布隆过滤器言简意赅讲解

布隆过滤器含义

• 先准备一个长度为n的二进制向量
• 若干个哈希函数，计算出来的若干个索引在0-n-1
• 某数据通过这组哈希函数计算出来若干个索引，在该向量中若都为1则表明该数据大概率存在，否则一定不存在
• 有误判率
• 设计难度在于：随机映射函数的设计 和 二进制向量的长度设为多少？

引用代码——guava实现布隆过滤器

  <dependency>
        <groupId>com.google.guava</groupId>
        <artifactId>guava</artifactId>
        <version>19.0</version>
    </dependency>

    private static int size = 1000000;//预计要插入多少数据

    private static double fpp = 0.01;//期望的误判率

    private static BloomFilter<Integer> bloomFilter = BloomFilter.create(Funnels.integerFunnel(), size, fpp);

    public static void main(String[] args) {
        //插入数据
        for (int i = 0; i < 1000000; i++) {
            bloomFilter.put(i);
        }
        int count = 0;
        for (int i = 1000000; i < 2000000; i++) {
            if (bloomFilter.mightContain(i)) {
                count++;
                System.out.println(i + "误判了");
            }
        }
        System.out.println("总共的误判数:" + count);
    }

引用代码——redis实现布隆过滤器

public class RedisMain {
    static final int expectedInsertions = 100;//要插入多少数据
    static final double fpp = 0.01;//期望的误判率

    //bit数组长度
    private static long numBits;

    //hash函数数量
    private static int numHashFunctions;

    static {
        numBits = optimalNumOfBits(expectedInsertions, fpp);
        numHashFunctions = optimalNumOfHashFunctions(expectedInsertions, numBits);
    }

    public static void main(String[] args) {
        Jedis jedis = new Jedis("192.168.0.109", 6379);
        for (int i = 0; i < 100; i++) {
            long[] indexs = getIndexs(String.valueOf(i));
            for (long index : indexs) {
                jedis.setbit("codebear:bloom", index, true);
            }
        }
        for (int i = 0; i < 100; i++) {
            long[] indexs = getIndexs(String.valueOf(i));
            for (long index : indexs) {
                Boolean isContain = jedis.getbit("codebear:bloom", index);
                if (!isContain) {
                    System.out.println(i + "肯定没有重复");
                }
            }
            System.out.println(i + "可能重复");
        }
    }

    /**
     * 根据key获取bitmap下标
     */
    private static long[] getIndexs(String key) {
        long hash1 = hash(key);
        long hash2 = hash1 >>> 16;
        long[] result = new long[numHashFunctions];
        for (int i = 0; i < numHashFunctions; i++) {
            long combinedHash = hash1 + i * hash2;
            if (combinedHash < 0) {
                combinedHash = ~combinedHash;
            }
            result[i] = combinedHash % numBits;
        }
        return result;
    }

    private static long hash(String key) {
        Charset charset = Charset.forName("UTF-8");
        return Hashing.murmur3_128().hashObject(key, Funnels.stringFunnel(charset)).asLong();
    }

    //计算hash函数个数
    private static int optimalNumOfHashFunctions(long n, long m) {
        return Math.max(1, (int) Math.round((double) m / n * Math.log(2)));
    }

    //计算bit数组长度
    private static long optimalNumOfBits(long n, double p) {
        if (p == 0) {
            p = Double.MIN_VALUE;
        }
        return (long) (-n * Math.log(p) / (Math.log(2) * Math.log(2)));
    }
}