I think this might be fragile in the presense of older implementation of git.
A new git may operate fine without having "well known" objects in the repository, and would happily write result that points at them; an older git would find the resulting repository corrupt.
We somehow need to force "well known" objects to be instantiated in the object database when something else points at them. I am not absolutely sure if keeping has_sha1_file() unaware of this magic is enough.
-- >8 -- Implement "well known" built-in objects.
Make read_sha1_file() aware of a handful "well known" objects and use built-in copy when they are not found in the object database.
Note that we do not hook this into has_sha1_file(), so it is possible that has_sha1_file() says you do not have an empty tree object in your repository but read_sha1_file() successfully gives you an empty tree object back.
Otherwise write_sha1_file() would not create "well known" objects in the repository, leaving the repository corrupt for older implementations of git.
---
Show changes to 3 files +39 −6
cache.h, merge-recursive.c, sha1_file.c
diff --git a/cache.h b/cache.h
index f2ec5c8..7ee40e8 100644
--- a/cache.h
+++ b/cache.h
@@ -241,6 +241,10 @@ int adjust_shared_perm(const char *path);
int safe_create_leading_directories(char *path);
char *enter_repo(char *path, int strict);
+/* Well known object names */
+extern unsigned const char EMPTY_TREE_NAME[];
+extern unsigned const char EMPTY_BLOB_NAME[];
+
/* Read and unpack a sha1 file into memory, write memory to a sha1 file */
extern int sha1_object_info(const unsigned char *, char *, unsigned long *);
extern void * unpack_sha1_file(void *map, unsigned long mapsize, char *type, unsigned long *size);
diff --git a/merge-recursive.c b/merge-recursive.c
index 32e186c..1c56fd3 100644
--- a/merge-recursive.c
+++ b/merge-recursive.c
@@ -1234,11 +1234,8 @@ static int merge(struct commit *h1,
merged_common_ancestors = pop_commit(&ca);
if (merged_common_ancestors == NULL) {
/* if there is no common ancestor, make an empty tree */
- struct tree *tree = xcalloc(1, sizeof(struct tree));
-
- tree->object.parsed = 1;
- tree->object.type = OBJ_TREE;
- write_sha1_file(NULL, 0, tree_type, tree->object.sha1);
+ struct tree *tree = lookup_tree(EMPTY_TREE_NAME);
+ parse_tree(tree);
merged_common_ancestors = make_virtual_commit(tree, "ancestor");
}
diff --git a/sha1_file.c b/sha1_file.c
index 63f416b..c6efe88 100644
--- a/sha1_file.c
+++ b/sha1_file.c
@@ -1315,11 +1315,32 @@ static void *read_packed_sha1(const unsigned char *sha1, char *type, unsigned lo
return unpack_entry(&e, type, size);
}
-void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size)
+unsigned const char EMPTY_TREE_NAME[20] = {
+ 0x4b, 0x82, 0x5d, 0xc6, 0x42, 0xcb, 0x6e, 0xb9, 0xa0, 0x60,
+ 0xe5, 0x4b, 0xf8, 0xd6, 0x92, 0x88, 0xfb, 0xee, 0x49, 0x04,
+};
+
+unsigned const char EMPTY_BLOB_NAME[20] = {
+ 0xe6, 0x9d, 0xe2, 0x9b, 0xb2, 0xd1, 0xd6, 0x43, 0x4b, 0x8b,
+ 0x29, 0xae, 0x77, 0x5a, 0xd8, 0xc2, 0xe4, 0x8c, 0x53, 0x91,
+};
+
+static struct well_known_objects {
+ char *type;
+ unsigned const char *sha1;
+ unsigned long size;
+ const char *data;
+} well_known_objects[] = {
+ { "tree", EMPTY_TREE_NAME, 0UL, "" },
+ { "blob", EMPTY_BLOB_NAME, 0UL, "" },
+};
+
+void *read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size)
{
unsigned long mapsize;
void *map, *buf;
struct pack_entry e;
+ int i;
if (find_pack_entry(sha1, &e, NULL))
return read_packed_sha1(sha1, type, size);
@@ -1332,6 +1353,17 @@ void * read_sha1_file(const unsigned char *sha1, char *type, unsigned long *size
reprepare_packed_git();
if (find_pack_entry(sha1, &e, NULL))
return read_packed_sha1(sha1, type, size);
+
+ /* "well known" objects */
+ for (i = 0; i < ARRAY_SIZE(well_known_objects); i++) {
+ if (!hashcmp(well_known_objects[i].sha1, sha1)) {
+ *size = well_known_objects[i].size;
+ buf = xmalloc(*size);
+ strcpy(type, well_known_objects[i].type);
+ memcpy(buf, well_known_objects[i].data, *size);
+ return buf;
+ }
+ }
return NULL;
}
Shawn O. Pearce
