commit-graph.c: introduce '--[no-]check-oids'

ttaylorr · gitster · commit 7a9ce0269bc0 · 2020-04-15T09:20:34.000-07:00
When operating on a stream of commit OIDs on stdin, 'git commit-graph
write' checks that each OID refers to an object that is indeed a commit.
This is convenient to make sure that the given input is well-formed, but
can sometimes be undesirable.

For example, server operators may wish to feed the refnames that were
updated during a push to 'git commit-graph write --input=stdin-commits',
and silently discard refs that don't point at commits. This can be done
by combing the output of 'git for-each-ref' with '--format
%(*objecttype)', but this requires opening up a potentially large number
of objects.  Instead, it is more convenient to feed the updated refs to
the commit-graph machinery, and let it throw out refs that don't point
to commits.

Introduce '--[no-]check-oids' to make such a behavior possible. With
'--check-oids' (the default behavior to retain backwards compatibility),
'git commit-graph write' will barf on a non-commit line in its input.
With 'no-check-oids', such lines will be silently ignored, making the
above possible by specifying this option.

No matter which is supplied, 'git commit-graph write' retains the
behavior from the previous commit of rejecting non-OID inputs like
"HEAD" and "refs/heads/foo" as before.

Signed-off-by: Taylor Blau &lt;me@ttaylorr.com&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/Documentation/git-commit-graph.txt b/Documentation/git-commit-graph.txt
@@ -82,6 +82,11 @@ tip with the previous tip.
 Finally, if `--expire-time=<datetime>` is not specified, let `datetime`
 be the current time. After writing the split commit-graph, delete all
 unused commit-graph whose modified times are older than `datetime`.
++
+The `--[no-]check-oids` option decides whether or not OIDs are required
+to be commits. By default, `--check-oids` is implied, generating an
+error on non-commit objects. If `--no-check-oids` is given, non-commits
+are silently discarded.
 
 'verify'::
 
diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
@@ -11,7 +11,7 @@ static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph verify [--object-dir <objdir>] [--shallow] [--[no-]progress]"),
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--[no-]progress] <split options>"),
+	   "[--[no-]progress] [--[no-]check-oids] <split options>"),
 	NULL
 };
 
@@ -23,7 +23,7 @@ static const char * const builtin_commit_graph_verify_usage[] = {
 static const char * const builtin_commit_graph_write_usage[] = {
 	N_("git commit-graph write [--object-dir <objdir>] [--append] "
 	   "[--split[=<strategy>]] [--reachable|--stdin-packs|--stdin-commits] "
-	   "[--[no-]progress] <split options>"),
+	   "[--[no-]progress] [--[no-]check-oids] <split options>"),
 	NULL
 };
 
@@ -36,6 +36,7 @@ static struct opts_commit_graph {
 	int split;
 	int shallow;
 	int progress;
+	int check_oids;
 } opts;
 
 static struct object_directory *find_odb(struct repository *r,
@@ -160,6 +161,8 @@ static int graph_write(int argc, const char **argv)
 			N_("allow writing an incremental commit-graph file"),
 			PARSE_OPT_OPTARG | PARSE_OPT_NONEG,
 			write_option_parse_split),
+		OPT_BOOL(0, "check-oids", &opts.check_oids,
+			N_("require OIDs to be commits")),
 		OPT_INTEGER(0, "max-commits", &split_opts.max_commits,
 			N_("maximum number of commits in a non-base split commit-graph")),
 		OPT_INTEGER(0, "size-multiple", &split_opts.size_multiple,
@@ -170,6 +173,7 @@ static int graph_write(int argc, const char **argv)
 	};
 
 	opts.progress = isatty(2);
+	opts.check_oids = 1;
 	split_opts.size_multiple = 2;
 	split_opts.max_commits = 0;
 	split_opts.expire_time = 0;
@@ -224,7 +228,8 @@ static int graph_write(int argc, const char **argv)
 
 				oidset_insert(&commits, &oid);
 			}
-			flags |= COMMIT_GRAPH_WRITE_CHECK_OIDS;
+			if (opts.check_oids)
+				flags |= COMMIT_GRAPH_WRITE_CHECK_OIDS;
 		}
 
 		UNLEAK(buf);
diff --git a/commit-graph.c b/commit-graph.c
@@ -145,7 +145,7 @@ static int verify_commit_graph_lite(struct commit_graph *g)
 	 *
 	 * There should only be very basic checks here to ensure that
 	 * we don't e.g. segfault in fill_commit_in_graph(), but
-	 * because this is a very hot codepath nothing that e.g. loops
+	 e because this is a very hot codepath nothing that e.g. loops
 	 * over g->num_commits, or runs a checksum on the commit-graph
 	 * itself.
 	 */
diff --git a/t/t5318-commit-graph.sh b/t/t5318-commit-graph.sh
@@ -49,6 +49,34 @@ test_expect_success 'exit with correct error on bad input to --stdin-commits' '
 	test_i18ngrep "invalid commit object id" stderr
 '
 
+graph_expect_commits() {
+	test-tool read-graph >got
+	if ! grep "num_commits: $1" got
+	then
+		echo "graph_expect_commits: expected $1 commit(s), got:"
+		cat got
+		false
+	fi
+}
+
+test_expect_success 'ignores non-commit OIDs to --input=stdin-commits with --no-check-oids' '
+	test_when_finished rm -rf "$objdir/info/commit-graph" &&
+	cd "$TRASH_DIRECTORY/full" &&
+	# write a graph to ensure layers are/are not added appropriately
+	git rev-parse HEAD~1 >base &&
+	git commit-graph write --stdin-commits <base &&
+	graph_expect_commits 2 &&
+	# bad input is rejected
+	echo HEAD >bad &&
+	test_expect_code 1 git commit-graph write --stdin-commits <bad 2>err &&
+	test_i18ngrep "unexpected non-hex object ID: HEAD" err &&
+	graph_expect_commits 2 &&
+	# update with valid commit OID, ignore tree OID
+	git rev-parse HEAD HEAD^{tree} >in &&
+	git commit-graph write --stdin-commits --no-check-oids <in &&
+	graph_expect_commits 3
+'
+
 graph_git_two_modes() {
 	git -c core.commitGraph=true $1 >output
 	git -c core.commitGraph=false $1 >expect

Original file line number	Diff line number	Diff line change
`@@ -145,7 +145,7 @@ static int verify_commit_graph_lite(struct commit_graph *g)`
`145`	`145`	`*`
`146`	`146`	`* There should only be very basic checks here to ensure that`
`147`	`147`	`* we don't e.g. segfault in fill_commit_in_graph(), but`
`148`		`- * because this is a very hot codepath nothing that e.g. loops`
	`148`	`+ e because this is a very hot codepath nothing that e.g. loops`
`149`	`149`	`* over g->num_commits, or runs a checksum on the commit-graph`
`150`	`150`	`* itself.`
`151`	`151`	`*/`