*  Document is split into tokens (words for example) 

or super-tokens (word tuples)* Each token is represented by its hash value; a traditional 

hash function is used* Weights are associated with tokens* A vector V of integers is initialized to 0, length of the vector 

corresponds to the desired hash size in bits* In a cycle for all token's hash values (h), vector V is updated:o ith element is decreased by token's weight if the ith bit of 

the hash h is 0, otherwiseo ith element is increased by token's weight if the ith bit of 

the hash h is 1* Finally, signs of elements of V corresponds to the bits of the

 final fingerprint

#!/usr/bin/python# Implementation of Charikar simhashes in Python
# See: http://dsrg.mff.cuni.cz/~holub/sw/shash/#a1class simhash():def __init__(self, tokens='', hashbits=128):self.hashbits = hashbitsself.hash = self.simhash(tokens)def __str__(self):return str(self.hash)def __long__(self):return long(self.hash)def __float__(self):return float(self.hash)def simhash(self, tokens):# Returns a Charikar simhash with appropriate bitlengthv = [0]*self.hashbitsfor t in [self._string_hash(x) for x in tokens]:bitmask = 0print (t)for i in range(self.hashbits):bitmask = 1 << iprint(t,bitmask, t & bitmask)if t & bitmask:v[i] += 1 #查看当前bit位是否为1，是的话则将该位+1 else:v[i] –= 1 #否则得话，该位减1fingerprint = 0for i in range(self.hashbits):if v[i] >= 0:fingerprint += 1 << i 

#整个文档的fingerprint为最终各个位大于等于0的位的和return fingerprintdef _string_hash(self, v):# A variable-length version of Python's builtin hashif v == "":return 0else:x = ord(v[0])<<7m = 1000003mask = 2**self.hashbits-1for c in v:x = ((x*m)^ord(c)) & maskx ^= len(v)if x == -1: x = -2return xdef hamming_distance(self, other_hash):x = (self.hash ^ other_hash.hash) & ((1 << self.hashbits) - 1)tot = 0while x:tot += 1x &= x-1return totdef similarity(self, other_hash):a = float(self.hash)b = float(other_hash)if a>b: return b/areturn a/bif __name__ == '__main__':s = 'This is a test string for testing'hash1 =simhash(s.split())#print("0x%x" % hash1)#print ("%s/t0x%x" % (s, hash1))s = 'This is a test string for testing also!'hash2 = simhash(s.split())#print ("%s/t[simhash = 0x%x]" % (s, hash2))print (hash1.similarity(hash2), "percent similar")print (hash1.hamming_distance(hash2), "bits differ out of", hash1.hashbits)