rev-list: support termination at promisor objects

Teach rev-list to support termination of an object traversal at any
object from a promisor remote (whether one that the local repo also has,
or one that the local repo knows about because it has another promisor
object that references it).

This will be used subsequently in gc and in the connectivity check used
by fetch.

For efficiency, if an object is referenced by a promisor object, and is
in the local repo only as a non-promisor object, object traversal will
not stop there. This is to avoid building the list of promisor object
references.

(In list-objects.c, the case where obj is NULL in process_blob() and
process_tree() do not need to be changed because those happen only when
there is a conflict between the expected type and the existing object.
If the object doesn't exist, an object will be synthesized, which is
fine.)

Signed-off-by: Jonathan Tan <jonathantanmy@google.com>
Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

builtin/rev-list.c

@@ -15,6 +15,7 @@
 #include "progress.h"
 #include "reflog-walk.h"
 #include "oidset.h"
+#include "packfile.h"
 
 static const char rev_list_usage[] =
 "git rev-list [OPTION] <commit-id>... [ -- paths... ]\n"
@@ -67,6 +68,7 @@ enum missing_action {
 	MA_ERROR = 0,    /* fail if any missing objects are encountered */
 	MA_ALLOW_ANY,    /* silently allow ALL missing objects */
 	MA_PRINT,        /* print ALL missing objects in special section */
+	MA_ALLOW_PROMISOR, /* silently allow all missing PROMISOR objects */
 };
 static enum missing_action arg_missing_action;
 
@@ -197,6 +199,12 @@ static void finish_commit(struct commit *commit, void *data)
 
 static inline void finish_object__ma(struct object *obj)
 {
+	/*
+	 * Whether or not we try to dynamically fetch missing objects
+	 * from the server, we currently DO NOT have the object.  We
+	 * can either print, allow (ignore), or conditionally allow
+	 * (ignore) them.
+	 */
 	switch (arg_missing_action) {
 	case MA_ERROR:
 		die("missing blob object '%s'", oid_to_hex(&obj->oid));
@@ -209,25 +217,36 @@ static inline void finish_object__ma(struct object *obj)
 		oidset_insert(&missing_objects, &obj->oid);
 		return;
 
+	case MA_ALLOW_PROMISOR:
+		if (is_promisor_object(&obj->oid))
+			return;
+		die("unexpected missing blob object '%s'",
+		    oid_to_hex(&obj->oid));
+		return;
+
 	default:
 		BUG("unhandled missing_action");
 		return;
 	}
 }
 
-static void finish_object(struct object *obj, const char *name, void *cb_data)
+static int finish_object(struct object *obj, const char *name, void *cb_data)
 {
 	struct rev_list_info *info = cb_data;
-	if (obj->type == OBJ_BLOB && !has_object_file(&obj->oid))
+	if (obj->type == OBJ_BLOB && !has_object_file(&obj->oid)) {
 		finish_object__ma(obj);
+		return 1;
+	}
 	if (info->revs->verify_objects && !obj->parsed && obj->type != OBJ_COMMIT)
 		parse_object(&obj->oid);
+	return 0;
 }
 
 static void show_object(struct object *obj, const char *name, void *cb_data)
 {
 	struct rev_list_info *info = cb_data;
-	finish_object(obj, name, cb_data);
+	if (finish_object(obj, name, cb_data))
+		return;
 	display_progress(progress, ++progress_counter);
 	if (info->flags & REV_LIST_QUIET)
 		return;
@@ -315,11 +334,19 @@ static inline int parse_missing_action_value(const char *value)
 
 	if (!strcmp(value, "allow-any")) {
 		arg_missing_action = MA_ALLOW_ANY;
+		fetch_if_missing = 0;
 		return 1;
 	}
 
 	if (!strcmp(value, "print")) {
 		arg_missing_action = MA_PRINT;
+		fetch_if_missing = 0;
+		return 1;
+	}
+
+	if (!strcmp(value, "allow-promisor")) {
+		arg_missing_action = MA_ALLOW_PROMISOR;
+		fetch_if_missing = 0;
 		return 1;
 	}
 
@@ -344,6 +371,35 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 	init_revisions(&revs, prefix);
 	revs.abbrev = DEFAULT_ABBREV;
 	revs.commit_format = CMIT_FMT_UNSPECIFIED;
+
+	/*
+	 * Scan the argument list before invoking setup_revisions(), so that we
+	 * know if fetch_if_missing needs to be set to 0.
+	 *
+	 * "--exclude-promisor-objects" acts as a pre-filter on missing objects
+	 * by not crossing the boundary from realized objects to promisor
+	 * objects.
+	 *
+	 * Let "--missing" to conditionally set fetch_if_missing.
+	 */
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+		if (!strcmp(arg, "--exclude-promisor-objects")) {
+			fetch_if_missing = 0;
+			revs.exclude_promisor_objects = 1;
+			break;
+		}
+	}
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+		if (skip_prefix(arg, "--missing=", &arg)) {
+			if (revs.exclude_promisor_objects)
+				die(_("cannot combine --exclude-promisor-objects and --missing"));
+			if (parse_missing_action_value(arg))
+				break;
+		}
+	}
+
 	argc = setup_revisions(argc, argv, &revs, NULL);
 
 	memset(&info, 0, sizeof(info));
@@ -412,9 +468,10 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			continue;
 		}
 
-		if (skip_prefix(arg, "--missing=", &arg) &&
-		    parse_missing_action_value(arg))
-			continue;
+		if (!strcmp(arg, "--exclude-promisor-objects"))
+			continue; /* already handled above */
+		if (skip_prefix(arg, "--missing=", &arg))
+			continue; /* already handled above */
 
 		usage(rev_list_usage);