From 8ce97a5730eb7732a332f419a2139071405b997d Mon Sep 17 00:00:00 2001 From: Seth Michael Larson Date: Wed, 11 Mar 2026 08:47:55 -0500 Subject: [PATCH] gh-141707: Skip TarInfo DIRTYPE normalization during GNU long name handling (cherry picked from commit 42d754e34c06e57ad6b8e7f92f32af679912d8ab) Co-authored-by: Seth Michael Larson Co-authored-by: Eashwar Ranganathan --- Lib/tarfile.py | 29 ++++++++-- Lib/test/test_tarfile.py | 21 +++++++ Misc/ACKS | 1 Misc/NEWS.d/next/Library/2025-11-18-06-35-53.gh-issue-141707.DBmQIy.rst | 2 4 files changed, 49 insertions(+), 4 deletions(-) create mode 100644 Misc/NEWS.d/next/Library/2025-11-18-06-35-53.gh-issue-141707.DBmQIy.rst Index: Python-3.6.15/Lib/tarfile.py =================================================================== --- Python-3.6.15.orig/Lib/tarfile.py 2026-03-26 20:58:51.203690688 +0100 +++ Python-3.6.15/Lib/tarfile.py 2026-03-26 20:58:51.438680931 +0100 @@ -1213,6 +1213,20 @@ @classmethod def frombuf(cls, buf, encoding, errors): """Construct a TarInfo object from a 512 byte bytes object. + + To support the old v7 tar format AREGTYPE headers are + transformed to DIRTYPE headers if their name ends in '/'. + """ + return cls._frombuf(buf, encoding, errors) + + @classmethod + def _frombuf(cls, buf, encoding, errors, *, dircheck=True): + """Construct a TarInfo object from a 512 byte bytes object. + + If ``dircheck`` is set to ``True`` then ``AREGTYPE`` headers will + be normalized to ``DIRTYPE`` if the name ends in a trailing slash. + ``dircheck`` must be set to ``False`` if this function is called + on a follow-up header such as ``GNUTYPE_LONGNAME``. """ if len(buf) == 0: raise EmptyHeaderError("empty header") @@ -1243,7 +1257,7 @@ # Old V7 tar format represents a directory as a regular # file with a trailing slash. - if obj.type == AREGTYPE and obj.name.endswith("/"): + if dircheck and obj.type == AREGTYPE and obj.name.endswith("/"): obj.type = DIRTYPE # The old GNU sparse format occupies some of the unused @@ -1278,8 +1292,15 @@ """Return the next TarInfo object from TarFile object tarfile. """ + return cls._fromtarfile(tarfile) + + @classmethod + def _fromtarfile(cls, tarfile, *, dircheck=True): + """ + See dircheck documentation in _frombuf(). + """ buf = tarfile.fileobj.read(BLOCKSIZE) - obj = cls.frombuf(buf, tarfile.encoding, tarfile.errors) + obj = cls._frombuf(buf, tarfile.encoding, tarfile.errors, dircheck=dircheck) obj.offset = tarfile.fileobj.tell() - BLOCKSIZE return obj._proc_member(tarfile) @@ -1332,7 +1353,7 @@ # Fetch the next header and process it. try: - next = self.fromtarfile(tarfile) + next = self._fromtarfile(tarfile, dircheck=False) except HeaderError: raise SubsequentHeaderError("missing or bad subsequent header") @@ -1463,7 +1484,7 @@ # Fetch the next header. try: - next = self.fromtarfile(tarfile) + next = self._fromtarfile(tarfile, dircheck=False) except HeaderError: raise SubsequentHeaderError("missing or bad subsequent header") Index: Python-3.6.15/Lib/test/test_tarfile.py =================================================================== --- Python-3.6.15.orig/Lib/test/test_tarfile.py 2026-03-26 20:58:51.204212205 +0100 +++ Python-3.6.15/Lib/test/test_tarfile.py 2026-03-26 20:58:51.439644758 +0100 @@ -948,10 +948,30 @@ self.assertEqual(tarinfo.type, self.longnametype) + def test_longname_file_not_directory(self): + # Test reading a longname file and ensure it is not handled as a directory + # Issue #141707 + buf = io.BytesIO() + with tarfile.open(mode='w', fileobj=buf, format=self.format) as tar: + ti = tarfile.TarInfo() + ti.type = tarfile.AREGTYPE + ti.name = ('a' * 99) + '/' + ('b' * 3) + tar.addfile(ti) + + expected = {t.name: t.type for t in tar.getmembers()} + + buf.seek(0) + with tarfile.open(mode='r', fileobj=buf) as tar: + actual = {t.name: t.type for t in tar.getmembers()} + + self.assertEqual(expected, actual) + + class GNUReadTest(LongnameTest, ReadTest, unittest.TestCase): subdir = "gnu" longnametype = tarfile.GNUTYPE_LONGNAME + format = tarfile.GNU_FORMAT # Since 3.2 tarfile is supposed to accurately restore sparse members and # produce files with holes. This is what we actually want to test here. @@ -1006,6 +1026,7 @@ subdir = "pax" longnametype = tarfile.XHDTYPE + format = tarfile.PAX_FORMAT def test_pax_global_headers(self): tar = tarfile.open(tarname, encoding="iso8859-1") Index: Python-3.6.15/Misc/ACKS =================================================================== --- Python-3.6.15.orig/Misc/ACKS 2026-03-26 20:58:50.446887757 +0100 +++ Python-3.6.15/Misc/ACKS 2026-03-26 20:58:51.440359426 +0100 @@ -1265,6 +1265,7 @@ Shorya Raj Jeff Ramnani Bayard Randel +Eashwar Ranganathan Varpu Rantala Brodie Rao Rémi Rampin Index: Python-3.6.15/Misc/NEWS.d/next/Library/2025-11-18-06-35-53.gh-issue-141707.DBmQIy.rst =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ Python-3.6.15/Misc/NEWS.d/next/Library/2025-11-18-06-35-53.gh-issue-141707.DBmQIy.rst 2026-03-26 20:58:51.440688506 +0100 @@ -0,0 +1,2 @@ +Don't change :class:`tarfile.TarInfo` type from ``AREGTYPE`` to ``DIRTYPE`` when parsing +GNU long name or link headers.