Merge branch 'sb/submodule-clone-rr'

"git clone --resurse-submodules --reference $path $URL" is a way to
reduce network transfer cost by borrowing objects in an existing
$path repository when cloning the superproject from $URL; it
learned to also peek into $path for presense of corresponding
repositories of submodules and borrow objects from there when able.

* sb/submodule-clone-rr:
  clone: recursive and reference option triggers submodule alternates
  clone: implement optional references
  clone: clarify option_reference as required
  clone: factor out checking for an alternate path
  submodule--helper update-clone: allow multiple references
  submodule--helper module-clone: allow multiple references
  t7408: merge short tests, factor out testing method
  t7408: modernize style

Author: gitster

Documentation/config.txt

@@ -2853,6 +2853,18 @@ submodule.fetchJobs::
 	in parallel. A value of 0 will give some reasonable default.
 	If unset, it defaults to 1.
 
+submodule.alternateLocation::
+	Specifies how the submodules obtain alternates when submodules are
+	cloned. Possible values are `no`, `superproject`.
+	By default `no` is assumed, which doesn't add references. When the
+	value is set to `superproject` the submodule to be cloned computes
+	its alternates location relative to the superprojects alternate.
+
+submodule.alternateErrorStrategy
+	Specifies how to treat errors with the alternates for a submodule
+	as computed via `submodule.alternateLocation`. Possible values are
+	`ignore`, `info`, `die`. Default is `die`.
+
 tag.forceSignAnnotated::
 	A boolean to specify whether annotated tags created should be GPG signed.
 	If `--annotate` is specified on the command line, it takes

Documentation/git-clone.txt

@@ -90,13 +90,16 @@ If you want to break the dependency of a repository cloned with `-s` on
 its source repository, you can simply run `git repack -a` to copy all
 objects from the source repository into a pack in the cloned repository.
 
---reference <repository>::
+--reference[-if-able] <repository>::
 	If the reference repository is on the local machine,
 	automatically setup `.git/objects/info/alternates` to
 	obtain objects from the reference repository.  Using
 	an already existing repository as an alternate will
 	require fewer objects to be copied from the repository
 	being cloned, reducing network and local storage costs.
+	When using the `--reference-if-able`, a non existing
+	directory is skipped with a warning instead of aborting
+	the clone.
 +
 *NOTE*: see the NOTE for the `--shared` option, and also the
 `--dissociate` option.

builtin/clone.c

@@ -50,7 +50,8 @@ static int option_verbosity;
 static int option_progress = -1;
 static enum transport_family family;
 static struct string_list option_config = STRING_LIST_INIT_NODUP;
-static struct string_list option_reference = STRING_LIST_INIT_NODUP;
+static struct string_list option_required_reference = STRING_LIST_INIT_NODUP;
+static struct string_list option_optional_reference = STRING_LIST_INIT_NODUP;
 static int option_dissociate;
 static int max_jobs = -1;
 
@@ -79,8 +80,10 @@ static struct option builtin_clone_options[] = {
 		    N_("number of submodules cloned in parallel")),
 	OPT_STRING(0, "template", &option_template, N_("template-directory"),
 		   N_("directory from which templates will be used")),
-	OPT_STRING_LIST(0, "reference", &option_reference, N_("repo"),
+	OPT_STRING_LIST(0, "reference", &option_required_reference, N_("repo"),
 			N_("reference repository")),
+	OPT_STRING_LIST(0, "reference-if-able", &option_optional_reference,
+			N_("repo"), N_("reference repository")),
 	OPT_BOOL(0, "dissociate", &option_dissociate,
 		 N_("use --reference only while cloning")),
 	OPT_STRING('o', "origin", &option_origin, N_("name"),
@@ -282,50 +285,37 @@ static void strip_trailing_slashes(char *dir)
 
 static int add_one_reference(struct string_list_item *item, void *cb_data)
 {
-	char *ref_git;
-	const char *repo;
-	struct strbuf alternate = STRBUF_INIT;
-
-	/* Beware: read_gitfile(), real_path() and mkpath() return static buffer */
-	ref_git = xstrdup(real_path(item->string));
-
-	repo = read_gitfile(ref_git);
-	if (!repo)
-		repo = read_gitfile(mkpath("%s/.git", ref_git));
-	if (repo) {
-		free(ref_git);
-		ref_git = xstrdup(repo);
-	}
+	struct strbuf err = STRBUF_INIT;
+	int *required = cb_data;
+	char *ref_git = compute_alternate_path(item->string, &err);
 
-	if (!repo && is_directory(mkpath("%s/.git/objects", ref_git))) {
-		char *ref_git_git = mkpathdup("%s/.git", ref_git);
-		free(ref_git);
-		ref_git = ref_git_git;
-	} else if (!is_directory(mkpath("%s/objects", ref_git))) {
+	if (!ref_git) {
+		if (*required)
+			die("%s", err.buf);
+		else
+			fprintf(stderr,
+				_("info: Could not add alternate for '%s': %s\n"),
+				item->string, err.buf);
+	} else {
 		struct strbuf sb = STRBUF_INIT;
-		if (get_common_dir(&sb, ref_git))
-			die(_("reference repository '%s' as a linked checkout is not supported yet."),
-			    item->string);
-		die(_("reference repository '%s' is not a local repository."),
-		    item->string);
+		strbuf_addf(&sb, "%s/objects", ref_git);
+		add_to_alternates_file(sb.buf);
+		strbuf_release(&sb);
 	}
 
-	if (!access(mkpath("%s/shallow", ref_git), F_OK))
-		die(_("reference repository '%s' is shallow"), item->string);
-
-	if (!access(mkpath("%s/info/grafts", ref_git), F_OK))
-		die(_("reference repository '%s' is grafted"), item->string);
-
-	strbuf_addf(&alternate, "%s/objects", ref_git);
-	add_to_alternates_file(alternate.buf);
-	strbuf_release(&alternate);
+	strbuf_release(&err);
 	free(ref_git);
 	return 0;
 }
 
 static void setup_reference(void)
 {
-	for_each_string_list(&option_reference, add_one_reference, NULL);
+	int required = 1;
+	for_each_string_list(&option_required_reference,
+			     add_one_reference, &required);
+	required = 0;
+	for_each_string_list(&option_optional_reference,
+			     add_one_reference, &required);
 }
 
 static void copy_alternates(struct strbuf *src, struct strbuf *dst,
@@ -957,6 +947,25 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		else
 			fprintf(stderr, _("Cloning into '%s'...\n"), dir);
 	}
+
+	if (option_recursive) {
+		if (option_required_reference.nr &&
+		    option_optional_reference.nr)
+			die(_("clone --recursive is not compatible with "
+			      "both --reference and --reference-if-able"));
+		else if (option_required_reference.nr) {
+			string_list_append(&option_config,
+				"submodule.alternateLocation=superproject");
+			string_list_append(&option_config,
+				"submodule.alternateErrorStrategy=die");
+		} else if (option_optional_reference.nr) {
+			string_list_append(&option_config,
+				"submodule.alternateLocation=superproject");
+			string_list_append(&option_config,
+				"submodule.alternateErrorStrategy=info");
+		}
+	}
+
 	init_db(option_template, INIT_DB_QUIET);
 	write_config(&option_config);
 
@@ -977,7 +986,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 	git_config_set(key.buf, repo);
 	strbuf_reset(&key);
 
-	if (option_reference.nr)
+	if (option_required_reference.nr || option_optional_reference.nr)
 		setup_reference();
 
 	fetch_pattern = value.buf;

builtin/submodule--helper.c

@@ -442,7 +442,7 @@ static int module_name(int argc, const char **argv, const char *prefix)
 }
 
 static int clone_submodule(const char *path, const char *gitdir, const char *url,
-			   const char *depth, const char *reference, int quiet)
+			   const char *depth, struct string_list *reference, int quiet)
 {
 	struct child_process cp = CHILD_PROCESS_INIT;
 
@@ -452,8 +452,12 @@ static int clone_submodule(const char *path, const char *gitdir, const char *url
 		argv_array_push(&cp.args, "--quiet");
 	if (depth && *depth)
 		argv_array_pushl(&cp.args, "--depth", depth, NULL);
-	if (reference && *reference)
-		argv_array_pushl(&cp.args, "--reference", reference, NULL);
+	if (reference->nr) {
+		struct string_list_item *item;
+		for_each_string_list_item(item, reference)
+			argv_array_pushl(&cp.args, "--reference",
+					 item->string, NULL);
+	}
 	if (gitdir && *gitdir)
 		argv_array_pushl(&cp.args, "--separate-git-dir", gitdir, NULL);
 
@@ -467,15 +471,114 @@ static int clone_submodule(const char *path, const char *gitdir, const char *url
 	return run_command(&cp);
 }
 
+struct submodule_alternate_setup {
+	const char *submodule_name;
+	enum SUBMODULE_ALTERNATE_ERROR_MODE {
+		SUBMODULE_ALTERNATE_ERROR_DIE,
+		SUBMODULE_ALTERNATE_ERROR_INFO,
+		SUBMODULE_ALTERNATE_ERROR_IGNORE
+	} error_mode;
+	struct string_list *reference;
+};
+#define SUBMODULE_ALTERNATE_SETUP_INIT { NULL, \
+	SUBMODULE_ALTERNATE_ERROR_IGNORE, NULL }
+
+static int add_possible_reference_from_superproject(
+		struct alternate_object_database *alt, void *sas_cb)
+{
+	struct submodule_alternate_setup *sas = sas_cb;
+
+	/* directory name, minus trailing slash */
+	size_t namelen = alt->name - alt->base - 1;
+	struct strbuf name = STRBUF_INIT;
+	strbuf_add(&name, alt->base, namelen);
+
+	/*
+	 * If the alternate object store is another repository, try the
+	 * standard layout with .git/modules/<name>/objects
+	 */
+	if (ends_with(name.buf, ".git/objects")) {
+		char *sm_alternate;
+		struct strbuf sb = STRBUF_INIT;
+		struct strbuf err = STRBUF_INIT;
+		strbuf_add(&sb, name.buf, name.len - strlen("objects"));
+		/*
+		 * We need to end the new path with '/' to mark it as a dir,
+		 * otherwise a submodule name containing '/' will be broken
+		 * as the last part of a missing submodule reference would
+		 * be taken as a file name.
+		 */
+		strbuf_addf(&sb, "modules/%s/", sas->submodule_name);
+
+		sm_alternate = compute_alternate_path(sb.buf, &err);
+		if (sm_alternate) {
+			string_list_append(sas->reference, xstrdup(sb.buf));
+			free(sm_alternate);
+		} else {
+			switch (sas->error_mode) {
+			case SUBMODULE_ALTERNATE_ERROR_DIE:
+				die(_("submodule '%s' cannot add alternate: %s"),
+				    sas->submodule_name, err.buf);
+			case SUBMODULE_ALTERNATE_ERROR_INFO:
+				fprintf(stderr, _("submodule '%s' cannot add alternate: %s"),
+					sas->submodule_name, err.buf);
+			case SUBMODULE_ALTERNATE_ERROR_IGNORE:
+				; /* nothing */
+			}
+		}
+		strbuf_release(&sb);
+	}
+
+	strbuf_release(&name);
+	return 0;
+}
+
+static void prepare_possible_alternates(const char *sm_name,
+		struct string_list *reference)
+{
+	char *sm_alternate = NULL, *error_strategy = NULL;
+	struct submodule_alternate_setup sas = SUBMODULE_ALTERNATE_SETUP_INIT;
+
+	git_config_get_string("submodule.alternateLocation", &sm_alternate);
+	if (!sm_alternate)
+		return;
+
+	git_config_get_string("submodule.alternateErrorStrategy", &error_strategy);
+
+	if (!error_strategy)
+		error_strategy = xstrdup("die");
+
+	sas.submodule_name = sm_name;
+	sas.reference = reference;
+	if (!strcmp(error_strategy, "die"))
+		sas.error_mode = SUBMODULE_ALTERNATE_ERROR_DIE;
+	else if (!strcmp(error_strategy, "info"))
+		sas.error_mode = SUBMODULE_ALTERNATE_ERROR_INFO;
+	else if (!strcmp(error_strategy, "ignore"))
+		sas.error_mode = SUBMODULE_ALTERNATE_ERROR_IGNORE;
+	else
+		die(_("Value '%s' for submodule.alternateErrorStrategy is not recognized"), error_strategy);
+
+	if (!strcmp(sm_alternate, "superproject"))
+		foreach_alt_odb(add_possible_reference_from_superproject, &sas);
+	else if (!strcmp(sm_alternate, "no"))
+		; /* do nothing */
+	else
+		die(_("Value '%s' for submodule.alternateLocation is not recognized"), sm_alternate);
+
+	free(sm_alternate);
+	free(error_strategy);
+}
+
 static int module_clone(int argc, const char **argv, const char *prefix)
 {
-	const char *name = NULL, *url = NULL;
-	const char *reference = NULL, *depth = NULL;
+	const char *name = NULL, *url = NULL, *depth = NULL;
 	int quiet = 0;
 	FILE *submodule_dot_git;
 	char *p, *path = NULL, *sm_gitdir;
 	struct strbuf rel_path = STRBUF_INIT;
 	struct strbuf sb = STRBUF_INIT;
+	struct string_list reference = STRING_LIST_INIT_NODUP;
 
 	struct option module_clone_options[] = {
 		OPT_STRING(0, "prefix", &prefix,
@@ -490,8 +593,8 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 		OPT_STRING(0, "url", &url,
 			   N_("string"),
 			   N_("url where to clone the submodule from")),
-		OPT_STRING(0, "reference", &reference,
-			   N_("string"),
+		OPT_STRING_LIST(0, "reference", &reference,
+			   N_("repo"),
 			   N_("reference repository")),
 		OPT_STRING(0, "depth", &depth,
 			   N_("string"),
@@ -527,7 +630,10 @@ static int module_clone(int argc, const char **argv, const char *prefix)
 	if (!file_exists(sm_gitdir)) {
 		if (safe_create_leading_directories_const(sm_gitdir) < 0)
 			die(_("could not create directory '%s'"), sm_gitdir);
-		if (clone_submodule(path, sm_gitdir, url, depth, reference, quiet))
+
+		prepare_possible_alternates(name, &reference);
+
+		if (clone_submodule(path, sm_gitdir, url, depth, &reference, quiet))
 			die(_("clone of '%s' into submodule path '%s' failed"),
 			    url, path);
 	} else {
@@ -579,7 +685,7 @@ struct submodule_update_clone {
 	/* configuration parameters which are passed on to the children */
 	int quiet;
 	int recommend_shallow;
-	const char *reference;
+	struct string_list references;
 	const char *depth;
 	const char *recursive_prefix;
 	const char *prefix;
@@ -595,7 +701,8 @@ struct submodule_update_clone {
 	int failed_clones_nr, failed_clones_alloc;
 };
 #define SUBMODULE_UPDATE_CLONE_INIT {0, MODULE_LIST_INIT, 0, \
-	SUBMODULE_UPDATE_STRATEGY_INIT, 0, -1, NULL, NULL, NULL, NULL, \
+	SUBMODULE_UPDATE_STRATEGY_INIT, 0, -1, STRING_LIST_INIT_DUP, \
+	NULL, NULL, NULL, \
 	STRING_LIST_INIT_DUP, 0, NULL, 0, 0}
 
 
@@ -705,8 +812,11 @@ static int prepare_to_clone_next_submodule(const struct cache_entry *ce,
 	argv_array_pushl(&child->args, "--path", sub->path, NULL);
 	argv_array_pushl(&child->args, "--name", sub->name, NULL);
 	argv_array_pushl(&child->args, "--url", url, NULL);
-	if (suc->reference)
-		argv_array_push(&child->args, suc->reference);
+	if (suc->references.nr) {
+		struct string_list_item *item;
+		for_each_string_list_item(item, &suc->references)
+			argv_array_pushl(&child->args, "--reference", item->string, NULL);
+	}
 	if (suc->depth)
 		argv_array_push(&child->args, suc->depth);
 
@@ -829,7 +939,7 @@ static int update_clone(int argc, const char **argv, const char *prefix)
 		OPT_STRING(0, "update", &update,
 			   N_("string"),
 			   N_("rebase, merge, checkout or none")),
-		OPT_STRING(0, "reference", &suc.reference, N_("repo"),
+		OPT_STRING_LIST(0, "reference", &suc.references, N_("repo"),
 			   N_("reference repository")),
 		OPT_STRING(0, "depth", &suc.depth, "<depth>",
 			   N_("Create a shallow clone truncated to the "

cache.h

@@ -1344,6 +1344,7 @@ extern struct alternate_object_database {
 } *alt_odb_list;
 extern void prepare_alt_odb(void);
 extern void read_info_alternates(const char * relative_base, int depth);
+extern char *compute_alternate_path(const char *path, struct strbuf *err);
 extern void add_to_alternates_file(const char *reference);
 typedef int alt_odb_fn(struct alternate_object_database *, void *);
 extern int foreach_alt_odb(alt_odb_fn, void*);

git-submodule.sh

@@ -576,7 +576,7 @@ cmd_update()
 		${wt_prefix:+--prefix "$wt_prefix"} \
 		${prefix:+--recursive-prefix "$prefix"} \
 		${update:+--update "$update"} \
-		${reference:+--reference "$reference"} \
+		${reference:+"$reference"} \
 		${depth:+--depth "$depth"} \
 		${recommend_shallow:+"$recommend_shallow"} \
 		${jobs:+$jobs} \