From ef2227e35d1ae833b7bfa1674a45f58c732ae1a6 Mon Sep 17 00:00:00 2001
From: "Jason R. Coombs" <jaraco@jaraco.com>
Date: Wed, 27 Nov 2024 23:27:57 -0800
Subject: [PATCH 1/5] Add SanitizedNames mixin.

Upstream-Status: Backport [https://github.com/jaraco/zipp/commit/564fcc10cdbfdaecdb33688e149827465931c9e0]
CVE: CVE-2024-5569
Rebase to v3.7.0
Signed-off-by: Hongxu Jia <hongxu.jia@windriver.com>
---
 zipp.py | 62 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/zipp.py b/zipp.py
index 26b723c..8f0950f 100644
--- a/zipp.py
+++ b/zipp.py
@@ -68,6 +68,68 @@ def _difference(minuend, subtrahend):
     return itertools.filterfalse(set(subtrahend).__contains__, minuend)
 
 
+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(zipfile.ZipFile):
     """
     A ZipFile subclass that ensures that implied directories
-- 
2.25.1