bpo-42208: Add _Py_GetLocaleEncoding() (GH-23050)

_io.TextIOWrapper no longer calls getpreferredencoding(False) of
_bootlocale to get the locale encoding, but calls
_Py_GetLocaleEncoding() instead.

Add config_get_fs_encoding() sub-function. Reorganize also
config_get_locale_encoding() code.

1 files changed, 42 insertions, 1 deletions

diff --git a/Python/fileutils.c b/Python/fileutils.c
index e125ba4..ba26904 100644
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@ -1,5 +1,6 @@
 #include "Python.h"
-#include "pycore_fileutils.h"
+#include "pycore_fileutils.h"     // fileutils definitions
+#include "pycore_runtime.h"       // _PyRuntime
 #include "osdefs.h"               // SEP
 #include <locale.h>
 
@@ -820,6 +821,46 @@ _Py_EncodeLocaleEx(const wchar_t *text, char **str,
 }
 
 
+// Get the current locale encoding: locale.getpreferredencoding(False).
+// See also config_get_locale_encoding()
+PyObject *
+_Py_GetLocaleEncoding(void)
+{
+#ifdef _Py_FORCE_UTF8_LOCALE
+    // On Android langinfo.h and CODESET are missing,
+    // and UTF-8 is always used in mbstowcs() and wcstombs().
+    return PyUnicode_FromString("UTF-8");
+#else
+    const PyPreConfig *preconfig = &_PyRuntime.preconfig;
+    if (preconfig->utf8_mode) {
+        return PyUnicode_FromString("UTF-8");
+    }
+
+#if defined(MS_WINDOWS)
+    return PyUnicode_FromFormat("cp%u", GetACP());
+#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
+        PyErr_SetString(PyExc_ValueError,
+                        "failed to get the locale encoding: "
+                        "nl_langinfo(CODESET) returns an empty string");
+        return NULL;
+#endif
+    }
+    // Decode from UTF-8
+    return PyUnicode_FromString(encoding);
+#endif  // !CODESET
+
+#endif
+}
+
+
 #ifdef MS_WINDOWS
 static __int64 secs_between_epochs = 11644473600; /* Seconds between 1.1.1601 and 1.1.1970 */