add status config and command line options for rename detection

Ben Peart · gitster · commit e8b2dc2c2a84 · 2018-05-13T10:57:37.000+09:00
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[=&lt;n&gt;] command line
option to status that enables detecting renames and optionally setting the
similarity index.

Reviewed-by: Elijah Newren &lt;newren@gmail.com&gt;
Original-Patch-by: Alejandro Pauly &lt;alpauly@microsoft.com&gt;
Signed-off-by: Ben Peart &lt;Ben.Peart@microsoft.com&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/Documentation/config.txt b/Documentation/config.txt
@@ -3119,6 +3119,18 @@ status.displayCommentPrefix::
 	behavior of linkgit:git-status[1] in Git 1.8.4 and previous.
 	Defaults to false.
 
+status.renameLimit::
+	The number of files to consider when performing rename detection
+	in linkgit:git-status[1] and linkgit:git-commit[1]. Defaults to
+	the value of diff.renameLimit.
+
+status.renames::
+	Whether and how Git detects renames in linkgit:git-status[1] and
+	linkgit:git-commit[1] .  If set to "false", rename detection is
+	disabled. If set to "true", basic rename detection is enabled.
+	If set to "copies" or "copy", Git will detect copies, as well.
+	Defaults to the value of diff.renames.
+
 status.showStash::
 	If set to true, linkgit:git-status[1] will display the number of
 	entries currently stashed away.
diff --git a/Documentation/git-status.txt b/Documentation/git-status.txt
@@ -135,6 +135,16 @@ ignored, then the directory is not shown, but all contents are shown.
 	Display or do not display detailed ahead/behind counts for the
 	branch relative to its upstream branch.  Defaults to true.
 
+--renames::
+--no-renames::
+	Turn on/off rename detection regardless of user configuration.
+	See also linkgit:git-diff[1] `--no-renames`.
+
+--find-renames[=<n>]::
+	Turn on rename detection, optionally setting the similarity
+	threshold.
+	See also linkgit:git-diff[1] `--find-renames`.
+
 <pathspec>...::
 	See the 'pathspec' entry in linkgit:gitglossary[7].
 
diff --git 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);
 
diff --git a/diff.c b/diff.c
@@ -177,7 +177,7 @@ static int parse_submodule_params(struct diff_options *options, const char *valu
 	return 0;
 }
 
-static int git_config_rename(const char *var, const char *value)
+int git_config_rename(const char *var, const char *value)
 {
 	if (!value)
 		return DIFF_DETECT_RENAME;
diff --git a/diff.h b/diff.h
@@ -324,6 +324,7 @@ extern int git_diff_ui_config(const char *var, const char *value, void *cb);
 extern void diff_setup(struct diff_options *);
 extern int diff_opt_parse(struct diff_options *, const char **, int, const char *);
 extern void diff_setup_done(struct diff_options *);
+extern int git_config_rename(const char *var, const char *value);
 
 #define DIFF_DETECT_RENAME	1
 #define DIFF_DETECT_COPY	2
diff --git a/t/t7525-status-rename.sh b/t/t7525-status-rename.sh
@@ -0,0 +1,113 @@
+#!/bin/sh
+
+test_description='git status rename detection options'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	echo 1 >original &&
+	git add . &&
+	git commit -m"Adding original file." &&
+	mv original renamed &&
+	echo 2 >> renamed &&
+	git add . &&
+	cat >.gitignore <<-\EOF
+	.gitignore
+	expect*
+	actual*
+	EOF
+'
+
+test_expect_success 'status no-options' '
+	git status >actual &&
+	test_i18ngrep "renamed:" actual
+'
+
+test_expect_success 'status --no-renames' '
+	git status --no-renames >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual
+'
+
+test_expect_success 'status.renames inherits from diff.renames false' '
+	git -c diff.renames=false status >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual
+'
+
+test_expect_success 'status.renames inherits from diff.renames true' '
+	git -c diff.renames=true status >actual &&
+	test_i18ngrep "renamed:" actual
+'
+
+test_expect_success 'status.renames overrides diff.renames false' '
+	git -c diff.renames=true -c status.renames=false status >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual
+'
+
+test_expect_success 'status.renames overrides from diff.renames true' '
+	git -c diff.renames=false -c status.renames=true status >actual &&
+	test_i18ngrep "renamed:" actual
+'
+
+test_expect_success 'status status.renames=false' '
+	git -c status.renames=false status >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual
+'
+
+test_expect_success 'status status.renames=true' '
+	git -c status.renames=true status >actual &&
+	test_i18ngrep "renamed:" actual
+'
+
+test_expect_success 'commit honors status.renames=false' '
+	git -c status.renames=false commit --dry-run >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual
+'
+
+test_expect_success 'commit honors status.renames=true' '
+	git -c status.renames=true commit --dry-run >actual &&
+	test_i18ngrep "renamed:" actual
+'
+
+test_expect_success 'status config overridden' '
+	git -c status.renames=true status --no-renames >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual
+'
+
+test_expect_success 'status score=100%' '
+	git status -M=100% >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual &&
+
+	git status --find-rename=100% >actual &&
+	test_i18ngrep "deleted:" actual &&
+	test_i18ngrep "new file:" actual
+'
+
+test_expect_success 'status score=01%' '
+	git status -M=01% >actual &&
+	test_i18ngrep "renamed:" actual &&
+
+	git status --find-rename=01% >actual &&
+	test_i18ngrep "renamed:" actual
+'
+
+test_expect_success 'copies not overridden by find-rename' '
+	cp renamed copy &&
+	git add copy &&
+
+	git -c status.renames=copies status -M=01% >actual &&
+	test_i18ngrep "copied:" actual &&
+	test_i18ngrep "renamed:" actual &&
+
+	git -c status.renames=copies status --find-rename=01% >actual &&
+	test_i18ngrep "copied:" actual &&
+	test_i18ngrep "renamed:" actual
+'
+
+test_done
diff --git a/wt-status.c b/wt-status.c
@@ -138,6 +138,9 @@ void wt_status_prepare(struct wt_status *s)
 	s->show_stash = 0;
 	s->ahead_behind_flags = AHEAD_BEHIND_UNSPECIFIED;
 	s->display_comment_prefix = 0;
+	s->detect_rename = -1;
+	s->rename_score = -1;
+	s->rename_limit = -1;
 }
 
 static void wt_longstatus_print_unmerged_header(struct wt_status *s)
@@ -592,6 +595,9 @@ static void wt_status_collect_changes_worktree(struct wt_status *s)
 	}
 	rev.diffopt.format_callback = wt_status_collect_changed_cb;
 	rev.diffopt.format_callback_data = s;
+	rev.diffopt.detect_rename = s->detect_rename >= 0 ? s->detect_rename : rev.diffopt.detect_rename;
+	rev.diffopt.rename_limit = s->rename_limit >= 0 ? s->rename_limit : rev.diffopt.rename_limit;
+	rev.diffopt.rename_score = s->rename_score >= 0 ? s->rename_score : rev.diffopt.rename_score;
 	copy_pathspec(&rev.prune_data, &s->pathspec);
 	run_diff_files(&rev, 0);
 }
@@ -625,6 +631,9 @@ static void wt_status_collect_changes_index(struct wt_status *s)
 	rev.diffopt.output_format |= DIFF_FORMAT_CALLBACK;
 	rev.diffopt.format_callback = wt_status_collect_updated_cb;
 	rev.diffopt.format_callback_data = s;
+	rev.diffopt.detect_rename = s->detect_rename >= 0 ? s->detect_rename : rev.diffopt.detect_rename;
+	rev.diffopt.rename_limit = s->rename_limit >= 0 ? s->rename_limit : rev.diffopt.rename_limit;
+	rev.diffopt.rename_score = s->rename_score >= 0 ? s->rename_score : rev.diffopt.rename_score;
 	copy_pathspec(&rev.prune_data, &s->pathspec);
 	run_diff_index(&rev, 1);
 }
@@ -982,6 +991,9 @@ static void wt_longstatus_print_verbose(struct wt_status *s)
 	setup_revisions(0, NULL, &rev, &opt);
 
 	rev.diffopt.output_format |= DIFF_FORMAT_PATCH;
+	rev.diffopt.detect_rename = s->detect_rename >= 0 ? s->detect_rename : rev.diffopt.detect_rename;
+	rev.diffopt.rename_limit = s->rename_limit >= 0 ? s->rename_limit : rev.diffopt.rename_limit;
+	rev.diffopt.rename_score = s->rename_score >= 0 ? s->rename_score : rev.diffopt.rename_score;
 	rev.diffopt.file = s->fp;
 	rev.diffopt.close_file = 0;
 	/*
diff --git a/wt-status.h b/wt-status.h
@@ -89,7 +89,9 @@ struct wt_status {
 	int show_stash;
 	int hints;
 	enum ahead_behind_flags ahead_behind_flags;
-
+	int detect_rename;
+	int rename_score;
+	int rename_limit;
 	enum wt_status_format status_format;
 	unsigned char sha1_commit[GIT_MAX_RAWSZ]; /* when not Initial */
 

Original file line number	Diff line number	Diff line change
`@@ -177,7 +177,7 @@ static int parse_submodule_params(struct diff_options options, const char valu`
`177`	`177`	`return 0;`
`178`	`178`	`}`
`179`	`179`
`180`		`-static int git_config_rename(const char var, const char value)`
	`180`	`+int git_config_rename(const char var, const char value)`
`181`	`181`	`{`
`182`	`182`	`if (!value)`
`183`	`183`	`return DIFF_DETECT_RENAME;`