数据结构实验——哈夫曼树及哈夫曼编码应用

 一、实验内容

（1）输入一段100—200字的英文短文，存入一文件a中。

（2）写函数统计短文出现的字母个数n及每个字母的出现次数

（3）写函数以字母出现次数作权值，建Haffman树（n个叶子），给出每个字母的Haffman编码。

（4）用每个字母编码对原短文进行编码，码文存入文件b中。

（5）用Haffman树对文件b中码文进行译码，结果存入文件c中，比较a,c是否一致，以检验编码、译码的正确性。

 二、实验代码

#include<stdio.h>
#include<stdlib.h>
#include<string.h>
//实验六
#define MAXTREESIZE 100
typedef struct 
{
	int weight;
	int parent, left, right;
}HTNode,*HuffmanTree;
typedef char** HuffmanCode;
void Select(HuffmanTree HT, int end, int* t1, int* t2)
{
	int min1, min2;
	int i = 1;
	while (HT[i].parent != 0 && i <= end)
	{
		i++;
	}
	min1 = HT[i].weight;//先找出来第一个无父节点的
	*t1 = i;
	i++;
	while (HT[i].parent != 0 && i <= end)
	{
		i++;
	}
	//确定min2
	if (HT[i].weight < min1)
	{
		min2 = min1;
		*t2 = *t1;
		min1 = HT[i].weight;
		*t1 = i;
	}
	else
	{
		min2 = HT[i].weight;
		*t2 = i;
	}
	int j = 0;
	for (j = i + 1; j <= end; j++)
	{
		if (HT[j].parent != 0)
		{
			continue;
		}
		else
		{
			if (HT[j].weight < min1)
			{
				min2 = min1;
				*t2 = *t1;
				min1 = HT[j].weight;
				*t1 = j;
			}
			else
			{
				if (HT[j].weight < min2)
				{
					min2 = HT[j].weight;
					*t2 = j;
				}
			}
		}
	}
}
void CreateHuffmanTree(HuffmanTree* HT, int* k, int n)
{
	if (n <= 1)
	{
		return;
	}
	int m = 2 * n - 1;
	*HT = (HuffmanTree)malloc((m + 1) * sizeof(HTNode));
	int i = 1;
	int j = 0;
	//初始化结点，即构造森林全是根
	for (j = 0;; j++)
	{
		if (k[j] > 0)
		{
			(*HT)[i].weight = k[j];
			(*HT)[i].parent = 0;
			(*HT)[i].left = 0;
			(*HT)[i].right = 0;
			i++;
			if (i == n + 1)
				break;
		}
	}
	//开始构建哈夫曼树，选用两小造新树，删除两小添新树
	for (i = n + 1; i <= m; i++)
	{
		int t1, t2;
		Select(*HT, m, &t1, &t2);
		(*HT)[t1].parent = i;
		(*HT)[t2].parent = i;
		(*HT)[i].parent = 0;
		(*HT)[i].left = t1;
		(*HT)[i].right = t2;
		(*HT)[i].weight = (*HT)[t1].weight + (*HT)[t2].weight;
	}
}
void save_text_to_file(char* text, char filename[])
{
	FILE* file;
	file = fopen(filename, "w"); // 打开文件a.txt，以写入方式打开
	if (file == NULL) { // 如果文件打开失败
		printf("Failed to open file\n");
		return;
	}
	fprintf(file, "%s", text); // 写入文本内容
	fclose(file); // 关闭文件
	printf("Text saved to file successfully\n");
}
void tongji(char* filename,int* num, int* n)
{
	FILE* file = fopen(filename, "r");
	if (file == NULL) 
	{
		printf("无法打开文件 %s\n", filename);
		return;
	}
	char letter;
	while ((letter = fgetc(file)) != EOF) 
	{
		if (letter >= 'a' && letter <= 'z')
		{
			num[letter - 71]++;
			(*n)++;
		}
		else if (letter >= 'A' && letter <= 'Z')
		{
			num[letter - 65]++;
			(*n)++;
		}
	}
	fclose(file);
}
void HuffmanCoding(HuffmanCode* HC, HuffmanTree HT, int n) 
{
	char* cd;
	*HC = (HuffmanCode)malloc((n + 1) * sizeof(char*));
	cd = (char*)malloc(n * sizeof(char));
	cd[n - 1] = '\0';
	int i = 0;
	int start = 0;
	int c = 0;
	int f = 0;
	for (i = 1; i <= n; ++i)
	{
		start = n - 1;
		for (c = i, f = HT[i].parent; f != 0; c = f, f = HT[f].parent)
		{
			if (HT[f].left == c)
				cd[--start] = '0';
			else
				cd[--start] = '1';
		}
		(*HC)[i] = (char*)malloc((n - start) * sizeof(char));
		strcpy((*HC)[i], &cd[start]);
	}//for
	free(cd);
}//HuffmanCoding
int Num(char arr[], char c)
{
	int i = 0;
	for (i = 0;; i++)
	{
		if (arr[i] == c)
		{
			return i + 1;
		}
	}
}
void Coding(char* filename,char* filename1, HuffmanCode HC, char* arr)
{
	FILE* file1;
	file1 = fopen(filename1, "w"); // 打开文件b.txt，以写入方式打开
	if (file1 == NULL) { // 如果文件打开失败
		printf("Failed to open file\n");
		return;
	}
	FILE* file = fopen(filename, "r");//打开a.txt，以读取方式打开
	if (file == NULL)
	{
		printf("无法打开文件 %s\n", filename);
		return;
	}
	char letter;
	while ((letter = fgetc(file)) != EOF)
	{
		char code[MAXTREESIZE] = { 0 };
		if (letter >= 'a' && letter <= 'z')
		{
			fprintf(file1, "%s ", HC[Num(arr,letter)]); // 写入文本内容
		}
		else if (letter >= 'A' && letter <= 'Z')
		{
			fprintf(file1, "%s ", HC[Num(arr, letter)]); // 写入文本内容
		}
	}
	fclose(file);
	fclose(file1); // 关闭文件
	printf("%s saved successfully\n",filename1);
}
int Code(HuffmanCode HC, char* s)
{
	int i = 0;
	for (i = 1;; i++)
	{
		if (strcmp(HC[i], s) == 0)
		{
			return i - 1;
		}
	}
}
void DeCoding(char* filename1, char* filename2, HuffmanCode HC, char* arr)
{
	FILE* file2;
	file2 = fopen(filename2, "w"); // 打开文件b.txt，以写入方式打开
	if (file2 == NULL) { // 如果文件打开失败
		printf("Failed to open file\n");
		return;
	}
	FILE* file1 = fopen(filename1, "r");//打开a.txt，以读取方式打开
	if (file1 == NULL)
	{
		printf("无法打开文件 %s\n", filename1);
		return;
	}
	char letter;
	char s[MAXTREESIZE] = { 0 };
	int i = 0;
	while ((letter = fgetc(file1)) != EOF)
	{
		if (letter != ' ')
		{
			s[i] = letter;
			printf("%c", letter);
			i++;
		}
		else
		{
			printf(" ");
			fprintf(file2, "%c ", arr[Code(HC,s)]); // 写入文本内容
			for (; i >= 0; i--)
			{
				s[i] = '\0';
			}
			i = 0;
		}
	}
	fclose(file1);
	fclose(file2);
	printf("%s is saved successfully!\n", filename2);
}
int main()
{
	char* filename = "a.txt";
	char* filename1 = "b.txt";
	char* filename2 = "c.txt";
	int k[MAXTREESIZE] = { 0 };
	int n = 0, w = 0;
	HuffmanTree HT = NULL;
	char text[200];
	printf("请输入一段200字以内的英文短文：\n");
	scanf("%[^\n]", text);
	save_text_to_file(text, filename);
	tongji(filename, k, &w);
	printf("所有字母出现的总次数：%d\n", w);
	int i = 0;
	char arr[MAXTREESIZE] = { 0 };//大写在前小写在后
	for (i = 0; i < 52; i++)
	{
		if (k[i] > 0)
		{
			if (i >= 26 && i <= 51)
			{
				printf("字母%c出现的次数是 %d\n", i + 71, k[i]);
				arr[n] = i + 71;
			}
			else
			{
				printf("字母%c出现的次数是 %d\n", i + 65, k[i]);
				arr[n] = i + 65;
			}
			n++;
		}
	}
	printf("\n-------/开始创建哈夫曼树/-------\n");
	CreateHuffmanTree(&HT, k, n);
	printf("最小权重和是%d\n", HT[2 * n - 1].weight);
	printf("-------/哈夫曼树创建完毕/-------\n");
	HuffmanCode HC = NULL;
	printf("\n-------/开始进行哈夫曼编码/-------\n\n");
	HuffmanCoding(&HC, HT, n);
	for (i = 1; i <= n; i++)
	{
		printf("字母%c的哈夫曼编码是%s\n", arr[i - 1], HC[i]);
	}
	printf("\n-------/哈夫曼编码已完成/---------\n");
	printf("---------/编码开始/--------\n");
	Coding(filename, filename1, HC, arr);
	printf("\n---------/编码结束/--------\n");
	printf("\n----------/译码开始/--------\n");
	DeCoding(filename1, filename2, HC, arr);
	printf("---------/译码结束/--------\n");
	return 0;
}

三、后记

仅作个人实验记录，如有错误还望各位指正。