gh-129724: gh-156504: Make marshal output independent of reference counts

Doc/c-api/marshal.rst

@@ -54,6 +54,10 @@ and :exc:`MemoryError` if memory allocation fails.
    Marshal a Python object, *value*, to *file*.
    *version* indicates the file format.
 
+   The marshalled representation of *value* is built in memory
+   and then written to *file*.
+   Nothing is written if *value* cannot be marshalled.
+
    This function can fail, in which case it sets the error indicator.
    Use :c:func:`PyErr_Occurred` to check for that.
 
@@ -68,6 +72,11 @@ and :exc:`MemoryError` if memory allocation fails.
       It can use :c:func:`PyMarshal_WriteObjectToString` and write the
       result itself, or validate what was written.
 
+   .. versionchanged:: next
+      Previously, the data was written to *file* as it was produced,
+      using a buffer of constant size,
+      and incomplete data was written if *value* could not be marshalled.
+
 .. c:function:: PyObject* PyMarshal_WriteObjectToString(PyObject *value, int version)
 
    Return a bytes object containing the marshalled representation of *value*.

Lib/test/test_capi/test_marshal.py

@@ -121,13 +121,39 @@ def test_write_object_to_file(self):
                     write_object_to_file(obj, filename, version)
                     data = read_file(filename)
                     self.assertEqual(marshal.loads(data), obj)
+                    self.assertEqual(data, marshal.dumps(obj, version))
+
+            # Larger than a stdio buffer, with references to objects
+            # written long before.
+            shared = (float('1.5'), b'bytes' * 10)
+            obj = [shared, 'long line ' * 10_000, shared, [shared] * 10_000]
+            write_object_to_file(obj, filename, version)
+            data = read_file(filename)
+            self.assertEqual(data, marshal.dumps(obj, version))
+            obj2 = marshal.loads(data)
+            self.assertEqual(obj2, obj)
+            if version >= 3:
+                self.assertIs(obj2[2], obj2[0])
+                self.assertIs(obj2[3][-1], obj2[0])
 
             with self.assertRaises(SystemError):
                 write_object_to_file(NULL, filename, version)
 
             with self.assertRaisesRegex(ValueError, 'cannot marshal object objects'):
                 write_object_to_file(UNMARSHALLABLE, filename, version)
 
+            # Nothing is written if the object cannot be marshalled,
+            # even if the error is only detected after more data than
+            # fits in a stdio buffer.
+            for obj in (UNMARSHALLABLE,
+                        [1, 'abc', UNMARSHALLABLE],
+                        [shared, 'long line ' * 10_000, shared,
+                         UNMARSHALLABLE]):
+                with self.assertRaisesRegex(ValueError,
+                                            'cannot marshal object objects'):
+                    write_object_to_file(obj, filename, version)
+                self.assertEqual(read_file(filename), b'')
+
     def test_read_short_from_file(self):
         # Test PyMarshal_ReadShortFromFile()
         read_short_from_file = _testcapi.pymarshal_read_short_from_file