数据压缩(七)——LZW压缩编码解码
程序员文章站
2022-03-23 11:09:06
...
对程序的具体分析我放在了程序的注释中。
LZW编码原理
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。LZW编码算法的步骤如下:
步骤1:将词典初始化为包含所有可能的单字符,当前前缀P初始化为空。
步骤2:当前字符C=字符流中的下一个字符。
步骤3:判断P+C是否在词典中
(1)如果“是”,则用C扩展P,即让P=P+C,返回到步骤2。
(2)如果“否”,则
输出与当前前缀P相对应的码字W;
将P+C添加到词典中;
令P=C,并返回到步骤2
LZW解码原理
LZW解码算法开始时,译码词典和编码词典相同,包含所有可能的前缀根。具体解码算法如下:
步骤1:在开始译码时词典包含所有可能的前缀根。
步骤2:令CW:=码字流中的第一个码字。
步骤3:输出当前缀-符串string.CW到码字流。
步骤4:先前码字PW:=当前码字CW。
步骤5:当前码字CW:=码字流的下一个码字。
步骤6:判断当前缀-符串string.CW 是否在词典中。
(1)如果”是”,则把当前缀-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)如果”否”,则当前前缀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。
步骤7:判断码字流中是否还有码字要译。
(1)如果”是”,就返回步骤4。
(2)如果”否”,结束。
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;
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
#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;//标准输出
else
{
errno_t err = 0;
err = fopen_s(&(bf->fp), 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;//rack和mask按位或,再赋值给rack
bf->mask >>= 1;//bit为0的情况
if (0 == bf->mask) { // eight bits in rack
fputc(bf->rack, bf->fp);//把rack写道fp指针指向的位置
bf->rack = 0;
bf->mask = 0x80;
}
}
void BitsOutput(BITFILE* bf, unsigned long code, int count) //code文件长度 count 4*8
{
unsigned long mask;
mask = 1L << (count - 1);//L把1强转成long型赋给mask,左移31位:10000000000......(32位)
while (0 != mask)
{
BitOutput(bf, (int)(0 == (code & mask) ? 0 : 1));//code和mask与运算,如果每位都是0,为0,否则为1
mask >>= 1;//mask=mask右移1位的值
}
}
#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
#include <stdlib.h>
#include<cstdio>
#include <stdio.h>
#include "bitio.h"
#include<iostream>
#define MAX_CODE 65535
using namespace std;
struct {
int suffix;
int parent, firstchild, nextsibling;
} dictionary[MAX_CODE + 1];
int next_code;
int d_stack[MAX_CODE]; // stack for decoding a phrase 用于解码 堆栈
#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);//指针指向文件尾
file_length = ftell(fp);//算当前指针到文件头的偏移,即文件长度
fseek(fp, 0, SEEK_SET);//指针指向文件开头
BitsOutput(bf, file_length, 4 * 8);//mask rack
InitDictionary();//初始化词典
string_code = -1;
while (EOF != (character = fgetc(fp))) //往后读一个字符
{
index = InDictionary(character, string_code);//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);
if (MAX_CODE > next_code) { // free space in dictionary
// add string+character to dictionary
AddToDictionary(character, string_code);
}
string_code = character;//string的编码
}
}
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;//同编码
while (0 < file_length)
{
new_code = input(bf);//BitsInput( f, 16)
if (new_code >= next_code) //>=256(不在字典里),就需要解码
{ // this is the case CSCSC( not in dict)
d_stack[0] = character;
phrase_length = DecodeString(1, last_code);//start=1,
}
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]) //编码 第一个参数的第一个字符是E
{
errno_t err = 0;
err = fopen_s(&fp,argv[2], "rb");
bf = OpenBitFileOutput(argv[3]);//wb形式打开文件argv[3],把这个文件放进bf结构体里的fp中,同时是给mask、rack赋值
if (NULL != fp && NULL != bf)
{
LZWEncode(fp, bf);//编码函数
fclose(fp);
CloseBitFileOutput(bf);
fprintf(stdout, "encoding done\n");
}
}
else if ('D' == argv[1][0]) { // do decoding
bf = OpenBitFileInput(argv[2]);
errno_t err1 = 0;
err1 = fopen_s(&fp,argv[3], "wb");
if (NULL != fp && NULL != bf)
{
LZWDecode(bf, fp);//解码
fclose(fp);
CloseBitFileInput(bf);
fprintf(stdout, "decoding done\n");
}
}
else { // otherwise
fprintf(stderr, "not supported operation\n");
}
return 0;
}
命令参数
argv[1][0]是“E”或者“D”。E代表编码,D代表解码,我把argv[2]直接理解为输入文件,argv[3]为输出文件。
用一个简单的txt文件,检验一下编解码程序的有效性
"1.txt"为原文件,“2.txt"为压缩后解压的文件。“2.dat”是压缩后的文件,用二进制打开。
用一张照片测试了一下各个文件格式的压缩程度,这张照片压缩后的文件都比原文件更大,猜想文件中字符的重复概率很低导致的结果。
下一篇: 通过Python爬取当当网,学正则表达式