Bloom Filter实现大数据集查询

import mmh3
from bitarray import bitarray
"""
首先需要使用pip安装这两个依赖的包
"""


BIT_SIZE = 5000000

class BloomFilter:
    
    def __init__(self):
        # Initialize bloom filter, set size and all bits to 0
        bit_array = bitarray(BIT_SIZE)
        bit_array.setall(0)

        self.bit_array = bit_array
        
    def add(self, url):
        # Add a url, and set points in bitarray to 1 (Points count is equal to hash funcs count.)
        # Here use 7 hash functions.
        point_list = self.get_postions(url)

        for b in point_list:
            self.bit_array[b] = 1

    def contains(self, url):
        # Check if a url is in a collection
        point_list = self.get_postions(url)

        result = True
        for b in point_list:
            result = result and self.bit_array[b]
    
        return result

    def get_postions(self, url):
        # Get points positions in bit vector.
        point1 = mmh3.hash(url, 41) % BIT_SIZE
        point2 = mmh3.hash(url, 42) % BIT_SIZE
        point3 = mmh3.hash(url, 43) % BIT_SIZE
        point4 = mmh3.hash(url, 44) % BIT_SIZE
        point5 = mmh3.hash(url, 45) % BIT_SIZE
        point6 = mmh3.hash(url, 46) % BIT_SIZE
        point7 = mmh3.hash(url, 47) % BIT_SIZE


        return [point1, point2, point3, point4, point5, point6, point7]

# 测试一下
if __name__ == ‘__main__‘:
    bloom = BloomFilter()
    bloom.add("www.baidu.com")
    bloom.add("www.yahoo.com")
    bloom.add("www.tencen.com")
    flag = bloom.contains("www.baidu.com")
    print flag

import java.util.BitSet;

/**
 *
 * @author xkey
 */
public class BloomFilter {

    private static final int DEFAULT_SIZE = 2 << 24;//布隆过滤器的比特长度
    private static final int[] seeds = {3,5,7, 11, 13, 31, 37, 61};//这里要选取质数，能很好的降低错误率
    private static BitSet bits = new BitSet(DEFAULT_SIZE);
    private static SimpleHash[] func = new SimpleHash[seeds.length];

    public static void addValue(String value)
    {
        for(SimpleHash f : func)//将字符串value哈希为8个或多个整数，然后在这些整数的bit上变为1
            bits.set(f.hash(value),true);
    }
    
    public static void add(String value)
    {
        if(value != null) addValue(value);
    }
    
    public static boolean contains(String value)
    {
        if(value == null) return false;
        boolean ret = true;
        for(SimpleHash f : func)//这里其实没必要全部跑完，只要一次ret==false那么就不包含这个字符串
            ret = ret && bits.get(f.hash(value));
        return ret;
    }
    
    public static void main(String[] args) {
        String value = "xkeyideal@gmail.com";
        for (int i = 0; i < seeds.length; i++) {
            func[i] = new SimpleHash(DEFAULT_SIZE, seeds[i]);
        }
        add(value);
        System.out.println(contains(value));
    }
}

class SimpleHash {//这玩意相当于C++中的结构体

    private int cap;
    private int seed;

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

    public int hash(String value) {//字符串哈希，选取好的哈希函数很重要
        int result = 0;
        int len = value.length();
        for (int i = 0; i < len; i++) {
            result = seed * result + value.charAt(i);
        }
        return (cap - 1) & result;
    }
}