Skip to content

[WIP] bpo-35502: Fix memory leak in xml.etree iterparse() #11169

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.

Sign up for GitHub

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

Closed
wants to merge 1 commit into from
Closed

[WIP] bpo-35502: Fix memory leak in xml.etree iterparse() #11169

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
31 changes: 23 additions & 8 deletions Lib/xml/etree/ElementTree.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1214,7 +1214,8 @@ def iterparse(source, events=None, parser=None):
# Use the internal, undocumented _parser argument for now; When the
# parser argument of iterparse is removed, this can be killed.
pullparser = XMLPullParser(events=events, _parser=parser)
def iterator():

def iterator(pullparser, source, close_source):
try:
while True:
yield from pullparser.read_events()
Expand All @@ -1223,24 +1224,35 @@ def iterator():
if not data:
break
pullparser.feed(data)

root = pullparser._close_and_return_root()
yield from pullparser.read_events()
it.root = root
return root
finally:
if close_source:
source.close()

class IterParseIterator(collections.abc.Iterator):
__next__ = iterator().__next__
it = IterParseIterator()
it.root = None
del iterator, IterParseIterator
# explicitly break reference cycles
pullparser = None

close_source = False
if not hasattr(source, "read"):
source = open(source, "rb")
close_source = True

class IterParseIterator(collections.abc.Iterator):
def __init__(self, gen):
self._gen = gen
self.root = None

def __next__(self):
try:
return self._gen.__next__()
except StopIteration as exc:
self.root = exc.value

it = IterParseIterator(iterator(pullparser, source, close_source))
del iterator, IterParseIterator, pullparser, source

return it


Expand All @@ -1267,6 +1279,9 @@ def feed(self, data):
self._parser.feed(data)
except SyntaxError as exc:
self._events_queue.append(exc)
# explicitly break reference cycles
self = None
exc = None

def _close_and_return_root(self):
# iterparse needs this to set its root attribute properly :(
Expand Down