统计文件中单词的频率,给出前N的单词

package test10;

import java.io.*;
import java.util.*;
import java.util.Map.Entry;

public class Frequency
{
    public static int n=0;//
    public static void main(String[] args) {
    Scanner sc=new Scanner(System.in);
    String s;
    int count=0;
    int num=1;
    //作为FileReader和FileWriter读取的对象
    String file1="C:\\Users\\DELL\\Desktop\\Harry Potter and the Sorcerer's Stone.txt";
   // String file2="d:/danci.txt";
    try
    {
      BufferedReader a=new BufferedReader(new FileReader(file1));
      //BufferedWriter b=new BufferedWriter(new FileWriter(file2));
      StringBuffer c=new StringBuffer();
      //将文件内容存入StringBuffer中
      while((s = a.readLine()) != null) 
      {
            //用于拼接字符串
            c.append(s);
      }
      //将StringBuffer转换成String,然后再将所有字符转化成小写字符
      String m=c.toString().toLowerCase();
      //匹配由数字和26个字母组成的字符串
      String [] d=m.split("[^a-zA-Z0-9]+");
      //遍历数组将其存入Map<String, Integer>中
      Map<String , Integer> myTreeMap=new  TreeMap<String, Integer>();
      for(int i = 0; i < d.length; i++) {
          //containsKey()方法用于检查特定键是否在TreeMap中映射
            if(myTreeMap.containsKey(d[i])) {
                count = myTreeMap.get(d[i]);
                myTreeMap.put(d[i], count + 1);
            }
            else {
                myTreeMap.put(d[i], 1);
            }
        } 
    //通过比较器实现排序
      List<Map.Entry<String, Integer>> list = new ArrayList<Map.Entry<String, Integer>>(myTreeMap.entrySet());
    //按降序排序
      Collections.sort(list, new Comparator<Map.Entry<String, Integer>>() {
          
            public int compare(Entry<String, Integer> k1, Entry<String, Integer> k2) {
                //返回两个单词出现次数较多的那个单词的出现次数
                return k2.getValue().compareTo(k1.getValue());
            }
            
        });
       System.out.println("请输入N:");
        n=sc.nextInt();
      for(Map.Entry<String, Integer> map : list) {
            if(num <= n) {
               //按内容输出到指定文件中去
               // b.write("出现次数第" + num + "的单词为:" + map.getKey() + ",出现频率为" + map.getValue() + "次");
                //换行
              //  b.newLine();
                //输出到程序控制台
                System.out.println(map.getKey() + ":" + map.getValue());
                num++;
            }
            //输出完毕退出
            else break;
        }
        //关闭文件指针
        a.close();
       // b.close();
    }
    catch(FileNotFoundException e)
    {
        System.out.println("找不到指定文件");
    }
    catch(IOException e)
    {
        System.out.println("文件读取错误");
    }
    System.out.println("输出完成");
}
}

  

猜你喜欢

转载自www.cnblogs.com/xiatian21/p/11794773.html