textfenhang(liuqiang).java

自己的一个判断词库的代码.能够很好的去除词库中的相同词汇.并保证词库的相异性

import java.io.*;
import java.util.*;
import java.lang.*;

public class TextFenhang
{
    public static Vector v=new Vector();

    private static void shuChu(String str)
    {
        StringTokenizer stoke=new StringTokenizer(str," \n、,.。");
        PrintWriter outputStream=null;
        //int n=str.countTokens();
        //String[] ss=new String[n];
        String s2=null;
        int i;
        try
        {
            outputStream=new PrintWriter(new FileOutputStream("D:/out1.txt"));
        }
        catch(FileNotFoundException e)
        {System.out.println("Error opening the file out.txt");}
        while(stoke.hasMoreTokens())
	    {
	        s2=stoke.nextToken();
	        for(i=0;i<TextFenhang.v.size();i++)
	        {
				if(s2.equals(v.get(i)))
				   {

					   break;
					   }

				}
		    if(i>=TextFenhang.v.size())
			{    v.addElement(s2);
	             outputStream.println(s2);
	             }
	    }
	    outputStream.close();
    }

    public static void main(String[] args)
    {
        try
        {
           BufferedReader inputStream=new BufferedReader(new FileReader("D:/ktokenizer.txt"));
           String s=null;
           while((s=inputStream.readLine())!=null)
           {
               shuChu(s);
           }
           inputStream.close();
        }
        catch(FileNotFoundException e)
        {
            System.out.println("File tokenizer was not found");

        }
        catch(IOException e)
        {
           System.out.println("Error reading from file tokenizer.txt");
        }
        for(int i=0;i<TextFenhang.v.size();i++)
        {
			System.out.println(v.get(i));
			}
    }

}