Bloom Filter

75 阅读1分钟

Bloom Filter 的 Java 实现示例:

import java.util.BitSet;

public class BloomFilter {
    private static final int DEFAULT_SIZE = 2 << 24; // 默认大小为 2^24
    private static final int[] seeds = {3, 5, 7, 11, 13, 31, 37, 61}; // 哈希种子数组
    private BitSet bits = new BitSet(DEFAULT_SIZE);
    private SimpleHash[] func = new SimpleHash[seeds.length];

    public BloomFilter() {
        for (int i = 0; i < seeds.length; i++) {
            func[i] = new SimpleHash(DEFAULT_SIZE, seeds[i]);
        }
    }

    public void add(String value) {
        for (SimpleHash f : func) {
            bits.set(f.hash(value), true);
        }
    }

    public boolean contains(String value) {
        if (value == null) {
            return false;
        }
        boolean result = true;
        for (SimpleHash f : func) {
            result = result && bits.get(f.hash(value));
        }
        return result;
    }

    public static class SimpleHash {
        private int cap;
        private int seed;

        public SimpleHash(int cap, int seed) {
            this.cap = cap;
            this.seed = seed;
        }

        public int hash(String value) {
            int result = 0;
            for (int i = 0; i < value.length(); i++) {
                result = seed * result + value.charAt(i);
            }
            return (cap - 1) & result;
        }
    }

    public static void main(String[] args) {
        BloomFilter bloomFilter = new BloomFilter();
        bloomFilter.add("apple");
        bloomFilter.add("banana");
        bloomFilter.add("orange");

        System.out.println(bloomFilter.contains("apple")); // true
        System.out.println(bloomFilter.contains("grape")); // false
        System.out.println(bloomFilter.contains("orange")); // true
    }
}

在这个示例中,我们实现了一个简单的 Bloom Filter 类。它包含了添加元素和检查元素存在性的方法。我们使用了 8 个不同的哈希函数,并且通过位图(BitSet)来表示 Bloom Filter 的位数组。