gh-152140: Reimplement _Extra to support .strip() and .iter()

Rework `_Extra` to keep the original `.strip()` behavior, to prevent
altering existing callers.

Add `.iter()` in place of `.strip()` to yield each subfield as tuples.
This has better semantic and is proved to be more performant than
subclassing `bytes` by benchmark.  The method name change also allows
feature detection for the behavior changes.  Also refactor
`ZipFile._decodeExtra` with this method.

Author: danny0838

Lib/test/test_zipfile/test_core.py

@@ -5840,7 +5840,7 @@ class StripExtraTests(unittest.TestCase):
 
     ZIP64_EXTRA = 1
 
-    strip_extra = staticmethod(zipfile._strip_extra_fields)
+    strip_extra = staticmethod(zipfile._Extra.strip)
 
     def test_no_data(self):
         s = struct.Struct("<HH")

Lib/zipfile/__init__.py

@@ -194,6 +194,34 @@ class LargeZipFile(Exception):
 
 _DD_SIGNATURE = 0x08074b50
 
+
+class _Extra:
+    @classmethod
+    def iter(cls, data):
+        """Iter through all subfields."""
+        # early return for empty extra data
+        if not data:
+            return
+
+        pos, data_len = 0, len(data)
+        while pos < data_len:
+            try:
+                xid, xlen = struct.unpack_from('<HH', data, pos)
+            except struct.error:
+                xid, xlen = None, 0
+            yield data[pos:pos + 4 + xlen], xid, xlen
+            pos += 4 + xlen
+
+    @classmethod
+    def strip(cls, data, xids):
+        """Remove Extra fields with specified IDs."""
+        result = b''
+        for xfield, xid, _ in cls.iter(data):
+            if xid not in xids:
+                result += xfield
+        return result
+
+
 def _check_zipfile(fp):
     try:
         endrec = _EndRecData(fp)
@@ -390,27 +418,6 @@ def _read_local_file_header(fp):
         raise BadZipFile("Bad magic number for file header")
     return fheader
 
-def _strip_extra_fields(data, field_ids):
-    """Remove Extra fields with specified IDs and return a bytearray."""
-    result = bytearray()
-
-    # early return for empty extra data
-    if not data:
-        return result
-
-    data_len = len(data)
-    pos = 0
-    while pos < data_len:
-        try:
-            xid, xlen = struct.unpack_from('<HH', data, pos)
-        except struct.error:
-            xid, xlen = None, 0
-        if xid not in field_ids:
-            result.extend(data[pos:pos + 4 + xlen])
-        pos += 4 + xlen
-
-    return result
-
 
 class ZipInfo:
     """Class with attributes describing each file in the ZIP archive."""
@@ -569,11 +576,9 @@ def _encodeFilenameFlags(self):
 
     def _decodeExtra(self, filename_crc):
         # Try to decode the extra field.
-        extra = self.extra
         unpack = struct.unpack
-        while len(extra) >= 4:
-            tp, ln = unpack('<HH', extra[:4])
-            if ln+4 > len(extra):
+        for extra, tp, ln in _Extra.iter(self.extra):
+            if ln > len(extra):
                 raise BadZipFile("Corrupt extra field %04x (size=%d)" % (tp, ln))
             if tp == 0x0001:
                 data = extra[4:ln+4]
@@ -610,8 +615,6 @@ def _decodeExtra(self, filename_crc):
                 except UnicodeDecodeError as e:
                     raise BadZipFile('Corrupt unicode path extra field (0x7075): invalid utf-8 bytes') from e
 
-            extra = extra[ln+4:]
-
     @classmethod
     def from_file(cls, filename, arcname=None, *, strict_timestamps=True):
         """Construct an appropriate ZipInfo for a file on the filesystem.
@@ -2650,10 +2653,10 @@ def _write_end_record(self):
             min_version = 0
             if extra:
                 # Prepend a ZIP64 field to the extra's
+                extra_data = _Extra.strip(extra_data, (1,))
                 extra_data = struct.pack(
                     '<HH' + 'Q'*len(extra),
-                    1, 8*len(extra), *extra
-                ) + _strip_extra_fields(extra_data, (1,))
+                    1, 8*len(extra), *extra) + extra_data
 
                 min_version = ZIP64_VERSION
 

Misc/NEWS.d/next/Core_and_Builtins/2026-06-25-00-41-52.gh-issue-152140.u0phBe.rst

@@ -1 +1,4 @@
-Replace :class:`!_Extra` with :func:`!_strip_extra_fields` in the :mod:`zipfile` module.
+Rework :class:`!_Extra` in the :mod:`zipfile` module::
+* Improve performance for the mostly used :meth:`!_Extra.strip`.
+* Replace :meth:`!_Extra.split` with :meth:`!_Extra.iter` for better semantic and performance.
+* Make it a namespace class rather than a subclass of :class:`bytes`.