数据压缩实验三——LZW编码

一、实验目的

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。

二、实验原理

（1）编码

1. 初始字典包含所有的单字符，初始化P=NULL；
2. 将数据流的下一个字符赋给C；
3. 判断P+C(P连接C)这个字符是否在字典里：
   1. 是：P=P+C；
   2. 否：输出P对应的码字CW，将P+C作为新串写入字典，P=C；返回步骤2。

（2）解码

1. 在开始译码时词典包含所有可能的前缀根；

2. 令CW=码字流中的第一个码字；

3. 输出当前缀-符串string.CW到码字流；

4. 先前码字PW=当前码字CW；

5. 当前码字CW=码字流的下一个码字；

6. 判断当前缀-符串string.CW 是否在词典中：
   1. 是：把当前缀-符串string.CW输出到字符流：
   当前前缀P=先前缀-符串string.PW；
   当前字符C=当前前缀-符串string.CW的第一个字符；
   把缀-符串P+C添加到词典；
   2. 否：当前前缀P=先前缀-符串string.PW。
   当前字符C=当前缀-符串string.CW的第一个字符。
   输出缀-符串P+C到字符流,然后把它添加到词典中。

7. 判断码字流中是否还有码字要译：

   1. 是：返回步骤4；
   2. 否：结束。

三、实验代码

1. bitio.h

#ifndef __BITIO__
#define __BITIO__

#include <stdio.h>

typedef struct{
	FILE *fp;
	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__

2. bitio.c

#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 bf->fp = fopen( 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 bf->fp = fopen( filename, "wb");
	if( NULL == bf->fp) return NULL;
	bf->mask = 0x80;
	bf->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;
	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);
		bf->rack = 0;
		bf->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

3. lzw_E.c

#include <stdlib.h>
#include <stdio.h>
#include "bitio.h"
#define MAX_CODE 65535

struct {
	int suffix;
	int parent, firstchild, nextsibling;
} 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);
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");
	}
}

int DecodeString( int start, int code){
	int count;
	count = start;
	while( 0<=code){
		d_stack[ count] = dictionary[code].suffix;
		code = dictionary[code].parent;
		count ++;
	}
	return count;
}
void InitDictionary( void){
	int i;

	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;
}
/*
 * 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;
	sibling = dictionary[string_code].firstchild;
	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;
	dictionary[next_code].parent = string_code;
	dictionary[next_code].nextsibling = -1;
	dictionary[next_code].firstchild = -1;
	firstsibling = dictionary[string_code].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);
	fseek( fp, 0, SEEK_SET);
	BitsOutput( bf, file_length, 4*8);
	InitDictionary();
	string_code = -1;
	while( EOF!=(character=fgetc( fp))){
		index = InDictionary( character, string_code);
		if( 0<=index){	// string+character in dictionary
			string_code = index;
		}else{	// string+character not in dictionary
			output( bf, 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);
}

void LZWDecode( BITFILE *bf, FILE *fp){
	int character;
	int new_code, last_code;
	int phrase_length;
	unsigned long file_length;

	file_length = BitsInput( bf, 4*8);
	if( -1 == file_length) file_length = 0;
	InitDictionary();
	last_code=-1;
	while(0<file_length)
	{
		new_code=input(bf);
		if(new_code>=next_code)
		{
			//this is the CSCSC(not in dict)
			d_stack[0]=character;
			phrase_length=DecodeString(1,last_code);
		}
		else
		{
			phrase_length=DecodeString(0,new_code);
		}
		character=d_stack[phrase_length-1];
		while(0<phrase_length)
		{
			phrase_length --;
			fputc(d_stack[phrase_length],fp);
			file_length--;
		}
		if(MAX_CODE>next_code)
		{
			//add the new phrase to dictionary
			AddToDictionary(character,last_code);
		}
		last_code=new_code;
	}
	/*需填充*/
}



int main( int argc, char **argv){
	FILE *fp;
	BITFILE *bf;

	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
		fp = fopen( argv[2], "rb");
		bf = OpenBitFileOutput( argv[3]);
		if( NULL!=fp && 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]);
		fp = fopen( 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;
}

四、实验结果

1. 调试程序
   
   
2. 选择至少十种不同格式类型的文件，使用LZW编码器进行压缩得到输出的压缩比特流文件。对各种不同格式的文件进行压缩效率的分析。

结论：有些文件可能会越压越大。