Function regcomp

v2/engine/regexp.c:216–294

- regcomp - compile a regular expression into internal code * * We can't allocate space until we know how big the compiled form will be, * but we can't compile it (and thus know how big it is) until we've got a * place to put the code. So we cheat: we compile it twice, once with code * generation turned off and size counting turned on, and once "for real". * This also means that we don't a

 * of the structure of the compiled regexp.
 */
regexp *
regcomp( const char *exp )
{
    register regexp *r;
    register char *scan;
    register char *longest;
    register unsigned len;
    int flags;

    if (exp == NULL)
        FAIL("NULL argument");

    /* First pass: determine size, legality. */
#ifdef notdef
    if (exp[0] == '.' && exp[1] == '*') exp += 2;  /* aid grep */
#endif
    regparse = (char *)exp;
    regnpar = 1;
    regsize = 0L;
    regcode = &regdummy;
    regc(MAGIC);
    if (reg(0, &flags) == NULL)
        return(NULL);

    /* Small enough for pointer-storage convention? */
    if (regsize >= 32767L)      /* Probably could be 65535L. */
        FAIL("regexp too big");

    /* Allocate space. */
    r = (regexp *)BJAM_MALLOC(sizeof(regexp) + (unsigned)regsize);
    if (r == NULL)
        FAIL("out of space");

    /* Second pass: emit code. */
    regparse = (char *)exp;
    regnpar = 1;
    regcode = r->program;
    regc(MAGIC);
    if (reg(0, &flags) == NULL)
        return(NULL);

    /* Dig out information for optimizations. */
    r->regstart = '\0'; /* Worst-case defaults. */
    r->reganch = 0;
    r->regmust = NULL;
    r->regmlen = 0;
    scan = r->program+1;            /* First BRANCH. */
    if (OP(regnext(scan)) == END) {     /* Only one top-level choice. */
        scan = OPERAND(scan);

        /* Starting-point info. */
        if (OP(scan) == EXACTLY)
            r->regstart = *OPERAND(scan);
        else if (OP(scan) == BOL)
            r->reganch++;

        /*
         * If there's something expensive in the r.e., find the