https://github.com/python/cpython/commit/8c7348939d8a3ecd79d630075f6be1b0c5b41f64
commit: 8c7348939d8a3ecd79d630075f6be1b0c5b41f64
branch: 3.13
author: Miss Islington (bot) <[email protected]>
committer: jaraco <[email protected]>
date: 2024-08-11T20:35:04-04:00
summary:
[3.13] gh-122905: Sanitize names in zipfile.Path. (GH-122906) (#122922)
files:
A Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
M Lib/test/test_zipfile/_path/test_path.py
M Lib/zipfile/_path/__init__.py
diff --git a/Lib/test/test_zipfile/_path/test_path.py
b/Lib/test/test_zipfile/_path/test_path.py
index 99842ffd63a64e..4a31caee0b81fa 100644
--- a/Lib/test/test_zipfile/_path/test_path.py
+++ b/Lib/test/test_zipfile/_path/test_path.py
@@ -577,3 +577,20 @@ 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',
+ ]
diff --git a/Lib/zipfile/_path/__init__.py b/Lib/zipfile/_path/__init__.py
index f5ea18cee61930..0f1814735cb78b 100644
--- a/Lib/zipfile/_path/__init__.py
+++ b/Lib/zipfile/_path/__init__.py
@@ -85,7 +85,69 @@ 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.
diff --git
a/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
new file mode 100644
index 00000000000000..1be44c906c4f30
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst
@@ -0,0 +1 @@
+:class:`zipfile.Path` objects now sanitize names from the zipfile.
_______________________________________________
Python-checkins mailing list -- [email protected]
To unsubscribe send an email to [email protected]
https://mail.python.org/mailman3/lists/python-checkins.python.org/
Member address: [email protected]
