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
(cherry picked from commit 22748a83d927d3da1beaed771be30887c42b2500)

Co-authored-by: Artem Bulgakov <ArtemSBulgakov@ya.ru>

diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index 7a69e1b1aa54404ebb309073a950398926cf393f..39f63b9cfc1ac90baec69c64b7d1ab919808aa0a 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 b512168d6ea87017d1acd602f281d25b681d4054..be717e315700ca639507b58fa56ff55b6161a329 100644 (file)
--- a/Lib/test/test_tarfile.py
+++ b/Lib/test/test_tarfile.py
@@ -1384,12 +1384,15 @@ 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
 
@@ -1432,8 +1435,17 @@ 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 35cabc7248bb427e7aa7e97e8f06959f8bd3974e..b0246402c354df463484dd909b7c84faef06de96 100644 (file)
--- a/Misc/ACKS
+++ b/Misc/ACKS
@@ -237,6 +237,7 @@ 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