bpo-41784: make PyUnicode_AsUTF8AndSize part of the limited API (GH-22252)

Author: alex

Doc/c-api/unicode.rst

@@ -1098,6 +1098,9 @@ These are the UTF-8 codec APIs:
    .. versionchanged:: 3.7
       The return type is now ``const char *`` rather of ``char *``.
 
+   .. versionchanged:: 3.10
+      This function is a part of the :ref:`limited API <stable>`.
+
 
 .. c:function:: const char* PyUnicode_AsUTF8(PyObject *unicode)
 

Doc/whatsnew/3.10.rst

@@ -323,6 +323,10 @@ New Features
   sending value into iterator without raising ``StopIteration`` exception.
   (Contributed by Vladimir Matveev in :issue:`41756`.)
 
+* Added :c:func:`PyUnicode_AsUTF8AndSize` to the limited C API.
+  (Contributed by Alex Gaynor in :issue:`41784`.)
+
+
 Porting to Python 3.10
 ----------------------
 

Include/cpython/unicodeobject.h

@@ -726,26 +726,6 @@ PyAPI_FUNC(int) _PyUnicode_FormatAdvancedWriter(
 
 /* --- Manage the default encoding ---------------------------------------- */
 
-/* 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.
-
-   _PyUnicode_AsStringAndSize is a #define for PyUnicode_AsUTF8AndSize to
-   support the previous internal function with the same behaviour.
-*/
-
-PyAPI_FUNC(const char *) PyUnicode_AsUTF8AndSize(
-    PyObject *unicode,
-    Py_ssize_t *size);
-
-#define _PyUnicode_AsStringAndSize PyUnicode_AsUTF8AndSize
-
 /* Returns a pointer to the default encoding (UTF-8) of the
    Unicode object unicode.
 

Include/unicodeobject.h

@@ -468,6 +468,23 @@ PyAPI_FUNC(PyObject*) PyUnicode_AsUTF8String(
     PyObject *unicode           /* Unicode object */
     );
 
+/* 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,
+    Py_ssize_t *size);
+#endif
+
 /* --- UTF-32 Codecs ------------------------------------------------------ */
 
 /* Decodes length bytes from a UTF-32 encoded buffer string and returns

Misc/NEWS.d/next/C API/2020-09-14-10-17-00.bpo-41784.Yl4gI2.rst

@@ -0,0 +1 @@
+Added ``PyUnicode_AsUTF8AndSize`` to the limited C API. 

PC/python3dll.c

@@ -568,6 +568,7 @@ EXPORT_FUNC(PyUnicode_AsUCS4Copy)
 EXPORT_FUNC(PyUnicode_AsUnicodeEscapeString)
 EXPORT_FUNC(PyUnicode_AsUTF16String)
 EXPORT_FUNC(PyUnicode_AsUTF32String)
+EXPORT_FUNC(PyUnicode_AsUTF8AndSize)
 EXPORT_FUNC(PyUnicode_AsUTF8String)
 EXPORT_FUNC(PyUnicode_AsWideChar)
 EXPORT_FUNC(PyUnicode_AsWideCharString)