mirror of https://github.com/python/cpython
[3.13] gh-122905: Sanitize names in zipfile.Path. (GH-122906) (#122922)
This commit is contained in:
parent
1788eb786b
commit
8c7348939d
|
@ -577,3 +577,20 @@ class TestPath(unittest.TestCase):
|
||||||
zipfile.Path(alpharep)
|
zipfile.Path(alpharep)
|
||||||
with self.assertRaises(KeyError):
|
with self.assertRaises(KeyError):
|
||||||
alpharep.getinfo('does-not-exist')
|
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',
|
||||||
|
]
|
||||||
|
|
|
@ -85,7 +85,69 @@ class InitializedState:
|
||||||
super().__init__(*args, **kwargs)
|
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
|
A ZipFile subclass that ensures that implied directories
|
||||||
are always included in the namelist.
|
are always included in the namelist.
|
||||||
|
|
|
@ -0,0 +1 @@
|
||||||
|
:class:`zipfile.Path` objects now sanitize names from the zipfile.
|
Loading…
Reference in New Issue