fetch: infer branches to fetch from a refmap-only remote

Configuring remote.<name>.refmap without remote.<name>.fetch used to
make a refspec-less "git fetch <name>" fail with "--refmap option is
only meaningful with command-line refspec(s)", since a refmap only
says where to put fetched refs, not what to fetch.

Make that case infer what to fetch: the local branches whose
@{upstream} is already on that remote. This lets a remote be
configured to fetch only the branches actually in use, without
listing them by hand in remote.<name>.fetch, and without needing to
touch the command line every time.

Signed-off-by: Harald Nordgren <haraldnordgren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/config/remote.adoc

@@ -36,7 +36,10 @@ remote.<name>.fetch::
 remote.<name>.refmap::
 	The default value of the `--refmap` option for linkgit:git-fetch[1].
 	Used to map remote refs being fetched to remote-tracking refs to
-	store. See the `--refmap` entry in linkgit:git-fetch[1].
+	store. If `remote.<name>.fetch` is not set either, a refspec-less
+	fetch infers what to fetch from local branches built on this
+	remote, instead of fetching every branch it has. See the
+	`--refmap` entry in linkgit:git-fetch[1].
 
 remote.<name>.push::
 	The default set of "refspec" for linkgit:git-push[1]. See

Documentation/fetch-options.adoc

@@ -245,8 +245,10 @@ endif::git-pull[]
 	command-line arguments. See section on "Configured Remote-tracking
 	Branches" for details.
 +
-`remote.<name>.refmap` provides the default value for this option, the
-same way `remote.<name>.fetch` provides the default refspecs to fetch.
+When a refmap is active (from `--refmap` or `remote.<name>.refmap`) but
+nothing to fetch is specified on the command line, nor is there a
+`remote.<name>.fetch`, branches from the remote that are used as the
+`@{upstream}` of our local branches are fetched.
 
 `-t`::
 `--tags`::

builtin/fetch.c

@@ -515,6 +515,8 @@ static struct ref *get_ref_map(struct remote *remote,
 	 */
 	struct refspec *effective_refmap =
 		refmap.nr ? &refmap : remote ? &remote->refmap : NULL;
+	struct refspec inferred_rs;
+	int infer_from_refmap = 0;
 
 	/* opportunistically-updated references: */
 	struct ref *orefs = NULL, **oref_tail = &orefs;
@@ -522,15 +524,32 @@ static struct ref *get_ref_map(struct remote *remote,
 	struct hashmap existing_refs;
 	int existing_refs_populated = 0;
 
+	refspec_init_fetch(&inferred_rs, the_hash_algo);
+
 	filter_prefetch_refspec(rs);
 	if (remote)
 		filter_prefetch_refspec(&remote->fetch);
 
+	if (!rs->nr && remote && !remote->fetch.nr &&
+	    effective_refmap && effective_refmap->nr) {
+		struct string_list tracked = STRING_LIST_INIT_DUP;
+		struct string_list_item *item;
+
+		branches_tracking_remote(the_repository, remote, &tracked);
+		for_each_string_list_item(item, &tracked)
+			refspec_append(&inferred_rs, item->string);
+		string_list_clear(&tracked, 0);
+
+		rs = &inferred_rs;
+		infer_from_refmap = 1;
+	}
+
 	if (rs->nr) {
 		struct refspec *fetch_refspec;
 
 		for (i = 0; i < rs->nr; i++) {
-			get_fetch_map(remote_refs, &rs->items[i], &tail, 0);
+			get_fetch_map(remote_refs, &rs->items[i], &tail,
+				      infer_from_refmap);
 			if (rs->items[i].dst && rs->items[i].dst[0])
 				*autotags = 1;
 		}
@@ -565,6 +584,8 @@ static struct ref *get_ref_map(struct remote *remote,
 
 		for (i = 0; i < fetch_refspec->nr; i++)
 			get_fetch_map(ref_map, &fetch_refspec->items[i], &oref_tail, 1);
+	} else if (infer_from_refmap) {
+		/* Already fully handled above. */
 	} else if (refmap.nr) {
 		die("--refmap option is only meaningful with command-line refspec(s)");
 	} else {
@@ -660,6 +681,7 @@ static struct ref *get_ref_map(struct remote *remote,
 	if (existing_refs_populated)
 		hashmap_clear_and_free(&existing_refs, struct refname_hash_entry, ent);
 
+	refspec_clear(&inferred_rs);
 	return ref_map;
 }
 
@@ -1983,11 +2005,24 @@ static int do_fetch(struct transport *transport,
 				    item->string);
 		string_list_clear(&tracked, 0);
 	} else {
+		/*
+		 * The --refmap command line option, if given, takes
+		 * precedence over remote.<name>.refmap.
+		 */
+		struct refspec *effective_refmap = refmap.nr ? &refmap :
+			&transport->remote->refmap;
 		struct string_list tracked = STRING_LIST_INIT_DUP;
 		struct string_list_item *item;
 
-		collect_upstream_from_remote(the_repository, &tracked,
-					      transport->remote, NULL);
+		if (effective_refmap->nr) {
+			branches_tracking_remote(the_repository,
+						  transport->remote, &tracked);
+			if (follow_remote_head != FOLLOW_REMOTE_NEVER)
+				do_set_head = 1;
+		} else {
+			collect_upstream_from_remote(the_repository, &tracked,
+						      transport->remote, NULL);
+		}
 		for_each_string_list_item(item, &tracked)
 			strvec_push(&transport_ls_refs_options.ref_prefixes,
 				    item->string);

remote.c

@@ -1899,6 +1899,30 @@ void collect_upstream_from_remote(struct repository *repo,
 		string_list_insert(tracked, branch->merge[i]->src);
 }
 
+struct branches_tracking_remote_cb_data {
+	struct repository *repo;
+	struct remote *remote;
+	struct string_list *tracked;
+};
+
+static int add_if_tracking_remote(const struct reference *ref, void *cb_data)
+{
+	struct branches_tracking_remote_cb_data *data = cb_data;
+
+	collect_upstream_from_remote(data->repo, data->tracked, data->remote,
+				      ref->name);
+	return 0;
+}
+
+void branches_tracking_remote(struct repository *repo, struct remote *remote,
+			       struct string_list *tracked)
+{
+	struct branches_tracking_remote_cb_data data = { repo, remote, tracked };
+
+	refs_for_each_branch_ref(get_main_ref_store(repo),
+				  add_if_tracking_remote, &data);
+}
+
 __attribute__((format (printf,2,3)))
 static char *error_buf(struct strbuf *err, const char *fmt, ...)
 {

remote.h

@@ -368,6 +368,10 @@ void collect_upstream_from_remote(struct repository *repo,
 				   struct remote *remote,
 				   const char *refname);
 
+/* fills tracked with the refname of every local branch's upstream on remote */
+void branches_tracking_remote(struct repository *repo, struct remote *remote,
+			       struct string_list *tracked);
+
 /* list of the remote in a group as configured */
 struct remote_group_data {
 	const char *name;

t/meson.build

@@ -728,6 +728,7 @@ integration_tests = [
   't5582-fetch-negative-refspec.sh',
   't5583-push-branches.sh',
   't5584-http-429-retry.sh',
+  't5586-fetch-refmap.sh',
   't5600-clone-fail-cleanup.sh',
   't5601-clone.sh',
   't5602-clone-remote-exec.sh',

t/t5586-fetch-refmap.sh

@@ -0,0 +1,119 @@
+#!/bin/sh
+
+test_description='"git fetch" with a remote.<name>.refmap but no remote.<name>.fetch
+
+When a remote has a refmap configured but no fetch refspec, a
+refspec-less fetch infers what to fetch from the local branches whose
+@{upstream} is on that remote.
+'
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./test-lib.sh
+
+test_expect_success 'setup' '
+	test_commit main-1 &&
+	test_commit main-2 &&
+	git checkout -b side main-1 &&
+	test_commit side-1 &&
+	git checkout -b next main-1 &&
+	test_commit next-1 &&
+	git checkout main
+'
+
+test_expect_success 'clone shallow and single-branch, then add a second remote' '
+	git clone --no-local --depth=1 --branch main --single-branch . client &&
+	(
+		cd client &&
+		git remote add upstream .. &&
+		test_might_fail git config unset remote.upstream.fetch &&
+		git config remote.upstream.refmap \
+			"+refs/heads/*:refs/remotes/upstream/*"
+	)
+'
+
+test_expect_success 'a bare fetch needs nothing until a branch is tracked' '
+	(
+		cd client &&
+		git fetch upstream &&
+		git for-each-ref --format="%(refname)" refs/remotes/upstream >actual &&
+		test_must_be_empty actual
+	)
+'
+
+test_expect_success 'an explicit one-time fetch lets a branch be tracked' '
+	(
+		cd client &&
+		git fetch upstream main &&
+		git branch --set-upstream-to=upstream/main &&
+		test_cmp_config upstream branch.main.remote &&
+		test_cmp_config refs/heads/main branch.main.merge
+	)
+'
+
+test_expect_success 'a branch checked out from a one-time fetch is kept updated by later plain fetches' '
+	(
+		cd client &&
+		git fetch upstream side:refs/remotes/upstream/side &&
+		git branch side-topic upstream/side
+	) &&
+	git checkout side &&
+	test_commit side-2 &&
+	git checkout main &&
+	(
+		cd client &&
+		git fetch upstream &&
+		git for-each-ref --format="%(refname)" refs/remotes/upstream >actual &&
+		cat >expect <<-\EOF &&
+		refs/remotes/upstream/HEAD
+		refs/remotes/upstream/main
+		refs/remotes/upstream/side
+		EOF
+		test_cmp expect actual &&
+		git rev-parse refs/remotes/upstream/side >actual-oid &&
+		git -C .. rev-parse side >expect-oid &&
+		test_cmp expect-oid actual-oid
+	)
+'
+
+test_expect_success 'a second branch tracking the same upstream branch does not fetch it twice' '
+	(
+		cd client &&
+		git branch side-topic-2 upstream/side &&
+		git fetch upstream &&
+		git for-each-ref --format="%(refname)" refs/remotes/upstream >actual &&
+		cat >expect <<-\EOF &&
+		refs/remotes/upstream/HEAD
+		refs/remotes/upstream/main
+		refs/remotes/upstream/side
+		EOF
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'a branch tracking a different remote is not fetched from upstream' '
+	(
+		cd client &&
+		git remote add other .. &&
+		git fetch other next:refs/remotes/other/next &&
+		git branch next-topic other/next &&
+		git fetch upstream &&
+		git for-each-ref --format="%(refname)" refs/remotes/upstream >actual &&
+		cat >expect <<-\EOF &&
+		refs/remotes/upstream/HEAD
+		refs/remotes/upstream/main
+		refs/remotes/upstream/side
+		EOF
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'git remote show does not choke on a refmap-only remote' '
+	(
+		cd client &&
+		git remote show upstream
+	)
+'
+
+test_done