java统计字符串中单词的数目

统计字符串中单词的数目

 

package com.commontest.pro1;

import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
 * @author jiangfuqiang
 * @version 2016/6/24.
 * @see com.commontest.pro1
 */
public class CountWord {

    public static void main(String[] args) {
        Map<String, Integer> map = new HashMap<String, Integer>();
        String data = "Learn the Spring spring - Spring Boot builds on many other Spring projects, check the spring.io web-site for a wealth of reference documentation. If you are just ";
        count(map,data,true);
        //这里将map.entrySet()转换成list
        List<Map.Entry<String,Integer>> list = new ArrayList<Map.Entry<String,Integer>>(map.entrySet());
        //然后通过比较器来实现排序
        Collections.sort(list,new Comparator<Map.Entry<String,Integer>>() {
            //升序排序
            public int compare(Map.Entry<String, Integer> o1,
                               Map.Entry<String, Integer> o2) {
                return o1.getValue().intValue() > o2.getValue().intValue()?-1:1;
            }

        });
        System.out.println(list.toString());
    }

    /**
     *
     * @param map
     * @param data
     * @param isLower  是否都转换为小写
     */
    private static void count(Map<String, Integer> map, String data, boolean isLower) {
        String[] datas = data.split("\\s+");
        Pattern pattern = Pattern.compile("((^[a-zA-Z]+[\\-]?(\\.[a-zA-Z]+)?[a-zA-Z]*)(\\W)?)");
        for (String str : datas) {
            Matcher matcher = pattern.matcher(str);

            if (matcher.matches()) {
                String word = matcher.group(2).trim();
                if (isLower) {
                    word = word.toLowerCase();
                }
                if (map.containsKey(word)) {
                    map.put(word, map.get(word) + 1);
                } else {
                    map.put(word, 1);
                }
            } else {
                System.out.println("not word: " + str);
            }
        }
    }

}