企业上网监控场景下布隆过滤器的 Java 算法构建及其性能优化研究

import java.util.BitSet;
import java.util.Random;
public class BloomFilter {
    private final BitSet bitSet;
    private final int bitSize;
    private final int hashCount;
    private final Random random;
    private static final int[] PRIME_SEEDS = {3, 5, 7, 11, 13, 17, 19}; // 哈希函数种子
    // 构造函数：指定预期元素数量和可接受误判率
    public BloomFilter(int expectedSize, double falsePositiveRate) {
        this.bitSize = calculateBitSize(expectedSize, falsePositiveRate);
        this.hashCount = calculateHashCount(bitSize, expectedSize);
        this.bitSet = new BitSet(bitSize);
        this.random = new Random();
    }
    // 计算最优位数组长度
    private int calculateBitSize(int n, double p) {
        return (int) (-n * Math.log(p) / (Math.log(2) * Math.log(2)));
    }
    // 计算最优哈希函数数量
    private int calculateHashCount(int m, int n) {
        return (int) (m * Math.log(2) / n);
    }
    // 插入违规网址
    public void add(String url) {
        for (int i = 0; i < hashCount; i++) {
            int index = Math.abs(url.hashCode() ^ PRIME_SEEDS[i % PRIME_SEEDS.length]) % bitSize;
            bitSet.set(index);
        }
    }
    // 检测网址是否可能为违规站点
    public boolean mightContain(String url) {
        for (int i = 0; i < hashCount; i++) {
            int index = Math.abs(url.hashCode() ^ PRIME_SEEDS[i % PRIME_SEEDS.length]) % bitSize;
            if (!bitSet.get(index)) {
                return false;
            }
        }
        return true;
    }
    // 企业上网监控中的使用示例
    public static void main(String[] args) {
        // 初始化过滤器：预期存储100万个违规网址，误判率0.1%
        BloomFilter filter = new BloomFilter(1_000_000, 0.001);
        // 加载违规网址库（示例）
        filter.add("https://www.vipshare.com");
        filter.add("https://malicious.example.com");
        // 模拟实时监控检测
        String[] testUrls = {
            "https://www.vipshare.com",
            "https://safe.example.com",
            "https://malicious.example.com"
        };
        for (String url : testUrls) {
            if (filter.mightContain(url)) {
                System.out.println("检测到疑似违规访问：" + url);
            } else {
                System.out.println("访问网址合规：" + url);
            }
        }
    }
}