import java.util.HashMap;
import java.util.Iterator;
import java.util.Map;
public class SimilarDegreeByCos
{
  /*
   * 計算兩個字符串(英文字符)的相似度，簡單的余弦計算，未添權(quán)重
   */
   public static double getSimilarDegree(String str1, String str2)
   {
    //創(chuàng)建向量空間模型，使用map實現(xiàn)，主鍵為詞項，值為長度為2的數(shù)組，存放著對應詞項在字符串中的出現(xiàn)次數(shù)
     Map<String, int[]> vectorSpace = new HashMap<String, int[]>();
     int[] itemCountArray = null;//為了避免頻繁產(chǎn)生局部變量，所以將itemCountArray聲明在此
     //以空格為分隔符，分解字符串
     String strArray[] = str1.split(" ");
     for(int i=0; i<strArray.length; ++i)
     {
       if(vectorSpace.containsKey(strArray[i]))
         ++(vectorSpace.get(strArray[i])[0]);
       else
       {
         itemCountArray = new int[2];
         itemCountArray[0] = 1;
         itemCountArray[1] = 0;
         vectorSpace.put(strArray[i], itemCountArray);
       }
     }
     strArray = str2.split(" ");
     for(int i=0; i<strArray.length; ++i)
     {
       if(vectorSpace.containsKey(strArray[i]))
         ++(vectorSpace.get(strArray[i])[1]);
       else
       {
         itemCountArray = new int[2];
         itemCountArray[0] = 0;
         itemCountArray[1] = 1;
         vectorSpace.put(strArray[i], itemCountArray);
       }
     }
     //計算相似度
     double vector1Modulo = 0.00;//向量1的模
     double vector2Modulo = 0.00;//向量2的模
     double vectorProduct = 0.00; //向量積
     Iterator iter = vectorSpace.entrySet().iterator();
     while(iter.hasNext())
     {
       Map.Entry entry = (Map.Entry)iter.next();
       itemCountArray = (int[])entry.getValue();
       vector1Modulo += itemCountArray[0]*itemCountArray[0];
       vector2Modulo += itemCountArray[1]*itemCountArray[1];
       vectorProduct += itemCountArray[0]*itemCountArray[1];
     }
     vector1Modulo = Math.sqrt(vector1Modulo);
     vector2Modulo = Math.sqrt(vector2Modulo);
     //返回相似度
    return (vectorProduct/(vector1Modulo*vector2Modulo));
   }
   /*
   *
   */
   public static void main(String args[])
   {
     String str1 = "gold silver truck";
     String str2 = "Shipment of gold damaged in a fire";
     String str3 = "Delivery of silver arrived in a silver truck";
     String str4 = "Shipment of gold arrived in a truck";
     String str5 = "gold gold gold gold gold gold";
     System.out.println(SimilarDegreeByCos.getSimilarDegree(str1, str2));
     System.out.println(SimilarDegreeByCos.getSimilarDegree(str1, str3));
     System.out.println(SimilarDegreeByCos.getSimilarDegree(str1, str4));
     System.out.println(SimilarDegreeByCos.getSimilarDegree(str1, str5));
   }
}