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.
This commit is contained in:
Victor Stinner 2017-12-13 12:29:09 +01:00 committed by GitHub
parent c3e070f849
commit 91106cd9ff
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
27 changed files with 598 additions and 183 deletions

View file

@ -1814,6 +1814,7 @@ static PyStructSequence_Field flags_fields[] = {
{"hash_randomization", "-R"},
{"isolated", "-I"},
{"dev_mode", "-X dev"},
{"utf8_mode", "-X utf8"},
{0}
};
@ -1821,7 +1822,7 @@ static PyStructSequence_Desc flags_desc = {
"sys.flags", /* name */
flags__doc__, /* doc */
flags_fields, /* fields */
14
15
};
static PyObject*
@ -1853,8 +1854,9 @@ make_flags(void)
SetFlag(Py_QuietFlag);
SetFlag(Py_HashRandomizationFlag);
SetFlag(Py_IsolatedFlag);
#undef SetFlag
PyStructSequence_SET_ITEM(seq, pos++, PyBool_FromLong(core_config->dev_mode));
SetFlag(Py_UTF8Mode);
#undef SetFlag
if (PyErr_Occurred()) {
Py_DECREF(seq);