/[suikacvs]/markup/html/whatpm/t/tokenizer-test-2.dat
Suika

Contents of /markup/html/whatpm/t/tokenizer-test-2.dat

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.11 - (hide annotations) (download)
Mon Sep 22 06:04:29 2008 UTC (16 years, 10 months ago) by wakaba
Branch: MAIN
Changes since 1.10: +2 -0 lines
++ whatpm/t/ChangeLog	22 Sep 2008 05:59:48 -0000
	* tokenizer-test-1.test: Test data on invalid character references
	are added (cf. HTML5 revision 2138).

	* tokenizer-test-2.dat: Test data on U+000B are updated (HTML5
	revision 2138).

2008-09-22  Wakaba  <wakaba@suika.fam.cx>

++ whatpm/Whatpm/ChangeLog	22 Sep 2008 06:02:01 -0000
2008-09-22  Wakaba  <wakaba@suika.fam.cx>

	* HTML.pm.src: Character references for non-space C0 characters,
	including U+000B VT, DEL character, noncharacter code points, are
	now converted to the U+FFFD character (cf. HTML5 revision 2138).

1 wakaba 1.1 #data escaped
2 wakaba 1.2 <!DOCTYPE HTML><html><head><title></title></head><body><p>\u0000</p></body>
3 wakaba 1.1 #errors
4     NULL
5     #document escaped
6 wakaba 1.2 | <!DOCTYPE HTML>
7 wakaba 1.1 | <html>
8     | <head>
9     | <title>
10     | <body>
11     | <p>
12     | "\uFFFD"
13    
14 wakaba 1.3 #data escaped
15     \u0000
16     #errors
17     NULL
18     #document-fragment p escaped
19     | "\uFFFD"
20    
21     #data escaped
22     <!DOCTYPE HTML><p>\u000D
23     #errors
24     #document escaped
25     | <!DOCTYPE HTML>
26     | <html>
27     | <head>
28     | <body>
29     | <p>
30     | "\u000A"
31    
32     #data escaped
33     <!DOCTYPE HTML><p>\u000D</p>
34     #errors
35     #document escaped
36     | <!DOCTYPE HTML>
37     | <html>
38     | <head>
39     | <body>
40     | <p>
41     | "\u000A"
42    
43     #data escaped
44 wakaba 1.5 <!DOCTYPE HTML><p>\u000D\u000D
45 wakaba 1.4 #errors
46     #document escaped
47     | <!DOCTYPE HTML>
48     | <html>
49     | <head>
50     | <body>
51     | <p>
52     | "\u000A\u000A"
53    
54     #data escaped
55 wakaba 1.6 <!DOCTYPE HTML><p>\u000D\u0000
56     #errors
57     NULL
58     #document escaped
59     | <!DOCTYPE HTML>
60     | <html>
61     | <head>
62     | <body>
63     | <p>
64     | "\u000A\uFFFD"
65    
66     #data escaped
67 wakaba 1.3 \u000D
68     #errors
69     #document-fragment p escaped
70     | "\u000A"
71 wakaba 1.4
72     #data escaped
73     \u000D\u000D
74     #errors
75     #document-fragment p escaped
76     | "\u000A\u000A"
77 wakaba 1.3
78     #data escaped
79     \u000Da
80     #errors
81     #document-fragment p escaped
82     | "\u000Aa"
83    
84     #data escaped
85     <!DOCTYPE HTML><p>\u000D\u000A</p>
86     #errors
87     #document escaped
88     | <!DOCTYPE HTML>
89     | <html>
90     | <head>
91     | <body>
92     | <p>
93     | "\u000A"
94    
95     #data escaped
96     \u000D\u000A
97     #errors
98     #document-fragment p escaped
99     | "\u000A"
100    
101     #data escaped
102     <!DOCTYPE HTML><p>\u000A</p>
103     #errors
104     #document escaped
105     | <!DOCTYPE HTML>
106     | <html>
107     | <head>
108     | <body>
109     | <p>
110     | "\u000A"
111    
112     #data escaped
113 wakaba 1.6 <!DOCTYPE HTML><p>\u000D\u0000</p>
114     #errors
115     NULL
116     #document escaped
117     | <!DOCTYPE HTML>
118     | <html>
119     | <head>
120     | <body>
121     | <p>
122     | "\u000A\uFFFD"
123    
124     #data escaped
125     <!DOCTYPE HTML><p>\u000D\u000D</p>
126     #errors
127     #document escaped
128     | <!DOCTYPE HTML>
129     | <html>
130     | <head>
131     | <body>
132     | <p>
133     | "\u000A\u000A"
134    
135     #data escaped
136 wakaba 1.3 \u000A
137     #errors
138     #document-fragment p escaped
139     | "\u000A"
140 wakaba 1.6
141     #data escaped
142     \u000D\u0000
143     #errors
144     NULL
145     #document-fragment p escaped
146     | "\u000A\uFFFD"
147    
148     #data escaped
149     \u000D\u000D
150     #errors
151     #document-fragment p escaped
152     | "\u000A\u000A"
153 wakaba 1.3
154     #data
155     <script><!-- </script> --></script>
156     #errors
157     #document-fragment p
158    
159     #data
160     <style><!-- </style> --></style>
161     #errors
162     #document-fragment p
163     | <style>
164     | "<!-- </style> -->"
165    
166 wakaba 1.7 #data
167     <script><!----x></script>foo
168     #errors
169     no DOCTYPE
170     no --></script> before EOF
171     #document
172     | <html>
173     | <head>
174     | <script>
175     | "<!----x></script>foo"
176     | <body>
177 wakaba 1.8
178     #data escaped
179     \u0001
180     #errors
181     no DOCTYPE
182     control character
183     #document escaped
184     | <html>
185     | <head>
186     | <body>
187     | "\u0001"
188    
189     #data escaped
190     \u0001
191     #errors
192     control character
193     #document-fragment p escaped
194     | "\u0001"
195    
196     #data escaped
197     \u0002
198     #errors
199     no DOCTYPE
200     control character
201     #document escaped
202     | <html>
203     | <head>
204     | <body>
205     | "\u0002"
206    
207     #data escaped
208     \u0002
209     #errors
210     control character
211     #document-fragment p escaped
212     | "\u0002"
213    
214     #data escaped
215     \u000b
216     #errors
217     no DOCTYPE
218 wakaba 1.11 U+000B
219 wakaba 1.8 #document escaped
220     | <html>
221     | <head>
222     | <body>
223 wakaba 1.10 | "\u000b"
224 wakaba 1.8
225     #data escaped
226     \u000b
227     #errors
228 wakaba 1.11 U+000B
229 wakaba 1.8 #document-fragment p escaped
230     | "\u000b"
231    
232     #data escaped
233     \u000e
234     #errors
235     no DOCTYPE
236     control character
237     #document escaped
238     | <html>
239     | <head>
240     | <body>
241     | "\u000e"
242    
243     #data escaped
244     \u000e
245     #errors
246     control character
247     #document-fragment p escaped
248     | "\u000e"
249    
250     #data escaped
251     \u001f
252     #errors
253     no DOCTYPE
254     control character
255     #document escaped
256     | <html>
257     | <head>
258     | <body>
259     | "\u001f"
260    
261     #data escaped
262     \u001f
263     #errors
264     control character
265     #document-fragment p escaped
266     | "\u001f"
267    
268     #data escaped
269     \u007f
270     #errors
271     no DOCTYPE
272     control character
273     #document escaped
274     | <html>
275     | <head>
276     | <body>
277     | "\u007f"
278    
279     #data escaped
280     \u007f
281     #errors
282     control character
283     #document-fragment p escaped
284     | "\u007f"
285    
286     #data escaped
287     \u0080
288     #errors
289     no DOCTYPE
290     control character
291     #document escaped
292     | <html>
293     | <head>
294     | <body>
295     | "\u0080"
296    
297     #data escaped
298     \u0080
299     #errors
300     control character
301     #document-fragment p escaped
302     | "\u0080"
303    
304     #data escaped
305     \u0085
306     #errors
307     no DOCTYPE
308     control character
309     #document escaped
310     | <html>
311     | <head>
312     | <body>
313     | "\u0085"
314    
315     #data escaped
316     \u0085
317     #errors
318     control character
319     #document-fragment p escaped
320     | "\u0085"
321    
322     #data escaped
323     \u009f
324     #errors
325     no DOCTYPE
326     control character
327     #document escaped
328     | <html>
329     | <head>
330     | <body>
331     | "\u009f"
332    
333     #data escaped
334     \u009f
335     #errors
336     control character
337     #document-fragment p escaped
338     | "\u009f"
339    
340     #data escaped
341     \ud800
342     #errors
343     no DOCTYPE
344     control character
345     #document escaped
346     | <html>
347     | <head>
348     | <body>
349     | "\ud800"
350    
351     #data escaped
352     \ud800
353     #errors
354     control character
355     #document-fragment p escaped
356     | "\ud800"
357    
358     #data escaped
359     \udfff
360     #errors
361     no DOCTYPE
362     control character
363     #document escaped
364     | <html>
365     | <head>
366     | <body>
367     | "\udfff"
368    
369     #data escaped
370     \udfff
371     #errors
372     control character
373     #document-fragment p escaped
374     | "\udfff"
375    
376     #data escaped
377     \ufdd0
378     #errors
379     no DOCTYPE
380     control character
381     #document escaped
382     | <html>
383     | <head>
384     | <body>
385     | "\ufdd0"
386    
387     #data escaped
388     \ufdd0
389     #errors
390     control character
391     #document-fragment p escaped
392     | "\ufdd0"
393    
394     #data escaped
395     \ufddf
396     #errors
397     no DOCTYPE
398     control character
399     #document escaped
400     | <html>
401     | <head>
402     | <body>
403     | "\ufddf"
404    
405     #data escaped
406     \ufddf
407     #errors
408     control character
409     #document-fragment p escaped
410     | "\ufddf"
411    
412     #data escaped
413     \ufffe
414     #errors
415     no DOCTYPE
416     control character
417     #document escaped
418     | <html>
419     | <head>
420     | <body>
421     | "\ufffe"
422    
423     #data escaped
424     \ufffe
425     #errors
426     control character
427     #document-fragment p escaped
428     | "\ufffe"
429    
430     #data escaped
431     \uffff
432     #errors
433     no DOCTYPE
434     control character
435     #document escaped
436     | <html>
437     | <head>
438     | <body>
439     | "\uffff"
440    
441     #data escaped
442     \uffff
443     #errors
444     control character
445     #document-fragment p escaped
446     | "\uffff"
447    
448     #data escaped
449     \U0010ffff
450     #errors
451     no DOCTYPE
452     control character
453     #document escaped
454     | <html>
455     | <head>
456     | <body>
457     | "\U0010ffff"
458    
459     #data escaped
460     \U0010ffff
461     #errors
462     control character
463     #document-fragment p escaped
464     | "\U0010ffff"
465    
466 wakaba 1.9 #data
467     <!DOCTYPE HTML SYSTEM "x"
468     #errors
469     not HTML5
470     #document
471     | <!DOCTYPE HTML SYSTEM "x">
472     | <html>
473     | <head>
474     | <body>
475    
476     #data
477     <!DOCTYPE HTML SYSTEM "x"y>
478     #errors
479     string after SYSTEM literal
480     not HTML5
481     #document
482     | <!DOCTYPE HTML SYSTEM "x">
483     | <html>
484     | <head>
485     | <body>
486    

admin@suikawiki.org
ViewVC Help
Powered by ViewVC 1.1.24