[PATCH v1 1/1] cat-file: add use-mailmap/no-use-mailmap to --batch-command

[Siddharth Asthana <siddharthasthana31@gmail.com>]

git-cat-file(1)'s --batch-command works with the --use-mailmap option,
but this option needs to be set when the process is created. This means
we cannot change this option mid-operation.

At GitLab, Gitaly caches git-cat-file processes and it would be useful
if --batch-command supported toggling mailmap dynamically with existing
processes.

Add `use-mailmap` and `no-use-mailmap` as new subcommands to
--batch-command. `use-mailmap` enables the mailmap mechanism for
subsequent `contents` and `info` commands, lazily loading the mailmap
data from disk on first invocation. `no-use-mailmap` disables it but
keeps the data in memory so re-enabling doesn't require reloading.

The subcommand names mirror the existing --use-mailmap/--no-use-mailmap
CLI options to keep the interface consistent.

Signed-off-by: Siddharth Asthana <siddharthasthana31@gmail.com>
---
CI: https://gitlab.com/gitlab-org/git/-/pipelines/2415084557

 Documentation/git-cat-file.adoc |  9 +++++++
 builtin/cat-file.c              | 33 ++++++++++++++++++++---
 t/t4203-mailmap.sh              | 48 +++++++++++++++++++++++++++++++++
 3 files changed, 86 insertions(+), 4 deletions(-)

diff --git a/Documentation/git-cat-file.adoc b/Documentation/git-cat-file.adoc
index c139f55a16..03aadbbe89 100644
--- a/Documentation/git-cat-file.adoc
+++ b/Documentation/git-cat-file.adoc
@@ -174,6 +174,15 @@ flush::
 	since the beginning or since the last flush was issued. When `--buffer`
 	is used, no output will come until a `flush` is issued. When `--buffer`
 	is not used, commands are flushed each time without issuing `flush`.
+
+use-mailmap::
+	Enable mailmap for subsequent `contents` and `info` commands. If the
+	mailmap has not been loaded yet, it is read from disk at this point.
+
+no-use-mailmap::
+	Disable mailmap for subsequent `contents` and `info` commands. The
+	mailmap data is kept in memory so that a later `use-mailmap` command
+	does not need to reload it from disk.
 --
 +
 
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index b6f12f41d6..7772d4d41b 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -54,6 +54,7 @@ static const char *force_path;
 
 static struct string_list mailmap = STRING_LIST_INIT_NODUP;
 static int use_mailmap;
+static int mailmap_loaded;
 
 static char *replace_idents_using_mailmap(char *, size_t *);
 
@@ -692,6 +693,26 @@ static void parse_cmd_info(struct batch_options *opt,
 	batch_one_object(line, output, opt, data);
 }
 
+static void parse_cmd_use_mailmap(struct batch_options *opt UNUSED,
+				  const char *line UNUSED,
+				  struct strbuf *output UNUSED,
+				  struct expand_data *data UNUSED)
+{
+	if (!mailmap_loaded) {
+		read_mailmap(the_repository, &mailmap);
+		mailmap_loaded = 1;
+	}
+	use_mailmap = 1;
+}
+
+static void parse_cmd_disable_mailmap(struct batch_options *opt UNUSED,
+				      const char *line UNUSED,
+				      struct strbuf *output UNUSED,
+				      struct expand_data *data UNUSED)
+{
+	use_mailmap = 0;
+}
+
 static void dispatch_calls(struct batch_options *opt,
 		struct strbuf *output,
 		struct expand_data *data,
@@ -725,9 +746,11 @@ static const struct parse_cmd {
 	parse_cmd_fn_t fn;
 	unsigned takes_args;
 } commands[] = {
-	{ "contents", parse_cmd_contents, 1},
-	{ "info", parse_cmd_info, 1},
-	{ "flush", NULL, 0},
+	{ "contents", parse_cmd_contents, 1 },
+	{ "info", parse_cmd_info, 1 },
+	{ "flush", NULL, 0 },
+	{ "use-mailmap", parse_cmd_use_mailmap, 0 },
+	{ "no-use-mailmap", parse_cmd_disable_mailmap, 0 },
 };
 
 static void batch_objects_command(struct batch_options *opt,
@@ -1127,8 +1150,10 @@ int cmd_cat_file(int argc,
 	opt_cw = (opt == 'c' || opt == 'w');
 	opt_epts = (opt == 'e' || opt == 'p' || opt == 't' || opt == 's');
 
-	if (use_mailmap)
+	if (use_mailmap) {
 		read_mailmap(the_repository, &mailmap);
+		mailmap_loaded = 1;
+	}
 
 	switch (batch.objects_filter.choice) {
 	case LOFC_DISABLED:
diff --git a/t/t4203-mailmap.sh b/t/t4203-mailmap.sh
index 74b7ddccb2..2ae063e5c3 100755
--- a/t/t4203-mailmap.sh
+++ b/t/t4203-mailmap.sh
@@ -1133,6 +1133,54 @@ test_expect_success 'git cat-file --batch-command returns correct size with --us
 	test_cmp expect actual
 '
 
+test_expect_success 'git cat-file --batch-command use-mailmap enables mailmap mid-stream' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(git rev-parse HEAD) &&
+	git cat-file commit HEAD >commit_no_mailmap.out &&
+	git cat-file --use-mailmap commit HEAD >commit_mailmap.out &&
+	size_no_mailmap=$(wc -c <commit_no_mailmap.out) &&
+	size_mailmap=$(wc -c <commit_mailmap.out) &&
+	printf "info HEAD\nuse-mailmap\ninfo HEAD\n" | git cat-file --batch-command >actual &&
+	echo $commit_sha commit $size_no_mailmap >expect &&
+	echo $commit_sha commit $size_mailmap >>expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git cat-file --batch-command no-use-mailmap disables mailmap mid-stream' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(git rev-parse HEAD) &&
+	git cat-file commit HEAD >commit_no_mailmap.out &&
+	git cat-file --use-mailmap commit HEAD >commit_mailmap.out &&
+	size_no_mailmap=$(wc -c <commit_no_mailmap.out) &&
+	size_mailmap=$(wc -c <commit_mailmap.out) &&
+	printf "use-mailmap\ninfo HEAD\nno-use-mailmap\ninfo HEAD\n" | git cat-file --batch-command >actual &&
+	echo $commit_sha commit $size_mailmap >expect &&
+	echo $commit_sha commit $size_no_mailmap >>expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git cat-file --batch-command use-mailmap works in --buffer mode' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(git rev-parse HEAD) &&
+	git cat-file commit HEAD >commit_no_mailmap.out &&
+	git cat-file --use-mailmap commit HEAD >commit_mailmap.out &&
+	size_no_mailmap=$(wc -c <commit_no_mailmap.out) &&
+	size_mailmap=$(wc -c <commit_mailmap.out) &&
+	printf "use-mailmap\ninfo HEAD\nno-use-mailmap\ninfo HEAD\nflush\n" | git cat-file --batch-command --buffer >actual &&
+	echo $commit_sha commit $size_mailmap >expect &&
+	echo $commit_sha commit $size_no_mailmap >>expect &&
+	test_cmp expect actual
+'
+
 test_expect_success 'git cat-file --mailmap works with different author and committer' '
 	test_when_finished "rm .mailmap" &&
 	cat >.mailmap <<-\EOF &&
-- 
2.51.0