mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-12-22 08:29:12 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

GH-133711: Enable UTF-8 mode by default (PEP 686) (#133712)

Browse source 
Co-authored-by: Victor Stinner <vstinner@python.org>
This commit is contained in:
Adam Turner 2025-07-15 10:45:41 +01:00 • committed by GitHub
parent f320c951c3
commit c89a66feb1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 93 additions and 85 deletions
Download patch file Download diff file Expand all files Collapse all files

3
Lib/locale.py
View file

@ -651,7 +651,8 @@ else:
if sys.flags.warn_default_encoding:
import warnings
warnings.warn(
"UTF-8 Mode affects locale.getpreferredencoding(). Consider locale.getencoding() instead.",
"UTF-8 Mode affects locale.getpreferredencoding(). "
"Consider locale.getencoding() instead.",
EncodingWarning, 2)
if sys.flags.utf8_mode:
return 'utf-8'

3
Lib/subprocess.py
View file

@ -380,8 +380,7 @@ def _text_encoding():
if sys.flags.utf8_mode:
return "utf-8"
else:
return locale.getencoding()
return locale.getencoding()
def call(*popenargs, timeout=None, **kwargs):

7
Lib/test/test_cmd_line.py
View file

@ -300,6 +300,10 @@ class CmdLineTest(unittest.TestCase):
cmd = [sys.executable, '-X', 'utf8', '-c', code, arg]
return subprocess.run(cmd, stdout=subprocess.PIPE, text=True)
def run_no_utf8_mode(arg):
cmd = [sys.executable, '-X', 'utf8=0', '-c', code, arg]
return subprocess.run(cmd, stdout=subprocess.PIPE, text=True)
valid_utf8 = 'e:\xe9, euro:\u20ac, non-bmp:\U0010ffff'.encode('utf-8')
# invalid UTF-8 byte sequences with a valid UTF-8 sequence
# in the middle.
@ -312,7 +316,8 @@ class CmdLineTest(unittest.TestCase):
)
test_args = [valid_utf8, invalid_utf8]
for run_cmd in (run_default, run_c_locale, run_utf8_mode):
for run_cmd in (run_default, run_c_locale, run_utf8_mode,
run_no_utf8_mode):
with self.subTest(run_cmd=run_cmd):
for arg in test_args:
proc = run_cmd(arg)

10
Lib/test/test_embed.py
View file

@ -543,7 +543,7 @@ class InitConfigTests(EmbeddingTestsMixin, unittest.TestCase):
'configure_locale': True,
'coerce_c_locale': False,
'coerce_c_locale_warn': False,
'utf8_mode': False,
'utf8_mode': True,
}
if MS_WINDOWS:
PRE_CONFIG_COMPAT.update({
@ -560,7 +560,7 @@ class InitConfigTests(EmbeddingTestsMixin, unittest.TestCase):
configure_locale=False,
isolated=True,
use_environment=False,
utf8_mode=False,
utf8_mode=True,
dev_mode=False,
coerce_c_locale=False,
)
@ -805,12 +805,6 @@ class InitConfigTests(EmbeddingTestsMixin, unittest.TestCase):
'stdio_encoding', 'stdio_errors'):
expected[key] = self.IGNORE_CONFIG
if not expected_preconfig['configure_locale']:
# UTF-8 Mode depends on the locale. There is no easy way
# to guess if UTF-8 Mode will be enabled or not if the locale
# is not configured.
expected_preconfig['utf8_mode'] = self.IGNORE_CONFIG
if expected_preconfig['utf8_mode'] == 1:
if expected['filesystem_encoding'] is self.GET_DEFAULT_CONFIG:
expected['filesystem_encoding'] = 'utf-8'

6
Lib/test/test_utf8_mode.py
View file

@ -89,8 +89,8 @@ class UTF8ModeTests(unittest.TestCase):
# 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')
out = self.get_output('-E', '-c', code, PYTHONUTF8='0')
self.assertEqual(out, '1')
# invalid mode
out = self.get_output('-c', code, PYTHONUTF8='xxx', failure=True)
@ -116,7 +116,7 @@ class UTF8ModeTests(unittest.TestCase):
# 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',
PYTHONUTF8='xxx',
PYTHONLEGACYWINDOWSFSENCODING='1')
self.assertEqual(out, 'mbcs/replace')