[v4,02/11] commit-reach(repo_in_merge_bases_many): optionally expect missing commits

Commit Message

Johannes Schindelin Feb. 28, 2024, 9:44 a.m. UTC

From: Johannes Schindelin <[e-mail]>

Currently this function treats unrelated commit histories the same way
as commit histories with missing commit objects.

Typically, missing commit objects constitute a corrupt repository,
though, and should be reported as such. The next commits will make it
so, but there is one exception: In `git fetch --update-shallow` we
_expect_ commit objects to be missing, and we do want to treat the
now-incomplete commit histories as unrelated.

To allow for that, let's introduce an additional parameter that is
passed to `repo_in_merge_bases_many()` to trigger this behavior, and use
it in the two callers in `shallow.c`.

This commit changes behavior slightly: unless called from the
`shallow.c` functions that set the `ignore_missing_commits` bit, any
non-existing tip commit that is passed to `repo_in_merge_bases_many()`
will now result in an error.

Note: When encountering missing commits while traversing the commit
history in search for merge bases, with this commit there won't be a
change in behavior just yet, their children will still be interpreted as
root commits. This bug will get fixed by follow-up commits.

Signed-off-by: Johannes Schindelin <[e-mail]>
---
 commit-reach.c        | 9 +++++----
 commit-reach.h        | 3 ++-
 remote.c              | 2 +-
 shallow.c             | 5 +++--
 t/helper/test-reach.c | 2 +-
 5 files changed, 12 insertions(+), 9 deletions(-)

Patch

diff --git a/commit-reach.c b/commit-reach.c
index 7ea916f9ebd..5c1b5256598 100644
--- a/commit-reach.c
+++ b/commit-reach.c
@@ -467,7 +467,7 @@  int repo_is_descendant_of(struct repository *r,
 
 			other = with_commit->item;
 			with_commit = with_commit->next;
-			if (repo_in_merge_bases_many(r, other, 1, &commit))
+			if (repo_in_merge_bases_many(r, other, 1, &commit, 0))
 				return 1;
 		}
 		return 0;
@@ -478,17 +478,18 @@  int repo_is_descendant_of(struct repository *r,
  * Is "commit" an ancestor of one of the "references"?
  */
 int repo_in_merge_bases_many(struct repository *r, struct commit *commit,
-			     int nr_reference, struct commit **reference)
+			     int nr_reference, struct commit **reference,
+			     int ignore_missing_commits)
 {
 	struct commit_list *bases;
 	int ret = 0, i;
 	timestamp_t generation, max_generation = GENERATION_NUMBER_ZERO;
 
 	if (repo_parse_commit(r, commit))
-		return ret;
+		return ignore_missing_commits ? 0 : -1;
 	for (i = 0; i < nr_reference; i++) {
 		if (repo_parse_commit(r, reference[i]))
-			return ret;
+			return ignore_missing_commits ? 0 : -1;
 
 		generation = commit_graph_generation(reference[i]);
 		if (generation > max_generation)
diff --git a/commit-reach.h b/commit-reach.h
index 35c4da49481..68f81549a44 100644
--- a/commit-reach.h
+++ b/commit-reach.h
@@ -30,7 +30,8 @@  int repo_in_merge_bases(struct repository *r,
 			struct commit *reference);
 int repo_in_merge_bases_many(struct repository *r,
 			     struct commit *commit,
-			     int nr_reference, struct commit **reference);
+			     int nr_reference, struct commit **reference,
+			     int ignore_missing_commits);
 
 /*
  * Takes a list of commits and returns a new list where those
diff --git a/remote.c b/remote.c
index abb24822beb..763c80f4a7d 100644
--- a/remote.c
+++ b/remote.c
@@ -2675,7 +2675,7 @@  static int is_reachable_in_reflog(const char *local, const struct ref *remote)
 		if (MERGE_BASES_BATCH_SIZE < size)
 			size = MERGE_BASES_BATCH_SIZE;
 
-		if ((ret = repo_in_merge_bases_many(the_repository, commit, size, chunk)))
+		if ((ret = repo_in_merge_bases_many(the_repository, commit, size, chunk, 0)))
 			break;
 	}
 
diff --git a/shallow.c b/shallow.c
index ac728cdd778..dfcc1f86a7f 100644
--- a/shallow.c
+++ b/shallow.c
@@ -797,7 +797,7 @@  static void post_assign_shallow(struct shallow_info *info,
 		for (j = 0; j < bitmap_nr; j++)
 			if (bitmap[0][j] &&
 			    /* Step 7, reachability test at commit level */
-			    !repo_in_merge_bases_many(the_repository, c, ca.nr, ca.commits)) {
+			    !repo_in_merge_bases_many(the_repository, c, ca.nr, ca.commits, 1)) {
 				update_refstatus(ref_status, info->ref->nr, *bitmap);
 				dst++;
 				break;
@@ -828,7 +828,8 @@  int delayed_reachability_test(struct shallow_info *si, int c)
 		si->reachable[c] = repo_in_merge_bases_many(the_repository,
 							    commit,
 							    si->nr_commits,
-							    si->commits);
+							    si->commits,
+							    1);
 		si->need_reachability_test[c] = 0;
 	}
 	return si->reachable[c];
diff --git a/t/helper/test-reach.c b/t/helper/test-reach.c
index 3e173399a00..aa816e168ea 100644
--- a/t/helper/test-reach.c
+++ b/t/helper/test-reach.c
@@ -113,7 +113,7 @@  int cmd__reach(int ac, const char **av)
 		       repo_in_merge_bases(the_repository, A, B));
 	else if (!strcmp(av[1], "in_merge_bases_many"))
 		printf("%s(A,X):%d\n", av[1],
-		       repo_in_merge_bases_many(the_repository, A, X_nr, X_array));
+		       repo_in_merge_bases_many(the_repository, A, X_nr, X_array, 0));
 	else if (!strcmp(av[1], "is_descendant_of"))
 		printf("%s(A,X):%d\n", av[1], repo_is_descendant_of(r, A, X));
 	else if (!strcmp(av[1], "get_merge_bases_many")) {