Skip to content

bpo-29942: Fix the use of recursion in itertools.chain.from_iterable. #889

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 5 commits into from
Mar 30, 2017
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
8 changes: 8 additions & 0 deletions Lib/test/test_itertools.py
Original file line number Diff line number Diff line change
Expand Up @@ -1976,6 +1976,14 @@ def gen2(x):
self.assertRaises(AssertionError, list, cycle(gen1()))
self.assertEqual(hist, [0,1])

def test_long_chain_of_empty_iterables(self):
# Make sure itertools.chain doesn't run into recursion limits when
# dealing with long chains of empty iterables. Even with a high
# number this would probably only fail in Py_DEBUG mode.
it = chain.from_iterable(() for unused in range(10000000))
with self.assertRaises(StopIteration):
next(it)

class SubclassWithKwargsTest(unittest.TestCase):
def test_keywords_in_subclass(self):
# count is not subclassable...
Expand Down
3 changes: 3 additions & 0 deletions Misc/NEWS
Original file line number Diff line number Diff line change
Expand Up @@ -301,6 +301,9 @@ Extension Modules
Library
-------

- bpo-29942: Fix a crash in itertools.chain.from_iterable when encountering
long runs of empty iterables.

- bpo-10030: Sped up reading encrypted ZIP files by 2 times.

- bpo-29204: Element.getiterator() and the html parameter of XMLParser() were
Expand Down
52 changes: 28 additions & 24 deletions Modules/itertoolsmodule.c
Original file line number Diff line number Diff line change
Expand Up @@ -1864,33 +1864,37 @@ chain_next(chainobject *lz)
{
PyObject *item;

if (lz->source == NULL)
return NULL; /* already stopped */

if (lz->active == NULL) {
PyObject *iterable = PyIter_Next(lz->source);
if (iterable == NULL) {
Py_CLEAR(lz->source);
return NULL; /* no more input sources */
}
lz->active = PyObject_GetIter(iterable);
Py_DECREF(iterable);
/* lz->source is the iterator of iterables. If it's NULL, we've already
* consumed them all. lz->active is the current iterator. If it's NULL,
* we should grab a new one from lz->source. */
while (lz->source != NULL) {
if (lz->active == NULL) {
Py_CLEAR(lz->source);
return NULL; /* input not iterable */
PyObject *iterable = PyIter_Next(lz->source);
if (iterable == NULL) {
Py_CLEAR(lz->source);
return NULL; /* no more input sources */
}
lz->active = PyObject_GetIter(iterable);
Py_DECREF(iterable);
if (lz->active == NULL) {
Py_CLEAR(lz->source);
return NULL; /* input not iterable */
}
}
item = (*Py_TYPE(lz->active)->tp_iternext)(lz->active);
if (item != NULL)
return item;
if (PyErr_Occurred()) {
if (PyErr_ExceptionMatches(PyExc_StopIteration))
PyErr_Clear();
else
return NULL; /* input raised an exception */
}
/* lz->active is consumed, try with the next iterable. */
Py_CLEAR(lz->active);
}
item = (*Py_TYPE(lz->active)->tp_iternext)(lz->active);
if (item != NULL)
return item;
if (PyErr_Occurred()) {
if (PyErr_ExceptionMatches(PyExc_StopIteration))
PyErr_Clear();
else
return NULL; /* input raised an exception */
}
Py_CLEAR(lz->active);
return chain_next(lz); /* recurse and use next active */
/* Everything had been consumed already. */
return NULL;
}

static PyObject *
Expand Down