The `--missing` object option in rev-list currently works only with missing blobs/trees. For missing commits the revision walker fails with a fatal error. Let's extend the functionality of `--missing` option to also support commit objects. This is done by adding a new `MISSING` flag that the revision walker sets whenever it encounters a missing tree/commit. The revision walker will now continue the traversal and call `show_commit()` even for missing commits. In rev-list we can then check for this flag and call the existing code for parsing `--missing` objects. A scenario where this option would be used is to find the boundary objects between different object directories. Consider a repository with a main object directory (GIT_OBJECT_DIRECTORY) and one or more alternate object directories (GIT_ALTERNATE_OBJECT_DIRECTORIES). In such a repository, using the `--missing=print` option while disabling the alternate object directory allows us to find the boundary objects between the main and alternate object directory. Signed-off-by: Karthik Nayak <karthik.188@xxxxxxxxx> --- builtin/rev-list.c | 6 +++ list-objects.c | 2 +- object.h | 4 +- revision.c | 11 ++++-- revision.h | 2 + t/t6022-rev-list-missing.sh | 74 +++++++++++++++++++++++++++++++++++++ 6 files changed, 93 insertions(+), 6 deletions(-) create mode 100755 t/t6022-rev-list-missing.sh diff --git a/builtin/rev-list.c b/builtin/rev-list.c index 98542e8b3c..604ae01d0c 100644 --- a/builtin/rev-list.c +++ b/builtin/rev-list.c @@ -149,6 +149,12 @@ static void show_commit(struct commit *commit, void *data) display_progress(progress, ++progress_counter); + if (revs->do_not_die_on_missing_objects && + commit->object.flags & MISSING) { + finish_object__ma(&commit->object); + return; + } + if (show_disk_usage) total_disk_usage += get_object_disk_usage(&commit->object); diff --git a/list-objects.c b/list-objects.c index 47296dff2f..60c5533721 100644 --- a/list-objects.c +++ b/list-objects.c @@ -387,7 +387,7 @@ static void do_traverse(struct traversal_context *ctx) * an uninteresting boundary commit may not have its tree * parsed yet, but we are not going to show them anyway */ - if (!ctx->revs->tree_objects) + if (!ctx->revs->tree_objects || commit->object.flags & MISSING) ; /* do not bother loading tree */ else if (repo_get_commit_tree(the_repository, commit)) { struct tree *tree = repo_get_commit_tree(the_repository, diff --git a/object.h b/object.h index 114d45954d..b76830fce1 100644 --- a/object.h +++ b/object.h @@ -62,7 +62,7 @@ void object_array_init(struct object_array *array); /* * object flag allocation: - * revision.h: 0---------10 15 23------27 + * revision.h: 0---------10 15 22------28 * fetch-pack.c: 01 67 * negotiator/default.c: 2--5 * walker.c: 0-2 @@ -82,7 +82,7 @@ void object_array_init(struct object_array *array); * builtin/show-branch.c: 0-------------------------------------------26 * builtin/unpack-objects.c: 2021 */ -#define FLAG_BITS 28 +#define FLAG_BITS 29 #define TYPE_BITS 3 diff --git a/revision.c b/revision.c index 219dc76716..8100806068 100644 --- a/revision.c +++ b/revision.c @@ -1110,7 +1110,7 @@ static int process_parents(struct rev_info *revs, struct commit *commit, struct commit_list *parent = commit->parents; unsigned pass_flags; - if (commit->object.flags & ADDED) + if (commit->object.flags & (ADDED | MISSING)) return 0; commit->object.flags |= ADDED; @@ -1168,7 +1168,8 @@ 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 +1177,11 @@ static int process_parents(struct rev_info *revs, struct commit *commit, break; continue; } - return -1; + + if (!revs->do_not_die_on_missing_objects) + return -1; + else + p->object.flags |= MISSING; } if (revs->sources) { char **slot = revision_sources_at(revs->sources, p); diff --git a/revision.h b/revision.h index c73c92ef40..d3c1ca0f4e 100644 --- a/revision.h +++ b/revision.h @@ -53,6 +53,8 @@ #define ANCESTRY_PATH (1u<<27) #define ALL_REV_FLAGS (((1u<<11)-1) | NOT_USER_GIVEN | TRACK_LINEAR | PULL_MERGE) +#define MISSING (1u<<28) + #define DECORATE_SHORT_REFS 1 #define DECORATE_FULL_REFS 2 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 -- 2.42.0