个人作业(统计单词)

输出某个英文文本文件中 26 字母出现的频率,由高到低排列,并显示字母出现的百分比,精确到小数点后面两位:

package test;
import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.text.DecimalFormat;
import java.text.NumberFormat;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Map;
 
public class W1 {

	public static void main(String[] args) throws IOException {
		try {
			//IO操作读取文件内容
			FileReader fr = new FileReader("d:\\文件\\单词.txt");
			BufferedReader br = new BufferedReader(fr);
			NumberFormat nf = NumberFormat.getInstance();
			 
			// 设置精确到小数点后2位
	 
			nf.setMaximumFractionDigits(2);
			HashMap<String, Integer> map = new HashMap<String, Integer>();
			
			String string =null;
			Integer count = 0;//每个字母的次数
			Integer total = 0;//总共多少个字母
			
			while ((string=br.readLine())!=null) {
				char[] ch = string.toCharArray();
				
				for (int i = 0; i < ch.length; i++) {
					if (ch[i] > 'A' && ch[i]< 'z') {
						
					total++;
					ch[i] = Character.toLowerCase(ch[i]);
					count = map.get(ch[i]+"");
					if (count == null) {
						count = 1;
					}else {
						count++;
					}
					map.put(ch[i]+"", count);
				}
				}
			}
			 ArrayList<String> list = new ArrayList<String>();
	         list.addAll(map.keySet());  //将单词添加到list中
	         
	         //排序按照出现次数降序排列
	         for(int i = 0;i < list.size();i++)
	         {
	             
	             for(int j = 0;j < (list.size() - i-1);j++)     //list.size() - i-1因为要用到i+1要考虑是否超出范围的问题
	             {
	                 
	                 if(map.get(list.get(j)) < map.get(list.get(j+1)))
	                 {
	                     String t = list.get(j);
	                     list.set(j, list.get(j+1));
	                     list.set( j+1, t);
	                 }
	             }
	         }
	         for(int i = 0 ; i < list.size();i++)
				{
					System.out.println(list.get(i) + ":" + map.get(list.get(i)) +"   "+ nf.format((float)(map.get(list.get(i)))*100/total) + "%");
				}
			
			
		} catch (FileNotFoundException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
	}
	
	
	
	
}

  截图

1.输出单个文件中的前 N 个最常出现的英语单词。

2.输出文件中所有不重复的单词,按照出现次数由多到少排列,出现次数同样多的,以字典序排列。

3.指定文件目录,对目录下每一个文件执行统计的操作。

4.指定文件目录,是会递归遍历目录下的所有子目录的文件进行统计单词的功能。

package test;
import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Scanner;


public class W2 {


public static String StatList(String str) {
	StringBuffer sb = new StringBuffer();
	HashMap<String ,Integer> has = new HashMap<String ,Integer> (); // 打开一个哈希表
	String[] slist = str.split("[^a-zA-Z\']+");
	for (int i = 0; i < slist.length; i++) 
	{
		if (!has.containsKey(slist[i])) 
		{ 
		       has.put(slist[i], 1);
		} 
		else 
		{
		       has.put(slist[i],has.get(slist[i])+1 );
		}
	}
	Iterator<String> iterator = has.keySet().iterator();
	String a[]=new String[100];
	int s[]=new int[100];
	int n=15;
	int judge;
	Scanner in=new Scanner(System.in);
	System.out.println("输入前n个最常出现的单词:");
	n=in.nextInt();
	for(int i=0;i<n;i++)
	{
	    iterator = has.keySet().iterator();
	    while(iterator.hasNext())
	    {
	    	String word = (String) iterator.next();
	    	if(s[i]<has.get(word))
	    	{
	    		s[i]=has.get(word);
	    		a[i]=word;
	    	}
	     }
	    judge=woor(a[i]);
	    if(judge==1)
	    {
	    	n++;
	    	has.remove(a[i]);
	    }
	    else
	    {
	     sb.append("单词:").append(a[i]).append(" 次数").append(has.get(a[i])).append("\r\n");
	     has.remove(a[i]);
	    }
	}
	     return sb.toString();
	}


	public static void main(String[] args) 
	{
		File file = new File("d:\\文件");
//		// TODO Auto-generated method stub
//		ArrayList<String> fil=getFiles("d:\\文件");//目录下的文件
		ArrayList<String> fil=getDirectory(file);//目录下的文件和子目录里的文件
		for(int i=0;i<fil.size();i++)
		{
		String filePath = fil.get(i);
		//String filePath = "d:\\文件\\单词.txt";
		String sz=W3.readTxtFile(filePath);
		String ltxt=null;
		System.out.println(ltxt=StatList(sz)); 
		try {
		W3.daochu(ltxt);
		} catch (IOException e) {
		// TODO Auto-generated catch block
		e.printStackTrace();
		}
		}
		
	}
	
	public static int woor(String a)
	{
		int n=0;
		String[] biao= {"a","the","an","and"};
		for(int i=0;i<biao.length;i++)
		{
			if(biao[i].equals(a))
			{
				n=1;
			}
		}
		return n;
	}
	
	public static ArrayList<String> getFiles(String path) {
	    ArrayList<String> files = new ArrayList<String>();
	    File file = new File(path);
	    File[] tempList = file.listFiles();
	    for (int i = 0; i < tempList.length; i++) {
	        if (tempList[i].isFile()) {
	            files.add(tempList[i].toString());
	        }
	        if (tempList[i].isDirectory()) {
	        }
	    }
	    return files;
	}
	
	private static ArrayList<String> getDirectory(File file) {
		ArrayList<String> files = new ArrayList<String>();
		ArrayList<String> files1 = new ArrayList<String>();
	    //获取该目录下的文件列表
	    File flist[] = file.listFiles();
	    for (File f : flist) {
	        if (f.isDirectory()) {
	            // 如果f是一个目录
	            files1=getFiles(f.getAbsolutePath());
	            files.addAll(files1);
	           
	            getDirectory(f);
	        } else {
	            //如果f是一个文件
	            files.add(f.getAbsolutePath());
	        }
	    }
	    return files;
	}


}

  

package test;

import java.io.BufferedReader; 
import java.io.File; 
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter; 
//import java.io.Reader; 
//从文本文档中读入
public class W3 {
	public static String readTxtFile(String filePath){ 
		try { 
			String encoding="GBK"; 
			File file=new File(filePath); 
			if(file.isFile() && file.exists()){ //判断文件是否存在 
			InputStreamReader read = new InputStreamReader( 
			new FileInputStream(file),encoding);//考虑到编码格式 
			BufferedReader bufferedReader = new BufferedReader(read); 
			String lineTxt = null;
			String lineText="";
			while((lineTxt = bufferedReader.readLine()) != null)
				{ 
				lineText+=(lineTxt); 
				} 
			read.close(); 
			return lineText;
			}
			else
				{ 
				System.out.println("找不到指定的文件"); 
				} 
			} catch (Exception e) { 
			System.out.println("读取文件内容出错"); 
			e.printStackTrace(); 
			} 
			return null;
		} 
		public static void daochu(String a) throws IOException
		{
			File file=new File("d:\\文件\\c.txt");
			FileOutputStream fos=new FileOutputStream(file);
			OutputStreamWriter osw = new OutputStreamWriter(fos,"UTF-8");
			osw.append(a);
			osw.close();
			fos.close();
		}
}

  

package test;

import java.io.BufferedReader; 
import java.io.File; 
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter; 
//import java.io.Reader; 
//从文本文档中读入
public class W3 {
	public static String readTxtFile(String filePath){ 
		try { 
			String encoding="GBK"; 
			File file=new File(filePath); 
			if(file.isFile() && file.exists()){ //判断文件是否存在 
			InputStreamReader read = new InputStreamReader( 
			new FileInputStream(file),encoding);//考虑到编码格式 
			BufferedReader bufferedReader = new BufferedReader(read); 
			String lineTxt = null;
			String lineText="";
			while((lineTxt = bufferedReader.readLine()) != null)
				{ 
				lineText+=(lineTxt); 
				} 
			read.close(); 
			return lineText;
			}
			else
				{ 
				System.out.println("找不到指定的文件"); 
				} 
			} catch (Exception e) { 
			System.out.println("读取文件内容出错"); 
			e.printStackTrace(); 
			} 
			return null;
		} 
		public static void daochu(String a) throws IOException
		{
			File file=new File("d:\\文件\\c.txt");
			FileOutputStream fos=new FileOutputStream(file);
			OutputStreamWriter osw = new OutputStreamWriter(fos,"UTF-8");
			osw.append(a);
			osw.close();
			fos.close();
		}

}

  

 截图:

 

 

posted on 2019-04-28 21:18  一往无前!  阅读(183)  评论(0编辑  收藏  举报