小实验1 单词频次统计-流的运用

一、实验目的与内容

1. 实验目的

掌握Java流的主要方法及运用，自学文本、字符串处理方法。

2.  实验内容

扫描指定文件夹里面的所有文件，给出各个文件的属性信息。另外，针对每个文件（如A.txt）统计里面文章中单词的出现频次并输出统计结果到文件Sta_A.txt。Sta_A.txt文件包含A.txt文件里面每个单词出现的频次。

 3. 实验要求：

1. 指定文件夹里面所有的文件的属性都得列出，输出到property.txt。
2. 指定文件夹里面每个文件的单词频次都得统计，并保存到对应输出文件。输出文件中单词按频次降序排列。
3. 统计程序运行时间，包括总体运行时间和各个文件单词频次统计所花时间。cx

   package test;
   import java.io.*;
   import java.nio.charset.StandardCharsets;
   import java.util.*;
   import java.util.regex.*;
   public class WordsCount {
       public static void main(String []args){
           long start ,end,totalStart,totalEnd,different;
           totalStart=System.currentTimeMillis();//从程序执行开始计算总时间
           //指定文件夹路径
           String inputPath="D:/work/Internet coding/Week3 datasets";
           File folder= new File(inputPath);//定义文件夹
           if(!folder.isDirectory()){//老规矩判断一下
               System.out.println("Invalid folder path");
               return;
           }
   
           File[] files=folder.listFiles();
           if(files!=null){
               //输出文件属性到property.txt
               try{
                       FileOutputStream fileoutputStream=new FileOutputStream("D:/work/Internet coding/property.txt");
                       OutputStreamWriter outputStreamWriter=new OutputStreamWriter(fileoutputStream,StandardCharsets.UTF_16LE);//记事本右下角显示格式是这个
                       BufferedWriter bufferedWriter=new BufferedWriter(outputStreamWriter);
                       //输出提示
                       System.out.println("Write file properties into property.txt.");
                       start=System.currentTimeMillis();
                       for(File file:files){
                           //向propert中写入信息
                           bufferedWriter.write("File absolute path: "+file.getAbsoluteFile());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File canonical path: "+file.getCanonicalPath());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File path: "+file.length()+"bytes");
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File name: "+file.getName());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File length: "+file.length()+"bytes");
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File can read: "+file.canRead());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File can write: "+file.canWrite());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File can execute: "+file.canExecute());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File is hidden: "+file.isHidden());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.write("File last modified: "+file.lastModified());
                           bufferedWriter.newLine();//另起一行
                           bufferedWriter.newLine();//另起一行
                       }
                       bufferedWriter.close();//关闭缓冲流，强制将缓冲区中的数据写入到文件中，即使缓冲区中的数据还不满
                       end=System.currentTimeMillis();
                       different=end-start;
                       System.out.println("File properties have been written to property.txt.");
                       System.out.println("It cost "+different+" millisecond.\n");
               }catch(Exception e){
                       e.printStackTrace();
               }
   
               //单词统计
               for(File file:files) {
                   start=System.currentTimeMillis();
                   if (file.isFile()) {//我直接把四个txt文件放到一个Week3 datasets文件夹里了
                       // 使用buffer流对每个文件进行单词统计并输出到对应的统计结果文件
   
                       try {
                           FileInputStream fileInputStream=new FileInputStream(file);
                           InputStreamReader inputStreamReader=new InputStreamReader(fileInputStream,StandardCharsets.UTF_16LE);
                           BufferedReader bufferedReader=new BufferedReader(inputStreamReader);
   
                           //统计单词出现频次
                           Map<String,Integer> wordMap=new HashMap<>();
                           String s;
                           while((s= bufferedReader.readLine())!=null){
                               //利用正则表达式分割单词
                               //先全部转为小写好对其进行后面的一系列处理
                               s=s.toLowerCase();
                               String[] words=s.split("[^a-z]+");//除字母外全是分隔符
                               for(String word:words){
                                   if(word.length()>=1){
                                       //统计结果
                                       if(wordMap.containsKey(word)){
                                           wordMap.put(word,wordMap.get(word)+1);
                                       }
                                       else{
                                           wordMap.put(word,1);
                                       }
                                   }
                               }
                           }
   
                           //按value降序排序
                           List<Map.Entry<String,Integer>> wordList=new ArrayList<>(wordMap.entrySet());
                           wordList.sort((o1,o2)->o2.getValue().compareTo(o1.getValue()));
   
                           //输出统计结果结果到文件
                           String resultFileName = "D:/work/Internet coding/Week3 datasets/Sta_" + file.getName();
                           try{
                               FileOutputStream fileOutputStream=new FileOutputStream(resultFileName);
                               OutputStreamWriter outputStreamWriter=new OutputStreamWriter(fileOutputStream,StandardCharsets.UTF_16LE);
                               BufferedWriter bufferedWriter=new BufferedWriter(outputStreamWriter);
                               for(Map.Entry<String,Integer> map:wordList){
                                   bufferedWriter.write(map.getKey()+" "+map.getValue());
                                   bufferedWriter.newLine();
                               }
                               System.out.println("Word count statistics for"+file.getName()+" is done");
                           }catch(Exception e) {
                               e.printStackTrace();
                           }
                       }catch(Exception e){
                           e.printStackTrace();
                       }
                   }
                   end=System.currentTimeMillis();
                   different=end-start;
                   System.out.println("It took a total of "+different+" milliseconds to process the file "+file.getName()+"\n");
               }
   
           }
           totalEnd=System.currentTimeMillis();
           different=totalEnd-totalStart;
           System.out.println("The hole running time: "+different+" milliseconds");
       }
   }