On Sat, Jan 07 2023, Jeff King wrote:
> When the pack code was split into its own file[1], it got a copy of the
> static read_object() function. But there's only one caller here, so we
> could just inline it. And it's worth doing so, as the name read_object()
> invites comparisons to the public read_object_file(), but the two don't
> behave quite the same.
>
> [1] The move happened over several commits, but the relevant one here is
> f1d8130be0 (pack: move clear_delta_base_cache(), packed_object_info(),
> unpack_entry(), 2017-08-18).
>
> Signed-off-by: Jeff King <peff@xxxxxxxx>
> ---
> packfile.c | 26 +++++++++-----------------
> 1 file changed, 9 insertions(+), 17 deletions(-)
>
> diff --git a/packfile.c b/packfile.c
> index c0d7dd93f4..79e21ab18e 100644
> --- a/packfile.c
> +++ b/packfile.c
> @@ -1650,22 +1650,6 @@ struct unpack_entry_stack_ent {
> unsigned long size;
> };
>
> -static void *read_object(struct repository *r,
> - const struct object_id *oid,
> - enum object_type *type,
> - unsigned long *size)
> -{
> - struct object_info oi = OBJECT_INFO_INIT;
> - void *content;
> - oi.typep = type;
> - oi.sizep = size;
> - oi.contentp = &content;
> -
> - if (oid_object_info_extended(r, oid, &oi, 0) < 0)
> - return NULL;
> - return content;
> -}
> -
> void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
> enum object_type *final_type, unsigned long *final_size)
> {
> @@ -1798,14 +1782,22 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
> uint32_t pos;
> struct object_id base_oid;
> if (!(offset_to_pack_pos(p, obj_offset, &pos))) {
> + struct object_info oi = OBJECT_INFO_INIT;
> +
> nth_packed_object_id(&base_oid, p,
> pack_pos_to_index(p, pos));
> error("failed to read delta base object %s"
> " at offset %"PRIuMAX" from %s",
> oid_to_hex(&base_oid), (uintmax_t)obj_offset,
> p->pack_name);
> mark_bad_packed_object(p, &base_oid);
> - base = read_object(r, &base_oid, &type, &base_size);
> +
> + oi.typep = &type;
> + oi.sizep = &base_size;
> + oi.contentp = &base;
> + if (oid_object_info_extended(r, &base_oid, &oi, 0) < 0)
> + base = NULL;
> +
> external_base = base;
> }
> }
This isn't introducing a behavior difference, in fact it's diligently
bending over backwards to preserve existing behavior, but I don't think
we need to do so, and shouldn't have this "base = NULL" line.
Here we're within an "if" block where we tested that "base == NULL"
(which is why we're trying to populate it)
Before when we had read_object() re-assigning to "base" here was the
obvious thing to do, but now this seems like undue an incomplete
paranoia.
If oid_object_info_extended() why can't we trust that it didn't touch
our "base"? And if we can't trust that, why are we trusting that it left
"type" and "base_size" untouched?
I think squashing this in would be much better:
diff --git a/packfile.c b/packfile.c
index 79e21ab18e7..f45017422a1 100644
--- a/packfile.c
+++ b/packfile.c
@@ -1795,10 +1795,8 @@ void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
oi.typep = &type;
oi.sizep = &base_size;
oi.contentp = &base;
- if (oid_object_info_extended(r, &base_oid, &oi, 0) < 0)
- base = NULL;
-
- external_base = base;
+ if (!oid_object_info_extended(r, &base_oid, &oi, 0))
+ external_base = base;
}
}
Not only aren't we second-guessing that our "base" was left alone, we're
using the return value of oid_object_info_extended() to guard that
assignment to "external_base" instead (it's NULL at this point too).
