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
|
# Copyright (C) 2004-2012 Bastian Kleineidam
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
"""
Test html parsing.
"""
from linkcheck.htmlutil import htmlsoup
from io import StringIO
import pytest
from .htmllib import pretty_print_html
# list of tuples
# (<test pattern>, <expected parse output>)
parsetests = [
# start tags
("""<a b="c" >""", """<a b="c"/>"""),
("""<a b='c' >""", """<a b="c"/>"""),
("""<a b=c" >""", """<a b="c""/>"""),
("""<a b=c' >""", """<a b="c'"/>"""),
("""<a b="" >""", """<a b=""/>"""),
("""<a b='' >""", """<a b=""/>"""),
("""<a b=>""", """<a b=""/>"""),
("""<a b= >""", """<a b=""/>"""),
("""<a =c>""", """<a =c=""/>"""),
("""<a =c >""", """<a =c=""/>"""),
("""<a =>""", """<a ==""/>"""),
("""<a = >""", """<a ==""/>"""),
("""<a b= "c" >""", """<a b="c"/>"""),
("""<a b ="c" >""", """<a b="c"/>"""),
("""<a b = "c" >""", """<a b="c"/>"""),
("""<a >""", """<a/>"""),
("""<>""", """"""),
("""< >""", """"""),
("""<aä>""", """<aä/>"""),
("""<a aä="b">""", """<a aä="b"/>"""),
("""<a a="bä">""", """<a a="bä"/>"""),
# multiple attribute names should be ignored...
("""<a b="c" b="c" >""", """<a b="c"/>"""),
# ... but which one wins - in our implementation the last one
("""<a b="c" b="d" >""", """<a b="d"/>"""),
# reduce test
("""<a b="c"><""", """<a b="c"><</a>"""),
# numbers in tag
("""<h1>bla</h1>""", """<h1>bla</h1>"""),
# more start tags
("""<a b=c"><a b="c">""", """<a b="c""/><a b="c"/>"""),
("""<a b=/c/></a><br>""", """<a b="/c/"/><br/>"""),
("""<br/>""", """<br/>"""),
("""<a b="50%"><br>""", """<a b="50%"/><br/>"""),
# start and end tag (HTML doctype assumed)
("""<a/>""", """<a/>"""),
("""<meta/>""", """<meta/>"""),
("""<MetA/>""", """<meta/>"""),
# line continuation (Dr. Fun webpage)
("""<img bo\\\nrder=0 >""", """<img bo\\="" rder="0"/>"""),
("""<img align="mid\\\ndle">""", """<img align="mid\\\ndle"/>"""),
("""<img align='mid\\\ndle'>""", """<img align="mid\\\ndle"/>"""),
# href with $
("""<a href="123$456">""", """<a href="123$456"/>"""),
# quoting
("""<a href=/ >""", """<a href="/"/>"""),
("""<a href= />""", """<a href="/"/>"""),
("""<a href= >""", """<a href=""/>"""),
("""<a href="'" >""", """<a href="'"/>"""),
("""<a href='"' >""", """<a href="""/>"""),
("""<a href="bla" %]" >""", """<a %]"="" href="bla"/>"""),
("""<a href=bla" >""", """<a href="bla""/>"""),
(
"""<a onmouseover=blubb('nav1','',"""
"""'/images/nav.gif',1);move(this); b="c">""",
"""<a b="c" onmouseover="blubb('nav1','',"""
"""'/images/nav.gif',1);move(this);"/>""",
),
(
"""<a onClick=location.href('/index.htm') b="c">""",
"""<a b="c" onclick="location.href('/index.htm')"/>""",
),
# entity resolving
("""<a href="D;ailto:" >""", """<a href="D;ailto:"/>"""),
("""<a href="&ailto:" >""", """<a href="&ailto:"/>"""),
("""<a href="&amp;ailto:" >""", """<a href="&amp;ailto:"/>"""),
("""<a href="&hulla;ailto:" >""", """<a href="&hulla;ailto:"/>"""),
("""<a href="mailto:" >""", """<a href="mailto:"/>"""),
("""<a href="mailto:" >""", """<a href="mailto:"/>"""),
# note that \u8156 is not valid encoding and therefore gets removed
("""<a href="῜ailto:" >""", """<a href="῜ailto:"/>"""),
# mailto link
(
"""<a href=mailto:calvin@LocalHost?subject=Hallo&to=michi>1</a>""",
"""<a href="mailto:calvin@LocalHost?subject=Hallo&to=michi">1</a>""",
),
# meta tag with charset encoding
(
"""<meta http-equiv="content-type" content>""",
"""<meta content="" http-equiv="content-type"/>""",
),
(
"""<meta http-equiv="content-type" content=>""",
"""<meta content="" http-equiv="content-type"/>""",
),
(
"""<meta http-equiv="content-type" content="hulla">""",
"""<meta content="hulla" http-equiv="content-type"/>""",
),
(
"""<meta http-equiv="content-type" content="text/html; charset=iso8859-1">""",
"""<meta content="text/html; charset=iso8859-1" http-equiv="content-type"/>""",
),
(
"""<meta http-equiv="content-type" content="text/html; charset=hulla">""",
"""<meta content="text/html; charset=hulla" http-equiv="content-type"/>""",
),
# missing > in end tag
("""</td <td a="b" >""", """"""),
("""</td<td a="b" >""", """"""),
# missing beginning quote
("""<td a=b">""", """<td a="b""/>"""),
# stray < before start tag
("""<0.<td a="b" >""", """<td a="b"/>"""),
# HTML5 tags
("""<audio src=bla>""", """<audio src="bla"/>"""),
("""<button formaction=bla>""", """<button formaction="bla"/>"""),
("""<html manifest=bla>""", """<html manifest="bla"/>"""),
("""<source src=bla>""", """<source src="bla"/>"""),
("""<track src=bla>""", """<track src="bla"/>"""),
("""<video src=bla>""", """<video src="bla"/>"""),
# Test inserted tag s
("""<a></a><b></b>""", """<a/><b/>"""),
# This is not correct result for an HTML parser, but it is for us
("""<b><a></a></b>""", """<b/><a/>"""),
]
class TestParser:
"""
Test html parser.
"""
@pytest.mark.parametrize("_in, _out", parsetests)
def test_parse(self, _in, _out):
# Parse all test patterns in one go.
out = StringIO()
pretty_print_html(out, htmlsoup.make_soup(_in))
self.check_results(_in, _out, out)
def check_results(self, _in, _out, out):
"""
Check parse results.
"""
res = out.getvalue()
msg = f"Test error; in: {_in!r}, out: {res!r}, expect: {_out!r}"
assert res == _out, msg
def test_encoding_detection_utf_content(self):
html = b'<meta http-equiv="content-type" content="text/html; charset=UTF-8">'
self.encoding_test(html, "utf-8")
def test_encoding_detection_utf_charset(self):
html = b'<meta charset="UTF-8">'
self.encoding_test(html, "utf-8")
def test_encoding_detection_iso_content(self):
html = (
b'<meta http-equiv="content-type" content="text/html; charset=ISO8859-1">'
)
self.encoding_test(html, "iso8859-1")
def test_encoding_detection_iso_charset(self):
html = b'<meta charset="ISO8859-1">'
self.encoding_test(html, "iso8859-1")
def test_encoding_detection_iso_bad_charset(self):
html = b'<meta charset="hulla">'
self.encoding_test(html, "ascii")
def test_encoding_detection_iso_bad_content(self):
html = b'<meta http-equiv="content-type" content="text/html; charset=blabla">'
self.encoding_test(html, "ascii")
def encoding_test(self, html, expected):
# For encoding detection Beautiful Soup uses if available in order
# of preference cchardet then chardet then charset-normalizer.
# Results for html without a valid charset may differ
# based on cchardet/chardet/charset-normalizer availability.
soup = htmlsoup.make_soup(html)
assert soup.original_encoding == expected
|
