",
69     "Otilde" => "\325",
70     "Otilde;" => "\325",
71     "Ouml" => "\326",
72     "Ouml;" => "\326",
73     "Phi;" => "\x{3a6}",
74     "Pi;" => "\x{3a0}",
75     "Prime;" => "\x{2033}",
76     "Psi;" => "\x{3a8}",
77     "QUOT" => "\"",
78     "QUOT;" => "\"",
79     "REG" => "\256",
80     "REG;" => "\256",
81     "Rho;" => "\x{3a1}",
82     "Scaron;" => "\x{160}",
83     "Sigma;" => "\x{3a3}",
84     "THORN" => "\336",
85     "THORN;" => "\336",
86     "TRADE;" => "\x{2122}",
87     "Tau;" => "\x{3a4}",
88     "Theta;" => "\x{398}",
89     "Uacute" => "\332",
90     "Uacute;" => "\332",
91     "Ucirc" => "\333",
92     "Ucirc;" => "\333",
93     "Ugrave" => "\331",
94     "Ugrave;" => "\331",
95     "Upsilon;" => "\x{3a5}",
96     "Uuml" => "\334",
97     "Uuml;" => "\334",
98     "Xi;" => "\x{39e}",
99     "Yacute" => "\335",
100     "Yacute;" => "\335",
101     "Yuml;" => "\x{178}",
102     "Zeta;" => "\x{396}",
103     "aacute" => "\341",
104     "aacute;" => "\341",
105     "acirc" => "\342",
106     "acirc;" => "\342",
107     "acute" => "\264",
108     "acute;" => "\264",
109     "aelig" => "\346",
110     "aelig;" => "\346",
111     "agrave" => "\340",
112     "agrave;" => "\340",
113     "alefsym;" => "\x{2135}",
114     "alpha;" => "\x{3b1}",
115     "amp" => "&",
116     "amp;" => "&",
117     "and;" => "\x{2227}",
118     "ang;" => "\x{2220}",
119     "apos;" => "'",
120     "aring" => "\345",
121     "aring;" => "\345",
122     "asymp;" => "\x{2248}",
123     "atilde" => "\343",
124     "atilde;" => "\343",
125     "auml" => "\344",
126     "auml;" => "\344",
127     "bdquo;" => "\x{201e}",
128     "beta;" => "\x{3b2}",
129     "brvbar" => "\246",
130     "brvbar;" => "\246",
131     "bull;" => "\x{2022}",
132     "cap;" => "\x{2229}",
133     "ccedil" => "\347",
134     "ccedil;" => "\347",
135     "cedil" => "\270",
136     "cedil;" => "\270",
137     "cent" => "\242",
138     "cent;" => "\242",
139     "chi;" => "\x{3c7}",
140     "circ;" => "\x{2c6}",
141     "clubs;" => "\x{2663}",
142     "cong;" => "\x{2245}",
143     "copy" => "\251",
144     "copy;" => "\251",
145     "crarr;" => "\x{21b5}",
146     "cup;" => "\x{222a}",
147     "curren" => "\244",
148     "curren;" => "\244",
149     "dArr;" => "\x{21d3}",
150     "dagger;" => "\x{2020}",
151     "darr;" => "\x{2193}",
152     "deg" => "\260",
153     "deg;" => "\260",
154     "delta;" => "\x{3b4}",
155     "diams;" => "\x{2666}",
156     "divide" => "\367",
157     "divide;" => "\367",
158     "eacute" => "\351",
159     "eacute;" => "\351",
160     "ecirc" => "\352",
161     "ecirc;" => "\352",
162     "egrave" => "\350",
163     "egrave;" => "\350",
164     "empty;" => "\x{2205}",
165     "emsp;" => "\x{2003}",
166     "ensp;" => "\x{2002}",
167     "epsilon;" => "\x{3b5}",
168     "equiv;" => "\x{2261}",
169     "eta;" => "\x{3b7}",
170     "eth" => "\360",
171     "eth;" => "\360",
172     "euml" => "\353",
173     "euml;" => "\353",
174     "euro;" => "\x{20ac}",
175     "exist;" => "\x{2203}",
176     "fnof;" => "\x{192}",
177     "forall;" => "\x{2200}",
178     "frac12" => "\275",
179     "frac12;" => "\275",
180     "frac14" => "\274",
181     "frac14;" => "\274",
182     "frac34" => "\276",
183     "frac34;" => "\276",
184     "frasl;" => "\x{2044}",
185     "gamma;" => "\x{3b3}",
186     "ge;" => "\x{2265}",
187     "gt" => ">",
188     "gt;" => ">",
189     "hArr;" => "\x{21d4}",
190     "harr;" => "\x{2194}",
191     "hearts;" => "\x{2665}",
192     "hellip;" => "\x{2026}",
193     "iacute" => "\355",
194     "iacute;" => "\355",
195     "icirc" => "\356",
196     "icirc;" => "\356",
197     "iexcl" => "\241",
198     "iexcl;" => "\241",
199     "igrave" => "\354",
200     "igrave;" => "\354",
201     "image;" => "\x{2111}",
202     "infin;" => "\x{221e}",
203     "int;" => "\x{222b}",
204     "iota;" => "\x{3b9}",
205     "iquest" => "\277",
206     "iquest;" => "\277",
207     "isin;" => "\x{2208}",
208     "iuml" => "\357",
209     "iuml;" => "\357",
210     "kappa;" => "\x{3ba}",
211     "lArr;" => "\x{21d0}",
212     "lambda;" => "\x{3bb}",
213 wakaba 1.2 "lang;" => "\x{27e8}",
214 wakaba 1.1 "laquo" => "\253",
215     "laquo;" => "\253",
216     "larr;" => "\x{2190}",
217     "lceil;" => "\x{2308}",
218     "ldquo;" => "\x{201c}",
219     "le;" => "\x{2264}",
220     "lfloor;" => "\x{230a}",
221     "lowast;" => "\x{2217}",
222     "loz;" => "\x{25ca}",
223     "lrm;" => "\x{200e}",
224     "lsaquo;" => "\x{2039}",
225     "lsquo;" => "\x{2018}",
226     "lt" => "<",
227     "lt;" => "<",
228     "macr" => "\257",
229     "macr;" => "\257",
230     "mdash;" => "\x{2014}",
231     "micro" => "\265",
232     "micro;" => "\265",
233     "middot" => "\267",
234     "middot;" => "\267",
235     "minus;" => "\x{2212}",
236     "mu;" => "\x{3bc}",
237     "nabla;" => "\x{2207}",
238     "nbsp" => "\240",
239     "nbsp;" => "\240",
240     "ndash;" => "\x{2013}",
241     "ne;" => "\x{2260}",
242     "ni;" => "\x{220b}",
243     "not" => "\254",
244     "not;" => "\254",
245     "notin;" => "\x{2209}",
246     "nsub;" => "\x{2284}",
247     "ntilde" => "\361",
248     "ntilde;" => "\361",
249     "nu;" => "\x{3bd}",
250     "oacute" => "\363",
251     "oacute;" => "\363",
252     "ocirc" => "\364",
253     "ocirc;" => "\364",
254     "oelig;" => "\x{153}",
255     "ograve" => "\362",
256     "ograve;" => "\362",
257     "oline;" => "\x{203e}",
258     "omega;" => "\x{3c9}",
259     "omicron;" => "\x{3bf}",
260     "oplus;" => "\x{2295}",
261     "or;" => "\x{2228}",
262     "ordf" => "\252",
263     "ordf;" => "\252",
264     "ordm" => "\272",
265     "ordm;" => "\272",
266     "oslash" => "\370",
267     "oslash;" => "\370",
268     "otilde" => "\365",
269     "otilde;" => "\365",
270     "otimes;" => "\x{2297}",
271     "ouml" => "\366",
272     "ouml;" => "\366",
273     "para" => "\266",
274     "para;" => "\266",
275     "part;" => "\x{2202}",
276     "permil;" => "\x{2030}",
277     "perp;" => "\x{22a5}",
278     "phi;" => "\x{3c6}",
279     "pi;" => "\x{3c0}",
280     "piv;" => "\x{3d6}",
281     "plusmn" => "\261",
282     "plusmn;" => "\261",
283     "pound" => "\243",
284     "pound;" => "\243",
285     "prime;" => "\x{2032}",
286     "prod;" => "\x{220f}",
287     "prop;" => "\x{221d}",
288     "psi;" => "\x{3c8}",
289     "quot" => "\"",
290     "quot;" => "\"",
291     "rArr;" => "\x{21d2}",
292     "radic;" => "\x{221a}",
293 wakaba 1.2 "rang;" => "\x{27e9}",
294 wakaba 1.1 "raquo" => "\273",
295     "raquo;" => "\273",
296     "rarr;" => "\x{2192}",
297     "rceil;" => "\x{2309}",
298     "rdquo;" => "\x{201d}",
299     "real;" => "\x{211c}",
300     "reg" => "\256",
301     "reg;" => "\256",
302     "rfloor;" => "\x{230b}",
303     "rho;" => "\x{3c1}",
304     "rlm;" => "\x{200f}",
305     "rsaquo;" => "\x{203a}",
306     "rsquo;" => "\x{2019}",
307     "sbquo;" => "\x{201a}",
308     "scaron;" => "\x{161}",
309     "sdot;" => "\x{22c5}",
310     "sect" => "\247",
311     "sect;" => "\247",
312     "shy" => "\255",
313     "shy;" => "\255",
314     "sigma;" => "\x{3c3}",
315     "sigmaf;" => "\x{3c2}",
316     "sim;" => "\x{223c}",
317     "spades;" => "\x{2660}",
318     "sub;" => "\x{2282}",
319     "sube;" => "\x{2286}",
320     "sum;" => "\x{2211}",
321     "sup1" => "\271",
322     "sup1;" => "\271",
323     "sup2" => "\262",
324     "sup2;" => "\262",
325     "sup3" => "\263",
326     "sup3;" => "\263",
327     "sup;" => "\x{2283}",
328     "supe;" => "\x{2287}",
329     "szlig" => "\337",
330     "szlig;" => "\337",
331     "tau;" => "\x{3c4}",
332     "there4;" => "\x{2234}",
333     "theta;" => "\x{3b8}",
334     "thetasym;" => "\x{3d1}",
335     "thinsp;" => "\x{2009}",
336     "thorn" => "\376",
337     "thorn;" => "\376",
338     "tilde;" => "\x{2dc}",
339     "times" => "\327",
340     "times;" => "\327",
341     "trade;" => "\x{2122}",
342     "uArr;" => "\x{21d1}",
343     "uacute" => "\372",
344     "uacute;" => "\372",
345     "uarr;" => "\x{2191}",
346     "ucirc" => "\373",
347     "ucirc;" => "\373",
348     "ugrave" => "\371",
349     "ugrave;" => "\371",
350     "uml" => "\250",
351     "uml;" => "\250",
352     "upsih;" => "\x{3d2}",
353     "upsilon;" => "\x{3c5}",
354     "uuml" => "\374",
355     "uuml;" => "\374",
356     "weierp;" => "\x{2118}",
357     "xi;" => "\x{3be}",
358     "yacute" => "\375",
359     "yacute;" => "\375",
360     "yen" => "\245",
361     "yen;" => "\245",
362     "yuml" => "\377",
363     "yuml;" => "\377",
364     "zeta;" => "\x{3b6}",
365     "zwj;" => "\x{200d}",
366     "zwnj;" => "\x{200c}"
367     };
368     1;
369     __DATA__
370    
371     =head1 NAME
372    
373     mkentitylist.pl - Generate a named entity list for HTML parser
374    
375     _NamedEntityList.pm - A named entity list for HTML parser
376    
377     =head1 DESCRIPTION
378    
379     The C<_NamedEntityList.pm> file contains a list of named entities
380     used in HTML documents, both conforming and non-conforming.
381     It is referenced by C<ContentHTML.pm>. For more
382     information, see L<Whatpm::HTML>.
383    
384     The C<mkentitylist.pl> script is used to generate
385     the C<_NamedEntityList.pm> file from the table in the HTML5
386     specification.
387    
388     =head1 SEE ALSO
389    
390     L<Whatpm::HTML>.
391    
392     HTML 5 - Entities
393     <http://www.whatwg.org/specs/web-apps/current-work/#entities>
394    
395     =head1 LICENSE
396    
397     (C) Copyright 2004-2007 Apple Computer, Inc., Mozilla Foundation,
398     and Opera Software ASA.
399    
400     Copyright 2007 Wakaba <[email protected]>.
401    
402     You are granted a license to use, reproduce and create derivative works
403     of this document.
404    
405     =cut
406    

[email protected]
ViewVC Help
Powered by ViewVC 1.1.24