regcomp/regexec/regfree--POSIX regex functions

语法

       #include <sys/types.h>
       #include <regex.h>

       int regcomp(regex_t *preg, const char *regex, int cflags);

       int regexec(const regex_t *preg, const char *string, size_t nmatch,
                   regmatch_t pmatch[], int eflags);

       size_t regerror(int errcode, const regex_t *preg, char *errbuf,
                       size_t errbuf_size);

       void regfree(regex_t *preg);

解析

正则表达式库函数主要分两部分，正则表达式编译和匹配。编译用于正则表达式提供格式（程序识别），匹配用于提供匹配位置便于提取。

regcomp()  is  used to compile a regular expression into a form that is suitable for subsequent regexec() searches.
regexec() is used to match a null-terminated string against the precompiled  pattern  buffer,  preg.   nmatch  and pmatch are used to provide information regarding the location of any matches.  eflags may  be  the bitwise-or  of  one  or  both  of REG_NOTBOL and REG_NOTEOL which cause changes in matching behavior described below.

示例

 

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <regex.h>

#define MATCH_NUM 3

char str[]={"Chinese love China! China, fighting!\n"};

int main(int argc, char **argv)
{
    regex_t reg;
    int ret = 0, i = 0;
    regmatch_t matches[MATCH_NUM];
    char *ps = NULL;

    ret = regcomp(&reg, "Chin.", REG_NEWLINE | REG_EXTENDED);
    if(ret != 0){ 
        perror("regcomp");
        exit(1);
    }   
    
    ret = regexec(&reg, str, MATCH_NUM, matches, 0); 
    if(ret != 0){ 
        perror("regexec");
        exit(1);
    }   
    for(i = 0; i < MATCH_NUM; i++){
        ps = strndup(str + matches[i].rm_so, matches[i].rm_eo - matches[i].rm_so);
        if(ps)
            printf("The match %dst is [%s]:[%d:%d]\n", i, ps, matches[i].rm_so, matches[i].rm_eo);
        free(ps);
    }

    regfree(&reg);

    return 0;
}

~$gcc regex.c -Wall
~$./a.out 
The match 0st is [Chine]:[0:5]
The match 1st is []:[-1:-1]
The match 2st is []:[-1:-1]

明显不是想要的结果，需继续测试。