/*
* Copyright (c) 2020-2030 Sishun.Co.Ltd. All Rights Reserved.
*/
package com.example.mytest.testbloom;
import java.util.BitSet;
/**
* @author : zhangsencheng
* @version : W1.0
* @description : 布隆过滤器实现类
* @program : com.example.mytest.testbloom
* @date : Created in 2020/9/22 19:46
*/
public class BloomFilter {
//2的24次方长度
private static final int DEFAULT_SIZE = 2 << 24;
//用质数防止hash冲突 并不是绝对的
private static final int[] seeds = new int[]{7, 11, 13, 17, 19};
//定义一个bitSet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]);
}
}
//存储方法
public void add(String value) {
for (SimpleHash f : func) {
bits.set(f.hash(value), true);
}
}
//验证方法
public boolean contains(String value) {
if (value == null) {
return false;
}
boolean ret = true;
for (SimpleHash f : func) {
ret = ret && bits.get(f.hash(value));
}
return ret;
}
// 内部类,simpleHash
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;
int len = value.length();
for (int i = 0; i < len; i++) {
result = seed * result + value.charAt(i);
}
return (cap - 1) & result;
}
}
}
/*
* Copyright (c) 2020-2030 Sishun.Co.Ltd. All Rights Reserved.
*/
package com.example.mytest.testbloom;
import java.util.ArrayList;
import java.util.List;
/**
* @author : zhangsencheng
* @version : W1.0
* @description :
* @program : com.example.mytest.testbloom
* @date : Created in 2020/9/22 20:20
*/
public class test1 {
public static void main(String[] args) {
BloomFilter bf = new BloomFilter();
List<String> strs = new ArrayList<String>();
strs.add("123456");
strs.add("hello word");
strs.add("transDocId");
strs.add("123456");
strs.add("transDocId");
strs.add("hello word");
strs.add("test");
strs.add("Test");
for (int i=0;i<strs.size();i++) {
String s = strs.get(i);
boolean bl = bf.contains(s);
if(bl){
System.out.println(i+","+s);
}else{
bf.add(s);
}
}
}
}