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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
|
#!/usr/bin/env python
#
# test_multibytecodec.py
# Unit test for multibytecodec itself
#
from test import test_support
from test import test_multibytecodec_support
from test.test_support import TESTFN
import unittest, StringIO, codecs, sys, os
ALL_CJKENCODINGS = [
# _codecs_cn
'gb2312', 'gbk', 'gb18030', 'hz',
# _codecs_hk
'big5hkscs',
# _codecs_jp
'cp932', 'shift_jis', 'euc_jp', 'euc_jisx0213', 'shift_jisx0213',
'euc_jis_2004', 'shift_jis_2004',
# _codecs_kr
'cp949', 'euc_kr', 'johab',
# _codecs_tw
'big5', 'cp950',
# _codecs_iso2022
'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004',
'iso2022_jp_3', 'iso2022_jp_ext', 'iso2022_kr',
]
class Test_MultibyteCodec(unittest.TestCase):
def test_nullcoding(self):
for enc in ALL_CJKENCODINGS:
self.assertEqual(''.decode(enc), '')
self.assertEqual(str('', enc), '')
self.assertEqual(''.encode(enc), '')
def test_str_decode(self):
for enc in ALL_CJKENCODINGS:
self.assertEqual('abcd'.encode(enc), 'abcd')
def test_errorcallback_longindex(self):
dec = codecs.getdecoder('euc-kr')
myreplace = lambda exc: ('', sys.maxint+1)
codecs.register_error('test.cjktest', myreplace)
self.assertRaises(IndexError, dec,
'apple\x92ham\x93spam', 'test.cjktest')
def test_codingspec(self):
try:
for enc in ALL_CJKENCODINGS:
print('# coding:', enc, file=open(TESTFN, 'w'))
execfile(TESTFN)
finally:
os.unlink(TESTFN)
class Test_IncrementalEncoder(unittest.TestCase):
def test_stateless(self):
# cp949 encoder isn't stateful at all.
encoder = codecs.getincrementalencoder('cp949')()
self.assertEqual(encoder.encode('\ud30c\uc774\uc36c \ub9c8\uc744'),
'\xc6\xc4\xc0\xcc\xbd\xe3 \xb8\xb6\xc0\xbb')
self.assertEqual(encoder.reset(), None)
self.assertEqual(encoder.encode('\u2606\u223c\u2606', True),
'\xa1\xd9\xa1\xad\xa1\xd9')
self.assertEqual(encoder.reset(), None)
self.assertEqual(encoder.encode('', True), '')
self.assertEqual(encoder.encode('', False), '')
self.assertEqual(encoder.reset(), None)
def test_stateful(self):
# jisx0213 encoder is stateful for a few codepoints. eg)
# U+00E6 => A9DC
# U+00E6 U+0300 => ABC4
# U+0300 => ABDC
encoder = codecs.getincrementalencoder('jisx0213')()
self.assertEqual(encoder.encode('\u00e6\u0300'), '\xab\xc4')
self.assertEqual(encoder.encode('\u00e6'), '')
self.assertEqual(encoder.encode('\u0300'), '\xab\xc4')
self.assertEqual(encoder.encode('\u00e6', True), '\xa9\xdc')
self.assertEqual(encoder.reset(), None)
self.assertEqual(encoder.encode('\u0300'), '\xab\xdc')
self.assertEqual(encoder.encode('\u00e6'), '')
self.assertEqual(encoder.encode('', True), '\xa9\xdc')
self.assertEqual(encoder.encode('', True), '')
def test_stateful_keep_buffer(self):
encoder = codecs.getincrementalencoder('jisx0213')()
self.assertEqual(encoder.encode('\u00e6'), '')
self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
self.assertEqual(encoder.encode('\u0300\u00e6'), '\xab\xc4')
self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
self.assertEqual(encoder.reset(), None)
self.assertEqual(encoder.encode('\u0300'), '\xab\xdc')
self.assertEqual(encoder.encode('\u00e6'), '')
self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
self.assertEqual(encoder.encode('', True), '\xa9\xdc')
class Test_IncrementalDecoder(unittest.TestCase):
def test_dbcs(self):
# cp949 decoder is simple with only 1 or 2 bytes sequences.
decoder = codecs.getincrementaldecoder('cp949')()
self.assertEqual(decoder.decode('\xc6\xc4\xc0\xcc\xbd'),
'\ud30c\uc774')
self.assertEqual(decoder.decode('\xe3 \xb8\xb6\xc0\xbb'),
'\uc36c \ub9c8\uc744')
self.assertEqual(decoder.decode(''), '')
def test_dbcs_keep_buffer(self):
decoder = codecs.getincrementaldecoder('cp949')()
self.assertEqual(decoder.decode('\xc6\xc4\xc0'), '\ud30c')
self.assertRaises(UnicodeDecodeError, decoder.decode, '', True)
self.assertEqual(decoder.decode('\xcc'), '\uc774')
self.assertEqual(decoder.decode('\xc6\xc4\xc0'), '\ud30c')
self.assertRaises(UnicodeDecodeError, decoder.decode, '\xcc\xbd', True)
self.assertEqual(decoder.decode('\xcc'), '\uc774')
def test_iso2022(self):
decoder = codecs.getincrementaldecoder('iso2022-jp')()
ESC = '\x1b'
self.assertEqual(decoder.decode(ESC + '('), '')
self.assertEqual(decoder.decode('B', True), '')
self.assertEqual(decoder.decode(ESC + '$'), '')
self.assertEqual(decoder.decode('B@$'), '\u4e16')
self.assertEqual(decoder.decode('@$@'), '\u4e16')
self.assertEqual(decoder.decode('$', True), '\u4e16')
self.assertEqual(decoder.reset(), None)
self.assertEqual(decoder.decode('@$'), '@$')
self.assertEqual(decoder.decode(ESC + '$'), '')
self.assertRaises(UnicodeDecodeError, decoder.decode, '', True)
self.assertEqual(decoder.decode('B@$'), '\u4e16')
class Test_StreamWriter(unittest.TestCase):
if len('\U00012345') == 2: # UCS2
def test_gb18030(self):
s= StringIO.StringIO()
c = codecs.getwriter('gb18030')(s)
c.write('123')
self.assertEqual(s.getvalue(), '123')
c.write('\U00012345')
self.assertEqual(s.getvalue(), '123\x907\x959')
c.write('\U00012345'[0])
self.assertEqual(s.getvalue(), '123\x907\x959')
c.write('\U00012345'[1] + '\U00012345' + '\uac00\u00ac')
self.assertEqual(s.getvalue(),
'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')
c.write('\U00012345'[0])
self.assertEqual(s.getvalue(),
'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')
self.assertRaises(UnicodeError, c.reset)
self.assertEqual(s.getvalue(),
'123\x907\x959\x907\x959\x907\x959\x827\xcf5\x810\x851')
def test_utf_8(self):
s= StringIO.StringIO()
c = codecs.getwriter('utf-8')(s)
c.write('123')
self.assertEqual(s.getvalue(), '123')
c.write('\U00012345')
self.assertEqual(s.getvalue(), '123\xf0\x92\x8d\x85')
# Python utf-8 codec can't buffer surrogate pairs yet.
if 0:
c.write('\U00012345'[0])
self.assertEqual(s.getvalue(), '123\xf0\x92\x8d\x85')
c.write('\U00012345'[1] + '\U00012345' + '\uac00\u00ac')
self.assertEqual(s.getvalue(),
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
'\xea\xb0\x80\xc2\xac')
c.write('\U00012345'[0])
self.assertEqual(s.getvalue(),
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
'\xea\xb0\x80\xc2\xac')
c.reset()
self.assertEqual(s.getvalue(),
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
'\xea\xb0\x80\xc2\xac\xed\xa0\x88')
c.write('\U00012345'[1])
self.assertEqual(s.getvalue(),
'123\xf0\x92\x8d\x85\xf0\x92\x8d\x85\xf0\x92\x8d\x85'
'\xea\xb0\x80\xc2\xac\xed\xa0\x88\xed\xbd\x85')
else: # UCS4
pass
def test_streamwriter_strwrite(self):
s = StringIO.StringIO()
wr = codecs.getwriter('gb18030')(s)
wr.write('abcd')
self.assertEqual(s.getvalue(), 'abcd')
class Test_ISO2022(unittest.TestCase):
def test_g2(self):
iso2022jp2 = '\x1b(B:hu4:unit\x1b.A\x1bNi de famille'
uni = ':hu4:unit\xe9 de famille'
self.assertEqual(iso2022jp2.decode('iso2022-jp-2'), uni)
def test_iso2022_jp_g0(self):
self.failIf('\x0e' in '\N{SOFT HYPHEN}'.encode('iso-2022-jp-2'))
for encoding in ('iso-2022-jp-2004', 'iso-2022-jp-3'):
e = '\u3406'.encode(encoding)
self.failIf(filter(lambda x: x >= '\x80', e))
def test_bug1572832(self):
if sys.maxunicode >= 0x10000:
myunichr = chr
else:
myunichr = lambda x: chr(0xD7C0+(x>>10)) + chr(0xDC00+(x&0x3FF))
for x in range(0x10000, 0x110000):
# Any ISO 2022 codec will cause the segfault
myunichr(x).encode('iso_2022_jp', 'ignore')
def test_main():
test_support.run_unittest(__name__)
if __name__ == "__main__":
test_main()
|
