/** * 计算 Bloom Filter的bit位数m * * <p>See http://en.wikipedia.org/wiki/Bloom_filter#Probability_of_false_positives for the * formula. * * @param n 预期数据量 * @param p 误判率 (must be 0 < p < 1) */
@VisibleForTesting
static long optimalNumOfBits(long n, double p) {  if (p == 0) {  p = Double.MIN_VALUE;  }  return (long) (-n * Math.log(p) / (Math.log(2) * Math.log(2)));
}  /** * 计算最佳k值，即在Bloom过滤器中插入的每个元素的哈希数 * * <p>See http://en.wikipedia.org/wiki/File:Bloom_filter_fp_probability.svg for the formula. * * @param n 预期数据量 * @param m bloom filter中总的bit位数 (must be positive) */
@VisibleForTesting
static int optimalNumOfHashFunctions(long n, long m) {  // (m / n) * log(2), but avoid truncation due to division!  return Math.max(1, (int) Math.round((double) m / n * Math.log(2)));
}

public <T> boolean put(  T object, Funnel<? super T> funnel, int numHashFunctions, LockFreeBitArray bits) {  long bitSize = bits.bitSize();  //利用MurmurHash3得到数据的hash值对应的字节数组  byte[] bytes = Hashing.murmur3_128().hashObject(object, funnel).getBytesInternal();  //取低8个字节、高8个字节，转成long类型  long hash1 = lowerEight(bytes);  long hash2 = upperEight(bytes);  boolean bitsChanged = false;  //这里的combinedHash = hash1 + i * hash2  long combinedHash = hash1;  //根据combinedHash，得到放入的元素在bit数组中的k个位置，将其置1  for (int i = 0; i < numHashFunctions; i++) {  bitsChanged |= bits.set((combinedHash & Long.MAX_VALUE) % bitSize);  combinedHash += hash2;  }  return bitsChanged;
}

package com.qunar.sage.wang.common.bloom.filter;  import com.google.common.base.Charsets;
import com.google.common.hash.BloomFilter;
import com.google.common.hash.Funnel;
import com.google.common.hash.Funnels;
import com.google.common.hash.PrimitiveSink;
import lombok.AllArgsConstructor;
import lombok.Builder;
import lombok.Data;
import lombok.ToString;  /** * BloomFilterTest * * @author sage.wang * @date 18-5-14 下午5:02 */
public class BloomFilterTest {  public static void main(String[] args) {  long expectedInsertions = 10000000;  double fpp = 0.00001;  BloomFilter<CharSequence> bloomFilter = BloomFilter.create(Funnels.stringFunnel(Charsets.UTF_8), expectedInsertions, fpp);  bloomFilter.put("aaa");  bloomFilter.put("bbb");  boolean containsString = bloomFilter.mightContain("aaa");  System.out.println(containsString);  BloomFilter<Email> emailBloomFilter = BloomFilter  .create((Funnel<Email>) (from, into) -> into.putString(from.getDomain(), Charsets.UTF_8),  expectedInsertions, fpp);  emailBloomFilter.put(new Email("sage.wang", "quanr.com"));  boolean containsEmail = emailBloomFilter.mightContain(new Email("sage.wangaaa", "quanr.com"));  System.out.println(containsEmail);  }  @Data  @Builder  @ToString  @AllArgsConstructor  public static class Email {  private String userName;  private String domain;  }  }