builtin/cat-file: wire up an option to filter objects

In batch mode, git-cat-file(1) enumerates all objects and prints them
by iterating through both loose and packed objects. This works without
considering their reachability at all, and consequently most options to
filter objects as they exist in e.g. git-rev-list(1) are not applicable.
In some situations it may still be useful though to filter objects based
on properties that are inherent to them. This includes the object size
as well as its type.

Such a filter already exists in git-rev-list(1) with the `--filter=`
command line option. While this option supports a couple of filters that
are not applicable to our usecase, some of them are quite a neat fit.

Wire up the filter as an option for git-cat-file(1). This allows us to
reuse the same syntax as in git-rev-list(1) so that we don't have to
reinvent the wheel. For now, we die when any of the filter options has
been passed by the user, but they will be wired up in subsequent
commits.

Further note that the filters that we are about to introduce don't
significantly speed up the runtime of git-cat-file(1). While we can skip
emitting a lot of objects in case they are uninteresting to us, the
majority of time is spent reading the packfile, which is bottlenecked by
I/O and not the processor. This will change though once we start to make
use of bitmaps, which will allow us to skip reading the whole packfile.

Signed-off-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 32 insertions, 4 deletions

diff --git a/builtin/cat-file.c b/builtin/cat-file.c
index 1261a3ce35..0e2176c449 100644
--- a/builtin/cat-file.c
+++ b/builtin/cat-file.c
@@ -15,6 +15,7 @@
 #include "gettext.h"
 #include "hex.h"
 #include "ident.h"
+#include "list-objects-filter-options.h"
 #include "parse-options.h"
 #include "userdiff.h"
 #include "streaming.h"
@@ -35,6 +36,7 @@ enum batch_mode {
 };
 
 struct batch_options {
+	struct list_objects_filter_options objects_filter;
 	int enabled;
 	int follow_symlinks;
 	enum batch_mode batch_mode;
@@ -495,6 +497,13 @@ static void batch_object_write(const char *obj_name,
 			return;
 		}
 
+		switch (opt->objects_filter.choice) {
+		case LOFC_DISABLED:
+			break;
+		default:
+			BUG("unsupported objects filter");
+		}
+
 		if (use_mailmap && (data->type == OBJ_COMMIT || data->type == OBJ_TAG)) {
 			size_t s = data->size;
 			char *buf = NULL;
@@ -820,7 +829,8 @@ static int batch_objects(struct batch_options *opt)
 		struct object_cb_data cb;
 		struct object_info empty = OBJECT_INFO_INIT;
 
-		if (!memcmp(&data.info, &empty, sizeof(empty)))
+		if (!memcmp(&data.info, &empty, sizeof(empty)) &&
+		    opt->objects_filter.choice == LOFC_DISABLED)
 			data.skip_object_info = 1;
 
 		if (repo_has_promisor_remote(the_repository))
@@ -944,10 +954,13 @@ int cmd_cat_file(int argc,
 	int opt_cw = 0;
 	int opt_epts = 0;
 	const char *exp_type = NULL, *obj_name = NULL;
-	struct batch_options batch = {0};
+	struct batch_options batch = {
+		.objects_filter = LIST_OBJECTS_FILTER_INIT,
+	};
 	int unknown_type = 0;
 	int input_nul_terminated = 0;
 	int nul_terminated = 0;
+	int ret;
 
 	const char * const builtin_catfile_usage[] = {
 		N_("git cat-file <type> <object>"),
@@ -1008,6 +1021,7 @@ int cmd_cat_file(int argc,
 			    N_("run filters on object's content"), 'w'),
 		OPT_STRING(0, "path", &force_path, N_("blob|tree"),
 			   N_("use a <path> for (--textconv | --filters); Not with 'batch'")),
+		OPT_PARSE_LIST_OBJECTS_FILTER(&batch.objects_filter),
 		OPT_END()
 	};
 
@@ -1022,6 +1036,14 @@ int cmd_cat_file(int argc,
 	if (use_mailmap)
 		read_mailmap(&mailmap);
 
+	switch (batch.objects_filter.choice) {
+	case LOFC_DISABLED:
+		break;
+	default:
+		usagef(_("objects filter not supported: '%s'"),
+		       list_object_filter_config_name(batch.objects_filter.choice));
+	}
+
 	/* --batch-all-objects? */
 	if (opt == 'b')
 		batch.all_objects = 1;
@@ -1076,7 +1098,8 @@ int cmd_cat_file(int argc,
 			usage_msg_opt(_("batch modes take no arguments"),
 				      builtin_catfile_usage, options);
 
-		return batch_objects(&batch);
+		ret = batch_objects(&batch);
+		goto out;
 	}
 
 	if (opt) {
@@ -1108,5 +1131,10 @@ int cmd_cat_file(int argc,
 
 	if (unknown_type && opt != 't' && opt != 's')
 		die("git cat-file --allow-unknown-type: use with -s or -t");
-	return cat_one_file(opt, exp_type, obj_name, unknown_type);
+
+	ret = cat_one_file(opt, exp_type, obj_name, unknown_type);
+
+out:
+	list_objects_filter_release(&batch.objects_filter);
+	return ret;
 }