二叉树及其应用

一、  实验内容

实现一个哈夫曼编码系统，系统包括以下功能：

(1) 字符信息统计：读取待编码的源文件txt文档，统计出现的字符及其频率。

(2) 建立哈夫曼树：根据统计结果建立哈夫曼树。

(3) 建立哈夫曼码表：利用得到的哈夫曼树，将各字符对应的编码表保存在文件结果txt文档中。

(4) 对源文件进行编码：根据哈夫曼码表，将原txt文件中的字符转换成相应的编码文件。

#include<iostream>
#include<string>
#include<malloc.h>
#include<stdlib.h>
#include<fstream>
#include<cassert>
#include<cstdio>
#include<stdio.h>
using namespace std;
#define OK 1
#define OVERFLOW -1
#define ERROR 0
#define MAXSIZE 100
int Sum[26];
int i = -1;
char c[100];
int typedef Status;
typedef char **HuffmanCode;
void Chu()//初始化数组
{
    for (int i = 0; i < 26; i++){
        Sum[i] = 0;
    }
}
typedef struct{
    int weight;
    int parent, lchild, rchild;

}HTNode,*HuffmanTree;//哈夫曼树定义
void Select(HuffmanTree &HT, int m, int &s1, int &s2)//选出最小数
{
    //cout << m << endl;
    int j,t;
    s1 = 1;
    s2 = 1;
    for (j = 1; j <=m; j++){
        if (HT[j].weight>HT[s1].weight){
            s1 = j;
            s2 = j;
            
        }
    }
    for (j = 1; j <= m; j++){
        if(HT[j].parent == 0){
            if (HT[j].weight < HT[s1].weight)
                s1 = j; 
        }
    }
    for (j = 1; j <= m; j++){
        if (HT[j].parent == 0 && j != s1){
            if (HT[j].weight < HT[s2].weight)
                s2 = j;
        }
    }
    //cout <<'\n'<< HT[s1].weight<< '\t' <<HT[s2].weight << endl;
}
void CreateHuffmanTree(HuffmanTree &HT, int n,int &s1, int & s2){//哈夫曼树构造
    if (n <= 1)return;
    int m = n * 2 - 1;
    HT = new HTNode[m + 1];
    for (int i = 1; i <=m; ++i){
        HT[i].parent = 0; HT[i].lchild = 0; HT[i].rchild = 0;
    }
    for (int i = 1; i <= n; ++i){
         HT[i].weight=Sum[i-1];
        // cout << HT[i].weight;
    }
    for (int i = n+1; i <= m; ++i){
        Select(HT, i - 1, s1, s2); 
        HT[s1].parent = i;
        HT[s2].parent = i;
        HT[i].lchild = s1;
        HT[i].rchild = s2; 
        HT[i].weight = HT[s1].weight + HT[s2].weight; 
        //cout << HT[i].weight << endl;
    }
}
void CreatHuffmanCode(HuffmanTree HT, HuffmanCode &HC, int n){//从叶子到跟逆向求出每个字哈夫曼编码，存在HC中
        char cd[7];
        HC = new char*[n + 1];
        cd == new char[n];
        cd[n - 1] = '\0'; 
        int start;
        int c, f;
        for (int i = 1; i <=n; i++){
            start = n - 1; 
            c = i; f = HT[i].parent;
            //cout << f << endl;
            //if (i == 4)cout << "55555555";
            while (f != 0){
                --start;
                if (HT[f].lchild == c)  cd[start] = '0';
                else cd[start] = '1';
                c = f; f = HT[f].parent; 
            }
            //cout << start<<"oooo"<<endl;
            //cout << n - start<<"adfas"<<endl;
            HC[i] = new char[n - start];
            strcpy_s(HC[i], strlen(&cd[start]) + 2, &cd[start]); 
            cout << i<<endl;
            cout << HC[i]<<"qqqqqqq"<<endl;
        }
        
        // delete cd;
         //cout << "退出循环";
    }
void readTxt(string file){
    ifstream infile;
    infile.open(file.data());
    assert(infile.is_open());
    while (!infile.eof()){
        i++;
        infile >> c[i];
        cout << c[i] << endl;
    }
    //for (int M = 0; M < i; M++)cout << c[M];
    infile.close();
}
void Txt_cun(){
    Chu();
    for (int I = 0; I < i; I++)
    {
        if (c[I] == 'a' || c[I] == 'A'){
            Sum[0] += 1;
        }
        else if (c[I] == 'b' || c[I] == 'B'){
            Sum[1] +=1 ;
        }
        else if (c[I] == 'c' || c[I] == 'C'){
            Sum[2] += 1;
        }
        else if (c[I] == 'd' || c[I] == 'D'){

            Sum[3] +=1;
        }
        else if (c[I] == 'e' || c[I] == 'E'){

            Sum[4] += 1;
        }
        else if (c[I] == 'f' || c[I] == 'F'){

            Sum[5] += 1;
        }
        else if (c[I] == 'g' || c[I] == 'G'){

            Sum[6] += 1;
        }
        else if (c[I] == 'h' || c[I] == 'H'){

            Sum[7] += 1;
        }
        else if (c[I] == 'I' || c[I] == 'i'){

            Sum[8] += 1;
        }
        else if (c[I] == 'j' || c[I] == 'J'){

            Sum[9] += 1;
        }
        else if (c[I] == 'k' || c[I] == 'K'){

            Sum[10] += 1;
        }
        else if (c[I] == 'l' || c[I] == 'L'){

            Sum[11]+= 1;
        }
        else if (c[I] == 'm' || c[I] == 'M'){

            Sum[12] += 1;
        }
        else if (c[I] == 'N' || c[I] == 'n'){

            Sum[13] += 1;
        }
        else if (c[I] == 'o' || c[I] == 'O'){

            Sum[14] += 1;
        }
        else if (c[I] == 'p' || c[I] == 'P'){

            Sum[15] += 1;
        }
        else if (c[I] == 'q' || c[I] == 'Q'){

            Sum[16] += 1;
        }
        else if (c[I] == 'r' || c[I] == 'R'){

            Sum[17] += 1;
        }
        else if (c[I] == 's' || c[I] == 'S'){

            Sum[18] += 1;
        }
        else if (c[I] == 't' || c[I] == 'T'){

            Sum[19] += 1;
        }
        else if (c[I] == 'u' || c[I] == 'U'){
            
            Sum[20] += 1;
        }
        else if (c[I] == 'v' || c[I] == 'V'){

            Sum[21] += 1;
        }
        else if (c[I] == 'w' || c[I] == 'W'){

            Sum[22] += 1;
        }
        else if (c[I] == 'x' || c[I] == 'X'){

            Sum[23] += 1;
        }
        else if (c[I] == 'y' || c[I] == 'Y'){

            Sum[24] += 1;
        }
        else if (c[I] == 'z' || c[I] == 'Z'){

            Sum[25] += 1;
        }
    }//for (int m = 0; m < 26; m++)cout << Sum[m] << endl;
}//对字母分配权值
int main(){
    readTxt("字符信息统计.txt");
    //cout << i;
    Txt_cun();
    int M = 26;
    for (int Z=0; Z < M; Z++){
        if (Sum[Z] == 0){
            for (int X = Z + 1; X < M; X++){
                Sum[X - 1] = Sum[X];
            }
            M--;
            Z--;
        }
        
    }
    HuffmanTree A;
    HuffmanCode HC;
    int s1, s2; 
    CreateHuffmanTree(A, M, s1, s2); 
    CreatHuffmanCode(A, HC, M);// cout << "vvvvvvvvvv";
    ofstream outfile;
    outfile.open("编码表.txt", ios::trunc);
    for (int L = 1; L <= M; L++){
        outfile << HC[L] << "\n";
    }
    outfile.close();
    //cout << HC;
}