8000 gh-117779: Fix reading duplicated entries in zipfile by name by serhiy-storchaka · Pull Request #129254 · python/cpython · GitHub
[go: up one dir, main page]

Skip to content

gh-117779: Fix reading duplicated entries in zipfile by name #129254

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
gh-117779: Fix reading duplicated entries in zipfile by name
  • Loading branch information
serhiy-storchaka committed Jan 24, 2025
commit b8a9ceabc9a1b666d087631e3558c4f592619d09
36 changes: 32 additions & 4 deletions Lib/test/test_zipfile/test_core.py
Original file line number Diff line number Diff line change
Expand Up @@ -2417,10 +2417,10 @@ def test_decompress_without_3rd_party_library(self):
self.assertRaises(RuntimeError, zf.extract, 'a.txt')

@requires_zlib()
def test_full_overlap(self):
def test_full_overlap_different_names(self):
data = (
b'PK\x03\x04\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2\x1e'
b'8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00a\xed'
b'8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00b\xed'
b'\xc0\x81\x08\x00\x00\x00\xc00\xd6\xfbK\\d\x0b`P'
b'K\x01\x02\x14\x00\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2'
b'\x1e8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00\x00'
Expand All @@ -2441,9 +2441,37 @@ def test_full_overlap(self):
self.assertEqual(zi.header_offset, 0)
self.assertEqual(zi.compress_size, 16)
self.assertEqual(zi.file_size, 1033)
self.assertEqual(len(zipf.read('a')), 1033)
self.assertEqual(len(zipf.read('b')), 1033)
with self.assertRaisesRegex(zipfile.BadZipFile, 'File name.*differ'):
zipf.read('b')
zipf.read('a')

@requires_zlib()
def test_full_overlap_same_name(self):
data = (
b'PK\x03\x04\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2\x1e'
b'8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00a\xed'
b'\xc0\x81\x08\x00\x00\x00\xc00\xd6\xfbK\\d\x0b`P'
b'K\x01\x02\x14\x00\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2'
b'\x1e8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00\x00'
b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00aPK'
b'\x01\x02\x14\x00\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2\x1e'
b'8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00\x00\x00'
b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00aPK\x05'
b'\x06\x00\x00\x00\x00\x02\x00\x02\x00^\x00\x00\x00/\x00\x00'
b'\x00\x00\x00'
)
with zipfile.ZipFile(io.BytesIO(data), 'r') as zipf:
self.assertEqual(zipf.namelist(), ['a', 'a'])
self.assertEqual(len(zipf.infolist()), 2)
zi = zipf.getinfo('a')
self.assertEqual(zi.header_offset, 0)
self.assertEqual(zi.compress_size, 16)
self.assertEqual(zi.file_size, 1033)
self.assertEqual(len(zipf.read('a')), 1033)
self.assertEqual(len(zipf.read(zi)), 1033)
self.assertEqual(len(zipf.read(zipf.infolist()[1])), 1033)
with self.assertRaisesRegex(zipfile.BadZipFile, 'Overlapped entries'):
zipf.read(zipf.infolist()[0])

@requires_zlib()
def test_quoted_overlap(self):
Expand Down
5 changes: 2 additions & 3 deletions Lib/zipfile/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -1545,9 +1545,8 @@ def _RealGetContents(self):
print("total", total)

end_offset = self.start_dir
for zinfo in sorted(self.filelist,
key=lambda zinfo: zinfo.header_offset,
reverse=True):
for zinfo in reversed(sorted(self.filelist,
key=lambda zinfo: zinfo.header_offset)):
zinfo._end_offset = end_offset
end_offset = zinfo.header_offset

Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
Fix reading duplicated entries in :mod:`zipfile` by name.
Loading
0