odb: hardcode the empty blob and treecmn/empty-objects

git hardocodes these as objects which exist regardless of whether they
are in the odb and uses them in the shell interface as a way of
expressing the lack of a blob or tree for one side of e.g. a diff.

In the library we use each language's natural way of declaring a lack of
value which makes a workaround like this unnecessary. Since git uses it,
it does however mean each shell application would need to perform this
check themselves.

This makes it common work across a range of applications and an issue
with compatibility with git, which fits right into what the library aims
to provide.

Thus we introduce the hard-coded empty blob and tree in the odb
frontend. These hard-coded objects are checked for before going to the
backends, but after the cache check, which means the second time they're
used, they will be treated as normal cached objects instead of creating
new ones.

2 files changed, 62 insertions, 1 deletions

diff --git a/src/odb.c b/src/odb.c
index a4fc02686..2c19c0311 100644
--- a/src/odb.c
+++ b/src/odb.c
@@ -752,6 +752,28 @@ int git_odb__read_header_or_object(
 	return 0;
 }
 
+static git_oid empty_blob = {{ 0xe6, 0x9d, 0xe2, 0x9b, 0xb2, 0xd1, 0xd6, 0x43, 0x4b, 0x8b,
+			       0x29, 0xae, 0x77, 0x5a, 0xd8, 0xc2, 0xe4, 0x8c, 0x53, 0x91 }};
+static git_oid empty_tree = {{ 0x4b, 0x82, 0x5d, 0xc6, 0x42, 0xcb, 0x6e, 0xb9, 0xa0, 0x60,
+			       0xe5, 0x4b, 0xf8, 0xd6, 0x92, 0x88, 0xfb, 0xee, 0x49, 0x04 }};
+
+static int hardcoded_objects(git_rawobj *raw, const git_oid *id)
+{
+	if (!git_oid_cmp(id, &empty_blob)) {
+		raw->type = GIT_OBJ_BLOB;
+		raw->len = 0;
+		raw->data = NULL;
+		return 0;
+	} else if (!git_oid_cmp(id, &empty_tree)) {
+		raw->type = GIT_OBJ_TREE;
+		raw->len = 0;
+		raw->data = NULL;
+		return 0;
+	} else {
+		return GIT_ENOTFOUND;
+	}
+}
+
 int git_odb_read(git_odb_object **out, git_odb *db, const git_oid *id)
 {
 	size_t i, reads = 0;
@@ -765,7 +787,7 @@ int git_odb_read(git_odb_object **out, git_odb *db, const git_oid *id)
 	if (*out != NULL)
 		return 0;
 
-	error = GIT_ENOTFOUND;
+	error = hardcoded_objects(&raw, id);
 
 	for (i = 0; i < db->backends.length && error < 0; ++i) {
 		backend_internal *internal = git_vector_get(&db->backends, i);
diff --git a/tests/odb/emptyobjects.c b/tests/odb/emptyobjects.c
new file mode 100644
index 000000000..d6d832cdf
--- /dev/null
+++ b/tests/odb/emptyobjects.c
@@ -0,0 +1,39 @@
+#include "clar_libgit2.h"
+#include "odb.h"
+#include "filebuf.h"
+
+git_repository *g_repo;
+
+void test_odb_emptyobjects__initialize(void)
+{
+	cl_git_pass(git_repository_open(&g_repo, cl_fixture("testrepo.git")));
+}
+void test_odb_emptyobjects__cleanup(void)
+{
+	git_repository_free(g_repo);
+}
+
+void test_odb_emptyobjects__read(void)
+{
+	git_oid id;
+	git_blob *blob;
+
+	cl_git_pass(git_oid_fromstr(&id, "e69de29bb2d1d6434b8b29ae775ad8c2e48c5391"));
+	cl_git_pass(git_blob_lookup(&blob, g_repo, &id));
+	cl_assert_equal_i(GIT_OBJ_BLOB, git_object_type((git_object *) blob));
+	cl_assert_equal_i(0, git_blob_rawsize(blob));
+	git_blob_free(blob);
+}
+
+void test_odb_emptyobjects__read_tree(void)
+{
+	git_oid id;
+	git_tree *tree;
+
+	cl_git_pass(git_oid_fromstr(&id, "4b825dc642cb6eb9a060e54bf8d69288fbee4904"));
+	cl_git_pass(git_tree_lookup(&tree, g_repo, &id));
+	cl_assert_equal_i(GIT_OBJ_TREE, git_object_type((git_object *) tree));
+	cl_assert_equal_i(0, git_tree_entrycount(tree));
+	cl_assert_equal_p(NULL, git_tree_entry_byname(tree, "foo"));
+	git_tree_free(tree);
+}