mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-08 01:41:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

bpo-42236: Enhance _locale._get_locale_encoding() (GH-23083)

Browse source 
* Rename _Py_GetLocaleEncoding() to _Py_GetLocaleEncodingObject()
* Add _Py_GetLocaleEncoding() which returns a wchar_t* string to
  share code between _Py_GetLocaleEncodingObject()
  and config_get_locale_encoding().
* _Py_GetLocaleEncodingObject() now decodes nl_langinfo(CODESET)
  from the current locale encoding with surrogateescape,
  rather than using UTF-8.
This commit is contained in:
Victor Stinner 2020-11-01 20:59:35 +01:00 • committed by GitHub
parent 1f7dfb277e
commit 82458b6cdb
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 76 additions and 52 deletions
Download patch file Download diff file Expand all files Collapse all files

47
Python/initconfig.c
View file

@ -11,11 +11,7 @@
#include "osdefs.h" // DELIM
#include <locale.h> // setlocale()
#ifdef HAVE_LANGINFO_H
# include <langinfo.h> // nl_langinfo(CODESET)
#endif
#if defined(MS_WINDOWS) || defined(__CYGWIN__)
# include <windows.h> // GetACP()
# ifdef HAVE_IO_H
# include <io.h>
# endif
@ -1497,41 +1493,24 @@ config_get_stdio_errors(const PyPreConfig *preconfig)
}
// See also _Py_GetLocaleEncoding() and config_get_fs_encoding()
// See also config_get_fs_encoding()
static PyStatus
config_get_locale_encoding(PyConfig *config, const PyPreConfig *preconfig,
wchar_t **locale_encoding)
{
#ifdef _Py_FORCE_UTF8_LOCALE
return PyConfig_SetString(config, locale_encoding, L"utf-8");
#else
if (preconfig->utf8_mode) {
return PyConfig_SetString(config, locale_encoding, L"utf-8");
const char *errmsg;
wchar_t *encoding = _Py_GetLocaleEncoding(&errmsg);
if (encoding == NULL) {
if (errmsg != NULL) {
return _PyStatus_ERR(errmsg);
}
else {
return _PyStatus_NO_MEMORY();
}
}
#ifdef MS_WINDOWS
char encoding[20];
PyOS_snprintf(encoding, sizeof(encoding), "cp%u", GetACP());
return PyConfig_SetBytesString(config, locale_encoding, encoding);
#else
const char *encoding = nl_langinfo(CODESET);
if (!encoding || encoding[0] == '\0') {
#ifdef _Py_FORCE_UTF8_FS_ENCODING
// nl_langinfo() can return an empty string when the LC_CTYPE locale is
// not supported. Default to UTF-8 in that case, because UTF-8 is the
// default charset on macOS.
encoding = "UTF-8";
#else
return _PyStatus_ERR("failed to get the locale encoding: "
"nl_langinfo(CODESET) returns an empty string");
#endif
}
/* nl_langinfo(CODESET) is decoded by Py_DecodeLocale() */
return CONFIG_SET_BYTES_STR(config,
locale_encoding, encoding,
"nl_langinfo(CODESET)");
#endif // !MS_WINDOWS
#endif // !_Py_FORCE_UTF8_LOCALE
PyStatus status = PyConfig_SetString(config, locale_encoding, encoding);
PyMem_RawFree(encoding);
return status;
}