forked from html5lib/html5lib-python
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_parser2.py
More file actions
121 lines (91 loc) · 5 KB
/
Copy pathtest_parser2.py
File metadata and controls
121 lines (91 loc) · 5 KB
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
import io
from . import support # noqa
from html5lib.constants import namespaces, tokenTypes
from html5lib import parse, parseFragment, HTMLParser
# tests that aren't autogenerated from text files
def test_assertDoctypeCloneable():
doc = parse('<!DOCTYPE HTML>', treebuilder="dom")
assert doc.cloneNode(True) is not None
def test_line_counter():
# http://groups.google.com/group/html5lib-discuss/browse_frm/thread/f4f00e4a2f26d5c0
assert parse("<pre>\nx\n>\n</pre>") is not None
def test_namespace_html_elements_0_dom():
doc = parse("<html></html>",
treebuilder="dom",
namespaceHTMLElements=True)
assert doc.childNodes[0].namespaceURI == namespaces["html"]
def test_namespace_html_elements_1_dom():
doc = parse("<html></html>",
treebuilder="dom",
namespaceHTMLElements=False)
assert doc.childNodes[0].namespaceURI is None
def test_namespace_html_elements_0_etree():
doc = parse("<html></html>",
treebuilder="etree",
namespaceHTMLElements=True)
assert doc.tag == "{%s}html" % (namespaces["html"],)
def test_namespace_html_elements_1_etree():
doc = parse("<html></html>",
treebuilder="etree",
namespaceHTMLElements=False)
assert doc.tag == "html"
def test_unicode_file():
assert parse(io.StringIO("a")) is not None
def test_maintain_attribute_order():
# This is here because we impl it in parser and not tokenizer
p = HTMLParser()
# generate loads to maximize the chance a hash-based mutation will occur
attrs = [(chr(x), i) for i, x in enumerate(range(ord('a'), ord('z')))]
token = {'name': 'html',
'selfClosing': False,
'selfClosingAcknowledged': False,
'type': tokenTypes["StartTag"],
'data': attrs}
out = p.normalizeToken(token)
attr_order = list(out["data"].keys())
assert attr_order == [x for x, i in attrs]
def test_duplicate_attribute():
# This is here because we impl it in parser and not tokenizer
doc = parse('<p class=a class=b>')
el = doc[1][0]
assert el.get("class") == "a"
def test_maintain_duplicate_attribute_order():
# This is here because we impl it in parser and not tokenizer
p = HTMLParser()
attrs = [(chr(x), i) for i, x in enumerate(range(ord('a'), ord('z')))]
token = {'name': 'html',
'selfClosing': False,
'selfClosingAcknowledged': False,
'type': tokenTypes["StartTag"],
'data': attrs + [('a', len(attrs))]}
out = p.normalizeToken(token)
attr_order = list(out["data"].keys())
assert attr_order == [x for x, i in attrs]
def test_debug_log():
parser = HTMLParser(debug=True)
parser.parse("<!doctype html><title>a</title><p>b<script>c</script>d</p>e")
expected = [('dataState', 'InitialPhase', 'InitialPhase', 'processDoctype', {'type': 'Doctype'}),
('dataState', 'BeforeHtmlPhase', 'BeforeHtmlPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
('dataState', 'BeforeHeadPhase', 'BeforeHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'title', 'type': 'StartTag'}),
('rcdataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'title', 'type': 'EndTag'}),
('dataState', 'InHeadPhase', 'InHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
('dataState', 'AfterHeadPhase', 'AfterHeadPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'p', 'type': 'StartTag'}),
('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
('dataState', 'InBodyPhase', 'InBodyPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
('dataState', 'InBodyPhase', 'InHeadPhase', 'processStartTag', {'name': 'script', 'type': 'StartTag'}),
('scriptDataState', 'TextPhase', 'TextPhase', 'processCharacters', {'type': 'Characters'}),
('dataState', 'TextPhase', 'TextPhase', 'processEndTag', {'name': 'script', 'type': 'EndTag'}),
('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'}),
('dataState', 'InBodyPhase', 'InBodyPhase', 'processEndTag', {'name': 'p', 'type': 'EndTag'}),
('dataState', 'InBodyPhase', 'InBodyPhase', 'processCharacters', {'type': 'Characters'})]
assert parser.log == expected
def test_no_duplicate_clone():
frag = parseFragment("<b><em><foo><foob><fooc><aside></b></em>")
assert len(frag) == 2
def test_self_closing_col():
parser = HTMLParser()
parser.parseFragment('<table><colgroup><col /></colgroup></table>')
assert not parser.errors