Safe pickle implementations

gistfile1.py

In [1]: %paste
 
import hmac
import hashlib
import cPickle
import cStringIO
 
key = '\xa7\x9ePS\xf5\x84\xce\xc8\xad\xcdfEb\x94\x10K\x9b\x12\xed'
dig_size = hashlib.sha1().digest_size
 
 
def safe_loads(data):
    fobj = cStringIO.StringIO(data)
    unpickler = cPickle.Unpickler(fobj)
    unpickler.find_global = None
    return unpickler.load()
 
 
def safe_dumps(data):
    return cPickle.dumps(data, protocol=-1)
 
 
def safe_loads_hmac(data):
    sig, data = data[:dig_size], data[dig_size:]
    expected = hmac.new(key, data, hashlib.sha1).digest()
    if expected != sig:
        raise cPickle.UnpicklingError('Signature wrong.')
    return cPickle.loads(data)
 
 
def safe_dumps_hmac(data):
    data = cPickle.dumps(data, protocol=-1)
    sig = hmac.new(key, data, hashlib.sha1).digest()
    return sig + data
 
## -- End pasted text --
 
In [2]: data = [1, 2, True, False, 'abcd']
 
In [3]: %timeit s = safe_dumps(data); safe_loads(s)
100000 loops, best of 3: 3.31 us per loop
 
In [4]: %timeit s = safe_dumps_hmac(data); safe_loads_hmac(s)
10000 loops, best of 3: 25.1 us per loop

In [5]: %timeit s = cPickle.dumps(data, protocol=-1); cPickle.loads(s)
100000 loops, best of 3: 2.55 us per loop
 
In [6]: data = dict((i, str(i) * 10) for i in xrange(20000))
 
In [7]: %timeit s = safe_dumps(data); safe_loads(s)
100 loops, best of 3: 6.86 ms per loop
 
In [8]: %timeit s = safe_dumps_hmac(data); safe_loads_hmac(s)
100 loops, best of 3: 13 ms per loop

In [9]: %timeit s = cPickle.dumps(data, protocol=-1); cPickle.loads(s)
100 loops, best of 3: 6.8 ms per loop