[PATCH v4 1/1] cat-file: add mailmap subcommand 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 keeps interacting with a long-lived git-cat-file
process and it would be useful if --batch-command supported toggling
mailmap dynamically on an existing process.

Add a `mailmap` subcommand to --batch-command that takes a boolean
argument (usual ways you can specify a boolean value like 'yes', 'true',
etc., are supported). Mailmap data is loaded lazily and kept in memory,
while a helper centralizes the one-time load path used both at startup
and from the batch-command handler.

Extend tests to cover runtime toggling, startup option interactions
(`--mailmap`/`--no-mailmap`), accepted boolean forms, and invalid values.

Signed-off-by: Siddharth Asthana <siddharthasthana31@gmail.com>
---
CI: https://gitlab.com/gitlab-org/git/-/pipelines/2455043368

 Documentation/git-cat-file.adoc |  12 ++++
 builtin/cat-file.c              |  37 +++++++++--
 t/t4203-mailmap.sh              | 105 ++++++++++++++++++++++++++++++++
 3 files changed, 150 insertions(+), 4 deletions(-)

diff --git a/Documentation/git-cat-file.adoc b/Documentation/git-cat-file.adoc
index c139f55a16..0f499c9d1b 100644
--- a/Documentation/git-cat-file.adoc
+++ b/Documentation/git-cat-file.adoc
@@ -174,6 +174,18 @@ 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`.
+
+`mailmap (<bool>)`::
+	Enable or disable mailmap for subsequent commands. The `<bool>`
+	argument accepts the same boolean values as linkgit:git-config[1].
+	Possible effects are:
++
+`true`;;
+	Mailmap data is loaded on first use and kept in memory until the
+	process exits. Passing `true` again does not reload the data.
+`false`;;
+	Mailmap replacements are disabled for subsequent commands, but data
+	already loaded stays in memory.
 --
 +
 
diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index d9fbad5358..fa45f774d7 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -57,6 +57,20 @@ static int use_mailmap;
 
 static char *replace_idents_using_mailmap(char *, size_t *);
 
+/*
+ * The mailmap is initialized with .strdup_strings set to 0,
+ * but read_mailmap() sets the bit to 1 (this is true even when
+ * not a single mailmap entry is read), so it can be used for
+ * lazy loading.
+ */
+static void load_mailmap(void)
+{
+	if (mailmap.strdup_strings)
+		return;
+
+	read_mailmap(the_repository, &mailmap);
+}
+
 static char *replace_idents_using_mailmap(char *object_buf, size_t *size)
 {
 	struct strbuf sb = STRBUF_INIT;
@@ -692,6 +706,20 @@ static void parse_cmd_info(struct batch_options *opt,
 	batch_one_object(line, output, opt, data);
 }
 
+static void parse_cmd_mailmap(struct batch_options *opt UNUSED,
+			      const char *line,
+			      struct strbuf *output UNUSED,
+			      struct expand_data *data UNUSED)
+{
+	use_mailmap = git_parse_maybe_bool(line);
+
+	if (use_mailmap < 0)
+		die(_("mailmap: invalid boolean '%s'"), line);
+
+	if (use_mailmap)
+		load_mailmap();
+}
+
 static void dispatch_calls(struct batch_options *opt,
 		struct strbuf *output,
 		struct expand_data *data,
@@ -725,9 +753,10 @@ 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 },
+	{ "mailmap", parse_cmd_mailmap, 1 },
 };
 
 static void batch_objects_command(struct batch_options *opt,
@@ -1131,7 +1160,7 @@ int cmd_cat_file(int argc,
 	opt_epts = (opt == 'e' || opt == 'p' || opt == 't' || opt == 's');
 
 	if (use_mailmap)
-		read_mailmap(the_repository, &mailmap);
+		load_mailmap();
 
 	switch (batch.objects_filter.choice) {
 	case LOFC_DISABLED:
diff --git a/t/t4203-mailmap.sh b/t/t4203-mailmap.sh
index 74b7ddccb2..249548eb9b 100755
--- a/t/t4203-mailmap.sh
+++ b/t/t4203-mailmap.sh
@@ -1133,6 +1133,111 @@ 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 mailmap yes 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\nmailmap yes\ninfo HEAD\n" | git cat-file --batch-command >actual &&
+	echo $commit_sha commit $size_no_mailmap >expect &&
+	echo $commit_sha commit $size_mailmap >>expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git cat-file --batch-command mailmap no disables mailmap mid-stream' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(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 "mailmap yes\ninfo HEAD\nmailmap no\ninfo HEAD\n" | git cat-file --batch-command >actual &&
+	echo $commit_sha commit $size_mailmap >expect &&
+	echo $commit_sha commit $size_no_mailmap >>expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git cat-file --batch-command mailmap works in --buffer mode' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(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 "mailmap yes\ninfo HEAD\nmailmap no\ninfo HEAD\nflush\n" | git cat-file --batch-command --buffer >actual &&
+	echo $commit_sha commit $size_mailmap >expect &&
+	echo $commit_sha commit $size_no_mailmap >>expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git cat-file --batch-command mailmap no overrides startup --mailmap' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(git rev-parse HEAD) &&
+	git cat-file --use-mailmap commit HEAD >commit_mailmap.out &&
+	size_mailmap=$(wc -c <commit_mailmap.out) &&
+	git cat-file commit HEAD >commit_no_mailmap.out &&
+	size_no_mailmap=$(wc -c <commit_no_mailmap.out) &&
+	printf "info HEAD\nmailmap no\ninfo HEAD\n" | \
+		git cat-file --mailmap --batch-command >actual &&
+	echo $commit_sha commit $size_mailmap >expect &&
+	echo $commit_sha commit $size_no_mailmap >>expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git cat-file --batch-command mailmap yes overrides startup --no-mailmap' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(git rev-parse HEAD) &&
+	git cat-file commit HEAD >commit_no_mailmap.out &&
+	size_no_mailmap=$(wc -c <commit_no_mailmap.out) &&
+	git cat-file --use-mailmap commit HEAD >commit_mailmap.out &&
+	size_mailmap=$(wc -c <commit_mailmap.out) &&
+	printf "info HEAD\nmailmap yes\ninfo HEAD\n" | \
+		git cat-file --no-mailmap --batch-command >actual &&
+	echo $commit_sha commit $size_no_mailmap >expect &&
+	echo $commit_sha commit $size_mailmap >>expect &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git cat-file --batch-command mailmap accepts true/false' '
+	test_when_finished "rm .mailmap" &&
+	cat >.mailmap <<-\EOF &&
+	C O Mitter <committer@example.com> Orig <orig@example.com>
+	EOF
+	commit_sha=$(git rev-parse HEAD) &&
+	git cat-file commit HEAD >commit_no_mailmap.out &&
+	size_no_mailmap=$(wc -c <commit_no_mailmap.out) &&
+	git cat-file --use-mailmap commit HEAD >commit_mailmap.out &&
+	size_mailmap=$(wc -c <commit_mailmap.out) &&
+	printf "mailmap true\ninfo HEAD\nmailmap false\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 mailmap rejects invalid boolean' '
+	echo "mailmap maybe" >in &&
+	test_must_fail git cat-file --batch-command <in 2>err &&
+	test_grep "mailmap: invalid boolean .*maybe" err
+'
+
 test_expect_success 'git cat-file --mailmap works with different author and committer' '
 	test_when_finished "rm .mailmap" &&
 	cat >.mailmap <<-\EOF &&
-- 
2.53.0