java实现读取一篇英文文章，统计其中每个单词出现的次数并排序输出

package com.test.string;

import java.io.BufferedReader;
import java.io.BufferedWriter;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.List;
import java.util.Map;
import java.util.TreeMap;
import java.util.Map.Entry;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
* java实现读取英文文章，统计其中每个单词出现的次数并输出
* @author halbert
*
*/
public class FileWordCount {

public void count() throws IOException{
BufferedReader reader = new BufferedReader(new FileReader("D:\\test\\english.txt"));
StringBuffer buffer = new StringBuffer();
String line = null;
while( (line = reader.readLine()) != null ){
buffer.append(line);
}
reader.close();
Pattern expression = Pattern.compile("[a-zA-Z]+");	//定义正则表达式匹配单词
String string = buffer.toString();
Matcher matcher = expression.matcher(string);
Map<string integer=""> map = new TreeMap<string integer="">();
String word = "";
int n = 0;
Integer times = 0;
while(matcher.find()){		//是否匹配单词
word = matcher.group();		//得到一个单词，树映射中的键
n++;
if( map.containsKey(word) ){	//如果该键存在，则表示单词出现过
times = map.get(word);		//得到单词出现的次数
map.put(word, times+1);
} else {
map.put(word, 1);	//否则单词是第一次出现，直接放入map
}
}
List<Map.Entry<string integer="">> list = new ArrayList<Map.Entry<string integer="">>(map.entrySet());
Comparator<Map.Entry<string integer="">> comparator = new Comparator<Map.Entry<string integer="">>(){

@Override
public int compare(Entry<string integer=""> left, Entry<string integer=""> right) {
return (left.getValue()).compareTo(right.getValue());
}

};
Collections.sort(list, comparator);
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("具体的信息在原文件目录的result.txt文件中");
BufferedWriter bufw = new BufferedWriter(new FileWriter("D:\\test\\result.txt"));
for(Entry<string integer=""> me : list){
bufw.write(me+"");
bufw.newLine();
}
bufw.write("english.txt中的单词总数" + n + "个");
bufw.newLine();
bufw.write("english.txt中不同单词" + map.size() + "个");
bufw.close();
}

public static void main(String[] args) {
try {
FileWordCount fwc = new FileWordCount();
fwc.count();
} catch (IOException e) {
e.printStackTrace();
}

}

}

</string></string></string></string></string></string></string></string></string>

统计分析如下：
t 文章中单词总数997个
具体的信息在当前目录的result.txt文件中