这篇文章主要讲解了“C语言如何实现短字符串压缩”，文中的讲解内容简单清晰，易于学习与理解，下面请大家跟着小编的思路慢慢深入，一起来研究和学习“C语言如何实现短字符串压缩”吧！
开门见山，我们使用一段比较短的文本：Narrator: It is raining today. So, Peppa and George cannot play outside.Peppa: Daddy, it's stopped raining.
使用ZSTD与LZ4分别压缩一下上面这段短文本。下面分别是它们的压缩结果。
ZSTD：
LZ4：
对短文本的压缩，zstd的压缩率很低，lz4压缩后的文本长度尽然超过了原有字符串的长度。这是为什么？说实话在这之前我也没想到。
引用两位大佬的名言：
Are you ok?
What's your problem?
从上面的结果可以得知，任何压缩算法都有它的使用场景，并不是所有长度的字符串都适合被某种算法压缩。一般原因是通用压缩算法维护了被压缩字符串的，用于字符串还原的相关数据结构，而这些数据结构的长度超过了被压缩短字符串的自身长度。
那么问题来了，“我真的有压缩短字符串的需求，我想体验压缩的极致感，怎么办？”。
短字符压缩算法它来了。这里挑选了3种比较优异的短字符压缩算法，分别是smaz，shoco，以及压轴的unisox2。跟前两章一样，还是从压缩率，压缩和解压缩性能的角度，一起看看他们在短字符压缩场景的各自表现吧。
1、Smaz的压缩和解压缩
#include <stdio.h>
#include <string.h>
#include <iostream>
#include "smaz.h"
using namespace std;
int main()
{
int buf_len;
int com_size;
int decom_size;
char com_buf[4096] = {0};
char decom_buf[4096] = {0};
char str_buf[1024] = "Narrator: It is raining today. So, Peppa and George cannot play outside.Peppa: Daddy, it's stopped raining.";
buf_len = strlen(str_buf);
com_size = smaz_compress(str_buf, buf_len, com_buf, 4096);
cout << "text size:" << buf_len << endl;
cout << "compress text size:" << com_size << endl;
cout << "compress ratio:" << (float)buf_len / (float)com_size << endl << endl;
decom_size = smaz_decompress(com_buf, com_size, decom_buf, 4096);
cout << "decompress text size:" << decom_size << endl;
if(strncmp(str_buf, decom_buf, buf_len)) {
cout << "decompress text is not equal to source text" << endl;
}
return 0;
}执行结果如下：
通过smaz压缩后的短字符串长度为77，和源字符串相比，减少了30Byte。
2、Smaz的压缩和解压缩性能
#include <stdio.h>
#include <string.h>
#include <iostream>
#include <sys/time.h>
#include "smaz.h"
using namespace std;
int main()
{
int cnt = 0;
int buf_len;
int com_size;
int decom_size;
timeval st, et;
char *com_ptr = NULL;
char* decom_ptr = NULL;
char str_buf[1024] = "Narrator: It is raining today. So, Peppa and George cannot play outside.Peppa: Daddy, it's stopped raining.";
buf_len = strlen(str_buf);
gettimeofday(&st, NULL);
while(1) {
com_ptr = (char *)malloc(buf_len);
com_size = smaz_compress(str_buf, buf_len, com_ptr, buf_len);
free(com_ptr);
cnt++;
gettimeofday(&et, NULL);
if(et.tv_sec - st.tv_sec >= 10) {
break;
}
}
cout << endl <<"compress per second:" << cnt/10 << " times" << endl;
cnt = 0;
com_ptr = (char *)malloc(buf_len);
com_size = smaz_compress(str_buf, buf_len, com_ptr, buf_len);
gettimeofday(&st, NULL);
while(1) {
// decompress length not more than origin buf length
decom_ptr = (char *)malloc(buf_len + 1);
decom_size = smaz_decompress(com_ptr, com_size, decom_ptr, buf_len + 1);
// check decompress length
if(buf_len != decom_size) {
cout << "decom error" << endl;
}
free(decom_ptr);
cnt++;
gettimeofday(&et, NULL);
if(et.tv_sec - st.tv_sec >= 10) {
break;
}
}
cout << "decompress per second:" << cnt/10 << " times" << endl << endl;
free(com_ptr);
return 0;
}结果如何？
压缩性能在40w条/S，解压在百万级，好像还不错哈！
1、Shoco的压缩和解压缩
#include <stdio.h>
#include <string.h>
#include <iostream>
#include "shoco.h"
using namespace std;
int main()
{
int buf_len;
int com_size;
int decom_size;
char com_buf[4096] = {0};
char decom_buf[4096] = {0};
char str_buf[1024] = "Narrator: It is raining today. So, Peppa and George cannot play outside.Peppa: Daddy, it's stopped raining.";
buf_len = strlen(str_buf);
com_size = shoco_compress(str_buf, buf_len, com_buf, 4096);
cout << "text size:" << buf_len << endl;
cout << "compress text size:" << com_size << endl;
cout << "compress ratio:" << (float)buf_len / (float)com_size << endl << endl;
decom_size = shoco_decompress(com_buf, com_size, decom_buf, 4096);
cout << "decompress text size:" << decom_size << endl;
if(strncmp(str_buf, decom_buf, buf_len)) {
cout << "decompress text is not equal to source text" << endl;
}
return 0;
}执行结果如下：
通过shoco压缩后的短字符串长度为86，和源字符串相比，减少了21Byte。压缩率比smaz要低。
2、Shoco的压缩和解压缩性能
#include <stdio.h>
#include <string.h>
#include <iostream>
#include <sys/time.h>
#include "shoco.h"
using namespace std;
int main()
{
int cnt = 0;
int buf_len;
int com_size;
int decom_size;
timeval st, et;
char *com_ptr = NULL;
char* decom_ptr = NULL;
char str_buf[1024] = "Narrator: It is raining today. So, Peppa and George cannot play outside.Peppa: Daddy, it's stopped raining.";
buf_len = strlen(str_buf);
gettimeofday(&st, NULL);
while(1) {
com_ptr = (char *)malloc(buf_len);
com_size = shoco_compress(str_buf, buf_len, com_ptr, buf_len);
free(com_ptr);
cnt++;
gettimeofday(&et, NULL);
if(et.tv_sec - st.tv_sec >= 10) {
break;
}
}
cout << endl <<"compress per second:" << cnt/10 << " times" << endl;
cnt = 0;
com_ptr = (char *)malloc(buf_len);
com_size = shoco_compress(str_buf, buf_len, com_ptr, buf_len);
gettimeofday(&st, NULL);
while(1) {
// decompress length not more than origin buf length
decom_ptr = (char *)malloc(buf_len + 1);
decom_size = shoco_decompress(com_ptr, com_size, decom_ptr, buf_len + 1);
// check decompress length
if(buf_len != decom_size) {
cout << "decom error" << endl;
}
free(decom_ptr);
cnt++;
gettimeofday(&et, NULL);
if(et.tv_sec - st.tv_sec >= 10) {
break;
}
}
cout << "decompress per second:" << cnt/10 << " times" << endl << endl;
free(com_ptr);
return 0;
}执行结果如何呢？
holy shit！压缩和解压缩居然都达到了惊人的百万级。就像算法作者们自己说的一样：“在长字符串压缩领域，shoco不想与通用压缩算法竞争，我们的优势是短字符的快速压缩，虽然压缩率很烂！”。这样说，好像也没毛病。
我们再来看看unisox2呢。
1、Unisox2的压缩和解压缩
#include <stdio.h>
#include <string.h>
#include "unishox2.h"
int main()
{
int buf_len;
int com_size;
int decom_size;
char com_buf[4096] = {0};
char decom_buf[4096] = {0};
char str_buf[1024] = "Narrator: It is raining today. So, Peppa and George cannot play outside.Peppa: Daddy, it's stopped raining.";
buf_len = strlen(str_buf);
com_size = unishox2_compress_simple(str_buf, buf_len, com_buf);
printf("text size:%d\n", buf_len);
printf("compress text size:%d\n", com_size);
printf("compress ratio:%f\n\n", (float)buf_len / (float)com_size);
decom_size = unishox2_decompress_simple(com_buf, com_size, decom_buf);
printf("decompress text size:%d\n", decom_size);
if(strncmp(str_buf, decom_buf, buf_len)) {
printf("decompress text is not equal to source text\n");
}
return 0;
}结果如下：
通过Unisox2压缩后的短字符串长度为67，和源字符串相比，减少了40Byte，相当于是打了6折啊！不错不错。
2、Unisox2的压缩和解压缩性能
Unisox2的压缩能力目前来看是三者中最好的，如果他的压缩和解压性能也不错的话，那就真的就比较完美了。再一起看看Unisox2的压缩和解压性能吧！
#include <stdio.h>
#include <string.h>
#include <malloc.h>
#include <sys/time.h>
#include "unishox2.h"
int main()
{
int cnt = 0;
int buf_len;
int com_size;
int decom_size;
struct timeval st, et;
char *com_ptr = NULL;
char* decom_ptr = NULL;
char str_buf[1024] = "Narrator: It is raining today. So, Peppa and George cannot play outside.Peppa: Daddy, it's stopped raining.";
buf_len = strlen(str_buf);
gettimeofday(&st, NULL);
while(1) {
com_ptr = (char *)malloc(buf_len);
com_size = unishox2_compress_simple(str_buf, buf_len, com_ptr);
free(com_ptr);
cnt++;
gettimeofday(&et, NULL);
if(et.tv_sec - st.tv_sec >= 10) {
break;
}
}
printf("\ncompress per second:%d times\n", cnt/10);
cnt = 0;
com_ptr = (char *)malloc(buf_len);
com_size = unishox2_compress_simple(str_buf, buf_len, com_ptr);
gettimeofday(&st, NULL);
while(1) {
// decompress length not more than origin buf length
decom_ptr = (char *)malloc(buf_len + 1);
decom_size = unishox2_decompress_simple(com_ptr, com_size, decom_ptr);
// check decompress length
if(buf_len != decom_size) {
printf("decom error\n");
}
free(decom_ptr);
cnt++;
gettimeofday(&et, NULL);
if(et.tv_sec - st.tv_sec >= 10) {
break;
}
}
printf("decompress per second:%d times\n\n", cnt/10);
free(com_ptr);
return 0;
}执行结果如下：
事与愿违，Unisox2虽然有三个算法中最好的压缩率，可是却也拥有最差的压缩和解压性能。
感谢各位的阅读，以上就是“C语言如何实现短字符串压缩”的内容了，经过本文的学习后，相信大家对C语言如何实现短字符串压缩这一问题有了更深刻的体会，具体使用情况还需要大家实践验证。这里是亿速云，小编将为大家推送更多相关知识点的文章，欢迎关注！
免责声明：本站发布的内容（图片、视频和文字）以原创、转载和分享为主，文章观点不代表本网站立场，如果涉及侵权请联系站长邮箱：is@yisu.com进行举报，并提供相关证据，一经查实，将立刻删除涉嫌侵权内容。
