Github地址：<>

项目设计

整体流程

函数功能

算法实现

计算hamming值

package Utils;

import com.hankcs.hanlp.HanLP;

import java.math.BigInteger;
import java.security.MessageDigest;
import java.util.List;

public class SimHashUtil {
    /*用MD5获取输入字符串对应的二进制编码*/
    public static String getHash(String str) {
        try {
            MessageDigest messageDigest = MessageDigest.getInstance("MD5");
            return new BigInteger(1, messageDigest.digest(str.getBytes("UTF-8"))).toString(2);
        } catch (Exception e) {
            e.printStackTrace();
            return str;
        }
    }
    /*计算simHash值*/
    public static String getSimHash(String str) {
        if (str.length() < 66) {
            System.out.println("输入文本过短");
        }
        int[] weight = new int[128];
        List<String> keywordList = HanLP.extractKeyword(str, str.length());
        int size = keywordList.size();
        int i = 0;
        for (String keyword : keywordList) {
            String hash = getHash(keyword);
            if (hash.length() < 128) {
                int distance = 128 - hash.length();
                for (int j = 0; j < distance; j++) {
                    hash += "0";
                }
            }
            for (int j = 0; j < weight.length; j++) {
                if (hash.charAt(j) == '1') {
                    weight[j] += (10 - (i / (size / 10)));
                } else {
                    weight[j] -= (10 - (i / (size / 10)));
                }
            }
            i++;
        }
        String simHash = "";
        for (int j = 0; j < weight.length; j++) {
            if (weight[j] > 0) {
                simHash += "1";
            } else simHash += "0";
        }
        return simHash;
    }
}

测试函数

package Utils;
public class HammingUtil {
   public static int getHammingDistance(String simHash1, String simHash2){
       if(simHash1.length()!=simHash2.length())
           return -1;
       int distance=0;
       System.out.println("str1的simHash值："+simHash1);
       System.out.println("str2的simHash值："+simHash2);
       for (int i=0;i<simHash1.length();i++){
           if(simHash1.charAt(i)!=simHash2.charAt(i))
               distance++;

       }
       System.out.println("海明距离为："+distance);
       return distance;
   }

   public static double getSimilarity(int distance){

       return 1-distance/128.0;
   }

}

异常处理

package Utils;

import java.io.*;

public class IOUtil {

    public static String readTxt(String txtPath) {
        String str = "";
        String strLine;
        // 将 txt文件按行读入 str中
        File file = new File(txtPath);
        FileInputStream fileInputStream = null;
        try {
            fileInputStream = new FileInputStream(file);
            InputStreamReader inputStreamReader = new InputStreamReader(fileInputStream, "UTF-8");
            BufferedReader bufferedReader = new BufferedReader(inputStreamReader);
            // 字符串拼接
            while ((strLine = bufferedReader.readLine()) != null) {
                str += strLine;
            }
            // 关闭资源
            inputStreamReader.close();
            bufferedReader.close();
            fileInputStream.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        return str;
    }

    public static void writeTxt(String  str,String txtPath){

        File file = new File(txtPath);
        FileWriter fileWriter = null;
        try {
            fileWriter = new FileWriter(file, true);
            fileWriter.write(str, 0, str.length());
            fileWriter.write("\r\n");
            // 关闭资源
            fileWriter.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

}

结果显示

性能分析

PSP分析