数据压缩（八）——LZW词典编解码

掌握词典编码的基本原理，用C/C++/Python等语言编程实现LZW解码器并分析编解码算法。

---

（一）背景知识

1.1 树的构成

  代码中定义了字典树，结构为：

1.2 LZW的编码实现过程

1.3 LZW的解码实现过程

1.4 编解码的初始词典

  以下为初始的词典

（二）实现代码

生成测试文件"1.dat"代码

#include <cstdio>
#include <iostream>
#include <fstream>
using namespace std;

int main()
{
	ofstream outfile("1.dat", ios::binary);
	if (!outfile) { cout << "error to create file!" << endl; }

	unsigned char a[14] = { 'a','b','b','a','b','a','b','a','c','a','b','a','c','d' };
	outfile.write((char*)a, 14);
	outfile.close();
	return 0;
}

bitio.h

#pragma once
/*
 * Declaration for bitwise IO
 *
 * vim: ts=4 sw=4 cindent
 */
#ifndef __BITIO__
#define __BITIO__

#include <stdio.h>

typedef struct {
    FILE* fp;//文件名字
    unsigned char mask;
    int rack;
}BITFILE;

BITFILE* OpenBitFileInput(char* filename);//
BITFILE* OpenBitFileOutput(char* filename);//
void CloseBitFileInput(BITFILE* bf);
void CloseBitFileOutput(BITFILE* bf);
int BitInput(BITFILE* bf);
unsigned long BitsInput(BITFILE* bf, int count);
void BitOutput(BITFILE* bf, int bit);
void BitsOutput(BITFILE* bf, unsigned long code, int count);
#endif	// __BITIO__

bitio.cpp

/*
 * Definitions for bitwise IO
 *
 * vim: ts=4 sw=4 cindent
 */

#include <stdlib.h>
#include <stdio.h>
#include "bitio.h"
BITFILE* OpenBitFileInput(char* filename) {
	BITFILE* bf;
	bf = (BITFILE*)malloc(sizeof(BITFILE));
	if (NULL == bf) { 
		return NULL; 
	}
	if (NULL == filename) { 
		bf->fp = stdin;
	}
	else {
		errno_t err = 0;
		err = fopen_s(&(bf->fp),filename, "rb");
	}
	if (NULL == bf->fp) return NULL;
	bf->mask = 0x80;
	bf->rack = 0;
	return bf;
}

BITFILE* OpenBitFileOutput(char* filename) {
	BITFILE* bf;
	bf = (BITFILE*)malloc(sizeof(BITFILE));
	if (NULL == bf) {
		return NULL;
	}
	if (NULL == filename) {
		bf->fp = stdout;
	}
	else {
		errno_t err = 0;
		err = fopen_s(&(bf->fp),filename, "wb");
		if (err != 0)
			return NULL;
	}
	if (NULL == bf->fp) return NULL;
	bf->mask = 0x80;//初始化mask=0x80
	bf->rack = 0;	//初始化rack = 0
	return bf;
}

void CloseBitFileInput(BITFILE* bf) {
	fclose(bf->fp);
	free(bf);
}

void CloseBitFileOutput(BITFILE* bf) {
	// Output the remaining bits
	if (0x80 != bf->mask) fputc(bf->rack, bf->fp);
	fclose(bf->fp);
	free(bf);
}

int BitInput(BITFILE* bf) {
	int value;

	if (0x80 == bf->mask) {
		bf->rack = fgetc(bf->fp);
		if (EOF == bf->rack) {
			fprintf(stderr, "Read after the end of file reached\n");
			exit(-1);
		}
	}
	value = bf->mask & bf->rack;
	bf->mask >>= 1;	//mask = mask/2;
	if (0 == bf->mask) bf->mask = 0x80;
	return((0 == value) ? 0 : 1);
}

unsigned long BitsInput(BITFILE* bf, int count) {
	unsigned long mask;
	unsigned long value;
	mask = 1L << (count - 1);
	value = 0L;
	while (0 != mask) {
		if (1 == BitInput(bf))
			value |= mask;
		mask >>= 1;
	}
	return value;
}

void BitOutput(BITFILE* bf, int bit) {
	if (0 != bit) bf->rack |= bf->mask;
	bf->mask >>= 1;
	if (0 == bf->mask) {	// eight bits in rack
		fputc(bf->rack, bf->fp);//把rack写到fp中
		bf->rack = 0;	//重新初始化rack = 0
		bf->mask = 0x80;//重新初始化mask = 0x80
	}
}

void BitsOutput(BITFILE* bf, unsigned long code, int count) {
	unsigned long mask;

	mask = 1L << (count - 1);
	while (0 != mask) {
		BitOutput(bf, (int)(0 == (code & mask) ? 0 : 1));
		mask >>= 1;
	}
}
#if 0
int main(int argc, char** argv) {
	BITFILE* bfi, * bfo;
	int bit;
	int count = 0;

	if (1 < argc) {
		if (NULL == OpenBitFileInput(bfi, argv[1])) {
			fprintf(stderr, "fail open the file\n");
			return -1;
		}
	}
	else {
		if (NULL == OpenBitFileInput(bfi, NULL)) {
			fprintf(stderr, "fail open stdin\n");
			return -2;
		}
	}
	if (2 < argc) {
		if (NULL == OpenBitFileOutput(bfo, argv[2])) {
			fprintf(stderr, "fail open file for output\n");
			return -3;
		}
	}
	else {
		if (NULL == OpenBitFileOutput(bfo, NULL)) {
			fprintf(stderr, "fail open stdout\n");
			return -4;
		}
	}
	while (1) {
		bit = BitInput(bfi);
		fprintf(stderr, "%d", bit);
		count++;
		if (0 == (count & 7))fprintf(stderr, " ");
		BitOutput(bfo, bit);
	}
	return 0;
}
#endif

lzw_E.cpp

/*
 * Definition for LZW coding
 *
 * vim: ts=4 sw=4 cindent nowrap
 */
#include <cstdio>
#include <iostream>
#include <stdlib.h>
#include <stdio.h>
#include <iostream>
#include <cstdio>
#include "bitio.h"
#define MAX_CODE 65535

using namespace std;

struct {
	int suffix = -1;//后缀
	int parent = -1, firstchild = -1, nextsibling = -1;//父亲，孩子，兄弟姐妹
} dictionary[MAX_CODE + 1];
int next_code;
int d_stack[MAX_CODE]; // stack for decoding a phrase

#define input(f) ((int)BitsInput( f, 16))
#define output(f, x) BitsOutput( f, (unsigned long)(x), 16)

int DecodeString(int start, int code);
void InitDictionary(void);

//打印词典
void PrintDictionary(void) {
	int n;
	int count;
	for (n = 256; n < next_code; n++) {
		count = DecodeString(0, n);
		printf("%4d->", n);
		while (0 < count--) printf("%c", (char)(d_stack[count]));
		printf("\n");
	}
}

//解码，可以用来计算phrase_length,也可以用来构造词典
int DecodeString(int start, int code) {
	int count;
	count = start;
	while (0 <= code) {
		d_stack[count] = dictionary[code].suffix;//尾缀
		code = dictionary[code].parent;
		count++;
	}
	return count;
}

int FindCharacter(int new_code,int &character)
{
	int code = new_code;
	int count = 0;
	while (0 <= code) {
		character = dictionary[code].suffix;
		code = dictionary[code].parent;
		count++;
	}
	return count;
}

void PrintCW(int phrase_length,int new_code,FILE* fp)
{
	int code = new_code;
	int count = phrase_length;
	unsigned char* fileout = new unsigned char[phrase_length];
	while (0 < count--) {
		fileout[count] = unsigned char(dictionary[code].suffix);
		code = dictionary[code].parent;
	}
	for (int i = 0; i < phrase_length; i++)
		fprintf(fp, "%c", fileout[i]);
}

//初始化字典
void InitDictionary(void) {
	int i;

	/*初始字典中每一个节点的根节点都是自身，兄弟姐妹就是自己+1，
	只有第256个没有兄弟姐妹*/
	for (i = 0; i < 256; i++) {
		dictionary[i].suffix = i;
		dictionary[i].parent = -1;
		dictionary[i].firstchild = -1;
		dictionary[i].nextsibling = i + 1;
	}
	dictionary[255].nextsibling = -1;
	next_code = 256;	//下一个要进行插入的suffix就是256了
}
/*
 * Input: string represented by string_code in dictionary,
 * Output: the index of character+string in the dictionary
 * 		index = -1 if not found
 */
int InDictionary(int character, int string_code) {
	int sibling;
	if (0 > string_code) return character;			//如果前面没有前缀，那么直接返回刚读入进来的字符
	sibling = dictionary[string_code].firstchild;	//前缀为string_code的first_child
	while (-1 < sibling) {							
		if (character == dictionary[sibling].suffix) return sibling;
		sibling = dictionary[sibling].nextsibling;
	}
	return -1;
}

void AddToDictionary(int character, int string_code) {
	int firstsibling, nextsibling;
	if (0 > string_code) return;
	dictionary[next_code].suffix = character;			//尾缀字符添加为character
	dictionary[next_code].parent = string_code;			//前缀为string_code
	dictionary[next_code].nextsibling = -1;				//没有nextsibling
	dictionary[next_code].firstchild = -1;				//没有firstchild
	firstsibling = dictionary[string_code].firstchild;	//firstsibling是查找string_code得到的firstchild
	if (-1 < firstsibling) {	// the parent has child			
		nextsibling = firstsibling;								
		while (-1 < dictionary[nextsibling].nextsibling)		
			nextsibling = dictionary[nextsibling].nextsibling;	
		dictionary[nextsibling].nextsibling = next_code;
	}
	else {// no child before, modify it to be the first
		dictionary[string_code].firstchild = next_code;
	}
	next_code++;
}

void LZWEncode(FILE* fp, BITFILE* bf) {
	int character;
	int string_code;
	int index;
	unsigned long file_length;

	fseek(fp, 0, SEEK_END);
	file_length = ftell(fp);				//文件的长度
	fseek(fp, 0, SEEK_SET);					//指针重新指回文件开头
	BitsOutput(bf, file_length, 4 * 8);		//写文件长度
	InitDictionary();						//初始化字典树
	string_code = -1;
	while (EOF != (character = fgetc(fp))) {			
		index = InDictionary(character, string_code);	//判断是否在字典中
		if (0 <= index) {	// string+character in dictionary
			string_code = index;
		}
		else {	// string+character not in dictionary
			output(bf, string_code);	//输出string_code
			if (MAX_CODE > next_code) {	// free space in dictionary
				// add string+character to dictionary
				AddToDictionary(character, string_code);
			}
			string_code = character;
		}
	}
	output(bf, string_code);
	PrintDictionary();
}

void LZWDecode(BITFILE* bf, FILE* fp) {
	int character = -1;			//C:str(PW)的第一个字符
	int new_code, last_code;//CW,PW
	int phrase_length;		//短语长度
	unsigned long file_length;

	file_length = BitsInput(bf, 4 * 8);		//读出文件长度
	if (-1 == file_length) file_length = 0;	//如果文件长度为
	InitDictionary();						//初始化字典树
	new_code = input(bf);
	last_code = new_code;
	fprintf(fp, "%c", new_code);
	int decode_length = 1;
	while (decode_length<file_length)	//没读到文件末尾
	{
		new_code = input(bf);
		decode_length++;
		if (dictionary[new_code].suffix != -1)//在字典中
		{
			phrase_length = FindCharacter(new_code,character);
			PrintCW(phrase_length, new_code,fp);
			AddToDictionary(character, last_code);
			last_code = new_code;
			decode_length = decode_length + phrase_length - 1;
		}
		else//不在字典中
		{
			phrase_length = FindCharacter(last_code, character);
			int temp = next_code;
			next_code = new_code;
			AddToDictionary(character, last_code);
			next_code = temp + 1;
			PrintCW(phrase_length + 1, new_code, fp);
			last_code = new_code;
			decode_length = phrase_length + decode_length;
		}
	}
	PrintDictionary();
}

int main(int argc, char** argv) {
	FILE* fp;//输入的文件
	BITFILE* bf;//输出的文件

	//argv[1]:"E/D" argv[2]:读入的文件 argv[3]:读出的文件
	if (4 > argc) {
		fprintf(stdout, "usage: \n%s <o> <ifile> <ofile>\n", argv[0]);
		fprintf(stdout, "\t<o>: E or D reffers encode or decode\n");
		fprintf(stdout, "\t<ifile>: input file name\n");
		fprintf(stdout, "\t<ofile>: output file name\n");
		return -1;
	}
	if ('E' == argv[1][0]) { // do encoding
		errno_t err = 0;
		err = fopen_s(&fp, argv[2], "rb");
		bf = OpenBitFileOutput(argv[3]);//输出的文件
		if (err == 0 && NULL != bf) {
			LZWEncode(fp, bf);
			fclose(fp);
			CloseBitFileOutput(bf);
			fprintf(stdout, "encoding done\n");
		}
	}
	else if ('D' == argv[1][0]) {	// do decoding
		bf = OpenBitFileInput(argv[2]);
		errno_t err = 0;
		err = fopen_s(&fp,argv[3],"wb");
		if (NULL != fp && NULL != bf) {
			LZWDecode(bf, fp);
			fclose(fp);
			CloseBitFileInput(bf);
			fprintf(stdout, "decoding done\n");
		}
	}
	else {	// otherwise
		fprintf(stderr, "not supported operation\n");
	}
	return 0;
}

（三）关键代码分析

3.1 调试属性设置

3.2 main()函数分析

3.3 LZWEncode()函数分析

3.4 LZWDecode()函数分析

3.5 各辅助函数分析

OpenBitFileOutput()函数分析

  作用就是打开需要进行输出的编码二进制文件。

OpenBitFileInput()函数分析

  作用就是打开需要进行解码的编码二进制文件。

BitsOutput()函数分析

InDictionary()函数分析

AddToDictionary()函数分析

PrintDictionary()函数分析

FindCharacter()函数分析

PrintCW()函数分析

  作用就是在解码时将new_code对应的码字输出到输出二进制文件中。

（四）实验结果

4.1 测试代码是否可以正确编解码

阶段	文件1二进制查看
编码前
编码后
解码后

文件1编码程序运行	文件1解码程序运行

文件2压缩解压缩前 txt查看	文件2压缩解压缩后 txt查看

  可以发现，编解码的代码是正确的，可以进行下一步LZW压缩效率的分析。

4.2 对10种不同格式的文件进行压缩

4.2.1 原始文件

4.2.2 压缩文件

4.2.3 压缩效率分析

  可以看出，LZW算法在一部分文件的压缩上有着非常好的效果，比如xls文件，压缩效率高达74.98%,但在另外一部分文件的压缩上则会起到相反的效果，不仅没有压缩，还使得数据量更加大，比如caj文件，压缩效率居然是-26.41%。
  猜测原因：由于文件的编码格式要求限制，一部分文件中字符的重复概率很高，而另一部分文件中字符的重复概率很低，造成了LZW在压缩不同文件时展现出来的截然相反的效果。