基于redis的布隆过滤器

import redis
from hashlib import md5
import configparser

#读取redis数据库配置
config = configparser.ConfigParser()
config.read('util/db_conf')
host = config['redis']['host']
port = config.getint('redis', 'port')
db = config.getint('redis', 'db')
password = config.get('redis', 'password')


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, host=host, port=port, db=db, blockNum=1, redis_name='bloomfilter'):
        """
        :param host: the host of Redis
        :param port: the port of Redis
        :param db: witch db in Redis
        :param blockNum: one blockNum for about 90,000,000; if you have more strings for filtering, increase it.
        :param redis_name: the key's name in Redis
        """
        self.r = redis.Redis(host=host, port=port, db=db,password=password)
        self.bit_size = 1 << 5  # Redis的String类型最大容量为512M
        self.seeds = [5, 7, 11, 13, 31, 37, 61]
        self.blockNum = blockNum
        self.hashfunc = []
        self.name=redis_name

        for seed in self.seeds:
            self.hashfunc.append(SimpleHash(self.bit_size, seed))

    def md5_encrypt(self,str_input):
        m5 = md5()
        m5.update(str_input.encode(encoding='utf8'))
        return m5.hexdigest()

    def isContains(self, str_input):
        str_input = self.md5_encrypt(str_input)
        ret = True
        for f in self.hashfunc:
            loc = f.hash(str_input)
            ret = ret & self.r.getbit(self.name, loc)
        return ret

    def insert(self, str_input):
        str_input = self.md5_encrypt(str_input)
        for f in self.hashfunc:
            loc = f.hash(str_input)
            self.r.setbit(self.name, loc, 1)

def test():
    words = ['hello', 'world', 'hello', 'Tom']
    bf = BloomFilter()
    for word in words:
        if bf.isContains(word):  # 判断字符串是否存在
            print('"{}"  has already in redis'.format(word))
        else:
            bf.insert(word)
            print('"{}"  has just been inserted into redis'.format(word))


if __name__ == '__main__':
    test()