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
|
Description: expect newer chardet output
Origin: upstream 50c49a5f + 86a42ecd
Author: Dominik Wombacher
Forwarded: not-needed
--- a/tests/test_pagure_lib_encoding_utils.py
+++ b/tests/test_pagure_lib_encoding_utils.py
@@ -40,7 +40,7 @@ class TestGuessEncoding(unittest.TestCas
"""
Test that strings that could be UTF-8 or ISO-8859-* result in UTF-8.
- python-chardet-3.0.4-2.fc27.noarch detects it as ISO-8859-9
+ python-chardet-3.0.4-2.fc27.noarch and above detects it as ISO-8859-9
python-chardet-2.2.1-1.el7_1.noarch detects it as ISO-8859-2
"""
data = "Šabata".encode("utf-8")
@@ -50,7 +50,7 @@ class TestGuessEncoding(unittest.TestCas
self.assertEqual(result, "WINDOWS-1250")
else:
self.assertEqual(result, "utf-8")
- if chardet.__version__[0] in ("3", "4"):
+ if chardet.__version__[0] in ("3", "4", "5"):
self.assertEqual(chardet_result["encoding"], "ISO-8859-9")
else:
self.assertEqual(chardet_result["encoding"], "ISO-8859-2")
@@ -75,7 +75,11 @@ class TestGuessEncodings(unittest.TestCa
# The first three have different confidence values
expexted_list = ["utf-8", "ISO-8859-9", "ISO-8859-1"]
# This is the one with the least confidence
- self.assertEqual(result[-1].encoding, "windows-1255")
+ print(result)
+ if chardet.__version__ >= '5.1.0':
+ self.assertEqual(result[-1].encoding, "TIS-620")
+ else:
+ self.assertEqual(result[-1].encoding, "windows-1255")
self.assertListEqual(
[encoding.encoding for encoding in result][:3],
expexted_list,
@@ -83,30 +87,58 @@ class TestGuessEncodings(unittest.TestCa
# The values in the middle of the list all have the same confidence
# value and can't be sorted reliably: use sets.
- expected_list = sorted(
- [
- "utf-8",
- "ISO-8859-9",
- "ISO-8859-1",
- "MacCyrillic",
- "IBM866",
- "TIS-620",
- "EUC-JP",
- "EUC-KR",
- "GB2312",
- "KOI8-R",
- "Big5",
- "IBM855",
- "ISO-8859-7",
- "SHIFT_JIS",
- "windows-1253",
- "CP949",
- "EUC-TW",
- "ISO-8859-5",
- "windows-1251",
- "windows-1255",
- ]
- )
+ if chardet.__version__ >= '5.1.0':
+ expected_list = sorted(
+ [
+ "utf-8",
+ "ISO-8859-9",
+ "ISO-8859-1",
+ "MacCyrillic",
+ "IBM866",
+ "TIS-620",
+ "EUC-JP",
+ "EUC-KR",
+ "GB2312",
+ "KOI8-R",
+ "Big5",
+ "IBM855",
+ "ISO-8859-7",
+ "SHIFT_JIS",
+ "windows-1253",
+ "CP949",
+ "EUC-TW",
+ "ISO-8859-5",
+ "windows-1251",
+ "windows-1255",
+ "Johab", # Added in 5.0.0
+ "MacRoman", # Added in 5.1.0
+ ]
+ )
+ else:
+ expected_list = sorted(
+ [
+ "utf-8",
+ "ISO-8859-9",
+ "ISO-8859-1",
+ "MacCyrillic",
+ "IBM866",
+ "TIS-620",
+ "EUC-JP",
+ "EUC-KR",
+ "GB2312",
+ "KOI8-R",
+ "Big5",
+ "IBM855",
+ "ISO-8859-7",
+ "SHIFT_JIS",
+ "windows-1253",
+ "CP949",
+ "EUC-TW",
+ "ISO-8859-5",
+ "windows-1251",
+ "windows-1255",
+ ]
+ )
self.assertListEqual(
sorted(set([encoding.encoding for encoding in result])),
expected_list,
|
