通俗易懂讲布隆过滤器

      <dependency>
          <groupId>com.google.guava</groupId>
          <artifactId>guava</artifactId>
          <version>21.0</version>
      </dependency>

    //插入多少数据
    private static final int insertions = 1000000;
    //期望的误判率
    private static double fpp = 0.02;
    public static void main(String[] args) {
        //初始化一个存储string数据的布隆过滤器,默认误判率是0.03
        BloomFilter<String> bf = BloomFilter.create(Funnels.stringFunnel(Charsets.UTF_8), insertions, fpp);
        //用于存放所有实际存在的key，用于是否存在
        Set<String> sets = new HashSet<String>(insertions);
        //用于存放所有实际存在的key，用于取出
        List<String> lists = new ArrayList<String>(insertions);
        //插入随机字符串
        for (int i = 0; i < insertions; i++) {
            String uuid = UUID.randomUUID().toString();
            bf.put(uuid);
            sets.add(uuid);
            lists.add(uuid);
        }
        int rightNum = 0;
        int wrongNum = 0;
        for (int i = 0; i < 10000; i++) {
            // 0-10000之间，可以被100整除的数有100个（100的倍数）
            String data = i % 100 == 0 ? lists.get(i / 100) : UUID.randomUUID().toString();
            //这里用了might,看上去不是很自信，所以如果布隆过滤器判断存在了,我们还要去sets中实锤
            if (bf.mightContain(data)) {
                if (sets.contains(data)) {
                    rightNum++;
                    continue;
                }
                wrongNum++;
            }
        }
        BigDecimal percent = new BigDecimal(wrongNum).divide(new BigDecimal(9900), 2, RoundingMode.HALF_UP);
        BigDecimal bingo = new BigDecimal(9900 - wrongNum).divide(new BigDecimal(9900), 2, RoundingMode.HALF_UP);
        System.out.println("在100W个元素中，判断100个实际存在的元素，布隆过滤器认为存在的：" + rightNum);
        System.out.println("在100W个元素中，判断9900个实际不存在的元素，误认为存在的：" + wrongNum + "，命中率：" + bingo + "，误判率：" + percent);
    }

/**
 * 布隆过滤器核心类
 *
 * @param <T>
 * @author jack xu
 */
public class BloomFilterHelper<T> {
    private int numHashFunctions;
    private int bitSize;
    private Funnel<T> funnel;
    public BloomFilterHelper(int expectedInsertions) {
        this.funnel = (Funnel<T>) Funnels.stringFunnel(Charset.defaultCharset());
        bitSize = optimalNumOfBits(expectedInsertions, 0.03);
        numHashFunctions = optimalNumOfHashFunctions(expectedInsertions, bitSize);
    }
    public BloomFilterHelper(Funnel<T> funnel, int expectedInsertions, double fpp) {
        this.funnel = funnel;
        bitSize = optimalNumOfBits(expectedInsertions, fpp);
        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;
    }
    /**
     * 计算bit数组长度
     */
    private int optimalNumOfBits(long n, double p) {
        if (p == 0) {
            p = Double.MIN_VALUE;
        }
        return (int) (-n * Math.log(p) / (Math.log(2) * Math.log(2)));
    }
    /**
     * 计算hash方法执行次数
     */
    private int optimalNumOfHashFunctions(long n, long m) {
        return Math.max(1, (int) Math.round((double) m / n * Math.log(2)));
    }
}

/**
 * redis操作布隆过滤器
 *
 * @param <T>
 * @author xhj
 */
public class RedisBloomFilter<T> {
    @Autowired
    private RedisTemplate redisTemplate;
    /**
     * 删除缓存的KEY
     *
     * @param key KEY
     */
    public void delete(String key) {
        redisTemplate.delete(key);
    }
    /**
     * 根据给定的布隆过滤器添加值，在添加一个元素的时候使用，批量添加的性能差
     *
     * @param bloomFilterHelper 布隆过滤器对象
     * @param key               KEY
     * @param value             值
     * @param <T>               泛型，可以传入任何类型的value
     */
    public <T> void add(BloomFilterHelper<T> bloomFilterHelper, String key, T value) {
        int[] offset = bloomFilterHelper.murmurHashOffset(value);
        for (int i : offset) {
            redisTemplate.opsForValue().setBit(key, i, true);
        }
    }
    /**
     * 根据给定的布隆过滤器添加值，在添加一批元素的时候使用，批量添加的性能好，使用pipeline方式(如果是集群下，请使用优化后RedisPipeline的操作)
     *
     * @param bloomFilterHelper 布隆过滤器对象
     * @param key               KEY
     * @param valueList         值，列表
     * @param <T>               泛型，可以传入任何类型的value
     */
    public <T> void addList(BloomFilterHelper<T> bloomFilterHelper, String key, List<T> valueList) {
        redisTemplate.executePipelined(new RedisCallback<Long>() {
            @Override
            public Long doInRedis(RedisConnection connection) throws DataAccessException {
                connection.openPipeline();
                for (T value : valueList) {
                    int[] offset = bloomFilterHelper.murmurHashOffset(value);
                    for (int i : offset) {
                        connection.setBit(key.getBytes(), i, true);
                    }
                }
                return null;
            }
        });
    }
    /**
     * 根据给定的布隆过滤器判断值是否存在
     *
     * @param bloomFilterHelper 布隆过滤器对象
     * @param key               KEY
     * @param value             值
     * @param <T>               泛型，可以传入任何类型的value
     * @return 是否存在
     */
    public <T> boolean contains(BloomFilterHelper<T> bloomFilterHelper, String key, T value) {
        int[] offset = bloomFilterHelper.murmurHashOffset(value);
        for (int i : offset) {
            if (!redisTemplate.opsForValue().getBit(key, i)) {
                return false;
            }
        }
        return true;
    }
}

    public static void main(String[] args) {
        RedisBloomFilter redisBloomFilter = new RedisBloomFilter();
        int expectedInsertions = 1000;
        double fpp = 0.1;
        redisBloomFilter.delete("bloom");
        BloomFilterHelper<CharSequence> bloomFilterHelper = new BloomFilterHelper<>(Funnels.stringFunnel(Charset.defaultCharset()), expectedInsertions, fpp);
        int j = 0;
        // 添加100个元素
        List<String> valueList = new ArrayList<>();
        for (int i = 0; i < 100; i++) {
            valueList.add(i + "");
        }
        long beginTime = System.currentTimeMillis();
        redisBloomFilter.addList(bloomFilterHelper, "bloom", valueList);
        long costMs = System.currentTimeMillis() - beginTime;
        log.info("布隆过滤器添加{}个值，耗时：{}ms", 100, costMs);
        for (int i = 0; i < 1000; i++) {
            boolean result = redisBloomFilter.contains(bloomFilterHelper, "bloom", i + "");
            if (!result) {
                j++;
            }
        }
        log.info("漏掉了{}个,验证结果耗时：{}ms", j, System.currentTimeMillis() - beginTime);
    }