利用hanlp比较文本相似度

import com.hankcs.hanlp.seg.common.Term;
import com.hankcs.hanlp.tokenizer.StandardTokenizer;

import org.apache.commons.lang3.StringUtils;
import org.jsoup.Jsoup;
import org.jsoup.safety.Whitelist;

import java.math.BigInteger;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
import java.util.Map;

import static com.hankcs.hanlp.dictionary.stopword.CoreStopWordDictionary.*;
import static java.lang.Math.log;

public class MySimHash {
    private String tokens; //字符串
    private BigInteger strSimHash;//字符产的hash值
    private int hashbits = 64; // 分词后的hash数;
    public MySimHash(){

    }

    public MySimHash(String tokens) {
        this.tokens = tokens;
        this.strSimHash = this.simHash();
    }

    private MySimHash(String tokens, int hashbits) {
        this.tokens = tokens;
        this.hashbits = hashbits;
        this.strSimHash = this.simHash();
    }


    /**
     * 清除html标签
     * @param content
     * @return
     */
    private String cleanResume(String content) {
        // 若输入为HTML,下面会过滤掉所有的HTML的tag
        content = Jsoup.clean(content, Whitelist.none());
        content = StringUtils.lowerCase(content);
        String[] strings = {" ", "\n", "\r", "\t", "\\r", "\\n", "\\t", " "};
        for (String s : strings) {
            content = content.replaceAll(s, "");
        }
        return content;
    }


    /**
     * 这个是对整个字符串进行hash计算
     * @return
     */
    private BigInteger simHash() {

        tokens = cleanResume(tokens); // cleanResume 删除一些特殊字符

        int[] v = new int[this.hashbits];

        List<Term> termList = StandardTokenizer.segment(this.tokens); // 对字符串进行分词

        //对分词的一些特殊处理 : 比如: 根据词性添加权重 , 过滤掉标点符号 , 过滤超频词汇等;
        Map<String, Integer> weightOfNature = new HashMap<String, Integer>(); // 词性的权重
        weightOfNature.put("n", 2); //给名词的权重是2;
        Map<String, String> stopNatures = new HashMap<String, String>();//停用的词性 如一些标点符号之类的;
        stopNatures.put("