Merge branch 'en/xdiff-cleanup-3' into pw/xdiff-shrink-memory-consumption

* en/xdiff-cleanup-3:
  xdiff/xdl_cleanup_records: simplify INVESTIGATE handling for clarity
  xdiff/xdl_cleanup_records: make setting action easier to follow
  xdiff/xdl_cleanup_records: make limits more clear
  xdiff/xdl_cleanup_records: use unambiguous types
  xdiff: use unambiguous types in xdl_bogo_sqrt()
  xdiff/xdl_cleanup_records: delete local recs pointer

Author: gitster

xdiff/xdiffi.c

@@ -348,7 +348,7 @@ int xdl_do_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp,
 	kvdf += xe->xdf2.nreff + 1;
 	kvdb += xe->xdf2.nreff + 1;
 
-	xenv.mxcost = xdl_bogosqrt(ndiags);
+	xenv.mxcost = (long)xdl_bogosqrt((uint64_t)ndiags);
 	if (xenv.mxcost < XDL_MAX_COST_MIN)
 		xenv.mxcost = XDL_MAX_COST_MIN;
 	xenv.snake_cnt = XDL_SNAKE_CNT;

xdiff/xprepare.c

@@ -197,8 +197,8 @@ void xdl_free_env(xdfenv_t *xe) {
 }
 
 
-static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) {
-	long r, rdis0, rpdis0, rdis1, rpdis1;
+static bool xdl_clean_mmatch(uint8_t const *action, ptrdiff_t i, ptrdiff_t s, ptrdiff_t e) {
+	ptrdiff_t r, rdis0, rpdis0, rdis1, rpdis1;
 
 	/*
 	 * Limits the window that is examined during the similar-lines
@@ -268,8 +268,7 @@ static bool xdl_clean_mmatch(uint8_t const *action, long i, long s, long e) {
  * might be potentially discarded if they appear in a run of discardable.
  */
 static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xdf2) {
-	long i, nm, mlim;
-	xrecord_t *recs;
+	ptrdiff_t i, nm, mlim1, mlim2;
 	xdlclass_t *rcrec;
 	uint8_t *action1 = NULL, *action2 = NULL;
 	bool need_min = !!(cf->flags & XDF_NEED_MINIMAL);
@@ -288,51 +287,80 @@ static int xdl_cleanup_records(xdlclassifier_t *cf, xdfile_t *xdf1, xdfile_t *xd
 		goto cleanup;
 	}
 
+	if (need_min) {
+		/* i.e. infinity */
+		mlim1 = PTRDIFF_MAX;
+		mlim2 = PTRDIFF_MAX;
+	} else {
+		mlim1 = XDL_MIN(xdl_bogosqrt(xdf1->nrec), XDL_MAX_EQLIMIT);
+		mlim2 = XDL_MIN(xdl_bogosqrt(xdf2->nrec), XDL_MAX_EQLIMIT);
+	}
+
 	/*
 	 * Initialize temporary arrays with DISCARD, KEEP, or INVESTIGATE.
 	 */
-	if ((mlim = xdl_bogosqrt((long)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->minimal_perfect_hash];
+	for (i = xdf1->dstart; i <= xdf1->dend; i++) {
+		size_t mph1 = xdf1->recs[i].minimal_perfect_hash;
+		rcrec = cf->rcrecs[mph1];
 		nm = rcrec ? rcrec->len2 : 0;
-		action1[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
+		if (nm == 0)
+			action1[i] = DISCARD;
+		else if (nm < mlim1)
+			action1[i] = KEEP;
+		else /* nm >= mlim1 */
+			action1[i] = INVESTIGATE;
 	}
 
-	if ((mlim = xdl_bogosqrt((long)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->minimal_perfect_hash];
+	for (i = xdf2->dstart; i <= xdf2->dend; i++) {
+		size_t mph2 = xdf2->recs[i].minimal_perfect_hash;
+		rcrec = cf->rcrecs[mph2];
 		nm = rcrec ? rcrec->len1 : 0;
-		action2[i] = (nm == 0) ? DISCARD: (nm >= mlim && !need_min) ? INVESTIGATE: KEEP;
+		if (nm == 0)
+			action2[i] = DISCARD;
+		else if (nm < mlim2)
+			action2[i] = KEEP;
+		else /* nm >= mlim2 */
+			action2[i] = INVESTIGATE;
 	}
 
 	/*
 	 * Use temporary arrays to decide if changed[i] should remain
 	 * false, or become true.
 	 */
 	xdf1->nreff = 0;
-	for (i = xdf1->dstart, recs = &xdf1->recs[xdf1->dstart];
-	     i <= xdf1->dend; i++, recs++) {
-		if (action1[i] == KEEP ||
-		    (action1[i] == INVESTIGATE && !xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend))) {
+	for (i = xdf1->dstart; i <= xdf1->dend; i++) {
+		if (action1[i] == INVESTIGATE) {
+			if (!xdl_clean_mmatch(action1, i, xdf1->dstart, xdf1->dend))
+				action1[i] = KEEP;
+			else
+				action1[i] = DISCARD;
+		}
+
+		if (action1[i] == KEEP) {
 			xdf1->reference_index[xdf1->nreff++] = i;
-			/* changed[i] remains false, i.e. keep */
-		} else
+			/* changed[i] remains false */
+		} else if (action1[i] == DISCARD)
 			xdf1->changed[i] = true;
-			/* i.e. discard */
+		else
+			BUG("Illegal state for action1[i]");
 	}
 
 	xdf2->nreff = 0;
-	for (i = xdf2->dstart, recs = &xdf2->recs[xdf2->dstart];
-	     i <= xdf2->dend; i++, recs++) {
-		if (action2[i] == KEEP ||
-		    (action2[i] == INVESTIGATE && !xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend))) {
+	for (i = xdf2->dstart; i <= xdf2->dend; i++) {
+		if (action2[i] == INVESTIGATE) {
+			if (!xdl_clean_mmatch(action2, i, xdf2->dstart, xdf2->dend))
+				action2[i] = KEEP;
+			else
+				action2[i] = DISCARD;
+		}
+
+		if (action2[i] == KEEP) {
 			xdf2->reference_index[xdf2->nreff++] = i;
-			/* changed[i] remains false, i.e. keep */
-		} else
+			/* changed[i] remains false */
+		} else if (action2[i] == DISCARD)
 			xdf2->changed[i] = true;
-			/* i.e. discard */
+		else
+			BUG("Illegal state for action2[i]");
 	}
 
 cleanup:

xdiff/xutils.c

@@ -23,8 +23,8 @@
 #include "xinclude.h"
 
 
-long xdl_bogosqrt(long n) {
-	long i;
+uint64_t xdl_bogosqrt(uint64_t n) {
+	uint64_t i;
 
 	/*
 	 * Classical integer square root approximation using shifts.

xdiff/xutils.h

@@ -25,7 +25,7 @@
 
 
 
-long xdl_bogosqrt(long n);
+uint64_t xdl_bogosqrt(uint64_t n);
 int xdl_emit_diffrec(char const *rec, long size, char const *pre, long psize,
 		     xdemitcb_t *ecb);
 int xdl_cha_init(chastore_t *cha, long isize, long icount);