持久化hashlib状态
我想创建一个 hashlib
的实例,然后用 update()
方法更新它,接着以某种方式保存它的状态。之后,我希望能用这些状态数据重新创建这个对象,并继续用 update()
方法更新它。最后,我想获取所有数据的 hexdigest()
。这个状态保存需要能在多次运行之间保持。
举个例子:
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 persisted state
m.update('three')
m.update('four')
print m.hexdigest()
# at this point, m.hexdigest() should be equal to hashlib.sha1().update('onetwothreefour').hextdigest()
编辑:
在2010年,我没有找到一个好的方法用Python来实现这个功能,所以我写了一个小的辅助程序用C语言来完成这个任务。不过,下面有一些很棒的答案,那时候我并不知道。
5 个回答
1
我也遇到过这个问题,找不到现成的解决办法,所以我最终写了一个库,做的事情和Devesh Saini描述的很相似:https://github.com/kislyuk/rehash。下面是一个例子:
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()
1
hashlib.sha1 是一个用 C 语言库封装的工具,所以你不能直接把它保存成文件。
要让 Python 能够访问它内部的状态,它需要实现 __getstate__
和 __setstate__
这两个方法。
如果你觉得速度够快的话,可以使用一个 纯 Python 的 sha1 实现。
5
你可以通过使用 ctypes
这种方式来实现,不需要在 C 语言中写辅助应用程序:-
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
注意:我想感谢 PM2Ring 提供的精彩代码。