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 |
1.1 |
{"description":"non-PCDATA content model flag, start tag-like string", |
132 |
|
|
"contentModelFlags":["PLAINTEXT","RCDATA","CDATA"], |
133 |
|
|
"input":"<div>", |
134 |
wakaba |
1.2 |
"output":[["Character", "<div>"]]}, |
135 |
|
|
|
136 |
|
|
{"description":"end tag followed by character data", |
137 |
|
|
"contentModelFlags":["RCDATA","CDATA"], |
138 |
|
|
"lastStartTag":"xxx", |
139 |
|
|
"input":"AB</xxx>CD", |
140 |
wakaba |
1.4 |
"output":[["Character", "AB"],["EndTag", "xxx"],["Character", "CD"]]}, |
141 |
wakaba |
1.1 |
|
142 |
wakaba |
1.4 |
{"description":"c1 character references", |
143 |
|
|
"input":"€‚ƒ„…†‡", |
144 |
|
|
"output":[ |
145 |
|
|
"ParseError", ["Character", "\u20AC"], |
146 |
|
|
"ParseError", ["Character", "\uFFFD"], |
147 |
|
|
"ParseError", ["Character", "\u201A"], |
148 |
|
|
"ParseError", ["Character", "\u0192"], |
149 |
|
|
"ParseError", ["Character", "\u201E"], |
150 |
|
|
"ParseError", ["Character", "\u2026"], |
151 |
|
|
"ParseError", ["Character", "\u2020"], |
152 |
|
|
"ParseError", ["Character", "\u2021"] |
153 |
|
|
]}, |
154 |
|
|
{"description":"c1 character references", |
155 |
|
|
"input":"ˆ‰Š‹ŒŽ", |
156 |
|
|
"output":[ |
157 |
|
|
"ParseError", ["Character", "\u02C6"], |
158 |
|
|
"ParseError", ["Character", "\u2030"], |
159 |
|
|
"ParseError", ["Character", "\u0160"], |
160 |
|
|
"ParseError", ["Character", "\u2039"], |
161 |
|
|
"ParseError", ["Character", "\u0152"], |
162 |
|
|
"ParseError", ["Character", "\uFFFD"], |
163 |
|
|
"ParseError", ["Character", "\u017D"], |
164 |
|
|
"ParseError", ["Character", "\uFFFD"] |
165 |
|
|
]}, |
166 |
|
|
{"description":"c1 character references", |
167 |
|
|
"input":"‘’“”•–—", |
168 |
|
|
"output":[ |
169 |
|
|
"ParseError", ["Character", "\uFFFD"], |
170 |
|
|
"ParseError", ["Character", "\u2018"], |
171 |
|
|
"ParseError", ["Character", "\u2019"], |
172 |
|
|
"ParseError", ["Character", "\u201C"], |
173 |
|
|
"ParseError", ["Character", "\u201D"], |
174 |
|
|
"ParseError", ["Character", "\u2022"], |
175 |
|
|
"ParseError", ["Character", "\u2013"], |
176 |
|
|
"ParseError", ["Character", "\u2014"] |
177 |
|
|
]}, |
178 |
|
|
{"description":"c1 character references", |
179 |
|
|
"input":"˜™š›œžŸ", |
180 |
|
|
"output":[ |
181 |
|
|
"ParseError", ["Character", "\u02DC"], |
182 |
|
|
"ParseError", ["Character", "\u2122"], |
183 |
|
|
"ParseError", ["Character", "\u0161"], |
184 |
|
|
"ParseError", ["Character", "\u203A"], |
185 |
|
|
"ParseError", ["Character", "\u0153"], |
186 |
|
|
"ParseError", ["Character", "\uFFFD"], |
187 |
|
|
"ParseError", ["Character", "\u017E"], |
188 |
|
|
"ParseError", ["Character", "\u0178"] |
189 |
|
|
]}, |
190 |
|
|
|
191 |
|
|
{"description":"c1 character references", |
192 |
|
|
"input":"€‚ƒ„…†‡", |
193 |
|
|
"output":[ |
194 |
|
|
"ParseError", ["Character", "\u20AC"], |
195 |
|
|
"ParseError", ["Character", "\uFFFD"], |
196 |
|
|
"ParseError", ["Character", "\u201A"], |
197 |
|
|
"ParseError", ["Character", "\u0192"], |
198 |
|
|
"ParseError", ["Character", "\u201E"], |
199 |
|
|
"ParseError", ["Character", "\u2026"], |
200 |
|
|
"ParseError", ["Character", "\u2020"], |
201 |
|
|
"ParseError", ["Character", "\u2021"] |
202 |
|
|
]}, |
203 |
|
|
{"description":"c1 character references", |
204 |
|
|
"input":"ˆ‰Š‹ŒŽ", |
205 |
|
|
"output":[ |
206 |
|
|
"ParseError", ["Character", "\u02C6"], |
207 |
|
|
"ParseError", ["Character", "\u2030"], |
208 |
|
|
"ParseError", ["Character", "\u0160"], |
209 |
|
|
"ParseError", ["Character", "\u2039"], |
210 |
|
|
"ParseError", ["Character", "\u0152"], |
211 |
|
|
"ParseError", ["Character", "\uFFFD"], |
212 |
|
|
"ParseError", ["Character", "\u017D"], |
213 |
|
|
"ParseError", ["Character", "\uFFFD"] |
214 |
|
|
]}, |
215 |
|
|
{"description":"c1 character references", |
216 |
|
|
"input":"‘’“”•–—", |
217 |
|
|
"output":[ |
218 |
|
|
"ParseError", ["Character", "\uFFFD"], |
219 |
|
|
"ParseError", ["Character", "\u2018"], |
220 |
|
|
"ParseError", ["Character", "\u2019"], |
221 |
|
|
"ParseError", ["Character", "\u201C"], |
222 |
|
|
"ParseError", ["Character", "\u201D"], |
223 |
|
|
"ParseError", ["Character", "\u2022"], |
224 |
|
|
"ParseError", ["Character", "\u2013"], |
225 |
|
|
"ParseError", ["Character", "\u2014"] |
226 |
|
|
]}, |
227 |
|
|
{"description":"c1 character references", |
228 |
|
|
"input":"˜™š›œžŸ", |
229 |
|
|
"output":[ |
230 |
|
|
"ParseError", ["Character", "\u02DC"], |
231 |
|
|
"ParseError", ["Character", "\u2122"], |
232 |
|
|
"ParseError", ["Character", "\u0161"], |
233 |
|
|
"ParseError", ["Character", "\u203A"], |
234 |
|
|
"ParseError", ["Character", "\u0153"], |
235 |
|
|
"ParseError", ["Character", "\uFFFD"], |
236 |
|
|
"ParseError", ["Character", "\u017E"], |
237 |
|
|
"ParseError", ["Character", "\u0178"] |
238 |
wakaba |
1.5 |
]}, |
239 |
|
|
|
240 |
|
|
{"description":"NULL character", |
241 |
|
|
"input":"\u0000", |
242 |
wakaba |
1.6 |
"output":["ParseError",["Character", "\uFFFD"]]}, |
243 |
|
|
|
244 |
|
|
{"description":"™", |
245 |
|
|
"input":"™", |
246 |
wakaba |
1.7 |
"output":[["Character", "\u2122"]]}, |
247 |
|
|
|
248 |
|
|
{"description":"⟨", |
249 |
|
|
"input":"⟨", |
250 |
|
|
"output":[["Character", "\u3008"]]}, |
251 |
|
|
|
252 |
|
|
{"description":"⟩", |
253 |
|
|
"input":"⟩", |
254 |
|
|
"output":[["Character", "\u3009"]]}, |
255 |
|
|
|
256 |
|
|
{"description":"&;", |
257 |
|
|
"input":"&;", |
258 |
wakaba |
1.8 |
"output":[["Character", "&;"]]}, |
259 |
|
|
|
260 |
|
|
{"description":"cdata end tag containing <", |
261 |
|
|
"contentModelFlags":["RCDATA","CDATA"], |
262 |
|
|
"lastStartTag":"xxx", |
263 |
|
|
"input":"</xxx<div>", |
264 |
wakaba |
1.10 |
"output":[["Character", "</xxx<div>"]]}, |
265 |
wakaba |
1.8 |
|
266 |
|
|
{"description":"< in tag name state", |
267 |
|
|
"input":"<p<div>", |
268 |
|
|
"output":[["StartTag", "p<div", {}]]}, |
269 |
|
|
|
270 |
|
|
{"description":"< in before attribute name state", |
271 |
|
|
"input":"<p <div>", |
272 |
|
|
"output":[["StartTag", "p", {"<div":""}]]}, |
273 |
|
|
|
274 |
|
|
{"description":"< in attribute name state", |
275 |
|
|
"input":"<p align<div>", |
276 |
|
|
"output":[["StartTag", "p", {"align<div":""}]]}, |
277 |
|
|
|
278 |
|
|
{"description":"< in after attribute name state", |
279 |
|
|
"input":"<p align <div>", |
280 |
|
|
"output":[["StartTag", "p", {"align":"","<div":""}]]}, |
281 |
|
|
|
282 |
|
|
{"description":"< in before attribute value state", |
283 |
|
|
"input":"<p align=<div>", |
284 |
|
|
"output":[["StartTag", "p", {"align":"<div"}]]}, |
285 |
|
|
|
286 |
|
|
{"description":"< in attribute value (unquoted) state", |
287 |
|
|
"input":"<p align=left<div>", |
288 |
|
|
"output":[["StartTag", "p", {"align":"left<div"}]]}, |
289 |
|
|
|
290 |
|
|
{"description":"< in attribute value (single-unquoted) state", |
291 |
|
|
"input":"<p align='left<div>", |
292 |
|
|
"output":["ParseError", ["StartTag", "p", {"align":"left<div>"}]]}, |
293 |
|
|
|
294 |
|
|
{"description":"< in attribute value (double-unquoted) state", |
295 |
|
|
"input":"<p align=\u0022left<div>", |
296 |
|
|
"output":["ParseError", ["StartTag", "p", {"align":"left<div>"}]]} |
297 |
wakaba |
1.4 |
|
298 |
|
|
]} |