bpo-29240: Fix locale encodings in UTF-8 Mode (#5170)
Modify locale.localeconv(), time.tzname, os.strerror() and other
functions to ignore the UTF-8 Mode: always use the current locale
encoding.
Changes:
* Add _Py_DecodeLocaleEx() and _Py_EncodeLocaleEx(). On decoding or
encoding error, they return the position of the error and an error
message which are used to raise Unicode errors in
PyUnicode_DecodeLocale() and PyUnicode_EncodeLocale().
* Replace _Py_DecodeCurrentLocale() with _Py_DecodeLocaleEx().
* PyUnicode_DecodeLocale() now uses _Py_DecodeLocaleEx() for all
cases, especially for the strict error handler.
* Add _Py_DecodeUTF8Ex(): return more information on decoding error
and supports the strict error handler.
* Rename _Py_EncodeUTF8_surrogateescape() to _Py_EncodeUTF8Ex().
* Replace _Py_EncodeCurrentLocale() with _Py_EncodeLocaleEx().
* Ignore the UTF-8 mode to encode/decode localeconv(), strerror()
and time zone name.
* Remove PyUnicode_DecodeLocale(), PyUnicode_DecodeLocaleAndSize()
and PyUnicode_EncodeLocale() now ignore the UTF-8 mode: always use
the "current" locale.
* Remove _PyUnicode_DecodeCurrentLocale(),
_PyUnicode_DecodeCurrentLocaleAndSize() and
_PyUnicode_EncodeCurrentLocale().
diff --git a/Modules/timemodule.c b/Modules/timemodule.c
index 4e7f9d9..b17ab5a 100644
--- a/Modules/timemodule.c
+++ b/Modules/timemodule.c
@@ -418,11 +418,11 @@
SET(8, p->tm_isdst);
#ifdef HAVE_STRUCT_TM_TM_ZONE
PyStructSequence_SET_ITEM(v, 9,
- _PyUnicode_DecodeCurrentLocale(p->tm_zone, "surrogateescape"));
+ PyUnicode_DecodeLocale(p->tm_zone, "surrogateescape"));
SET(10, p->tm_gmtoff);
#else
PyStructSequence_SET_ITEM(v, 9,
- _PyUnicode_DecodeCurrentLocale(zone, "surrogateescape"));
+ PyUnicode_DecodeLocale(zone, "surrogateescape"));
PyStructSequence_SET_ITEM(v, 10, _PyLong_FromTime_t(gmtoff));
#endif /* HAVE_STRUCT_TM_TM_ZONE */
#undef SET
@@ -809,8 +809,7 @@
#ifdef HAVE_WCSFTIME
ret = PyUnicode_FromWideChar(outbuf, buflen);
#else
- ret = _PyUnicode_DecodeCurrentLocaleAndSize(outbuf, buflen,
- "surrogateescape");
+ ret = PyUnicode_DecodeLocaleAndSize(outbuf, buflen, "surrogateescape");
#endif
PyMem_Free(outbuf);
break;
@@ -1541,8 +1540,8 @@
PyModule_AddIntConstant(m, "altzone", timezone-3600);
#endif
PyModule_AddIntConstant(m, "daylight", daylight);
- otz0 = _PyUnicode_DecodeCurrentLocale(tzname[0], "surrogateescape");
- otz1 = _PyUnicode_DecodeCurrentLocale(tzname[1], "surrogateescape");
+ otz0 = PyUnicode_DecodeLocale(tzname[0], "surrogateescape");
+ otz1 = PyUnicode_DecodeLocale(tzname[1], "surrogateescape");
PyModule_AddObject(m, "tzname", Py_BuildValue("(NN)", otz0, otz1));
#else /* !HAVE_TZNAME || __GLIBC__ || __CYGWIN__*/
{