Function regatom

v2/engine/regexp.c:479–651

- regatom - the lowest level * * Optimization: gobbles an entire sequence of ordinary characters so that * it can turn them into a single node, which is smaller to store and * faster to run. Backslashed characters are exceptions, each becoming a * separate node; the code is simpler that way and it's not worth fixing. */

 * separate node; the code is simpler that way and it's not worth fixing.
 */
static char *
regatom( int *flagp )
{
    register char *ret;
    int flags;

    *flagp = WORST;     /* Tentatively. */

    switch (*regparse++) {
    /* FIXME: these chars only have meaning at beg/end of pat? */
    case '^':
        ret = regnode(BOL);
        break;
    case '$':
        ret = regnode(EOL);
        break;
    case '.':
        ret = regnode(ANY);
        *flagp |= HASWIDTH|SIMPLE;
        break;
    case '[': {
            register int classr;
            register int classend;

            if (*regparse == '^') { /* Complement of range. */
                ret = regnode(ANYBUT);
                regparse++;
            } else
                ret = regnode(ANYOF);
            if (*regparse == ']' || *regparse == '-')
                regc(*regparse++);
            while (*regparse != '\0' && *regparse != ']') {
                if (*regparse == '-') {
                    regparse++;
                    if (*regparse == ']' || *regparse == '\0')
                        regc('-');
                    else {
                        classr = UCHARAT(regparse-2)+1;
                        classend = UCHARAT(regparse);
                        if (classr > classend+1)
                            FAIL("invalid [] range");
                        for (; classr <= classend; classr++)
                            regc(classr);
                        regparse++;
                    }
                } else
                    regc(*regparse++);
            }
            regc('\0');
            if (*regparse != ']')
                FAIL("unmatched []");
            regparse++;
            *flagp |= HASWIDTH|SIMPLE;
        }
        break;
    case '(':
        ret = reg(1, &flags);
        if (ret == NULL)