Fix marshal's incorrect handling of subclasses of builtin types (backport candidate).

diff --git a/Doc/library/marshal.rst b/Doc/library/marshal.rst
index 19a56d74a30527c19e109be9e2cc215f26b0aec2..4f5b16ac869a5c511c75a54348c1c9c82c1b78d6 100644 (file)
--- a/Doc/library/marshal.rst
+++ b/Doc/library/marshal.rst
@@ -44,12 +44,6 @@ and dictionaries are only supported as long as the values contained therein are
 themselves supported; and recursive lists and dictionaries should not be written
 (they will cause infinite loops).
 
-.. warning::
-
-   Some unsupported types such as subclasses of builtins will appear to marshal
-   and unmarshal correctly, but in fact, their type will change and the
-   additional subclass functionality and instance attributes will be lost.
-
 .. warning::
    
    On machines where C's ``long int`` type has more than 32 bits (such as the

diff --git a/Lib/test/test_marshal.py b/Lib/test/test_marshal.py
index 656fc1facc7f392ac07d937522b8636b220f1a5b..1b2c8b7162968d3ceb24388e626fa6c6bf6a000f 100644 (file)
--- a/Lib/test/test_marshal.py
+++ b/Lib/test/test_marshal.py
@@ -244,6 +244,17 @@ class BugsTestCase(unittest.TestCase):
         last.append([0])
         self.assertRaises(ValueError, marshal.dumps, head)
 
+    def test_exact_type_match(self):
+        # Former bug:
+        #   >>> class Int(int): pass
+        #   >>> type(loads(dumps(Int())))
+        #   <type 'int'>
+        for typ in (int, long, float, complex, tuple, list, dict, set, frozenset):
+            # Note: str and unicode sublclasses are not tested because they get handled
+            # by marshal's routines for objects supporting the buffer API.
+            subtyp = type('subtyp', (typ,), {})
+            self.assertRaises(ValueError, marshal.dumps, subtyp())
+
 def test_main():
     test_support.run_unittest(IntTestCase,
                               FloatTestCase,

diff --git a/Misc/NEWS b/Misc/NEWS
index 502b18253fa2b47e5e3ecb90c868de80bfc5cfe0..997a49a1469b439cbce52d86fe016277fb60cf65 100644 (file)
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -812,6 +812,10 @@ Library
 Extension Modules
 -----------------
 
+- Marshal.dumps() now expects exact type matches for int, long, float, complex,
+  tuple, list, dict, set, and frozenset.  Formerly, it would silently miscode
+  subclasses of those types.  Now, it raises a ValueError instead.
+
 - Patch #1388440: Add set_completion_display_matches_hook and
   get_completion_type to readline.
 

diff --git a/Python/marshal.c b/Python/marshal.c
index 897c15ec8ad26424734f43eb3fe1a4ea22ce29e5..0c611b618c2ba4a463c42476bfa820e9f81b184d 100644 (file)
--- a/Python/marshal.c
+++ b/Python/marshal.c
@@ -144,7 +144,7 @@ w_object(PyObject *v, WFILE *p)
        else if (v == Py_True) {
                w_byte(TYPE_TRUE, p);
        }
-       else if (PyInt_Check(v)) {
+       else if (PyInt_CheckExact(v)) {
                long x = PyInt_AS_LONG((PyIntObject *)v);
 #if SIZEOF_LONG > 4
                long y = Py_ARITHMETIC_RIGHT_SHIFT(long, x, 31);
@@ -159,7 +159,7 @@ w_object(PyObject *v, WFILE *p)
                        w_long(x, p);
                }
        }
-       else if (PyLong_Check(v)) {
+       else if (PyLong_CheckExact(v)) {
                PyLongObject *ob = (PyLongObject *)v;
                w_byte(TYPE_LONG, p);
                n = ob->ob_size;
@@ -169,7 +169,7 @@ w_object(PyObject *v, WFILE *p)
                for (i = 0; i < n; i++)
                        w_short(ob->ob_digit[i], p);
        }
-       else if (PyFloat_Check(v)) {
+       else if (PyFloat_CheckExact(v)) {
                if (p->version > 1) {
                        unsigned char buf[8];
                        if (_PyFloat_Pack8(PyFloat_AsDouble(v), 
@@ -190,7 +190,7 @@ w_object(PyObject *v, WFILE *p)
                }
        }
 #ifndef WITHOUT_COMPLEX
-       else if (PyComplex_Check(v)) {
+       else if (PyComplex_CheckExact(v)) {
                if (p->version > 1) {
                        unsigned char buf[8];
                        if (_PyFloat_Pack8(PyComplex_RealAsDouble(v),
@@ -236,7 +236,7 @@ w_object(PyObject *v, WFILE *p)
                }
        }
 #endif
-       else if (PyString_Check(v)) {
+       else if (PyString_CheckExact(v)) {
                if (p->strings && PyString_CHECK_INTERNED(v)) {
                        PyObject *o = PyDict_GetItem(p->strings, v);
                        if (o) {
@@ -273,7 +273,7 @@ w_object(PyObject *v, WFILE *p)
                w_string(PyString_AS_STRING(v), (int)n, p);
        }
 #ifdef Py_USING_UNICODE
-       else if (PyUnicode_Check(v)) {
+       else if (PyUnicode_CheckExact(v)) {
                PyObject *utf8;
                utf8 = PyUnicode_AsUTF8String(v);
                if (utf8 == NULL) {
@@ -293,7 +293,7 @@ w_object(PyObject *v, WFILE *p)
                Py_DECREF(utf8);
        }
 #endif
-       else if (PyTuple_Check(v)) {
+       else if (PyTuple_CheckExact(v)) {
                w_byte(TYPE_TUPLE, p);
                n = PyTuple_Size(v);
                w_long((long)n, p);
@@ -301,7 +301,7 @@ w_object(PyObject *v, WFILE *p)
                        w_object(PyTuple_GET_ITEM(v, i), p);
                }
        }
-       else if (PyList_Check(v)) {
+       else if (PyList_CheckExact(v)) {
                w_byte(TYPE_LIST, p);
                n = PyList_GET_SIZE(v);
                w_long((long)n, p);
@@ -309,7 +309,7 @@ w_object(PyObject *v, WFILE *p)
                        w_object(PyList_GET_ITEM(v, i), p);
                }
        }
-       else if (PyDict_Check(v)) {
+       else if (PyDict_CheckExact(v)) {
                Py_ssize_t pos;
                PyObject *key, *value;
                w_byte(TYPE_DICT, p);
@@ -321,7 +321,7 @@ w_object(PyObject *v, WFILE *p)
                }
                w_object((PyObject *)NULL, p);
        }
-       else if (PyAnySet_Check(v)) {
+       else if (PyAnySet_CheckExact(v)) {
                PyObject *value, *it;
 
                if (PyObject_TypeCheck(v, &PySet_Type))