*flagp |= flags&(HASWIDTH|SPSTART);
		break;
	case '\0':
	case '|':
	case ')':
		FAIL("internal urp");	/* Supposed to be caught earlier. */
		break;
	case '?':
	case '+':
	case '*':
		FAIL("?+* follows nothing");
		break;
	case '\\':
		if (*regparse == '\0')
			FAIL("trailing \\");
		ret = regnode(EXACTLY);
		regc(*regparse++);
		regc('\0');
		*flagp |= HASWIDTH|SIMPLE;
		break;
	default: {
			register int len;
			register char ender;

			regparse--;
			len = strcspn(regparse, META);
			if (len <= 0)
				FAIL("internal disaster");
			ender = *(regparse+len);
			if (len > 1 && ISMULT(ender))
				len--;		/* Back off clear of ?+* operand. */
			*flagp |= HASWIDTH;
			if (len == 1)
				*flagp |= SIMPLE;
			ret = regnode(EXACTLY);
			while (len > 0) {
				regc(*regparse++);
				len--;
			}
			regc('\0');
		}
		break;
	}

	return(ret);
}

/*
 - regnode - emit a node
 */
static char *			/* Location. */
regnode(op)
char op;
{
	register char *ret;
	register char *ptr;

	ret = regcode;
	if (ret == &regdummy) {
		regsize += 3;
		return(ret);
	}

	ptr = ret;
	*ptr++ = op;
	*ptr++ = '\0';		/* Null "next" pointer. */
	*ptr++ = '\0';
	regcode = ptr;

	return(ret);
}

/*
 - regc - emit (if appropriate) a byte of code
 */
static void
regc(b)
char b;
{
	if (regcode != &regdummy)
		*regcode++ = b;
	else
		regsize++;
}

/*
 - reginsert - insert an operator in front of already-emitted operand
 *
 * Means relocating the operand.
 */
static void
reginsert(op, opnd)
char op;
char *opnd;
{
	register char *src;
	register char *dst;
	register char *place;

	if (regcode == &regdummy) {
		regsize += 3;
		return;
	}

	src = regcode;
	regcode += 3;
	dst = regcode;
	while (src > opnd)
		*--dst = *--src;

	place = opnd;		/* Op node, where operand used to be. */
	*place++ = op;
	*place++ = '\0';
	*place++ = '\0';
}

/*
 - regtail - set the next-pointer at the end of a node chain
 */
static void
regtail(p, val)
char *p;
char *val;
{
	register char *scan;
	register char *temp;
	register int offset;

	if (p == &regdummy)
		return;

	/* Find last node. */
	scan = p;
	for (;;) {
		temp = regnext(scan);
		if (temp == NULL)
			break;
		scan = temp;
	}

	if (OP(scan) == BACK)
		offset = scan - val;
	else
		offset = val - scan;
	*(scan+1) = (offset>>8)&0377;
	*(scan+2) = offset&0377;
}

/*
 - regoptail - regtail on operand of first argument; nop if operandless
 */
static void
regoptail(p, val)
char *p;
char *val;
{
	/* "Operandless" and "op != BRANCH" are synonymous in practice. */
	if (p == NULL || p == &regdummy || OP(p) != BRANCH)
		return;
	regtail(OPERAND(p), val);
}

/*
 * regexec and friends
 */

/*
 * Global work variables for regexec().
 */
static char *reginput;		/* String-input pointer. */
static char *regbol;		/* Beginning of input, for ^ check. */
static char **regstartp;	/* Pointer to startp array. */
static char **regendp;		/* Ditto for endp. */

/*
 * Forwards.
 */
#ifdef PROTOTYPES
static int regtry(regexp *, char *);
static int regmatch(char *);
static int regrepeat(char *);
#else
static int regtry();
static int regmatch();
static int regrepeat();
#endif

/*
 - regexec - match a regexp against a string
 */
int
regexec(prog, string)
register regexp *prog;
register char *string;
{
	register char *s;
	extern char *strchr();

	/* Be paranoid... */
	if (prog == NULL || string == NULL) {
		regerror("NULL parameter");
		return(0);
	}

	/* Check validity of program. */
	if (UCHARAT(prog->program) != MAGIC) {
		regerror("corrupted program");
		return(0);
	}

	/* If there is a "must appear" string, look for it. */
	if (prog->regmust != NULL) {
		s = string;
		while ((s = strchr(s, prog->regmust[0])) != NULL) {
			if (strncmp(s, prog->regmust, prog->regmlen) == 0)
				break;	/* Found it. */
			s++;
		}
		if (s == NULL)	/* Not present. */
			return(0);
	}

	/* Mark beginning of line for ^ . */
	regbol = string;

	/* Simplest case:  anchored match need be tried only once. */
	if (prog->reganch)
		return(regtry(prog, string));

	/* Messy cases:	 unanchored match. */
	s = string;
	if (prog->regstart != '\0')
		/* We know what char it must start with. */
		while ((s = strchr(s, prog->regstart)) != NULL) {
			if (regtry(prog, s))
				return(1);
			s++;
		}
	else
		/* We don't -- general case. */
		do {
			if (regtry(prog, s))
				return(1);
		} while (*s++ != '\0');

	/* Failure. */
	return(0);
}

/*
 - regtry - try match at specific point
 */
static int			/* 0 failure, 1 success */
regtry(prog, string)
regexp *prog;
char *string;
{
	register int i;
	register char **sp;
	register char **ep;

	reginput = string;
	regstartp = prog->startp;
	regendp = prog->endp;

	sp = prog->startp;
	ep = prog->endp;
	for (i = NSUBEXP; i > 0; i--) {
		*sp++ = NULL;
		*ep++ = NULL;
	}
	if (regmatch(prog->program + 1)) {
		prog->startp[0] = string;
		prog->endp[0] = reginput;
		return(1);
	} else
		return(0);
}

/*
 - regmatch - main matching routine
 *
 * Conceptually the strategy is simple:	 check to see whether the current
 * node matches, call self recursively to see whether the rest matches,
 * and then act accordingly.  In practice we make some effort to avoid
 * recursion, in particular by going through "ordinary" nodes (that don't
 * need to know whether the rest of the match failed) by a loop instead of
 * by recursion.
 */
static int			/* 0 failure, 1 success */
regmatch(prog)
char *prog;
{
	register char *scan;	/* Current node. */
	char *next;		/* Next node. */
	extern char *strchr();

	scan = prog;
	while (scan != NULL) {
		next = regnext(scan);

		switch (OP(scan)) {
		case BOL:
			if (reginput != regbol)
				return(0);
			break;
		case EOL:
			if (*reginput != '\0')
				return(0);
			break;
		case ANY:
			if (*reginput == '\0')
				return(0);
			reginput++;
			break;
		case EXACTLY: {
				register int len;
				register char *opnd;

				opnd = OPERAND(scan);
				/* Inline the first character, for speed. */
				if (*opnd != *reginput)
					return(0);
				len = strlen(opnd);
				if (len > 1 && strncmp(opnd, reginput, len) != 0)
					return(0);
				reginput += len;
			}
			break;
		case ANYOF:
			if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) == NULL)
				return(0);
			reginput++;
			break;
		case ANYBUT:
			if (*reginput == '\0' || strchr(OPERAND(scan), *reginput) != NULL)
				return(0);
			reginput++;
			break;
		case NOTHING:
			break;
		case BACK:
			break;
		case OPEN+1:
		case OPEN+2:
		case OPEN+3:
		case OPEN+4:
		case OPEN+5:
		case OPEN+6:
		case OPEN+7:
		case OPEN+8:
		case OPEN+9: {
				register int no;
				register char *save;

				no = OP(scan) - OPEN;
				save = reginput;

				if (regmatch(next)) {
					/*
					 * Don't set startp if some later
					 * invocation of the same parentheses
					 * already has.
					 */
					if (regstartp[no] == NULL)
						regstartp[no] = save;
					return(1);
				} else
					return(0);
			}
			break;
		case CLOSE+1:
		case CLOSE+2:
		case CLOSE+3:
		case CLOSE+4:
		case CLOSE+5:
		case CLOSE+6:
		case CLOSE+7:
		case CLOSE+8:
		case CLOSE+9: {
				register int no;
				register char *save;

				no = OP(scan) - CLOSE;
				save = reginput;

				if (regmatch(next)) {
					/*
					 * Don't set endp if some later
					 * invocation of the same parentheses
					 * already has.
					 */
					if (regendp[no] == NULL)
						regendp[no] = save;
					return(1);
				} else
					return(0);
			}
			break;
		case BRANCH: {
				register char *save;

				if (OP(next) != BRANCH)		/* No choice. */
					next = OPERAND(scan);	/* Avoid recursion. */
				else {
					do {
						save = reginput;
						if (regmatch(OPERAND(scan)))
							return(1);
						reginput = save;
						scan = regnext(scan);
					} while (scan != NULL && OP(scan) == BRANCH);
					return(0);
					/* NOTREACHED */
				}
			}
			break;
		case STAR:
		case PLUS: {
				register char nextch;
				register int no;
				register char *save;
				register int min;

				/*
				 * Lookahead to avoid useless match attempts
				 * when we know what character comes next.
				 */
				nextch = '\0';
				if (OP(next) == EXACTLY)
					nextch = *OPERAND(next);
				min = (OP(scan) == STAR) ? 0 : 1;
				save = reginput;
				no = regrepeat(OPERAND(scan));
				while (no >= min) {
					/* If it could work, try it. */
					if (nextch == '\0' || *reginput == nextch)
						if (regmatch(next))
							return(1);
					/* Couldn't or didn't -- back up. */
					no--;
					reginput = save + no;
				}
				return(0);
			}
			break;
		case END:
			return(1);	/* Success! */
			break;
		default:
			regerror("memory corruption");
			return(0);
			break;
		}

		scan = next;
	}

	/*
	 * We get here only if there's trouble -- normally "case END" is
	 * the terminating point.
	 */
	regerror("corrupted pointers");
	return(0);
}

/*
 - regrepeat - repeatedly match something simple, report how many
 */
static int
regrepeat(p)
char *p;
{
	register int count = 0;
	register char *scan;
	register char *opnd;

	scan = reginput;
	opnd = OPERAND(p);
	switch (OP(p)) {
	case ANY:
		count = strlen(scan);
		scan += count;
		break;
	case EXACTLY:
		while (*opnd == *scan) {
			count++;
			scan++;
		}
		break;
	case ANYOF:
		while (*scan != '\0' && strchr(opnd, *scan) != NULL) {
			count++;
			scan++;
		}
		break;
	case ANYBUT:
		while (*scan != '\0' && strchr(opnd, *scan) == NULL) {
			count++;
			scan++;
		}
		break;
	default:		/* Oh dear.  Called inappropriately. */
		regerror("internal foulup");
		count = 0;	/* Best compromise. */
		break;
	}
	reginput = scan;

	return(count);
}

/*
 - regnext - dig the "next" pointer out of a node
 */
static char *
regnext(p)
register char *p;
{
	register int offset;

	if (p == &regdummy)
		return(NULL);

	offset = NEXT(p);
	if (offset == 0)
		return(NULL);

	if (OP(p) == BACK)
		return(p-offset);
	else
		return(p+offset);
}

@1.1log@Initial revision@text@d27 1a27 1/* $Id$ */@