add status config and command line options for rename detection

After performing a merge that has conflicts git status will, by default,
attempt to detect renames which causes many objects to be examined.  In a
virtualized repo, those objects do not exist locally so the rename logic
triggers them to be fetched from the server. This results in the status call
taking hours to complete on very large repos vs seconds with this patch.

Add a new config status.renames setting to enable turning off rename
detection during status and commit.  This setting will default to the value
of diff.renames.

Add a new config status.renamelimit setting to to enable bounding the time
spent finding out inexact renames during status and commit.  This setting
will default to the value of diff.renamelimit.

Add --no-renames command line option to status that enables overriding the
config setting from the command line. Add --find-renames[=<n>] command line
option to status that enables detecting renames and optionally setting the
similarity index.

Reviewed-by: Elijah Newren <newren@gmail.com>
Original-Patch-by: Alejandro Pauly <alpauly@microsoft.com>
Signed-off-by: Ben Peart <Ben.Peart@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 42 insertions, 0 deletions

diff --git a/builtin/commit.c b/builtin/commit.c
index 5240f11225..b50e33ef48 100644
--- a/builtin/commit.c
+++ b/builtin/commit.c
@@ -143,6 +143,16 @@ static int opt_parse_m(const struct option *opt, const char *arg, int unset)
 	return 0;
 }
 
+static int opt_parse_rename_score(const struct option *opt, const char *arg, int unset)
+{
+	const char **value = opt->value;
+	if (arg != NULL && *arg == '=')
+		arg = arg + 1;
+
+	*value = arg;
+	return 0;
+}
+
 static void determine_whence(struct wt_status *s)
 {
 	if (file_exists(git_path_merge_head()))
@@ -1259,11 +1269,31 @@ static int git_status_config(const char *k, const char *v, void *cb)
 			return error(_("Invalid untracked files mode '%s'"), v);
 		return 0;
 	}
+	if (!strcmp(k, "diff.renamelimit")) {
+		if (s->rename_limit == -1)
+			s->rename_limit = git_config_int(k, v);
+		return 0;
+	}
+	if (!strcmp(k, "status.renamelimit")) {
+		s->rename_limit = git_config_int(k, v);
+		return 0;
+	}
+	if (!strcmp(k, "diff.renames")) {
+		if (s->detect_rename == -1)
+			s->detect_rename = git_config_rename(k, v);
+		return 0;
+	}
+	if (!strcmp(k, "status.renames")) {
+		s->detect_rename = git_config_rename(k, v);
+		return 0;
+	}
 	return git_diff_ui_config(k, v, NULL);
 }
 
 int cmd_status(int argc, const char **argv, const char *prefix)
 {
+	static int no_renames = -1;
+	static const char *rename_score_arg = (const char *)-1;
 	static struct wt_status s;
 	int fd;
 	struct object_id oid;
@@ -1297,6 +1327,10 @@ int cmd_status(int argc, const char **argv, const char *prefix)
 		  N_("ignore changes to submodules, optional when: all, dirty, untracked. (Default: all)"),
 		  PARSE_OPT_OPTARG, NULL, (intptr_t)"all" },
 		OPT_COLUMN(0, "column", &s.colopts, N_("list untracked files in columns")),
+		OPT_BOOL(0, "no-renames", &no_renames, N_("do not detect renames")),
+		{ OPTION_CALLBACK, 'M', "find-renames", &rename_score_arg,
+		  N_("n"), N_("detect renames, optionally set similarity index"),
+		  PARSE_OPT_OPTARG, opt_parse_rename_score },
 		OPT_END(),
 	};
 
@@ -1336,6 +1370,14 @@ int cmd_status(int argc, const char **argv, const char *prefix)
 	s.ignore_submodule_arg = ignore_submodule_arg;
 	s.status_format = status_format;
 	s.verbose = verbose;
+	if (no_renames != -1)
+		s.detect_rename = !no_renames;
+	if ((intptr_t)rename_score_arg != -1) {
+		if (s.detect_rename < DIFF_DETECT_RENAME)
+			s.detect_rename = DIFF_DETECT_RENAME;
+		if (rename_score_arg)
+			s.rename_score = parse_rename_score(&rename_score_arg);
+	}
 
 	wt_status_collect(&s);