/[suikacvs]/markup/html/whatpm/t/tokenizer/test1.test
Suika

Contents of /markup/html/whatpm/t/tokenizer/test1.test

Parent Directory Parent Directory | Revision Log Revision Log

Revision 1.3 - (hide annotations) (download)
Mon Jul 16 07:03:09 2007 UTC (18 years ago) by wakaba
Branch: MAIN
Changes since 1.2: +4 -0 lines 
++ whatpm/t/ChangeLog	16 Jul 2007 07:03:04 -0000
	* HTML-tokenizer.t: It now requires newer version
	of JSON.pm due to the broken handling for utf8 string
	of older version.  Test data files |test3.test|
	and |test4.test| are added.  Convert surrogate
	pair |\u| escapes in JSON file before it is input
	into JSON.pm parser since it does not decode
	them correctly.  U+000D convertion was incorrect.

	* HTML-tree.t: Support for new format for fragment
	parsing tests.

	* Makefile (tokenizer-files): New test
	data files |test3.test| and |test4.test| are added.

	* tokenizer-test-1.test: Test data for bare |hcro| and
	entity references in attribute values are added.

	* tokenizer-test-2.dat: Test data for U+000D are added.

2007-07-16  Wakaba  <wakaba@suika.fam.cx>

++ whatpm/Whatpm/ChangeLog	16 Jul 2007 06:56:42 -0000
	* HTML.pm.src: The character immediately following
	a bare |hcro| was discarded.  Fix handling of
	entity references in attribute values.

2007-07-16  Wakaba  <wakaba@suika.fam.cx>
1 wakaba 1.1 {"tests": [
2    
3     {"description":"Correct Doctype lowercase",
4     "input":"<!DOCTYPE html>",
5 wakaba 1.2 "output":[["DOCTYPE", "html", null, null, true]]},
6 wakaba 1.1
7     {"description":"Correct Doctype uppercase",
8 wakaba 1.2 "input":"<!DOCTYPE HTML>",
9     "output":[["DOCTYPE", "HTML", null, null, true]]},
10 wakaba 1.1
11     {"description":"Correct Doctype mixed case",
12     "input":"<!DOCTYPE HtMl>",
13 wakaba 1.2 "output":[["DOCTYPE", "HtMl", null, null, true]]},
14 wakaba 1.1
15     {"description":"Truncated doctype start",
16     "input":"<!DOC>",
17     "output":["ParseError", ["Comment", "DOC"]]},
18    
19     {"description":"Doctype in error",
20     "input":"<!DOCTYPE foo>",
21 wakaba 1.2 "output":[["DOCTYPE", "foo", null, null, true]]},
22 wakaba 1.1
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":[["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 wakaba 1.2 {"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 wakaba 1.1 "input":"&",
102 wakaba 1.2 "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 wakaba 1.1
112     {"description":"Unfinished entity",
113     "input":"&f",
114 wakaba 1.2 "output":["ParseError", ["Character", "&f"]]},
115 wakaba 1.1
116     {"description":"Ampersand, number sign",
117     "input":"&#",
118 wakaba 1.2 "output":["ParseError", ["Character", "&#"]]},
119 wakaba 1.1
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 &not;it",
126     "output":[["Character","I'm ¬it"]]},
127    
128     {"description":"Entity with trailing semicolon (2)",
129     "input":"I'm &notin;",
130     "output":[["Character","I'm ∉"]]},
131    
132     {"description":"Entity without trailing semicolon (1)",
133     "input":"I'm &notit",
134 wakaba 1.2 "output":[["Character","I'm "], "ParseError", ["Character", "¬it"]]},
135 wakaba 1.1
136     {"description":"Entity without trailing semicolon (2)",
137     "input":"I'm &notin",
138 wakaba 1.2 "output":[["Character","I'm "], "ParseError", ["Character", "¬in"]]},
139 wakaba 1.1
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":"ASCII decimal entity",
145     "input":"&#0036;",
146     "output":[["Character","$"]]},
147    
148     {"description":"ASCII hexadecimal entity",
149     "input":"&#x3f;",
150     "output":[["Character","?"]]},
151    
152     {"description":"Hexadecimal entity in attribute",
153     "input":"<h a='&#x3f;'></h>",
154 wakaba 1.2 "output":[["StartTag", "h", {"a":"?"}], ["EndTag", "h"]]},
155    
156     {"description":"Entity in attribute without semicolon ending in x",
157     "input":"<h a='&notx'>",
158     "output":["ParseError", ["StartTag", "h", {"a":"&notx"}]]},
159    
160     {"description":"Entity in attribute without semicolon ending in 1",
161     "input":"<h a='&not1'>",
162     "output":["ParseError", ["StartTag", "h", {"a":"&not1"}]]},
163    
164 wakaba 1.3 {"description":"Entity in attribute without semicolon ending in i",
165     "input":"<h a='&noti'>",
166     "output":["ParseError", ["StartTag", "h", {"a":"&noti"}]]},
167    
168 wakaba 1.2 {"description":"Entity in attribute without semicolon",
169     "input":"<h a='&COPY'>",
170     "output":["ParseError", ["StartTag", "h", {"a":"©"}]]}
171 wakaba 1.1
172     ]}
admin@suikawiki.org
 ViewVC Help
Powered by ViewVC 1.1.24