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
|
# -*- coding: utf-8 -*-
# Copyright (C) 2004-2009 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
import zipfile
from . import LinkCheckTest, get_file
def unzip (filename, targetdir):
"""Unzip given zipfile into targetdir."""
if isinstance(targetdir, unicode):
targetdir = str(targetdir)
zf = zipfile.ZipFile(filename)
for name in zf.namelist():
if name.endswith('/'):
os.mkdir(os.path.join(targetdir, name), 0700)
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")
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_urllist (self):
self.file_test("urllist.txt")
def test_firefox_bookmarks (self):
# firefox 3 bookmark file parsing
self.file_test("places.sqlite")
def test_opera_bookmarks (self):
# Opera bookmark file parsing
self.file_test("opera6.adr")
def test_directory_listing (self):
# unpack non-unicode filename which cannot be stored
# in the SF subversion repository
if os.name != 'posix':
return
dirname = get_file("dir")
if not os.path.isdir(dirname):
unzip(dirname+".zip", os.path.dirname(dirname))
self.file_test("dir")
def test_unicode_filename (self):
# a unicode filename
self.file_test(u"Мошкова.bin")
def test_good_file (self):
url = u"file://%(curdir)s/%(datadir)s/file.txt" % self.get_attrs()
nurl = self.norm(url)
resultlines = [
u"url %s" % url,
u"cache key %s" % nurl,
u"real url %s" % nurl,
u"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.
return
url = u"file:/%(curdir)s/%(datadir)s/file.txt" % self.get_attrs()
nurl = self.norm(url)
resultlines = [
u"url %s" % url,
u"cache key %s" % nurl,
u"real url %s" % nurl,
u"error",
]
self.direct(url, resultlines)
def test_good_file_missing_dslash (self):
# good file (missing double slash)
attrs = self.get_attrs()
url = u"file:%(curdir)s/%(datadir)s/file.txt" % attrs
nurl = self.norm(url)
resultlines = [
u"url %s" % url,
u"cache key file://%(curdir)s/%(datadir)s/file.txt" % attrs,
u"real url file://%(curdir)s/%(datadir)s/file.txt" % attrs,
u"warning Base URL is not properly normed. Normed URL is %s." % nurl,
u"valid",
]
self.direct(url, resultlines)
def test_good_dir (self):
url = u"file://%(curdir)s/%(datadir)s/" % self.get_attrs()
resultlines = [
u"url %s" % url,
u"cache key %s" % url,
u"real url %s" % url,
u"valid",
]
self.direct(url, resultlines)
|
