Java编程：统计文本文件中单词出现频率

从文本文件中读取文本，文本文件名被作为命令行参数传递，统计单词不区分大小写。如果第一个字符不是字母，就不统计这个单词，以字典序显示输出，每个单词后面紧跟它的出现次数。

方法一

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

public class Test{
    public static void main(String args[])throws Exception{
        File file = new File("d:\\src\\Test.java");
        display(file);
    }
    public static void display(File file)throws Exception{
        BufferedReader br = new BufferedReader(new FileReader(file));
        String line = null;
        TreeMap<String,Integer> tm = new TreeMap<String,Integer>();
        while((line=br.readLine())!=null){
            line.toLowerCase();
            String reg1 = "\\s+";
            String reg2 ="^[a-zA-Z]\\w*";
            String str[] = line.split(reg1);
            for(String s: str){

                if(s.matches(reg2)){
                    if(!tm.containsKey(s)){
                        tm.put(s,1);
                    }
                    else{
                        tm.put(s,tm.get(s)+1);
                    }
                }
            }
        }
        System.out.println(tm);
    }
}

方法二

思路： 1、将文件内容存入StringBuffer中。 2、利用split()函数分割字符串，可按(“，”，“.”，“！”，“空格”，“回车”)分割，得到一个数组。 3、遍历数组，将其放入一个Map <String,Integer>中,key=单词，value=单词出现的次数。 4、如要求出文件中出现频率最高的几个单词，则要对Map进行排序。

//以下是实现一个文件中出现频率最高的单词的统计

//FileWordCount.java主函数所在文件

import java.io.BufferedReader;
import java.io.FileNotFoundException;
import java.io.FileReader;
import java.io.IOException;
import java.util.*;

/**
 * Created by IntelliJ IDEA.
 * User: FLY
 * Date: 11-9-13
 * Time: 下午3:59
 * To change this template use File | Settings | File Templates.
 */
public class FileWordCount {
    public static void main(String[] args) {
        try {
            BufferedReader br = new BufferedReader(new FileReader("D:\\test.txt"));
            String s;
            StringBuffer sb = new StringBuffer();
            while ((s = br.readLine()) != null) {
                sb.append(s);
            }
            Map<String,Integer> map = new HashMap<String, Integer>();
            StringTokenizer st = new StringTokenizer(sb.toString(),",.! \n");
            while (st.hasMoreTokens()) {
                String letter = st.nextToken();
                int count;
                if (map.get(letter) == null) {
                    count = 1;
                } else {
                    count = map.get(letter).intValue() + 1;
                }
                map.put(letter,count);
            }
            Set<WordEntity> set = new TreeSet<WordEntity>();
            for (String key : map.keySet()) {
                set.add(new WordEntity(key,map.get(key)));
            }
            // 自己拼接字符串，输出我们想要的字符串格式
            System.out.println("输出形式一：");
            for (Iterator<WordEntity> it = set.iterator(); it.hasNext(); ) {
                WordEntity w = it.next();
                System.out.println("单词:" + w.getKey() + " 出现的次数为： " + w.getCount());
            }
            // 直接打印 WordEntity 对象，实现我们想要的输出效果，只需在WordEntity类中重写toString()方法
            System.out.println("输出形式二：");
            for (Iterator<WordEntity> it = set.iterator(); it.hasNext(); ) {
                WordEntity w = it.next();
                System.out.println(w);
            }
            // 我们可以控制只输出前三名来
            System.out.println("输出形式三：");
            int count = 1;
            for (Iterator<WordEntity> it = set.iterator(); it.hasNext(); ) {
                WordEntity w = it.next();
                System.out.println("第" + count + "名为单词:" + w.getKey() + " 出现的次数为： "
                        + w.getCount());
                if (count == 3)// 当输出3个后跳出循环
                    break;
                count++;
            }
        } catch (FileNotFoundException e) {
            System.out.println("文件未找到~！");
        } catch (IOException e) {
            System.out.println("文件读异常~！");
        }
    }
}

//WordEntity.java文件

/**
 * Created by IntelliJ IDEA.
 * User: FLY
 * Date: 11-9-13
 * Time: 下午4:57
 * To change this template use File | Settings | File Templates.
 */
public class WordEntity implements Comparable<WordEntity> {
    private String key;
    private Integer count;
    public WordEntity (String key, Integer count) {
        this.key = key;
        this.count = count;
    }
    public int compareTo(WordEntity o) {
        int cmp = count.intValue() - o.count.intValue();
        return (cmp == 0 ? key.compareTo(o.key) : -cmp);
        //只需在这儿加一个负号就可以决定是升序还是降序排列  -cmp降序排列，cmp升序排列
        //因为TreeSet会调用WorkForMap的compareTo方法来决定自己的排序
    }

    @Override
    public String toString() {
        return key + " 出现的次数为：" + count;
    }

    public String getKey() {
        return key;
    }

    public Integer getCount() {
        return count;
    }
}