How can I extract from hashlib.sha256 in Python?

Question

A naive attempt fails:

import hashlib

class fred(hashlib.sha256):
    pass

-> TypeError: Error when calling the metaclass bases
       cannot create 'builtin_function_or_method' instances

Well, it turns out that hashlib.sha256 is a callable, not a class. Trying something more creative doesn't work either:

 import hashlib

 class fred(type(hashlib.sha256())):
     pass

 f = fred

 -> TypeError: cannot create 'fred' instances

Hmmm ...

So how do I do this?

Here is what I really want to achieve:

class shad_256(sha256):
    """Double SHA - sha256(sha256(data).digest())
Less susceptible to length extension attacks than sha256 alone."""
    def digest(self):
        return sha256(sha256.digest(self)).digest()
    def hexdigest(self):
        return sha256(sha256.digest(self)).hexdigest()

Basically, I want everything to go away, except when someone requires a result, I want to add an extra step. Is there any reasonable way to do this using __new__some kind of metaclass magic?

, , , , - - . , ( update), .

: :

# test_sha._timehash takes three parameters, the hash object generator to use,
# the number of updates and the size of the updates.

# Built in hashlib.sha256
$ python2.7 -m timeit -n 100 -s 'import test_sha, hashlib' 'test_sha._timehash(hashlib.sha256, 20000, 512)'
100 loops, best of 3: 104 msec per loop

# My wrapper based approach (see my answer)
$ python2.7 -m timeit -n 100 -s 'import test_sha, hashlib' 'test_sha._timehash(test_sha.wrapper_shad_256, 20000, 512)'
100 loops, best of 3: 108 msec per loop

# Glen Maynard getattr based approach
$ python2.7 -m timeit -n 100 -s 'import test_sha, hashlib' 'test_sha._timehash(test_sha.getattr_shad_256, 20000, 512)'
100 loops, best of 3: 103 msec per loop

Answer 1

__getattr__, , , :

import hashlib

class shad_256(object):
    """
    Double SHA - sha256(sha256(data).digest())
    Less susceptible to length extension attacks than sha256 alone.

    >>> s = shad_256('hello world')
    >>> s.digest_size
    32
    >>> s.block_size
    64
    >>> s.sha256.hexdigest()
    'b94d27b9934d3e08a52e52d7da7dabfac484efe37a5380ee9088f7ace2efcde9'
    >>> s.hexdigest()
    'bc62d4b80d9e36da29c16c5d4d9f11731f36052c72401a76c23c0fb5a9b74423'
    >>> s.nonexistant()
    Traceback (most recent call last):
    ...
    AttributeError: '_hashlib.HASH' object has no attribute 'nonexistant'
    >>> s2 = s.copy()
    >>> s2.digest() == s.digest()
    True
    >>> s2.update("text")
    >>> s2.digest() == s.digest()
    False
    """
    def __init__(self, data=None):
        self.sha256 = hashlib.sha256()
        if data is not None:
            self.update(data)

    def __getattr__(self, key):
        return getattr(self.sha256, key)

    def _get_final_sha256(self):
        return hashlib.sha256(self.sha256.digest())

    def digest(self):
        return self._get_final_sha256().digest()

    def hexdigest(self):
        return self._get_final_sha256().hexdigest()

    def copy(self):
        result = shad_256()
        result.sha256 = self.sha256.copy()
        return result

if __name__ == "__main__":
    import doctest
    doctest.testmod()

update, . , __init__ ( copy):

self.update = self.sha256.update

__getattr__ update.

- Python: . , :

a = "hello"
b = a.upper
b()

- , . , __getattr__ self.sha256.update, self.sha256, self.

Answer 2

, , hashlib.sha256 var init, , - , -.

- :

import hashlib

class MyThing(object):
    def __init__(self):
        self._hasher = hashlib.sha256()

    def digest(self):
        return self._hasher.digest()

.

Answer 3

, , , , :

import hashlib

class _double_wrapper(object):
    """This wrapper exists because the various hashes from hashlib are
    factory functions and there is no type that can be derived from.
    So this class simulates deriving from one of these factory
    functions as if it were a class and then implements the 'd'
    version of the hash function which avoids length extension attacks
    by applying H(H(text)) instead of just H(text)."""

    __slots__ = ('_wrappedinstance', '_wrappedfactory', 'update')
    def __init__(self, wrappedfactory, *args):
        self._wrappedfactory = wrappedfactory
        self._assign_instance(wrappedfactory(*args))

    def _assign_instance(self, instance):
        "Assign new wrapped instance and set update method."
        self._wrappedinstance = instance
        self.update = instance.update

    def digest(self):
        "return the current digest value"
        return self._wrappedfactory(self._wrappedinstance.digest()).digest()

    def hexdigest(self):
        "return the current digest as a string of hexadecimal digits"
        return self._wrappedfactory(self._wrappedinstance.digest()).hexdigest()

    def copy(self):
        "return a copy of the current hash object"
        new = self.__class__()
        new._assign_instance(self._wrappedinstance.copy())
        return new

    digest_size = property(lambda self: self._wrappedinstance.digest_size,
                           doc="number of bytes in this hashes output")
    digestsize = digest_size
    block_size = property(lambda self: self._wrappedinstance.block_size,
                          doc="internal block size of hash function")

class shad_256(_double_wrapper):
    """
    Double SHA - sha256(sha256(data))
    Less susceptible to length extension attacks than SHA2_256 alone.

    >>> import binascii
    >>> s = shad_256('hello world')
    >>> s.name
    'shad256'
    >>> int(s.digest_size)
    32
    >>> int(s.block_size)
    64
    >>> s.hexdigest()
    'bc62d4b80d9e36da29c16c5d4d9f11731f36052c72401a76c23c0fb5a9b74423'
    >>> binascii.hexlify(s.digest()) == s.hexdigest()
    True
    >>> s2 = s.copy()
    >>> s2.digest() == s.digest()
    True
    >>> s2.update("text")
    >>> s2.digest() == s.digest()
    False
    """
    __slots__ = ()
    def __init__(self, *args):
        super(shad_256, self).__init__(hashlib.sha256, *args)
    name = property(lambda self: 'shad256', doc='algorithm name')

, , . Glen update , .

, , update docstring. , /, .

Answer 4

from hashlib import sha256

class shad_256(object):
    def __init__(self, data=''):
        self._hash = sha256(data)

    def __getattr__(self, attr):
        setattr(self, attr, getattr(self._hash, attr))
        return getattr(self, attr)

    def copy(self):
        ret = shad_256()
        ret._hash = self._hash.copy()
        return ret

    def digest(self):
        return sha256(self._hash.digest()).digest()

    def hexdigest(self):
        return sha256(self._hash.digest()).hexdigest()

, , __getattr__. copy() , .