Add PyUnicode_AsUTF8AndSize to cpython imports [0.29.x] (#5164)

Backport of https://github.com/cython/cython/pull/5163

1 files changed, 17 insertions, 1 deletions

diff --git a/Cython/Includes/cpython/unicode.pxd b/Cython/Includes/cpython/unicode.pxd
index ad01ed64d..2072c8cb2 100644
--- a/Cython/Includes/cpython/unicode.pxd
+++ b/Cython/Includes/cpython/unicode.pxd
@@ -314,9 +314,25 @@ cdef extern from *:
     # raised by the codec.
     bytes PyUnicode_EncodeUTF8(Py_UNICODE *s, Py_ssize_t size, char *errors)
 
-    # Encode a Unicode objects using UTF-8 and return the result as Python string object. Error handling is ``strict''. Return NULL if an exception was raised by the codec.
+    # Encode a Unicode objects using UTF-8 and return the result as Python bytes object. Error handling is ``strict''. Return NULL if an exception was raised by the codec.
     bytes PyUnicode_AsUTF8String(object unicode)
 
+
+    # Return a pointer to the UTF-8 encoding of the Unicode object,
+    # and store the size of the encoded representation (in bytes) in size.
+    # The size argument can be NULL; in this case no size will be stored.
+    # The returned buffer always has an extra null byte appended
+    # (not included in size), regardless of whether there are any
+    # other null code points.
+
+    # In the case of an error, NULL is returned with an exception set and
+    # no size is stored.
+
+    # This caches the UTF-8 representation of the string in the Unicode
+    # object, and subsequent calls will return a pointer to the same buffer.
+    # The caller is not responsible for deallocating the buffer
+    const char* PyUnicode_AsUTF8AndSize(object unicode, Py_ssize_t *size)
+
 # These are the UTF-16 codec APIs:
 
     # Decode length bytes from a UTF-16 encoded buffer string and