-
Notifications
You must be signed in to change notification settings - Fork 575
/
test_simple_characters.py
155 lines (110 loc) · 4.94 KB
/
test_simple_characters.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
# coding=utf-8
#
# This file is part of Hypothesis, which may be found at
# https://github.com/HypothesisWorks/hypothesis/
#
# Most of this work is copyright (C) 2013-2019 David R. MacIver
# (david@drmaciver.com), but it contains contributions by others. See
# CONTRIBUTING.rst for a full list of people who may hold copyright, and
# consult the git log if you need to determine who owns an individual
# contribution.
#
# This Source Code Form is subject to the terms of the Mozilla Public License,
# v. 2.0. If a copy of the MPL was not distributed with this file, You can
# obtain one at https://mozilla.org/MPL/2.0/.
#
# END HEADER
from __future__ import absolute_import, division, print_function
import unicodedata
import pytest
from hypothesis.errors import InvalidArgument
from hypothesis.internal.compat import text_type
from hypothesis.strategies import characters
from tests.common.debug import assert_no_examples, find_any, minimal
from tests.common.utils import fails_with
@fails_with(InvalidArgument)
def test_nonexistent_category_argument():
characters(blacklist_categories=["foo"]).example()
def test_bad_codepoint_arguments():
with pytest.raises(InvalidArgument):
characters(min_codepoint=42, max_codepoint=24).example()
def test_exclude_all_available_range():
with pytest.raises(InvalidArgument):
characters(
min_codepoint=ord("0"), max_codepoint=ord("0"), blacklist_characters="0"
).example()
def test_when_nothing_could_be_produced():
with pytest.raises(InvalidArgument):
characters(
whitelist_categories=["Cc"], min_codepoint=ord("0"), max_codepoint=ord("9")
).example()
def test_characters_of_specific_groups():
st = characters(whitelist_categories=("Lu", "Nd"))
find_any(st, lambda c: unicodedata.category(c) == "Lu")
find_any(st, lambda c: unicodedata.category(c) == "Nd")
assert_no_examples(st, lambda c: unicodedata.category(c) not in ("Lu", "Nd"))
def test_characters_of_major_categories():
st = characters(whitelist_categories=("L", "N"))
find_any(st, lambda c: unicodedata.category(c).startswith("L"))
find_any(st, lambda c: unicodedata.category(c).startswith("N"))
assert_no_examples(st, lambda c: unicodedata.category(c)[0] not in ("L", "N"))
def test_exclude_characters_of_specific_groups():
st = characters(blacklist_categories=("Lu", "Nd"))
find_any(st, lambda c: unicodedata.category(c) != "Lu")
find_any(st, lambda c: unicodedata.category(c) != "Nd")
assert_no_examples(st, lambda c: unicodedata.category(c) in ("Lu", "Nd"))
def test_exclude_characters_of_major_categories():
st = characters(blacklist_categories=("L", "N"))
find_any(st, lambda c: not unicodedata.category(c).startswith("L"))
find_any(st, lambda c: not unicodedata.category(c).startswith("N"))
assert_no_examples(st, lambda c: unicodedata.category(c)[0] in ("L", "N"))
def test_find_one():
char = minimal(characters(min_codepoint=48, max_codepoint=48), lambda _: True)
assert char == u"0"
def test_find_something_rare():
st = characters(whitelist_categories=["Zs"], min_codepoint=12288)
find_any(st, lambda c: unicodedata.category(c) == "Zs")
assert_no_examples(st, lambda c: unicodedata.category(c) != "Zs")
def test_whitelisted_characters_alone():
with pytest.raises(InvalidArgument):
characters(whitelist_characters=u"te02тест49st").example()
def test_whitelisted_characters_overlap_blacklisted_characters():
good_chars = u"te02тест49st"
bad_chars = u"ts94тсет"
with pytest.raises(InvalidArgument) as exc:
characters(
min_codepoint=ord("0"),
max_codepoint=ord("9"),
whitelist_characters=good_chars,
blacklist_characters=bad_chars,
).example()
assert repr(good_chars) in text_type(exc)
assert repr(bad_chars) in text_type(exc)
def test_whitelisted_characters_override():
good_characters = u"teтестst"
st = characters(
min_codepoint=ord("0"),
max_codepoint=ord("9"),
whitelist_characters=good_characters,
)
find_any(st, lambda c: c in good_characters)
find_any(st, lambda c: c in "0123456789")
assert_no_examples(st, lambda c: c not in good_characters + "0123456789")
@pytest.mark.skip # temporary skip due to 560 second (!) perf regression; see #1864
def test_blacklisted_characters():
bad_chars = u"te02тест49st"
st = characters(
min_codepoint=ord("0"), max_codepoint=ord("9"), blacklist_characters=bad_chars
)
assert "1" == minimal(st, lambda c: True)
assert_no_examples(st, lambda c: c in bad_chars)
def test_whitelist_characters_disjoint_blacklist_characters():
good_chars = u"123abc"
bad_chars = u"456def"
st = characters(
min_codepoint=ord("0"),
max_codepoint=ord("9"),
blacklist_characters=bad_chars,
whitelist_characters=good_chars,
)
assert_no_examples(st, lambda c: c in bad_chars)