pythongh-111089: Revert PyUnicode_AsUTF8() changes (python#111833)

* Revert "pythongh-111089: Use PyUnicode_AsUTF8() in Argument Clinic (python#111585)"

This reverts commit d9b606b.

* Revert "pythongh-111089: Use PyUnicode_AsUTF8() in getargs.c (python#111620)"

This reverts commit cde1071.

* Revert "pythongh-111089: PyUnicode_AsUTF8() now raises on embedded NUL (python#111091)"

This reverts commit d731579.

* Revert "pythongh-111089: Add PyUnicode_AsUTF8() to the limited C API (python#111121)"

This reverts commit d8f32be.

* Revert "pythongh-111089: Use PyUnicode_AsUTF8() in sqlite3 (python#111122)"

This reverts commit 37e4e20.

Doc/c-api/unicode.rst

@@ -992,19 +992,11 @@ These are the UTF-8 codec APIs:
 
    As :c:func:`PyUnicode_AsUTF8AndSize`, but does not store the size.
 
-   Raise an exception if the *unicode* string contains embedded null
-   characters. To accept embedded null characters and truncate on purpose
-   at the first null byte, ``PyUnicode_AsUTF8AndSize(unicode, NULL)`` can be
-   used instead.
-
    .. versionadded:: 3.3
 
    .. versionchanged:: 3.7
       The return type is now ``const char *`` rather of ``char *``.
 
-   .. versionchanged:: 3.13
-      Raise an exception if the string contains embedded null characters.
-
 
 UTF-32 Codecs
 """""""""""""

Doc/whatsnew/3.13.rst

@@ -1149,9 +1149,6 @@ New Features
   :c:func:`PyErr_WriteUnraisable`, but allow to customize the warning mesage.
   (Contributed by Serhiy Storchaka in :gh:`108082`.)
 
-* Add :c:func:`PyUnicode_AsUTF8` function to the limited C API.
-  (Contributed by Victor Stinner in :gh:`111089`.)
-
 
 Porting to Python 3.13
 ----------------------
@@ -1222,12 +1219,6 @@ Porting to Python 3.13
   Note that ``Py_TRASHCAN_BEGIN`` has a second argument which
   should be the deallocation function it is in.
 
-* The :c:func:`PyUnicode_AsUTF8` function now raises an exception if the string
-  contains embedded null characters. To accept embedded null characters and
-  truncate on purpose at the first null byte,
-  ``PyUnicode_AsUTF8AndSize(unicode, NULL)`` can be used instead.
-  (Contributed by Victor Stinner in :gh:`111089`.)
-
 * On Windows, ``Python.h`` no longer includes the ``<stddef.h>`` standard
   header file. If needed, it should now be included explicitly. For example, it
   provides ``offsetof()`` function, and ``size_t`` and ``ptrdiff_t`` types.

Include/cpython/unicodeobject.h

@@ -440,6 +440,22 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
     const void *buffer,
     Py_ssize_t size);
 
+/* --- Manage the default encoding ---------------------------------------- */
+
+/* Returns a pointer to the default encoding (UTF-8) of the
+   Unicode object unicode.
+
+   Like PyUnicode_AsUTF8AndSize(), this also caches the UTF-8 representation
+   in the unicodeobject.
+
+   _PyUnicode_AsString is a #define for PyUnicode_AsUTF8 to
+   support the previous internal function with the same behaviour.
+
+   Use of this API is DEPRECATED since no size information can be
+   extracted from the returned data.
+*/
+
+PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode);
 
 /* === Characters Type APIs =============================================== */
 

Include/unicodeobject.h

@@ -443,25 +443,17 @@ PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String(
     PyObject *unicode           /* Unicode object */
     );
 
-// Returns a pointer to the UTF-8 encoding of the Unicode object unicode.
-//
-// Raise an exception if the string contains embedded null characters.
-// Use PyUnicode_AsUTF8AndSize() to accept embedded null characters.
-//
-// This function caches the UTF-8 encoded string in the Unicode object
-// and subsequent calls will return the same string. The memory is released
-// when the Unicode object is deallocated.
-PyAPI_FUNC(const char *) PyUnicode_AsUTF8(PyObject *unicode);
-
-// Returns a pointer to the UTF-8 encoding of the
-// Unicode object unicode and the size of the encoded representation
-// in bytes stored in `*size` (if size is not NULL).
-//
-// On error, `*size` is set to 0 (if size is not NULL).
-//
-// This function caches the UTF-8 encoded string in the Unicode object
-// and subsequent calls will return the same string. The memory is released
-// when the Unicode object is deallocated.
+/* Returns a pointer to the default encoding (UTF-8) of the
+   Unicode object unicode and the size of the encoded representation
+   in bytes stored in *size.
+
+   In case of an error, no *size is set.
+
+   This function caches the UTF-8 encoded string in the unicodeobject
+   and subsequent calls will return the same string.  The memory is released
+   when the unicodeobject is deallocated.
+*/
+
 #if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x030A0000
 PyAPI_FUNC(const char *) PyUnicode_AsUTF8AndSize(
     PyObject *unicode,

Lib/test/test_capi/test_unicode.py

@@ -914,10 +914,7 @@ def test_asutf8(self):
         self.assertEqual(unicode_asutf8('abc', 4), b'abc\0')
         self.assertEqual(unicode_asutf8('абв', 7), b'\xd0\xb0\xd0\xb1\xd0\xb2\0')
         self.assertEqual(unicode_asutf8('\U0001f600', 5), b'\xf0\x9f\x98\x80\0')
-
-        # disallow embedded null characters
-        self.assertRaises(ValueError, unicode_asutf8, 'abc\0', 0)
-        self.assertRaises(ValueError, unicode_asutf8, 'abc\0def', 0)
+        self.assertEqual(unicode_asutf8('abc\0def', 8), b'abc\0def\0')
 
         self.assertRaises(UnicodeEncodeError, unicode_asutf8, '\ud8ff', 0)
         self.assertRaises(TypeError, unicode_asutf8, b'abc', 0)

Misc/stable_abi.toml

@@ -2478,8 +2478,6 @@
     added = '3.13'
 [function.PySys_AuditTuple]
     added = '3.13'
-[function.PyUnicode_AsUTF8]
-    added = '3.13'
 [function._Py_SetRefcnt]
     added = '3.13'
     abi_only = true

Modules/_multiprocessing/posixshmem.c

@@ -48,7 +48,7 @@ _posixshmem_shm_open_impl(PyObject *module, PyObject *path, int flags,
 {
     int fd;
     int async_err = 0;
-    const char *name = PyUnicode_AsUTF8(path);
+    const char *name = PyUnicode_AsUTF8AndSize(path, NULL);
     if (name == NULL) {
         return -1;
     }
@@ -87,7 +87,7 @@ _posixshmem_shm_unlink_impl(PyObject *module, PyObject *path)
 {
     int rv;
     int async_err = 0;
-    const char *name = PyUnicode_AsUTF8(path);
+    const char *name = PyUnicode_AsUTF8AndSize(path, NULL);
     if (name == NULL) {
         return NULL;
     }