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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
|
import itertools
import sys
import pytest
try:
import lxml.etree
except ImportError:
pass
from .support import treeTypes
from html5rdf import html5parser, treewalkers
from html5rdf.filters.lint import Filter as Lint
import re
attrlist = re.compile(r"^(\s+)\w+=.*(\n\1\w+=.*)+", re.M)
def sortattrs(x):
lines = x.group(0).split("\n")
lines.sort()
return "\n".join(lines)
def test_all_tokens():
expected = [
{'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'html'},
{'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'head'},
{'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'head'},
{'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'body'},
{'data': 'a', 'type': 'Characters'},
{'data': {}, 'type': 'StartTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'div'},
{'data': 'b', 'type': 'Characters'},
{'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'div'},
{'data': 'c', 'type': 'Characters'},
{'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'body'},
{'type': 'EndTag', 'namespace': 'http://www.w3.org/1999/xhtml', 'name': 'html'}
]
for _, treeCls in sorted(treeTypes.items()):
if treeCls is None:
continue
p = html5parser.HTMLParser(tree=treeCls["builder"])
document = p.parse("<html><head></head><body>a<div>b</div>c</body></html>")
document = treeCls.get("adapter", lambda x: x)(document)
output = Lint(treeCls["walker"](document))
for expectedToken, outputToken in zip(expected, output):
assert expectedToken == outputToken
def set_attribute_on_first_child(docfrag, name, value, treeName):
"""naively sets an attribute on the first child of the document
fragment passed in"""
setter = {'ElementTree': lambda d: d[0].set,
'DOM': lambda d: d.firstChild.setAttribute}
setter['cElementTree'] = setter['ElementTree']
try:
setter.get(treeName, setter['DOM'])(docfrag)(name, value)
except AttributeError:
setter['ElementTree'](docfrag)(name, value)
def param_treewalker_six_mix():
"""Str/Unicode mix. If str attrs added to tree"""
# On Python 2.x string literals are of type str. Unless, like this
# file, the programmer imports unicode_literals from __future__.
# In that case, string literals become objects of type unicode.
# This test simulates a Py2 user, modifying attributes on a document
# fragment but not using the u'' syntax nor importing unicode_literals
sm_tests = [
('<a href="http://example.com">Example</a>',
[('class', 'test123')],
'<a>\n class="test123"\n href="http://example.com"\n "Example"'),
('<link href="http://example.com/cow">',
[('rel', 'alternate')],
'<link>\n href="http://example.com/cow"\n rel="alternate"\n "Example"')
]
for tree in sorted(treeTypes.items()):
for intext, attrs, expected in sm_tests:
yield intext, expected, attrs, tree
@pytest.mark.parametrize("intext, expected, attrs_to_add, tree", param_treewalker_six_mix())
def test_treewalker_six_mix(intext, expected, attrs_to_add, tree):
"""tests what happens when we add attributes to the intext"""
treeName, treeClass = tree
if treeClass is None:
pytest.skip("Treebuilder not loaded")
parser = html5parser.HTMLParser(tree=treeClass["builder"])
document = parser.parseFragment(intext)
for nom, val in attrs_to_add:
set_attribute_on_first_child(document, nom, val, treeName)
document = treeClass.get("adapter", lambda x: x)(document)
output = treewalkers.pprint(treeClass["walker"](document))
output = attrlist.sub(sortattrs, output)
if output not in expected:
raise AssertionError("TreewalkerEditTest: %s\nExpected:\n%s\nReceived:\n%s" % (treeName, expected, output))
@pytest.mark.parametrize("tree,char", itertools.product(sorted(treeTypes.items()), ["x", "\u1234"]))
def test_fragment_single_char(tree, char):
expected = [
{'data': char, 'type': 'Characters'}
]
treeName, treeClass = tree
if treeClass is None:
pytest.skip("Treebuilder not loaded")
parser = html5parser.HTMLParser(tree=treeClass["builder"])
document = parser.parseFragment(char)
document = treeClass.get("adapter", lambda x: x)(document)
output = Lint(treeClass["walker"](document))
assert list(output) == expected
@pytest.mark.skipif(treeTypes["lxml"] is None, reason="lxml not importable")
def test_lxml_xml():
expected = [
{'data': {}, 'name': 'div', 'namespace': None, 'type': 'StartTag'},
{'data': {}, 'name': 'div', 'namespace': None, 'type': 'StartTag'},
{'name': 'div', 'namespace': None, 'type': 'EndTag'},
{'name': 'div', 'namespace': None, 'type': 'EndTag'}
]
lxmltree = lxml.etree.fromstring('<div><div></div></div>')
walker = treewalkers.getTreeWalker('lxml')
output = Lint(walker(lxmltree))
assert list(output) == expected
@pytest.mark.parametrize("treeName",
[pytest.param(treeName, marks=[getattr(pytest.mark, treeName),
pytest.mark.skipif(
treeName != "lxml" or
sys.version_info < (3, 7), reason="dict order undef")])
for treeName in sorted(treeTypes.keys())])
def test_maintain_attribute_order(treeName):
treeAPIs = treeTypes[treeName]
if treeAPIs is None:
pytest.skip("Treebuilder not loaded")
# 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')))]
data = "<span " + " ".join("%s='%s'" % (x, i) for x, i in attrs) + ">"
parser = html5parser.HTMLParser(tree=treeAPIs["builder"])
document = parser.parseFragment(data)
document = treeAPIs.get("adapter", lambda x: x)(document)
output = list(Lint(treeAPIs["walker"](document)))
assert len(output) == 2
assert output[0]['type'] == 'StartTag'
assert output[1]['type'] == "EndTag"
attrs_out = output[0]['data']
assert len(attrs) == len(attrs_out)
for (in_name, in_value), (out_name, out_value) in zip(attrs, attrs_out.items()):
assert (None, in_name) == out_name
assert in_value == out_value
@pytest.mark.parametrize("treeName",
[pytest.param(treeName, marks=[getattr(pytest.mark, treeName),
pytest.mark.skipif(
treeName != "lxml" or
sys.version_info < (3, 7), reason="dict order undef")])
for treeName in sorted(treeTypes.keys())])
def test_maintain_attribute_order_adjusted(treeName):
treeAPIs = treeTypes[treeName]
if treeAPIs is None:
pytest.skip("Treebuilder not loaded")
# generate loads to maximize the chance a hash-based mutation will occur
data = "<svg a=1 refx=2 b=3 xml:lang=4 c=5>"
parser = html5parser.HTMLParser(tree=treeAPIs["builder"])
document = parser.parseFragment(data)
document = treeAPIs.get("adapter", lambda x: x)(document)
output = list(Lint(treeAPIs["walker"](document)))
assert len(output) == 2
assert output[0]['type'] == 'StartTag'
assert output[1]['type'] == "EndTag"
attrs_out = output[0]['data']
assert list(attrs_out.items()) == [((None, 'a'), '1'),
((None, 'refX'), '2'),
((None, 'b'), '3'),
(('http://www.w3.org/XML/1998/namespace', 'lang'), '4'),
((None, 'c'), '5')]
|
