Merge branch 'rs/diff-cleanup-records-fix'

* rs/diff-cleanup-records-fix:
  diff: resurrect XDF_NEED_MINIMAL with --minimal
  Revert removal of multi-match discard heuristic in 27af01

3 files changed, 15 insertions, 3 deletions

diff --git a/Documentation/diff-options.txt b/Documentation/diff-options.txt
index b620b3afec..5c53bdba94 100644
--- a/Documentation/diff-options.txt
+++ b/Documentation/diff-options.txt
@@ -45,6 +45,10 @@ ifndef::git-format-patch[]
 	Synonym for `-p --raw`.
 endif::git-format-patch[]
 
+--minimal::
+	Spend extra time to make sure the smallest possible
+	diff is produced.
+
 --patience::
 	Generate a diff using the "patience diff" algorithm.
 
diff --git a/diff.c b/diff.c
index eed227a6ac..d922b77aef 100644
--- a/diff.c
+++ b/diff.c
@@ -3387,6 +3387,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	}
 
 	/* xdiff options */
+	else if (!strcmp(arg, "--minimal"))
+		DIFF_XDL_SET(options, NEED_MINIMAL);
+	else if (!strcmp(arg, "--no-minimal"))
+		DIFF_XDL_CLR(options, NEED_MINIMAL);
 	else if (!strcmp(arg, "-w") || !strcmp(arg, "--ignore-all-space"))
 		DIFF_XDL_SET(options, IGNORE_WHITESPACE);
 	else if (!strcmp(arg, "-b") || !strcmp(arg, "--ignore-space-change"))
diff --git a/xdiff/xprepare.c b/xdiff/xprepare.c
index 5a33d1a869..e419f4f726 100644
--- a/xdiff/xprepare.c
+++ b/xdiff/xprepare.c
@@ -383,7 +383,7 @@ 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 +396,20 @@ 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];