Merge branch 'kn/rev-list-missing-fix'

"git rev-list --missing" did not work for missing commit objects,
which has been corrected.

* kn/rev-list-missing-fix:
  rev-list: add commit object support in `--missing` option
  rev-list: move `show_commit()` to the bottom
  revision: rename bit to `do_not_die_on_missing_objects`

6 files changed, 155 insertions, 56 deletions

diff --git a/builtin/reflog.c b/builtin/reflog.c
index 21337292f5..6e490f83d5 100644
--- a/builtin/reflog.c
+++ b/builtin/reflog.c
@@ -298,7 +298,7 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix)
 		struct rev_info revs;
 
 		repo_init_revisions(the_repository, &revs, prefix);
-		revs.do_not_die_on_missing_tree = 1;
+		revs.do_not_die_on_missing_objects = 1;
 		revs.ignore_missing = 1;
 		revs.ignore_missing_links = 1;
 		if (verbose)
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
index ff715d6918..181353dcf5 100644
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@ -100,7 +100,48 @@ static off_t get_object_disk_usage(struct object *obj)
 	return size;
 }
 
-static void finish_commit(struct commit *commit);
+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 %s object '%s'",
+		    type_name(obj->type), oid_to_hex(&obj->oid));
+		return;
+
+	case MA_ALLOW_ANY:
+		return;
+
+	case MA_PRINT:
+		oidset_insert(&missing_objects, &obj->oid);
+		return;
+
+	case MA_ALLOW_PROMISOR:
+		if (is_promisor_object(&obj->oid))
+			return;
+		die("unexpected missing %s object '%s'",
+		    type_name(obj->type), oid_to_hex(&obj->oid));
+		return;
+
+	default:
+		BUG("unhandled missing_action");
+		return;
+	}
+}
+
+static void finish_commit(struct commit *commit)
+{
+	free_commit_list(commit->parents);
+	commit->parents = NULL;
+	free_commit_buffer(the_repository->parsed_objects,
+			   commit);
+}
+
 static void show_commit(struct commit *commit, void *data)
 {
 	struct rev_list_info *info = data;
@@ -108,6 +149,12 @@ static void show_commit(struct commit *commit, void *data)
 
 	display_progress(progress, ++progress_counter);
 
+	if (revs->do_not_die_on_missing_objects &&
+	    oidset_contains(&revs->missing_commits, &commit->object.oid)) {
+		finish_object__ma(&commit->object);
+		return;
+	}
+
 	if (show_disk_usage)
 		total_disk_usage += get_object_disk_usage(&commit->object);
 
@@ -219,48 +266,6 @@ static void show_commit(struct commit *commit, void *data)
 	finish_commit(commit);
 }
 
-static void finish_commit(struct commit *commit)
-{
-	free_commit_list(commit->parents);
-	commit->parents = NULL;
-	free_commit_buffer(the_repository->parsed_objects,
-			   commit);
-}
-
-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 %s object '%s'",
-		    type_name(obj->type), oid_to_hex(&obj->oid));
-		return;
-
-	case MA_ALLOW_ANY:
-		return;
-
-	case MA_PRINT:
-		oidset_insert(&missing_objects, &obj->oid);
-		return;
-
-	case MA_ALLOW_PROMISOR:
-		if (is_promisor_object(&obj->oid))
-			return;
-		die("unexpected missing %s object '%s'",
-		    type_name(obj->type), oid_to_hex(&obj->oid));
-		return;
-
-	default:
-		BUG("unhandled missing_action");
-		return;
-	}
-}
-
 static int finish_object(struct object *obj, const char *name UNUSED,
 			 void *cb_data)
 {
@@ -561,7 +566,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 	}
 
 	if (arg_missing_action)
-		revs.do_not_die_on_missing_tree = 1;
+		revs.do_not_die_on_missing_objects = 1;
 
 	argc = setup_revisions(argc, argv, &revs, &s_r_opt);
 
diff --git a/list-objects.c b/list-objects.c
index c25c72b32c..f4e1104b56 100644
--- a/list-objects.c
+++ b/list-objects.c
@@ -177,7 +177,7 @@ static void process_tree(struct traversal_context *ctx,
 		    is_promisor_object(&obj->oid))
 			return;
 
-		if (!revs->do_not_die_on_missing_tree)
+		if (!revs->do_not_die_on_missing_objects)
 			die("bad tree object %s", oid_to_hex(&obj->oid));
 	}
 
@@ -389,6 +389,9 @@ static void do_traverse(struct traversal_context *ctx)
 		 */
 		if (!ctx->revs->tree_objects)
 			; /* do not bother loading tree */
+		else if (ctx->revs->do_not_die_on_missing_objects &&
+			 oidset_contains(&ctx->revs->missing_commits, &commit->object.oid))
+			;
 		else if (repo_get_commit_tree(the_repository, commit)) {
 			struct tree *tree = repo_get_commit_tree(the_repository,
 								 commit);
diff --git a/revision.c b/revision.c
index 219dc76716..00d5c29bfc 100644
--- a/revision.c
+++ b/revision.c
@@ -6,6 +6,7 @@
 #include "object-name.h"
 #include "object-file.h"
 #include "object-store-ll.h"
+#include "oidset.h"
 #include "tag.h"
 #include "blob.h"
 #include "tree.h"
@@ -1112,6 +1113,9 @@ static int process_parents(struct rev_info *revs, struct commit *commit,
 
 	if (commit->object.flags & ADDED)
 		return 0;
+	if (revs->do_not_die_on_missing_objects &&
+	    oidset_contains(&revs->missing_commits, &commit->object.oid))
+		return 0;
 	commit->object.flags |= ADDED;
 
 	if (revs->include_check &&
@@ -1168,7 +1172,8 @@ static int process_parents(struct rev_info *revs, struct commit *commit,
 	for (parent = commit->parents; parent; parent = parent->next) {
 		struct commit *p = parent->item;
 		int gently = revs->ignore_missing_links ||
-			     revs->exclude_promisor_objects;
+			     revs->exclude_promisor_objects ||
+			     revs->do_not_die_on_missing_objects;
 		if (repo_parse_commit_gently(revs->repo, p, gently) < 0) {
 			if (revs->exclude_promisor_objects &&
 			    is_promisor_object(&p->object.oid)) {
@@ -1176,7 +1181,11 @@ static int process_parents(struct rev_info *revs, struct commit *commit,
 					break;
 				continue;
 			}
-			return -1;
+
+			if (revs->do_not_die_on_missing_objects)
+				oidset_insert(&revs->missing_commits, &p->object.oid);
+			else
+				return -1; /* corrupt repository */
 		}
 		if (revs->sources) {
 			char **slot = revision_sources_at(revs->sources, p);
@@ -3109,6 +3118,7 @@ void release_revisions(struct rev_info *revs)
 	clear_decoration(&revs->merge_simplification, free);
 	clear_decoration(&revs->treesame, free);
 	line_log_free(revs);
+	oidset_clear(&revs->missing_commits);
 }
 
 static void add_child(struct rev_info *revs, struct commit *parent, struct commit *child)
@@ -3800,6 +3810,8 @@ int prepare_revision_walk(struct rev_info *revs)
 				       FOR_EACH_OBJECT_PROMISOR_ONLY);
 	}
 
+	oidset_init(&revs->missing_commits, 0);
+
 	if (!revs->reflog_info)
 		prepare_to_use_bloom_filter(revs);
 	if (!revs->unsorted_input)
diff --git a/revision.h b/revision.h
index 50091bbd13..94c43138bc 100644
--- a/revision.h
+++ b/revision.h
@@ -4,6 +4,7 @@
 #include "commit.h"
 #include "grep.h"
 #include "notes.h"
+#include "oidset.h"
 #include "pretty.h"
 #include "diff.h"
 #include "commit-slab-decl.h"
@@ -212,18 +213,19 @@ struct rev_info {
 
 			/*
 			 * Blobs are shown without regard for their existence.
-			 * But not so for trees: unless exclude_promisor_objects
+			 * But not so for trees/commits: unless exclude_promisor_objects
 			 * is set and the tree in question is a promisor object;
 			 * OR ignore_missing_links is set, the revision walker
-			 * dies with a "bad tree object HASH" message when
-			 * encountering a missing tree. For callers that can
-			 * handle missing trees and want them to be filterable
+			 * dies with a "bad <type> object HASH" message when
+			 * encountering a missing object. For callers that can
+			 * handle missing trees/commits and want them to be filterable
 			 * and showable, set this to true. The revision walker
-			 * will filter and show such a missing tree as usual,
-			 * but will not attempt to recurse into this tree
-			 * object.
+			 * will filter and show such a missing object as usual,
+			 * but will not attempt to recurse into this tree/commit
+			 * object. The revision walker will also set the MISSING
+			 * flag for such objects.
 			 */
-			do_not_die_on_missing_tree:1,
+			do_not_die_on_missing_objects:1,
 
 			/* for internal use only */
 			exclude_promisor_objects:1;
@@ -372,6 +374,9 @@ struct rev_info {
 
 	/* Location where temporary objects for remerge-diff are written. */
 	struct tmp_objdir *remerge_objdir;
+
+	/* Missing commits to be tracked without failing traversal. */
+	struct oidset missing_commits;
 };
 
 /**
diff --git a/t/t6022-rev-list-missing.sh b/t/t6022-rev-list-missing.sh
new file mode 100755
index 0000000000..40265a4f66
--- /dev/null
+++ b/t/t6022-rev-list-missing.sh
@@ -0,0 +1,74 @@
+#!/bin/sh
+
+test_description='handling of missing objects in rev-list'
+
+TEST_PASSES_SANITIZE_LEAK=true
+. ./test-lib.sh
+
+# We setup the repository with two commits, this way HEAD is always
+# available and we can hide commit 1.
+test_expect_success 'create repository and alternate directory' '
+	test_commit 1 &&
+	test_commit 2 &&
+	test_commit 3
+'
+
+for obj in "HEAD~1" "HEAD~1^{tree}" "HEAD:1.t"
+do
+	test_expect_success "rev-list --missing=error fails with missing object $obj" '
+		oid="$(git rev-parse $obj)" &&
+		path=".git/objects/$(test_oid_to_path $oid)" &&
+
+		mv "$path" "$path.hidden" &&
+		test_when_finished "mv $path.hidden $path" &&
+
+		test_must_fail git rev-list --missing=error --objects \
+			--no-object-names HEAD
+	'
+done
+
+for obj in "HEAD~1" "HEAD~1^{tree}" "HEAD:1.t"
+do
+	for action in "allow-any" "print"
+	do
+		test_expect_success "rev-list --missing=$action with missing $obj" '
+			oid="$(git rev-parse $obj)" &&
+			path=".git/objects/$(test_oid_to_path $oid)" &&
+
+			# Before the object is made missing, we use rev-list to
+			# get the expected oids.
+			git rev-list --objects --no-object-names \
+				HEAD ^$obj >expect.raw &&
+
+			# Blobs are shared by all commits, so evethough a commit/tree
+			# might be skipped, its blob must be accounted for.
+			if [ $obj != "HEAD:1.t" ]; then
+				echo $(git rev-parse HEAD:1.t) >>expect.raw &&
+				echo $(git rev-parse HEAD:2.t) >>expect.raw
+			fi &&
+
+			mv "$path" "$path.hidden" &&
+			test_when_finished "mv $path.hidden $path" &&
+
+			git rev-list --missing=$action --objects --no-object-names \
+				HEAD >actual.raw &&
+
+			# When the action is to print, we should also add the missing
+			# oid to the expect list.
+			case $action in
+			allow-any)
+				;;
+			print)
+				grep ?$oid actual.raw &&
+				echo ?$oid >>expect.raw
+				;;
+			esac &&
+
+			sort actual.raw >actual &&
+			sort expect.raw >expect &&
+			test_cmp expect actual
+		'
+	done
+done
+
+test_done