bpo-43292: Fix file leak in `ET.iterparse()` when not exhausted (GH-31696)

Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>

diff --git a/Lib/test/test_xml_etree.py b/Lib/test/test_xml_etree.py
index 35d901f9d08244dd75f2f66391255118781fda0c..d2bdc4f7f044457416d4af41c4e396401477e503 100644 (file)
--- a/Lib/test/test_xml_etree.py
+++ b/Lib/test/test_xml_etree.py
@@ -658,6 +658,14 @@ class ElementTreeTest(unittest.TestCase):
                     '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 6059e2f592d2d065f38cdb76e30d5ef708149c44..5249c7ab82b84b25f031fffdb932c656bdda7b42 100644 (file)
--- 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 iterparse(source, events=None, parser=None):
                 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 da2c82610d5adfcbe28b2b4d89584db43c600976..df851bb834cd4e0590a548ac61b52c767e0ecdf9 100644 (file)
--- 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 (file)
index 0000000..a59f0a7
--- /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.