Python code coverage for Lib/test/test_multibytecodec.py

#	count	content
1	n/a	#
2	n/a	# test_multibytecodec.py
3	n/a	# Unit test for multibytecodec itself
4	n/a	#
5	n/a
6	n/a	from test import support
7	n/a	from test.support import TESTFN
8	n/a	import unittest, io, codecs, sys
9	n/a	import _multibytecodec
10	n/a
11	n/a	ALL_CJKENCODINGS = [
12	n/a	# _codecs_cn
13	n/a	'gb2312', 'gbk', 'gb18030', 'hz',
14	n/a	# _codecs_hk
15	n/a	'big5hkscs',
16	n/a	# _codecs_jp
17	n/a	'cp932', 'shift_jis', 'euc_jp', 'euc_jisx0213', 'shift_jisx0213',
18	n/a	'euc_jis_2004', 'shift_jis_2004',
19	n/a	# _codecs_kr
20	n/a	'cp949', 'euc_kr', 'johab',
21	n/a	# _codecs_tw
22	n/a	'big5', 'cp950',
23	n/a	# _codecs_iso2022
24	n/a	'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2', 'iso2022_jp_2004',
25	n/a	'iso2022_jp_3', 'iso2022_jp_ext', 'iso2022_kr',
26	n/a	]
27	n/a
28	n/a	class Test_MultibyteCodec(unittest.TestCase):
29	n/a
30	n/a	def test_nullcoding(self):
31	n/a	for enc in ALL_CJKENCODINGS:
32	n/a	self.assertEqual(b''.decode(enc), '')
33	n/a	self.assertEqual(str(b'', enc), '')
34	n/a	self.assertEqual(''.encode(enc), b'')
35	n/a
36	n/a	def test_str_decode(self):
37	n/a	for enc in ALL_CJKENCODINGS:
38	n/a	self.assertEqual('abcd'.encode(enc), b'abcd')
39	n/a
40	n/a	def test_errorcallback_longindex(self):
41	n/a	dec = codecs.getdecoder('euc-kr')
42	n/a	myreplace = lambda exc: ('', sys.maxsize+1)
43	n/a	codecs.register_error('test.cjktest', myreplace)
44	n/a	self.assertRaises(IndexError, dec,
45	n/a	b'apple\x92ham\x93spam', 'test.cjktest')
46	n/a
47	n/a	def test_errorcallback_custom_ignore(self):
48	n/a	# Issue #23215: MemoryError with custom error handlers and multibyte codecs
49	n/a	data = 100 * "\udc00"
50	n/a	codecs.register_error("test.ignore", codecs.ignore_errors)
51	n/a	for enc in ALL_CJKENCODINGS:
52	n/a	self.assertEqual(data.encode(enc, "test.ignore"), b'')
53	n/a
54	n/a	def test_codingspec(self):
55	n/a	try:
56	n/a	for enc in ALL_CJKENCODINGS:
57	n/a	code = '# coding: {}\n'.format(enc)
58	n/a	exec(code)
59	n/a	finally:
60	n/a	support.unlink(TESTFN)
61	n/a
62	n/a	def test_init_segfault(self):
63	n/a	# bug #3305: this used to segfault
64	n/a	self.assertRaises(AttributeError,
65	n/a	_multibytecodec.MultibyteStreamReader, None)
66	n/a	self.assertRaises(AttributeError,
67	n/a	_multibytecodec.MultibyteStreamWriter, None)
68	n/a
69	n/a	def test_decode_unicode(self):
70	n/a	# Trying to decode a unicode string should raise a TypeError
71	n/a	for enc in ALL_CJKENCODINGS:
72	n/a	self.assertRaises(TypeError, codecs.getdecoder(enc), "")
73	n/a
74	n/a	class Test_IncrementalEncoder(unittest.TestCase):
75	n/a
76	n/a	def test_stateless(self):
77	n/a	# cp949 encoder isn't stateful at all.
78	n/a	encoder = codecs.getincrementalencoder('cp949')()
79	n/a	self.assertEqual(encoder.encode('\ud30c\uc774\uc36c \ub9c8\uc744'),
80	n/a	b'\xc6\xc4\xc0\xcc\xbd\xe3 \xb8\xb6\xc0\xbb')
81	n/a	self.assertEqual(encoder.reset(), None)
82	n/a	self.assertEqual(encoder.encode('\u2606\u223c\u2606', True),
83	n/a	b'\xa1\xd9\xa1\xad\xa1\xd9')
84	n/a	self.assertEqual(encoder.reset(), None)
85	n/a	self.assertEqual(encoder.encode('', True), b'')
86	n/a	self.assertEqual(encoder.encode('', False), b'')
87	n/a	self.assertEqual(encoder.reset(), None)
88	n/a
89	n/a	def test_stateful(self):
90	n/a	# jisx0213 encoder is stateful for a few code points. eg)
91	n/a	# U+00E6 => A9DC
92	n/a	# U+00E6 U+0300 => ABC4
93	n/a	# U+0300 => ABDC
94	n/a
95	n/a	encoder = codecs.getincrementalencoder('jisx0213')()
96	n/a	self.assertEqual(encoder.encode('\u00e6\u0300'), b'\xab\xc4')
97	n/a	self.assertEqual(encoder.encode('\u00e6'), b'')
98	n/a	self.assertEqual(encoder.encode('\u0300'), b'\xab\xc4')
99	n/a	self.assertEqual(encoder.encode('\u00e6', True), b'\xa9\xdc')
100	n/a
101	n/a	self.assertEqual(encoder.reset(), None)
102	n/a	self.assertEqual(encoder.encode('\u0300'), b'\xab\xdc')
103	n/a
104	n/a	self.assertEqual(encoder.encode('\u00e6'), b'')
105	n/a	self.assertEqual(encoder.encode('', True), b'\xa9\xdc')
106	n/a	self.assertEqual(encoder.encode('', True), b'')
107	n/a
108	n/a	def test_stateful_keep_buffer(self):
109	n/a	encoder = codecs.getincrementalencoder('jisx0213')()
110	n/a	self.assertEqual(encoder.encode('\u00e6'), b'')
111	n/a	self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
112	n/a	self.assertEqual(encoder.encode('\u0300\u00e6'), b'\xab\xc4')
113	n/a	self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
114	n/a	self.assertEqual(encoder.reset(), None)
115	n/a	self.assertEqual(encoder.encode('\u0300'), b'\xab\xdc')
116	n/a	self.assertEqual(encoder.encode('\u00e6'), b'')
117	n/a	self.assertRaises(UnicodeEncodeError, encoder.encode, '\u0123')
118	n/a	self.assertEqual(encoder.encode('', True), b'\xa9\xdc')
119	n/a
120	n/a	def test_issue5640(self):
121	n/a	encoder = codecs.getincrementalencoder('shift-jis')('backslashreplace')
122	n/a	self.assertEqual(encoder.encode('\xff'), b'\\xff')
123	n/a	self.assertEqual(encoder.encode('\n'), b'\n')
124	n/a
125	n/a	class Test_IncrementalDecoder(unittest.TestCase):
126	n/a
127	n/a	def test_dbcs(self):
128	n/a	# cp949 decoder is simple with only 1 or 2 bytes sequences.
129	n/a	decoder = codecs.getincrementaldecoder('cp949')()
130	n/a	self.assertEqual(decoder.decode(b'\xc6\xc4\xc0\xcc\xbd'),
131	n/a	'\ud30c\uc774')
132	n/a	self.assertEqual(decoder.decode(b'\xe3 \xb8\xb6\xc0\xbb'),
133	n/a	'\uc36c \ub9c8\uc744')
134	n/a	self.assertEqual(decoder.decode(b''), '')
135	n/a
136	n/a	def test_dbcs_keep_buffer(self):
137	n/a	decoder = codecs.getincrementaldecoder('cp949')()
138	n/a	self.assertEqual(decoder.decode(b'\xc6\xc4\xc0'), '\ud30c')
139	n/a	self.assertRaises(UnicodeDecodeError, decoder.decode, b'', True)
140	n/a	self.assertEqual(decoder.decode(b'\xcc'), '\uc774')
141	n/a
142	n/a	self.assertEqual(decoder.decode(b'\xc6\xc4\xc0'), '\ud30c')
143	n/a	self.assertRaises(UnicodeDecodeError, decoder.decode,
144	n/a	b'\xcc\xbd', True)
145	n/a	self.assertEqual(decoder.decode(b'\xcc'), '\uc774')
146	n/a
147	n/a	def test_iso2022(self):
148	n/a	decoder = codecs.getincrementaldecoder('iso2022-jp')()
149	n/a	ESC = b'\x1b'
150	n/a	self.assertEqual(decoder.decode(ESC + b'('), '')
151	n/a	self.assertEqual(decoder.decode(b'B', True), '')
152	n/a	self.assertEqual(decoder.decode(ESC + b'$'), '')
153	n/a	self.assertEqual(decoder.decode(b'B@$'), '\u4e16')
154	n/a	self.assertEqual(decoder.decode(b'@$@'), '\u4e16')
155	n/a	self.assertEqual(decoder.decode(b'$', True), '\u4e16')
156	n/a	self.assertEqual(decoder.reset(), None)
157	n/a	self.assertEqual(decoder.decode(b'@$'), '@$')
158	n/a	self.assertEqual(decoder.decode(ESC + b'$'), '')
159	n/a	self.assertRaises(UnicodeDecodeError, decoder.decode, b'', True)
160	n/a	self.assertEqual(decoder.decode(b'B@$'), '\u4e16')
161	n/a
162	n/a	def test_decode_unicode(self):
163	n/a	# Trying to decode a unicode string should raise a TypeError
164	n/a	for enc in ALL_CJKENCODINGS:
165	n/a	decoder = codecs.getincrementaldecoder(enc)()
166	n/a	self.assertRaises(TypeError, decoder.decode, "")
167	n/a
168	n/a	class Test_StreamReader(unittest.TestCase):
169	n/a	def test_bug1728403(self):
170	n/a	try:
171	n/a	f = open(TESTFN, 'wb')
172	n/a	try:
173	n/a	f.write(b'\xa1')
174	n/a	finally:
175	n/a	f.close()
176	n/a	f = codecs.open(TESTFN, encoding='cp949')
177	n/a	try:
178	n/a	self.assertRaises(UnicodeDecodeError, f.read, 2)
179	n/a	finally:
180	n/a	f.close()
181	n/a	finally:
182	n/a	support.unlink(TESTFN)
183	n/a
184	n/a	class Test_StreamWriter(unittest.TestCase):
185	n/a	def test_gb18030(self):
186	n/a	s= io.BytesIO()
187	n/a	c = codecs.getwriter('gb18030')(s)
188	n/a	c.write('123')
189	n/a	self.assertEqual(s.getvalue(), b'123')
190	n/a	c.write('\U00012345')
191	n/a	self.assertEqual(s.getvalue(), b'123\x907\x959')
192	n/a	c.write('\uac00\u00ac')
193	n/a	self.assertEqual(s.getvalue(),
194	n/a	b'123\x907\x959\x827\xcf5\x810\x851')
195	n/a
196	n/a	def test_utf_8(self):
197	n/a	s= io.BytesIO()
198	n/a	c = codecs.getwriter('utf-8')(s)
199	n/a	c.write('123')
200	n/a	self.assertEqual(s.getvalue(), b'123')
201	n/a	c.write('\U00012345')
202	n/a	self.assertEqual(s.getvalue(), b'123\xf0\x92\x8d\x85')
203	n/a	c.write('\uac00\u00ac')
204	n/a	self.assertEqual(s.getvalue(),
205	n/a	b'123\xf0\x92\x8d\x85'
206	n/a	b'\xea\xb0\x80\xc2\xac')
207	n/a
208	n/a	def test_streamwriter_strwrite(self):
209	n/a	s = io.BytesIO()
210	n/a	wr = codecs.getwriter('gb18030')(s)
211	n/a	wr.write('abcd')
212	n/a	self.assertEqual(s.getvalue(), b'abcd')
213	n/a
214	n/a	class Test_ISO2022(unittest.TestCase):
215	n/a	def test_g2(self):
216	n/a	iso2022jp2 = b'\x1b(B:hu4:unit\x1b.A\x1bNi de famille'
217	n/a	uni = ':hu4:unit\xe9 de famille'
218	n/a	self.assertEqual(iso2022jp2.decode('iso2022-jp-2'), uni)
219	n/a
220	n/a	def test_iso2022_jp_g0(self):
221	n/a	self.assertNotIn(b'\x0e', '\N{SOFT HYPHEN}'.encode('iso-2022-jp-2'))
222	n/a	for encoding in ('iso-2022-jp-2004', 'iso-2022-jp-3'):
223	n/a	e = '\u3406'.encode(encoding)
224	n/a	self.assertFalse(any(x > 0x80 for x in e))
225	n/a
226	n/a	def test_bug1572832(self):
227	n/a	for x in range(0x10000, 0x110000):
228	n/a	# Any ISO 2022 codec will cause the segfault
229	n/a	chr(x).encode('iso_2022_jp', 'ignore')
230	n/a
231	n/a	class TestStateful(unittest.TestCase):
232	n/a	text = '\u4E16\u4E16'
233	n/a	encoding = 'iso-2022-jp'
234	n/a	expected = b'\x1b$B@$@$'
235	n/a	reset = b'\x1b(B'
236	n/a	expected_reset = expected + reset
237	n/a
238	n/a	def test_encode(self):
239	n/a	self.assertEqual(self.text.encode(self.encoding), self.expected_reset)
240	n/a
241	n/a	def test_incrementalencoder(self):
242	n/a	encoder = codecs.getincrementalencoder(self.encoding)()
243	n/a	output = b''.join(
244	n/a	encoder.encode(char)
245	n/a	for char in self.text)
246	n/a	self.assertEqual(output, self.expected)
247	n/a	self.assertEqual(encoder.encode('', final=True), self.reset)
248	n/a	self.assertEqual(encoder.encode('', final=True), b'')
249	n/a
250	n/a	def test_incrementalencoder_final(self):
251	n/a	encoder = codecs.getincrementalencoder(self.encoding)()
252	n/a	last_index = len(self.text) - 1
253	n/a	output = b''.join(
254	n/a	encoder.encode(char, index == last_index)
255	n/a	for index, char in enumerate(self.text))
256	n/a	self.assertEqual(output, self.expected_reset)
257	n/a	self.assertEqual(encoder.encode('', final=True), b'')
258	n/a
259	n/a	class TestHZStateful(TestStateful):
260	n/a	text = '\u804a\u804a'
261	n/a	encoding = 'hz'
262	n/a	expected = b'~{ADAD'
263	n/a	reset = b'~}'
264	n/a	expected_reset = expected + reset
265	n/a
266	n/a	def test_main():
267	n/a	support.run_unittest(__name__)
268	n/a
269	n/a	if __name__ == "__main__":
270	n/a	test_main()