From 7d4e4d5dc88ed70b73ae10d4d3283f661110c99c Mon Sep 17 00:00:00 2001 From: Eric Wong Date: Fri, 23 Aug 2024 22:46:27 +0000 Subject: [PATCH] object_info: content_limit only applies to blobs Streaming is only supported for blobs, so we'd end up having to slurp all the other object types into memory regardless. So slurp all the non-blob types up front when requesting content since we always handle them in-core, anyways. Signed-off-by: Eric Wong Signed-off-by: Junio C Hamano --- builtin/cat-file.c | 21 +++++++++++++++++++-- object-file.c | 3 ++- packfile.c | 8 +++++--- t/t1006-cat-file.sh | 19 ++++++++++++++++--- 4 files changed, 42 insertions(+), 9 deletions(-) diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 8debcdca3e..2aedd62324 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -385,7 +385,24 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d assert(data->info.typep); if (data->content) { - batch_write(opt, data->content, data->size); + void *content = data->content; + unsigned long size = data->size; + + data->content = NULL; + if (use_mailmap && (data->type == OBJ_COMMIT || + data->type == OBJ_TAG)) { + size_t s = size; + + if (data->info.whence == OI_DBCACHED) { + content = xmemdupz(content, s); + data->info.whence = OI_PACKED; + } + + content = replace_idents_using_mailmap(content, &s); + size = cast_size_t_to_ulong(s); + } + + batch_write(opt, content, size); switch (data->info.whence) { case OI_CACHED: /* @@ -395,7 +412,7 @@ static void print_object_or_die(struct batch_options *opt, struct expand_data *d BUG("TODO OI_CACHED support not done"); case OI_LOOSE: case OI_PACKED: - FREE_AND_NULL(data->content); + free(content); break; case OI_DBCACHED: unlock_delta_base_cache(); diff --git a/object-file.c b/object-file.c index 19100e823d..59842cfe1b 100644 --- a/object-file.c +++ b/object-file.c @@ -1492,7 +1492,8 @@ static int loose_object_info(struct repository *r, if (!oi->contentp) break; - if (oi->content_limit && *oi->sizep > oi->content_limit) { + if (oi->content_limit && *oi->typep == OBJ_BLOB && + *oi->sizep > oi->content_limit) { git_inflate_end(&stream); oi->contentp = NULL; goto cleanup; diff --git a/packfile.c b/packfile.c index 94d20034e4..a592e0b32c 100644 --- a/packfile.c +++ b/packfile.c @@ -1546,7 +1546,7 @@ int packed_object_info(struct repository *r, struct packed_git *p, if (oi->direct_cache) { lock_delta_base_cache(); *oi->contentp = ent->data; - } else if (!oi->content_limit || + } else if (type != OBJ_BLOB || !oi->content_limit || ent->size <= oi->content_limit) { *oi->contentp = xmemdupz(ent->data, ent->size); } else { @@ -1583,10 +1583,12 @@ int packed_object_info(struct repository *r, struct packed_git *p, } if (oi->contentp) { - if (oi->sizep && *oi->sizep <= oi->content_limit) { + final_type = packed_to_object_type(r, p, obj_offset, + type, &w_curs, curpos); + if (final_type != OBJ_BLOB || (oi->sizep && + *oi->sizep <= oi->content_limit)) { *oi->contentp = unpack_entry(r, p, obj_offset, &type, oi->sizep); - final_type = type; if (!*oi->contentp) type = OBJ_BAD; } else { diff --git a/t/t1006-cat-file.sh b/t/t1006-cat-file.sh index ff9bf213aa..841e8567e9 100755 --- a/t/t1006-cat-file.sh +++ b/t/t1006-cat-file.sh @@ -622,20 +622,33 @@ test_expect_success 'confirm that neither loose blob is a delta' ' test_cmp expect actual ' +test_expect_success 'setup delta base tests' ' + foo="$(git rev-parse HEAD:foo)" && + foo_plus="$(git rev-parse HEAD:foo-plus)" && + git repack -ad +' + # To avoid relying too much on the current delta heuristics, # we will check only that one of the two objects is a delta # against the other, but not the order. We can do so by just # asking for the base of both, and checking whether either # oid appears in the output. test_expect_success '%(deltabase) reports packed delta bases' ' - git repack -ad && git cat-file --batch-check="%(deltabase)" actual && { - grep "$(git rev-parse HEAD:foo)" actual || - grep "$(git rev-parse HEAD:foo-plus)" actual + grep "$foo" actual || grep "$foo_plus" actual } ' +test_expect_success 'delta base direct cache use succeeds w/o asserting' ' + commands="info $foo +info $foo_plus +contents $foo_plus +contents $foo" && + echo "$commands" >in && + git cat-file --batch-command out +' + test_expect_success 'setup bogus data' ' bogus_short_type="bogus" && bogus_short_content="bogus" &&