shiyan

import javax.xml.transform.Result;
import java.util.Arrays;
public class ParseText {
    //需要统计的字符串为
    private String text="Abstract-This paper presents an overview";
    private Result[] res;
    private int count;

    public ParseText(){
        res=new Result[100];
        count=0;
    }

    public void clean(){//数据清洗
        String flag="-.:;";
        for(int i=0;i<flags.length();i++){
            text=text.replace(flags.charAt(i)+".");
        }
    }

    //统计text中每次单词出现的次数
    public void parse(){
        //获取text中所有单词
        String[] words=text.split("\\s+");
        //为每个单词设置统计标志：true代表已经统计，false代表未被统计
        boolean[]flags=new boolean[words.length];
        for (int i=0;i<words.length;i++){
            flags[i]=false;
        }
        //统计每个单词出现的次数
        for (int i=0;i<words.length;i++){
            //统计words[i]在后续元素中出现的次数
            if (flags[i]==false){//表示尚未统计
                int times=1;
                for (int j=i+1;j<words.length;j++){
                    if (flags[j]==false&&words[i].equals(words[j])){
                        times++;
                        flags[j]=true;
                    }
                }
                //经统计结果写入Result[]数组
                res[count++]=new Result(words[i],times);
        }
    }
}

public void printResult(){
    Result[] tmp=new Result[count];
    tmp=Arrays.copyOfRange(res,0,count);
    //排序
    Arrays.sort(tmp);
    //输出结果
    for (int i=0;i<count;i++){
        System.out.println(tmp[i].getWords()+":"+tmp[i].getTimes());
    }
    }
    public static void main(String[] args){
        ParseText pt=new ParseText();
        pt.clean();
        pt.parse();
        pt.printResult();
    }
}