短文本聚合，长文本相似度

src/main/java/com/zhiweidata/titleAggregation/bean/Result.java

@@ -5,9 +5,10 @@
  * @author xuyimeng 
  * @date 2017年12月28日 上午11:52:42 
  * @version V1.0 
- */ /**
- * 
  */
+/**
+* 
+*/
 package com.zhiweidata.titleAggregation.bean;
 
 /**
@@ -16,23 +17,24 @@ package com.zhiweidata.titleAggregation.bean;
  * @author xuyimeng
  * @date 2017年12月28日 上午11:52:42
  */
-public class Result {
-	/**类簇名*/
+public class Result{
+	/** 类簇名 */
 	private String clusterName;
-	/**节点名*/
+	/** 节点名 */
 	private String datapointName;
-	/**索引位置*/
+	/** 索引位置 */
 	private Integer i;
-	/**simhash距离*/
+	/** simhash距离 */
 	private int simhash;
-	/**余弦算法相似度*/
+	/** 余弦算法相似度 */
 	private double cosSimilarity;
-	/**切割算法相似度*/
+	/** 切割算法相似度 */
 	private double cut;
 
-	public Result() {}
+	public Result() {
+	}
 
-	public Result(String clusterName, String datapointName, int simhash, double cosSimilarity, double cut,Integer i) {
+	public Result(String clusterName, String datapointName, int simhash, double cosSimilarity, double cut, Integer i) {
 		super();
 		this.clusterName = clusterName;
 		this.datapointName = datapointName;
@@ -96,4 +98,5 @@ public class Result {
 				+ simhash + ", cosSimilarity=" + cosSimilarity + ", cut=" + cut + "]";
 	}
 
+
 }

src/main/java/com/zhiweidata/titleAggregation/main/HCluster.java

 package com.zhiweidata.titleAggregation.main;
 
 import java.util.ArrayList;
+import java.util.Collections;
+import java.util.Comparator;
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
@@ -51,6 +53,14 @@ public class HCluster {
 				list.add(result);
 			}
 		}
+		
+		Collections.sort(list, new Comparator<Result>() {
+			@Override
+			public int compare(Result o1, Result o2) {
+				return o1.getI() - o2.getI();
+			}
+		});
+
 		return list;
 	}
 	/**

src/test/java/StartTest/ResultTest.java

@@ -6,15 +6,33 @@ import java.util.List;
 
 import org.ansj.domain.Term;
 import org.junit.Test;
-import org.nlpcn.commons.lang.util.AnsjArrays;
 
-import com.zhiweidata.titleAggregation.main.ClusterUtil;
+import com.zhiweidata.titleAggregation.bean.Result;
+import com.zhiweidata.titleAggregation.main.ClusterResult;
 import com.zhiweidata.titleAggregation.method.CosineSimilarity;
 import com.zhiweidata.titleAggregation.method.MySimHash;
 import com.zhiweidata.titleAggregation.util.AnsjSeg;
 
 public class ResultTest {
 	@Test 
+	public void test5() {
+		List<String> texts = new ArrayList<>();
+		texts.add("慰安妇纪录片遭截图制成表情包被网友质疑 腾讯致歉");
+		texts.add("慰安妇纪录片遭截图制成QQ表情包 配文：我真委屈");
+		texts.add("慰安妇纪录片遭截图制成QQ表情包 配文：我真委屈");
+		texts.add("慰安妇纪录片被做成表情包 QQ空间道歉");
+		texts.add("慰安妇纪录片遭截图制成表情包 配文：我真委屈");
+		texts.add("慰安妇纪录片遭截图制成表情包 网友质疑");
+		
+		List<Result> list = ClusterResult.getResult(texts);
+		for (Result result : list)
+		{
+			System.out.println("聚合标题："+result.getClusterName()+
+					"          标题："+result.getDatapointName());
+		}
+	}
+	
+	@Test
 	public void test4() {
 		AnsjSeg ansj = AnsjSeg.getInstance();
 		String text = "愤怒!慰安妇纪录片《二十二》被截图制作表情包";