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
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
|
"""
Test the implementation of the PEP 540: the UTF-8 Mode.
"""
import locale
import subprocess
import sys
import textwrap
import unittest
from test import support
from test.support.script_helper import assert_python_ok, assert_python_failure
from test.support import os_helper
MS_WINDOWS = (sys.platform == 'win32')
POSIX_LOCALES = ('C', 'POSIX')
VXWORKS = (sys.platform == "vxworks")
class UTF8ModeTests(unittest.TestCase):
DEFAULT_ENV = {
'PYTHONUTF8': '',
'PYTHONLEGACYWINDOWSFSENCODING': '',
'PYTHONCOERCECLOCALE': '0',
}
def posix_locale(self):
loc = locale.setlocale(locale.LC_CTYPE, None)
return (loc in POSIX_LOCALES)
def get_output(self, *args, failure=False, **kw):
kw = dict(self.DEFAULT_ENV, **kw)
if failure:
out = assert_python_failure(*args, **kw)
out = out[2]
else:
out = assert_python_ok(*args, **kw)
out = out[1]
return out.decode().rstrip("\n\r")
@unittest.skipIf(MS_WINDOWS, 'Windows has no POSIX locale')
def test_posix_locale(self):
code = 'import sys; print(sys.flags.utf8_mode)'
for loc in POSIX_LOCALES:
with self.subTest(LC_ALL=loc):
out = self.get_output('-c', code, LC_ALL=loc)
self.assertEqual(out, '1')
def test_xoption(self):
code = 'import sys; print(sys.flags.utf8_mode)'
out = self.get_output('-X', 'utf8', '-c', code)
self.assertEqual(out, '1')
# undocumented but accepted syntax: -X utf8=1
out = self.get_output('-X', 'utf8=1', '-c', code)
self.assertEqual(out, '1')
out = self.get_output('-X', 'utf8=0', '-c', code)
self.assertEqual(out, '0')
if MS_WINDOWS:
# PYTHONLEGACYWINDOWSFSENCODING disables the UTF-8 Mode
# and has the priority over -X utf8
out = self.get_output('-X', 'utf8', '-c', code,
PYTHONLEGACYWINDOWSFSENCODING='1')
self.assertEqual(out, '0')
def test_env_var(self):
code = 'import sys; print(sys.flags.utf8_mode)'
out = self.get_output('-c', code, PYTHONUTF8='1')
self.assertEqual(out, '1')
out = self.get_output('-c', code, PYTHONUTF8='0')
self.assertEqual(out, '0')
# -X utf8 has the priority over PYTHONUTF8
out = self.get_output('-X', 'utf8=0', '-c', code, PYTHONUTF8='1')
self.assertEqual(out, '0')
if MS_WINDOWS:
# PYTHONLEGACYWINDOWSFSENCODING disables the UTF-8 mode
# and has the priority over PYTHONUTF8
out = self.get_output('-X', 'utf8', '-c', code, PYTHONUTF8='1',
PYTHONLEGACYWINDOWSFSENCODING='1')
self.assertEqual(out, '0')
# Cannot test with the POSIX locale, since the POSIX locale enables
# the UTF-8 mode
if not self.posix_locale():
# PYTHONUTF8 should be ignored if -E is used
out = self.get_output('-E', '-c', code, PYTHONUTF8='1')
self.assertEqual(out, '0')
# invalid mode
out = self.get_output('-c', code, PYTHONUTF8='xxx', failure=True)
self.assertIn('invalid PYTHONUTF8 environment variable value',
out.rstrip())
def test_filesystemencoding(self):
code = textwrap.dedent('''
import sys
print("{}/{}".format(sys.getfilesystemencoding(),
sys.getfilesystemencodeerrors()))
''')
if MS_WINDOWS:
expected = 'utf-8/surrogatepass'
else:
expected = 'utf-8/surrogateescape'
out = self.get_output('-X', 'utf8', '-c', code)
self.assertEqual(out, expected)
if MS_WINDOWS:
# PYTHONLEGACYWINDOWSFSENCODING disables the UTF-8 mode
# and has the priority over -X utf8 and PYTHONUTF8
out = self.get_output('-X', 'utf8', '-c', code,
PYTHONUTF8='strict',
PYTHONLEGACYWINDOWSFSENCODING='1')
self.assertEqual(out, 'mbcs/replace')
def test_stdio(self):
code = textwrap.dedent('''
import sys
print(f"stdin: {sys.stdin.encoding}/{sys.stdin.errors}")
print(f"stdout: {sys.stdout.encoding}/{sys.stdout.errors}")
print(f"stderr: {sys.stderr.encoding}/{sys.stderr.errors}")
''')
out = self.get_output('-X', 'utf8', '-c', code,
PYTHONIOENCODING='')
self.assertEqual(out.splitlines(),
['stdin: utf-8/surrogateescape',
'stdout: utf-8/surrogateescape',
'stderr: utf-8/backslashreplace'])
# PYTHONIOENCODING has the priority over PYTHONUTF8
out = self.get_output('-X', 'utf8', '-c', code,
PYTHONIOENCODING="latin1")
self.assertEqual(out.splitlines(),
['stdin: iso8859-1/strict',
'stdout: iso8859-1/strict',
'stderr: iso8859-1/backslashreplace'])
out = self.get_output('-X', 'utf8', '-c', code,
PYTHONIOENCODING=":namereplace")
self.assertEqual(out.splitlines(),
['stdin: utf-8/namereplace',
'stdout: utf-8/namereplace',
'stderr: utf-8/backslashreplace'])
def test_io(self):
code = textwrap.dedent('''
import sys
filename = sys.argv[1]
with open(filename) as fp:
print(f"{fp.encoding}/{fp.errors}")
''')
filename = __file__
out = self.get_output('-c', code, filename, PYTHONUTF8='1')
self.assertEqual(out, 'UTF-8/strict')
def _check_io_encoding(self, module, encoding=None, errors=None):
filename = __file__
# Encoding explicitly set
args = []
if encoding:
args.append(f'encoding={encoding!r}')
if errors:
args.append(f'errors={errors!r}')
code = textwrap.dedent('''
import sys
from %s import open
filename = sys.argv[1]
with open(filename, %s) as fp:
print(f"{fp.encoding}/{fp.errors}")
''') % (module, ', '.join(args))
out = self.get_output('-c', code, filename,
PYTHONUTF8='1')
if not encoding:
encoding = 'UTF-8'
if not errors:
errors = 'strict'
self.assertEqual(out, f'{encoding}/{errors}')
def check_io_encoding(self, module):
self._check_io_encoding(module, encoding="latin1")
self._check_io_encoding(module, errors="namereplace")
self._check_io_encoding(module,
encoding="latin1", errors="namereplace")
def test_io_encoding(self):
self.check_io_encoding('io')
def test_pyio_encoding(self):
self.check_io_encoding('_pyio')
def test_locale_getpreferredencoding(self):
code = 'import locale; print(locale.getpreferredencoding(False), locale.getpreferredencoding(True))'
out = self.get_output('-X', 'utf8', '-c', code)
self.assertEqual(out, 'UTF-8 UTF-8')
for loc in POSIX_LOCALES:
with self.subTest(LC_ALL=loc):
out = self.get_output('-X', 'utf8', '-c', code, LC_ALL=loc)
self.assertEqual(out, 'UTF-8 UTF-8')
@unittest.skipIf(MS_WINDOWS, 'test specific to Unix')
def test_cmd_line(self):
arg = 'h\xe9\u20ac'.encode('utf-8')
arg_utf8 = arg.decode('utf-8')
arg_ascii = arg.decode('ascii', 'surrogateescape')
code = 'import locale, sys; print("%s:%s" % (locale.getpreferredencoding(), ascii(sys.argv[1:])))'
def check(utf8_opt, expected, **kw):
out = self.get_output('-X', utf8_opt, '-c', code, arg, **kw)
args = out.partition(':')[2].rstrip()
self.assertEqual(args, ascii(expected), out)
check('utf8', [arg_utf8])
for loc in POSIX_LOCALES:
with self.subTest(LC_ALL=loc):
check('utf8', [arg_utf8], LC_ALL=loc)
if sys.platform == 'darwin' or support.is_android or VXWORKS:
c_arg = arg_utf8
elif sys.platform.startswith("aix"):
c_arg = arg.decode('iso-8859-1')
else:
c_arg = arg_ascii
for loc in POSIX_LOCALES:
with self.subTest(LC_ALL=loc):
check('utf8=0', [c_arg], LC_ALL=loc)
def test_optim_level(self):
# CPython: check that Py_Main() doesn't increment Py_OptimizeFlag
# twice when -X utf8 requires to parse the configuration twice (when
# the encoding changes after reading the configuration, the
# configuration is read again with the new encoding).
code = 'import sys; print(sys.flags.optimize)'
out = self.get_output('-X', 'utf8', '-O', '-c', code)
self.assertEqual(out, '1')
out = self.get_output('-X', 'utf8', '-OO', '-c', code)
self.assertEqual(out, '2')
code = 'import sys; print(sys.flags.ignore_environment)'
out = self.get_output('-X', 'utf8', '-E', '-c', code)
self.assertEqual(out, '1')
@unittest.skipIf(MS_WINDOWS,
"os.device_encoding() doesn't implement "
"the UTF-8 Mode on Windows")
def test_device_encoding(self):
# Use stdout as TTY
if not sys.stdout.isatty():
self.skipTest("sys.stdout is not a TTY")
filename = 'out.txt'
self.addCleanup(os_helper.unlink, filename)
code = (f'import os, sys; fd = sys.stdout.fileno(); '
f'out = open({filename!r}, "w", encoding="utf-8"); '
f'print(os.isatty(fd), os.device_encoding(fd), file=out); '
f'out.close()')
cmd = [sys.executable, '-X', 'utf8', '-c', code]
# The stdout TTY is inherited to the child process
proc = subprocess.run(cmd, text=True)
self.assertEqual(proc.returncode, 0, proc)
# In UTF-8 Mode, device_encoding(fd) returns "UTF-8" if fd is a TTY
with open(filename, encoding="utf8") as fp:
out = fp.read().rstrip()
self.assertEqual(out, 'True UTF-8')
if __name__ == "__main__":
unittest.main()
|
