[3.14] gh-157265: tarfile: Honor None result of filter for link fallbacks (GH-157266) (#157307)

* gh-157265: tarfile: Honor None result of filter for link fallbacks (GH-157266)

(cherry picked from commit fb2f0bb)

Co-authored-by: Petr Viktorin <encukou@gmail.com>
Co-authored-by: Stan Ulbrych <stan@python.org>

* gh-157265: Adjust test for Windows (GH-157334)

gh-157266: Adjust test for Windows

On Windows (no symlinks, no hardlinks), the behaviour is
the same as without the fix in GH-157266:
- a/t/dummy is extracted
- b/ is extracted
- c/ is *not* created (the target, a/t, is not in the archive)
- c/escape: c/ is created; escape is skipped (target,
   c/../../link_here, is not in archive)
- c is not recreated as a directory
- boom is not created (target is c/escape, which falls back to
  ..\..\link_here, which does not exist in archive)

---------

Co-authored-by: Petr Viktorin <encukou@gmail.com>
Co-authored-by: Stan Ulbrych <stan@python.org>

Author: 3 people

Lib/tarfile.py

@@ -2827,9 +2827,11 @@ def makelink_with_filter(self, tarinfo, targetpath,
                     "makelink_with_filter: if filter_function is not None, "
                     + "extraction_root must also not be None")
             try:
-                filter_function(
+                filtered = filter_function(
                     unfiltered.replace(name=tarinfo.name, deep=False),
                     extraction_root)
+                if filtered is None:
+                    return
                 filtered = filter_function(unfiltered, extraction_root)
             except _FILTER_ERRORS as cause:
                 raise LinkFallbackError(tarinfo, unfiltered.name) from cause

Lib/test/test_tarfile.py

@@ -4451,9 +4451,15 @@ def test_sneaky_hardlink_fallback(self):
         for filter in 'tar', 'fully_trusted':
             with self.subTest(filter), self.check_context(arc.open(), filter):
                 if not os_helper.can_symlink():
-                    self.expect_file("a/t/dummy")
-                    self.expect_file("b/")
-                    self.expect_file("c/")
+                    if filter == 'fully_trusted' or sys.platform == "win32":
+                        self.expect_file("a/t/dummy")
+                        self.expect_file("b/")
+                        self.expect_file("c/")
+                    else:
+                        self.expect_exception(
+                            tarfile.LinkFallbackError,
+                            "link 'boom' would be extracted as a copy of "
+                            + "'c/escape', which was rejected")
                 else:
                     self.expect_file("a/t/dummy")
                     self.expect_file("b/")
@@ -4650,6 +4656,25 @@ def testing_filter(member, path):
             if os_helper.can_chmod():
                 self.assertFalse(path.stat().st_mode & stat.S_IWUSR)
 
+    @symlink_test
+    def test_extract_filters_target_none(self):
+        # Test that when extract() falls back to extracting (rather than
+        # linking) a hardlink target, the member is skipped if the filter
+        # returns None.
+        with ArchiveMaker() as arc:
+            arc.add('a/b/s', symlink_to='../escape')
+            arc.add('q', hardlink_to='a/b/s')
+        def filter_unsafe_members(member, path):
+            try:
+                return tarfile.data_filter(member, path)
+            except tarfile.FilterError as error:
+                return None
+        with self.check_context(arc.open(), filter_unsafe_members):
+            if os_helper.can_symlink():
+                self.expect_file('a/b/s', symlink_to='../escape')
+            else:
+                self.expect_file('a/b/')  # symlink is not extracted
+
     def test_link_fallback_normalizes(self):
         # Make sure hardlink fallbacks work for non-normalized paths for all
         # filters

Misc/NEWS.d/next/Security/2026-09-10-13-38-11.gh-issue-157265.-vYuMp.rst

@@ -0,0 +1,3 @@
+In :mod:`tarfile`, when extracting a link falls back to extracting a member
+of the archive, skip the member when the filter function returns None when
+called with the extracted member's name replaced with the link's.