Merge branch 'jk/diff-no-rename-empty' into maint

Rename detection logic used to match two empty files as renames during
merge-recursive, leading unnatural mismerges.

By Jeff King
* jk/diff-no-rename-empty:
  merge-recursive: don't detect renames of empty files
  teach diffcore-rename to optionally ignore empty content
  make is_empty_blob_sha1 available everywhere
  drop casts from users EMPTY_TREE_SHA1_BIN

builtin/diff.c

@@ -327,7 +327,7 @@ int cmd_diff(int argc, const char **argv, const char *prefix)
 				add_head_to_pending(&rev);
 				if (!rev.pending.nr) {
 					struct tree *tree;
-					tree = lookup_tree((const unsigned char*)EMPTY_TREE_SHA1_BIN);
+					tree = lookup_tree(EMPTY_TREE_SHA1_BIN);
 					add_pending_object(&rev, &tree->object, "HEAD");
 				}
 				break;

cache.h

@@ -708,6 +708,19 @@ static inline void hashclr(unsigned char *hash)
 #define EMPTY_TREE_SHA1_BIN \
 	 ((const unsigned char *) EMPTY_TREE_SHA1_BIN_LITERAL)
 
+#define EMPTY_BLOB_SHA1_HEX \
+	"e69de29bb2d1d6434b8b29ae775ad8c2e48c5391"
+#define EMPTY_BLOB_SHA1_BIN_LITERAL \
+	"\xe6\x9d\xe2\x9b\xb2\xd1\xd6\x43\x4b\x8b" \
+	"\x29\xae\x77\x5a\xd8\xc2\xe4\x8c\x53\x91"
+#define EMPTY_BLOB_SHA1_BIN \
+	((const unsigned char *) EMPTY_BLOB_SHA1_BIN_LITERAL)
+
+static inline int is_empty_blob_sha1(const unsigned char *sha1)
+{
+	return !hashcmp(sha1, EMPTY_BLOB_SHA1_BIN);
+}
+
 int git_mkstemp(char *path, size_t n, const char *template);
 
 int git_mkstemps(char *path, size_t n, const char *template, int suffix_len);

diff.c

@@ -3146,6 +3146,7 @@ void diff_setup(struct diff_options *options)
 	options->rename_limit = -1;
 	options->dirstat_permille = diff_dirstat_permille_default;
 	options->context = 3;
+	DIFF_OPT_SET(options, RENAME_EMPTY);
 
 	options->change = diff_change;
 	options->add_remove = diff_addremove;
@@ -3516,6 +3517,10 @@ int diff_opt_parse(struct diff_options *options, const char **av, int ac)
 	}
 	else if (!strcmp(arg, "--no-renames"))
 		options->detect_rename = 0;
+	else if (!strcmp(arg, "--rename-empty"))
+		DIFF_OPT_SET(options, RENAME_EMPTY);
+	else if (!strcmp(arg, "--no-rename-empty"))
+		DIFF_OPT_CLR(options, RENAME_EMPTY);
 	else if (!strcmp(arg, "--relative"))
 		DIFF_OPT_SET(options, RELATIVE_NAME);
 	else if (!prefixcmp(arg, "--relative=")) {

diff.h

@@ -60,7 +60,7 @@ typedef struct strbuf *(*diff_prefix_fn_t)(struct diff_options *opt, void *data)
 #define DIFF_OPT_SILENT_ON_REMOVE    (1 <<  5)
 #define DIFF_OPT_FIND_COPIES_HARDER  (1 <<  6)
 #define DIFF_OPT_FOLLOW_RENAMES      (1 <<  7)
-/* (1 <<  8) unused */
+#define DIFF_OPT_RENAME_EMPTY        (1 <<  8)
 /* (1 <<  9) unused */
 #define DIFF_OPT_HAS_CHANGES         (1 << 10)
 #define DIFF_OPT_QUICK               (1 << 11)

diffcore-rename.c

@@ -512,9 +512,15 @@ void diffcore_rename(struct diff_options *options)
 			else if (options->single_follow &&
 				 strcmp(options->single_follow, p->two->path))
 				continue; /* not interested */
+			else if (!DIFF_OPT_TST(options, RENAME_EMPTY) &&
+				 is_empty_blob_sha1(p->two->sha1))
+				continue;
 			else
 				locate_rename_dst(p->two, 1);
 		}
+		else if (!DIFF_OPT_TST(options, RENAME_EMPTY) &&
+			 is_empty_blob_sha1(p->one->sha1))
+			continue;
 		else if (!DIFF_PAIR_UNMERGED(p) && !DIFF_FILE_VALID(p->two)) {
 			/*
 			 * If the source is a broken "delete", and

merge-recursive.c

@@ -485,6 +485,7 @@ static struct string_list *get_renames(struct merge_options *o,
 	renames = xcalloc(1, sizeof(struct string_list));
 	diff_setup(&opts);
 	DIFF_OPT_SET(&opts, RECURSIVE);
+	DIFF_OPT_CLR(&opts, RENAME_EMPTY);
 	opts.detect_rename = DIFF_DETECT_RENAME;
 	opts.rename_limit = o->merge_rename_limit >= 0 ? o->merge_rename_limit :
 			    o->diff_rename_limit >= 0 ? o->diff_rename_limit :
@@ -1914,7 +1915,7 @@ int merge_recursive(struct merge_options *o,
 		/* if there is no common ancestor, use an empty tree */
 		struct tree *tree;
 
-		tree = lookup_tree((const unsigned char *)EMPTY_TREE_SHA1_BIN);
+		tree = lookup_tree(EMPTY_TREE_SHA1_BIN);
 		merged_common_ancestors = make_virtual_commit(tree, "ancestor");
 	}
 

read-cache.c

@@ -157,16 +157,6 @@ static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st)
 	return 0;
 }
 
-static int is_empty_blob_sha1(const unsigned char *sha1)
-{
-	static const unsigned char empty_blob_sha1[20] = {
-		0xe6,0x9d,0xe2,0x9b,0xb2,0xd1,0xd6,0x43,0x4b,0x8b,
-		0x29,0xae,0x77,0x5a,0xd8,0xc2,0xe4,0x8c,0x53,0x91
-	};
-
-	return !hashcmp(sha1, empty_blob_sha1);
-}
-
 static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
 {
 	unsigned int changed = 0;

sequencer.c

@@ -164,7 +164,7 @@ static void write_message(struct strbuf *msgbuf, const char *filename)
 
 static struct tree *empty_tree(void)
 {
-	return lookup_tree((const unsigned char *)EMPTY_TREE_SHA1_BIN);
+	return lookup_tree(EMPTY_TREE_SHA1_BIN);
 }
 
 static int error_dirty_index(struct replay_opts *opts)

t/t6022-merge-rename.sh

@@ -884,4 +884,20 @@ test_expect_success 'no spurious "refusing to lose untracked" message' '
 	! grep "refusing to lose untracked file" errors.txt
 '
 
+test_expect_success 'do not follow renames for empty files' '
+	git checkout -f -b empty-base &&
+	>empty1 &&
+	git add empty1 &&
+	git commit -m base &&
+	echo content >empty1 &&
+	git add empty1 &&
+	git commit -m fill &&
+	git checkout -b empty-topic HEAD^ &&
+	git mv empty1 empty2 &&
+	git commit -m rename &&
+	test_must_fail git merge empty-base &&
+	>expect &&
+	test_cmp expect empty2
+'
+
 test_done