cpython/Lib/_bootlocale.py
Victor Stinner 91106cd9ff
bpo-29240: PEP 540: Add a new UTF-8 Mode (#855)
* Add -X utf8 command line option, PYTHONUTF8 environment variable
  and a new sys.flags.utf8_mode flag.
* If the LC_CTYPE locale is "C" at startup: enable automatically the
  UTF-8 mode.
* Add _winapi.GetACP(). encodings._alias_mbcs() now calls
  _winapi.GetACP() to get the ANSI code page
* locale.getpreferredencoding() now returns 'UTF-8' in the UTF-8
  mode. As a side effect, open() now uses the UTF-8 encoding by
  default in this mode.
* Py_DecodeLocale() and Py_EncodeLocale() now use the UTF-8 encoding
  in the UTF-8 Mode.
* Update subprocess._args_from_interpreter_flags() to handle -X utf8
* Skip some tests relying on the current locale if the UTF-8 mode is
  enabled.
* Add test_utf8mode.py.
* _Py_DecodeUTF8_surrogateescape() gets a new optional parameter to
  return also the length (number of wide characters).
* pymain_get_global_config() and pymain_set_global_config() now
  always copy flag values, rather than only copying if the new value
  is greater than the old value.
2017-12-13 12:29:09 +01:00

47 lines
1.8 KiB
Python

"""A minimal subset of the locale module used at interpreter startup
(imported by the _io module), in order to reduce startup time.
Don't import directly from third-party code; use the `locale` module instead!
"""
import sys
import _locale
if sys.platform.startswith("win"):
def getpreferredencoding(do_setlocale=True):
if sys.flags.utf8_mode:
return 'UTF-8'
return _locale._getdefaultlocale()[1]
else:
try:
_locale.CODESET
except AttributeError:
if hasattr(sys, 'getandroidapilevel'):
# On Android langinfo.h and CODESET are missing, and UTF-8 is
# always used in mbstowcs() and wcstombs().
def getpreferredencoding(do_setlocale=True):
return 'UTF-8'
else:
def getpreferredencoding(do_setlocale=True):
if sys.flags.utf8_mode:
return 'UTF-8'
# This path for legacy systems needs the more complex
# getdefaultlocale() function, import the full locale module.
import locale
return locale.getpreferredencoding(do_setlocale)
else:
def getpreferredencoding(do_setlocale=True):
assert not do_setlocale
if sys.flags.utf8_mode:
return 'UTF-8'
result = _locale.nl_langinfo(_locale.CODESET)
if not result and sys.platform == 'darwin':
# nl_langinfo can return an empty string
# when the setting has an invalid value.
# Default to UTF-8 in that case because
# UTF-8 is the default charset on OSX and
# returning nothing will crash the
# interpreter.
result = 'UTF-8'
return result