LZW字典压缩算法

LZW字典压缩算法

#define  _CRT_SECURE_NO_WARNINGS
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
#define NOT_EXIST -1
//创建字典变量
typedef struct Dictionary{
	char** seq;		//字典字符
	int* code;		//字典编码
	int size;		//字典尺寸
	int maxsize;	//字典最大容量

}Dictionary;

//将字符插入字典中
//dict 字典；
//seq 字符
void insert_seq(Dictionary* dict, char* seq)
{
	int i = dict->size;			//字符编码
	dict->seq[i] = malloc(sizeof(char) * strlen(seq) + 1);		//为字典字符分配空间
	dict->code[i] = i;			//为字符分配编码
	dict->size++;				//编码+1
	strcpy(dict->seq[i], seq);	//将字符存入字典
}

//初始化字典
//dict 字典
//maxsize 最大容量
void init_dictionary(Dictionary* dict, int maxsize)
{
	dict->maxsize = maxsize;		//最大容量
	dict->size = 0;					//初始尺寸为0
	dict->seq = malloc(sizeof(char*) * maxsize);	//为字典分配空间
	dict->code = malloc(sizeof(int) * maxsize);		//为编码分配空间

	insert_seq(dict, "#");			//将‘0’号初始化为‘#’
	char seq[2] = "A";				//将'A'插入字典
	for (int i = 0; i < 26; i++)	//为26个字母分配编码
	{
		insert_seq(dict, seq);		//插入字母
		seq[0]++;					//编码+1
	}
}

//从字典获取字符编码
int get_seq_code(Dictionary* dict, char* seq)
{
	for (int i = 0; i < dict->size; i++)
	{
		if(strcmp(dict->seq[i],seq)==0)			//将给定的字符与字典比较，相等则返回编码
			return dict->code[i];
	}
	return NOT_EXIST;			//否则返回-1
}
//打印字典与编码
void print_dictionary(Dictionary* dict)
{
	printf("====================\n");
	printf(" Code       Sequence\n");
	printf("====================\n");
	for (int i = 0; i < dict->size; i++)
	{
		printf("%5d%7c", dict->code[i], ' ');		//编码
		printf("%s\n", dict->seq[i]);				//字符
	}

	printf("====================\n");
}

//对字符进行编码
void lzw_encode(char* text, Dictionary* dict)
{

	char current[1000];
	char next;
	int code;
	int i = 0;
	while (i < strlen(text))
	{
		sprintf(current,"%c", text[i]);		//将第i个字符赋值给current
		next = text[i + 1];					//next为第i+1个字符
		while (get_seq_code(dict, current) != NOT_EXIST)	//当编码存在的时候
		{
			sprintf(current, "%s%c", current, next);//将current和next中的字符赋值给current
			i++;									//字符指针往后移
			next = text[i + 1];						
		}
		current[strlen(current) - 1] = '\0';		//当编码不存在，将current中的字符回退一个
		next = text[i];								//next减去一个字符
		code = get_seq_code(dict, current);			//获取编码
		sprintf(current, "%s%c", current, next);	//将current和next中的字符赋值给current
		insert_seq(dict, current);					//将字符插入字典

		//printf("%d %s\n", code,current);			//打印编码和字符

		printf("%d\n", code);						//打印编码
	}
}

char* get_code_seq(Dictionary* dict, int code)
{
	if (code < 0 || code >= dict->size)
		return NULL;
	else
	{
		int i = code;
		return dict->seq[i];
	}
}

void lzw_decode(int codes[], int n, Dictionary* dict)
{
	int code;
	char prev[1000];
	char* output;

	code = codes[0];
	output = get_code_seq(dict, code);
	printf("%s ", output);

	int i;
	for (i = 1; i < n; i++)
	{
		strcpy(prev, output);
		output = get_code_seq(dict, codes[i]);
		sprintf(prev, "%s%c", prev, output[0]);
		insert_seq(dict, prev);
		printf("%s ", output);
	}
}
int main()
{
	Dictionary dict;
	init_dictionary(&dict, 1000);
	print_dictionary(&dict);


	lzw_encode("TOBEORNOTTOBEORNOTTOBE",&dict);//编码

	int arr[16] = { 20,15,2,5,15,18,14,15,20,27,29,31,33,35,28,5 };
	lzw_decode(arr, 16, &dict);//解码
	return 0;
}