path: root/regex/engine.c

/*
 * The matching engine and friends.  This file is #included by regexec.c
 * after suitable #defines of a variety of macros used herein, so that
 * different state representations can be used without duplicating masses
 * of code.
 */

#ifdef SNAMES
#define	matcher	smatcher
#define	fast	sfast
#define	slow	sslow
#define	dissect	sdissect
#define	backref	sbackref
#define	step	sstep
#define	print	sprint
#define	at	sat
#define	match	smat
#endif
#ifdef LNAMES
#define	matcher	lmatcher
#define	fast	lfast
#define	slow	lslow
#define	dissect	ldissect
#define	backref	lbackref
#define	step	lstep
#define	print	lprint
#define	at	lat
#define	match	lmat
#endif

/* another structure passed up and down to avoid zillions of parameters */
struct match {
	struct re_guts *g;
	int eflags;
	regmatch_t *pmatch;	/* [nsub+1] (0 element unused) */
	char *offp;		/* offsets work from here */
	char *beginp;		/* start of string -- virtual NUL precedes */
	char *endp;		/* end of string -- virtual NUL here */
	char *coldp;		/* can be no match starting before here */
	char **lastpos;		/* [nplus+1] */
	STATEVARS;
	states st;		/* current states */
	states fresh;		/* states for a fresh start */
	states tmp;		/* temporary */
	states empty;		/* empty set of states */
};

#include "engine.ih"

#ifdef REDEBUG
#define	SP(t, s, c)	print(m, t, s, c, stdout)
#define	AT(t, p1, p2, s1, s2)	at(m, t, p1, p2, s1, s2)
#define	NOTE(str)	{ if (m->eflags&REG_TRACE) printf("=%s\n", (str)); }
#else
#define	SP(t, s, c)	/* nothing */
#define	AT(t, p1, p2, s1, s2)	/* nothing */
#define	NOTE(s)	/* nothing */
#endif

/*
 - matcher - the actual matching engine
 == static int matcher(register struct re_guts *g, char *string, \
 ==	size_t nmatch, regmatch_t pmatch[], int eflags);
 */
static int			/* 0 success, REG_NOMATCH failure */
matcher(g, string, nmatch, pmatch, eflags)
register struct re_guts *g;
char *string;
size_t nmatch;
regmatch_t pmatch[];
int eflags;
{
	register char *endp;
	register int i;
	struct match mv;
	register struct match *m = &mv;
	register char *dp;
	const register sopno gf = g->firststate+1;	/* +1 for OEND */
	const register sopno gl = g->laststate;
	char *start;
	char *stop;

	/* simplify the situation where possible */
	if (g->cflags&REG_NOSUB)
		nmatch = 0;
	if (eflags&REG_STARTEND) {
		start = string + pmatch[0].rm_so;
		stop = string + pmatch[0].rm_eo;
	} else {
		start = string;
		stop = start + strlen(start);
	}
	if (stop < start)
		return(REG_INVARG);

	/* prescreening; this does wonders for this rather slow code */
	if (g->must != NULL) {
		for (dp = start; dp < stop; dp++)
			if (*dp == g->must[0] && stop - dp >= g->mlen &&
				memcmp(dp, g->must, (size_t)g->mlen) == 0)
				break;
		if (dp == stop)		/* we didn't find g->must */
			return(REG_NOMATCH);
	}

	/* match struct setup */
	m->g = g;
	m->eflags = eflags;
	m->pmatch = NULL;
	m->lastpos = NULL;
	m->offp = string;
	m->beginp = start;
	m->endp = stop;
	STATESETUP(m, 4);
	SETUP(m->st);
	SETUP(m->fresh);
	SETUP(m->tmp);
	SETUP(m->empty);
	CLEAR(m->empty);

	/* this loop does only one repetition except for backrefs */
	for (;;) {
		endp = fast(m, start, stop, gf, gl);
		if (endp == NULL) {		/* a miss */
			STATETEARDOWN(m);
			return(REG_NOMATCH);
		}
		if (nmatch == 0 && !g->backrefs)
			break;		/* no further info needed */

		/* where? */
		assert(m->coldp != NULL);
		for (;;) {
			NOTE("finding start");
			endp = slow(m, m->coldp, stop, gf, gl);
			if (endp != NULL)
				break;
			assert(m->coldp < m->endp);
			m->coldp++;
		}
		if (nmatch == 1 && !g->backrefs)
			break;		/* no further info needed */

		/* oh my, he wants the subexpressions... */
		if (m->pmatch == NULL)
			m->pmatch = (regmatch_t *)malloc((m->g->nsub + 1) *
							sizeof(regmatch_t));
		if (m->pmatch == NULL)