forked from explosion/spaCy
-
Notifications
You must be signed in to change notification settings - Fork 0
/
test_urls.py
206 lines (178 loc) · 6.31 KB
/
test_urls.py
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
import pytest
from spacy.lang.tokenizer_exceptions import BASE_EXCEPTIONS
URLS_BASIC = [
"http://www.nytimes.com/2016/04/20/us/politics/new-york-primary-preview.html?hp&action=click&pgtype=Homepage&clickSource=story-heading&module=a-lede-package-region®ion=top-news&WT.nav=top-news&_r=0",
"www.red-stars.com",
"mailto:[email protected]",
]
URLS_FULL = URLS_BASIC + [
"mailto:[email protected]",
"mailto:[email protected]?subject=hi",
"www.google.com?q=google",
"http://foo.com/blah_(wikipedia)#cite-1",
]
# URL SHOULD_MATCH and SHOULD_NOT_MATCH patterns courtesy of https://mathiasbynens.be/demo/url-regex
URLS_SHOULD_MATCH = [
"http://foo.com/blah_blah",
"http://BlahBlah.com/Blah_Blah",
"http://foo.com/blah_blah/",
"http://www.example.com/wpstyle/?p=364",
"https://www.example.com/foo/?bar=baz&inga=42&quux",
"http://userid:[email protected]:8080",
"http://userid:[email protected]:8080/",
"http://[email protected]",
"http://[email protected]/",
"http://[email protected]:8080",
"http://[email protected]:8080/",
"http://userid:[email protected]",
"http://userid:[email protected]/",
"http://142.42.1.1/",
"http://142.42.1.1:8080/",
"http://foo.com/blah_(wikipedia)#cite-1",
"http://foo.com/blah_(wikipedia)_blah#cite-1",
"http://foo.com/unicode_(✪)_in_parens",
"http://foo.com/(something)?after=parens",
"http://code.google.com/events/#&product=browser",
"http://j.mp",
"ftp://foo.bar/baz",
"http://foo.bar/?q=Test%20URL-encoded%20stuff",
"http://-.~_!$&'()*+,;=:%40:80%2f::::::@example.com",
"http://1337.net",
"http://a.b-c.de",
"http://223.255.255.254",
"http://a.b--c.de/", # this is a legit domain name see: https://gist.github.com/dperini/729294 comment on 9/9/2014
"ssh://[email protected]:12345/repository.git",
"svn+ssh://[email protected]/path",
pytest.param(
"chrome://extensions/?id=mhjfbmdgcfjbbpaeojofohoefgiehjai",
marks=pytest.mark.xfail(),
),
pytest.param(
"chrome-extension://mhjfbmdgcfjbbpaeojofohoefgiehjai", marks=pytest.mark.xfail()
),
"http://foo.com/blah_blah_(wikipedia)",
"http://foo.com/blah_blah_(wikipedia)_(again)",
"http://www.foo.co.uk",
"http://www.foo.co.uk/",
"http://www.foo.co.uk/blah/blah",
"http://⌘.ws",
"http://⌘.ws/",
"http://☺.damowmow.com/",
"http://✪df.ws/123",
"http://➡.ws/䨹",
"http://مثال.إختبار",
"http://例子.测试",
"http://उदाहरण.परीक्षा",
]
URLS_SHOULD_NOT_MATCH = [
"http://",
"http://.",
"http://..",
"http://../",
"http://?",
"http://??",
"http://??/",
"http://#",
"http://##",
"http://##/",
"http://foo.bar?q=Spaces should be encoded",
"//",
"//a",
"///a",
"///",
"http:///a",
"rdar://1234",
"h://test",
"http:// shouldfail.com",
":// should fail",
"http://foo.bar/foo(bar)baz quux",
"http://-error-.invalid/",
"http://a.b-.co",
"http://0.0.0.0",
"http://10.1.1.0",
"http://10.1.1.255",
"http://224.1.1.1",
"http://123.123.123",
"http://3628126748",
"http://.www.foo.bar/",
"http://.www.foo.bar./",
"http://10.1.1.1",
"NASDAQ:GOOG",
"http://-a.b.co",
pytest.param("foo.com", marks=pytest.mark.xfail()),
"http://1.1.1.1.1",
"http://www.foo.bar./",
]
# Punctuation we want to check is split away before the URL
PREFIXES = ["(", '"', ">"]
# Punctuation we want to check is split away after the URL
SUFFIXES = ['"', ":", ">"]
@pytest.mark.parametrize("url", URLS_SHOULD_MATCH)
def test_should_match(en_tokenizer, url):
assert en_tokenizer.url_match(url) is not None
@pytest.mark.parametrize("url", URLS_SHOULD_NOT_MATCH)
def test_should_not_match(en_tokenizer, url):
assert en_tokenizer.url_match(url) is None
@pytest.mark.parametrize("url", URLS_BASIC)
def test_tokenizer_handles_simple_url(tokenizer, url):
tokens = tokenizer(url)
assert len(tokens) == 1
assert tokens[0].text == url
@pytest.mark.parametrize("url", URLS_BASIC)
def test_tokenizer_handles_simple_surround_url(tokenizer, url):
tokens = tokenizer("(" + url + ")")
assert len(tokens) == 3
assert tokens[0].text == "("
assert tokens[1].text == url
assert tokens[2].text == ")"
@pytest.mark.slow
@pytest.mark.parametrize("prefix", PREFIXES)
@pytest.mark.parametrize("url", URLS_FULL)
def test_tokenizer_handles_prefixed_url(tokenizer, prefix, url):
tokens = tokenizer(prefix + url)
assert len(tokens) == 2
assert tokens[0].text == prefix
assert tokens[1].text == url
@pytest.mark.slow
@pytest.mark.parametrize("suffix", SUFFIXES)
@pytest.mark.parametrize("url", URLS_FULL)
def test_tokenizer_handles_suffixed_url(tokenizer, url, suffix):
tokens = tokenizer(url + suffix)
assert len(tokens) == 2
assert tokens[0].text == url
assert tokens[1].text == suffix
@pytest.mark.slow
@pytest.mark.parametrize("prefix", PREFIXES)
@pytest.mark.parametrize("suffix", SUFFIXES)
@pytest.mark.parametrize("url", URLS_FULL)
def test_tokenizer_handles_surround_url(tokenizer, prefix, suffix, url):
tokens = tokenizer(prefix + url + suffix)
assert len(tokens) == 3
assert tokens[0].text == prefix
assert tokens[1].text == url
assert tokens[2].text == suffix
@pytest.mark.slow
@pytest.mark.parametrize("prefix1", PREFIXES)
@pytest.mark.parametrize("prefix2", PREFIXES)
@pytest.mark.parametrize("url", URLS_FULL)
def test_tokenizer_handles_two_prefix_url(tokenizer, prefix1, prefix2, url):
tokens = tokenizer(prefix1 + prefix2 + url)
assert len(tokens) == 3
assert tokens[0].text == prefix1
assert tokens[1].text == prefix2
assert tokens[2].text == url
@pytest.mark.slow
@pytest.mark.parametrize("suffix1", SUFFIXES)
@pytest.mark.parametrize("suffix2", SUFFIXES)
@pytest.mark.parametrize("url", URLS_FULL)
def test_tokenizer_handles_two_suffix_url(tokenizer, suffix1, suffix2, url):
tokens = tokenizer(url + suffix1 + suffix2)
if suffix1 + suffix2 in BASE_EXCEPTIONS:
assert len(tokens) == 2
assert tokens[0].text == url
assert tokens[1].text == suffix1 + suffix2
else:
assert len(tokens) == 3
assert tokens[0].text == url
assert tokens[1].text == suffix1
assert tokens[2].text == suffix2