regexp.c

C++的一个好库。。。现在很流行

 *
 * 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( char *prog )
{
	register char *scan;	/* Current node. */
	char *next;		/* Next node. */

	scan = prog;
#ifdef DEBUG
	if (scan != NULL && regnarrate)
		fprintf(stderr, "%s(\n", regprop(scan));
#endif
	while (scan != NULL) {
#ifdef DEBUG
		if (regnarrate)
			fprintf(stderr, "%s...\n", regprop(scan));
#endif
		next = regnext(scan);

		switch (OP(scan)) {
		case BOL:
			if (reginput != regbol)
				return(0);
			break;
		case EOL:
			if (*reginput != '\0')
				return(0);
			break;
		case WORDA:
			/* Must be looking at a letter, digit, or _ */
			if ((!isalnum(*reginput)) && *reginput != '_')
				return(0);
			/* Prev must be BOL or nonword */
			if (reginput > regbol &&
			    (isalnum(reginput[-1]) || reginput[-1] == '_'))
				return(0);
			break;
		case WORDZ:
			/* Must be looking at non letter, digit, or _ */
			if (isalnum(*reginput) || *reginput == '_')
				return(0);
			/* We don't care what the previous char was */
			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( 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( 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);
}

#ifdef DEBUG

STATIC char *regprop();

/*
 - regdump - dump a regexp onto stdout in vaguely comprehensible form
 */
void
regdump( regexp *r )
{
	register char *s;
	register char op = EXACTLY;	/* Arbitrary non-END op. */
	register char *next;


	s = r->program + 1;
	while (op != END) {	/* While that wasn't END last time... */
		op = OP(s);
		printf("%2d%s", s-r->program, regprop(s));	/* Where, what. */
		next = regnext(s);
		if (next == NULL)		/* Next ptr. */
			printf("(0)");
		else 
			printf("(%d)", (s-r->program)+(next-s));
		s += 3;
		if (op == ANYOF || op == ANYBUT || op == EXACTLY) {
			/* Literal string, where present. */
			while (*s != '\0') {
				putchar(*s);
				s++;
			}
			s++;
		}
		putchar('\n');
	}

	/* Header fields of interest. */
	if (r->regstart != '\0')
		printf("start `%c' ", r->regstart);
	if (r->reganch)
		printf("anchored ");
	if (r->regmust != NULL)
		printf("must have \"%s\"", r->regmust);
	printf("\n");
}

/*
 - regprop - printable representation of opcode
 */
static char *
regprop( char *op )
{
	register char *p;
	static char buf[50];

	(void) strcpy(buf, ":");

	switch (OP(op)) {
	case BOL:
		p = "BOL";
		break;
	case EOL:
		p = "EOL";
		break;
	case ANY:
		p = "ANY";
		break;
	case ANYOF:
		p = "ANYOF";
		break;
	case ANYBUT:
		p = "ANYBUT";
		break;
	case BRANCH:
		p = "BRANCH";
		break;
	case EXACTLY:
		p = "EXACTLY";
		break;
	case NOTHING:
		p = "NOTHING";
		break;
	case BACK:
		p = "BACK";
		break;
	case END:
		p = "END";
		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:
		sprintf(buf+strlen(buf), "OPEN%d", OP(op)-OPEN);
		p = NULL;
		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:
		sprintf(buf+strlen(buf), "CLOSE%d", OP(op)-CLOSE);
		p = NULL;
		break;
	case STAR:
		p = "STAR";
		break;
	case PLUS:
		p = "PLUS";
		break;
	case WORDA:
		p = "WORDA";
		break;
	case WORDZ:
		p = "WORDZ";
		break;
	default:
		regerror("corrupted opcode");
		break;
	}
	if (p != NULL)
		(void) strcat(buf, p);
	return(buf);
}
#endif

/*
 * The following is provided for those people who do not have strcspn() in
 * their C libraries.  They should get off their butts and do something
 * about it; at least one public-domain implementation of those (highly
 * useful) string routines has been published on Usenet.
 */
#ifdef STRCSPN
/*
 * strcspn - find length of initial segment of s1 consisting entirely
 * of characters not from s2
 */

static int
strcspn(
	char *s1,
	char *s2 )
{
	register char *scan1;
	register char *scan2;
	register int count;

	count = 0;
	for (scan1 = s1; *scan1 != '\0'; scan1++) {
		for (scan2 = s2; *scan2 != '\0';)	/* ++ moved down. */
			if (*scan1 == *scan2++)
				return(count);
		count++;
	}
	return(count);
}
#endif