1 files changed, 17 insertions, 14 deletions

diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
index 5a33d1a869..63a22c630e 100644
--- a/xdiff/xprepare.c
+++ b/xdiff/xprepare.c
@@ -181,7 +181,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 	if (!(recs = (xrecord_t **) xdl_malloc(narec * sizeof(xrecord_t *))))
 		goto abort;
 
-	if (xpp->flags & XDF_HISTOGRAM_DIFF)
+	if (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF)
 		hbits = hsize = 0;
 	else {
 		hbits = xdl_hashbits((unsigned int) narec);
@@ -209,8 +209,8 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 			crec->ha = hav;
 			recs[nrec++] = crec;
 
-			if (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
-				xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
+			if ((XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) &&
+			    xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
 				goto abort;
 		}
 	}
@@ -273,16 +273,15 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	 * (nrecs) will be updated correctly anyway by
 	 * xdl_prepare_ctx().
 	 */
-	sample = xpp->flags & XDF_HISTOGRAM_DIFF ? XDL_GUESS_NLINES2 : XDL_GUESS_NLINES1;
+	sample = (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF
+		  ? XDL_GUESS_NLINES2 : XDL_GUESS_NLINES1);
 
 	enl1 = xdl_guess_lines(mf1, sample) + 1;
 	enl2 = xdl_guess_lines(mf2, sample) + 1;
 
-	if (!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
-		xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0) {
-
+	if (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF &&
+	    xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0)
 		return -1;
-	}
 
 	if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
 
@@ -296,9 +295,9 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		return -1;
 	}
 
-	if (!(xpp->flags & XDF_PATIENCE_DIFF) &&
-			!(xpp->flags & XDF_HISTOGRAM_DIFF) &&
-			xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) {
+	if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) &&
+	    (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) &&
+	    xdl_optimize_ctxs(&cf, &xe->xdf1, &xe->xdf2) < 0) {
 
 		xdl_free_ctx(&xe->xdf2);
 		xdl_free_ctx(&xe->xdf1);
@@ -383,7 +382,7 @@ static int xdl_clean_mmatch(char const *dis, long i, long s, long e) {
  * might be potentially discarded if they happear in a run of discardable.
  */
 static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
-	long i, nm, nreff;
+	long i, nm, nreff, mlim;
 	xrecord_t **recs;
 	xdlclass_t *rcrec;
 	char *dis, *dis1, *dis2;
@@ -396,16 +395,20 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
 	dis1 = dis;
 	dis2 = dis1 + xdf1->nrec + 1;
 
+	if ((mlim = xdl_bogosqrt(xdf1->nrec)) > XDL_MAX_EQLIMIT)
+		mlim = XDL_MAX_EQLIMIT;
 	for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart]; i <= xdf1->dend; i++, recs++) {
 		rcrec = cf->rcrecs[(*recs)->ha];
 		nm = rcrec ? rcrec->len2 : 0;
-		dis1[i] = (nm == 0) ? 0: 1;
+		dis1[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
 	}
 
+	if ((mlim = xdl_bogosqrt(xdf2->nrec)) > XDL_MAX_EQLIMIT)
+		mlim = XDL_MAX_EQLIMIT;
 	for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart]; i <= xdf2->dend; i++, recs++) {
 		rcrec = cf->rcrecs[(*recs)->ha];
 		nm = rcrec ? rcrec->len1 : 0;
-		dis2[i] = (nm == 0) ? 0: 1;
+		dis2[i] = (nm == 0) ? 0: (nm >= mlim) ? 2: 1;
 	}
 
 	for (nreff = 0, i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];