summaryrefslogtreecommitdiff
path: root/test/data/tokeniser2/test1.test
blob: ddb98146eeaebf735e1e5492389bf7add57f75cc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
{"tests": [

{"description":"Correct Doctype lowercase",
"input":"<!DOCTYPE html>",
"output":[["DOCTYPE", "html", null, null, true]]},

{"description":"Correct Doctype uppercase",
"input":"<!DOCTYPE HTML>",
"output":[["DOCTYPE", "HTML", null, null, true]]},

{"description":"Correct Doctype mixed case",
"input":"<!DOCTYPE HtMl>", 
"output":[["DOCTYPE", "HtMl", null, null, true]]},

{"description":"Truncated doctype start",
"input":"<!DOC>", 
"output":["ParseError", ["Comment", "DOC"]]},

{"description":"Doctype in error",
"input":"<!DOCTYPE foo>", 
"output":[["DOCTYPE", "foo", null, null, true]]},

{"description":"Single Start Tag",
"input":"<h>",
"output":[["StartTag", "h", {}]]},

{"description":"Empty end tag",
"input":"</>",
"output":["ParseError"]},

{"description":"Empty start tag",
"input":"<>",
"output":["ParseError", ["Character", "<>"]]},

{"description":"Start Tag w/attribute",
"input":"<h a='b'>",
"output":[["StartTag", "h", {"a":"b"}]]},

{"description":"Start Tag w/attribute no quotes",
"input":"<h a=b>",
"output":[["StartTag", "h", {"a":"b"}]]},

{"description":"Start/End Tag",
"input":"<h></h>",
"output":[["StartTag", "h", {}], ["EndTag", "h"]]},

{"description":"Two unclosed start tags",
"input":"<p>One<p>Two",
"output":[["StartTag", "p", {}], ["Character", "One"], ["StartTag", "p", {}], ["Character", "Two"]]},

{"description":"End Tag w/attribute",
"input":"<h></h a='b'>",
"output":[["StartTag", "h", {}], "ParseError", ["EndTag", "h"]]},

{"description":"Multiple atts",
"input":"<h a='b' c='d'>",
"output":[["StartTag", "h", {"a":"b", "c":"d"}]]},

{"description":"Multiple atts no space",
"input":"<h a='b'c='d'>",
"output":["ParseError", ["StartTag", "h", {"a":"b", "c":"d"}]]},

{"description":"Repeated attr",
 "input":"<h a='b' a='d'>",
 "output":["ParseError", ["StartTag", "h", {"a":"b"}]]},

{"description":"Simple comment",
 "input":"<!--comment-->",
 "output":[["Comment", "comment"]]},

{"description":"Comment, Central dash no space",
 "input":"<!----->",
 "output":["ParseError", ["Comment", "-"]]},

{"description":"Comment, two central dashes",
"input":"<!-- --comment -->",
"output":["ParseError", ["Comment", " --comment "]]},

{"description":"Unfinished comment",
"input":"<!--comment",
"output":["ParseError", ["Comment", "comment"]]},

{"description":"Start of a comment",
"input":"<!-",
"output":["ParseError", ["Comment", "-"]]},

{"description":"Short comment",
 "input":"<!-->",
 "output":["ParseError", ["Comment", ""]]},

{"description":"Short comment two",
 "input":"<!--->",
 "output":["ParseError", ["Comment", ""]]},

{"description":"Short comment three",
 "input":"<!---->",
 "output":[["Comment", ""]]},


{"description":"Ampersand EOF",
"input":"&",
"output":[["Character", "&"]]},

{"description":"Ampersand ampersand EOF",
"input":"&&",
"output":[["Character", "&&"]]},

{"description":"Ampersand space EOF",
"input":"& ",
"output":[["Character", "& "]]},

{"description":"Unfinished entity",
"input":"&f",
"output":["ParseError", ["Character", "&f"]]},

{"description":"Ampersand, number sign",
"input":"&#",
"output":["ParseError", ["Character", "&#"]]},

{"description":"Unfinished numeric entity",
"input":"&#x",
"output":["ParseError", ["Character", "&#x"]]},

{"description":"Entity with trailing semicolon (1)",
"input":"I'm &not;it",
"output":[["Character","I'm \u00ACit"]]},

{"description":"Entity with trailing semicolon (2)",
"input":"I'm &notin;",
"output":[["Character","I'm \u2209"]]},

{"description":"Entity without trailing semicolon (1)",
"input":"I'm &notit",
"output":[["Character","I'm "], "ParseError", ["Character", "\u00ACit"]]},

{"description":"Entity without trailing semicolon (2)",
"input":"I'm &notin",
"output":[["Character","I'm "], "ParseError", ["Character", "\u00ACin"]]},

{"description":"Partial entity match at end of file",
"input":"I'm &no",
"output":[["Character","I'm "], "ParseError", ["Character", "&no"]]},

{"description":"ASCII decimal entity",
"input":"&#0036;",
"output":[["Character","$"]]},

{"description":"ASCII hexadecimal entity",
"input":"&#x3f;",
"output":[["Character","?"]]},

{"description":"Hexadecimal entity in attribute",
"input":"<h a='&#x3f;'></h>",
"output":[["StartTag", "h", {"a":"?"}], ["EndTag", "h"]]},

{"description":"Entity in attribute without semicolon ending in x",
"input":"<h a='&notx'>",
"output":["ParseError", ["StartTag", "h", {"a":"&notx"}]]},

{"description":"Entity in attribute without semicolon ending in 1",
"input":"<h a='&not1'>",
"output":["ParseError", ["StartTag", "h", {"a":"&not1"}]]},

{"description":"Entity in attribute without semicolon ending in i",
"input":"<h a='&noti'>",
"output":["ParseError", ["StartTag", "h", {"a":"&noti"}]]},

{"description":"Entity in attribute without semicolon",
"input":"<h a='&COPY'>",
"output":["ParseError", ["StartTag", "h", {"a":"\u00A9"}]]}

]}