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
|
# Copyright (C) 2004-2014 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 file parsing.
"""
import os
from pathlib import Path
import sys
import zipfile
import pytest
from tests import need_network, need_word, need_pdflib
from . import LinkCheckTest, get_file
def unzip(filename, targetdir):
"""Unzip given zipfile into targetdir."""
# There are likely problems with zipfile and non-Unicode filenames
# https://github.com/python/cpython/issues/83042
# https://github.com/python/cpython/issues/72267
# https://github.com/python/cpython/issues/95463
zf = zipfile.ZipFile(filename)
for name in zf.namelist():
if name.endswith("/"):
os.mkdir(os.path.join(targetdir, name), 0o700)
else:
outfile = open(os.path.join(targetdir, name), "wb")
try:
outfile.write(zf.read(name))
finally:
outfile.close()
class TestFile(LinkCheckTest):
"""
Test file:// link checking (and file content parsing).
"""
def test_html(self):
self.file_test("file.html")
@need_network
def test_html_url_quote(self):
self.file_test("file_url_quote.html")
def test_wml(self):
self.file_test("file.wml")
def test_text(self):
self.file_test("file.txt")
def test_asc(self):
self.file_test("file.asc")
def test_css(self):
self.file_test("file.css")
def test_php(self):
self.file_test("file.php")
def test_empty(self):
self.file_test("empty.html")
@need_word
def test_word(self):
confargs = dict(enabledplugins=["WordParser"])
self.file_test("file.doc", confargs=confargs)
@need_pdflib
def test_pdf(self):
confargs = dict(enabledplugins=["PdfParser"])
self.file_test("file.pdf", confargs=confargs)
def test_markdown(self):
confargs = dict(enabledplugins=["MarkdownCheck"])
if sys.version_info < (3, 12, 5):
markdown_file = "file-octet-stream.markdown"
else:
markdown_file = "file.markdown"
self.file_test(markdown_file, confargs=confargs)
def test_urllist(self):
self.file_test("urllist.txt")
@pytest.mark.xfail(strict=True)
def test_directory_listing(self):
# unpack non-unicode filename which cannot be stored
# in the SF subversion repository
if os.name != "posix" or sys.platform != "linux":
pytest.skip("Not running on POSIX or Linux")
dirname = get_file("dir")
if not os.path.isdir(dirname):
unzip(dirname + ".zip", os.path.dirname(dirname))
self.file_test("dir")
def test_directory_listing_unicode(self):
if os.name != "posix" or sys.platform != "linux":
pytest.skip("Not running on POSIX or Linux")
dirname = Path(get_file("udir"))
dirname.mkdir(exist_ok=True)
Path(dirname, "í»¯¿.dat").touch()
self.file_test("udir")
def test_unicode_filename(self):
# a unicode filename
self.file_test("Мошкова.bin")
def test_good_file(self):
url = "file://%(curdir)s/%(datadir)s/file.txt" % self.get_attrs()
nurl = self.norm(url)
resultlines = [
"url %s" % url,
"cache key %s" % nurl,
"real url %s" % nurl,
"valid",
]
self.direct(url, resultlines)
def test_bad_file(self):
if os.name == "nt":
# Fails on NT platforms and I am too lazy to fix
# Cause: url get quoted %7C which gets lowercased to
# %7c and this fails.
pytest.skip("Running on Windows")
url = "file:/%(curdir)s/%(datadir)s/file.txt" % self.get_attrs()
nurl = self.norm(url)
resultlines = [
"url %s" % url,
"cache key %s" % nurl,
"real url %s" % nurl,
"error",
]
self.direct(url, resultlines)
def test_good_file_missing_dslash(self):
# good file (missing double slash)
attrs = self.get_attrs()
url = "file:%(curdir)s/%(datadir)s/file.txt" % attrs
resultlines = [
"url %s" % url,
"cache key file://%(curdir)s/%(datadir)s/file.txt" % attrs,
"real url file://%(curdir)s/%(datadir)s/file.txt" % attrs,
"valid",
]
self.direct(url, resultlines)
def test_good_dir(self):
url = "file://%(curdir)s/%(datadir)s/" % self.get_attrs()
resultlines = [
"url %s" % url,
"cache key %s" % url,
"real url %s" % url,
"valid",
]
self.direct(url, resultlines)
def test_good_dir_space(self):
url = "file://%(curdir)s/%(datadir)s/a b/" % self.get_attrs()
nurl = self.norm(url)
url2 = "file://%(curdir)s/%(datadir)s/a b/el.html" % self.get_attrs()
nurl2 = self.norm(url2)
url3 = "file://%(curdir)s/%(datadir)s/a b/t.txt" % self.get_attrs()
nurl3 = self.norm(url3)
resultlines = [
"url %s" % url,
"cache key %s" % nurl,
"real url %s" % nurl,
"valid",
"url el.html",
"cache key %s" % nurl2,
"real url %s" % nurl2,
"name el.html",
"valid",
"url t.txt",
"cache key %s" % nurl3,
"real url %s" % nurl3,
"name t.txt",
"valid",
]
self.direct(url, resultlines, recursionlevel=2)
|
