布隆過濾器言簡意賅講解

布隆過濾器含義

• 先準備一個長度爲n的二進制向量
• 若干個哈希函數，計算出來的若干個索引在0-n-1
• 某數據通過這組哈希函數計算出來若干個索引，在該向量中若都爲1則表明該數據大概率存在，否則一定不存在
• 有誤判率
• 設計難度在於：隨機映射函數的設計 和 二進制向量的長度設爲多少？

引用代碼——guava實現布隆過濾器

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

    private static int size = 1000000;//預計要插入多少數據

    private static double fpp = 0.01;//期望的誤判率

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

    public static void main(String[] args) {
        //插入數據
        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 + "誤判了");
            }
        }
        System.out.println("總共的誤判數:" + count);
    }

引用代碼——redis實現布隆過濾器

public class RedisMain {
    static final int expectedInsertions = 100;//要插入多少數據
    static final double fpp = 0.01;//期望的誤判率

    //bit數組長度
    private static long numBits;

    //hash函數數量
    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 + "肯定沒有重複");
                }
            }
            System.out.println(i + "可能重複");
        }
    }

    /**
     * 根據key獲取bitmap下標
     */
    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();
    }

    //計算hash函數個數
    private static int optimalNumOfHashFunctions(long n, long m) {
        return Math.max(1, (int) Math.round((double) m / n * Math.log(2)));
    }

    //計算bit數組長度
    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)));
    }
}