java词频统计

主要利用JAVA 的map,arraylist方法进行词频统计

package count;
import java.io.BufferedReader;
import java.io.FileReader;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.TreeMap;
public class WordCount {
		public static void main(String args[]) throws Exception{
			BufferedReader  br=new BufferedReader(new FileReader("F:/oldman.txt")); //读取文件
			List<String> lists=new ArrayList<String>();
			String readline=null;
			while((readline=br.readLine())!=null){				//readline 读取文件行
				String[] wordsArr=readline.split("[^a-zA-Z]");		//正则匹配英文
				for (int i=0;i<wordsArr.length;i++){			//遍历数组，将其添加到列表中
						lists.add(wordsArr[i]);						
					}							
			}System.out.println(lists.size());
			br.close();
			Map<String,Integer> wordcount=new TreeMap<String,Integer>();	//实例TreeMap,好处是实现英文字母顺序排列
			for(int j=0;j<lists.size();j++){				
				String key=lists.get(j).toLowerCase();			
				if(wordcount.get(key)!=null){				//判断是否单词是否重复
					wordcount.put(key, wordcount.get(key)+1);        // value++
				}else{	
					wordcount.put(key, 1);		
				}	
			}
			System.out.println(wordcount.entrySet());
		}}