app7.java

词频统计程序。具体功能是在当前目录下读取文本文件

/**
 * AWT Sample application
 *
 * @author 
 * @version 1.00 07/10/24
 */
import java.util.*;
import java.util.regex.*;
import java.io.*;

public class App7 {
    
    public static void main(String[] args) throws IOException{
        // Create application frame.
        BufferedReader buf=new BufferedReader(new FileReader("english.txt"));
        System.out.println("读取当前目录下的文本文件 english.txt");
        StringBuffer sbuf=new StringBuffer();
        String line=null;
        while((line=buf.readLine())!=null){
        	sbuf.append(line);
        }
        buf.close();
        Pattern expression=Pattern.compile("[a-zA-Z]+");
        String string1=sbuf.toString().toLowerCase();
        Matcher matcher=expression.matcher(string1);
        TreeMap myTreeMap=new TreeMap();
        int n=0;
        Object word=null;
        Object num=null;
        while(matcher.find()){
        	word=matcher.group();
        	n++;
        	if(myTreeMap.containsKey(word)){
        		num=myTreeMap.get(word);
        		Integer count=(Integer)num;
        		myTreeMap.put(word,new Integer(count.intValue()+1));
        	}
        	else{
        		myTreeMap.put(word,new Integer(1));
        	}
        }
        System.out.println("统计分析如下：");
        System.out.println("\t 文章中单词总数"+n+"个");
        System.out.println("\t 文章中不同单词"+myTreeMap.size()+"个");
        System.out.println("具体信息在当前目录下的result.txt中");
        BufferedWriter bufw=new BufferedWriter(new FileWriter("result.txt"));
        Iterator iter=myTreeMap.keySet().iterator();
        Object key=null;
        while(iter.hasNext()){
        	key=iter.next();
        	bufw.write((String)key+":"+myTreeMap.get(key));
        	bufw.newLine();
        }
        bufw.write("english.txt中单词总数"+n+"个");
        bufw.newLine();
        bufw.write("english.txt中不同单词"+myTreeMap.size()+"个");
        bufw.close();
    }
}