gh-128646: Implement GzipFile.readinto() functions

Lib/gzip.py

@@ -338,6 +338,20 @@ def read1(self, size=-1):
             size = io.DEFAULT_BUFFER_SIZE
         return self._buffer.read1(size)
 
+    def readinto(self, b):
+        self._check_not_closed()
+        if self.mode != READ:
+            import errno
+            raise OSError(errno.EBADF, "readinto() on write-only GzipFile object")
+        return self._buffer.readinto(b)
+
+    def readinto1(self, b):
+        self._check_not_closed()
+        if self.mode != READ:
+            import errno
+            raise OSError(errno.EBADF, "readinto1() on write-only GzipFile object")
+        return self._buffer.readinto1(b)
+
     def peek(self, n):
         self._check_not_closed()
         if self.mode != READ:

Lib/test/test_gzip.py

@@ -141,6 +141,38 @@ def test_read1(self):
                 self.assertEqual(f.tell(), nread)
         self.assertEqual(b''.join(blocks), data1 * 50)
 
+    def test_readinto(self):
+        # 10MB of uncompressible data to ensure multiple reads
+        large_data = os.urandom(10 * 2**20)
+        with gzip.GzipFile(self.filename, 'wb') as f:
+            f.write(large_data)
+
+        buf = bytearray(len(large_data))
+        with gzip.GzipFile(self.filename, 'r') as f:
+            nbytes = f.readinto(buf)
+        self.assertEqual(nbytes, len(large_data))
+        self.assertEqual(buf, large_data)
+
+    def test_readinto1(self):
+        # 10MB of uncompressible data to ensure multiple reads
+        large_data = os.urandom(10 * 2**20)
+        with gzip.GzipFile(self.filename, 'wb') as f:
+            f.write(large_data)
+
+        nread = 0
+        buf = bytearray(len(large_data))
+        memview = memoryview(buf)  # Simplifies slicing
+        with gzip.GzipFile(self.filename, 'r') as f:
+            for count in range(200):
+                nbytes = f.readinto1(memview[nread:])
+                if not nbytes:
+                    break
+                nread += nbytes
+                self.assertEqual(f.tell(), nread)
+        self.assertEqual(buf, large_data)
+        # readinto1() should require multiple loops
+        self.assertGreater(count, 1)
+
     @bigmemtest(size=_4G, memuse=1)
     def test_read_large(self, size):
         # Read chunk size over UINT_MAX should be supported, despite zlib's

Misc/NEWS.d/next/Library/2025-01-08-15-14-17.gh-issue-128647.GabglU.rst

@@ -0,0 +1,4 @@
+Eagerly write to buffers passed to :class:`gzip.GzipFile`'s
+:meth:`~io.BufferedIOBase.readinto` and
+:meth:`~io.BufferedIOBase.readinto1` implementations,
+avoiding unnecessary allocations. Patch by Chris Markiewicz.