文本内容统计

1.一个用于统计文本文件中的英语单词出现频率的控制台程序

package com.word;

import java.io.BufferedReader;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.text.NumberFormat;

public class test {

    public class java {

    }

    public static void main(String[] args) throws Exception {
        BufferedReader bf = new BufferedReader(new InputStreamReader(
                new FileInputStream("E:\\qq  receive files\\Harry Potter and the Sorcerer's Stone.txt")));
        int[] count = new int[26];

        char[] c = new char[1];
        int len = bf.read(c);
        while (len != -1) {

            if (c[0] <= 'Z' && c[0] >= 'A') {
                int number = c[0];
                count[number - 65]++;
            }
            if (c[0] <= 'z' && c[0] >= 'a') {
                int number = c[0];
                count[number - 97]++;
            }
            len = bf.read(c);
        }
        count = Sort(count);
        Print(count);
        bf.close();

    }

    public static int[] Sort(int[] count) {
        int temp;
        int size = count.length;
        for (int i = 0; i < size - 1; i++) {
            for (int j = i + 1; j < size; j++) {
                if (count[i] < count[j]) {
                    temp = count[j];
                    count[j] = count[i];
                    count[i] = temp;

                }
            }
        }
        return count;

    }

    public static void Print(int[] count) {
        NumberFormat df = NumberFormat.getInstance();

        

       df.setMaximumFractionDigits(2);

        int sum = 0;
        for (int i = 0; i < count.length; i++) {
            sum = count[i] + sum;
        }
        String[] a = new String[count.length];
        for (int i = 0; i < count.length; i++) {
            a[i] = dt.format((float) count[i] / (float) sum * 100);
        }
        for (int i = 0; i < 26; i++) {
            if (count[i] > 0) {
                char lowerCase = (char) (i + 101);
                System.out.println(lowerCase + "(" + a[i] + "%)");
            }
        }

    }

}

 

 

 

2.要求:输出单个文件中的前 N 个最常出现的英语单词。
功能1：输出文件中所有不重复的单词，按照出现次数由多到少排列，出现次数同样多的，以字典序排列。
功能2：指定文件目录，对目录下每一个文件执行  功能1的操作。
功能3：指定文件目录， 但是会递归遍历目录下的所有子目录，每个文件执行功能1的做操。

只完成了输出文件中的前N个单词的功能....

package com.word;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.*;
import java.util.StringTokenizer;
public class Test2 {
    private static String str1;
    private static String[] str3 = new String[20000];
    private static int[] n=new int[20000];
    
    public static void main(String[] args) throws IOException {
        
        Scanner sc=new Scanner(System.in);
        File file = new File("//E:\\\\qq  receive files\\\\Harry Potter and the Sorcerer's Stone.txt");
        String tempstr=null;
        BufferedReader reader = null;
        reader = new BufferedReader(new FileReader(file));
        int i=0,sum=0,j=0;
        while((tempstr=reader.readLine())!=null) {
        StringTokenizer st = new StringTokenizer(tempstr," .,?”“;:''　　　!—‘");
        while(st.hasMoreElements()) {
        str1=(String)st.nextElement();
        str1=str1.toLowerCase();
        for(i=0;i<=sum;i++)
        {
            if(str1.equals(str3[i])) {
                n[i]++;
                break;}
        }
        if(i>sum) {
            str3[sum]=str1;
            n[sum]=1;
            sum++;
            }
                }
                    }
        
        for( i=0;i) {
            for( j=i+1;j) {
                if(n[j]>n[i]) {
                    int temp=n[i];
                    n[i]=n[j];
                    n[j]=temp;
                    String Temp=str3[i];
                    str3[i]=str3[j];
                    str3[j]=Temp;
                }
            }
        }

        System.out.print("你要前几个最常出现的单词:");
         int choose = sc.nextInt();
         for(i=0;i) {
             System.out.println(str3[i]+"    "+n[i]);
         }
    }
}