https://github.com/python/cpython/commit/6cd1d6c6b142697fb72f422b7b448c27ebc30534
commit: 6cd1d6c6b142697fb72f422b7b448c27ebc30534
branch: main
author: Emma Smith <e...@emmatyping.dev>
committer: hugovk <1324225+hug...@users.noreply.github.com>
date: 2025-04-08T10:43:14+03:00
summary:
gh-84481: Make ZipFile.data_offset more robust (#132178)
files:
M Lib/test/test_zipfile/test_core.py
M Lib/zipfile/__init__.py
diff --git a/Lib/test/test_zipfile/test_core.py
b/Lib/test/test_zipfile/test_core.py
index 94c0a44f3758d2..2a4e1acf2195ca 100644
--- a/Lib/test/test_zipfile/test_core.py
+++ b/Lib/test/test_zipfile/test_core.py
@@ -3348,6 +3348,12 @@ def test_data_offset_write_with_prefix(self):
with zipfile.ZipFile(fp, "w") as zipfp:
self.assertEqual(zipfp.data_offset, 16)
+ def test_data_offset_append_with_bad_zip(self):
+ with io.BytesIO() as fp:
+ fp.write(b"this is a prefix")
+ with zipfile.ZipFile(fp, "a") as zipfp:
+ self.assertEqual(zipfp.data_offset, 16)
+
def test_data_offset_write_no_tell(self):
# The initializer in ZipFile checks if tell raises AttributeError or
# OSError when creating a file in write mode when deducing the offset
@@ -3357,7 +3363,7 @@ def tell(self):
raise OSError("Unimplemented!")
with NoTellBytesIO() as fp:
with zipfile.ZipFile(fp, "w") as zipfp:
- self.assertIs(zipfp.data_offset, None)
+ self.assertIsNone(zipfp.data_offset)
class EncodedMetadataTests(unittest.TestCase):
diff --git a/Lib/zipfile/__init__.py b/Lib/zipfile/__init__.py
index b061691ac6f8b9..e3a94215bd6700 100644
--- a/Lib/zipfile/__init__.py
+++ b/Lib/zipfile/__init__.py
@@ -1403,6 +1403,7 @@ def __init__(self, file, mode="r",
compression=ZIP_STORED, allowZip64=True,
self._lock = threading.RLock()
self._seekable = True
self._writing = False
+ self._data_offset = None
try:
if mode == 'r':
@@ -1418,7 +1419,6 @@ def __init__(self, file, mode="r",
compression=ZIP_STORED, allowZip64=True,
self.fp = _Tellable(self.fp)
self.start_dir = 0
self._seekable = False
- self._data_offset = None
else:
# Some file-like objects can provide tell() but not seek()
try:
@@ -1439,6 +1439,7 @@ def __init__(self, file, mode="r",
compression=ZIP_STORED, allowZip64=True,
# even if no files are added to the archive
self._didModify = True
self.start_dir = self.fp.tell()
+ self._data_offset = self.start_dir
else:
raise ValueError("Mode must be 'r', 'w', 'x', or 'a'")
except:
_______________________________________________
Python-checkins mailing list -- python-checkins@python.org
To unsubscribe send an email to python-checkins-le...@python.org
https://mail.python.org/mailman3/lists/python-checkins.python.org/
Member address: arch...@mail-archive.com
