[Python-checkins] bpo-43292: Fix file leak in `ET.iterparse()` when not exhausted (GH-31696)
serhiy-storchaka
webhook-mailer at python.org
Mon Mar 7 04:32:26 EST 2022
https://github.com/python/cpython/commit/496c428de3318c9c5770937491b71dc3d3f18a6a
commit: 496c428de3318c9c5770937491b71dc3d3f18a6a
branch: main
author: Jacob Walls <jacobtylerwalls at gmail.com>
committer: serhiy-storchaka <storchaka at gmail.com>
date: 2022-03-07T11:31:46+02:00
summary:
bpo-43292: Fix file leak in `ET.iterparse()` when not exhausted (GH-31696)
Co-authored-by: Serhiy Storchaka <storchaka at gmail.com>
files:
A Misc/NEWS.d/next/Library/2022-03-05-09-43-53.bpo-25707.gTlclP.rst
M Lib/test/test_xml_etree.py
M Lib/xml/etree/ElementTree.py
M Misc/ACKS
diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
index 35d901f9d0824..d2bdc4f7f0444 100644
--- a/Lib/test/test_xml_etree.py
+++ b/Lib/test/test_xml_etree.py
@@ -658,6 +658,14 @@ def test_iterparse(self):
'junk after document element: line 1, column 12')
del cm, it
+ # Not exhausting the iterator still closes the resource (bpo-43292)
+ with warnings_helper.check_no_resource_warning(self):
+ it = iterparse(TESTFN)
+ del it
+
+ with self.assertRaises(FileNotFoundError):
+ iterparse("nonexistent")
+
def test_writefile(self):
elem = ET.Element("tag")
elem.text = "text"
diff --git a/Lib/xml/etree/ElementTree.py b/Lib/xml/etree/ElementTree.py
index 6059e2f592d2d..5249c7ab82b84 100644
--- a/Lib/xml/etree/ElementTree.py
+++ b/Lib/xml/etree/ElementTree.py
@@ -1244,8 +1244,14 @@ 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(source):
+ close_source = False
try:
+ if not hasattr(source, "read"):
+ source = open(source, "rb")
+ close_source = True
+ yield None
while True:
yield from pullparser.read_events()
# load event buffer
@@ -1261,16 +1267,12 @@ def iterator():
source.close()
class IterParseIterator(collections.abc.Iterator):
- __next__ = iterator().__next__
+ __next__ = iterator(source).__next__
it = IterParseIterator()
it.root = None
del iterator, IterParseIterator
- close_source = False
- if not hasattr(source, "read"):
- source = open(source, "rb")
- close_source = True
-
+ next(it)
return it
diff --git a/Misc/ACKS b/Misc/ACKS
index da2c82610d5ad..df851bb834cd4 100644
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -1879,6 +1879,7 @@ Wojtek Walczak
Charles Waldman
Richard Walker
Larry Wall
+Jacob Walls
Kevin Walzer
Rodrigo Steinmuller Wanderley
Dingyuan Wang
diff --git a/Misc/NEWS.d/next/Library/2022-03-05-09-43-53.bpo-25707.gTlclP.rst b/Misc/NEWS.d/next/Library/2022-03-05-09-43-53.bpo-25707.gTlclP.rst
new file mode 100644
index 0000000000000..a59f0a7657ff2
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2022-03-05-09-43-53.bpo-25707.gTlclP.rst
@@ -0,0 +1,2 @@
+Fixed a file leak in :func:`xml.etree.ElementTree.iterparse` when the
+iterator is not exhausted. Patch by Jacob Walls.
More information about the Python-checkins
mailing list