Regular expressions in C: examples?

Viewed 404507

I'm after some simple examples and best practices of how to use regular expressions in ANSI C. man regex.h does not provide that much help.

5 Answers

Regular expressions actually aren't part of ANSI C. It sounds like you might be talking about the POSIX regular expression library, which comes with most (all?) *nixes. Here's an example of using POSIX regexes in C (based on this):

#include <regex.h>        
regex_t regex;
int reti;
char msgbuf[100];

/* Compile regular expression */
reti = regcomp(&regex, "^a[[:alnum:]]", 0);
if (reti) {
    fprintf(stderr, "Could not compile regex\n");
    exit(1);
}

/* Execute regular expression */
reti = regexec(&regex, "abc", 0, NULL, 0);
if (!reti) {
    puts("Match");
}
else if (reti == REG_NOMATCH) {
    puts("No match");
}
else {
    regerror(reti, &regex, msgbuf, sizeof(msgbuf));
    fprintf(stderr, "Regex match failed: %s\n", msgbuf);
    exit(1);
}

/* Free memory allocated to the pattern buffer by regcomp() */
regfree(&regex);

Alternatively, you may want to check out PCRE, a library for Perl-compatible regular expressions in C. The Perl syntax is pretty much that same syntax used in Java, Python, and a number of other languages. The POSIX syntax is the syntax used by grep, sed, vi, etc.

It's probably not what you want, but a tool like re2c can compile POSIX(-ish) regular expressions to ANSI C. It's written as a replacement for lex, but this approach allows you to sacrifice flexibility and legibility for the last bit of speed, if you really need it.

This is an example of using REG_EXTENDED. This regular expression

"^(-)?([0-9]+)((,|.)([0-9]+))?\n$"

Allows you to catch decimal numbers in Spanish system and international. :)

#include <regex.h>
#include <stdlib.h>
#include <stdio.h>
regex_t regex;
int reti;
char msgbuf[100];

int main(int argc, char const *argv[])
{
    while(1){
        fgets( msgbuf, 100, stdin );
        reti = regcomp(&regex, "^(-)?([0-9]+)((,|.)([0-9]+))?\n$", REG_EXTENDED);
        if (reti) {
            fprintf(stderr, "Could not compile regex\n");
            exit(1);
        }

        /* Execute regular expression */
        printf("%s\n", msgbuf);
        reti = regexec(&regex, msgbuf, 0, NULL, 0);
        if (!reti) {
            puts("Match");
        }
        else if (reti == REG_NOMATCH) {
            puts("No match");
        }
        else {
            regerror(reti, &regex, msgbuf, sizeof(msgbuf));
            fprintf(stderr, "Regex match failed: %s\n", msgbuf);
            exit(1);
        }

        /* Free memory allocated to the pattern buffer by regcomp() */
        regfree(&regex);
    }

}

While the answer above is good, I recommend using PCRE2. This means you can literally use all the regex examples out there now and not have to translate from some ancient regex.

I made an answer for this already, but I think it can help here too..

Regex In C To Search For Credit Card Numbers

// YOU MUST SPECIFY THE UNIT WIDTH BEFORE THE INCLUDE OF THE pcre.h

#define PCRE2_CODE_UNIT_WIDTH 8
#include <stdio.h>
#include <string.h>
#include <pcre2.h>
#include <stdbool.h>

int main(){

bool Debug = true;
bool Found = false;
pcre2_code *re;
PCRE2_SPTR pattern;
PCRE2_SPTR subject;
int errornumber;
int i;
int rc;
PCRE2_SIZE erroroffset;
PCRE2_SIZE *ovector;
size_t subject_length;
pcre2_match_data *match_data;


char * RegexStr = "(?:\\D|^)(5[1-5][0-9]{2}(?:\\ |\\-|)[0-9]{4}(?:\\ |\\-|)[0-9]{4}(?:\\ |\\-|)[0-9]{4})(?:\\D|$)";
char * source = "5111 2222 3333 4444";

pattern = (PCRE2_SPTR)RegexStr;// <<<<< This is where you pass your REGEX 
subject = (PCRE2_SPTR)source;// <<<<< This is where you pass your bufer that will be checked. 
subject_length = strlen((char *)subject);




  re = pcre2_compile(
  pattern,               /* the pattern */
  PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
  0,                     /* default options */
  &errornumber,          /* for error number */
  &erroroffset,          /* for error offset */
  NULL);                 /* use default compile context */

/* Compilation failed: print the error message and exit. */
if (re == NULL)
  {
  PCRE2_UCHAR buffer[256];
  pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
  printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset,buffer);
  return 1;
  }


match_data = pcre2_match_data_create_from_pattern(re, NULL);

rc = pcre2_match(
  re,
  subject,              /* the subject string */
  subject_length,       /* the length of the subject */
  0,                    /* start at offset 0 in the subject */
  0,                    /* default options */
  match_data,           /* block for storing the result */
  NULL);

if (rc < 0)
  {
  switch(rc)
    {
    case PCRE2_ERROR_NOMATCH: //printf("No match\n"); //
    pcre2_match_data_free(match_data);
    pcre2_code_free(re);
    Found = 0;
    return Found;
    //  break;
    /*
    Handle other special cases if you like
    */
    default: printf("Matching error %d\n", rc); //break;
    }
  pcre2_match_data_free(match_data);   /* Release memory used for the match */
  pcre2_code_free(re);
  Found = 0;                /* data and the compiled pattern. */
  return Found;
  }


if (Debug){
ovector = pcre2_get_ovector_pointer(match_data);
printf("Match succeeded at offset %d\n", (int)ovector[0]);

if (rc == 0)
  printf("ovector was not big enough for all the captured substrings\n");


if (ovector[0] > ovector[1])
  {
  printf("\\K was used in an assertion to set the match start after its end.\n"
    "From end to start the match was: %.*s\n", (int)(ovector[0] - ovector[1]),
      (char *)(subject + ovector[1]));
  printf("Run abandoned\n");
  pcre2_match_data_free(match_data);
  pcre2_code_free(re);
  return 0;
}

for (i = 0; i < rc; i++)
  {
  PCRE2_SPTR substring_start = subject + ovector[2*i];
  size_t substring_length = ovector[2*i+1] - ovector[2*i];
  printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
  }
}

else{
  if(rc > 0){
    Found = true;

    } 
} 
pcre2_match_data_free(match_data);
pcre2_code_free(re);
return Found;

}

Install PCRE using:

wget https://ftp.pcre.org/pub/pcre/pcre2-10.31.zip
make 
sudo make install 
sudo ldconfig

Compile using :

gcc foo.c -lpcre2-8 -o foo

Check my answer for more details.

Related