gh-94199: Remove hashlib.pbkdf2_hmac() Python implementation (GH-94200)

Remove the pure Python implementation of hashlib.pbkdf2_hmac(),
deprecated in Python 3.10. Python 3.10 and newer requires OpenSSL
1.1.1 or newer (PEP 644), this OpenSSL version provides a C
implementation of pbkdf2_hmac() which is faster.

diff --git a/Doc/library/hashlib.rst b/Doc/library/hashlib.rst
index 0906ce7cb7a2d9c99c696a6a94da1730ef25a401..386541acf510ac19ae94721c0f1eb975d79e1099 100644 (file)
--- a/Doc/library/hashlib.rst
+++ b/Doc/library/hashlib.rst
@@ -300,23 +300,17 @@ include a `salt <https://en.wikipedia.org/wiki/Salt_%28cryptography%29>`_.
 
    >>> from hashlib import pbkdf2_hmac
    >>> our_app_iters = 500_000  # Application specific, read above.
-   >>> dk = pbkdf2_hmac('sha256', b'password', b'bad salt'*2, our_app_iters)
+   >>> dk = pbkdf2_hmac('sha256', b'password', b'bad salt' * 2, our_app_iters)
    >>> dk.hex()
    '15530bba69924174860db778f2c6f8104d3aaf9d26241840c8c4a641c8d000a9'
 
-   .. versionadded:: 3.4
-
-   .. note::
+   Function only available when Python is compiled with OpenSSL.
 
-      A fast implementation of *pbkdf2_hmac* is available with OpenSSL.  The
-      Python implementation uses an inline version of :mod:`hmac`. It is about
-      three times slower and doesn't release the GIL.
-
-   .. deprecated:: 3.10
+   .. versionadded:: 3.4
 
-      Slow Python implementation of *pbkdf2_hmac* is deprecated. In the
-      future the function will only be available when Python is compiled
-      with OpenSSL.
+   .. versionchanged:: 3.12
+      Function now only available when Python is built with OpenSSL. The slow
+      pure Python implementation has been removed.
 
 .. function:: scrypt(password, *, salt, n, r, p, maxmem=0, dklen=64)
 

diff --git a/Doc/whatsnew/3.12.rst b/Doc/whatsnew/3.12.rst
index e0b95999e38a925f9e9ad7179c67b0d249ab6376..0a4d49841eff8bcc0dd5c78b9baac78aff5bd29b 100644 (file)
--- a/Doc/whatsnew/3.12.rst
+++ b/Doc/whatsnew/3.12.rst
@@ -273,6 +273,12 @@ Removed
   use :func:`locale.format_string` instead.
   (Contributed by Victor Stinner in :gh:`94226`.)
 
+* :mod:`hashlib`: Remove the pure Python implementation of
+  :func:`hashlib.pbkdf2_hmac()`, deprecated in Python 3.10. Python 3.10 and
+  newer requires OpenSSL 1.1.1 (:pep:`644`): this OpenSSL version provides
+  a C implementation of :func:`~hashlib.pbkdf2_hmac()` which is faster.
+  (Contributed by Victor Stinner in :gh:`94199`.)
+
 
 Porting to Python 3.12
 ======================

diff --git a/Lib/hashlib.py b/Lib/hashlib.py
index b546a3fd795311a1cd2772cb85edcc820f0cd5c3..21b5e912f3c771a78802fd98ea6690d3af4540ea 100644 (file)
--- a/Lib/hashlib.py
+++ b/Lib/hashlib.py
@@ -65,7 +65,7 @@ algorithms_guaranteed = set(__always_supported)
 algorithms_available = set(__always_supported)
 
 __all__ = __always_supported + ('new', 'algorithms_guaranteed',
-                                'algorithms_available', 'pbkdf2_hmac', 'file_digest')
+                                'algorithms_available', 'file_digest')
 
 
 __builtin_constructor_cache = {}
@@ -180,72 +180,10 @@ except ImportError:
 try:
     # OpenSSL's PKCS5_PBKDF2_HMAC requires OpenSSL 1.0+ with HMAC and SHA
     from _hashlib import pbkdf2_hmac
+    __all__ += ('pbkdf2_hmac',)
 except ImportError:
-    from warnings import warn as _warn
-    _trans_5C = bytes((x ^ 0x5C) for x in range(256))
-    _trans_36 = bytes((x ^ 0x36) for x in range(256))
-
-    def pbkdf2_hmac(hash_name, password, salt, iterations, dklen=None):
-        """Password based key derivation function 2 (PKCS #5 v2.0)
-
-        This Python implementations based on the hmac module about as fast
-        as OpenSSL's PKCS5_PBKDF2_HMAC for short passwords and much faster
-        for long passwords.
-        """
-        _warn(
-            "Python implementation of pbkdf2_hmac() is deprecated.",
-            category=DeprecationWarning,
-            stacklevel=2
-        )
-        if not isinstance(hash_name, str):
-            raise TypeError(hash_name)
-
-        if not isinstance(password, (bytes, bytearray)):
-            password = bytes(memoryview(password))
-        if not isinstance(salt, (bytes, bytearray)):
-            salt = bytes(memoryview(salt))
-
-        # Fast inline HMAC implementation
-        inner = new(hash_name)
-        outer = new(hash_name)
-        blocksize = getattr(inner, 'block_size', 64)
-        if len(password) > blocksize:
-            password = new(hash_name, password).digest()
-        password = password + b'\x00' * (blocksize - len(password))
-        inner.update(password.translate(_trans_36))
-        outer.update(password.translate(_trans_5C))
-
-        def prf(msg, inner=inner, outer=outer):
-            # PBKDF2_HMAC uses the password as key. We can re-use the same
-            # digest objects and just update copies to skip initialization.
-            icpy = inner.copy()
-            ocpy = outer.copy()
-            icpy.update(msg)
-            ocpy.update(icpy.digest())
-            return ocpy.digest()
-
-        if iterations < 1:
-            raise ValueError(iterations)
-        if dklen is None:
-            dklen = outer.digest_size
-        if dklen < 1:
-            raise ValueError(dklen)
-
-        dkey = b''
-        loop = 1
-        from_bytes = int.from_bytes
-        while len(dkey) < dklen:
-            prev = prf(salt + loop.to_bytes(4))
-            # endianness doesn't matter here as long to / from use the same
-            rkey = from_bytes(prev)
-            for i in range(iterations - 1):
-                prev = prf(prev)
-                # rkey = rkey ^ prev
-                rkey ^= from_bytes(prev)
-            loop += 1
-            dkey += rkey.to_bytes(inner.digest_size)
-
-        return dkey[:dklen]
+    pass
+
 
 try:
     # OpenSSL's scrypt requires OpenSSL 1.1+

diff --git a/Lib/test/test_hashlib.py b/Lib/test/test_hashlib.py
index bc9407dc9e424dbf52b0aecf2a7e91554ae48fab..450dc4933f47f73c59eda3b9baa3187587f9abec 100644 (file)
--- a/Lib/test/test_hashlib.py
+++ b/Lib/test/test_hashlib.py
@@ -1096,15 +1096,7 @@ class KDFTests(unittest.TestCase):
                 iterations=1, dklen=None)
             self.assertEqual(out, self.pbkdf2_results['sha1'][0][0])
 
-    @unittest.skipIf(builtin_hashlib is None, "test requires builtin_hashlib")
-    def test_pbkdf2_hmac_py(self):
-        with warnings_helper.check_warnings():
-            self._test_pbkdf2_hmac(
-                builtin_hashlib.pbkdf2_hmac, builtin_hashes
-            )
-
-    @unittest.skipUnless(hasattr(openssl_hashlib, 'pbkdf2_hmac'),
-                     '   test requires OpenSSL > 1.0')
+    @unittest.skipIf(openssl_hashlib is None, "requires OpenSSL bindings")
     def test_pbkdf2_hmac_c(self):
         self._test_pbkdf2_hmac(openssl_hashlib.pbkdf2_hmac, openssl_md_meth_names)
 

diff --git a/Misc/NEWS.d/next/Library/2022-06-24-10-18-59.gh-issue-94199.kYOo8g.rst b/Misc/NEWS.d/next/Library/2022-06-24-10-18-59.gh-issue-94199.kYOo8g.rst
new file mode 100644 (file)
index 0000000..f3a9a35
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2022-06-24-10-18-59.gh-issue-94199.kYOo8g.rst
@@ -0,0 +1,5 @@
+:mod:`hashlib`: Remove the pure Python implementation of
+:func:`hashlib.pbkdf2_hmac()`, deprecated in Python 3.10. Python 3.10 and
+newer requires OpenSSL 1.1.1 (:pep:`644`): this OpenSSL version provides
+a C implementation of :func:`~hashlib.pbkdf2_hmac()` which is faster. Patch
+by Victor Stinner.