python 布隆过滤器

import hashlib
import redis


class SimpleHash(object):
    def __init__(self, cap, seed):
        self.cap = cap
        self.seed = seed

    def hash(self, value):
        ret = 0
        for i in range(len(value)):
            ret += self.seed * ret + ord(value[i])
        return (self.cap - 1) & ret

class BloomFilter(object): def __init__(self, redis_obj, block_num=1, key='bloomfilter'): """ :param block_num: one block_num for about 90,000,000; if u have more strings for filtering, increase it. """ self.server = redis_obj self.bit_size = 1 << 31 # redis的string类型最大容量为512M,现在使用256M self.seeds = [5,7,11,1,3,31,37,61] self.key = key self.block_num = block_num self.hashfunc = [] for seed in self.seeds: self.hashfunc.append(SimpleHash(self.bit_size, seed)) def is_contains(self, str_input): if not str_input: return False md5 = hashlib.md5() md5.update(str_input.encode()) str_input = md5.hexdigest() ret = True name = self.key + str(int(str_input[0:2], 16) % self.block_num) print(str_input[0:2]) print(int(str_input[0:2], 16)) print(int(str_input[0:2], 16) % self.block_num) for f in self.hashfunc: loc = f.hash(str_input) ret = ret & self.server.getbit(name, loc) return ret def insert(self, str_input): md5 = hashlib.md5() md5.update(str_input.encode()) str_input = md5.hexdigest() name = self.key + str(int(str_input[0:2], 16) % self.block_num) for f in self.hashfunc: loc = f.hash(str_input) self.server.setbit(name, loc, int) if __name__ == '__main__': """第一次运行时会显示 not exists!,之后再运行会显示 exists!""" redis = redis.from_url('redis://127.0.0.1') bf = BloomFilter(redis) for i in range(10): url = 'http://www.baidu.com?bai=2132{}'.format(i) if bf.is_contains(url): print('exists!') else: print('not exists') bf.insert(url)

猜你喜欢

转载自www.cnblogs.com/zhangjian0092/p/12340631.html