aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--Lib/test/test_zipfile.py17
-rw-r--r--Lib/zipfile.py61
2 files changed, 77 insertions, 1 deletions
diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
index 32c01704d9d..a60dc11688d 100644
--- a/Lib/test/test_zipfile.py
+++ b/Lib/test/test_zipfile.py
@@ -3280,6 +3280,23 @@ with zipfile.ZipFile(io.BytesIO(), "w") as zf:
zipfile.Path(zf)
zf.extractall(source_path.parent)
+ 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',
+ ]
+
class StripExtraTests(unittest.TestCase):
# Note: all of the "z" characters are technically invalid, but up
diff --git a/Lib/zipfile.py b/Lib/zipfile.py
index 7d18bc2479f..cbac8d9160e 100644
--- a/Lib/zipfile.py
+++ b/Lib/zipfile.py
@@ -9,6 +9,7 @@ import io
import itertools
import os
import posixpath
+import re
import shutil
import stat
import struct
@@ -2182,7 +2183,65 @@ 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.