[3.11] gh-122905: Sanitize names in zipfile.Path. (GH-122906) (#122925)

* gh-122905: Sanitize names in zipfile.Path. (#122906)

Ported from zipp 3.19.1; ref jaraco/zipp#119.

(cherry picked from commit 9cd0326310)

* [3.11] gh-122905: Sanitize names in zipfile.Path. (GH-122906)

Ported from zipp 3.19.1; ref jaraco/zippGH-119.
(cherry picked from commit 9cd0326310)

Co-authored-by: Jason R. Coombs <jaraco@jaraco.com>
This commit is contained in:
Jason R. Coombs 2024-08-19 19:28:20 -04:00 committed by GitHub
parent 8a978a75c2
commit 795f2597a4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 78 additions and 1 deletions

View file

@ -9,6 +9,7 @@ import io
import itertools
import os
import posixpath
import re
import shutil
import stat
import struct
@ -2243,7 +2244,65 @@ def _difference(minuend, subtrahend):
return itertools.filterfalse(set(subtrahend).__contains__, minuend)
class CompleteDirs(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(SanitizedNames, ZipFile):
"""
A ZipFile subclass that ensures that implied directories
are always included in the namelist.