t/tokenizer/test1.test

{"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":"Non-ASCII character reference name",
"input":"&\u00AC;",
"output":["ParseError", ["Character", "&\u00AC;"]]},

{"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"}]]}

]}
1	{"tests": [
2
3	{"description":"Correct Doctype lowercase",
4	"input":"<!DOCTYPE html>",
5	"output":[["DOCTYPE", "html", null, null, true]]},
6
7	{"description":"Correct Doctype uppercase",
8	"input":"<!DOCTYPE HTML>",
9	"output":[["DOCTYPE", "HTML", null, null, true]]},
10
11	{"description":"Correct Doctype mixed case",
12	"input":"<!DOCTYPE HtMl>",
13	"output":[["DOCTYPE", "HtMl", null, null, true]]},
14
15	{"description":"Truncated doctype start",
16	"input":"<!DOC>",
17	"output":["ParseError", ["Comment", "DOC"]]},
18
19	{"description":"Doctype in error",
20	"input":"<!DOCTYPE foo>",
21	"output":[["DOCTYPE", "foo", null, null, true]]},
22
23	{"description":"Single Start Tag",
24	"input":"<h>",
25	"output":[["StartTag", "h", {}]]},
26
27	{"description":"Empty end tag",
28	"input":"</>",
29	"output":["ParseError"]},
30
31	{"description":"Empty start tag",
32	"input":"<>",
33	"output":["ParseError", ["Character", "<>"]]},
34
35	{"description":"Start Tag w/attribute",
36	"input":"<h a='b'>",
37	"output":[["StartTag", "h", {"a":"b"}]]},
38
39	{"description":"Start Tag w/attribute no quotes",
40	"input":"<h a=b>",
41	"output":[["StartTag", "h", {"a":"b"}]]},
42
43	{"description":"Start/End Tag",
44	"input":"<h></h>",
45	"output":[["StartTag", "h", {}], ["EndTag", "h"]]},
46
47	{"description":"Two unclosed start tags",
48	"input":"<p>One<p>Two",
49	"output":[["StartTag", "p", {}], ["Character", "One"], ["StartTag", "p", {}], ["Character", "Two"]]},
50
51	{"description":"End Tag w/attribute",
52	"input":"<h></h a='b'>",
53	"output":[["StartTag", "h", {}], "ParseError", ["EndTag", "h"]]},
54
55	{"description":"Multiple atts",
56	"input":"<h a='b' c='d'>",
57	"output":[["StartTag", "h", {"a":"b", "c":"d"}]]},
58
59	{"description":"Multiple atts no space",
60	"input":"<h a='b'c='d'>",
61	"output":["ParseError", ["StartTag", "h", {"a":"b", "c":"d"}]]},
62
63	{"description":"Repeated attr",
64	"input":"<h a='b' a='d'>",
65	"output":["ParseError", ["StartTag", "h", {"a":"b"}]]},
66
67	{"description":"Simple comment",
68	"input":"<!--comment-->",
69	"output":[["Comment", "comment"]]},
70
71	{"description":"Comment, Central dash no space",
72	"input":"<!----->",
73	"output":["ParseError", ["Comment", "-"]]},
74
75	{"description":"Comment, two central dashes",
76	"input":"<!-- --comment -->",
77	"output":["ParseError", ["Comment", " --comment "]]},
78
79	{"description":"Unfinished comment",
80	"input":"<!--comment",
81	"output":["ParseError", ["Comment", "comment"]]},
82
83	{"description":"Start of a comment",
84	"input":"<!-",
85	"output":["ParseError", ["Comment", "-"]]},
86
87	{"description":"Short comment",
88	"input":"<!-->",
89	"output":["ParseError", ["Comment", ""]]},
90
91	{"description":"Short comment two",
92	"input":"<!--->",
93	"output":["ParseError", ["Comment", ""]]},
94
95	{"description":"Short comment three",
96	"input":"<!---->",
97	"output":[["Comment", ""]]},
98
99
100	{"description":"Ampersand EOF",
101	"input":"&",
102	"output":[["Character", "&"]]},
103
104	{"description":"Ampersand ampersand EOF",
105	"input":"&&",
106	"output":[["Character", "&&"]]},
107
108	{"description":"Ampersand space EOF",
109	"input":"& ",
110	"output":[["Character", "& "]]},
111
112	{"description":"Unfinished entity",
113	"input":"&f",
114	"output":["ParseError", ["Character", "&f"]]},
115
116	{"description":"Ampersand, number sign",
117	"input":"&#",
118	"output":["ParseError", ["Character", "&#"]]},
119
120	{"description":"Unfinished numeric entity",
121	"input":"&#x",
122	"output":["ParseError", ["Character", "&#x"]]},
123
124	{"description":"Entity with trailing semicolon (1)",
125	"input":"I'm ¬it",
126	"output":[["Character","I'm \u00ACit"]]},
127
128	{"description":"Entity with trailing semicolon (2)",
129	"input":"I'm ∉",
130	"output":[["Character","I'm \u2209"]]},
131
132	{"description":"Entity without trailing semicolon (1)",
133	"input":"I'm &notit",
134	"output":[["Character","I'm "], "ParseError", ["Character", "\u00ACit"]]},
135
136	{"description":"Entity without trailing semicolon (2)",
137	"input":"I'm &notin",
138	"output":[["Character","I'm "], "ParseError", ["Character", "\u00ACin"]]},
139
140	{"description":"Partial entity match at end of file",
141	"input":"I'm &no",
142	"output":[["Character","I'm "], "ParseError", ["Character", "&no"]]},
143
144	{"description":"Non-ASCII character reference name",
145	"input":"&\u00AC;",
146	"output":["ParseError", ["Character", "&\u00AC;"]]},
147
148	{"description":"ASCII decimal entity",
149	"input":"$",
150	"output":[["Character","$"]]},
151
152	{"description":"ASCII hexadecimal entity",
153	"input":"?",
154	"output":[["Character","?"]]},
155
156	{"description":"Hexadecimal entity in attribute",
157	"input":"<h a='?'></h>",
158	"output":[["StartTag", "h", {"a":"?"}], ["EndTag", "h"]]},
159
160	{"description":"Entity in attribute without semicolon ending in x",
161	"input":"<h a='&notx'>",
162	"output":["ParseError", ["StartTag", "h", {"a":"&notx"}]]},
163
164	{"description":"Entity in attribute without semicolon ending in 1",
165	"input":"<h a='&not1'>",
166	"output":["ParseError", ["StartTag", "h", {"a":"&not1"}]]},
167
168	{"description":"Entity in attribute without semicolon ending in i",
169	"input":"<h a='&noti'>",
170	"output":["ParseError", ["StartTag", "h", {"a":"&noti"}]]},
171
172	{"description":"Entity in attribute without semicolon",
173	"input":"<h a='&COPY'>",
174	"output":["ParseError", ["StartTag", "h", {"a":"\u00A9"}]]}
175
176	]}