Question

The title is pretty explicit and below are couple of samples input/output. Note that the regexps used are supposed to match from beginning to end of the string.

'abc' =~ 'abc' (match)
'abc' =~ 'a*bc' (match)
'aaaaaaabc' =~ 'c*bc' (no match)
'aaaaaaabc' =~ 'a.*bc' (match)
'abbbbaaaaaabc' =~ 'ab*a*b*c' (match)
'abbbbaaaaaabc' =~ 'ab*a*h*bc' (match)
'bbd' =~ 'b*bbd' (match)
'bbd' =~ '.*bbd' (match)
'bbd' =~ '.*cbd' (no match)
'' =~ '.*' (match)

My implementation for this is located at:

https://github.com/jpbillaud/piexposed/blob/master/string/string_match_regexp.c

Now I was wondering if anybody would think about a more interesting way to solve this using DP, Finite Automata or whatever else.

Answer 1

Take a look at this implementation of a regular expression matcher by Rob Pike, taken from the book The Practice of Programming. It’s absolutely beautiful code, in just 35 lines of C it happens to meet all the requirements in the question (and a bit more!). Quoting from the article referenced above:

/* match: search for regexp anywhere in text */
int match(char *regexp, char *text)
{
    if (regexp[0] == '^')
        return matchhere(regexp+1, text);
    do {    /* must look even if string is empty */
        if (matchhere(regexp, text))
            return 1;
    } while (*text++ != '\0');
    return 0;
}

/* matchhere: search for regexp at beginning of text */
int matchhere(char *regexp, char *text)
{
    if (regexp[0] == '\0')
        return 1;
    if (regexp[1] == '*')
        return matchstar(regexp[0], regexp+2, text);
    if (regexp[0] == '$' && regexp[1] == '\0')
        return *text == '\0';
    if (*text!='\0' && (regexp[0]=='.' || regexp[0]==*text))
        return matchhere(regexp+1, text+1);
    return 0;
}

/* matchstar: search for c*regexp at beginning of text */
int matchstar(int c, char *regexp, char *text)
{
    do {    /* a * matches zero or more instances */
        if (matchhere(regexp, text))
            return 1;
    } while (*text != '\0' && (*text++ == c || c == '.'));
    return 0;
}