python312/CVE-2024-8088-inf-loop-zipfile_Path.patch

---
 Lib/test/test_zipfile/_path/test_path.py                                |   78 ++++++++++
 Lib/zipfile/_path/__init__.py                                           |   18 ++
 Misc/NEWS.d/next/Library/2024-08-11-14-08-04.gh-issue-122905.7tDsxA.rst |    1 
 Misc/NEWS.d/next/Library/2024-08-26-13-45-20.gh-issue-123270.gXHvNJ.rst |    3 
 4 files changed, 98 insertions(+), 2 deletions(-)

--- a/Lib/test/test_zipfile/_path/test_path.py
+++ b/Lib/test/test_zipfile/_path/test_path.py
@@ -4,6 +4,7 @@ import contextlib
 import pathlib
 import pickle
 import sys
+import time
 import unittest
 import zipfile
 
@@ -577,3 +578,80 @@ class TestPath(unittest.TestCase):
         zipfile.Path(alpharep)
         with self.assertRaises(KeyError):
             alpharep.getinfo('does-not-exist')
+
+    def test_malformed_paths(self):
+        """
+        Path should handle malformed paths gracefully.
+
+        Paths with leading slashes are not visible.
+
+        Paths with dots are treated like regular files.
+        """
+        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())) == ['../']
+        assert root.joinpath('..').joinpath('parent.txt').read_bytes() == b'content'
+
+    def test_unsupported_names(self):
+        """
+        Path segments with special characters are readable.
+
+        On some platforms or file systems, characters like
+        ``:`` and ``?`` are not allowed, but they are valid
+        in the zip file.
+        """
+        data = io.BytesIO()
+        zf = zipfile.ZipFile(data, "w")
+        zf.writestr("path?", b"content")
+        zf.writestr("V: NMS.flac", b"fLaC...")
+        zf.filename = ''
+        root = zipfile.Path(zf)
+        contents = root.iterdir()
+        assert next(contents).name == 'path?'
+        assert next(contents).name == 'V: NMS.flac'
+        assert root.joinpath('V: NMS.flac').read_bytes() == b"fLaC..."
+
+    def test_backslash_not_separator(self):
+        """
+        In a zip file, backslashes are not separators.
+        """
+        data = io.BytesIO()
+        zf = zipfile.ZipFile(data, "w")
+        zf.writestr(DirtyZipInfo.for_name("foo\\bar", zf), b"content")
+        zf.filename = ''
+        root = zipfile.Path(zf)
+        (first,) = root.iterdir()
+        assert not first.is_dir()
+        assert first.name == 'foo\\bar'
+
+
+class DirtyZipInfo(zipfile.ZipInfo):
+    """
+    Bypass name sanitization.
+    """
+
+    def __init__(self, filename, *args, **kwargs):
+        super().__init__(filename, *args, **kwargs)
+        self.filename = filename
+
+    @classmethod
+    def for_name(cls, name, archive):
+        """
+        Construct the same way that ZipFile.writestr does.
+
+        TODO: extract this functionality and re-use
+        """
+        self = cls(filename=name, date_time=time.localtime(time.time())[:6])
+        self.compress_type = archive.compression
+        self.compress_level = archive.compresslevel
+        if self.filename.endswith('/'):  # pragma: no cover
+            self.external_attr = 0o40775 << 16  # drwxrwxr-x
+            self.external_attr |= 0x10  # MS-DOS directory flag
+        else:
+            self.external_attr = 0o600 << 16  # ?rw-------
+        return self
--- a/Lib/zipfile/_path/__init__.py
+++ b/Lib/zipfile/_path/__init__.py
@@ -1,3 +1,12 @@
+"""
+A Path-like interface for zipfiles.
+
+This codebase is shared between zipfile.Path in the stdlib
+and zipp in PyPI. See
+https://github.com/python/importlib_metadata/wiki/Development-Methodology
+for more detail.
+"""
+
 import io
 import posixpath
 import zipfile
@@ -34,7 +43,7 @@ def _parents(path):
 def _ancestry(path):
     """
     Given a path with elements separated by
-    posixpath.sep, generate all elements of that path
+    posixpath.sep, generate all elements of that path.
 
     >>> list(_ancestry('b/d'))
     ['b/d', 'b']
@@ -46,9 +55,14 @@ def _ancestry(path):
     ['b']
     >>> list(_ancestry(''))
     []
+
+    Multiple separators are treated like a single.
+
+    >>> list(_ancestry('//b//d///f//'))
+    ['//b//d///f', '//b//d', '//b']
     """
     path = path.rstrip(posixpath.sep)
-    while path and path != posixpath.sep:
+    while path.rstrip(posixpath.sep):
         yield path
         path, tail = posixpath.split(path)
 
--- /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.
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2024-08-26-13-45-20.gh-issue-123270.gXHvNJ.rst
@@ -0,0 +1,3 @@
+Applied a more surgical fix for malformed payloads in :class:`zipfile.Path`
+causing infinite loops (gh-122905) without breaking contents using
+legitimate characters.