Skip to content

gh-151987: Pass filter_function to TarFile._extract_one() during .extract() #151988

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.

Sign up for GitHub

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

Open
encukou wants to merge 7 commits into
base: main
Choose a base branch
from
+96 −1
Open

gh-151987: Pass filter_function to TarFile._extract_one() during .extract() #151988

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
b612154
Pass filter_function to TarFile._extract_one() during .extract()
sethmlarson Mar 18, 2026
5edbc2e
Use os_helper for temporary directory
encukou Jun 23, 2026
4318869
Add test for filtering the hardlink targed
encukou Jun 23, 2026
49f92a1
Merge in the main branch
encukou Jun 23, 2026
afc0bec
Use helpers for tests
encukou Jun 23, 2026
b873e05
Add blurb
encukou Jun 23, 2026
c2831a9
Skip test if mocked functions are unavailable
encukou Jun 23, 2026
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
3 changes: 2 additions & 1 deletion Lib/tarfile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2532,7 +2532,8 @@ def extract(self, member, path="", set_attrs=True, *, numeric_owner=False,
tarinfo, unfiltered = self._get_extract_tarinfo(
member, filter_function, path)
if tarinfo is not None:
self._extract_one(tarinfo, path, set_attrs, numeric_owner)
self._extract_one(tarinfo, path, set_attrs, numeric_owner,
filter_function=filter_function)

def _get_extract_tarinfo(self, member, filter_function, path):
"""Get (filtered, unfiltered) TarInfos from *member*
Expand Down
92 changes: 92 additions & 0 deletions Lib/test/test_tarfile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4515,6 +4515,98 @@ def test_chmod_outside_dir(self):
st_mode = cc.outerdir.stat().st_mode
self.assertNotEqual(st_mode & 0o777, 0o777)

@symlink_test
@unittest.skipUnless(hasattr(os, 'chown'), "missing os.chown")
@unittest.skipUnless(hasattr(os, 'lchown'), "missing os.lchown")
@unittest.skipUnless(hasattr(os, 'geteuid'), "missing os.geteuid")
@support.subTests('link_type', (tarfile.SYMTYPE, tarfile.LNKTYPE))
def test_chown_links_on_extract(self, link_type):
with ArchiveMaker() as arc:
arc.add("test.txt",
uid=1337, gid=1337, uname="", gname="", mode='-rwxr-xr-x')
arc.add("link",
type=link_type,
linkname='test.txt',
uid=1337, gid=1337, uname="", gname="", mode='-rwxr-xr-x')

with (
os_helper.temp_dir() as tmpdir,
arc.open() as tar,
unittest.mock.patch("os.chown") as mock_chown,
unittest.mock.patch("os.lchown") as mock_lchown,
unittest.mock.patch("os.geteuid") as mock_geteuid,
):
# Set UID to 0 so chown() is attempted.
mock_geteuid.return_value = 0
tar.extract("link", path=tmpdir, filter='data')
extract_path = os.path.join(tmpdir, "link")

if link_type == tarfile.SYMTYPE:
mock_chown.assert_not_called()
mock_lchown.assert_called_once_with(extract_path, -1, -1)
else:
mock_chown.assert_has_calls([
unittest.mock.call(extract_path, -1, -1),
unittest.mock.call(extract_path, -1, -1)
])
mock_lchown.assert_not_called()

@symlink_test
@unittest.skipUnless(hasattr(os, 'chown'), "missing os.chown")
@unittest.skipUnless(hasattr(os, 'lchown'), "missing os.lchown")
@unittest.skipUnless(hasattr(os, 'geteuid'), "missing os.geteuid")
@support.subTests('link_type', (tarfile.SYMTYPE, tarfile.LNKTYPE))
def test_chown_links_on_extractall(self, link_type):
with ArchiveMaker() as arc:
arc.add("test.txt",
uid=1337, gid=1337, uname="", gname="", mode='-rwxr-xr-x')
arc.add("link",
type=link_type,
linkname='test.txt',
uid=1337, gid=1337, uname="", gname="", mode='-rwxr-xr-x')

with (
os_helper.temp_dir() as tmpdir,
arc.open() as tar,
unittest.mock.patch("os.chown") as mock_chown,
unittest.mock.patch("os.lchown") as mock_lchown,
unittest.mock.patch("os.geteuid") as mock_geteuid,
):
# Set UID to 0 so chown() is attempted.
mock_geteuid.return_value = 0
tar.extractall(path=tmpdir, filter='data')
extract_link_path = os.path.join(tmpdir, "link")
extract_file_path = os.path.join(tmpdir, "test.txt")

if link_type == tarfile.SYMTYPE:
mock_chown.assert_called_once_with(extract_file_path, -1, -1)
mock_lchown.assert_called_once_with(extract_link_path, -1, -1)
else:
mock_chown.assert_has_calls([
unittest.mock.call(extract_file_path, -1, -1),
unittest.mock.call(extract_link_path, -1, -1)
])
mock_lchown.assert_not_called()

def test_extract_filters_target(self):
# Test that when extract() falls back to extracting (rather than
# linking) a hardlink target, it filters the target.
with ArchiveMaker() as arc:
arc.add("target")
arc.add("link", hardlink_to="target")
def testing_filter(member, path):
if member.name == 'target':
# target: set read-only
return member.replace(mode=stat.S_IRUSR)
# link: don't overwrite the mode
return member.replace(mode=None)
tempdir = pathlib.Path(TEMPDIR) / 'extract'
with os_helper.temp_dir(tempdir), arc.open() as tar:
tar.extract("link", path=tempdir, filter=testing_filter)
path = tempdir / 'link'
if os_helper.can_chmod():
self.assertFalse(path.stat().st_mode & stat.S_IWUSR)

def test_link_fallback_normalizes(self):
# Make sure hardlink fallbacks work for non-normalized paths for all
# filters
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Library/2026-06-23-14-19-30.gh-issue-151987.8mNIMf.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
The :meth:`tarfile.TarFile.extract` method now applies the given filter when
it extracts a link target from the archive as a fallback.
Loading