Fix issue #14315: The zipfile module now ignores extra fields in the central
directory that are too short to be parsed instead of letting a struct.unpack
error bubble up as this "bad data" appears in many real world zip files in the
wild and is ignored by other zip tools.
diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
index 6bf5c2f..604e57b 100644
--- a/Lib/test/test_zipfile.py
+++ b/Lib/test/test_zipfile.py
@@ -1157,6 +1157,21 @@
self.assertRaises(ValueError,
zipfile.ZipInfo, 'seventies', (1979, 1, 1, 0, 0, 0))
+ def test_zipfile_with_short_extra_field(self):
+ """If an extra field in the header is less than 4 bytes, skip it."""
+ zipdata = (
+ b'PK\x03\x04\x14\x00\x00\x00\x00\x00\x93\x9b\xad@\x8b\x9e'
+ b'\xd9\xd3\x01\x00\x00\x00\x01\x00\x00\x00\x03\x00\x03\x00ab'
+ b'c\x00\x00\x00APK\x01\x02\x14\x03\x14\x00\x00\x00\x00'
+ b'\x00\x93\x9b\xad@\x8b\x9e\xd9\xd3\x01\x00\x00\x00\x01\x00\x00'
+ b'\x00\x03\x00\x02\x00\x00\x00\x00\x00\x00\x00\x00\x00\xa4\x81\x00'
+ b'\x00\x00\x00abc\x00\x00PK\x05\x06\x00\x00\x00\x00'
+ b'\x01\x00\x01\x003\x00\x00\x00%\x00\x00\x00\x00\x00'
+ )
+ with zipfile.ZipFile(io.BytesIO(zipdata), 'r') as zipf:
+ # testzip returns the name of the first corrupt file, or None
+ self.assertIsNone(zipf.testzip())
+
def tearDown(self):
unlink(TESTFN)
unlink(TESTFN2)