bundle: create filtered bundles
A previous change allowed Git to parse bundles with the 'filter' capability. Now, teach Git to create bundles with this option. Some rearranging of code is required to get the option parsing in the correct spot. There are now two reasons why we might need capabilities (a new hash algorithm or an object filter) so that is pulled out into a place where we can check both at the same time. The --filter option is parsed as part of setup_revisions(), but it expected the --objects flag, too. That flag is somewhat implied by 'git bundle' because it creates a pack-file walking objects, but there is also a walk that walks the revision range expecting only commits. Make this parsing work by setting 'revs.tree_objects' and 'revs.blob_objects' before the call to setup_revisions(). Signed-off-by: Derrick Stolee <derrickstolee@github.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Derrick Stolee committed
Mar 9, 2022 at 16:01 UTC
f18b512bbba8ee508fec64698f581920bfa5b46d
2 files changed
+90
-11
bundle.c
+42
-11
@@ -332,6 +332,9 @@ static int write_pack_data(int bundle_fd, struct rev_info *revs, struct strvec *
332
"--stdout", "--thin", "--delta-base-offset",
333
NULL);
334
strvec_pushv(&pack_objects.args, pack_options->v);
335
+ if (revs->filter.choice)
336
+ strvec_pushf(&pack_objects.args, "--filter=%s",
337
+ list_objects_filter_spec(&revs->filter));
338
pack_objects.in = -1;
339
pack_objects.out = bundle_fd;
340
pack_objects.git_cmd = 1;
@@ -499,10 +502,37 @@ int create_bundle(struct repository *r, const char *path,
502
int bundle_to_stdout;
503
int ref_count = 0;
504
struct rev_info revs, revs_copy;
502
- int min_version = the_hash_algo == &hash_algos[GIT_HASH_SHA1] ? 2 : 3;
505
+ int min_version = 2;
506
struct bundle_prerequisites_info bpi;
507
int i;
508
509
+ /* init revs to list objects for pack-objects later */
510
+ save_commit_buffer = 0;
511
+ repo_init_revisions(r, &revs, NULL);
512
+
513
+ /*
514
+ * Pre-initialize the '--objects' flag so we can parse a
515
+ * --filter option successfully.
516
+ */
517
+ revs.tree_objects = revs.blob_objects = 1;
518
+
519
+ argc = setup_revisions(argc, argv, &revs, NULL);
520
+
521
+ /*
522
+ * Reasons to require version 3:
523
+ *
524
+ * 1. @object-format is required because our hash algorithm is not
525
+ * SHA1.
526
+ * 2. @filter is required because we parsed an object filter.
527
+ */
528
+ if (the_hash_algo != &hash_algos[GIT_HASH_SHA1] || revs.filter.choice)
529
+ min_version = 3;
530
+
531
+ if (argc > 1) {
532
+ error(_("unrecognized argument: %s"), argv[1]);
533
+ goto err;
534
+ }
535
+
536
bundle_to_stdout = !strcmp(path, "-");
537
if (bundle_to_stdout)
538
bundle_fd = 1;
@@ -525,17 +555,14 @@ int create_bundle(struct repository *r, const char *path,
555
write_or_die(bundle_fd, capability, strlen(capability));
556
write_or_die(bundle_fd, the_hash_algo->name, strlen(the_hash_algo->name));
557
write_or_die(bundle_fd, "\n", 1);
528
- }
529
-
530
- /* init revs to list objects for pack-objects later */
531
- save_commit_buffer = 0;
532
- repo_init_revisions(r, &revs, NULL);
558
534
- argc = setup_revisions(argc, argv, &revs, NULL);
535
-
536
- if (argc > 1) {
537
- error(_("unrecognized argument: %s"), argv[1]);
538
- goto err;
559
+ if (revs.filter.choice) {
560
+ const char *value = expand_list_objects_filter_spec(&revs.filter);
561
+ capability = "@filter=";
562
+ write_or_die(bundle_fd, capability, strlen(capability));
563
+ write_or_die(bundle_fd, value, strlen(value));
564
+ write_or_die(bundle_fd, "\n", 1);
565
+ }
566
}
567
568
/* save revs.pending in revs_copy for later use */
@@ -558,6 +585,10 @@ int create_bundle(struct repository *r, const char *path,
585
bpi.fd = bundle_fd;
586
bpi.pending = &revs_copy.pending;
587
588
+ /*
589
+ * Remove any object walking here. We only care about commits and
590
+ * tags here. The revs_copy has the right instances of these values.
591
+ */
592
revs.blob_objects = revs.tree_objects = 0;
593
traverse_commit_list(&revs, write_bundle_prerequisites, NULL, &bpi);
594
object_array_remove_duplicates(&revs_copy.pending);
t/t6020-bundle-misc.sh
+48
@@ -487,4 +487,52 @@ test_expect_success 'unfiltered bundle with --objects' '
487
test_cmp expect actual
488
'
489
490
+for filter in "blob:none" "tree:0" "tree:1" "blob:limit=100"
491
+do
492
+ test_expect_success "filtered bundle: $filter" '
493
+ test_when_finished rm -rf .git/objects/pack cloned unbundled &&
494
+ git bundle create partial.bdl \
495
+ --all \
496
+ --filter=$filter &&
497
+
498
+ git bundle verify partial.bdl >unfiltered &&
499
+ make_user_friendly_and_stable_output <unfiltered >actual &&
500
+
501
+ cat >expect <<-EOF &&
502
+ The bundle contains these 10 refs:
503
+ <COMMIT-P> refs/heads/main
504
+ <COMMIT-N> refs/heads/release
505
+ <COMMIT-D> refs/heads/topic/1
506
+ <COMMIT-H> refs/heads/topic/2
507
+ <COMMIT-D> refs/pull/1/head
508
+ <COMMIT-G> refs/pull/2/head
509
+ <TAG-1> refs/tags/v1
510
+ <TAG-2> refs/tags/v2
511
+ <TAG-3> refs/tags/v3
512
+ <COMMIT-P> HEAD
513
+ The bundle uses this filter: $filter
514
+ The bundle records a complete history.
515
+ EOF
516
+ test_cmp expect actual &&
517
+
518
+ test_config uploadpack.allowfilter 1 &&
519
+ test_config uploadpack.allowanysha1inwant 1 &&
520
+ git clone --no-local --filter=$filter --bare "file://$(pwd)" cloned &&
521
+
522
+ git init unbundled &&
523
+ git -C unbundled bundle unbundle ../partial.bdl >ref-list.txt &&
524
+
525
+ # Count the same number of reachable objects.
526
+ reflist=$(git for-each-ref --format="%(objectname)") &&
527
+ git rev-list --objects --filter=$filter --missing=allow-any \
528
+ $reflist >expect &&
529
+ for repo in cloned unbundled
530
+ do
531
+ git -C $repo rev-list --objects --missing=allow-any \
532
+ $reflist >actual &&
533
+ test_cmp expect actual || return 1
534
+ done
535
+ '
536
+done
537
+
538
test_done