gh-111089: PyUnicode_AsUTF8() now raises on embedded NUL (#111091)

* PyUnicode_AsUTF8() now raises an exception if the string contains
  embedded null characters.
* Update related C API tests (test_capi.test_unicode).
* type_new_set_doc() uses PyUnicode_AsUTF8AndSize() to silently
  truncate doc containing null bytes.

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>

2 files changed, 19 insertions, 21 deletions

diff --git a/Include/cpython/unicodeobject.h b/Include/cpython/unicodeobject.h
index 859ab71..d67553c 100644
--- a/Include/cpython/unicodeobject.h
+++ b/Include/cpython/unicodeobject.h
@@ -442,18 +442,18 @@ PyAPI_FUNC(PyObject*) PyUnicode_FromKindAndData(
 
 /* --- 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.
-
-   Use of this API is DEPRECATED since no size information can be
-   extracted from the returned data.
-*/
-
+// Returns a pointer to the default encoding (UTF-8) 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);
 
+
 /* === Characters Type APIs =============================================== */
 
 /* These should not be used directly. Use the Py_UNICODE_IS* and
diff --git a/Include/unicodeobject.h b/Include/unicodeobject.h
index dee0071..1e5753d 100644
--- a/Include/unicodeobject.h
+++ b/Include/unicodeobject.h
@@ -443,17 +443,15 @@ 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.
-*/
-
+// 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` (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.
 #if !defined(Py_LIMITED_API) || Py_LIMITED_API+0 >= 0x030A0000
 PyAPI_FUNC(const char *) PyUnicode_AsUTF8AndSize(
     PyObject *unicode,