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
|
# -*- coding: koi8-r -*-
import unittest
from test.support import TESTFN, unlink, unload, rmtree, script_helper, captured_stdout
import importlib
import os
import sys
import subprocess
import tempfile
class MiscSourceEncodingTest(unittest.TestCase):
def test_pep263(self):
self.assertEqual(
"ðÉÔÏÎ".encode("utf-8"),
b'\xd0\x9f\xd0\xb8\xd1\x82\xd0\xbe\xd0\xbd'
)
self.assertEqual(
"\ð".encode("utf-8"),
b'\\\xd0\x9f'
)
def test_compilestring(self):
# see #1882
c = compile(b"\n# coding: utf-8\nu = '\xc3\xb3'\n", "dummy", "exec")
d = {}
exec(c, d)
self.assertEqual(d['u'], '\xf3')
def test_issue2301(self):
try:
compile(b"# coding: cp932\nprint '\x94\x4e'", "dummy", "exec")
except SyntaxError as v:
self.assertEqual(v.text.rstrip('\n'), "print '\u5e74'")
else:
self.fail()
def test_issue4626(self):
c = compile("# coding=latin-1\n\u00c6 = '\u00c6'", "dummy", "exec")
d = {}
exec(c, d)
self.assertEqual(d['\xc6'], '\xc6')
def test_issue3297(self):
c = compile("a, b = '\U0001010F', '\\U0001010F'", "dummy", "exec")
d = {}
exec(c, d)
self.assertEqual(d['a'], d['b'])
self.assertEqual(len(d['a']), len(d['b']))
self.assertEqual(ascii(d['a']), ascii(d['b']))
def test_issue7820(self):
# Ensure that check_bom() restores all bytes in the right order if
# check_bom() fails in pydebug mode: a buffer starts with the first
# byte of a valid BOM, but next bytes are different
# one byte in common with the UTF-16-LE BOM
self.assertRaises(SyntaxError, eval, b'\xff\x20')
# two bytes in common with the UTF-8 BOM
self.assertRaises(SyntaxError, eval, b'\xef\xbb\x20')
def test_20731(self):
sub = subprocess.Popen([sys.executable,
os.path.join(os.path.dirname(__file__),
'coding20731.py')],
stderr=subprocess.PIPE)
err = sub.communicate()[1]
self.assertEqual(sub.returncode, 0)
self.assertNotIn(b'SyntaxError', err)
def test_error_message(self):
compile(b'# -*- coding: iso-8859-15 -*-\n', 'dummy', 'exec')
compile(b'\xef\xbb\xbf\n', 'dummy', 'exec')
compile(b'\xef\xbb\xbf# -*- coding: utf-8 -*-\n', 'dummy', 'exec')
with self.assertRaisesRegex(SyntaxError, 'fake'):
compile(b'# -*- coding: fake -*-\n', 'dummy', 'exec')
with self.assertRaisesRegex(SyntaxError, 'iso-8859-15'):
compile(b'\xef\xbb\xbf# -*- coding: iso-8859-15 -*-\n',
'dummy', 'exec')
with self.assertRaisesRegex(SyntaxError, 'BOM'):
compile(b'\xef\xbb\xbf# -*- coding: iso-8859-15 -*-\n',
'dummy', 'exec')
with self.assertRaisesRegex(SyntaxError, 'fake'):
compile(b'\xef\xbb\xbf# -*- coding: fake -*-\n', 'dummy', 'exec')
with self.assertRaisesRegex(SyntaxError, 'BOM'):
compile(b'\xef\xbb\xbf# -*- coding: fake -*-\n', 'dummy', 'exec')
def test_bad_coding(self):
module_name = 'bad_coding'
self.verify_bad_module(module_name)
def test_bad_coding2(self):
module_name = 'bad_coding2'
self.verify_bad_module(module_name)
def verify_bad_module(self, module_name):
self.assertRaises(SyntaxError, __import__, 'test.' + module_name)
path = os.path.dirname(__file__)
filename = os.path.join(path, module_name + '.py')
with open(filename, "rb") as fp:
bytes = fp.read()
self.assertRaises(SyntaxError, compile, bytes, filename, 'exec')
def test_exec_valid_coding(self):
d = {}
exec(b'# coding: cp949\na = "\xaa\xa7"\n', d)
self.assertEqual(d['a'], '\u3047')
def test_file_parse(self):
# issue1134: all encodings outside latin-1 and utf-8 fail on
# multiline strings and long lines (>512 columns)
unload(TESTFN)
filename = TESTFN + ".py"
f = open(filename, "w", encoding="cp1252")
sys.path.insert(0, os.curdir)
try:
with f:
f.write("# -*- coding: cp1252 -*-\n")
f.write("'''A short string\n")
f.write("'''\n")
f.write("'A very long string %s'\n" % ("X" * 1000))
importlib.invalidate_caches()
__import__(TESTFN)
finally:
del sys.path[0]
unlink(filename)
unlink(filename + "c")
unlink(filename + "o")
unload(TESTFN)
rmtree('__pycache__')
def test_error_from_string(self):
# See http://bugs.python.org/issue6289
input = "# coding: ascii\n\N{SNOWMAN}".encode('utf-8')
with self.assertRaises(SyntaxError) as c:
compile(input, "<string>", "exec")
expected = "'ascii' codec can't decode byte 0xe2 in position 16: " \
"ordinal not in range(128)"
self.assertTrue(c.exception.args[0].startswith(expected),
msg=c.exception.args[0])
class AbstractSourceEncodingTest:
def test_default_coding(self):
src = (b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xe4'")
def test_first_coding_line(self):
src = (b'#coding:iso8859-15\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xc3\u20ac'")
def test_second_coding_line(self):
src = (b'#\n'
b'#coding:iso8859-15\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xc3\u20ac'")
def test_third_coding_line(self):
# Only first two lines are tested for a magic comment.
src = (b'#\n'
b'#\n'
b'#coding:iso8859-15\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xe4'")
def test_double_coding_line(self):
# If the first line matches the second line is ignored.
src = (b'#coding:iso8859-15\n'
b'#coding:latin1\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xc3\u20ac'")
def test_double_coding_same_line(self):
src = (b'#coding:iso8859-15 coding:latin1\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xc3\u20ac'")
def test_first_non_utf8_coding_line(self):
src = (b'#coding:iso-8859-15 \xa4\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xc3\u20ac'")
def test_second_non_utf8_coding_line(self):
src = (b'\n'
b'#coding:iso-8859-15 \xa4\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xc3\u20ac'")
def test_utf8_bom(self):
src = (b'\xef\xbb\xbfprint(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xe4'")
def test_utf8_bom_and_utf8_coding_line(self):
src = (b'\xef\xbb\xbf#coding:utf-8\n'
b'print(ascii("\xc3\xa4"))\n')
self.check_script_output(src, br"'\xe4'")
class BytesSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase):
def check_script_output(self, src, expected):
with captured_stdout() as stdout:
exec(src)
out = stdout.getvalue().encode('latin1')
self.assertEqual(out.rstrip(), expected)
class FileSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase):
def check_script_output(self, src, expected):
with tempfile.TemporaryDirectory() as tmpd:
fn = os.path.join(tmpd, 'test.py')
with open(fn, 'wb') as fp:
fp.write(src)
res = script_helper.assert_python_ok(fn)
self.assertEqual(res.out.rstrip(), expected)
if __name__ == "__main__":
unittest.main()
|
