Custom Clustering algorithm based on MinHash

CustomClusterizator.java

/**
 * 
 */
package es.colbenson.sb.clustering;

import java.util.HashSet;
import java.util.Set;
import java.util.SortedSet;
import java.util.TreeSet;

import com.google.common.hash.HashFunction;
import com.google.common.hash.Hashing;

/**
 * @author Samuel García Martínez <samuelg@colbenson.es>
 *
 */
public class CustomClusterizator implements Clusterizator {

	private HashFunction function = Hashing.murmur3_128(17239195);
	
	public Set<String> proccessClusterIds(Set<String> set) {
		StringBuilder sb = new StringBuilder();
		
		SortedSet<Long> longHashes = new TreeSet<Long>(); 
		 
		for(String str : set) {
			longHashes.add(function.hashString(str).asLong());
		}
		
		for(Long longHash : longHashes) {
			sb.append(longHash);
		}
		
		Set<String> buckets = new HashSet<String>(1);
		buckets.add(function.hashString(sb.toString()).toString());
		
		return buckets;
	}
	
}