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
|
# SPDX-License-Identifier: CC0-1.0
# Copyright (C) 2022 Wojtek Kosior <koszko@koszko.org>
#
# Available under the terms of Creative Commons Zero v1.0 Universal.
import pytest
import re
import dataclasses as dc
from immutables import Map
from hydrilla import url_patterns
from hydrilla.exceptions import HaketiloException
from .url_patterns_common import *
# @pytest.mark.parametrize('_in, out', [
# ({}, sample_url_str),
# ({'path_segments': ()}, 'http://example.com'),
# ({'has_trailing_slash': True}, 'http://example.com/aa/bb/'),
# ({'orig_scheme': 'http*'}, 'http*://example.com/aa/bb'),
# ({'scheme': 'http_sth'}, 'http://example.com/aa/bb'),
# ({'port': 443}, 'http://example.com:443/aa/bb'),
# ({'path_segments': (),
# 'has_trailing_slash': True},
# 'http://example.com/'),
# ({'orig_scheme': 'https',
# 'scheme': 'https',
# 'port': 443},
# 'https://example.com/aa/bb'),
# ({'orig_scheme': 'ftp',
# 'scheme': 'ftp',
# 'port': 21},
# 'ftp://example.com/aa/bb'),
# ({'orig_scheme': 'file',
# 'scheme': 'file',
# 'port': None,
# 'domain_labels': ()},
# 'file:///aa/bb')
# ])
# def test_reconstruct_parsed_url(_in, out, sample_url_parsed):
# """Test the reconstruct_url() method of ParsedUrl class."""
# parsed_url = dc.replace(sample_url_parsed, **_in)
# assert parsed_url.reconstruct_url() == out
@pytest.mark.parametrize('_in, out', [
({'url': sample_url_str}, {}),
({'url': 'http://example.com:80/aa/bb'}, {}),
({'url': 'http://example.com//aa///bb'}, {}),
({'url': 'http://example...com/aa/bb'}, {}),
({'url': 'http://example.com/aa/bb?c=d#ef'}, {}),
({'url': 'http://example.com'}, {'path_segments': ()}),
({'url': 'http://example.com/aa/bb/'}, {'has_trailing_slash': True}),
({'url': 'http://example.com:443/aa/bb'}, {'port': 443}),
({'url': 'http://example.com/'},
{'path_segments': (),
'has_trailing_slash': True}),
({'url': 'http://example.com/aa/bb',
'is_pattern': True,
'orig_url': 'http*://example.com/aa/bb/'},
{}),
({'url': 'https://example.com/aa/bb'},
{'scheme': 'https',
'port': 443}),
({'url': 'ftp://example.com/aa/bb'},
{'scheme': 'ftp',
'port': 21}),
({'url': 'file:///aa/bb'},
{'scheme': 'file',
'port': None,
'domain_labels': ()})
])
def test_parse_pattern_or_url(_in, out, sample_url_parsed):
"""Test normal use (no errors) of the _parse_pattern_or_url() function."""
if 'orig_url' not in _in:
_in = {**_in, 'orig_url': _in['url']}
out = {**out, 'orig_url': _in['orig_url']}
parsed_url = url_patterns._parse_pattern_or_url(**_in)
assert parsed_url == dc.replace(sample_url_parsed, **out)
@pytest.mark.parametrize('_in, err', [
({'url': 'file://:78/unexpected/port'}, 'err.url_{}.bad'),
({'url': 'file://unexpected.hostname/'}, 'err.url_{}.bad'),
({'url': 'http:///no/hostname'}, 'err.url_{}.bad'),
({'url': 'invalid?://example.com'}, 'err.url_{}.bad'),
({'url': 'invalid?://example.com',
'orig_url': 'invalid?://example.com',
'is_pattern': True},
'err.url_pattern_{}.bad'),
({'url': 'unknown://example.com'}, 'err.url_{}.bad_scheme'),
({'url': 'unknown://example.com',
'orig_url': 'unknown://example.com',
'is_pattern': True},
'err.url_pattern_{}.bad_scheme'),
({'url': 'http://example.com:80',
'orig_url': 'http*://example.com:80',
'is_pattern': True},
'err.url_pattern_{}.special_scheme_port'),
({'url': 'http://example.com:65536'}, 'err.url_{}.bad_port'),
({'url': 'http://example.com:0'}, 'err.url_{}.bad_port'),
({'url': 'http://example.com:65537',
'orig_url': 'http://example.com:65537',
'is_pattern': True},
'err.url_pattern_{}.bad_port'),
({'url': 'http://example.com/?a=b',
'orig_url': 'http://example.com/?a=b',
'is_pattern': True},
'err.url_pattern_{}.has_query'),
({'url': 'http://example.com/#abc',
'orig_url': 'http://example.com/#abc',
'is_pattern': True},
'err.url_pattern_{}.has_frag')
])
def test_parse_pattern_or_url_err(_in, err, sample_url_parsed):
"""Test error conditions of the _parse_pattern_or_url() function."""
if 'orig_url' not in _in:
_in = {**_in, 'orig_url': _in['url']}
err_url = _in['orig_url']
err_regex = err.format(re.escape(err_url))
with pytest.raises(HaketiloException, match=f'^{err_regex}$'):
url_patterns._parse_pattern_or_url(**_in)
def test_parse_pattern_or_url_different_urls():
"""
Verify the _parse_pattern_or_url() function allows passed URLs to be
different only when parsing a pattern.
"""
urls = [sample_url_str, sample_url_str.replace('http', 'http*')]
url_patterns._parse_pattern_or_url(*urls, is_pattern=True)
with pytest.raises(AssertionError):
url_patterns._parse_pattern_or_url(*urls)
@pytest.mark.parametrize('_in, out', [
('http://example.com', ('mocked_pr_http://example.com',)),
('ftp://example.com', ('mocked_pr_ftp://example.com',)),
('http*://example.com', ('mocked_pr_http://example.com',
'mocked_pr_https://example.com'))
])
def test_parse_pattern(monkeypatch, _in, out):
"""...."""
def mocked_parse_pattern_or_url(url, orig_url, is_pattern=False):
"""...."""
assert is_pattern
assert orig_url == _in
return f'mocked_pr_{url}'
monkeypatch.setattr(url_patterns, '_parse_pattern_or_url',
mocked_parse_pattern_or_url)
assert url_patterns.parse_pattern(_in) == out
def test_parse_url(monkeypatch):
"""...."""
def mocked_parse_pattern_or_url(url, orig_url):
"""...."""
return f'mocked_pr_{url}'
monkeypatch.setattr(url_patterns, '_parse_pattern_or_url',
mocked_parse_pattern_or_url)
assert url_patterns.parse_url('https://example.com') == \
'mocked_pr_https://example.com'
def test_parsed_url_hash(sample_url_parsed):
"""...."""
hash(sample_url_parsed)
|
