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
|
import codecs
from collections import OrderedDict
from test.test_json import PyTest, CTest
class TestUnicode:
# test_encoding1 and test_encoding2 from 2.x are irrelevant (only str
# is supported as input, not bytes).
def test_encoding3(self):
u = '\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = self.dumps(u)
self.assertEqual(j, '"\\u03b1\\u03a9"')
def test_encoding4(self):
u = '\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = self.dumps([u])
self.assertEqual(j, '["\\u03b1\\u03a9"]')
def test_encoding5(self):
u = '\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = self.dumps(u, ensure_ascii=False)
self.assertEqual(j, '"{0}"'.format(u))
def test_encoding6(self):
u = '\N{GREEK SMALL LETTER ALPHA}\N{GREEK CAPITAL LETTER OMEGA}'
j = self.dumps([u], ensure_ascii=False)
self.assertEqual(j, '["{0}"]'.format(u))
def test_big_unicode_encode(self):
u = '\U0001d120'
self.assertEqual(self.dumps(u), '"\\ud834\\udd20"')
self.assertEqual(self.dumps(u, ensure_ascii=False), '"\U0001d120"')
def test_big_unicode_decode(self):
u = 'z\U0001d120x'
self.assertEqual(self.loads('"' + u + '"'), u)
self.assertEqual(self.loads('"z\\ud834\\udd20x"'), u)
def test_unicode_decode(self):
for i in range(0, 0xd7ff):
u = chr(i)
s = '"\\u{0:04x}"'.format(i)
self.assertEqual(self.loads(s), u)
def test_unicode_preservation(self):
self.assertEqual(type(self.loads('""')), str)
self.assertEqual(type(self.loads('"a"')), str)
self.assertEqual(type(self.loads('["a"]')[0]), str)
def test_bytes_encode(self):
self.assertRaises(TypeError, self.dumps, b"hi")
self.assertRaises(TypeError, self.dumps, [b"hi"])
def test_bytes_decode(self):
for encoding, bom in [
('utf-8', codecs.BOM_UTF8),
('utf-16be', codecs.BOM_UTF16_BE),
('utf-16le', codecs.BOM_UTF16_LE),
('utf-32be', codecs.BOM_UTF32_BE),
('utf-32le', codecs.BOM_UTF32_LE),
]:
data = ["a\xb5\u20ac\U0001d120"]
encoded = self.dumps(data).encode(encoding)
self.assertEqual(self.loads(bom + encoded), data)
self.assertEqual(self.loads(encoded), data)
self.assertRaises(UnicodeDecodeError, self.loads, b'["\x80"]')
def test_object_pairs_hook_with_unicode(self):
s = '{"xkd":1, "kcw":2, "art":3, "hxm":4, "qrt":5, "pad":6, "hoy":7}'
p = [("xkd", 1), ("kcw", 2), ("art", 3), ("hxm", 4),
("qrt", 5), ("pad", 6), ("hoy", 7)]
self.assertEqual(self.loads(s), eval(s))
self.assertEqual(self.loads(s, object_pairs_hook = lambda x: x), p)
od = self.loads(s, object_pairs_hook = OrderedDict)
self.assertEqual(od, OrderedDict(p))
self.assertEqual(type(od), OrderedDict)
# the object_pairs_hook takes priority over the object_hook
self.assertEqual(self.loads(s, object_pairs_hook = OrderedDict,
object_hook = lambda x: None),
OrderedDict(p))
class TestPyUnicode(TestUnicode, PyTest): pass
class TestCUnicode(TestUnicode, CTest): pass
|
