Merge branch 'pw/xdiff-classify-record-in-histogram'

"diff --histogram" optimization.

* pw/xdiff-classify-record-in-histogram:
  xdiff: drop unused flags parameter from recs_match
  xdiff: drop xpparam_t parameter from histogram cmp_recs()
  xdiff: drop CMP_ENV macro from xhistogram
  xdiff: simplify comparison
  xdiff: avoid unnecessary memory allocations
  diff histogram: intern strings

xdiff/xdiffi.c

@@ -390,12 +390,9 @@ static xdchange_t *xdl_add_change(xdchange_t *xscr, long i1, long i2, long chg1,
 }
 
 
-static int recs_match(xrecord_t *rec1, xrecord_t *rec2, long flags)
+static int recs_match(xrecord_t *rec1, xrecord_t *rec2)
 {
-	return (rec1->ha == rec2->ha &&
-		xdl_recmatch(rec1->ptr, rec1->size,
-			     rec2->ptr, rec2->size,
-			     flags));
+	return (rec1->ha == rec2->ha);
 }
 
 /*
@@ -759,10 +756,10 @@ static inline int group_previous(xdfile_t *xdf, struct xdlgroup *g)
  * following group, expand this group to include it. Return 0 on success or -1
  * if g cannot be slid down.
  */
-static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g, long flags)
+static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g)
 {
 	if (g->end < xdf->nrec &&
-	    recs_match(xdf->recs[g->start], xdf->recs[g->end], flags)) {
+	    recs_match(xdf->recs[g->start], xdf->recs[g->end])) {
 		xdf->rchg[g->start++] = 0;
 		xdf->rchg[g->end++] = 1;
 
@@ -780,10 +777,10 @@ static int group_slide_down(xdfile_t *xdf, struct xdlgroup *g, long flags)
  * into a previous group, expand this group to include it. Return 0 on success
  * or -1 if g cannot be slid up.
  */
-static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g, long flags)
+static int group_slide_up(xdfile_t *xdf, struct xdlgroup *g)
 {
 	if (g->start > 0 &&
-	    recs_match(xdf->recs[g->start - 1], xdf->recs[g->end - 1], flags)) {
+	    recs_match(xdf->recs[g->start - 1], xdf->recs[g->end - 1])) {
 		xdf->rchg[--g->start] = 1;
 		xdf->rchg[--g->end] = 0;
 
@@ -833,7 +830,7 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 			end_matching_other = -1;
 
 			/* Shift the group backward as much as possible: */
-			while (!group_slide_up(xdf, &g, flags))
+			while (!group_slide_up(xdf, &g))
 				if (group_previous(xdfo, &go))
 					BUG("group sync broken sliding up");
 
@@ -848,7 +845,7 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 
 			/* Now shift the group forward as far as possible: */
 			while (1) {
-				if (group_slide_down(xdf, &g, flags))
+				if (group_slide_down(xdf, &g))
 					break;
 				if (group_next(xdfo, &go))
 					BUG("group sync broken sliding down");
@@ -875,7 +872,7 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 			 * other file that it can align with.
 			 */
 			while (go.end == go.start) {
-				if (group_slide_up(xdf, &g, flags))
+				if (group_slide_up(xdf, &g))
 					BUG("match disappeared");
 				if (group_previous(xdfo, &go))
 					BUG("group sync broken sliding to match");
@@ -918,7 +915,7 @@ int xdl_change_compact(xdfile_t *xdf, xdfile_t *xdfo, long flags) {
 			}
 
 			while (g.end > best_shift) {
-				if (group_slide_up(xdf, &g, flags))
+				if (group_slide_up(xdf, &g))
 					BUG("best shift unreached");
 				if (group_previous(xdfo, &go))
 					BUG("group sync broken sliding to blank line");

xdiff/xhistogram.c

@@ -88,19 +88,14 @@ struct region {
 #define REC(env, s, l) \
 	(env->xdf##s.recs[l - 1])
 
-static int cmp_recs(xpparam_t const *xpp,
-	xrecord_t *r1, xrecord_t *r2)
+static int cmp_recs(xrecord_t *r1, xrecord_t *r2)
 {
-	return r1->ha == r2->ha &&
-		xdl_recmatch(r1->ptr, r1->size, r2->ptr, r2->size,
-			    xpp->flags);
-}
+	return r1->ha == r2->ha;
 
-#define CMP_ENV(xpp, env, s1, l1, s2, l2) \
-	(cmp_recs(xpp, REC(env, s1, l1), REC(env, s2, l2)))
+}
 
 #define CMP(i, s1, l1, s2, l2) \
-	(cmp_recs(i->xpp, REC(i->env, s1, l1), REC(i->env, s2, l2)))
+	(cmp_recs(REC(i->env, s1, l1), REC(i->env, s2, l2)))
 
 #define TABLE_HASH(index, side, line) \
 	XDL_HASHLONG((REC(index->env, side, line))->ha, index->table_bits)

xdiff/xprepare.c

@@ -181,15 +181,11 @@ 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 (XDF_DIFF_ALG(xpp->flags) == XDF_HISTOGRAM_DIFF)
-		hbits = hsize = 0;
-	else {
-		hbits = xdl_hashbits((unsigned int) narec);
-		hsize = 1 << hbits;
-		if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *))))
-			goto abort;
-		memset(rhash, 0, hsize * sizeof(xrecord_t *));
-	}
+	hbits = xdl_hashbits((unsigned int) narec);
+	hsize = 1 << hbits;
+	if (!(rhash = (xrecord_t **) xdl_malloc(hsize * sizeof(xrecord_t *))))
+		goto abort;
+	memset(rhash, 0, hsize * sizeof(xrecord_t *));
 
 	nrec = 0;
 	if ((cur = blk = xdl_mmfile_first(mf, &bsize)) != NULL) {
@@ -208,9 +204,7 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 			crec->size = (long) (cur - prev);
 			crec->ha = hav;
 			recs[nrec++] = crec;
-
-			if ((XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF) &&
-			    xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
+			if (xdl_classify_record(pass, cf, rhash, hbits, crec) < 0)
 				goto abort;
 		}
 	}
@@ -219,10 +213,13 @@ static int xdl_prepare_ctx(unsigned int pass, mmfile_t *mf, long narec, xpparam_
 		goto abort;
 	memset(rchg, 0, (nrec + 2) * sizeof(char));
 
-	if (!(rindex = (long *) xdl_malloc((nrec + 1) * sizeof(long))))
-		goto abort;
-	if (!(ha = (unsigned long *) xdl_malloc((nrec + 1) * sizeof(unsigned long))))
-		goto abort;
+	if ((XDF_DIFF_ALG(xpp->flags) != XDF_PATIENCE_DIFF) &&
+	    (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)) {
+		if (!(rindex = xdl_malloc((nrec + 1) * sizeof(*rindex))))
+			goto abort;
+		if (!(ha = xdl_malloc((nrec + 1) * sizeof(*ha))))
+			goto abort;
+	}
 
 	xdf->nrec = nrec;
 	xdf->recs = recs;
@@ -279,8 +276,7 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	enl1 = xdl_guess_lines(mf1, sample) + 1;
 	enl2 = xdl_guess_lines(mf2, sample) + 1;
 
-	if (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF &&
-	    xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0)
+	if (xdl_init_classifier(&cf, enl1 + enl2 + 1, xpp->flags) < 0)
 		return -1;
 
 	if (xdl_prepare_ctx(1, mf1, enl1, xpp, &cf, &xe->xdf1) < 0) {
@@ -305,8 +301,7 @@ int xdl_prepare_env(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 		return -1;
 	}
 
-	if (XDF_DIFF_ALG(xpp->flags) != XDF_HISTOGRAM_DIFF)
-		xdl_free_classifier(&cf);
+	xdl_free_classifier(&cf);
 
 	return 0;
 }