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
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
|
import urllib
from html5lib.tokenizer import HTMLTokenizer
from nose.tools import eq_
from bleach import linkify, url_re
def filter_url(url):
return u'http://bouncer/?u=%s' % urllib.quote_plus(url)
def test_url_re():
def no_match(s):
match = url_re.search(s)
if match:
assert not match, 'matched %s' % s[slice(*match.span())]
yield no_match, 'just what i am looking for...it'
def test_empty():
eq_('', linkify(''))
def test_simple_link():
eq_('a <a href="http://example.com" rel="nofollow">http://example.com'
'</a> link',
linkify('a http://example.com link'))
eq_('a <a href="https://example.com" rel="nofollow">https://example.com'
'</a> link',
linkify('a https://example.com link'))
eq_('an <a href="http://example.com" rel="nofollow">example.com</a> link',
linkify('an example.com link'))
def test_trailing_slash():
eq_('<a href="http://example.com/" rel="nofollow">http://example.com/</a>',
linkify('http://example.com/'))
eq_('<a href="http://example.com/foo/" rel="nofollow">'
'http://example.com/foo/</a>',
linkify('http://example.com/foo/'))
eq_('<a href="http://example.com/foo/bar/" rel="nofollow">'
'http://example.com/foo/bar/</a>',
linkify('http://example.com/foo/bar/'))
def test_mangle_link():
eq_('<a href="http://bouncer/?u=http%3A%2F%2Fexample.com" rel="nofollow">'
'http://example.com</a>',
linkify('http://example.com', filter_url=filter_url))
def test_email_link():
eq_('a james@example.com mailto',
linkify('a james@example.com mailto'))
eq_('a james@example.com.au mailto',
linkify('a james@example.com.au mailto'))
eq_('a <a href="mailto:james@example.com" rel="nofollow">'
'james@example.com</a> mailto',
linkify('a james@example.com mailto', parse_email=True))
eq_('aussie <a href="mailto:james@example.com.au" rel="nofollow">'
'james@example.com.au</a> mailto',
linkify('aussie james@example.com.au mailto', parse_email=True))
eq_('email to <a href="james@example.com" rel="nofollow">'
'james@example.com</a>',
linkify('email to <a href="james@example.com">'
'james@example.com</a>', parse_email=True))
def test_email_link_escaping():
eq_('''<a href='mailto:"james"@example.com' rel="nofollow">'''
'''"james"@example.com</a>''',
linkify('"james"@example.com', parse_email=True))
eq_('''<a href="mailto:"j'ames"@example.com" rel="nofollow">'''
'''"j'ames"@example.com</a>''',
linkify('"j\'ames"@example.com', parse_email=True))
eq_('''<a href='mailto:"ja>mes"@example.com' rel="nofollow">'''
'''"ja>mes"@example.com</a>''',
linkify('"ja>mes"@example.com', parse_email=True))
def test_tlds():
eq_('<a href="http://example.com" rel="nofollow">example.com</a>',
linkify('example.com'))
eq_('<a href="http://example.co.uk" rel="nofollow">example.co.uk</a>',
linkify('example.co.uk'))
eq_('<a href="http://example.edu" rel="nofollow">example.edu</a>',
linkify('example.edu'))
eq_('example.xxx', linkify('example.xxx'))
eq_(' brie', linkify(' brie'))
eq_('<a href="http://bit.ly/fun" rel="nofollow">bit.ly/fun</a>',
linkify('bit.ly/fun'))
def test_escaping():
eq_('< unrelated', linkify('< unrelated'))
def test_nofollow_off():
eq_('<a href="http://example.com">example.com</a>',
linkify(u'example.com', nofollow=False))
def test_link_in_html():
eq_('<i><a href="http://yy.com" rel="nofollow">http://yy.com</a></i>',
linkify('<i>http://yy.com</i>'))
eq_('<em><strong><a href="http://xx.com" rel="nofollow">http://xx.com</a>'
'</strong></em>',
linkify('<em><strong>http://xx.com</strong></em>'))
def test_links_https():
eq_('<a href="https://yy.com" rel="nofollow">https://yy.com</a>',
linkify('https://yy.com'))
def test_add_rel_nofollow():
"""Verify that rel="nofollow" is added to an existing link"""
eq_('<a href="http://yy.com" rel="nofollow">http://yy.com</a>',
linkify('<a href="http://yy.com">http://yy.com</a>'))
def test_url_with_path():
eq_('<a href="http://example.com/path/to/file" rel="nofollow">'
'http://example.com/path/to/file</a>',
linkify('http://example.com/path/to/file'))
def test_link_ftp():
eq_('<a href="ftp://ftp.mozilla.org/some/file" rel="nofollow">'
'ftp://ftp.mozilla.org/some/file</a>',
linkify('ftp://ftp.mozilla.org/some/file'))
def test_link_query():
eq_('<a href="http://xx.com/?test=win" rel="nofollow">'
'http://xx.com/?test=win</a>',
linkify('http://xx.com/?test=win'))
eq_('<a href="http://xx.com/?test=win" rel="nofollow">'
'xx.com/?test=win</a>',
linkify('xx.com/?test=win'))
eq_('<a href="http://xx.com?test=win" rel="nofollow">'
'xx.com?test=win</a>',
linkify('xx.com?test=win'))
def test_link_fragment():
eq_('<a href="http://xx.com/path#frag" rel="nofollow">'
'http://xx.com/path#frag</a>',
linkify('http://xx.com/path#frag'))
def test_link_entities():
eq_('<a href="http://xx.com/?a=1&b=2" rel="nofollow">'
'http://xx.com/?a=1&b=2</a>',
linkify('http://xx.com/?a=1&b=2'))
def test_escaped_html():
"""If I pass in escaped HTML, it should probably come out escaped."""
s = '<em>strong</em>'
eq_(s, linkify(s))
def test_link_http_complete():
eq_('<a href="https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d'
'&e#f" rel="nofollow">'
'https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f</a>',
linkify('https://user:pass@ftp.mozilla.org/x/y.exe?a=b&c=d&e#f'))
def test_non_url():
"""document.vulnerable should absolutely not be linkified."""
s = 'document.vulnerable'
eq_(s, linkify(s))
def test_javascript_url():
"""javascript: urls should never be linkified."""
s = 'javascript:document.vulnerable'
eq_(s, linkify(s))
def test_unsafe_url():
"""Any unsafe char ({}[]<>, etc.) in the path should end URL scanning."""
eq_('All your{"<a href="http://xx.yy.com/grover.png" '
'rel="nofollow">xx.yy.com/grover.png</a>"}base are',
linkify('All your{"xx.yy.com/grover.png"}base are'))
def test_skip_pre():
"""Skip linkification in <pre> tags."""
simple = 'http://xx.com <pre>http://xx.com</pre>'
linked = ('<a href="http://xx.com" rel="nofollow">http://xx.com</a> '
'<pre>http://xx.com</pre>')
all_linked = ('<a href="http://xx.com" rel="nofollow">http://xx.com</a> '
'<pre><a href="http://xx.com" rel="nofollow">http://xx.com'
'</a></pre>')
eq_(linked, linkify(simple, skip_pre=True))
eq_(all_linked, linkify(simple))
already_linked = '<pre><a href="http://xx.com">xx</a></pre>'
nofollowed = '<pre><a href="http://xx.com" rel="nofollow">xx</a></pre>'
eq_(nofollowed, linkify(already_linked))
eq_(nofollowed, linkify(already_linked, skip_pre=True))
def test_libgl():
"""libgl.so.1 should not be linkified."""
eq_('libgl.so.1', linkify('libgl.so.1'))
def test_end_of_sentence():
"""example.com. should match."""
out = u'<a href="http://%s" rel="nofollow">%s</a>%s'
in_ = u'%s%s'
def check(u, p):
eq_(out % (u, u, p), linkify(in_ % (u, p)))
tests = (
('example.com', '.'),
('example.com', '...'),
('ex.com/foo', '.'),
('ex.com/foo', '....'),
)
for u, p in tests:
yield check, u, p
def test_end_of_clause():
"""example.com/foo, shouldn't include the ,"""
eq_('<a href="http://ex.com/foo" rel="nofollow">ex.com/foo</a>, bar',
linkify('ex.com/foo, bar'))
def test_sarcasm():
"""Jokes should crash.<sarcasm/>"""
dirty = u'Yeah right <sarcasm/>'
clean = u'Yeah right <sarcasm/>'
eq_(clean, linkify(dirty))
def test_wrapping_parentheses():
"""URLs wrapped in parantheses should not include them."""
out = u'%s<a href="http://%s" rel="nofollow">%s</a>%s'
tests = (
('(example.com)', out % ('(', 'example.com', 'example.com', ')')),
('(example.com/)', out % ('(', 'example.com/', 'example.com/', ')')),
('(example.com/foo)', out % ('(', 'example.com/foo',
'example.com/foo', ')')),
('(((example.com/))))', out % ('(((', 'example.com/)',
'example.com/)', ')))')),
('example.com/))', out % ('', 'example.com/))',
'example.com/))', '')),
('http://en.wikipedia.org/wiki/Test_(assessment)',
out % ('', 'en.wikipedia.org/wiki/Test_(assessment)',
'http://en.wikipedia.org/wiki/Test_(assessment)', '')),
('(http://en.wikipedia.org/wiki/Test_(assessment))',
out % ('(', 'en.wikipedia.org/wiki/Test_(assessment)',
'http://en.wikipedia.org/wiki/Test_(assessment)', ')')),
('((http://en.wikipedia.org/wiki/Test_(assessment))',
out % ('((', 'en.wikipedia.org/wiki/Test_(assessment',
'http://en.wikipedia.org/wiki/Test_(assessment', '))')),
('(http://en.wikipedia.org/wiki/Test_(assessment)))',
out % ('(', 'en.wikipedia.org/wiki/Test_(assessment))',
'http://en.wikipedia.org/wiki/Test_(assessment))', ')')),
('(http://en.wikipedia.org/wiki/)Test_(assessment',
out % ('(', 'en.wikipedia.org/wiki/)Test_(assessment',
'http://en.wikipedia.org/wiki/)Test_(assessment', '')),
)
def check(test, expected_output):
eq_(expected_output, linkify(test))
for test, expected_output in tests:
yield check, test, expected_output
def test_ports():
"""URLs can contain port numbers."""
tests = (
('http://foo.com:8000', ('http://foo.com:8000', '')),
('http://foo.com:8000/', ('http://foo.com:8000/', '')),
('http://bar.com:xkcd', ('http://bar.com', ':xkcd')),
('http://foo.com:81/bar', ('http://foo.com:81/bar', '')),
('http://foo.com:', ('http://foo.com', ':')),
)
def check(test, output):
eq_(u'<a href="{0}" rel="nofollow">{0}</a>{1}'.format(*output),
linkify(test))
for test, output in tests:
yield check, test, output
def test_target():
eq_('<a href="http://example.com" rel="nofollow" '
'target="_blank">example.com</a>',
linkify(u'example.com', target='_blank'))
eq_('<a href="http://example.com" target="_blank">example.com</a>',
linkify(u'example.com', target='_blank', nofollow=False))
def test_tokenizer():
"""Linkify doesn't always have to sanitize."""
raw = '<em>test<x></x></em>'
eq_('<em>test<x></x></em>', linkify(raw))
eq_(raw, linkify(raw, tokenizer=HTMLTokenizer))
|