Java版统计文件中的每个单词出现次数

正则表达式之Pattern和Matcher，请参见转载博客    http://www.cnblogs.com/haodawang/p/5967219.html

代码实现：

 1 import java.io.BufferedReader;
 2 import java.io.FileNotFoundException;
 3 import java.io.FileReader;
 4 import java.io.IOException;
 5 import java.util.Map;
 6 import java.util.Set;
 7 import java.util.TreeMap;
 8 import java.util.regex.Matcher;
 9 import java.util.regex.Pattern;
10 
11 public class CountWorks {
12     public static void main(String[] args) {
13         BufferedReader br = null;
14         try {
15             br = new BufferedReader(new FileReader("short.txt"));
16         } catch (FileNotFoundException e) {
17             e.printStackTrace();
18         }
19         StringBuffer sb1 = new StringBuffer();
20         String line = null;
21         try {
22             while((line = br.readLine()) != null) {
23                 sb1 = sb1.append(line);
24             }
25         } catch (IOException e) {
26             e.printStackTrace();
27         }
28         try {
29             br.close();
30         } catch (IOException e1) {
31             e1.printStackTrace();
32         }
33         String sb=sb1.toString().toLowerCase();
34         Pattern pattern = Pattern.compile("[a-zA-Z']+");//a 到 z 或 A 到 Z，两头的字母包括在内（范围）
35         Matcher matcher = pattern.matcher(sb);
36         Map<String, Integer> map = new TreeMap<String, Integer>();
37         String word = "";
38         Integer num = null;
39         int total = 0;
40         
41         while(matcher.find()) {
42             word = matcher.group();
43             total ++;
44             if(map.containsKey(word)) {
45                 num = map.get(word);//get(),返回指定键值所映射的值，取出map中word单词的个数
46                 num += 1;
47             } else {
48                 num = 1;
49             }
50             map.put(word, num);
51         }
52         Set<String> keys = map.keySet();
53         for (String key : keys) {
54             Integer value = map.get(key);
55             System.out.printf("%s: %s\n", key, value);
56         }
57         System.out.println();
58         System.out.println("total words : " + total);
59         System.out.println("different words : " + map.size());
60     }
61 }

 

转载于:https://www.cnblogs.com/LJHAHA/p/10211186.html