Debian Codegraph @

Lib/test/test_codecencodings_jp.py

raw
1 #
2 # test_codecencodings_jp.py
3 # Codec encoding tests for Japanese encodings.
4 #
5
6 from test import multibytecodec_support
7 import unittest
8
9 class Test_CP932(multibytecodec_support.TestBase, unittest.TestCase):
10 encoding = 'cp932'
11 tstring = multibytecodec_support.load_teststring('shift_jis')
12 codectests = (
13 # invalid bytes
14 (b"abc\x81\x00\x81\x00\x82\x84", "strict", None),
15 (b"abc\xf8", "strict", None),
16 (b"abc\x81\x00\x82\x84", "replace", "abc\ufffd\x00\uff44"),
17 (b"abc\x81\x00\x82\x84\x88", "replace", "abc\ufffd\x00\uff44\ufffd"),
18 (b"abc\x81\x00\x82\x84", "ignore", "abc\x00\uff44"),
19 (b"ab\xEBxy", "replace", "ab\uFFFDxy"),
20 (b"ab\xF0\x39xy", "replace", "ab\uFFFD9xy"),
21 (b"ab\xEA\xF0xy", "replace", 'ab\ufffd\ue038y'),
22 # sjis vs cp932
23 (b"\\\x7e", "replace", "\\\x7e"),
24 (b"\x81\x5f\x81\x61\x81\x7c", "replace", "\uff3c\u2225\uff0d"),
25 )
26
27 euc_commontests = (
28 # invalid bytes
29 (b"abc\x80\x80\xc1\xc4", "strict", None),
30 (b"abc\x80\x80\xc1\xc4", "replace", "abc\ufffd\ufffd\u7956"),
31 (b"abc\x80\x80\xc1\xc4\xc8", "replace", "abc\ufffd\ufffd\u7956\ufffd"),
32 (b"abc\x80\x80\xc1\xc4", "ignore", "abc\u7956"),
33 (b"abc\xc8", "strict", None),
34 (b"abc\x8f\x83\x83", "replace", "abc\ufffd\ufffd\ufffd"),
35 (b"\x82\xFCxy", "replace", "\ufffd\ufffdxy"),
36 (b"\xc1\x64", "strict", None),
37 (b"\xa1\xc0", "strict", "\uff3c"),
38 (b"\xa1\xc0\\", "strict", "\uff3c\\"),
39 (b"\x8eXY", "replace", "\ufffdXY"),
40 )
41
42 class Test_EUC_JIS_2004(multibytecodec_support.TestBase,
43 unittest.TestCase):
44 encoding = 'euc_jis_2004'
45 tstring = multibytecodec_support.load_teststring('euc_jisx0213')
46 codectests = euc_commontests
47 xmlcharnametest = (
48 "\xab\u211c\xbb = \u2329\u1234\u232a",
49 b"\xa9\xa8ℜ\xa9\xb2 = ⟨ሴ⟩"
50 )
51
52 class Test_EUC_JISX0213(multibytecodec_support.TestBase,
53 unittest.TestCase):
54 encoding = 'euc_jisx0213'
55 tstring = multibytecodec_support.load_teststring('euc_jisx0213')
56 codectests = euc_commontests
57 xmlcharnametest = (
58 "\xab\u211c\xbb = \u2329\u1234\u232a",
59 b"\xa9\xa8ℜ\xa9\xb2 = ⟨ሴ⟩"
60 )
61
62 class Test_EUC_JP_COMPAT(multibytecodec_support.TestBase,
63 unittest.TestCase):
64 encoding = 'euc_jp'
65 tstring = multibytecodec_support.load_teststring('euc_jp')
66 codectests = euc_commontests + (
67 ("\xa5", "strict", b"\x5c"),
68 ("\u203e", "strict", b"\x7e"),
69 )
70
71 shiftjis_commonenctests = (
72 (b"abc\x80\x80\x82\x84", "strict", None),
73 (b"abc\xf8", "strict", None),
74 (b"abc\x80\x80\x82\x84def", "ignore", "abc\uff44def"),
75 )
76
77 class Test_SJIS_COMPAT(multibytecodec_support.TestBase, unittest.TestCase):
78 encoding = 'shift_jis'
79 tstring = multibytecodec_support.load_teststring('shift_jis')
80 codectests = shiftjis_commonenctests + (
81 (b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\ufffd\uff44"),
82 (b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\ufffd\uff44\ufffd"),
83
84 (b"\\\x7e", "strict", "\\\x7e"),
85 (b"\x81\x5f\x81\x61\x81\x7c", "strict", "\uff3c\u2016\u2212"),
86 (b"abc\x81\x39", "replace", "abc\ufffd9"),
87 (b"abc\xEA\xFC", "replace", "abc\ufffd\ufffd"),
88 (b"abc\xFF\x58", "replace", "abc\ufffdX"),
89 )
90
91 class Test_SJIS_2004(multibytecodec_support.TestBase, unittest.TestCase):
92 encoding = 'shift_jis_2004'
93 tstring = multibytecodec_support.load_teststring('shift_jis')
94 codectests = shiftjis_commonenctests + (
95 (b"\\\x7e", "strict", "\xa5\u203e"),
96 (b"\x81\x5f\x81\x61\x81\x7c", "strict", "\\\u2016\u2212"),
97 (b"abc\xEA\xFC", "strict", "abc\u64bf"),
98 (b"\x81\x39xy", "replace", "\ufffd9xy"),
99 (b"\xFF\x58xy", "replace", "\ufffdXxy"),
100 (b"\x80\x80\x82\x84xy", "replace", "\ufffd\ufffd\uff44xy"),
101 (b"\x80\x80\x82\x84\x88xy", "replace", "\ufffd\ufffd\uff44\u5864y"),
102 (b"\xFC\xFBxy", "replace", '\ufffd\u95b4y'),
103 )
104 xmlcharnametest = (
105 "\xab\u211c\xbb = \u2329\u1234\u232a",
106 b"\x85Gℜ\x85Q = ⟨ሴ⟩"
107 )
108
109 class Test_SJISX0213(multibytecodec_support.TestBase, unittest.TestCase):
110 encoding = 'shift_jisx0213'
111 tstring = multibytecodec_support.load_teststring('shift_jisx0213')
112 codectests = shiftjis_commonenctests + (
113 (b"abc\x80\x80\x82\x84", "replace", "abc\ufffd\ufffd\uff44"),
114 (b"abc\x80\x80\x82\x84\x88", "replace", "abc\ufffd\ufffd\uff44\ufffd"),
115
116 # sjis vs cp932
117 (b"\\\x7e", "replace", "\xa5\u203e"),
118 (b"\x81\x5f\x81\x61\x81\x7c", "replace", "\x5c\u2016\u2212"),
119 )
120 xmlcharnametest = (
121 "\xab\u211c\xbb = \u2329\u1234\u232a",
122 b"\x85Gℜ\x85Q = ⟨ሴ⟩"
123 )
124
125 if __name__ == "__main__":
126 unittest.main()