Merge pull request #120 from jaraco/bugfix/119-malformed-paths

Sanitize malformed paths

Author: jaraco

newsfragments/119.bugfix.rst

@@ -0,0 +1 @@
+Improved handling of malformed zip files.

tests/test_path.py

@@ -571,3 +571,20 @@ def test_getinfo_missing(self, alpharep):
         zipfile.Path(alpharep)
         with self.assertRaises(KeyError):
             alpharep.getinfo('does-not-exist')
+
+    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 = zipfile.Path(zf)
+        assert list(map(str, root.iterdir())) == [
+            'one-slash.txt',
+            'two-slash.txt',
+            'parent.txt',
+        ]

zipp/__init__.py

@@ -86,7 +86,69 @@ def __setstate__(self, state):
         super().__init__(*args, **kwargs)
 
 
-class CompleteDirs(InitializedState, zipfile.ZipFile):
+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 CompleteDirs(InitializedState, SanitizedNames, zipfile.ZipFile):
     """
     A ZipFile subclass that ensures that implied directories
     are always included in the namelist.