diff -ur zipp-0.5.1.orig/test_zipp.py zipp-0.5.1/test_zipp.py --- zipp-0.5.1.orig/test_zipp.py 2019-05-17 01:34:53.000000000 +1000 +++ zipp-0.5.1/test_zipp.py 2024-09-22 18:45:15.000000000 +1000 @@ -170,3 +170,20 @@ root = zipp.Path(zipfile_abcde) assert (root / 'a').parent.at == '' assert (root / 'a' / 'b').parent.at == 'a/' + + def test_malformed_paths(self): + """ + Path should handle malformed paths. + """ + data = io.BytesIO() + zf = zipfile.ZipFile(data, "w") + zf.writestr("/one-slash.txt", b"content") + zf.writestr("//two-slash.txt", b"content") + zf.writestr("../parent.txt", b"content") + zf.filename = '' + root = zipp.Path(zf) + assert list(map(str, root.iterdir())) == [ + 'one-slash.txt', + 'two-slash.txt', + 'parent.txt', + ] diff -ur zipp-0.5.1.orig/zipp.py zipp-0.5.1/zipp.py --- zipp-0.5.1.orig/zipp.py 2019-05-17 01:34:53.000000000 +1000 +++ zipp-0.5.1/zipp.py 2024-09-22 16:33:44.000000000 +1000 @@ -7,10 +7,67 @@ import posixpath import zipfile import functools +import re __metaclass__ = type +class SanitizedNames: + """ + ZipFile mix-in to ensure names are sanitized. + """ + + def namelist(self): + return list(map(self._sanitize, super().namelist())) + + @staticmethod + def _sanitize(name): + r""" + Ensure a relative path with posix separators and no dot names. + Modeled after + https://github.com/python/cpython/blob/bcc1be39cb1d04ad9fc0bd1b9193d3972835a57c/Lib/zipfile/__init__.py#L1799-L1813 + but provides consistent cross-platform behavior. + >>> san = SanitizedNames._sanitize + >>> san('/foo/bar') + 'foo/bar' + >>> san('//foo.txt') + 'foo.txt' + >>> san('foo/.././bar.txt') + 'foo/bar.txt' + >>> san('foo../.bar.txt') + 'foo../.bar.txt' + >>> san('\\foo\\bar.txt') + 'foo/bar.txt' + >>> san('D:\\foo.txt') + 'D/foo.txt' + >>> san('\\\\server\\share\\file.txt') + 'server/share/file.txt' + >>> san('\\\\?\\GLOBALROOT\\Volume3') + '?/GLOBALROOT/Volume3' + >>> san('\\\\.\\PhysicalDrive1\\root') + 'PhysicalDrive1/root' + Retain any trailing slash. + >>> san('abc/') + 'abc/' + Raises a ValueError if the result is empty. + >>> san('../..') + Traceback (most recent call last): + ... + ValueError: Empty filename + """ + + def allowed(part): + return part and part not in {'..', '.'} + # Remove the drive letter. + # Don't use ntpath.splitdrive, because that also strips UNC paths + bare = re.sub('^([A-Z]):', r'\1', name, flags=re.IGNORECASE) + clean = bare.replace('\\', '/') + parts = clean.split('/') + joined = '/'.join(filter(allowed, parts)) + if not joined: + raise ValueError("Empty filename") + return joined + '/' * name.endswith('/') + class Path: """ A pathlib-compatible interface for zip files. @@ -165,7 +222,7 @@ return self._next(parent_at) def _names(self): - return self._add_implied_dirs(self.root.namelist()) + return self._add_implied_dirs(list(map(SanitizedNames._sanitize, self.root.namelist()))) if sys.version_info < (3,): __div__ = __truediv__