• 文本中单词统计


    package word;
    
    import java.io.BufferedReader;
    import java.io.FileReader;
    import java.util.*;
    
    
    public class wordcount {
        public static void main(String [] args) throws Exception {
    
            BufferedReader br = new BufferedReader(new FileReader("D:/学习/大二选修java/fly.txt"));
    
            StringBuffer sb = new StringBuffer();
            String text =null;
            while ((text=br.readLine())!= null){
                sb.append(text);// 将读取出的字符追加到stringbuffer中
            }
            br.close();  // 关闭读入流
    
            String str = sb.toString().toLowerCase(); // 将stringBuffer转为字符并转换为小写
            String[] words = str.split("[^(a-zA-Z)]+");  // 非单词的字符来分割,得到所有单词
            Map<String ,Integer> map = new HashMap<String, Integer>() ;
    
            for(String word :words){
                if(map.get(word)==null){  // 若不存在说明是第一次,则加入到map,出现次数为1
                    map.put(word,1);
                }else{
                    map.put(word,map.get(word)+1);  // 若存在,次数累加1
                }
            }
          
            // 排序
            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>>() {
                public int compare(Map.Entry<String, Integer> left, Map.Entry<String, Integer> right) {
                    return (left.getValue().compareTo(right.getValue()));
                }
            };
            // 集合默认升序升序
           
            Collections.sort(list,comparator);
            
           
            float sum=0;
            float a;
            float b;
            for(int i=0;i<list.size();i++) {
                if(list.get(list.size()-i-1).getKey().equals("a")||list.get(list.size()-i-1).getKey().equals("the")||list.get(list.size()-i-1).getKey().equals("and")) {
                    
                }else {
    
                    a=list.get(list.size()-i-1).getValue();
                    b=sum;
                    sum=a+b; 
                }
                
                    
                
            }
                    System.out.println("可用单词总和为:"+sum);
                    System.out.println("可用单词出现次数及所占百分比降序排列如下:");
                   
                
            
            for(int i=0;i<list.size();i++){// 由高到低输出
                if(list.get(list.size()-i-1).getKey().equals("a")||list.get(list.size()-i-1).getKey().equals("the")||list.get(list.size()-i-1).getKey().equals("and")) {}
                else{
                    System.out.println(list.get(list.size()-i-1).getKey() +":出现"+list.get(list.size()-i-1).getValue()+"次  占比"+String.format("%.2f",(list.get(list.size()-i-1).getValue()/sum)*100));
                    
                }
                }
                
            }
    
        }

    运行结果如下图所示:

  • 相关阅读:
    INFORMATION_SCHEMA.INNODB_LOCKS
    INFORMATION_SCHEMA.INNODB_TRX 详解
    zabbix 通过key 获取
    匿名hash
    [] 和{} 匿名引用
    perl 初始化Hash
    9.2 数组的散列
    数组的数组
    RMAN恢复目录
    验证备份前设置CONFIGURE CONTROLFILE AUTOBACKUP ON/OFF; 的区别
  • 原文地址:https://www.cnblogs.com/jinseliunian/p/10809513.html
Copyright © 2020-2023  润新知