Skip to content

bpo-31758: Prevent crashes when using an uninitialized _elementtree.XMLParser object #3997

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Apr 12, 2020
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 15 additions & 0 deletions Lib/test/test_xml_etree_c.py
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,21 @@ def __del__(self):
elem.tail = X()
elem.__setstate__({'tag': 42}) # shouldn't cause an assertion failure

@support.cpython_only
def test_uninitialized_parser(self):
# The interpreter shouldn't crash in case of calling methods or
# accessing attributes of uninitialized XMLParser objects.
parser = cET.XMLParser.__new__(cET.XMLParser)
self.assertRaises(ValueError, parser.close)
self.assertRaises(ValueError, parser.feed, 'foo')
class MockFile:
def read(*args):
return ''
self.assertRaises(ValueError, parser._parse_whole, MockFile())
self.assertRaises(ValueError, parser._setevents, None)
self.assertIsNone(parser.entity)
self.assertIsNone(parser.target)

def test_setstate_leaks(self):
# Test reference leaks
elem = cET.Element.__new__(cET.Element)
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
Prevent crashes when using an uninitialized ``_elementtree.XMLParser``
object. Patch by Oren Milman.
24 changes: 24 additions & 0 deletions Modules/_elementtree.c
Original file line number Diff line number Diff line change
Expand Up @@ -3818,6 +3818,17 @@ xmlparser_dealloc(XMLParserObject* self)
Py_TYPE(self)->tp_free((PyObject *)self);
}

Py_LOCAL_INLINE(int)
_check_xmlparser(XMLParserObject* self)
{
if (self->target == NULL) {
PyErr_SetString(PyExc_ValueError,
"XMLParser.__init__() wasn't called");
return 0;
}
return 1;
}

LOCAL(PyObject*)
expat_parse(XMLParserObject* self, const char* data, int data_len, int final)
{
Expand Down Expand Up @@ -3854,6 +3865,10 @@ _elementtree_XMLParser_close_impl(XMLParserObject *self)
/* end feeding data to parser */

PyObject* res;

if (!_check_xmlparser(self)) {
return NULL;
}
res = expat_parse(self, "", 0, 1);
if (!res)
return NULL;
Expand Down Expand Up @@ -3885,6 +3900,9 @@ _elementtree_XMLParser_feed(XMLParserObject *self, PyObject *data)
{
/* feed data to parser */

if (!_check_xmlparser(self)) {
return NULL;
}
if (PyUnicode_Check(data)) {
Py_ssize_t data_len;
const char *data_ptr = PyUnicode_AsUTF8AndSize(data, &data_len);
Expand Down Expand Up @@ -3932,6 +3950,9 @@ _elementtree_XMLParser__parse_whole(XMLParserObject *self, PyObject *file)
PyObject* temp;
PyObject* res;

if (!_check_xmlparser(self)) {
return NULL;
}
reader = PyObject_GetAttrString(file, "read");
if (!reader)
return NULL;
Expand Down Expand Up @@ -4019,6 +4040,9 @@ _elementtree_XMLParser__setevents_impl(XMLParserObject *self,
TreeBuilderObject *target;
PyObject *events_append, *events_seq;

if (!_check_xmlparser(self)) {
return NULL;
}
if (!TreeBuilder_CheckExact(self->target)) {
PyErr_SetString(
PyExc_TypeError,
Expand Down