kwic--Java统计单词个数并按照顺序输出

提示：扫一扫查出行
【扫一扫了解最新限行尾号】
复制提示

是一个统计文件中单词个数，并按照个数从大到小输出的。输入文件名OK 了

单词是按照首字母排序的，，，里面用到映射等，，，注意重写比较函数，因为我们是要按值排序，而不是一般的按照键排序，，，，我们要输出的由多到少的个数，，，有个数是重复的

由于我们要按照个数多少排序，所以记得重写比较函数，为啥不能让数字做键，因为键不能重复，所以这里单词是键，OK 。

1 str.split("\\s+");这里记录分隔符

2 正则表达式,
\\d表示 0-9 的数字,
\\s表示空格,回车,换行等空白符,
\\w表示单词字符(数字字母下划线)
+号表示一个或多个的意思

代码：

 package calnum;

 import java.io.BufferedReader;

 import java.io.FileNotFoundException;

 import java.io.FileReader;

 import java.io.IOException;

 import java.nio.Buffer;

 import java.nio.ShortBuffer;

 import java.util.ArrayList;

 import java.util.Collections;

 import java.util.Comparator;

 import java.util.HashMap;

 import java.util.Iterator;

 import java.util.List;

 import java.util.Map;

 import java.util.Map.Entry;

 import java.util.Scanner;

 import java.util.TreeMap;

 import javax.swing.Spring;

 import javax.swing.text.html.parser.Entity;

 public class calwordnum{

     public String readfile() throws IOException {

         String all = null;

         // System.out.print("##########################");

         Scanner cin = new Scanner(System.in);

         System.out.print("plz input file name:");

         String filename = cin.next();

         FileReader read = new FileReader(filename);

         BufferedReader re = new BufferedReader(read);

         StringBuffer strbuf = new StringBuffer();

         String ss;

         while ((ss = re.readLine()) != null) {

             strbuf.append(ss);

         //读全文

         }

         return strbuf.toString();

     }

     //

     public String[] input(String str) {

         String[] arr = str.split("\\s+");

         return arr;

     }

     public void putmap(List<String> ls) {

         String temp, theword = null;

         int flage = 0;

         theword = ls.get(0);

         Map<String, Integer> map = new HashMap<String, Integer>();

         Iterator it = ls.iterator();

         while (it.hasNext()) {

             // System.out.println("sss"+it.next().toString());

             temp = it.next().toString();

             if (temp.equals(theword)) {

                 flage++;

                 continue;

             } else {

                 map.put(theword, flage);

                 flage = 1;

                 theword = temp;

             }

         }

         map.put(theword, flage);

         //重写比较方法，treemap按值排序。用两个map 比较函数需要参数

         ValueComparator bvc =  new ValueComparator(map);

        Map<String,Integer> map2 = new TreeMap<String,Integer>(bvc);

        map2.putAll(map);

         Iterator mapit = map2.entrySet().iterator();

         while (mapit.hasNext()) {

             Entry tr = (Entry) mapit.next();

             String num = (String) tr.getKey();

             int sa = (Integer) tr.getValue();

             System.out.println("this word:"+num + " has:" + sa + "个");

         }

     }

     // /

     public static void main(String[] args) throws IOException {

         // TODO Auto-generated method stub

         List<String> ls = new ArrayList<String>();

         calwordnum ca = new calwordnum();

         String allword = ca.readfile();

         String[] arr = ca.input(allword);

         for (int i = 0; i < arr.length; i++) {

             ls.add(arr[i].toLowerCase());

         }

         Collections.sort(ls);

         display(ls);

         ca.putmap(ls);

     }

     @Override

     public boolean equals(Object obj) {

         // TODO Auto-generated method stub

         return super.equals(obj);

     }

     private static void display(List<String> ls) {

         // TODO Auto-generated method stub

         for (String s : ls)

             System.out.println(s);

     }    

 }

 //

 class ValueComparator implements Comparator<String> {  

     Map<String, Integer> base;

     public ValueComparator(Map<String, Integer> base) {

         this.base = base;

     }  

     public int compare(String a, String b) {

         if (base.get(a) >=base.get(b)) {

             return -1;  //注意   不要返回0 会删除重复

         } 

         else {

             return 1;

         }

     }

 }