Persisting hashlib state

I'd like to create a hashlib instance, update() it, then persist its state in some way. Later, I'd like to recreate the object using this state data, and continue to update() it. Finally, I'd like to get the hexdigest() of the total cumulative run of data. State persistence has to survive across multiple runs.

Example:

import hashlib
m = hashlib.sha1()
m.update('one')
m.update('two')
# somehow, persist the state of m here

#later, possibly in another process
# recreate m from the p开发者_JAVA百科ersisted state
m.update('three')
m.update('four')
print m.hexdigest()
# at this point, m.hexdigest() should be equal to hashlib.sha1().update('onetwothreefour').hextdigest()

EDIT:

I did not find a good way to do this with python in 2010 and ended up writing a small helper app in C to accomplish this. However, there are some great answers below that were not available or known to me at the time.

You can do it this way using ctypes, no helper app in C is needed:-

rehash.py

#! /usr/bin/env python

''' A resumable implementation of SHA-256 using ctypes with the OpenSSL crypto library

    Written by PM 2Ring 2014.11.13
'''

from ctypes import *

SHA_LBLOCK = 16
SHA256_DIGEST_LENGTH = 32

class SHA256_CTX(Structure):
    _fields_ = [
        ("h", c_long * 8),
        ("Nl", c_long),
        ("Nh", c_long),
        ("data", c_long * SHA_LBLOCK),
        ("num", c_uint),
        ("md_len", c_uint)
    ]

HashBuffType = c_ubyte * SHA256_DIGEST_LENGTH

#crypto = cdll.LoadLibrary("libcrypto.so")
crypto = cdll.LoadLibrary("libeay32.dll" if os.name == "nt" else "libssl.so")

class sha256(object):
    digest_size = SHA256_DIGEST_LENGTH

    def __init__(self, datastr=None):
        self.ctx = SHA256_CTX()
        crypto.SHA256_Init(byref(self.ctx))
        if datastr:
            self.update(datastr)

    def update(self, datastr):
        crypto.SHA256_Update(byref(self.ctx), datastr, c_int(len(datastr)))

    #Clone the current context
    def _copy_ctx(self):
        ctx = SHA256_CTX()
        pointer(ctx)[0] = self.ctx
        return ctx

    def copy(self):
        other = sha256()
        other.ctx = self._copy_ctx()
        return other

    def digest(self):
        #Preserve context in case we get called before hashing is
        # really finished, since SHA256_Final() clears the SHA256_CTX
        ctx = self._copy_ctx()
        hashbuff = HashBuffType()
        crypto.SHA256_Final(hashbuff, byref(self.ctx))
        self.ctx = ctx
        return str(bytearray(hashbuff))

    def hexdigest(self):
        return self.digest().encode('hex')

#Tests
def main():
    import cPickle
    import hashlib

    data = ("Nobody expects ", "the spammish ", "imposition!")

    print "rehash\n"

    shaA = sha256(''.join(data))
    print shaA.hexdigest()
    print repr(shaA.digest())
    print "digest size =", shaA.digest_size
    print

    shaB = sha256()
    shaB.update(data[0])
    print shaB.hexdigest()

    #Test pickling
    sha_pickle = cPickle.dumps(shaB, -1)
    print "Pickle length:", len(sha_pickle)
    shaC = cPickle.loads(sha_pickle)

    shaC.update(data[1])
    print shaC.hexdigest()

    #Test copying. Note that copy can be pickled
    shaD = shaC.copy()

    shaC.update(data[2])
    print shaC.hexdigest()


    #Verify against hashlib.sha256()
    print "\nhashlib\n"

    shaD = hashlib.sha256(''.join(data))
    print shaD.hexdigest()
    print repr(shaD.digest())
    print "digest size =", shaD.digest_size
    print

    shaE = hashlib.sha256(data[0])
    print shaE.hexdigest()

    shaE.update(data[1])
    print shaE.hexdigest()

    #Test copying. Note that hashlib copy can NOT be pickled
    shaF = shaE.copy()
    shaF.update(data[2])
    print shaF.hexdigest()


if __name__ == '__main__':
    main()

resumable_SHA-256.py

#! /usr/bin/env python

''' Resumable SHA-256 hash for large files using the OpenSSL crypto library

    The hashing process may be interrupted by Control-C (SIGINT) or SIGTERM.
    When a signal is received, hashing continues until the end of the
    current chunk, then the current file position, total file size, and
    the sha object is saved to a file. The name of this file is formed by
    appending '.hash' to the name of the file being hashed.

    Just re-run the program to resume hashing. The '.hash' file will be deleted
    once hashing is completed.

    Written by PM 2Ring 2014.11.14
'''

import cPickle as pickle
import os
import signal
import sys

import rehash

quit = False

blocksize = 1<<16   # 64kB
blocksperchunk = 1<<8

chunksize = blocksize * blocksperchunk

def handler(signum, frame):
    global quit
    print "\nGot signal %d, cleaning up." % signum
    quit = True


def do_hash(fname, filesize):
    hashname = fname + '.hash'
    if os.path.exists(hashname):
        with open(hashname, 'rb') as f:
            pos, fsize, sha = pickle.load(f)
        if fsize != filesize:
            print "Error: file size of '%s' doesn't match size recorded in '%s'" % (fname, hashname)
            print "%d != %d. Aborting" % (fsize, filesize)
            exit(1)
    else:
        pos, fsize, sha = 0, filesize, rehash.sha256()

    finished = False
    with open(fname, 'rb') as f:
        f.seek(pos)
        while not (quit or finished):
            for _ in xrange(blocksperchunk):
                block = f.read(blocksize)
                if block == '':
                    finished = True
                    break
                sha.update(block)

            pos += chunksize
            sys.stderr.write(" %6.2f%% of %d\r" % (100.0 * pos / fsize, fsize))
            if finished or quit:
                break

    if quit:
        with open(hashname, 'wb') as f:
            pickle.dump((pos, fsize, sha), f, -1)
    elif os.path.exists(hashname):
        os.remove(hashname)

    return (not quit), pos, sha.hexdigest()


def main():
    if len(sys.argv) != 2:
        print "Resumable SHA-256 hash of a file."
        print "Usage:\npython %s filename\n" % sys.argv[0]
        exit(1)

    fname = sys.argv[1]
    filesize = os.path.getsize(fname)

    signal.signal(signal.SIGINT, handler)
    signal.signal(signal.SIGTERM, handler)

    finished, pos, hexdigest = do_hash(fname, filesize)
    if finished:
        print "%s  %s" % (hexdigest, fname)
    else:
        print "sha-256 hash of '%s' incomplete" % fname
        print "%s" % hexdigest
        print "%d / %d bytes processed." % (pos, filesize)


if __name__ == '__main__':
    main()

demo

import rehash
import pickle
sha=rehash.sha256("Hello ")
s=pickle.dumps(sha.ctx)
sha=rehash.sha256()
sha.ctx=pickle.loads(s)
sha.update("World")
print sha.hexdigest()

output

a591a6d40bf420404a011733cfb7b190d62c65bf0bcda32b57b277d9ad9f146e

Note: I would like to thank PM2Ring for his wonderful code.

hashlib.sha1 is a wrapper around a C library so you won't be able to pickle it.

It would need to implement the __getstate__ and __setstate__ methods for Python to access its internal state

You could use a pure Python implementation of sha1 if it is fast enough for your requirements

I was facing this problem too, and found no existing solution, so I ended up writing a library that does something very similar to what Devesh Saini described: https://github.com/kislyuk/rehash. Example:

import pickle, rehash
hasher = rehash.sha256(b"foo")
state = pickle.dumps(hasher)

hasher2 = pickle.loads(state)
hasher2.update(b"bar")

assert hasher2.hexdigest() == rehash.sha256(b"foobar").hexdigest()

Hash algorithm for dynamic growing/streaming data?

You can easily build a wrapper object around the hash object which can transparently persist the data.

The obvious drawback is that it needs to retain the hashed data in full in order to restore the state - so depending on the data size you are dealing with, this may not suit your needs. But it should work fine up to some tens of MB.

Unfortunattely the hashlib does not expose the hash algorithms as proper classes, it rathers gives factory functions that construct the hash objects - so we can't properly subclass those without loading reserved symbols - a situation I'd rather avoid. That only means you have to built your wrapper class from the start, which is not such that an overhead from Python anyway.

here is a sample code that might even fill your needs:

import hashlib
from cStringIO import StringIO

class PersistentSha1(object):
    def __init__(self, salt=""):
        self.__setstate__(salt)

    def update(self, data):
        self.__data.write(data)
        self.hash.update(data)

    def __getattr__(self, attr):
        return getattr(self.hash, attr)

    def __setstate__(self, salt=""):
        self.__data = StringIO()
        self.__data.write(salt)
        self.hash = hashlib.sha1(salt)

    def __getstate__(self):
        return self.data

    def _get_data(self):
        self.__data.seek(0)
        return self.__data.read()

    data = property(_get_data, __setstate__)

You can access the "data" member itself to get and set the state straight, or you can use python pickling functions:

>>> a = PersistentSha1()
>>> a
<__main__.PersistentSha1 object at 0xb7d10f0c>
>>> a.update("lixo")
>>> a.data
'lixo'
>>> a.hexdigest()
'6d6332a54574aeb35dcde5cf6a8774f938a65bec'
>>> import pickle
>>> b = pickle.dumps(a)
>>>
>>> c = pickle.loads(b)
>>> c.hexdigest()
'6d6332a54574aeb35dcde5cf6a8774f938a65bec'

>>> c.data
'lixo'