Re: [PATCH v2 5/6] builtin/repo: add keyvalue and nul format for stats

From: Patrick Steinhardt <ps@pks.im>
Date: Sep 25, 2025, 05:39 UTC
Message-ID: <aNTVdy4hhLDlMpVT@pks.im>
In-Reply-To: <20250924212426.2930029-6-jltobler@gmail.com>

On Wed, Sep 24, 2025 at 04:24:25PM -0500, Justin Tobler wrote:

Show 16 quoted lines

> diff --git a/Documentation/git-repo.adoc b/Documentation/git-repo.adoc
> index 0b8d74ed3e..db21b75522 100644
> --- a/Documentation/git-repo.adoc
> +++ b/Documentation/git-repo.adoc
> @@ -52,7 +52,26 @@ supported:
>  * Reachable object counts categorized by type
>  
>  +
> -The table output format may change and is not intended for machine parsing.
> +The output format can be chosen through the flag `--format`. Three formats are
> +supported:
> ++
> +`table`:::
> +	Outputs repository stats in a human-friendly table and is used by
> +	default. This format may change and is not intended for machine
> +	parsing.

Let's mention that this is the default format.

Show 5 quoted lines

> +`keyvalue`:::
> +	Each line of output contains a key-value pair for a repository stat.
> +	The '=' character is used to delimit between the key and the value.
> +	Values containing "unusual" characters are quoted as explained for the
> +	configuration variable `core.quotePath` (see linkgit:git-config[1]).

In the current state there is never any quoting, so this statement here is a bit misleading. Should we maybe drop that part?

Show 6 quoted lines

> +`nul`:::
> +	Similar to `keyvalue`, but uses a NUL character to delimit between
> +	key-value pairs instead of a newline. Also uses a newline character as
> +	the delimiter between the key and value instead of '='. Unlike the
> +	`keyvalue` format, values containing "unusual" characters are never
> +	quoted.

Likewise.

Show 34 quoted lines

> diff --git a/builtin/repo.c b/builtin/repo.c
> index 8f130bca66..fe7d43f78e 100644
> --- a/builtin/repo.c
> +++ b/builtin/repo.c
> @@ -312,6 +317,33 @@ static void stats_table_clear(struct stats_table *table)
>  	string_list_clear(&table->rows, 1);
>  }
>  
> +static void stats_keyvalue_print(struct repo_stats *stats, char key_delim,
> +				 char value_delim)
> +{
> +	struct strbuf buf = STRBUF_INIT;
> +
> +	strbuf_addf(&buf, "references.branches.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->refs.branches, value_delim);
> +	strbuf_addf(&buf, "references.tags.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->refs.tags, value_delim);
> +	strbuf_addf(&buf, "references.remotes.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->refs.remotes, value_delim);
> +	strbuf_addf(&buf, "references.others.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->refs.others, value_delim);
> +
> +	strbuf_addf(&buf, "objects.commits.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->objects.commits, value_delim);
> +	strbuf_addf(&buf, "objects.trees.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->objects.trees, value_delim);
> +	strbuf_addf(&buf, "objects.blobs.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->objects.blobs, value_delim);
> +	strbuf_addf(&buf, "objects.tags.count%c%" PRIuMAX "%c",
> +		    key_delim, (uintmax_t)stats->objects.tags, value_delim);
> +
> +	fwrite(buf.buf, sizeof(char), buf.len, stdout);
> +	strbuf_release(&buf);
> +}

Same question here regarding the buffering. Can't we print to stdout directly, or is there a reason not to?

Show 25 quoted lines

> @@ -389,17 +421,25 @@ static void stats_count_objects(struct object_stats *stats,
>  	path_walk_info_clear(&info);
>  }
>  
> -static int cmd_repo_stats(int argc UNUSED, const char **argv UNUSED,
> -			  const char *prefix, struct repository *repo)
> +static int cmd_repo_stats(int argc, const char **argv, const char *prefix,
> +			  struct repository *repo)
>  {
>  	struct ref_filter filter = REF_FILTER_INIT;
>  	struct stats_table table = {
>  		.rows = STRING_LIST_INIT_DUP,
>  	};
> +	enum output_format format = FORMAT_TABLE;
>  	struct repo_stats stats = { 0 };
>  	struct ref_array refs = { 0 };
>  	struct rev_info revs;
> +	struct option options[] = {
> +		OPT_CALLBACK_F(0, "format", &format, N_("format"),
> +			       N_("output format"),
> +			       PARSE_OPT_NONEG, parse_format_cb),
> +		OPT_END()
> +	};
>  
> +	parse_options(argc, argv, prefix, options, repo_usage, 0);

I think it would be sensible to introduce this call to `parse_options()` right in the first commit that wires up the new subcommand. If we don't do that we otherwise accept arbitrary arguments without raising any error, and neither do we know to output help.

So we should move the addition to a previous commit and probably do the following:

        argc = parse_options(...);
        if (argc)
            usagef("too many arguments");

Show 17 quoted lines

> @@ -407,8 +447,20 @@ static int cmd_repo_stats(int argc UNUSED, const char **argv UNUSED,
>  	stats_count_references(&stats.refs, &refs);
>  	stats_count_objects(&stats.objects, &refs, &revs);
>  
> -	stats_table_setup(&table, &stats);
> -	stats_table_print(&table);
> +	switch (format) {
> +	case FORMAT_TABLE:
> +		stats_table_setup(&table, &stats);
> +		stats_table_print(&table);
> +		break;
> +	case FORMAT_KEYVALUE:
> +		stats_keyvalue_print(&stats, '=', '\n');
> +		break;
> +	case FORMAT_NUL_TERMINATED:
> +		stats_keyvalue_print(&stats, '\n', '\0');
> +		break;

This reads much nicer now. The newline as key-value delimiter is a curious choice, but you simply do what we already do in `git repo info`.

Show 34 quoted lines

> diff --git a/t/t1901-repo-stats.sh b/t/t1901-repo-stats.sh
> index 315b9e1767..d2c1b6e307 100755
> --- a/t/t1901-repo-stats.sh
> +++ b/t/t1901-repo-stats.sh
> @@ -73,4 +73,37 @@ test_expect_success 'repository with references and objects' '
>  	)
>  '
>  
> +test_expect_success 'repository stats with keyvalue and nul format' '
> +	test_when_finished "rm -rf repo" &&
> +	git init repo &&
> +	(
> +		cd repo &&
> +		test_commit_bulk 42 &&
> +		git tag -a foo -m bar &&
> +
> +		cat >expect <<-\EOF &&
> +		references.branches.count=1
> +		references.tags.count=1
> +		references.remotes.count=0
> +		references.others.count=0
> +		objects.commits.count=42
> +		objects.trees.count=42
> +		objects.blobs.count=42
> +		objects.tags.count=1
> +		EOF
> +
> +		git repo stats --format=keyvalue >out 2>err &&
> +
> +		test_cmp expect out &&
> +		test_line_count = 0 err &&
> +
> +		# Replace key and value delimiters for nul format.
> +		tr "\n" "\0" <expect | tr "=" "\n" >expect_null &&

You can do this without the pipe:

    tr "\n=" "\0\n" <expect >expect_nul

Also, let's call the file `expect_nul` (with a single 'l') to match the format.

Patrick