cat-file: add --batch-command mode

Add a new flag --batch-command that accepts commands and arguments
from stdin, similar to git-update-ref --stdin.

At GitLab, we use a pair of long running cat-file processes when
accessing object content. One for iterating over object metadata with
--batch-check, and the other to grab object contents with --batch.

However, if we had --batch-command, we wouldn't need to keep both
processes around, and instead just have one --batch-command process
where we can flip between getting object info, and getting object
contents. Since we have a pair of cat-file processes per repository,
this means we can get rid of roughly half of long lived git cat-file
processes. Given there are many repositories being accessed at any given
time, this can lead to huge savings.

git cat-file --batch-command

will enter an interactive command mode whereby the user can enter in
commands and their arguments that get queued in memory:

<command1> [arg1] [arg2] LF
<command2> [arg1] [arg2] LF

When --buffer mode is used, commands will be queued in memory until a
flush command is issued that execute them:

flush LF

The reason for a flush command is that when a consumer process (A)
talks to a git cat-file process (B) and interactively writes to and
reads from it in --buffer mode, (A) needs to be able to control when
the buffer is flushed to stdout.

Currently, from (A)'s perspective, the only way is to either

1. kill (B)'s process
2. send an invalid object to stdin.

1. is not ideal from a performance perspective as it will require
spawning a new cat-file process each time, and 2. is hacky and not a
good long term solution.

With this mechanism of queueing up commands and letting (A) issue a
flush command, process (A) can control when the buffer is flushed and
can guarantee it will receive all of the output when in --buffer mode.
--batch-command also will not allow (B) to flush to stdout until a flush
is received.

This patch adds the basic structure for adding command which can be
extended in the future to add more commands. It also adds the following
two commands (on top of the flush command):

contents <object> LF
info <object> LF

The contents command takes an <object> argument and prints out the object
contents.

The info command takes an <object> argument and prints out the object
metadata.

These can be used in the following way with --buffer:

info <object> LF
contents <object> LF
contents <object> LF
info <object> LF
flush LF
info <object> LF
flush LF

When used without --buffer:

info <object> LF
contents <object> LF
contents <object> LF
info <object> LF
info <object> LF

Helped-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: John Cai <johncai86@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 119 insertions, 1 deletions

diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh
index 2d52851dad..1b85207694 100755
--- a/t/t1006-cat-file.sh
+++ b/t/t1006-cat-file.sh
@@ -182,12 +182,36 @@ $content"
 	test_cmp expect actual
     '
 
+    for opt in --buffer --no-buffer
+    do
+	test -z "$content" ||
+		test_expect_success "--batch-command $opt output of $type content is correct" '
+		maybe_remove_timestamp "$batch_output" $no_ts >expect &&
+		maybe_remove_timestamp "$(test_write_lines "contents $sha1" |
+		git cat-file --batch-command $opt)" $no_ts >actual &&
+		test_cmp expect actual
+	'
+
+	test_expect_success "--batch-command $opt output of $type info is correct" '
+		echo "$sha1 $type $size" >expect &&
+		test_write_lines "info $sha1" |
+		git cat-file --batch-command $opt >actual &&
+		test_cmp expect actual
+	'
+    done
+
     test_expect_success "custom --batch-check format" '
 	echo "$type $sha1" >expect &&
 	echo $sha1 | git cat-file --batch-check="%(objecttype) %(objectname)" >actual &&
 	test_cmp expect actual
     '
 
+    test_expect_success "custom --batch-command format" '
+	echo "$type $sha1" >expect &&
+	echo "info $sha1" | git cat-file --batch-command="%(objecttype) %(objectname)" >actual &&
+	test_cmp expect actual
+    '
+
     test_expect_success '--batch-check with %(rest)' '
 	echo "$type this is some extra content" >expect &&
 	echo "$sha1    this is some extra content" |
@@ -229,6 +253,22 @@ test_expect_success "setup" '
 
 run_tests 'blob' $hello_sha1 $hello_size "$hello_content" "$hello_content"
 
+test_expect_success '--batch-command --buffer with flush for blob info' '
+	echo "$hello_sha1 blob $hello_size" >expect &&
+	test_write_lines "info $hello_sha1" "flush" |
+	GIT_TEST_CAT_FILE_NO_FLUSH_ON_EXIT=1 \
+	git cat-file --batch-command --buffer >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success '--batch-command --buffer without flush for blob info' '
+	touch output &&
+	test_write_lines "info $hello_sha1" |
+	GIT_TEST_CAT_FILE_NO_FLUSH_ON_EXIT=1 \
+	git cat-file --batch-command --buffer >>output &&
+	test_must_be_empty output
+'
+
 test_expect_success '--batch-check without %(rest) considers whole line' '
 	echo "$hello_sha1 blob $hello_size" >expect &&
 	git update-index --add --cacheinfo 100644 $hello_sha1 "white space" &&
@@ -272,7 +312,7 @@ test_expect_success \
     "Reach a blob from a tag pointing to it" \
     "test '$hello_content' = \"\$(git cat-file blob $tag_sha1)\""
 
-for batch in batch batch-check
+for batch in batch batch-check batch-command
 do
     for opt in t s e p
     do
@@ -378,6 +418,49 @@ test_expect_success "--batch-check with multiple sha1s gives correct format" '
     "$(echo_without_newline "$batch_check_input" | git cat-file --batch-check)"
 '
 
+test_expect_success '--batch-command with multiple info calls gives correct format' '
+	cat >expect <<-EOF &&
+	$hello_sha1 blob $hello_size
+	$tree_sha1 tree $tree_size
+	$commit_sha1 commit $commit_size
+	$tag_sha1 tag $tag_size
+	deadbeef missing
+	EOF
+
+	git cat-file --batch-command --buffer >actual <<-EOF &&
+	info $hello_sha1
+	info $tree_sha1
+	info $commit_sha1
+	info $tag_sha1
+	info deadbeef
+	EOF
+
+	test_cmp expect actual
+'
+
+test_expect_success '--batch-command with multiple command calls gives correct format' '
+	remove_timestamp >expect <<-EOF &&
+	$hello_sha1 blob $hello_size
+	$hello_content
+	$commit_sha1 commit $commit_size
+	$commit_content
+	$tag_sha1 tag $tag_size
+	$tag_content
+	deadbeef missing
+	EOF
+
+	git cat-file --batch-command --buffer >actual_raw <<-EOF &&
+	contents $hello_sha1
+	contents $commit_sha1
+	contents $tag_sha1
+	contents deadbeef
+	flush
+	EOF
+
+	remove_timestamp <actual_raw >actual &&
+	test_cmp expect actual
+'
+
 test_expect_success 'setup blobs which are likely to delta' '
 	test-tool genrandom foo 10240 >foo &&
 	{ cat foo && echo plus; } >foo-plus &&
@@ -968,5 +1051,40 @@ test_expect_success 'cat-file --batch-all-objects --batch-check ignores replace'
 	echo "$orig commit $orig_size" >expect &&
 	test_cmp expect actual
 '
+test_expect_success 'batch-command empty command' '
+	echo "" >cmd &&
+	test_expect_code 128 git cat-file --batch-command <cmd 2>err &&
+	grep "^fatal:.*empty command in input.*" err
+'
+
+test_expect_success 'batch-command whitespace before command' '
+	echo " info deadbeef" >cmd &&
+	test_expect_code 128 git cat-file --batch-command <cmd 2>err &&
+	grep "^fatal:.*whitespace before command.*" err
+'
+
+test_expect_success 'batch-command unknown command' '
+	echo unknown_command >cmd &&
+	test_expect_code 128 git cat-file --batch-command <cmd 2>err &&
+	grep "^fatal:.*unknown command.*" err
+'
+
+test_expect_success 'batch-command missing arguments' '
+	echo "info" >cmd &&
+	test_expect_code 128 git cat-file --batch-command <cmd 2>err &&
+	grep "^fatal:.*info requires arguments.*" err
+'
+
+test_expect_success 'batch-command flush with arguments' '
+	echo "flush arg" >cmd &&
+	test_expect_code 128 git cat-file --batch-command --buffer <cmd 2>err &&
+	grep "^fatal:.*flush takes no arguments.*" err
+'
+
+test_expect_success 'batch-command flush without --buffer' '
+	echo "flush" >cmd &&
+	test_expect_code 128 git cat-file --batch-command <cmd 2>err &&
+	grep "^fatal:.*flush is only for --buffer mode.*" err
+'
 
 test_done