Java记录文件中单词的书数量

一.统计所给出文件中英文字母出现的频率（区分大小写），并且按着出现频率倒序输出

   将文件用BufferedReader读取;

   对每行进行读取在进行分割成单词;

   对单词进行循环判断是否在A-Z，a-z之间，若在存储到数组里计数.

package li;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.text.DecimalFormat;
import java.util.ArrayList;
import java.util.List;

public class baifenbi {
    public static void main(String[] args)throws IOException     //IOException用来读写数据
    {
        List<Integer> list=new ArrayList<>(); //定义一个integer类型的list变量
        DecimalFormat df=new DecimalFormat("######0.00");  //格式化十进制数字
         FileInputStream fip = new FileInputStream ("C:\\Users\\28681\\Desktop\\Harry Potter and the Sorcerer's Stone.txt");
                                                     //导入文件
        InputStreamReader reader = new InputStreamReader(fip, "gbk");   //从字节流到字符流的桥接器
        StringBuffer sb = new StringBuffer();
        while (reader.ready()) {
            sb.append((char) reader.read());
        }
        reader.close();
        fip.close();
        
        int i;
        String A=sb.toString();
        String M="abcdefghijklmnopqrstuvwxyz";
        String temp = "";
        char NUM[]=new char[A.length()];
        char Z[]=new char[26];
        int X[]=new int[26];
        int MAX=0;
        Z=M.toCharArray();
        for(int k=0;k<26;k++)
        {
            X[k]=0;
        for(i=0;i<A.length();i++)
        {
            NUM[i]=A.charAt(i);
            if(Z[k]==NUM[i]||Z[k]==ch(NUM[i]))
            {
                X[k]++;
            }
        }
        }
        System.out.println("这篇文章中英文字母个数分别为:");
        
        double sum=0;
        System.out.println("排序如下:");
        for(i=0;i<25;i++)
            for(int k=0;k<25-i;k++)
            {
                if(X[k]<X[k+1])
                {
                    int temp2=X[k];
                    X[k]=X[k+1];
                    X[k+1]=temp2;
                    char temp3=Z[k];
                    Z[k]=Z[k+1];
                    Z[k+1]=temp3;
                }
            }
        for(i=0;i<26;i++) {
            sum=sum+X[i];
        }
        for(i=0;i<26;i++)
        {
            double jkl=(X[i])/sum*100;
        System.out.println(Z[i]+"字母个数为:"+X[i]+"字母频率为："+df.format(jkl)+"%");
        }
        
    }
    static char ch(char c)
    {
        if(!(c>=97&&c<=122))
            c+=32;
        return c;
    }

}

 

二、输出单个文件的前N个最常出现的英文单词

package com.wenjian;
import java.io.File;
import java.util.Scanner;
import java.io.FileNotFoundException;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Set;
public class nword {
    public static <type> void main (String[] args) throws FileNotFoundException {
        File file=new File("E:\\Harry Potter and the Sorcerer's Stone.txt");                 
        if(!file.exists()){
            System.out.println("未找到文件");
            return;
        }
        Scanner in=new Scanner(System.in);
        System.out.println("请输入前n个常用单词");
        int n=in.nextInt();
        Scanner scanner=new Scanner(file);
        HashMap<String,Integer> hashMap=new HashMap<String,Integer>();
        while(scanner.hasNextLine()) {
            String line=scanner.nextLine();
            String[] lineWords=line.split(" ");          
            Set<String> wordSet=hashMap.keySet();
            for(int i=0;i<lineWords.length;i++) {
                if(wordSet.contains(lineWords[i])) {//判断set集合里是否有该单词
                    Integer number=hashMap.get(lineWords[i]);//若有次数+1
                    number++;
                    hashMap.put(lineWords[i], number); 
                    }
                else {//没有就将其放入set里，次数为1
                    hashMap.put(lineWords[i], 1);
                }
            }
        }
        //计算总体单词数
        int sum=0;
        Iterator<String> it=hashMap.keySet().iterator();
        while(it.hasNext()){
            sum+=hashMap.get(it.next());
        }
        //输出前n个单词
        while(n>0)
        {
            Iterator<String> iterator=hashMap.keySet().iterator();
            int max=0;
            String maxword=null;
            while(iterator.hasNext()){
                String word=iterator.next();
                
                if(hashMap.get(word)>max) {                         
                    max=hashMap.get(word);
                    maxword=word;
                }
            }  
            hashMap.remove(maxword);
            double ans=max*1.0/sum*100;
            if(!maxword.equals("")) {
                System.out.println(maxword+":"+max);
                n--;
            }
            
        }
    }
}