Redis中Bloom filter布隆过滤器的学习

<!--guava实现布隆过滤器-->
<dependency>
    <groupId>com.Google.guava</groupId>
    <artifactId>guava</artifactId>
    <version>19.0</version>
</dependency>

//初始化布隆过滤器，放入到spring容器里面
@Bean
public MyBloomFilter<String> initBloomFilterHelper() {
    return new MyBloomFilter<>((Funnel<String>) (from, into) -> into.putString(from, Charsets.UTF_8).putString(from, Charsets.UTF_8)
                               , 1000000, 0.01);
}

package com.qin.redis.bloomfilter;
import com.google.common.base.Preconditions;
import com.google.common.hash.Funnel;
import com.google.common.hash.Hashing;

public class MyBloomFilter<T> {
    private int numHashFunctions;
    private int bitSize;
    private Funnel<T> funnel;
    public MyBloomFilter(Funnel<T> funnel, int expectedInsertions, double fpp) {
        Preconditions.checkArgument(funnel != null, "funnel不能为空");
        this.funnel = funnel;
        // 计算bit数组长度
        bitSize = optimalNumOfBits(expectedInsertions, fpp);
        // 计算hash方法执行次数
        numHashFunctions = optimalNumOfHashFunctions(expectedInsertions, bitSize);
    }
    public int[] murmurHashOffset(T value) {
        int[] offset = new int[numHashFunctions];
        long hash64 = Hashing.murmur3_128().hashObject(value, funnel).asLong();
        int hash1 = (int) hash64;
        int hash2 = (int) (hash64 >>> 32);
        for (int i = 1; i <= numHashFunctions; i++) {
            int nextHash = hash1 + i * hash2;
            if (nextHash < 0) {
                nextHash = ~nextHash;
            }
            offset[i - 1] = nextHash % bitSize;
        }
        return offset;
    }
    
    private int optimalNumOfBits(long n, double p) {
        if (p == 0) {
            // 设定最小期望长度
            p = Double.MIN_VALUE;
        }
        int sizeOfBitArray = (int) (-n * Math.log(p) / (Math.log(2) * Math.log(2)));
        return sizeOfBitArray;
    }
    
    private static int optimalNumOfHashFunctions(long n, long m) {
        int countOfHash = Math.max(1, (int) Math.round((double) m / n * Math.log(2)));
        return countOfHash;
    }
    public static void main(String[] args) {
        System.out.println(optimalNumOfHashFunctions(1000000000L, 123450000L));
    }
}

package com.qin.redis.bloomfilter.service;
import com.google.common.base.Preconditions;
import com.hikvison.aksk.redis.bloomfilter.MyBloomFilter;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.data.redis.core.RedisTemplate;
import org.springframework.stereotype.Service;

@Service
public class RedisBloomFilterService {
    @Autowired
    private RedisTemplate redisTemplate;
    
    public <T> void addByBloomFilter(MyBloomFilter<T> bloomFilterHelper, String key, T value) {
        Preconditions.checkArgument(bloomFilterHelper != null, "myBloomFilter不能为空");
        int[] offset = bloomFilterHelper.murmurHashOffset(value);
        for (int i : offset) {
            System.out.println("key : " + key + " " + "value : " + i);
            redisTemplate.opsForValue().setBit(key, i, true);
        }
    }
    
    public <T> boolean includeByBloomFilter(MyBloomFilter<T> bloomFilterHelper, String key, T value) {
        Preconditions.checkArgument(bloomFilterHelper != null, "myBloomFilter不能为空");
        int[] offset = bloomFilterHelper.murmurHashOffset(value);
        for (int i : offset) {
            System.out.println("key : " + key + " " + "value : " + i);
            if (!redisTemplate.opsForValue().getBit(key, i)) {
                return false;
            }
        }
        return true;
    }
}

<dependency>
    <groupId>org.redisson</groupId>
    <artifactId>redisson</artifactId>
    <version>2.7.0</version>
</dependency>

 //单机模式：可以设置集群、哨兵模式
    @Bean
    public Redisson redisson() {
        Config config = new Config();
        config.useSingleServer().setAddress("redis://127.0.0.1:6379");
        RedissonClient redissonClient = Redisson.create(config);
        //初始化过滤器
        RBloomFilter<Object> bloomFilter = redissonClient.getBloomFilter("testBloomFilter");
        bloomFilter.tryInit(1000000L,0.05);
        //插入元素
        bloomFilter.add("zhangsan");
        bloomFilter.add("lisi");
        //判断元素是否存在
        boolean flag = bloomFilter.contains("lisi");
        return (Redisson) redissonClient;
    }