单词统计

统计文本中26个字母的频率：

package bao;
import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.text.NumberFormat;

public class Text2 {
    
     private static String formattedDecimalToPercentage(double decimal)
        {
            //获取格式化对象
            NumberFormat nt = NumberFormat.getPercentInstance();
            //设置百分数精确度2即保留两位小数
            nt.setMinimumFractionDigits(2);
            return nt.format(decimal);
        }    
public static void main(String []args) {
    String a1;
    char a='A';
    int a2[]=new int[27];
    char b1[]=new char[26];
    char b2[]=new char[26];
    
    for(int i=0;i<26;i++)
    {
    b1[i]=a;
    b2[i]=(char)(a+32);
    a++;
    }

    for(int i=0;i<26;i++) {
        
        System.out.println(b1[i]);
        System.out.println(b2[i]);
        
    }
    
    
    try {
        BufferedReader in = new BufferedReader(new FileReader("D:\Downloadbaidu\2.txt"));
        String str;
        while ((str = in.readLine()) != null) {
            System.out.println(str);
            char[] d=str.toCharArray();
            for(int i=0;i<d.length-1;i++) {
                for(int j=0;j<26;j++) {
                    if(b1[j]==d[i]||b2[j]==d[i]) {
                        a2[j]++;
                    }
                    
                    
                }
                
            }
           
         
        }
        
        a2[26]=0;
        for(int i=0;i<26;i++) {
            a2[26]=a2[i]+a2[26];
        }

        for(int i=0;i<26;i++) {
            System.out.print(b1[i]);
            System.out.print("和");
            System.out.print(b2[i]);
            System.out.print("出现的次数为：");
            System.out.println(a2[i]);
            double d=(double)((double)a2[i]/(double)a2[26]);
            String result2=formattedDecimalToPercentage(d);
            System.out.println("result = "+result2);

        }
 
    } catch (IOException e) {
    }
    
    
}
}

统计文本中单词出现次数：

package bao;
import java.io.BufferedReader;
import java.io.FileReader;
import java.util.*;


public class Text3 {
    public static void main(String [] args) throws Exception {

        BufferedReader br = new BufferedReader(new FileReader("D:\Downloadbaidu\2.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);

        for(int i=0;i<list.size();i++){// 由高到低输出
            System.out.println(list.get(list.size()-i-1).getKey() +":"+list.get(list.size()-i-1).getValue());
        }

    }

学习于网络。