bpo-36443: Disable C locale coercion and UTF-8 Mode by default (GH-12589)

bpo-36443, bpo-36202: Since Python 3.7.0, calling Py_DecodeLocale()
before Py_Initialize() produces mojibake if the LC_CTYPE locale is
coerced and/or if the UTF-8 Mode is enabled by the user
configuration. This change fix the issue by disabling LC_CTYPE
coercion and UTF-8 Mode by default. They must now be enabled
explicitly (opt-in) using the new _Py_PreInitialize() API with
_PyPreConfig.

When embedding Python, set coerce_c_locale and utf8_mode attributes
of _PyPreConfig to -1 to enable automatically these parameters
depending on the LC_CTYPE locale, environment variables and command
line arguments

Alternative: Setting Py_UTF8Mode to 1 always explicitly enables the
UTF-8 Mode.

Changes:

* _PyPreConfig_INIT now sets coerce_c_locale and utf8_mode to 0 by
  default.
* _Py_InitializeFromArgs() and _Py_InitializeFromWideArgs() can now
  be called with config=NULL.
This commit is contained in:
Victor Stinner 2019-03-27 18:28:46 +01:00 committed by GitHub
parent 4a9a505d6f
commit d929f1838a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
7 changed files with 58 additions and 46 deletions

View file

@ -441,8 +441,6 @@ static int test_init_from_config(void)
putenv("PYTHONMALLOCSTATS=0");
config.malloc_stats = 1;
/* FIXME: test coerce_c_locale and coerce_c_locale_warn */
putenv("PYTHONPYCACHEPREFIX=env_pycache_prefix");
config.pycache_prefix = L"conf_pycache_prefix";
@ -617,17 +615,6 @@ static int test_init_isolated(void)
{
_PyInitError err;
_PyPreConfig preconfig = _PyPreConfig_INIT;
/* Set coerce_c_locale and utf8_mode to not depend on the locale */
preconfig.coerce_c_locale = 0;
preconfig.utf8_mode = 0;
err = _Py_PreInitialize(&preconfig);
if (_Py_INIT_FAILED(err)) {
_Py_ExitInitError(err);
}
/* Test _PyCoreConfig.isolated=1 */
_PyCoreConfig config = _PyCoreConfig_INIT;
@ -654,10 +641,6 @@ static int test_preinit_isolated1(void)
_PyInitError err;
_PyPreConfig preconfig = _PyPreConfig_INIT;
/* Set coerce_c_locale and utf8_mode to not depend on the locale */
preconfig.coerce_c_locale = 0;
preconfig.utf8_mode = 0;
preconfig.isolated = 1;
err = _Py_PreInitialize(&preconfig);
@ -685,10 +668,6 @@ static int test_preinit_isolated2(void)
_PyInitError err;
_PyPreConfig preconfig = _PyPreConfig_INIT;
/* Set coerce_c_locale and utf8_mode to not depend on the locale */
preconfig.coerce_c_locale = 0;
preconfig.utf8_mode = 0;
preconfig.isolated = 0;
err = _Py_PreInitialize(&preconfig);