【第二周】Java实现英语文章词频统计（改进1）

本周根据杨老师的spec对英语文章词频统计进行了改进

1.需求分析：

对英文文章中的英文单词进行词频统计并按照有大到小的顺序输出，

2.算法思想：

（1）构建一个类用于存放英文单词及其出现的次数

class WordAndNum{
    public String word;
    public int num;
}

（2）从txt中获取字符串

BufferedReader in=new BufferedReader(new FileReader("D:\\test.txt"));
String line=null;
while((line=in.readLine())!=null)

（3）将字符串中的单词截取出来存到ArrayList中

ArrayList<WordAndNum> list=new ArrayList<WordAndNum>();

int index1=0;
int index2 = 0;
//截取英文单词
index1=line.indexOf(" ");
String word=line.substring(0,index1);
WordAndNum wdn=new WordAndNum();
wdn.word=word;
wdn.num=1;
list.add(wdn);
for(int i=index1+1;i<line.length();i++){
　　 if(line.charAt(i)==','||line.charAt(i)=='.'||line.charAt(i)==';'||line.charAt(i)==' '||line.charAt(i)=='?'){
        index2=i;
        WordAndNum wdn2=new WordAndNum();
        word=line.substring(index1+1,index2);
        wdn2.word=word;
        boolean flag=falsefor(int j=0;j<list.size();j++){
            if(list.get(j).word.equals(word)){
                wdn2.num=list.get(j).num+1;
                list.set(j, wdn2);
                flag=true;
                break;
            }
        }
        if(flag==false){
            wdn2.num=1;
            list.add(wdn2);
        }
        index1=index2;
    }
}

（4）对ArrayList进行冒泡排序

//冒泡排序
for(int i=0;i<list.size();i++){
     for(int j=0;j<list.size()-i-1;j++){
      if(list.get(j).num<list.get(j+1).num){
          WordAndNum wd1=list.get(j);
          WordAndNum wd2=list.get(j+1);
          list.set(j, wd2);
          list.set(j+1, wd1);
          }
     }
}

3.具体代码

 package ruan.jian.gong.cheng;

 import java.io.BufferedReader;
 import java.io.FileReader;
 import java.util.ArrayList;

 class WordAndNum{
     public String word;
     public int num;
 }

 public class wordNum2 {
     public static void main(String[] args) {
         try{
             BufferedReader in=new BufferedReader(new FileReader("D:\\test.txt"));
             String line=null;
             ArrayList<WordAndNum> list=new ArrayList<WordAndNum>();
             while((line=in.readLine())!=null){
                 int index1=0;
                 int index2 = 0;
                 //截取英文单词
                 index1=line.indexOf(" ");
                 String word=line.substring(0,index1);
                 WordAndNum wdn=new WordAndNum();
                 wdn.word=word;
                 wdn.num=1;
                 list.add(wdn);
                 for(int i=index1+1;i<line.length();i++){
                     if(line.charAt(i)==','||line.charAt(i)=='.'||line.charAt(i)==';'||line.charAt(i)==' '||line.charAt(i)=='?'){
                         index2=i;
                         WordAndNum wdn2=new WordAndNum();
                         word=line.substring(index1+1,index2);
                         wdn2.word=word;
                         boolean flag=false;
                         for(int j=0;j<list.size();j++){
                             if(list.get(j).word.equals(word)){
                                 wdn2.num=list.get(j).num+1;
                                 list.set(j, wdn2);
                                 flag=true;
                                 break;
                             }
                         }
                         if(flag==false){
                             wdn2.num=1;
                             list.add(wdn2);
                         }
                         index1=index2;
                     }
                 }
             }
             //冒泡排序
             for(int i=0;i<list.size();i++){
                 for(int j=0;j<list.size()-i-1;j++){
                     if(list.get(j).num<list.get(j+1).num){
                         WordAndNum wd1=list.get(j);
                         WordAndNum wd2=list.get(j+1);
                         list.set(j, wd2);
                         list.set(j+1, wd1);
                     }
                 }
             }
             for(int i=0;i<list.size();i++){
                 System.out.println(list.get(i).word+"==="+list.get(i).num);
             }
         }catch(Exception e){
             e.printStackTrace();
         }

     }
 }

4.以如下英文文章为例，输出结果为

5.结果分析:可以对英文文章进行词频统计并按从大到小进行输出