Merge branch 'jc/rename-degrade-cc-to-c'

* jc/rename-degrade-cc-to-c:
  diffcore-rename: fall back to -C when -C -C busts the rename limit
  diffcore-rename: record filepair for rename src
  diffcore-rename: refactor "too many candidates" logic
  builtin/diff.c: remove duplicated call to diff_result_code()

8 files changed, 152 insertions, 40 deletions

diff --git a/builtin/diff-tree.c b/builtin/diff-tree.c
index 0d2a3e9fa2..be6417d166 100644
--- a/builtin/diff-tree.c
+++ b/builtin/diff-tree.c
@@ -163,6 +163,9 @@ int cmd_diff_tree(int argc, const char **argv, const char *prefix)
 	}
 
 	if (read_stdin) {
+		int saved_nrl = 0;
+		int saved_dcctc = 0;
+
 		if (opt->diffopt.detect_rename)
 			opt->diffopt.setup |= (DIFF_SETUP_USE_SIZE_CACHE |
 					       DIFF_SETUP_USE_CACHE);
@@ -173,9 +176,16 @@ int cmd_diff_tree(int argc, const char **argv, const char *prefix)
 				fputs(line, stdout);
 				fflush(stdout);
 			}
-			else
+			else {
 				diff_tree_stdin(line);
+				if (saved_nrl < opt->diffopt.needed_rename_limit)
+					saved_nrl = opt->diffopt.needed_rename_limit;
+				if (opt->diffopt.degraded_cc_to_c)
+					saved_dcctc = 1;
+			}
 		}
+		opt->diffopt.degraded_cc_to_c = saved_dcctc;
+		opt->diffopt.needed_rename_limit = saved_nrl;
 	}
 
 	return diff_result_code(&opt->diffopt, 0);
diff --git a/builtin/diff.c b/builtin/diff.c
index 717fa1a341..14bd14fce0 100644
--- a/builtin/diff.c
+++ b/builtin/diff.c
@@ -202,7 +202,6 @@ static void refresh_index_quietly(void)
 
 static int builtin_diff_files(struct rev_info *revs, int argc, const char **argv)
 {
-	int result;
 	unsigned int options = 0;
 
 	while (1 < argc && argv[1][0] == '-') {
@@ -236,8 +235,7 @@ static int builtin_diff_files(struct rev_info *revs, int argc, const char **argv
 		perror("read_cache_preload");
 		return -1;
 	}
-	result = run_diff_files(revs, options);
-	return diff_result_code(&revs->diffopt, result);
+	return run_diff_files(revs, options);
 }
 
 int cmd_diff(int argc, const char **argv, const char *prefix)
diff --git a/builtin/log.c b/builtin/log.c
index c6dce9b895..55abe07610 100644
--- a/builtin/log.c
+++ b/builtin/log.c
@@ -256,6 +256,8 @@ static void finish_early_output(struct rev_info *rev)
 static int cmd_log_walk(struct rev_info *rev)
 {
 	struct commit *commit;
+	int saved_nrl = 0;
+	int saved_dcctc = 0;
 
 	if (rev->early_output)
 		setup_early_output(rev);
@@ -286,7 +288,14 @@ static int cmd_log_walk(struct rev_info *rev)
 		}
 		free_commit_list(commit->parents);
 		commit->parents = NULL;
+		if (saved_nrl < rev->diffopt.needed_rename_limit)
+			saved_nrl = rev->diffopt.needed_rename_limit;
+		if (rev->diffopt.degraded_cc_to_c)
+			saved_dcctc = 1;
 	}
+	rev->diffopt.degraded_cc_to_c = saved_dcctc;
+	rev->diffopt.needed_rename_limit = saved_nrl;
+
 	if (rev->diffopt.output_format & DIFF_FORMAT_CHECKDIFF &&
 	    DIFF_OPT_TST(&rev->diffopt, CHECK_FAILED)) {
 		return 02;
diff --git a/diff.c b/diff.c
index 5376d01e1b..56758c7dca 100644
--- a/diff.c
+++ b/diff.c
@@ -3987,6 +3987,28 @@ static int is_summary_empty(const struct diff_queue_struct *q)
 	return 1;
 }
 
+static const char rename_limit_warning[] =
+"inexact rename detection was skipped due to too many files.";
+
+static const char degrade_cc_to_c_warning[] =
+"only found copies from modified paths due to too many files.";
+
+static const char rename_limit_advice[] =
+"you may want to set your %s variable to at least "
+"%d and retry the command.";
+
+void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc)
+{
+	if (degraded_cc)
+		warning(degrade_cc_to_c_warning);
+	else if (needed)
+		warning(rename_limit_warning);
+	else
+		return;
+	if (0 < needed && needed < 32767)
+		warning(rename_limit_advice, varname, needed);
+}
+
 void diff_flush(struct diff_options *options)
 {
 	struct diff_queue_struct *q = &diff_queued_diff;
@@ -4268,6 +4290,10 @@ void diffcore_std(struct diff_options *options)
 int diff_result_code(struct diff_options *opt, int status)
 {
 	int result = 0;
+
+	diff_warn_rename_limit("diff.renamelimit",
+			       opt->needed_rename_limit,
+			       opt->degraded_cc_to_c);
 	if (!DIFF_OPT_TST(opt, EXIT_WITH_STATUS) &&
 	    !(opt->output_format & DIFF_FORMAT_CHECKDIFF))
 		return status;
diff --git a/diff.h b/diff.h
index 007a0554d4..b8dde8a750 100644
--- a/diff.h
+++ b/diff.h
@@ -111,6 +111,7 @@ struct diff_options {
 	int rename_score;
 	int rename_limit;
 	int needed_rename_limit;
+	int degraded_cc_to_c;
 	int show_rename_progress;
 	int dirstat_percent;
 	int setup;
@@ -273,6 +274,7 @@ extern void diffcore_fix_diff_index(struct diff_options *);
 
 extern int diff_queue_is_empty(void);
 extern void diff_flush(struct diff_options*);
+extern void diff_warn_rename_limit(const char *varname, int needed, int degraded_cc);
 
 /* diff-raw status letters */
 #define DIFF_STATUS_ADDED		'A'
diff --git a/diffcore-rename.c b/diffcore-rename.c
index d40e40a3ac..f62587e523 100644
--- a/diffcore-rename.c
+++ b/diffcore-rename.c
@@ -55,22 +55,23 @@ static struct diff_rename_dst *locate_rename_dst(struct diff_filespec *two,
 
 /* Table of rename/copy src files */
 static struct diff_rename_src {
-	struct diff_filespec *one;
+	struct diff_filepair *p;
 	unsigned short score; /* to remember the break score */
 } *rename_src;
 static int rename_src_nr, rename_src_alloc;
 
-static struct diff_rename_src *register_rename_src(struct diff_filespec *one,
-						   unsigned short score)
+static struct diff_rename_src *register_rename_src(struct diff_filepair *p)
 {
 	int first, last;
+	struct diff_filespec *one = p->one;
+	unsigned short score = p->score;
 
 	first = 0;
 	last = rename_src_nr;
 	while (last > first) {
 		int next = (last + first) >> 1;
 		struct diff_rename_src *src = &(rename_src[next]);
-		int cmp = strcmp(one->path, src->one->path);
+		int cmp = strcmp(one->path, src->p->one->path);
 		if (!cmp)
 			return src;
 		if (cmp < 0) {
@@ -90,7 +91,7 @@ static struct diff_rename_src *register_rename_src(struct diff_filespec *one,
 	if (first < rename_src_nr)
 		memmove(rename_src + first + 1, rename_src + first,
 			(rename_src_nr - first - 1) * sizeof(*rename_src));
-	rename_src[first].one = one;
+	rename_src[first].p = p;
 	rename_src[first].score = score;
 	return &(rename_src[first]);
 }
@@ -205,7 +206,7 @@ static void record_rename_pair(int dst_index, int src_index, int score)
 	if (rename_dst[dst_index].pair)
 		die("internal error: dst already matched.");
 
-	src = rename_src[src_index].one;
+	src = rename_src[src_index].p->one;
 	src->rename_used++;
 	src->count++;
 
@@ -389,7 +390,7 @@ static int find_exact_renames(struct diff_options *options)
 
 	init_hash(&file_table);
 	for (i = 0; i < rename_src_nr; i++)
-		insert_file_table(&file_table, -1, i, rename_src[i].one);
+		insert_file_table(&file_table, -1, i, rename_src[i].p->one);
 
 	for (i = 0; i < rename_dst_nr; i++)
 		insert_file_table(&file_table, 1, i, rename_dst[i].two);
@@ -419,6 +420,55 @@ static void record_if_better(struct diff_score m[], struct diff_score *o)
 		m[worst] = *o;
 }
 
+/*
+ * Returns:
+ * 0 if we are under the limit;
+ * 1 if we need to disable inexact rename detection;
+ * 2 if we would be under the limit if we were given -C instead of -C -C.
+ */
+static int too_many_rename_candidates(int num_create,
+				      struct diff_options *options)
+{
+	int rename_limit = options->rename_limit;
+	int num_src = rename_src_nr;
+	int i;
+
+	options->needed_rename_limit = 0;
+
+	/*
+	 * This basically does a test for the rename matrix not
+	 * growing larger than a "rename_limit" square matrix, ie:
+	 *
+	 *    num_create * num_src > rename_limit * rename_limit
+	 *
+	 * but handles the potential overflow case specially (and we
+	 * assume at least 32-bit integers)
+	 */
+	if (rename_limit <= 0 || rename_limit > 32767)
+		rename_limit = 32767;
+	if ((num_create <= rename_limit || num_src <= rename_limit) &&
+	    (num_create * num_src <= rename_limit * rename_limit))
+		return 0;
+
+	options->needed_rename_limit =
+		num_src > num_create ? num_src : num_create;
+
+	/* Are we running under -C -C? */
+	if (!DIFF_OPT_TST(options, FIND_COPIES_HARDER))
+		return 1;
+
+	/* Would we bust the limit if we were running under -C? */
+	for (num_src = i = 0; i < rename_src_nr; i++) {
+		if (diff_unmodified_pair(rename_src[i].p))
+			continue;
+		num_src++;
+	}
+	if ((num_create <= rename_limit || num_src <= rename_limit) &&
+	    (num_create * num_src <= rename_limit * rename_limit))
+		return 2;
+	return 1;
+}
+
 static int find_renames(struct diff_score *mx, int dst_cnt, int minimum_score, int copies)
 {
 	int count = 0, i;
@@ -432,7 +482,7 @@ static int find_renames(struct diff_score *mx, int dst_cnt, int minimum_score, i
 		dst = &rename_dst[mx[i].dst];
 		if (dst->pair)
 			continue; /* already done, either exact or fuzzy. */
-		if (!copies && rename_src[mx[i].src].one->rename_used)
+		if (!copies && rename_src[mx[i].src].p->one->rename_used)
 			continue;
 		record_rename_pair(mx[i].dst, mx[i].src, mx[i].score);
 		count++;
@@ -444,11 +494,10 @@ void diffcore_rename(struct diff_options *options)
 {
 	int detect_rename = options->detect_rename;
 	int minimum_score = options->rename_score;
-	int rename_limit = options->rename_limit;
 	struct diff_queue_struct *q = &diff_queued_diff;
 	struct diff_queue_struct outq;
 	struct diff_score *mx;
-	int i, j, rename_count;
+	int i, j, rename_count, skip_unmodified = 0;
 	int num_create, num_src, dst_cnt;
 	struct progress *progress = NULL;
 
@@ -476,7 +525,7 @@ void diffcore_rename(struct diff_options *options)
 			 */
 			if (p->broken_pair && !p->score)
 				p->one->rename_used++;
-			register_rename_src(p->one, p->score);
+			register_rename_src(p);
 		}
 		else if (detect_rename == DIFF_DETECT_COPY) {
 			/*
@@ -484,7 +533,7 @@ void diffcore_rename(struct diff_options *options)
 			 * one, to indicate ourselves as a user.
 			 */
 			p->one->rename_used++;
-			register_rename_src(p->one, p->score);
+			register_rename_src(p);
 		}
 	}
 	if (rename_dst_nr == 0 || rename_src_nr == 0)
@@ -511,23 +560,15 @@ void diffcore_rename(struct diff_options *options)
 	if (!num_create)
 		goto cleanup;
 
-	/*
-	 * This basically does a test for the rename matrix not
-	 * growing larger than a "rename_limit" square matrix, ie:
-	 *
-	 *    num_create * num_src > rename_limit * rename_limit
-	 *
-	 * but handles the potential overflow case specially (and we
-	 * assume at least 32-bit integers)
-	 */
-	options->needed_rename_limit = 0;
-	if (rename_limit <= 0 || rename_limit > 32767)
-		rename_limit = 32767;
-	if ((num_create > rename_limit && num_src > rename_limit) ||
-	    (num_create * num_src > rename_limit * rename_limit)) {
-		options->needed_rename_limit =
-			num_src > num_create ? num_src : num_create;
+	switch (too_many_rename_candidates(num_create, options)) {
+	case 1:
 		goto cleanup;
+	case 2:
+		options->degraded_cc_to_c = 1;
+		skip_unmodified = 1;
+		break;
+	default:
+		break;
 	}
 
 	if (options->show_rename_progress) {
@@ -549,8 +590,13 @@ void diffcore_rename(struct diff_options *options)
 			m[j].dst = -1;
 
 		for (j = 0; j < rename_src_nr; j++) {
-			struct diff_filespec *one = rename_src[j].one;
+			struct diff_filespec *one = rename_src[j].p->one;
 			struct diff_score this_src;
+
+			if (skip_unmodified &&
+			    diff_unmodified_pair(rename_src[j].p))
+				continue;
+
 			this_src.score = estimate_similarity(one, two,
 							     minimum_score);
 			this_src.name_score = basename_same(one, two);
diff --git a/merge-recursive.c b/merge-recursive.c
index 7c12673553..fb3c874ff4 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -22,11 +22,6 @@
 #include "dir.h"
 #include "submodule.h"
 
-static const char rename_limit_advice[] =
-"inexact rename detection was skipped because there were too many\n"
-"  files. You may want to set your merge.renamelimit variable to at least\n"
-"  %d and retry this merge.";
-
 static struct tree *shift_tree_object(struct tree *one, struct tree *two,
 				      const char *subtree_shift)
 {
@@ -1664,8 +1659,9 @@ int merge_recursive(struct merge_options *o,
 		commit_list_insert(h2, &(*result)->parents->next);
 	}
 	flush_output(o);
-	if (o->needed_rename_limit)
-		warning(rename_limit_advice, o->needed_rename_limit);
+	if (show(o, 2))
+		diff_warn_rename_limit("merge.renamelimit",
+				       o->needed_rename_limit, 0);
 	return clean;
 }
 
diff --git a/t/t4001-diff-rename.sh b/t/t4001-diff-rename.sh
index cad85450b7..3dadf9b316 100755
--- a/t/t4001-diff-rename.sh
+++ b/t/t4001-diff-rename.sh
@@ -77,4 +77,29 @@ test_expect_success C_LOCALE_OUTPUT  'favour same basenames even with minor diff
 	git show HEAD:path1 | sed "s/15/16/" > subdir/path1 &&
 	git status | grep "renamed: .*path1 -> subdir/path1"'
 
+test_expect_success 'setup for many rename source candidates' '
+	git reset --hard &&
+	for i in 0 1 2 3 4 5 6 7 8 9;
+	do
+		for j in 0 1 2 3 4 5 6 7 8 9;
+		do
+			echo "$i$j" >"path$i$j"
+		done
+	done &&
+	git add "path??" &&
+	test_tick &&
+	git commit -m "hundred" &&
+	(cat path1; echo new) >new-path &&
+	echo old >>path1 &&
+	git add new-path path1 &&
+	git diff -l 4 -C -C --cached --name-status >actual 2>actual.err &&
+	sed -e "s/^\([CM]\)[0-9]*	/\1	/" actual >actual.munged &&
+	cat >expect <<-EOF &&
+	C	path1	new-path
+	M	path1
+	EOF
+	test_cmp expect actual.munged &&
+	grep warning actual.err
+'
+
 test_done