From b2457efc78b74a1d6d1b77d11a939e886b8a4e2c Mon Sep 17 00:00:00 2001
From: Victor Stinner <vstinner@redhat.com>
Date: Wed, 29 Aug 2018 13:25:36 +0200
Subject: bpo-34523: Add _PyCoreConfig.filesystem_encoding (GH-8963)

_PyCoreConfig_Read() is now responsible to choose the filesystem
encoding and error handler. Using Py_Main(), the encoding is now
chosen even before calling Py_Initialize().

_PyCoreConfig.filesystem_encoding is now the reference, instead of
Py_FileSystemDefaultEncoding, for the Python filesystem encoding.

Changes:

* Add filesystem_encoding and filesystem_errors to _PyCoreConfig
* _PyCoreConfig_Read() now reads the locale encoding for the file
  system encoding.
* PyUnicode_EncodeFSDefault() and PyUnicode_DecodeFSDefaultAndSize()
  now use the interpreter configuration rather than
  Py_FileSystemDefaultEncoding and Py_FileSystemDefaultEncodeErrors
  global configuration variables.
* Add _Py_SetFileSystemEncoding() and _Py_ClearFileSystemEncoding()
  private functions to only modify Py_FileSystemDefaultEncoding and
  Py_FileSystemDefaultEncodeErrors in coreconfig.c.
* _Py_CoerceLegacyLocale() now takes an int rather than
  _PyCoreConfig for the warning.
---
 Objects/unicodeobject.c | 42 ++++++++++++++++++------------------------
 1 file changed, 18 insertions(+), 24 deletions(-)

(limited to 'Objects')

diff --git a/Objects/unicodeobject.c b/Objects/unicodeobject.c
index 087cfca58d..60adcd9c88 100644
--- a/Objects/unicodeobject.c
+++ b/Objects/unicodeobject.c
@@ -3410,27 +3410,24 @@ PyUnicode_EncodeLocale(PyObject *unicode, const char *errors)
 PyObject *
 PyUnicode_EncodeFSDefault(PyObject *unicode)
 {
+    PyInterpreterState *interp = _PyInterpreterState_GET_UNSAFE();
+    const _PyCoreConfig *config = &interp->core_config;
 #if defined(__APPLE__)
-    return _PyUnicode_AsUTF8String(unicode, Py_FileSystemDefaultEncodeErrors);
+    return _PyUnicode_AsUTF8String(unicode, config->filesystem_errors);
 #else
-    PyInterpreterState *interp = _PyInterpreterState_GET_UNSAFE();
     /* Bootstrap check: if the filesystem codec is implemented in Python, we
        cannot use it to encode and decode filenames before it is loaded. Load
        the Python codec requires to encode at least its own filename. Use the C
-       version of the locale codec until the codec registry is initialized and
-       the Python codec is loaded.
-
-       Py_FileSystemDefaultEncoding is shared between all interpreters, we
-       cannot only rely on it: check also interp->fscodec_initialized for
-       subinterpreters. */
-    if (Py_FileSystemDefaultEncoding && interp->fscodec_initialized) {
+       implementation of the locale codec until the codec registry is
+       initialized and the Python codec is loaded. See initfsencoding(). */
+    if (interp->fscodec_initialized) {
         return PyUnicode_AsEncodedString(unicode,
-                                         Py_FileSystemDefaultEncoding,
-                                         Py_FileSystemDefaultEncodeErrors);
+                                         config->filesystem_encoding,
+                                         config->filesystem_errors);
     }
     else {
         return unicode_encode_locale(unicode,
-                                     Py_FileSystemDefaultEncodeErrors, 0);
+                                     config->filesystem_errors, 0);
     }
 #endif
 }
@@ -3636,27 +3633,24 @@ PyUnicode_DecodeFSDefault(const char *s) {
 PyObject*
 PyUnicode_DecodeFSDefaultAndSize(const char *s, Py_ssize_t size)
 {
+    PyInterpreterState *interp = _PyInterpreterState_GET_UNSAFE();
+    const _PyCoreConfig *config = &interp->core_config;
 #if defined(__APPLE__)
-    return PyUnicode_DecodeUTF8Stateful(s, size, Py_FileSystemDefaultEncodeErrors, NULL);
+    return PyUnicode_DecodeUTF8Stateful(s, size, config->filesystem_errors, NULL);
 #else
-    PyInterpreterState *interp = _PyInterpreterState_GET_UNSAFE();
     /* Bootstrap check: if the filesystem codec is implemented in Python, we
        cannot use it to encode and decode filenames before it is loaded. Load
        the Python codec requires to encode at least its own filename. Use the C
-       version of the locale codec until the codec registry is initialized and
-       the Python codec is loaded.
-
-       Py_FileSystemDefaultEncoding is shared between all interpreters, we
-       cannot only rely on it: check also interp->fscodec_initialized for
-       subinterpreters. */
-    if (Py_FileSystemDefaultEncoding && interp->fscodec_initialized) {
+       implementation of the locale codec until the codec registry is
+       initialized and the Python codec is loaded. See initfsencoding(). */
+    if (interp->fscodec_initialized) {
         return PyUnicode_Decode(s, size,
-                                Py_FileSystemDefaultEncoding,
-                                Py_FileSystemDefaultEncodeErrors);
+                                config->filesystem_encoding,
+                                config->filesystem_errors);
     }
     else {
         return unicode_decode_locale(s, size,
-                                     Py_FileSystemDefaultEncodeErrors, 0);
+                                     config->filesystem_errors, 0);
     }
 #endif
 }
-- 
cgit v1.2.1