/[suikacvs]/markup/html/whatpm/t/tokenizer-test-1.test
Suika

Contents of /markup/html/whatpm/t/tokenizer-test-1.test

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.14 - (hide annotations) (download)
Sat Jul 7 13:41:06 2007 UTC (18 years ago) by wakaba
Branch: MAIN
Changes since 1.13: +8 -0 lines
++ whatpm/t/ChangeLog	7 Jul 2007 13:35:29 -0000
2007-07-07  Wakaba  <wakaba@suika.fam.cx>

	* tokenizer-test-1.test: A comment test is added.

++ whatpm/Whatpm/ChangeLog	7 Jul 2007 13:41:02 -0000
2007-07-07  Wakaba  <wakaba@suika.fam.cx>

	* HTML.pm.src: |<!---x-->| was not processed correctly.

1 wakaba 1.1 {"tests": [
2    
3 wakaba 1.3 {"description":"<!DOCTYPE",
4     "input":"<!DOCTYPE",
5 wakaba 1.9 "output":["ParseError","ParseError",["DOCTYPE", null, null, null, false]]},
6 wakaba 1.3
7     {"description":"<!DOCTYPE ",
8     "input":"<!DOCTYPE ",
9 wakaba 1.9 "output":["ParseError",["DOCTYPE", null, null, null, false]]},
10 wakaba 1.3
11     {"description":"<!DOCTYPE >",
12     "input":"<!DOCTYPE >",
13 wakaba 1.9 "output":["ParseError",["DOCTYPE", null, null, null, false]]},
14 wakaba 1.3
15     {"description":"<!DOCTYPE h",
16     "input":"<!DOCTYPE h",
17 wakaba 1.9 "output":["ParseError",["DOCTYPE", "h", null, null, false]]},
18 wakaba 1.3
19     {"description":"<!DOCTYPE H",
20     "input":"<!DOCTYPE H",
21 wakaba 1.9 "output":["ParseError",["DOCTYPE", "H", null, null, false]]},
22 wakaba 1.3
23     {"description":"<!DOCTYPE h>",
24     "input":"<!DOCTYPE h>",
25 wakaba 1.9 "output":[["DOCTYPE", "h", null, null, true]]},
26 wakaba 1.3
27     {"description":"<!DOCTYPE H>",
28     "input":"<!DOCTYPE H>",
29 wakaba 1.9 "output":[["DOCTYPE", "H", null, null, true]]},
30 wakaba 1.3
31     {"description":"<!DOCTYPE ht",
32     "input":"<!DOCTYPE ht",
33 wakaba 1.9 "output":["ParseError",["DOCTYPE", "ht", null, null, false]]},
34 wakaba 1.3
35     {"description":"<!DOCTYPE Ht",
36     "input":"<!DOCTYPE Ht",
37 wakaba 1.9 "output":["ParseError",["DOCTYPE", "Ht", null, null, false]]},
38 wakaba 1.3
39     {"description":"<!DOCTYPE hT",
40     "input":"<!DOCTYPE hT",
41 wakaba 1.9 "output":["ParseError",["DOCTYPE", "hT", null, null, false]]},
42 wakaba 1.3
43     {"description":"<!DOCTYPE ht>",
44     "input":"<!DOCTYPE ht>",
45 wakaba 1.9 "output":[["DOCTYPE", "ht", null, null, true]]},
46 wakaba 1.3
47     {"description":"<!DOCTYPE Ht>",
48     "input":"<!DOCTYPE Ht>",
49 wakaba 1.9 "output":[["DOCTYPE", "Ht", null, null, true]]},
50 wakaba 1.3
51     {"description":"<!DOCTYPE hT>",
52     "input":"<!DOCTYPE hT>",
53 wakaba 1.9 "output":[["DOCTYPE", "hT", null, null, true]]},
54 wakaba 1.3
55     {"description":"<!DOCTYPE hT>",
56     "input":"<!DOCTYPE hT>",
57 wakaba 1.9 "output":[["DOCTYPE", "hT", null, null, true]]},
58 wakaba 1.3
59     {"description":"<!DOCTYPE htm",
60     "input":"<!DOCTYPE htm",
61 wakaba 1.9 "output":["ParseError",["DOCTYPE", "htm", null, null, false]]},
62 wakaba 1.3
63     {"description":"<!DOCTYPE Htm",
64     "input":"<!DOCTYPE Htm",
65 wakaba 1.9 "output":["ParseError",["DOCTYPE", "Htm", null, null, false]]},
66 wakaba 1.3
67     {"description":"<!DOCTYPE hTM",
68     "input":"<!DOCTYPE hTM",
69 wakaba 1.9 "output":["ParseError",["DOCTYPE", "hTM", null, null, false]]},
70 wakaba 1.3
71     {"description":"<!DOCTYPE htm>",
72     "input":"<!DOCTYPE htm>",
73 wakaba 1.9 "output":[["DOCTYPE", "htm", null, null, true]]},
74 wakaba 1.3
75     {"description":"<!DOCTYPE Htm>",
76     "input":"<!DOCTYPE Htm>",
77 wakaba 1.9 "output":[["DOCTYPE", "Htm", null, null, true]]},
78 wakaba 1.3
79     {"description":"<!DOCTYPE hTM>",
80     "input":"<!DOCTYPE hTM>",
81 wakaba 1.9 "output":[["DOCTYPE", "hTM", null, null, true]]},
82 wakaba 1.3
83     {"description":"<!DOCTYPE html5",
84     "input":"<!DOCTYPE html5",
85 wakaba 1.9 "output":["ParseError",["DOCTYPE", "html5", null, null, false]]},
86 wakaba 1.3
87     {"description":"<!DOCTYPE html5>",
88     "input":"<!DOCTYPE html5>",
89 wakaba 1.9 "output":[["DOCTYPE", "html5", null, null, true]]},
90    
91     {"description":"PUBLIC\u0022\u0022",
92     "input":"<!DOCTYPE html PUBLIC\u0022\u0022>",
93     "output":[["DOCTYPE", "html", "", null, true]]},
94    
95     {"description":"PUBLIC''",
96     "input":"<!DOCTYPE html PUBLIC''>",
97     "output":[["DOCTYPE", "html", "", null, true]]},
98    
99     {"description":"PUBLICbogus",
100     "input":"<!DOCTYPE html PUBLICbogus>",
101     "output":["ParseError",["DOCTYPE", "html", null, null, false]]},
102    
103     {"description":"PUBLIC bogus",
104     "input":"<!DOCTYPE html PUBLIC bogus>",
105     "output":["ParseError",["DOCTYPE", "html", null, null, false]]},
106    
107     {"description":"PUBLIC \u0022\u0022bogus",
108     "input":"<!DOCTYPE html PUBLIC \u0022\u0022bogus>",
109     "output":["ParseError",["DOCTYPE", "html", "", null, false]]},
110    
111     {"description":"PUBLIC \u0022\u0022 bogus",
112     "input":"<!DOCTYPE html PUBLIC \u0022\u0022 bogus>",
113     "output":["ParseError",["DOCTYPE", "html", "", null, false]]},
114    
115     {"description":"PUBLIC \u0022\u0022 \u0022\u0022bogus",
116     "input":"<!DOCTYPE html PUBLIC \u0022\u0022 \u0022\u0022bogus>",
117     "output":["ParseError",["DOCTYPE", "html", "", "", false]]},
118    
119     {"description":"PUBLIC \u0022\u0022 \u0022\u0022 bogus",
120     "input":"<!DOCTYPE html PUBLIC \u0022\u0022 \u0022\u0022 bogus>",
121     "output":["ParseError",["DOCTYPE", "html", "", "", false]]},
122    
123     {"description":"PUBLIC \u0022\u0022\u0022\u0022>",
124     "input":"<!DOCTYPE html PUBLIC \u0022\u0022\u0022\u0022>",
125     "output":[["DOCTYPE", "html", "", "", true]]},
126    
127     {"description":"PUBLIC \u0022\u0022''>",
128     "input":"<!DOCTYPE html PUBLIC \u0022\u0022''>",
129     "output":[["DOCTYPE", "html", "", "", true]]},
130 wakaba 1.3
131 wakaba 1.13 {"description":"SYSTEM a",
132     "input":"<!DOCTYPE html SYSTEM a>",
133     "output":["ParseError", ["DOCTYPE", "html", null, null, false]]},
134    
135 wakaba 1.14 {"description":"<!---x-->",
136     "input":"<!---x-->",
137     "output":[["Comment", "-x"]]},
138    
139     {"description":"<!----x-->",
140     "input":"<!----x-->",
141     "output":["ParseError", ["Comment", "--x"]]},
142    
143 wakaba 1.1 {"description":"non-PCDATA content model flag, start tag-like string",
144     "contentModelFlags":["PLAINTEXT","RCDATA","CDATA"],
145     "input":"<div>",
146 wakaba 1.2 "output":[["Character", "<div>"]]},
147    
148     {"description":"end tag followed by character data",
149     "contentModelFlags":["RCDATA","CDATA"],
150     "lastStartTag":"xxx",
151     "input":"AB</xxx>CD",
152 wakaba 1.4 "output":[["Character", "AB"],["EndTag", "xxx"],["Character", "CD"]]},
153 wakaba 1.1
154 wakaba 1.12 {"description":"NULL character reference",
155     "input":"&#0;",
156     "output":["ParseError", ["Character", "\uFFFD"]]},
157    
158     {"description":"NULL character reference",
159     "input":"&#x0;",
160     "output":["ParseError", ["Character", "\uFFFD"]]},
161    
162     {"description":"character entity &#13;",
163     "input":"&#13;",
164     "output":["ParseError", ["Character", "\u000A"]]},
165    
166     {"description":"character entity &#xd;",
167     "input":"&#xd;",
168     "output":["ParseError", ["Character", "\u000A"]]},
169    
170     {"description":"character entities &#13;&#10;",
171     "input":"&#13;&#10;",
172     "output":["ParseError", ["Character", "\u000A\u000A"]]},
173    
174     {"description":"character entity &#13; followed by a LF",
175     "input":"&#13;\u000A",
176     "output":["ParseError", ["Character", "\u000A\u000A"]]},
177    
178 wakaba 1.4 {"description":"c1 character references",
179     "input":"&#128;&#129;&#130;&#131;&#132;&#133;&#134;&#135;",
180     "output":[
181     "ParseError", ["Character", "\u20AC"],
182     "ParseError", ["Character", "\uFFFD"],
183     "ParseError", ["Character", "\u201A"],
184     "ParseError", ["Character", "\u0192"],
185     "ParseError", ["Character", "\u201E"],
186     "ParseError", ["Character", "\u2026"],
187     "ParseError", ["Character", "\u2020"],
188     "ParseError", ["Character", "\u2021"]
189     ]},
190     {"description":"c1 character references",
191     "input":"&#136;&#137;&#138;&#139;&#140;&#141;&#142;&#143;",
192     "output":[
193     "ParseError", ["Character", "\u02C6"],
194     "ParseError", ["Character", "\u2030"],
195     "ParseError", ["Character", "\u0160"],
196     "ParseError", ["Character", "\u2039"],
197     "ParseError", ["Character", "\u0152"],
198     "ParseError", ["Character", "\uFFFD"],
199     "ParseError", ["Character", "\u017D"],
200     "ParseError", ["Character", "\uFFFD"]
201     ]},
202     {"description":"c1 character references",
203     "input":"&#144;&#145;&#146;&#147;&#148;&#149;&#150;&#151;",
204     "output":[
205     "ParseError", ["Character", "\uFFFD"],
206     "ParseError", ["Character", "\u2018"],
207     "ParseError", ["Character", "\u2019"],
208     "ParseError", ["Character", "\u201C"],
209     "ParseError", ["Character", "\u201D"],
210     "ParseError", ["Character", "\u2022"],
211     "ParseError", ["Character", "\u2013"],
212     "ParseError", ["Character", "\u2014"]
213     ]},
214     {"description":"c1 character references",
215     "input":"&#152;&#153;&#154;&#155;&#156;&#157;&#158;&#159;",
216     "output":[
217     "ParseError", ["Character", "\u02DC"],
218     "ParseError", ["Character", "\u2122"],
219     "ParseError", ["Character", "\u0161"],
220     "ParseError", ["Character", "\u203A"],
221     "ParseError", ["Character", "\u0153"],
222     "ParseError", ["Character", "\uFFFD"],
223     "ParseError", ["Character", "\u017E"],
224     "ParseError", ["Character", "\u0178"]
225     ]},
226    
227     {"description":"c1 character references",
228     "input":"&#x80;&#x81;&#x82;&#x83;&#x84;&#x85;&#x86;&#x87;",
229     "output":[
230     "ParseError", ["Character", "\u20AC"],
231     "ParseError", ["Character", "\uFFFD"],
232     "ParseError", ["Character", "\u201A"],
233     "ParseError", ["Character", "\u0192"],
234     "ParseError", ["Character", "\u201E"],
235     "ParseError", ["Character", "\u2026"],
236     "ParseError", ["Character", "\u2020"],
237     "ParseError", ["Character", "\u2021"]
238     ]},
239     {"description":"c1 character references",
240     "input":"&#x88;&#x89;&#x8a;&#x8b;&#x8c;&#x8d;&#x8e;&#x8f;",
241     "output":[
242     "ParseError", ["Character", "\u02C6"],
243     "ParseError", ["Character", "\u2030"],
244     "ParseError", ["Character", "\u0160"],
245     "ParseError", ["Character", "\u2039"],
246     "ParseError", ["Character", "\u0152"],
247     "ParseError", ["Character", "\uFFFD"],
248     "ParseError", ["Character", "\u017D"],
249     "ParseError", ["Character", "\uFFFD"]
250     ]},
251     {"description":"c1 character references",
252     "input":"&#x90;&#x91;&#x92;&#x93;&#x94;&#x95;&#x96;&#x97;",
253     "output":[
254     "ParseError", ["Character", "\uFFFD"],
255     "ParseError", ["Character", "\u2018"],
256     "ParseError", ["Character", "\u2019"],
257     "ParseError", ["Character", "\u201C"],
258     "ParseError", ["Character", "\u201D"],
259     "ParseError", ["Character", "\u2022"],
260     "ParseError", ["Character", "\u2013"],
261     "ParseError", ["Character", "\u2014"]
262     ]},
263     {"description":"c1 character references",
264     "input":"&#x98;&#x99;&#x9a;&#x9b;&#x9c;&#x9d;&#x9e;&#x9f;",
265     "output":[
266     "ParseError", ["Character", "\u02DC"],
267     "ParseError", ["Character", "\u2122"],
268     "ParseError", ["Character", "\u0161"],
269     "ParseError", ["Character", "\u203A"],
270     "ParseError", ["Character", "\u0153"],
271     "ParseError", ["Character", "\uFFFD"],
272     "ParseError", ["Character", "\u017E"],
273     "ParseError", ["Character", "\u0178"]
274 wakaba 1.5 ]},
275    
276 wakaba 1.12 {"description":"surrogate character reference",
277     "input":"&#xD800;",
278     "output":["ParseError", ["Character", "\uFFFD"]]},
279    
280     {"description":"surrogate character references",
281     "input":"&#xD800;&#xDFFF;",
282     "output":["ParseError", ["Character", "\uFFFD"],
283     "ParseError", ["Character", "\uFFFD"]]},
284    
285     {"description":"surrogate character reference",
286     "input":"\uD800&#xDFFF;",
287     "output":[["Character", "\uD800"],
288     "ParseError", ["Character", "\uFFFD"]]},
289    
290     {"description":"surrogate character reference",
291     "input":"&#xD800;\uDFFF",
292     "output":["ParseError", ["Character", "\uFFFD\uDFFF"]]},
293    
294     {"description":"surrogate character reference",
295     "input":"&#55296;",
296     "output":["ParseError", ["Character", "\uFFFD"]]},
297    
298     {"description":"surrogate character reference",
299     "input":"&#57343;",
300     "output":["ParseError", ["Character", "\uFFFD"]]},
301    
302     {"description":"non-Unicode character reference",
303     "input":"&#1114112;",
304     "output":["ParseError", ["Character", "\uFFFD"]]},
305    
306     {"description":"non-Unicode character reference",
307     "input":"&#x110000;",
308     "output":["ParseError", ["Character", "\uFFFD"]]},
309    
310 wakaba 1.5 {"description":"NULL character",
311     "input":"\u0000",
312 wakaba 1.6 "output":["ParseError",["Character", "\uFFFD"]]},
313    
314     {"description":"&TRADE;",
315     "input":"&TRADE;",
316 wakaba 1.7 "output":[["Character", "\u2122"]]},
317    
318     {"description":"&lang;",
319     "input":"&lang;",
320     "output":[["Character", "\u3008"]]},
321    
322     {"description":"&rang;",
323     "input":"&rang;",
324     "output":[["Character", "\u3009"]]},
325    
326     {"description":"&amp;;",
327     "input":"&amp;;",
328 wakaba 1.8 "output":[["Character", "&;"]]},
329    
330 wakaba 1.11 {"description":"&HT",
331     "input":"&\u0009",
332     "output":[["Character", "&\u0009"]]},
333    
334     {"description":"&LF",
335     "input":"&\u000A",
336     "output":[["Character", "&\u000A"]]},
337    
338     {"description":"&VT",
339     "input":"&\u000B",
340     "output":[["Character", "&\u000B"]]},
341    
342     {"description":"&FF",
343     "input":"&\u000C",
344     "output":[["Character", "&\u000C"]]},
345    
346     {"description":"&SP",
347     "input":"& ",
348     "output":[["Character", "& "]]},
349    
350     {"description":"&<",
351     "input":"&<",
352 wakaba 1.12 "output":[["Character", "&"], "ParseError", ["Character", "<"]]},
353 wakaba 1.11
354     {"description":"&<p>",
355     "input":"&<p>",
356     "output":[["Character", "&"], ["StartTag", "p", {}]]},
357    
358     {"description":"&&",
359     "input":"&&",
360     "output":[["Character", "&&"]]},
361    
362     {"description":"&&amp;",
363     "input":"&&amp;",
364     "output":[["Character", "&&"]]},
365    
366     {"description":"&",
367     "input":"&",
368     "output":[["Character", "&"]]},
369 wakaba 1.12
370     {"description":"named character reference w/o refc",
371     "input":"&ampabc",
372     "output":["ParseError", ["Character", "&abc"]]},
373    
374     {"description":"named character reference",
375     "input":"&amp;abc",
376     "output":[["Character", "&abc"]]},
377    
378     {"description":"named character reference w/o refc",
379     "input":"&abc",
380     "output":["ParseError", ["Character", "&abc"]]},
381    
382     {"description":"unknown named character reference",
383     "input":"&abc;",
384     "output":["ParseError", ["Character", "&abc;"]]},
385    
386     {"description":"named character reference w/o refc in attr",
387     "input":"<a href='&ampabc'>",
388     "output":["ParseError", ["StartTag", "a", {"href": "&ampabc"}]]},
389    
390     {"description":"named character reference in attr",
391     "input":"<a href='&amp;abc'>",
392     "output":[["StartTag", "a", {"href": "&abc"}]]},
393    
394     {"description":"named character reference w/o refc in attr",
395     "input":"<a href='&abc'>",
396     "output":["ParseError", ["StartTag", "a", {"href": "&abc"}]]},
397    
398     {"description":"unknown named character reference in attr",
399     "input":"<a href='&abc;'>",
400     "output":["ParseError", ["StartTag", "a", {"href": "&abc;"}]]},
401 wakaba 1.11
402 wakaba 1.8 {"description":"cdata end tag containing <",
403     "contentModelFlags":["RCDATA","CDATA"],
404     "lastStartTag":"xxx",
405     "input":"</xxx<div>",
406 wakaba 1.10 "output":[["Character", "</xxx<div>"]]},
407 wakaba 1.8
408     {"description":"< in tag name state",
409     "input":"<p<div>",
410     "output":[["StartTag", "p<div", {}]]},
411    
412     {"description":"< in before attribute name state",
413     "input":"<p <div>",
414     "output":[["StartTag", "p", {"<div":""}]]},
415    
416     {"description":"< in attribute name state",
417     "input":"<p align<div>",
418     "output":[["StartTag", "p", {"align<div":""}]]},
419    
420     {"description":"< in after attribute name state",
421     "input":"<p align <div>",
422     "output":[["StartTag", "p", {"align":"","<div":""}]]},
423    
424     {"description":"< in before attribute value state",
425     "input":"<p align=<div>",
426     "output":[["StartTag", "p", {"align":"<div"}]]},
427    
428     {"description":"< in attribute value (unquoted) state",
429     "input":"<p align=left<div>",
430     "output":[["StartTag", "p", {"align":"left<div"}]]},
431    
432     {"description":"< in attribute value (single-unquoted) state",
433     "input":"<p align='left<div>",
434     "output":["ParseError", ["StartTag", "p", {"align":"left<div>"}]]},
435    
436     {"description":"< in attribute value (double-unquoted) state",
437     "input":"<p align=\u0022left<div>",
438     "output":["ParseError", ["StartTag", "p", {"align":"left<div>"}]]}
439 wakaba 1.4
440     ]}

admin@suikawiki.org
ViewVC Help
Powered by ViewVC 1.1.24