[3.9] gh-123270: Replaced SanitizedNames with a more surgical fix. (GH-123354) (...

Applies changes from zipp 3.20.1 and jaraco/zippGH-124
(cherry picked from commit 2231286d78d328c2f575e0b05b16fe447d1656d6)
(cherry picked from commit 17b77bb41409259bad1cd6c74761c18b6ab1e860)

Co-authored-by: Jason R. Coombs <jaraco@jaraco.com>

diff --git a/Lib/test/test_zipfile.py b/Lib/test/test_zipfile.py
index 17e95eb86239a5eb1b7b003bd2b6bd9e6a7dd877..5809b2c00060a60a2c9ca287e08f1a58c36fe545 100644 (file)
--- a/Lib/test/test_zipfile.py
+++ b/Lib/test/test_zipfile.py
@@ -3054,6 +3054,83 @@ class TestPath(unittest.TestCase):
         data = ['/'.join(string.ascii_lowercase + str(n)) for n in range(10000)]
         zipfile.CompleteDirs._implied_dirs(data)
 
+    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
+
 
 if __name__ == "__main__":
     unittest.main()

diff --git a/Lib/zipfile.py b/Lib/zipfile.py
index 95f95ee112667a23ccd5989977754058dffc8bd2..68d643ddbdd8e6ab00a224be0ac5b8afb3dff6a8 100644 (file)
--- a/Lib/zipfile.py
+++ b/Lib/zipfile.py
@@ -2146,7 +2146,7 @@ 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']
@@ -2158,9 +2158,14 @@ 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)
 

diff --git a/Misc/NEWS.d/next/Library/2024-08-26-13-45-20.gh-issue-123270.gXHvNJ.rst b/Misc/NEWS.d/next/Library/2024-08-26-13-45-20.gh-issue-123270.gXHvNJ.rst
new file mode 100644 (file)
index 0000000..ee9fde6
--- /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.