数据结构 哈夫曼树

哈夫曼树是一种经典的数据结构，也称为最优二叉树。它被用来压缩数据，尤其是文本文件，因为文本文件有很多重复的部分。

哈夫曼树是由一组权值给定的叶子节点构建而成的，其中每个叶子节点代表一个具有权值的字符。哈夫曼树的构建过程是基于贪心策略的，它将频率高的字符对应的叶子节点放在较浅的层次上，频率低的字符对应的叶子节点放在较深的层次上，从而使整个树的深度最小。

哈夫曼树的构建过程需要通过反复合并两个权值最小的节点来实现，直到树中只剩下一个根节点。构建完成后，从根节点到每个叶子节点的路径就是该叶子节点对应的字符的编码，哈夫曼编码是一种前缀编码，它保证任何一个字符的编码都不是另一个字符编码的前缀，因此在解码时，可以保证无歧义地恢复出原始的文本。

代码

#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#define MAXSIZE 32767

typedef char HuffmanCode;

typedef struct {
	char data;
	int weight;
	int parent, lchild, rchild;
}HTNode, * HuffmanTree;

typedef struct {
	char data;
	int weight;
}Auxiliary;

Auxiliary character[MAXSIZE] = {};
int length = 0;

void InitialEssay(char* essay) {
	int i, j;
	bool flag;
	for (i = 0;i < strlen(essay);i++) {
		flag = 1;
		for (j = 0;j < length;j++) {
			if (essay[i] == character[j].data) {
				character[j].weight++;
				flag = 0;
			}
		}
		if (flag) {
			character[j].data = essay[i];
			character[j].weight++;
			length++;
		}
	}
}

void InitialHT(HuffmanTree &HT) {
	if (length <= 0) {
		return;
	}
	int number = length * 2 - 1;
	HT = (HTNode*)malloc(sizeof(HTNode) * number);
	for (int i = 0;i < number;i++) {
		HT[i].data = -1;
		HT[i].weight = -1;
		HT[i].parent = -1;
		HT[i].lchild = -1;
		HT[i].rchild = -1;
	}
	for (int i = 0;i < length;i++) {
		HT[i].data = character[i].data;
		HT[i].weight = character[i].weight;
	}
}

void Select(HuffmanTree &HT, int size, int& position1, int& position2) {
	int min1 = MAXSIZE, min2 = MAXSIZE;
	for (int i = 0;i < size;i++) {
		if (HT[i].weight < min1 && HT[i].parent == -1) {
			position2 = position1;
			min2 = min1;
			min1 = HT[i].weight;
			position1 = i;
		}
		else if (HT[i].weight < min2 && HT[i].parent == -1) {
			min2 = HT[i].weight;
			position2 = i;
		}
	}
}

void CreateHT(HuffmanTree &HT) {
	if (length <= 1) {
		return;
	}
	int position1, position2;
	int number = length * 2 - 1;
	for (int i = length;i < number;i++) {
		Select(HT, i, position1, position2);
		HT[position1].parent = i;
		HT[position2].parent = i;
		HT[i].lchild = position1;
		HT[i].rchild = position2;
		HT[i].weight = HT[position1].weight + HT[position2].weight;
	}
}

void PrintHT(HuffmanTree &HT, HuffmanCode** HC) {
	int i, j, k;
	char* temp = (char*)malloc(sizeof(char) * length);
	HC = (HuffmanCode**)malloc(sizeof(HuffmanCode*) * length);
	temp[length - 1] = '\0';
	for (i = 0;i < length;i++) {
		int start = length;
		int flag = HT[i].parent;
		int ins = i;
		while (flag != -1) {
			start--;
			if (ins == HT[flag].lchild) {
				temp[start] = '0';
			}
			else {
				temp[start] = '1';
			}
			ins = flag;
			flag = HT[flag].parent;
		}
		HC[i] = (HuffmanCode*)malloc(sizeof(HuffmanCode) * (length - start));
		for (j = start, k = 0;j < length;j++, k++) {
			HC[i][k] = temp[j];
		}
		HC[i][k] = '\0';
		printf("%c -> %s\n", HT[i].data, HC[i]);
	}
	free(temp);
}

int main() {
	HuffmanTree HT = NULL;
	HuffmanCode** HC = NULL;
	char essay[MAXSIZE] = "";
	printf("请输入想要进行编码的原文：\n");
	scanf("%s", essay);
	InitialEssay(essay);
	InitialHT(HT);
	CreateHT(HT);
	printf("该文本各个字符的哈夫曼编码为：\n");
	PrintHT(HT, HC);
	return 0;
}

运行结果