统计英文文本文件中的单词及字母

1.输出某个英文文本文件中 26 字母出现的频率，由高到低排列，并显示字母出现的百分比，精确到小数点后面两位。

源代码：

import java.io.*;
import java.text.DecimalFormat;
import java.util.*;
public class Test {
    public static void main(String[] args){
        demo(new File("C:\Harry Potter and the Sorcerer's Stone.txt"));
    }
    public static void demo(File file){
        BufferedReader bfr = null;
        try{
            DecimalFormat df = new DecimalFormat("######0.00");
            int sum = 0;
            int i = 0;
            double[] ss = new double[99];
            char[] en = new char[99];
            int[] num = new int[99];
            bfr = new BufferedReader(new FileReader(file));
            String value = null;
            String newValue = "";
            while((value = bfr.readLine())!=null){
                newValue = newValue+value;
            }
            char[] ch = newValue.toCharArray();
            TreeMap<Character,Integer> tm = new TreeMap<Character,Integer>(Collections.reverseOrder());
            for(int x = 0;(x<ch.length);x++){
                char c = ch[x];
                if(tm.containsKey(c)){
                    int conut = tm.get(c);
                    tm.put(c,conut+1);
                }
                else{
                    tm.put(c, 1);
                }
            }
            Set<Map.Entry<Character, Integer>> set = tm.entrySet();
            Iterator<Map.Entry<Character, Integer>> iter = set.iterator();
          
            while(iter.hasNext()){
                Map.Entry<Character, Integer> map = iter.next();
                char k = map.getKey();
                int v = map.getValue();
                if(((k>='a')&&(k<='z'))||((k>='A')&&(k<='Z'))) {
                    num[i] = v;
                    en[i] = k;
                    i++;
                }
                
            }
            for(int h=0;h<i;h++) {
                sum = sum + num[h];
            }
            for(int j=0;j<i;j++) {
                ss[j] = (double) (((double)num[j]*100)/(double)sum);
            }
            for(int k=0;k<26;k++)
            {
                for(int m=0;m<26-1-k;m++)
                {
                    if(ss[m+1]>ss[m])
                    {
                        double t=ss[m];
                        char g = en[m];
                        en[m]=en[m+1];
                        en[m+1]=g;
                        ss[m]=ss[m+1];
                        ss[m+1]=t;
                    }
                }
            }
            for(int n=0;n<i;n++) {
                System.out.print(en[n]+"    ");
                System.out.print(df.format(ss[n]));
                System.out.println("%");
            }
        }
        catch(IOException e){
            System.out.println("文件读取错误");
        }
        finally{
            try{
                if(bfr!=null)
                    bfr.close();
            }
            catch(IOException e){
                System.out.println("文件关闭错误");
            }
        }
    }
}

部分运行截图：

2. 输出单个文件中的前 N 个最常出现的英语单词。

源代码：

import java.io.BufferedReader;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.util.*;
public class Eng {
    class Word
    {
        String value;
        int num;
        Word next;
        public Word(String value,int num)
        {
            this.value=value;
            this.num=num;
            next=null;
        }
        public Word()
        {
            this.value="";
            this.num=0;
            next=null;
        }
    }    
    public void getFileList() throws IOException {
        BufferedReader br=new BufferedReader(new FileReader("C:\Harry Potter and the Sorcerer's Stone.txt"));        
        TreeMap<Character,Integer> hm=new TreeMap<>();
        int  bb;
        while((bb=br.read())!=-1) {    
                    Word word=new Word();
                    Word linklist,nw;                                             
                    String str="";
                    char[] c=new char[1];
                    int b=0;
                    boolean exist=false;
                    while((b=br.read(c))!=-1)
                    {
                        if(String.valueOf(c).equals("
")||String.valueOf(c).equals("
")||String.valueOf(c).equals(" ")||String.valueOf(c).equals(",")||String.valueOf(c).equals(".")||String.valueOf(c).equals(""")||String.valueOf(c).equals("'"))
                        {
                            linklist=word;
                            while(linklist!=null)            
                            {
                                if(linklist.value.equalsIgnoreCase(str))
                                {
                                    linklist.num++;exist=true;
                                    break;
                                }
                                else
                                {
                                    linklist=linklist.next;
                                }
                            }
                            if(exist==false)
                            {
                                nw=new Word(str,1);
                                nw.next=word.next;
                                word.next=nw;
                                str="";
                            }
                            else
                            {
                                exist=false;
                                str="";
                            }
                        }
                        else                                      //单词
                        {
                            str+=String.valueOf(c);
                        }
                    }
                    System.out.print("请输入您想查询的前几个出现此处最多的单词:");
                    Scanner scan=new Scanner(System.in);
                    int N=scan.nextInt();
                    for(int i=1;i<=N;i++)                   
                    {
                        nw=new Word("",0);
                        linklist=word.next;
                        while(linklist!=null)
                        {
                            if(linklist.num>nw.num)
                            {
                                nw=linklist;
                            }
                            linklist=linklist.next;
                        }
                        System.out.println("第"+i+"个 :"+nw.value+"  个数："+nw.num);
                        linklist=word;
                        while(linklist.next!=null)
                        {
                            if(linklist.next.value.equalsIgnoreCase(nw.value))
                            {
                                linklist.next=linklist.next.next;
                                break;
                            }
                            linklist=linklist.next;
                        }
                    }
                    
                }            
            }         
    public static void main(String[] args) throws IOException {
        Eng rf = new Eng();
        rf.getFileList();
    }
}

运行截图：