跨平台正则表达式POSIX regex的使用

Unix系列平台下有现成的regex库，直接添加即可使用。

windows下可以使用Regex for Windows

相关的函数在regex.h中：

int regcomp (regex_t *compiled, const char *pattern, int cflags)
int regexec (regex_t *compiled, char *string, size_t nmatch, regmatch_t matchptr [], int
　　　           eflags)
void regfree (regex_t *compiled)
size_t regerror (int errcode, regex_t *compiled, char *buffer, size_t length)

正则表达式需要经过regcomp编译，regexec执行，最后regfree释放资源。

测试代码：

#include <iostream>
#include <sys/types.h>
#include <stdio.h>
#include <cstring>
#include <regex.h>

using namespace std;

#define SUBSLEN 10
#define EBUFLEN 100
#define BUFLEN 1000

int main(int argc,char** argv)
{
size_t       len;
regex_t       re;
regmatch_t    subs [SUBSLEN];
char          matched [BUFLEN];
char          errbuf [EBUFLEN];
int           err;

char          string[] = "!@#$%^&hello world!@#$%^&*()";
char          pattern[] = "hello";

printf("String to match: %s\n", string);
printf("Match pattern: \"%s\"\n", pattern);

err = regcomp(&re, pattern, REG_EXTENDED);
if (err)
{
len = regerror(err, &re, errbuf, sizeof(errbuf));
printf("error: regcomp: %s\n", errbuf);
return 1;
}

err = regexec(&re, string, (size_t) SUBSLEN, subs, 0);
if (err == REG_NOMATCH)
{
printf("No match found.\n");
regfree(&re);
return 0;
}
else if (err)
{
len = regerror(err, &re, errbuf, sizeof(errbuf));
printf("Error in regexec: %s\n", errbuf);
return 1;
}

printf("Match found.\n");
for (int i = 0; i <= re.re_nsub; i++)
{
len = subs[i].rm_eo - subs[i].rm_so;
if (i == 0)
{
printf ("Substring begin:%d, len = %d   ", (int)subs[i].rm_so, (int)len);
}
else
{
printf("subexpression_r_r %d begin: %d, len = %d   ", i, (int)subs[i].rm_so, (int)len);
}

memcpy (matched, string + subs[i].rm_so, len);
matched[len] = '\0';
printf("Matched substring: %s\n", matched);
}

regfree(&re);
return 0 ;
}

Linux下编译：

g++ -c regextest.cpp

g++ -o regextest regextest.o -ldl

执行：

davinciyxw@ubuntu:~/develop/regex_test$ ./regextest

String to match: !@#$%^&hello world!@#$%^&*()

Match pattern: "hello"

Match found.

Substring begin:7, len = 5 Matched substring: hello

---------------------------------------------------------------------------------------------------------

AIX下编译：

xlC -q64 -brtl -o regextest -lpthread regextest.cpp

执行：

[aix][davinciyxw][/Dev/Test]>regextest

String to match: !@#$%^&hello world!@#$%^&*()

Match pattern: "hello"

Match found.

Substring begin:7, len = 5 Matched substring: hello

---------------------------------------------------------------------------------------------------------

Windows下建立C++控制台程序

添加上文中下载的regex.lib到链接器输入，将regex2.dll拷贝至运行目录编译即可。

执行：

略。