Re: [PATCH 1/5] builtin/repo: update stats for each object

[Junio C Hamano <gitster@pobox.com>]

Justin Tobler <jltobler@gmail.com> writes:

> +		switch (type) {
> +		case OBJ_TAG:
> +			stats->type_counts.tags++;
> +			stats->inflated_sizes.tags += inflated;
> +			stats->disk_sizes.tags += disk;
> +			break;
> +		case OBJ_COMMIT:
> +			stats->type_counts.commits++;
> +			stats->inflated_sizes.commits += inflated;
> +			stats->disk_sizes.commits += disk;
> +			break;
> +		case OBJ_TREE:
> +			stats->type_counts.trees++;
> +			stats->inflated_sizes.trees += inflated;
> +			stats->disk_sizes.trees += disk;
> +			break;
> +		case OBJ_BLOB:
> +			stats->type_counts.blobs++;
> +			stats->inflated_sizes.blobs += inflated;
> +			stats->disk_sizes.blobs += disk;
> +			break;
> +		default:
> +			BUG("invalid object type");
> +		}
>  	}

The repetition above makes me wonder if it might be a better
organization to have

    struct object_stat {       
        struct type_stat {
            size_t count;
            size_t inflated_size;
            size_t disk_size;
	} tag, commit, tree, blob;
	... possibly other members ...
    } *stats;

or even

    struct object_stat {       
        struct type_stat {
            size_t count;
            size_t inflated_size;
            size_t disk_size;
	} t[4];
	... possibly other members ...
    };

and have this part of the code be

	struct type_stat *t;

	if (OBJ_COMMIT <= type && type <= OBJ_TAG)
		t = stats->t[type - 1];
	else
		BUG("invalid object type");

	t->count++;
	t->inflated_size += inflated;
	t->disk_size += disk;

but that is probably only because I am looking at this part of the
code.  Other parts of the code may have good reasons to have the
structure nested the other way around like you have.