Re: [PATCH GSoC v18 11/13] cat-file: add remote-object-info to batch-command

> diff --git a/Documentation/git-cat-file.adoc b/Documentation/git-cat-file.adoc
> index 86b9181599..a7fa6674c3 100644
> --- a/Documentation/git-cat-file.adoc
> +++ b/Documentation/git-cat-file.adoc
> @@ -169,6 +169,13 @@ info <object>::
>  	Print object info for object reference `<object>`. This corresponds to the
>  	output of `--batch-check`.
>
> +remote-object-info <remote> <object>...::
> +	Print object info for object references `<object>` at specified
> +	`<remote>` without downloading objects from the remote.
> +	Raise an error when the `object-info` capability is not supported by the remote.
> +	Raise an error when no object references are provided.
> +	This command may be combined with `--buffer`.
> +
>  flush::
>  	Used with `--buffer` to execute all preceding commands that were issued
>  	since the beginning or since the last flush was issued. When `--buffer`
> @@ -301,7 +308,8 @@ one per line, and print information based on the command given. With
>  `--batch-command`, the `info` command followed by an object will print
>  information about the object the same way `--batch-check` would, and the
>  `contents` command followed by an object prints contents in the same way
> -`--batch` would.
> +`--batch` would. The `remote-object-info` command followed by a remote and
> +objects IDs prints object info from the remote without downloading the objects.
>
>  You can specify the information shown for each object by using a custom
>  `<format>`. The `<format>` is copied literally to stdout for each
> @@ -324,15 +332,12 @@ newline. The available atoms are:
>  	reports).
>
>  `objectsize:disk`::
> -	The size, in bytes, that the object takes up on disk. See the
> -	note about on-disk sizes in the `CAVEATS` section below.
> +	The size, in bytes, that the object takes up on disk.
>

>  `deltabase`::
>  	If the object is stored as a delta on-disk, this expands to the
>  	full hex representation of the delta base object name.
> -	Otherwise, expands to the null OID (all zeroes). See `CAVEATS`
> -	below.
> -
> +	Otherwise, expands to the null OID (all zeroes).

>  `rest`::
>  	If this atom is used in the output string, input lines are split
>  	at the first whitespace boundary. All characters before that
> @@ -340,8 +345,14 @@ newline. The available atoms are:
>  	after that first run of whitespace (i.e., the "rest" of the
>  	line) are output in place of the `%(rest)` atom.
>
> +The command `remote-object-info` only supports the `%(objectname)` and
> +`%(objectsize)` placeholders. See `CAVEATS` below for more information.
> +
>  If no format is specified, the default format is `%(objectname)
> -%(objecttype) %(objectsize)`.
> +%(objecttype) %(objectsize)`, except for `remote-object-info` commands which
> +use `%(objectname) %(objectsize)` because "%(objecttype)" is not supported yet.
> +WARNING: When "%(objecttype)" is supported, the default format WILL be unified,
> +so DO NOT RELY on the current default format to stay the same!!!
>
>  If `--batch` is specified, or if `--batch-command` is used with the `contents`
>  command, the object information is followed by the object contents (consisting
> @@ -438,6 +449,10 @@ scripting purposes.
>  CAVEATS
>  -------
>
> +Note that since only `%(objectname)` and `%(objectsize)` are currently
> +supported by the `remote-object-info` command. Using any other placeholder in
> +the format string will raise an error.
> +
>  Note that the sizes of objects on disk are reported accurately, but care
>  should be taken in drawing conclusions about which refs or objects are
>  responsible for disk usage. The size of a packed non-delta object may
> be
>

> +static void parse_cmd_remote_object_info(struct batch_options *opt,
> +					 const char *line, struct strbuf *output,
> +					 struct expand_data *data)
> +{
> +	int count;
> +	const char **argv;
> +	char *line_to_split;
> +	struct object_info *remote_object_info = NULL;
> +	struct oid_array object_info_oids = OID_ARRAY_INIT;
> +
> +	if (strlen(line) >= MAX_REMOTE_OBJ_INFO_LINE)
> +		die(_("remote-object-info command too long"));
> +
> +	line_to_split = xstrdup(line);
> +	count = split_cmdline(line_to_split, &argv);
> +	if (count < 0)
> +		die(_("remote-object-info: %s"), split_cmdline_strerror(count));

> +	if (count - 1 > MAX_ALLOWED_OBJ_LIMIT)
> +		die(_("remote-object-info supports at most %d objects"),
> +		    MAX_ALLOWED_OBJ_LIMIT);
> +
> +	if (get_remote_info(opt, count, argv, &remote_object_info,
> +			    &object_info_oids))
> +		goto cleanup;
> +
> +	data->skip_object_info = 1;
> +	for (size_t i = 0; i < object_info_oids.nr; i++) {
> +		data->oid = object_info_oids.oid[i];
> +		if (remote_object_info[i].sizep) {
> +			/*
> +			 * When reaching here, it means remote-object-info can retrieve
> +			 * information from server without downloading them.
> +			 */
> +			data->size = *remote_object_info[i].sizep;
> +			opt->batch_mode = BATCH_MODE_INFO;
> +			batch_object_write(argv[i + 1], output, opt, data, NULL, 0);
> +		} else {
> +			report_object_status(opt, oid_to_hex(&data->oid), &data->oid, "missing");
> +		}
> +	}
> +	data->skip_object_info = 0;
> +
> +cleanup:
> +	for (size_t i = 0; i < object_info_oids.nr; i++)
> +		free_object_info_contents(&remote_object_info[i]);
> +	free(line_to_split);
> +	free(argv);
> +	free(remote_object_info);
> +	oid_array_clear(&object_info_oids);
> +}
> +
>  static void dispatch_calls(struct batch_options *opt,
>  		struct strbuf *output,
>  		struct expand_data *data,
> @@ -748,8 +889,9 @@ static const struct parse_cmd {
>  } commands[] = {
>  	{ "contents", parse_cmd_contents, 1 },
>  	{ "info", parse_cmd_info, 1 },
> -	{ "flush", NULL, 0 },
>  	{ "mailmap", parse_cmd_mailmap, 1 },
> +	{ "remote-object-info", parse_cmd_remote_object_info, 1 },
> +	{ "flush", NULL, 0 },

>  };
>
>  static void batch_objects_command(struct batch_options *opt,
> diff --git a/object-file.c b/object-file.c
> index 6453b1d6fa..07f019a0f6 100644
> --- a/object-file.c
> +++ b/object-file.c
> @@ -1694,3 +1694,13 @@ struct odb_transaction *odb_transaction_files_begin(struct odb_source *source)
>
>  	return &transaction->base;
>  }
> +
> +void free_object_info_contents(struct object_info *object_info)
> +{
> +	if (!object_info)
> +		return;
> +	free(object_info->typep);
> +	free(object_info->sizep);
> +	free(object_info->disk_sizep);
> +	free(object_info->delta_base_oid);
> +}