bpo-41316: Make tarfile follow specs for FNAME (GH-21511)

tarfile writes full path to FNAME field of GZIP format instead of just basename if user specified absolute path. Some archive viewers may process file incorrectly. Also it creates security issue because anyone can know structure of directories on system and know username or other personal information.

RFC1952 says about FNAME:
This is the original name of the file being compressed, with any directory components removed.

So tarfile must remove directory names from FNAME and write only basename of file.

Automerge-Triggered-By: @jaraco

diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 6769066cabd6fcb2434a52126bb534f55af7fcb6..1fae29430fefffe8b522f898cc879976ffe2b1de 100755 (executable)
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -420,6 +420,8 @@ class _Stream:
         self.__write(b"\037\213\010\010" + timestamp + b"\002\377")
         if self.name.endswith(".gz"):
             self.name = self.name[:-3]
+        # Honor "directory components removed" from RFC1952
+        self.name = os.path.basename(self.name)
         # RFC1952 says we must use ISO-8859-1 for the FNAME field.
         self.__write(self.name.encode("iso-8859-1", "replace") + NUL)
 

diff --git a/Lib/test/test_tarfile.py b/Lib/test/test_tarfile.py
index 4ef20db097163629848281566caf8f3349cc194f..7b34d53d216013abd0f725d1ed13277554adf71b 100644 (file)
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -1417,12 +1417,15 @@ class WriteTest(WriteTestBase, unittest.TestCase):
                                    pax_headers={'non': 'empty'})
             self.assertFalse(f.closed)
 
+
 class GzipWriteTest(GzipTest, WriteTest):
     pass
 
+
 class Bz2WriteTest(Bz2Test, WriteTest):
     pass
 
+
 class LzmaWriteTest(LzmaTest, WriteTest):
     pass
 
@@ -1465,8 +1468,17 @@ class StreamWriteTest(WriteTestBase, unittest.TestCase):
         finally:
             os.umask(original_umask)
 
+
 class GzipStreamWriteTest(GzipTest, StreamWriteTest):
-    pass
+    def test_source_directory_not_leaked(self):
+        """
+        Ensure the source directory is not included in the tar header
+        per bpo-41316.
+        """
+        tarfile.open(tmpname, self.mode).close()
+        payload = pathlib.Path(tmpname).read_text(encoding='latin-1')
+        assert os.path.dirname(tmpname) not in payload
+
 
 class Bz2StreamWriteTest(Bz2Test, StreamWriteTest):
     decompressor = bz2.BZ2Decompressor if bz2 else None

diff --git a/Misc/ACKS b/Misc/ACKS
index a2cdeb8504059958f98e581d8ca6c03f793bff4f..8b0d7a45da16953e7cdd993a37035376a99811da 100644 (file)
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -242,6 +242,7 @@ Colm Buckley
 Erik de Bueger
 Jan-Hein Bührman
 Lars Buitinck
+Artem Bulgakov
 Dick Bulterman
 Bill Bumgarner
 Jimmy Burgett

diff --git a/Misc/NEWS.d/next/Library/2020-07-28-12-08-58.bpo-41316.bSCbK4.rst b/Misc/NEWS.d/next/Library/2020-07-28-12-08-58.bpo-41316.bSCbK4.rst
new file mode 100644 (file)
index 0000000..139a170
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2020-07-28-12-08-58.bpo-41316.bSCbK4.rst
@@ -0,0 +1 @@
+Fix the :mod:`tarfile` module to write only basename of TAR file to GZIP compression header.
\ No newline at end of file