From cd4bccc51bc8eeca5ff4bd8329770b76c09ce03e Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Sun, 20 Mar 2022 16:58:59 +0900
Subject: [PATCH 01/13] bpo-47000: Add locale.get_encoding()

---
 Lib/locale.py                    | 20 ++++++++++----------
 Modules/_localemodule.c          |  8 ++++----
 Modules/clinic/_localemodule.c.h | 16 ++++++++--------
 Python/fileutils.c               |  7 +++----
 Python/initconfig.c              |  8 +++++++-
 5 files changed, 32 insertions(+), 27 deletions(-)

diff --git a/Lib/locale.py b/Lib/locale.py
index a710f27a807b09..d729c3f394bdcb 100644
--- a/Lib/locale.py
+++ b/Lib/locale.py
@@ -28,7 +28,7 @@
            "setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm",
            "str", "atof", "atoi", "format", "format_string", "currency",
            "normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY",
-           "LC_NUMERIC", "LC_ALL", "CHAR_MAX"]
+           "LC_NUMERIC", "LC_ALL", "CHAR_MAX", "get_encoding"]
 
 def _strcoll(a,b):
     """ strcoll(string,string) -> int.
@@ -637,19 +637,17 @@ def resetlocale(category=LC_ALL):
 
 
 try:
-    from _locale import _get_locale_encoding
+    from _locale import get_encoding
 except ImportError:
-    def _get_locale_encoding():
+    def get_encoding():
         if hasattr(sys, 'getandroidapilevel'):
             # On Android langinfo.h and CODESET are missing, and UTF-8 is
             # always used in mbstowcs() and wcstombs().
             return 'UTF-8'
-        if sys.flags.utf8_mode:
-            return 'UTF-8'
         encoding = getdefaultlocale()[1]
         if encoding is None:
-            # LANG not set, default conservatively to ASCII
-            encoding = 'ascii'
+            # LANG not set, default to UTF-8
+            encoding = 'UTF-8'
         return encoding
 
 try:
@@ -657,7 +655,9 @@ def _get_locale_encoding():
 except NameError:
     def getpreferredencoding(do_setlocale=True):
         """Return the charset that the user is likely using."""
-        return _get_locale_encoding()
+        if sys.flags.utf8_mode:
+            return 'UTF-8'
+        return get_encoding()
 else:
     # On Unix, if CODESET is available, use that.
     def getpreferredencoding(do_setlocale=True):
@@ -667,7 +667,7 @@ def getpreferredencoding(do_setlocale=True):
             return 'UTF-8'
 
         if not do_setlocale:
-            return _get_locale_encoding()
+            return get_encoding()
 
         old_loc = setlocale(LC_CTYPE)
         try:
@@ -675,7 +675,7 @@ def getpreferredencoding(do_setlocale=True):
                 setlocale(LC_CTYPE, "")
             except Error:
                 pass
-            return _get_locale_encoding()
+            return get_encoding()
         finally:
             setlocale(LC_CTYPE, old_loc)
 
diff --git a/Modules/_localemodule.c b/Modules/_localemodule.c
index 564f5598edcc66..ff6623f9e3a48a 100644
--- a/Modules/_localemodule.c
+++ b/Modules/_localemodule.c
@@ -773,14 +773,14 @@ _locale_bind_textdomain_codeset_impl(PyObject *module, const char *domain,
 
 
 /*[clinic input]
-_locale._get_locale_encoding
+_locale.get_encoding
 
 Get the current locale encoding.
 [clinic start generated code]*/
 
 static PyObject *
-_locale__get_locale_encoding_impl(PyObject *module)
-/*[clinic end generated code: output=e8e2f6f6f184591a input=513d9961d2f45c76]*/
+_locale_get_encoding_impl(PyObject *module)
+/*[clinic end generated code: output=7811932060493a1b input=163753befd041d95]*/
 {
     return _Py_GetLocaleEncodingObject();
 }
@@ -811,7 +811,7 @@ static struct PyMethodDef PyLocale_Methods[] = {
     _LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF
 #endif
 #endif
-    _LOCALE__GET_LOCALE_ENCODING_METHODDEF
+    _LOCALE_GET_ENCODING_METHODDEF
   {NULL, NULL}
 };
 
diff --git a/Modules/clinic/_localemodule.c.h b/Modules/clinic/_localemodule.c.h
index 703d034c32e801..c556bb58cb0cb3 100644
--- a/Modules/clinic/_localemodule.c.h
+++ b/Modules/clinic/_localemodule.c.h
@@ -545,22 +545,22 @@ _locale_bind_textdomain_codeset(PyObject *module, PyObject *const *args, Py_ssiz
 
 #endif /* defined(HAVE_LIBINTL_H) && defined(HAVE_BIND_TEXTDOMAIN_CODESET) */
 
-PyDoc_STRVAR(_locale__get_locale_encoding__doc__,
-"_get_locale_encoding($module, /)\n"
+PyDoc_STRVAR(_locale_get_encoding__doc__,
+"get_encoding($module, /)\n"
 "--\n"
 "\n"
 "Get the current locale encoding.");
 
-#define _LOCALE__GET_LOCALE_ENCODING_METHODDEF    \
-    {"_get_locale_encoding", (PyCFunction)_locale__get_locale_encoding, METH_NOARGS, _locale__get_locale_encoding__doc__},
+#define _LOCALE_GET_ENCODING_METHODDEF    \
+    {"get_encoding", (PyCFunction)_locale_get_encoding, METH_NOARGS, _locale_get_encoding__doc__},
 
 static PyObject *
-_locale__get_locale_encoding_impl(PyObject *module);
+_locale_get_encoding_impl(PyObject *module);
 
 static PyObject *
-_locale__get_locale_encoding(PyObject *module, PyObject *Py_UNUSED(ignored))
+_locale_get_encoding(PyObject *module, PyObject *Py_UNUSED(ignored))
 {
-    return _locale__get_locale_encoding_impl(module);
+    return _locale_get_encoding_impl(module);
 }
 
 #ifndef _LOCALE_STRCOLL_METHODDEF
@@ -602,4 +602,4 @@ _locale__get_locale_encoding(PyObject *module, PyObject *Py_UNUSED(ignored))
 #ifndef _LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF
     #define _LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF
 #endif /* !defined(_LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF) */
-/*[clinic end generated code: output=cd703c8a3a75fcf4 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=08f5d9744143d9f2 input=a9049054013a1b77]*/
diff --git a/Python/fileutils.c b/Python/fileutils.c
index 111d7fa84b1882..ecf22ba1c6798b 100644
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@ -93,6 +93,9 @@ _Py_device_encoding(int fd)
 
     return PyUnicode_FromFormat("cp%u", (unsigned int)cp);
 #else
+    if (_PyRuntime.preconfig.utf8_mode) {
+        return PyUnicode_FromString("utf-8"); //TODO: Use _Py_STR
+    }
     return _Py_GetLocaleEncodingObject();
 #endif
 }
@@ -890,10 +893,6 @@ _Py_GetLocaleEncoding(void)
     // and UTF-8 is always used in mbstowcs() and wcstombs().
     return _PyMem_RawWcsdup(L"UTF-8");
 #else
-    const PyPreConfig *preconfig = &_PyRuntime.preconfig;
-    if (preconfig->utf8_mode) {
-        return _PyMem_RawWcsdup(L"UTF-8");
-    }
 
 #ifdef MS_WINDOWS
     wchar_t encoding[23];
diff --git a/Python/initconfig.c b/Python/initconfig.c
index 47ebc64c8470a9..d9a9e429b81f51 100644
--- a/Python/initconfig.c
+++ b/Python/initconfig.c
@@ -1779,7 +1779,13 @@ static PyStatus
 config_get_locale_encoding(PyConfig *config, const PyPreConfig *preconfig,
                            wchar_t **locale_encoding)
 {
-    wchar_t *encoding = _Py_GetLocaleEncoding();
+    wchar_t *encoding;
+    if (preconfig->utf8_mode) {
+        encoding = _PyMem_RawWcsdup(L"UTF-8");
+    }
+    else {
+        encoding = _Py_GetLocaleEncoding();
+    }
     if (encoding == NULL) {
         return _PyStatus_NO_MEMORY();
     }

From aaa89568fd9ea76c5fa5216f9dd1faeca7e5555f Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Thu, 31 Mar 2022 15:17:57 +0900
Subject: [PATCH 02/13] get_encoding() -> getencoding()

---
 Lib/locale.py                    |  6 +++---
 Modules/_localemodule.c          |  8 ++++----
 Modules/clinic/_localemodule.c.h | 16 ++++++++--------
 3 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/Lib/locale.py b/Lib/locale.py
index d729c3f394bdcb..ceffe8370ac1e2 100644
--- a/Lib/locale.py
+++ b/Lib/locale.py
@@ -28,7 +28,7 @@
            "setlocale", "resetlocale", "localeconv", "strcoll", "strxfrm",
            "str", "atof", "atoi", "format", "format_string", "currency",
            "normalize", "LC_CTYPE", "LC_COLLATE", "LC_TIME", "LC_MONETARY",
-           "LC_NUMERIC", "LC_ALL", "CHAR_MAX", "get_encoding"]
+           "LC_NUMERIC", "LC_ALL", "CHAR_MAX", "getencoding"]
 
 def _strcoll(a,b):
     """ strcoll(string,string) -> int.
@@ -637,9 +637,9 @@ def resetlocale(category=LC_ALL):
 
 
 try:
-    from _locale import get_encoding
+    from _locale import getencoding
 except ImportError:
-    def get_encoding():
+    def getencoding():
         if hasattr(sys, 'getandroidapilevel'):
             # On Android langinfo.h and CODESET are missing, and UTF-8 is
             # always used in mbstowcs() and wcstombs().
diff --git a/Modules/_localemodule.c b/Modules/_localemodule.c
index ff6623f9e3a48a..23c38e14d997d1 100644
--- a/Modules/_localemodule.c
+++ b/Modules/_localemodule.c
@@ -773,14 +773,14 @@ _locale_bind_textdomain_codeset_impl(PyObject *module, const char *domain,
 
 
 /*[clinic input]
-_locale.get_encoding
+_locale.getencoding
 
 Get the current locale encoding.
 [clinic start generated code]*/
 
 static PyObject *
-_locale_get_encoding_impl(PyObject *module)
-/*[clinic end generated code: output=7811932060493a1b input=163753befd041d95]*/
+_locale_getencoding_impl(PyObject *module)
+/*[clinic end generated code: output=86b326b971872e46 input=6503d11e5958b360]*/
 {
     return _Py_GetLocaleEncodingObject();
 }
@@ -811,7 +811,7 @@ static struct PyMethodDef PyLocale_Methods[] = {
     _LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF
 #endif
 #endif
-    _LOCALE_GET_ENCODING_METHODDEF
+    _LOCALE_GETENCODING_METHODDEF
   {NULL, NULL}
 };
 
diff --git a/Modules/clinic/_localemodule.c.h b/Modules/clinic/_localemodule.c.h
index c556bb58cb0cb3..2958127e430de5 100644
--- a/Modules/clinic/_localemodule.c.h
+++ b/Modules/clinic/_localemodule.c.h
@@ -545,22 +545,22 @@ _locale_bind_textdomain_codeset(PyObject *module, PyObject *const *args, Py_ssiz
 
 #endif /* defined(HAVE_LIBINTL_H) && defined(HAVE_BIND_TEXTDOMAIN_CODESET) */
 
-PyDoc_STRVAR(_locale_get_encoding__doc__,
-"get_encoding($module, /)\n"
+PyDoc_STRVAR(_locale_getencoding__doc__,
+"getencoding($module, /)\n"
 "--\n"
 "\n"
 "Get the current locale encoding.");
 
-#define _LOCALE_GET_ENCODING_METHODDEF    \
-    {"get_encoding", (PyCFunction)_locale_get_encoding, METH_NOARGS, _locale_get_encoding__doc__},
+#define _LOCALE_GETENCODING_METHODDEF    \
+    {"getencoding", (PyCFunction)_locale_getencoding, METH_NOARGS, _locale_getencoding__doc__},
 
 static PyObject *
-_locale_get_encoding_impl(PyObject *module);
+_locale_getencoding_impl(PyObject *module);
 
 static PyObject *
-_locale_get_encoding(PyObject *module, PyObject *Py_UNUSED(ignored))
+_locale_getencoding(PyObject *module, PyObject *Py_UNUSED(ignored))
 {
-    return _locale_get_encoding_impl(module);
+    return _locale_getencoding_impl(module);
 }
 
 #ifndef _LOCALE_STRCOLL_METHODDEF
@@ -602,4 +602,4 @@ _locale_get_encoding(PyObject *module, PyObject *Py_UNUSED(ignored))
 #ifndef _LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF
     #define _LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF
 #endif /* !defined(_LOCALE_BIND_TEXTDOMAIN_CODESET_METHODDEF) */
-/*[clinic end generated code: output=08f5d9744143d9f2 input=a9049054013a1b77]*/
+/*[clinic end generated code: output=ea71e9b94bdaa47d input=a9049054013a1b77]*/

From 104206a17ca897533da83e85634970a79a82f51b Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Thu, 31 Mar 2022 15:22:09 +0900
Subject: [PATCH 03/13] fix TextIOWrapper.__init__

---
 Modules/_io/textio.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/Modules/_io/textio.c b/Modules/_io/textio.c
index d9d1c881418742..f0d74b5fe758a2 100644
--- a/Modules/_io/textio.c
+++ b/Modules/_io/textio.c
@@ -1145,7 +1145,14 @@ _io_TextIOWrapper___init___impl(textio *self, PyObject *buffer,
         }
     }
     if (encoding == NULL && self->encoding == NULL) {
-        self->encoding = _Py_GetLocaleEncodingObject();
+        const PyPreConfig *preconfig = &_PyRuntime.preconfig;
+        if (preconfig->utf8_mode) {
+            // TODO: Use _Py_STR
+            self->encoding = PyUnicode_FromString("utf-8");
+        }
+        else {
+            self->encoding = _Py_GetLocaleEncodingObject();
+        }
         if (self->encoding == NULL) {
             goto error;
         }

From 8b50eb10de0805d0eda6a3e9aeb8865d32c6f7b7 Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Thu, 31 Mar 2022 15:31:43 +0900
Subject: [PATCH 04/13] get_encoding -> getencoding

---
 Lib/locale.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Lib/locale.py b/Lib/locale.py
index ceffe8370ac1e2..bc11164015245e 100644
--- a/Lib/locale.py
+++ b/Lib/locale.py
@@ -657,7 +657,7 @@ def getpreferredencoding(do_setlocale=True):
         """Return the charset that the user is likely using."""
         if sys.flags.utf8_mode:
             return 'UTF-8'
-        return get_encoding()
+        return getencoding()
 else:
     # On Unix, if CODESET is available, use that.
     def getpreferredencoding(do_setlocale=True):
@@ -667,7 +667,7 @@ def getpreferredencoding(do_setlocale=True):
             return 'UTF-8'
 
         if not do_setlocale:
-            return get_encoding()
+            return getencoding()
 
         old_loc = setlocale(LC_CTYPE)
         try:
@@ -675,7 +675,7 @@ def getpreferredencoding(do_setlocale=True):
                 setlocale(LC_CTYPE, "")
             except Error:
                 pass
-            return get_encoding()
+            return getencoding()
         finally:
             setlocale(LC_CTYPE, old_loc)
 

From a0204c25f4cc6bd91beba56cba0395f6d4906ac6 Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Mon, 4 Apr 2022 12:23:32 +0900
Subject: [PATCH 05/13] Use _Py_STR for "utf-8"

---
 Modules/_io/textio.c | 8 ++++----
 Python/fileutils.c   | 5 ++++-
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/Modules/_io/textio.c b/Modules/_io/textio.c
index f0d74b5fe758a2..ea0f9b3d45a374 100644
--- a/Modules/_io/textio.c
+++ b/Modules/_io/textio.c
@@ -1145,10 +1145,10 @@ _io_TextIOWrapper___init___impl(textio *self, PyObject *buffer,
         }
     }
     if (encoding == NULL && self->encoding == NULL) {
-        const PyPreConfig *preconfig = &_PyRuntime.preconfig;
-        if (preconfig->utf8_mode) {
-            // TODO: Use _Py_STR
-            self->encoding = PyUnicode_FromString("utf-8");
+        if (_PyRuntime.preconfig.utf8_mode) {
+            _Py_DECLARE_STR(utf_8, "utf-8");
+            self->encoding = &_Py_STR(utf_8);
+            Py_INCREF(self->encoding);
         }
         else {
             self->encoding = _Py_GetLocaleEncodingObject();
diff --git a/Python/fileutils.c b/Python/fileutils.c
index ecf22ba1c6798b..f880375b0d3aec 100644
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@ -94,7 +94,10 @@ _Py_device_encoding(int fd)
     return PyUnicode_FromFormat("cp%u", (unsigned int)cp);
 #else
     if (_PyRuntime.preconfig.utf8_mode) {
-        return PyUnicode_FromString("utf-8"); //TODO: Use _Py_STR
+        _Py_DECLARE_STR(utf_8, "utf-8");
+        PyObject *encoding = &_Py_STR(utf_8);
+        Py_INCREF(encoding);
+        return encoding;
     }
     return _Py_GetLocaleEncodingObject();
 #endif

From 08413f1208c5cdfcfd10e6ddc2d4c5bf9dad914d Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Wed, 6 Apr 2022 11:54:23 +0900
Subject: [PATCH 06/13] Update the doc.

---
 Doc/library/locale.rst | 15 ++++++++++++++-
 Doc/whatsnew/3.11.rst  |  6 ++++++
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/Doc/library/locale.rst b/Doc/library/locale.rst
index 01e14a151d299c..5783c5c78be5f2 100644
--- a/Doc/library/locale.rst
+++ b/Doc/library/locale.rst
@@ -334,10 +334,23 @@ The :mod:`locale` module defines the following exception and functions:
    locale. See also the :term:`filesystem encoding and error handler`.
 
    .. versionchanged:: 3.7
-      The function now always returns ``UTF-8`` on Android or if the
+      The function now always returns ``"UTF-8"`` on Android or if the
       :ref:`Python UTF-8 Mode <utf8-mode>` is enabled.
 
 
+.. function:: getencoding()
+
+   Returns the :term:`locale encoding`.
+
+   On Android, it always returns ``"UTF-8"``, the :term:`locale encoding` is
+   ignored.
+
+   This function is same to ``getpreferredencoding(False)`` except this
+   function ignore the :ref:`UTF-8 Mode <utf8-mode>`.
+
+   .. versionadded:: 3.11
+
+
 .. function:: normalize(localename)
 
    Returns a normalized locale code for the given locale name.  The returned locale
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
index 809cbd556c8c7f..d91b83ee494bc8 100644
--- a/Doc/whatsnew/3.11.rst
+++ b/Doc/whatsnew/3.11.rst
@@ -274,6 +274,12 @@ inspect
 * Add :func:`inspect.ismethodwrapper` for checking if the type of an object is a
   :class:`~types.MethodWrapperType`. (Contributed by Hakan Çelik in :issue:`29418`.)
 
+locale
+------
+
+* Add :func:`locale.getencoding` that is same to
+  ``locale.getpreferredencoding(False)`` but ignores :ref:`UTF-8 Mode <utf8-mode>`.
+
 math
 ----
 

From f61b62269e6ae38886c1ca6c4a5bd4aa6f3c436b Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Wed, 6 Apr 2022 11:54:56 +0900
Subject: [PATCH 07/13] Add news

---
 .../NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst

diff --git a/Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst b/Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst
new file mode 100644
index 00000000000000..c1d655068da74d
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst
@@ -0,0 +1 @@
+Add :func:`locale.getencoding`.

From 1c60e5b6bfae00a47fd1eb63581a49aacb7a7953 Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Wed, 6 Apr 2022 17:16:17 +0900
Subject: [PATCH 08/13] Apply proposed changes.

---
 Doc/glossary.rst       | 5 +++--
 Doc/library/locale.rst | 9 ++++++---
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/Doc/glossary.rst b/Doc/glossary.rst
index 258a06f7217035..233a129faaefba 100644
--- a/Doc/glossary.rst
+++ b/Doc/glossary.rst
@@ -710,8 +710,9 @@ Glossary
 
       On Windows, it is the ANSI code page (ex: ``cp1252``).
 
-      ``locale.getpreferredencoding(False)`` can be used to get the locale
-      encoding.
+      On Android and VxWorks, return ``"UTF-8"``.
+
+      ``locale.getencoding()`` can be used to get the locale encoding.
 
       Python uses the :term:`filesystem encoding and error handler` to convert
       between Unicode filenames and bytes filenames.
diff --git a/Doc/library/locale.rst b/Doc/library/locale.rst
index 5783c5c78be5f2..08e8b6266d0e1e 100644
--- a/Doc/library/locale.rst
+++ b/Doc/library/locale.rst
@@ -340,10 +340,13 @@ The :mod:`locale` module defines the following exception and functions:
 
 .. function:: getencoding()
 
-   Returns the :term:`locale encoding`.
+   Get the current :term:`locale encoding`:
 
-   On Android, it always returns ``"UTF-8"``, the :term:`locale encoding` is
-   ignored.
+   * On Android and VxWorks, return ``"UTF-8"``.
+   * On Unix, return the encoding of the current :data:`LC_CTYPE` locale.
+     Return ``"UTF-8"`` if :ref:`nl_langinfo(CODESET) <nl_langinfo>`
+     returns an empty string: for example, if the current LC_CTYPE locale is not supported.
+   * On Windows, return the ANSI code page.
 
    This function is same to ``getpreferredencoding(False)`` except this
    function ignore the :ref:`UTF-8 Mode <utf8-mode>`.

From 7397493344e6ebd16a655e4319550a3df78b7acb Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Wed, 6 Apr 2022 17:35:26 +0900
Subject: [PATCH 09/13] Fix doc error.

---
 Doc/library/locale.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Doc/library/locale.rst b/Doc/library/locale.rst
index 08e8b6266d0e1e..acd772ace61ce3 100644
--- a/Doc/library/locale.rst
+++ b/Doc/library/locale.rst
@@ -344,8 +344,8 @@ The :mod:`locale` module defines the following exception and functions:
 
    * On Android and VxWorks, return ``"UTF-8"``.
    * On Unix, return the encoding of the current :data:`LC_CTYPE` locale.
-     Return ``"UTF-8"`` if :ref:`nl_langinfo(CODESET) <nl_langinfo>`
-     returns an empty string: for example, if the current LC_CTYPE locale is not supported.
+     Return ``"UTF-8"`` if ``nl_langinfo(CODESET)`` returns an empty string:
+     for example, if the current LC_CTYPE locale is not supported.
    * On Windows, return the ANSI code page.
 
    This function is same to ``getpreferredencoding(False)`` except this

From 44730dd227b4381f65653c3783b6dfb59871da3a Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Thu, 7 Apr 2022 12:39:30 +0900
Subject: [PATCH 10/13] Apply suggestions from code review

Co-authored-by: Victor Stinner <vstinner@python.org>
---
 Doc/glossary.rst       | 4 ++--
 Doc/library/locale.rst | 4 ++--
 Doc/whatsnew/3.11.rst  | 2 +-
 Modules/_io/textio.c   | 3 +--
 4 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/Doc/glossary.rst b/Doc/glossary.rst
index 233a129faaefba..54f32810a6e6f9 100644
--- a/Doc/glossary.rst
+++ b/Doc/glossary.rst
@@ -708,9 +708,9 @@ Glossary
       On Unix, it is the encoding of the LC_CTYPE locale. It can be set with
       ``locale.setlocale(locale.LC_CTYPE, new_locale)``.
 
-      On Windows, it is the ANSI code page (ex: ``cp1252``).
+      On Windows, it is the ANSI code page (ex: ``"cp1252"``).
 
-      On Android and VxWorks, return ``"UTF-8"``.
+      On Android and VxWorks, Python uses ``"UTF-8"`` as the locale encoding.
 
       ``locale.getencoding()`` can be used to get the locale encoding.
 
diff --git a/Doc/library/locale.rst b/Doc/library/locale.rst
index acd772ace61ce3..efe72fa38c4ccd 100644
--- a/Doc/library/locale.rst
+++ b/Doc/library/locale.rst
@@ -348,8 +348,8 @@ The :mod:`locale` module defines the following exception and functions:
      for example, if the current LC_CTYPE locale is not supported.
    * On Windows, return the ANSI code page.
 
-   This function is same to ``getpreferredencoding(False)`` except this
-   function ignore the :ref:`UTF-8 Mode <utf8-mode>`.
+   This function is similar to :func:`getpreferredencoding(False) <getpreferredencoding>` except this
+   function ignores the :ref:`Python UTF-8 Mode <utf8-mode>`.
 
    .. versionadded:: 3.11
 
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
index d91b83ee494bc8..29f8196f52caa2 100644
--- a/Doc/whatsnew/3.11.rst
+++ b/Doc/whatsnew/3.11.rst
@@ -277,7 +277,7 @@ inspect
 locale
 ------
 
-* Add :func:`locale.getencoding` that is same to
+* Add :func:`locale.getencoding` to get the current locale encoding. It is similar to
   ``locale.getpreferredencoding(False)`` but ignores :ref:`UTF-8 Mode <utf8-mode>`.
 
 math
diff --git a/Modules/_io/textio.c b/Modules/_io/textio.c
index ea0f9b3d45a374..0e207413257f49 100644
--- a/Modules/_io/textio.c
+++ b/Modules/_io/textio.c
@@ -1147,8 +1147,7 @@ _io_TextIOWrapper___init___impl(textio *self, PyObject *buffer,
     if (encoding == NULL && self->encoding == NULL) {
         if (_PyRuntime.preconfig.utf8_mode) {
             _Py_DECLARE_STR(utf_8, "utf-8");
-            self->encoding = &_Py_STR(utf_8);
-            Py_INCREF(self->encoding);
+            self->encoding = Py_NewRef(&_Py_STR(utf_8));
         }
         else {
             self->encoding = _Py_GetLocaleEncodingObject();

From 7720b109f491879dea4a93cc3955e4ae6895a918 Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Thu, 7 Apr 2022 13:16:21 +0900
Subject: [PATCH 11/13] UTF-8 -> utf-8

---
 Doc/glossary.rst       |  4 ++--
 Doc/library/locale.rst | 13 +++++++++----
 Lib/locale.py          |  8 ++++----
 Python/fileutils.c     | 14 ++++++--------
 Python/initconfig.c    |  2 +-
 5 files changed, 22 insertions(+), 19 deletions(-)

diff --git a/Doc/glossary.rst b/Doc/glossary.rst
index 54f32810a6e6f9..479071436eb3e7 100644
--- a/Doc/glossary.rst
+++ b/Doc/glossary.rst
@@ -706,11 +706,11 @@ Glossary
 
    locale encoding
       On Unix, it is the encoding of the LC_CTYPE locale. It can be set with
-      ``locale.setlocale(locale.LC_CTYPE, new_locale)``.
+      :func:`locale.setlocale(locale.LC_CTYPE, new_locale) <locale.setlocale>`.
 
       On Windows, it is the ANSI code page (ex: ``"cp1252"``).
 
-      On Android and VxWorks, Python uses ``"UTF-8"`` as the locale encoding.
+      On Android and VxWorks, Python uses ``"utf-8"`` as the locale encoding.
 
       ``locale.getencoding()`` can be used to get the locale encoding.
 
diff --git a/Doc/library/locale.rst b/Doc/library/locale.rst
index efe72fa38c4ccd..f0a86651f9a93f 100644
--- a/Doc/library/locale.rst
+++ b/Doc/library/locale.rst
@@ -327,7 +327,7 @@ The :mod:`locale` module defines the following exception and functions:
    is not necessary or desired, *do_setlocale* should be set to ``False``.
 
    On Android or if the :ref:`Python UTF-8 Mode <utf8-mode>` is enabled, always
-   return ``'UTF-8'``, the :term:`locale encoding` and the *do_setlocale*
+   return ``'utf-8'``, the :term:`locale encoding` and the *do_setlocale*
    argument are ignored.
 
    The :ref:`Python preinitialization <c-preinit>` configures the LC_CTYPE
@@ -337,18 +337,23 @@ The :mod:`locale` module defines the following exception and functions:
       The function now always returns ``"UTF-8"`` on Android or if the
       :ref:`Python UTF-8 Mode <utf8-mode>` is enabled.
 
+   .. versionchanged:: 3.11
+      The function now returns ``"utf-8"`` instead of ``"UTF-8"`` on Android
+      or if the :ref:`Python UTF-8 Mode <utf8-mode>` is enabled.
+
 
 .. function:: getencoding()
 
    Get the current :term:`locale encoding`:
 
-   * On Android and VxWorks, return ``"UTF-8"``.
+   * On Android and VxWorks, return ``"utf-8"``.
    * On Unix, return the encoding of the current :data:`LC_CTYPE` locale.
-     Return ``"UTF-8"`` if ``nl_langinfo(CODESET)`` returns an empty string:
+     Return ``"utf-8"`` if ``nl_langinfo(CODESET)`` returns an empty string:
      for example, if the current LC_CTYPE locale is not supported.
    * On Windows, return the ANSI code page.
 
-   This function is similar to :func:`getpreferredencoding(False) <getpreferredencoding>` except this
+   This function is similar to
+   :func:`getpreferredencoding(False) <getpreferredencoding>` except this
    function ignores the :ref:`Python UTF-8 Mode <utf8-mode>`.
 
    .. versionadded:: 3.11
diff --git a/Lib/locale.py b/Lib/locale.py
index bc11164015245e..496cc803c88f7c 100644
--- a/Lib/locale.py
+++ b/Lib/locale.py
@@ -643,11 +643,11 @@ def getencoding():
         if hasattr(sys, 'getandroidapilevel'):
             # On Android langinfo.h and CODESET are missing, and UTF-8 is
             # always used in mbstowcs() and wcstombs().
-            return 'UTF-8'
+            return 'utf-8'
         encoding = getdefaultlocale()[1]
         if encoding is None:
             # LANG not set, default to UTF-8
-            encoding = 'UTF-8'
+            encoding = 'utf-8'
         return encoding
 
 try:
@@ -656,7 +656,7 @@ def getencoding():
     def getpreferredencoding(do_setlocale=True):
         """Return the charset that the user is likely using."""
         if sys.flags.utf8_mode:
-            return 'UTF-8'
+            return 'utf-8'
         return getencoding()
 else:
     # On Unix, if CODESET is available, use that.
@@ -664,7 +664,7 @@ def getpreferredencoding(do_setlocale=True):
         """Return the charset that the user is likely using,
         according to the system configuration."""
         if sys.flags.utf8_mode:
-            return 'UTF-8'
+            return 'utf-8'
 
         if not do_setlocale:
             return getencoding()
diff --git a/Python/fileutils.c b/Python/fileutils.c
index f880375b0d3aec..f1b253446bd178 100644
--- a/Python/fileutils.c
+++ b/Python/fileutils.c
@@ -95,9 +95,7 @@ _Py_device_encoding(int fd)
 #else
     if (_PyRuntime.preconfig.utf8_mode) {
         _Py_DECLARE_STR(utf_8, "utf-8");
-        PyObject *encoding = &_Py_STR(utf_8);
-        Py_INCREF(encoding);
-        return encoding;
+        return Py_NewRef(&_Py_STR(utf_8));
     }
     return _Py_GetLocaleEncodingObject();
 #endif
@@ -879,10 +877,10 @@ _Py_EncodeLocaleEx(const wchar_t *text, char **str,
 
 // Get the current locale encoding name:
 //
-// - Return "UTF-8" if _Py_FORCE_UTF8_LOCALE macro is defined (ex: on Android)
-// - Return "UTF-8" if the UTF-8 Mode is enabled
+// - Return "utf-8" if _Py_FORCE_UTF8_LOCALE macro is defined (ex: on Android)
+// - Return "utf-8" if the UTF-8 Mode is enabled
 // - On Windows, return the ANSI code page (ex: "cp1250")
-// - Return "UTF-8" if nl_langinfo(CODESET) returns an empty string.
+// - Return "utf-8" if nl_langinfo(CODESET) returns an empty string.
 // - Otherwise, return nl_langinfo(CODESET).
 //
 // Return NULL on memory allocation failure.
@@ -894,7 +892,7 @@ _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 _PyMem_RawWcsdup(L"UTF-8");
+    return _PyMem_RawWcsdup(L"utf-8");
 #else
 
 #ifdef MS_WINDOWS
@@ -908,7 +906,7 @@ _Py_GetLocaleEncoding(void)
     if (!encoding || encoding[0] == '\0') {
         // Use UTF-8 if nl_langinfo() returns an empty string. It can happen on
         // macOS if the LC_CTYPE locale is not supported.
-        return _PyMem_RawWcsdup(L"UTF-8");
+        return _PyMem_RawWcsdup(L"utf-8");
     }
 
     wchar_t *wstr;
diff --git a/Python/initconfig.c b/Python/initconfig.c
index d9a9e429b81f51..d2e74f5878a513 100644
--- a/Python/initconfig.c
+++ b/Python/initconfig.c
@@ -1781,7 +1781,7 @@ config_get_locale_encoding(PyConfig *config, const PyPreConfig *preconfig,
 {
     wchar_t *encoding;
     if (preconfig->utf8_mode) {
-        encoding = _PyMem_RawWcsdup(L"UTF-8");
+        encoding = _PyMem_RawWcsdup(L"utf-8");
     }
     else {
         encoding = _Py_GetLocaleEncoding();

From 104008dfdb1b0807439db93522221f4a04b91a8b Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Thu, 7 Apr 2022 13:43:22 +0900
Subject: [PATCH 12/13] Fix test_utf8_mode

---
 Lib/test/test_utf8_mode.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Lib/test/test_utf8_mode.py b/Lib/test/test_utf8_mode.py
index 308e8e8aea6c22..ec29ba6d51b127 100644
--- a/Lib/test/test_utf8_mode.py
+++ b/Lib/test/test_utf8_mode.py
@@ -203,12 +203,12 @@ def test_pyio_encoding(self):
     def test_locale_getpreferredencoding(self):
         code = 'import locale; print(locale.getpreferredencoding(False), locale.getpreferredencoding(True))'
         out = self.get_output('-X', 'utf8', '-c', code)
-        self.assertEqual(out, 'UTF-8 UTF-8')
+        self.assertEqual(out, 'utf-8 utf-8')
 
         for loc in POSIX_LOCALES:
             with self.subTest(LC_ALL=loc):
                 out = self.get_output('-X', 'utf8', '-c', code, LC_ALL=loc)
-                self.assertEqual(out, 'UTF-8 UTF-8')
+                self.assertEqual(out, 'utf-8 utf-8')
 
     @unittest.skipIf(MS_WINDOWS, 'test specific to Unix')
     def test_cmd_line(self):
@@ -276,7 +276,7 @@ def test_device_encoding(self):
         # In UTF-8 Mode, device_encoding(fd) returns "UTF-8" if fd is a TTY
         with open(filename, encoding="utf8") as fp:
             out = fp.read().rstrip()
-        self.assertEqual(out, 'True UTF-8')
+        self.assertEqual(out, 'True utf-8')
 
 
 if __name__ == "__main__":

From a8e50bd0112e79768c8360256bfc7b1ca965c840 Mon Sep 17 00:00:00 2001
From: Inada Naoki <songofacandy@gmail.com>
Date: Fri, 8 Apr 2022 16:20:37 +0900
Subject: [PATCH 13/13] Update based on suggestions

---
 Doc/glossary.rst                                         | 3 +--
 Doc/library/locale.rst                                   | 9 ++++-----
 Doc/whatsnew/3.11.rst                                    | 3 ++-
 .../Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst     | 4 +++-
 4 files changed, 10 insertions(+), 9 deletions(-)

diff --git a/Doc/glossary.rst b/Doc/glossary.rst
index 479071436eb3e7..75db433abd6007 100644
--- a/Doc/glossary.rst
+++ b/Doc/glossary.rst
@@ -714,8 +714,7 @@ Glossary
 
       ``locale.getencoding()`` can be used to get the locale encoding.
 
-      Python uses the :term:`filesystem encoding and error handler` to convert
-      between Unicode filenames and bytes filenames.
+      See also the :term:`filesystem encoding and error handler`.
 
    list
       A built-in Python :term:`sequence`.  Despite its name it is more akin
diff --git a/Doc/library/locale.rst b/Doc/library/locale.rst
index f0a86651f9a93f..77a3e036841baa 100644
--- a/Doc/library/locale.rst
+++ b/Doc/library/locale.rst
@@ -334,13 +334,9 @@ The :mod:`locale` module defines the following exception and functions:
    locale. See also the :term:`filesystem encoding and error handler`.
 
    .. versionchanged:: 3.7
-      The function now always returns ``"UTF-8"`` on Android or if the
+      The function now always returns ``"utf-8"`` on Android or if the
       :ref:`Python UTF-8 Mode <utf8-mode>` is enabled.
 
-   .. versionchanged:: 3.11
-      The function now returns ``"utf-8"`` instead of ``"UTF-8"`` on Android
-      or if the :ref:`Python UTF-8 Mode <utf8-mode>` is enabled.
-
 
 .. function:: getencoding()
 
@@ -352,6 +348,9 @@ The :mod:`locale` module defines the following exception and functions:
      for example, if the current LC_CTYPE locale is not supported.
    * On Windows, return the ANSI code page.
 
+   The :ref:`Python preinitialization <c-preinit>` configures the LC_CTYPE
+   locale. See also the :term:`filesystem encoding and error handler`.
+
    This function is similar to
    :func:`getpreferredencoding(False) <getpreferredencoding>` except this
    function ignores the :ref:`Python UTF-8 Mode <utf8-mode>`.
diff --git a/Doc/whatsnew/3.11.rst b/Doc/whatsnew/3.11.rst
index 29f8196f52caa2..9256642c981a59 100644
--- a/Doc/whatsnew/3.11.rst
+++ b/Doc/whatsnew/3.11.rst
@@ -278,7 +278,8 @@ locale
 ------
 
 * Add :func:`locale.getencoding` to get the current locale encoding. It is similar to
-  ``locale.getpreferredencoding(False)`` but ignores :ref:`UTF-8 Mode <utf8-mode>`.
+  ``locale.getpreferredencoding(False)`` but ignores the
+  :ref:`Python UTF-8 Mode <utf8-mode>`.
 
 math
 ----
diff --git a/Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst b/Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst
index c1d655068da74d..0dd3d416c51e59 100644
--- a/Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst
+++ b/Misc/NEWS.d/next/Library/2022-04-06-11-54-53.bpo-47000.2nmAR1.rst
@@ -1 +1,3 @@
-Add :func:`locale.getencoding`.
+Add :func:`locale.getencoding` to get the current locale encoding.
+It is similar to ``locale.getpreferredencoding(False)`` but ignores the
+:ref:`Python UTF-8 Mode <utf8-mode>`.