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
|
import io
from html5rdf._tokenizer import HTMLTokenizer
from html5rdf.constants import tokenTypes
def ignore_parse_errors(toks):
for tok in toks:
if tok['type'] != tokenTypes['ParseError']:
yield tok
def test_maintain_attribute_order():
# generate loads to maximize the chance a hash-based mutation will occur
attrs = [(chr(x), str(i)) for i, x in enumerate(range(ord('a'), ord('z')))]
stream = io.StringIO("<span " + " ".join("%s='%s'" % (x, i) for x, i in attrs) + ">")
toks = HTMLTokenizer(stream)
out = list(ignore_parse_errors(toks))
assert len(out) == 1
assert out[0]['type'] == tokenTypes['StartTag']
attrs_tok = out[0]['data']
assert len(attrs_tok) == len(attrs)
for (in_name, in_value), (out_name, out_value) in zip(attrs, attrs_tok.items()):
assert in_name == out_name
assert in_value == out_value
def test_duplicate_attribute():
stream = io.StringIO("<span a=1 a=2 a=3>")
toks = HTMLTokenizer(stream)
out = list(ignore_parse_errors(toks))
assert len(out) == 1
assert out[0]['type'] == tokenTypes['StartTag']
attrs_tok = out[0]['data']
assert len(attrs_tok) == 1
assert list(attrs_tok.items()) == [('a', '1')]
def test_maintain_duplicate_attribute_order():
# generate loads to maximize the chance a hash-based mutation will occur
attrs = [(chr(x), str(i)) for i, x in enumerate(range(ord('a'), ord('z')))]
stream = io.StringIO("<span " + " ".join("%s='%s'" % (x, i) for x, i in attrs) + " a=100>")
toks = HTMLTokenizer(stream)
out = list(ignore_parse_errors(toks))
assert len(out) == 1
assert out[0]['type'] == tokenTypes['StartTag']
attrs_tok = out[0]['data']
assert len(attrs_tok) == len(attrs)
for (in_name, in_value), (out_name, out_value) in zip(attrs, attrs_tok.items()):
assert in_name == out_name
assert in_value == out_value
|
