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
|
# This file is part of Hypothesis, which may be found at
# https://github.com/HypothesisWorks/hypothesis/
#
# Copyright the Hypothesis Authors.
# Individual contributors are listed in AUTHORS.rst and the git log.
#
# 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/.
import string
from encodings.aliases import aliases
import pytest
from hypothesis import given, settings, strategies as st
from tests.common.utils import Why, xfail_on_crosshair
IDENTIFIER_CHARS = string.ascii_letters + string.digits + "_"
@given(st.characters(exclude_characters=IDENTIFIER_CHARS))
def test_large_blacklist(c):
assert c not in IDENTIFIER_CHARS
@xfail_on_crosshair(Why.symbolic_outside_context) # seems like a crosshair bug here
@given(st.data())
def test_arbitrary_blacklist(data):
blacklist = data.draw(st.text(st.characters(max_codepoint=1000), min_size=1))
ords = list(map(ord, blacklist))
c = data.draw(
st.characters(
exclude_characters=blacklist,
min_codepoint=max(0, min(ords) - 1),
max_codepoint=max(0, max(ords) + 1),
)
)
assert c not in blacklist
def _enc(cdc):
try:
"".encode(cdc)
return True
except Exception:
return False
lots_of_encodings = sorted(x for x in set(aliases).union(aliases.values()) if _enc(x))
assert len(lots_of_encodings) > 100 # sanity-check
@pytest.mark.skipif(
settings._current_profile == "crosshair",
reason="takes 2000s; large & slow symbolic strings",
)
@given(data=st.data(), codec=st.sampled_from(lots_of_encodings))
@settings(max_examples=10)
def test_can_constrain_characters_to_codec(data, codec):
s = data.draw(st.text(st.characters(codec=codec), min_size=50))
s.encode(codec)
|
