一.LWZ编解码原理
- LZW编码原理思路
LZW的编码思想是不断地从字符流中提取新的字符串,通俗地理解为新“词条”,然后用“代号”也就是码字表示这个“词条”。这样一来,对字符流的编码就变成了用码字去替换字符流,生成码字流,从而达到压缩数据的目的。LZW编码是围绕称为词典的转换表来完成的。LZW编码器通过管理这个词典完成输入与输出之间的转换。LZW编码器的输入是字符流,字符流可以是用8位ASCII字符组成的字符串,而输出是用n位(例如12位)表示的码字流。
初始状态,字典里只有所有的默认项,例如0->a,1->b,2->c。此时P和C都是空的。
读入新的字符C,与P合并形成字符串P+C。
在字典里查找P+C,如果:
P+C在字典里,P=P+C。
P+C不在字典里,将P的记号输出;在字典中为P+C建立一个记号映射;更新P=C。
返回步骤2重复,直至读完原字符串中所有字符。
下面举一个例子来解释该原理,首先我们先来定义一个字典:
0->a
1->b
2->c
而后我们对一串字符串进行编码:abcababa
首先P为空,C为a ,,P+C在字典中,则P=P+C=a,C=b,P+C=ab不在字典中,则更新字典3->ab而后输出P为0 P=C=b,而后C=c,P+C=bc不在,4->bc ,输出P为1,以此类推,直到最后一个字符,可得出编码完成为0 1 2 3 6,字典更新完成为:
0->a
1->b
2->c
3->ab
4->bc
5->ca
6->aba
- LZW解码原理思路
在开始译码时词典包含所有可能的前缀根;
令CW=码字流中的第一个码字;
输出当前缀-符串string.CW到码字流;
先前码字PW=当前码字CW;
当前码字CW=码字流的下一个码字;
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。
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。
二.代码实现
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__
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;
}
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 case 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;
}
}
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;
}
三.实验结论
对于重复率较高的文件,利用字典压缩效果较好;对于字符重复率较低的文件,字典带来的数据反而成了一种冗余。