[c] Regular expressions in C: examples?

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.

man regex.h reports there is no manual entry for regex.h, but man 3 regex gives you a page explaining the POSIX functions for pattern matching.
The same functions are described in The GNU C Library: Regular Expression Matching, which explains that the GNU C Library supports both the POSIX.2 interface and the interface the GNU C Library has had for many years.

For example, for an hypothetical program that prints which of the strings passed as argument match the pattern passed as first argument, you could use code similar to the following one.

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

void print_regerror (int errcode, size_t length, regex_t *compiled);

int
main (int argc, char *argv[])
{
  regex_t regex;
  int result;

  if (argc < 3)
    {
      // The number of passed arguments is lower than the number of
      // expected arguments.
      fputs ("Missing command line arguments\n", stderr);
      return EXIT_FAILURE;
    }

  result = regcomp (&regex, argv[1], REG_EXTENDED);
  if (result)
    {
      // Any value different from 0 means it was not possible to 
      // compile the regular expression, either for memory problems
      // or problems with the regular expression syntax.
      if (result == REG_ESPACE)
        fprintf (stderr, "%s\n", strerror(ENOMEM));
      else
        fputs ("Syntax error in the regular expression passed as first argument\n", stderr);
      return EXIT_FAILURE;               
    }
  for (int i = 2; i < argc; i++)
    {
      result = regexec (&regex, argv[i], 0, NULL, 0);
      if (!result)
        {
          printf ("'%s' matches the regular expression\n", argv[i]);
        }
      else if (result == REG_NOMATCH)
        {
          printf ("'%s' doesn't the regular expression\n", argv[i]);
        }
      else
        {
          // The function returned an error; print the string 
          // describing it.
          // Get the size of the buffer required for the error message.
          size_t length = regerror (result, &regex, NULL, 0);
          print_regerror (result, length, &regex);       
          return EXIT_FAILURE;
        }
    }

  /* Free the memory allocated from regcomp(). */
  regfree (&regex);
  return EXIT_SUCCESS;
}

void
print_regerror (int errcode, size_t length, regex_t *compiled)
{
  char buffer[length];
  (void) regerror (errcode, compiled, buffer, length);
  fprintf(stderr, "Regex match failed: %s\n", buffer);
}

The last argument of regcomp() needs to be at least REG_EXTENDED, or the functions will use basic regular expressions, which means that (for example) you would need to use a\{3\} instead of a{3} used from extended regular expressions, which is probably what you expect to use.

POSIX.2 has also another function for wildcard matching: fnmatch(). It doesn't allow to compile the regular expression, or get the substrings matching a sub-expression, but it is very specific for checking when a filename match a wildcard (e.g. it uses the FNM_PATHNAME flag).

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.

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.

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);
    }

}