gh-136170: Revert adding ZipFile.data_offset (GH-136950)

emmatyping · gpshead · web-flow · commit 6bf1c0ab3497 · 2025-07-21T23:16:30.000Z
* Revert "gh-84481: Make ZipFile.data_offset more robust (#132178)" This reverts commit 6cd1d6c. * Revert "gh-84481: Add ZipFile.data_offset attribute (#132165)" This reverts commit 0788948. --------- Co-authored-by: Gregory P. Smith <greg@krypto.org>
diff --git a/Doc/library/zipfile.rst b/Doc/library/zipfile.rst
@@ -558,14 +558,6 @@ The following data attributes are also available:
    it should be no longer than 65535 bytes.  Comments longer than this will be
    truncated.
 
-.. attribute:: ZipFile.data_offset
-
-   The offset to the start of ZIP data from the beginning of the file. When the
-   :class:`ZipFile` is opened in either mode ``'w'`` or ``'x'`` and the
-   underlying file does not support ``tell()``, the value will be ``None``
-   instead.
-
-   .. versionadded:: 3.14
 
 .. _path-objects:
 
diff --git a/Lib/test/test_zipfile/test_core.py b/Lib/test/test_zipfile/test_core.py
@@ -3470,60 +3470,6 @@ def test_execute_zip64(self):
         self.assertIn(b'number in executable: 5', output)
 
 
-class TestDataOffsetPrependedZip(unittest.TestCase):
-    """Test .data_offset on reading zip files with an executable prepended."""
-
-    def setUp(self):
-        self.exe_zip = findfile('exe_with_zip', subdir='archivetestdata')
-        self.exe_zip64 = findfile('exe_with_z64', subdir='archivetestdata')
-
-    def _test_data_offset(self, name):
-        with zipfile.ZipFile(name) as zipfp:
-            self.assertEqual(zipfp.data_offset, 713)
-
-    def test_data_offset_with_exe_prepended(self):
-        self._test_data_offset(self.exe_zip)
-
-    def test_data_offset_with_exe_prepended_zip64(self):
-        self._test_data_offset(self.exe_zip64)
-
-class TestDataOffsetZipWrite(unittest.TestCase):
-    """Test .data_offset for ZipFile opened in write mode."""
-
-    def setUp(self):
-        os.mkdir(TESTFNDIR)
-        self.addCleanup(rmtree, TESTFNDIR)
-        self.test_path = os.path.join(TESTFNDIR, 'testoffset.zip')
-
-    def test_data_offset_write_no_prefix(self):
-        with io.BytesIO() as fp:
-            with zipfile.ZipFile(fp, "w") as zipfp:
-                self.assertEqual(zipfp.data_offset, 0)
-
-    def test_data_offset_write_with_prefix(self):
-        with io.BytesIO() as fp:
-            fp.write(b"this is a prefix")
-            with zipfile.ZipFile(fp, "w") as zipfp:
-                self.assertEqual(zipfp.data_offset, 16)
-
-    def test_data_offset_append_with_bad_zip(self):
-        with io.BytesIO() as fp:
-            fp.write(b"this is a prefix")
-            with zipfile.ZipFile(fp, "a") as zipfp:
-                self.assertEqual(zipfp.data_offset, 16)
-
-    def test_data_offset_write_no_tell(self):
-        # The initializer in ZipFile checks if tell raises AttributeError or
-        # OSError when creating a file in write mode when deducing the offset
-        # of the beginning of zip data
-        class NoTellBytesIO(io.BytesIO):
-            def tell(self):
-                raise OSError("Unimplemented!")
-        with NoTellBytesIO() as fp:
-            with zipfile.ZipFile(fp, "w") as zipfp:
-                self.assertIsNone(zipfp.data_offset)
-
-
 class EncodedMetadataTests(unittest.TestCase):
     file_names = ['\u4e00', '\u4e8c', '\u4e09']  # Han 'one', 'two', 'three'
     file_content = [
diff --git a/Lib/zipfile/__init__.py b/Lib/zipfile/__init__.py
@@ -1452,7 +1452,6 @@ def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True,
         self._lock = threading.RLock()
         self._seekable = True
         self._writing = False
-        self._data_offset = None
 
         try:
             if mode == 'r':
@@ -1463,7 +1462,6 @@ def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True,
                 self._didModify = True
                 try:
                     self.start_dir = self.fp.tell()
-                    self._data_offset = self.start_dir
                 except (AttributeError, OSError):
                     self.fp = _Tellable(self.fp)
                     self.start_dir = 0
@@ -1488,7 +1486,6 @@ def __init__(self, file, mode="r", compression=ZIP_STORED, allowZip64=True,
                     # even if no files are added to the archive
                     self._didModify = True
                     self.start_dir = self.fp.tell()
-                    self._data_offset = self.start_dir
             else:
                 raise ValueError("Mode must be 'r', 'w', 'x', or 'a'")
         except:
@@ -1535,10 +1532,6 @@ def _RealGetContents(self):
         # self.start_dir:  Position of start of central directory
         self.start_dir = offset_cd + concat
 
-        # store the offset to the beginning of data for the
-        # .data_offset property
-        self._data_offset = concat
-
         if self.start_dir < 0:
             raise BadZipFile("Bad offset for central directory")
         fp.seek(self.start_dir, 0)
@@ -1599,12 +1592,6 @@ def _RealGetContents(self):
             zinfo._end_offset = end_offset
             end_offset = zinfo.header_offset
 
-    @property
-    def data_offset(self):
-        """The offset to the start of zip data in the file or None if
-        unavailable."""
-        return self._data_offset
-
     def namelist(self):
         """Return a list of file names in the archive."""
         return [data.filename for data in self.filelist]
diff --git a/Misc/NEWS.d/next/Library/2025-07-21-22-35-50.gh-issue-136170.QUlc78.rst b/Misc/NEWS.d/next/Library/2025-07-21-22-35-50.gh-issue-136170.QUlc78.rst
@@ -0,0 +1,3 @@
+Removed the unreleased ``zipfile.ZipFile.data_offset`` property added in 3.14.0a7
+as it wasn't fully clear which behavior it should have in some situations so
+the result was not always what a user might expect.

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,3 @@`
	`1`	+Removed the unreleased ``zipfile.ZipFile.data_offset`` property added in 3.14.0a7
	`2`	`+as it wasn't fully clear which behavior it should have in some situations so`
	`3`	`+the result was not always what a user might expect.`