Here's a less trivial thing, and slightly more dubious one.
I was looking at that "struct object_array objects", and wondering why we
do that. I have honestly totally forgotten. Why not just call the "show()"
function as we encounter the objects? Rather than add the objects to the
object_array, and then at the very end going through the array and doing a
'show' on all, just do things more incrementally.
Now, there are possible downsides to this:
- the "buffer using object_array" _can_ in theory result in at least
better I-cache usage (two tight loops rather than one more spread out
one). I don't think this is a real issue, but in theory..
- this _does_ change the order of the objects printed. Instead of doing a
"process_tree(revs, commit->tree, &objects, NULL, "");" in the loop
over the commits (which puts all the root trees _first_ in the object
list, this patch just adds them to the list of pending objects, and
then we'll traverse them in that order (and thus show each root tree
object together with the objects we discover under it)
I _think_ the new ordering actually makes more sense, but the object
ordering is actually a subtle thing when it comes to packing
efficiency, so any change in order is going to have implications for
packing. Good or bad, I dunno.
- There may be some reason why we did it that odd way with the object
array, that I have simply forgotten.
Anyway, now that we don't buffer up the objects before showing them
that may actually result in lower memory usage during that whole
traverse_commit_list() phase.
This is seriously not very deeply tested. It makes sense to me, it seems
to pass all the tests, it looks ok, but...
Does anybody remember why we did that "object_array" thing? It used to be
an "object_list" a long long time ago, but got changed into the array due
to better memory usage patterns (those linked lists of obejcts are
horrible from a memory allocation standpoint). But I wonder why we didn't
do this back then. Maybe there's a reason for it.
Or maybe there _used_ to be a reason, and no longer is.
Signed-off-by: Junio C Hamano <gitster@pobox.com>
commit->object.flags |= OBJECT_ADDED;
}
-static void show_object(struct object_array_entry *p)
+static void show_object(struct object *obj, const char *name)
{
- add_preferred_base_object(p->name);
- add_object_entry(p->item->sha1, p->item->type, p->name, 0);
- p->item->flags |= OBJECT_ADDED;
- free((char *)p->name);
- p->name = NULL;
+ add_preferred_base_object(name);
+ add_object_entry(obj->sha1, obj->type, name, 0);
+ obj->flags |= OBJECT_ADDED;
+
+ /*
+ * We will have generated the hash from the name,
+ * but not saved a pointer to it - we can free it
+ */
+ free((char *)name);
}
static void show_edge(struct commit *commit)
commit->buffer = NULL;
}
-static void finish_object(struct object_array_entry *p)
+static void finish_object(struct object *obj, const char *name)
{
- if (p->item->type == OBJ_BLOB && !has_sha1_file(p->item->sha1))
- die("missing blob object '%s'", sha1_to_hex(p->item->sha1));
+ if (obj->type == OBJ_BLOB && !has_sha1_file(obj->sha1))
+ die("missing blob object '%s'", sha1_to_hex(obj->sha1));
}
-static void show_object(struct object_array_entry *p)
+static void show_object(struct object *obj, const char *name)
{
/* An object with name "foo\n0000000..." can be used to
* confuse downstream "git pack-objects" very badly.
*/
- const char *ep = strchr(p->name, '\n');
+ const char *ep = strchr(name, '\n');
- finish_object(p);
+ finish_object(obj, name);
if (ep) {
- printf("%s %.*s\n", sha1_to_hex(p->item->sha1),
- (int) (ep - p->name),
- p->name);
+ printf("%s %.*s\n", sha1_to_hex(obj->sha1),
+ (int) (ep - name),
+ name);
}
else
- printf("%s %s\n", sha1_to_hex(p->item->sha1), p->name);
+ printf("%s %s\n", sha1_to_hex(obj->sha1), name);
}
static void show_edge(struct commit *commit)
static void process_blob(struct rev_info *revs,
struct blob *blob,
- struct object_array *p,
+ show_object_fn show,
struct name_path *path,
const char *name)
{
if (obj->flags & (UNINTERESTING | SEEN))
return;
obj->flags |= SEEN;
- add_object(obj, p, path, name);
+ show(obj, path_name(path, name));
}
/*
*/
static void process_gitlink(struct rev_info *revs,
const unsigned char *sha1,
- struct object_array *p,
+ show_object_fn show,
struct name_path *path,
const char *name)
{
static void process_tree(struct rev_info *revs,
struct tree *tree,
- struct object_array *p,
+ show_object_fn show,
struct name_path *path,
const char *name)
{
if (parse_tree(tree) < 0)
die("bad tree object %s", sha1_to_hex(obj->sha1));
obj->flags |= SEEN;
- add_object(obj, p, path, name);
+ show(obj, path_name(path, name));
me.up = path;
me.elem = name;
me.elem_len = strlen(name);
if (S_ISDIR(entry.mode))
process_tree(revs,
lookup_tree(entry.sha1),
- p, &me, entry.path);
+ show, &me, entry.path);
else if (S_ISGITLINK(entry.mode))
process_gitlink(revs, entry.sha1,
- p, &me, entry.path);
+ show, &me, entry.path);
else
process_blob(revs,
lookup_blob(entry.sha1),
- p, &me, entry.path);
+ show, &me, entry.path);
}
free(tree->buffer);
tree->buffer = NULL;
}
}
+static void add_pending_tree(struct rev_info *revs, struct tree *tree)
+{
+ add_pending_object(revs, &tree->object, "");
+}
+
void traverse_commit_list(struct rev_info *revs,
void (*show_commit)(struct commit *),
- void (*show_object)(struct object_array_entry *))
+ void (*show_object)(struct object *, const char *))
{
int i;
struct commit *commit;
- struct object_array objects = { 0, 0, NULL };
while ((commit = get_revision(revs)) != NULL) {
- process_tree(revs, commit->tree, &objects, NULL, "");
+ add_pending_tree(revs, commit->tree);
show_commit(commit);
}
for (i = 0; i < revs->pending.nr; i++) {
continue;
if (obj->type == OBJ_TAG) {
obj->flags |= SEEN;
- add_object_array(obj, name, &objects);
+ show_object(obj, name);
continue;
}
if (obj->type == OBJ_TREE) {
- process_tree(revs, (struct tree *)obj, &objects,
+ process_tree(revs, (struct tree *)obj, show_object,
NULL, name);
continue;
}
if (obj->type == OBJ_BLOB) {
- process_blob(revs, (struct blob *)obj, &objects,
+ process_blob(revs, (struct blob *)obj, show_object,
NULL, name);
continue;
}
die("unknown pending object %s (%s)",
sha1_to_hex(obj->sha1), name);
}
- for (i = 0; i < objects.nr; i++)
- show_object(&objects.objects[i]);
- free(objects.objects);
if (revs->pending.nr) {
free(revs->pending.objects);
revs->pending.nr = 0;
#define LIST_OBJECTS_H
typedef void (*show_commit_fn)(struct commit *);
-typedef void (*show_object_fn)(struct object_array_entry *);
+typedef void (*show_object_fn)(struct object *, const char *);
typedef void (*show_edge_fn)(struct commit *);
void traverse_commit_list(struct rev_info *revs, show_commit_fn, show_object_fn);
volatile show_early_output_fn_t show_early_output;
-static char *path_name(struct name_path *path, const char *name)
+char *path_name(struct name_path *path, const char *name)
{
struct name_path *p;
char *n, *m;
const char *elem;
};
+char *path_name(struct name_path *path, const char *name);
+
extern void add_object(struct object *obj,
struct object_array *p,
struct name_path *path,
commit->buffer = NULL;
}
-static void show_object(struct object_array_entry *p)
+static void show_object(struct object *obj, const char *name)
{
/* An object with name "foo\n0000000..." can be used to
* confuse downstream git-pack-objects very badly.
*/
- const char *ep = strchr(p->name, '\n');
+ const char *ep = strchr(name, '\n');
if (ep) {
- fprintf(pack_pipe, "%s %.*s\n", sha1_to_hex(p->item->sha1),
- (int) (ep - p->name),
- p->name);
+ fprintf(pack_pipe, "%s %.*s\n", sha1_to_hex(obj->sha1),
+ (int) (ep - name),
+ name);
}
else
fprintf(pack_pipe, "%s %s\n",
- sha1_to_hex(p->item->sha1), p->name);
+ sha1_to_hex(obj->sha1), name);
}
static void show_edge(struct commit *commit)
projects / git.git / commitdiff