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
|
from protego._utils import _hexescape, _unquote
class TestUnquote:
"""Tests for unquote()"""
def test_unquoting(self):
# Make sure unquoting of all ASCII values works
escape_list = []
for num in range(128):
given = _hexescape(chr(num))
expect = chr(num)
result = _unquote(given)
assert expect == result
escape_list.append(given)
escape_string = "".join(escape_list)
del escape_list
result = _unquote(escape_string)
assert result.count("%") == 1, (
f"using unquote(): not all characters escaped: {result}"
)
def test_unquoting_badpercent(self):
# Test unquoting on bad percent-escapes
given = "%xab"
expect = given
result = _unquote(given)
assert expect == result
given = "%x"
expect = given
result = _unquote(given)
assert expect == result
given = "%"
expect = given
result = _unquote(given)
assert expect == result
def test_unquoting_parts(self):
# Make sure unquoting works when have non-quoted characters
# interspersed
given = f"ab{_hexescape('c')}d"
expect = "abcd"
result = _unquote(given)
assert expect == result
def test_unquoting_plus(self):
# Test difference between unquote() and unquote_plus()
given = "are+there+spaces..."
expect = given
result = _unquote(given)
assert expect == result
def test_unquote_with_unicode(self):
# Characters in the Latin-1 range, encoded with UTF-8
given = "br%C3%BCckner_sapporo_20050930.doc"
expect = "br\u00fcckner_sapporo_20050930.doc"
result = _unquote(given)
assert expect == result
# Characters in the Latin-1 range, encoded with None (default)
result = _unquote(given)
assert expect == result
# Characters in BMP, encoded with UTF-8
given = "%E6%BC%A2%E5%AD%97"
expect = "\u6f22\u5b57" # "Kanji"
result = _unquote(given)
assert expect == result
# Decode with UTF-8, invalid sequence
given = "%F3%B1"
expect = "\ufffd" # Replacement character
result = _unquote(given)
assert expect == result
# Decode with UTF-8, invalid sequence, replace errors
result = _unquote(given, errors="replace")
assert expect == result
# Decode with UTF-8, invalid sequence, ignoring errors
given = "%F3%B1"
expect = ""
result = _unquote(given, errors="ignore")
assert expect == result
# A mix of non-ASCII and percent-encoded characters, UTF-8
result = _unquote("\u6f22%C3%BC")
expect = "\u6f22\u00fc"
assert expect == result
def test_escape_sequence_uppercase(self):
result = _unquote("%2fabc%7exyz", ignore="/~")
expect = "%2Fabc%7Exyz"
assert expect == result
|
