gh-117779: Fix reading duplicated entries in zipfile by name

Author: serhiy-storchaka

Lib/test/test_zipfile/test_core.py

@@ -2445,6 +2445,34 @@ def test_full_overlap(self):
             with self.assertRaisesRegex(zipfile.BadZipFile, 'File name.*differ'):
                 zipf.read('b')
 
+    @requires_zlib()
+    def test_full_overlap_same_name(self):
+        data = (
+            b'PK\x03\x04\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2\x1e'
+            b'8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00a\xed'
+            b'\xc0\x81\x08\x00\x00\x00\xc00\xd6\xfbK\\d\x0b`P'
+            b'K\x01\x02\x14\x00\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2'
+            b'\x1e8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00\x00'
+            b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00aPK'
+            b'\x01\x02\x14\x00\x14\x00\x00\x00\x08\x00\xa0lH\x05\xe2\x1e'
+            b'8\xbb\x10\x00\x00\x00\t\x04\x00\x00\x01\x00\x00\x00\x00\x00'
+            b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00aPK\x05'
+            b'\x06\x00\x00\x00\x00\x02\x00\x02\x00^\x00\x00\x00/\x00\x00'
+            b'\x00\x00\x00'
+        )
+        with zipfile.ZipFile(io.BytesIO(data), 'r') as zipf:
+            self.assertEqual(zipf.namelist(), ['a', 'a'])
+            self.assertEqual(len(zipf.infolist()), 2)
+            zi = zipf.getinfo('a')
+            self.assertEqual(zi.header_offset, 0)
+            self.assertEqual(zi.compress_size, 16)
+            self.assertEqual(zi.file_size, 1033)
+            self.assertEqual(len(zipf.read('a')), 1033)
+            self.assertEqual(len(zipf.read(zi)), 1033)
+            self.assertEqual(len(zipf.read(zipf.infolist()[1])), 1033)
+            with self.assertRaisesRegex(zipfile.BadZipFile, 'Overlapped entries'):
+                zipf.read(zipf.infolist()[0])
+
     @requires_zlib()
     def test_quoted_overlap(self):
         data = (

Lib/zipfile/__init__.py

@@ -1545,9 +1545,8 @@ def _RealGetContents(self):
                 print("total", total)
 
         end_offset = self.start_dir
-        for zinfo in sorted(self.filelist,
-                            key=lambda zinfo: zinfo.header_offset,
-                            reverse=True):
+        for zinfo in reversed(sorted(self.filelist,
+                                     key=lambda zinfo: zinfo.header_offset)):
             zinfo._end_offset = end_offset
             end_offset = zinfo.header_offset
 

Misc/NEWS.d/next/Library/2025-01-24-12-30-38.gh-issue-117779.gADGXI.rst

@@ -0,0 +1 @@
+Fix reading duplicated entries in :mod:`zipfile` by name.