diff options
| -rw-r--r-- | Lib/test/test_zipfile.py | 15 | ||||
| -rw-r--r-- | Lib/zipfile.py | 2 | ||||
| -rw-r--r-- | Misc/NEWS | 5 |
3 files changed, 21 insertions, 1 deletions
diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py index 1bef575..0ee75ad 100644 --- a/Lib/test/test_zipfile.py +++ b/Lib/test/test_zipfile.py @@ -1290,6 +1290,21 @@ class OtherTests(unittest.TestCase): 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) diff --git a/Lib/zipfile.py b/Lib/zipfile.py index 7b6bd5f..ee228b1 100644 --- a/Lib/zipfile.py +++ b/Lib/zipfile.py @@ -411,7 +411,7 @@ class ZipInfo (object): # Try to decode the extra field. extra = self.extra unpack = struct.unpack - while extra: + while len(extra) >= 4: tp, ln = unpack('<HH', extra[:4]) if tp == 1: if ln >= 24: @@ -18,6 +18,11 @@ Core and Builtins Library ------- +- 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. + - Issue #21402: tkinter.ttk now works when default root window is not set. - Issue #10203: sqlite3.Row now truly supports sequence protocol. In particulr |