git/list-objects.c
Jeff King 13528ab37c list-objects: convert name_path to a strbuf
The "struct name_path" data is examined in only two places:
we generate it in process_tree(), and we convert it to a
single string in path_name(). Everyone else just passes it
through to those functions.

We can further note that process_tree() already keeps a
single strbuf with the leading tree path, for use with
tree_entry_interesting().

Instead of building a separate name_path linked list, let's
just use the one we already build in "base". This reduces
the amount of code (especially tricky code in path_name()
which did not check for integer overflows caused by deep
or large pathnames).

It is also more efficient in some instances.  Any time we
were using tree_entry_interesting, we were building up the
strbuf anyway, so this is an immediate and obvious win
there. In cases where we were not, we trade off storing
"pathname/" in a strbuf on the heap for each level of the
path, instead of two pointers and an int on the stack (with
one pointer into the tree object). On a 64-bit system, the
latter is 20 bytes; so if path components are less than that
on average, this has lower peak memory usage.  In practice
it probably doesn't matter either way; we are already
holding in memory all of the tree objects leading up to each
pathname, and for normal-depth pathnames, we are only
talking about hundreds of bytes.

This patch leaves "struct name_path" as a thin wrapper
around the strbuf, to avoid disrupting callbacks. We should
fix them, but leaving it out makes this diff easier to view.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-02-12 12:51:10 -08:00

233 lines
6 KiB
C

#include "cache.h"
#include "tag.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "diff.h"
#include "tree-walk.h"
#include "revision.h"
#include "list-objects.h"
static void process_blob(struct rev_info *revs,
struct blob *blob,
show_object_fn show,
struct name_path *path,
const char *name,
void *cb_data)
{
struct object *obj = &blob->object;
if (!revs->blob_objects)
return;
if (!obj)
die("bad blob object");
if (obj->flags & (UNINTERESTING | SEEN))
return;
obj->flags |= SEEN;
show(obj, path, name, cb_data);
}
/*
* Processing a gitlink entry currently does nothing, since
* we do not recurse into the subproject.
*
* We *could* eventually add a flag that actually does that,
* which would involve:
* - is the subproject actually checked out?
* - if so, see if the subproject has already been added
* to the alternates list, and add it if not.
* - process the commit (or tag) the gitlink points to
* recursively.
*
* However, it's unclear whether there is really ever any
* reason to see superprojects and subprojects as such a
* "unified" object pool (potentially resulting in a totally
* humongous pack - avoiding which was the whole point of
* having gitlinks in the first place!).
*
* So for now, there is just a note that we *could* follow
* the link, and how to do it. Whether it necessarily makes
* any sense what-so-ever to ever do that is another issue.
*/
static void process_gitlink(struct rev_info *revs,
const unsigned char *sha1,
show_object_fn show,
struct name_path *path,
const char *name,
void *cb_data)
{
/* Nothing to do */
}
static void process_tree(struct rev_info *revs,
struct tree *tree,
show_object_fn show,
struct strbuf *base,
const char *name,
void *cb_data)
{
struct object *obj = &tree->object;
struct tree_desc desc;
struct name_entry entry;
struct name_path me;
enum interesting match = revs->diffopt.pathspec.nr == 0 ?
all_entries_interesting: entry_not_interesting;
int baselen = base->len;
if (!revs->tree_objects)
return;
if (!obj)
die("bad tree object");
if (obj->flags & (UNINTERESTING | SEEN))
return;
if (parse_tree_gently(tree, revs->ignore_missing_links) < 0) {
if (revs->ignore_missing_links)
return;
die("bad tree object %s", oid_to_hex(&obj->oid));
}
obj->flags |= SEEN;
me.base = base;
show(obj, &me, name, cb_data);
strbuf_addstr(base, name);
if (base->len)
strbuf_addch(base, '/');
init_tree_desc(&desc, tree->buffer, tree->size);
while (tree_entry(&desc, &entry)) {
if (match != all_entries_interesting) {
match = tree_entry_interesting(&entry, base, 0,
&revs->diffopt.pathspec);
if (match == all_entries_not_interesting)
break;
if (match == entry_not_interesting)
continue;
}
if (S_ISDIR(entry.mode))
process_tree(revs,
lookup_tree(entry.sha1),
show, base, entry.path,
cb_data);
else if (S_ISGITLINK(entry.mode))
process_gitlink(revs, entry.sha1,
show, &me, entry.path,
cb_data);
else
process_blob(revs,
lookup_blob(entry.sha1),
show, &me, entry.path,
cb_data);
}
strbuf_setlen(base, baselen);
free_tree_buffer(tree);
}
static void mark_edge_parents_uninteresting(struct commit *commit,
struct rev_info *revs,
show_edge_fn show_edge)
{
struct commit_list *parents;
for (parents = commit->parents; parents; parents = parents->next) {
struct commit *parent = parents->item;
if (!(parent->object.flags & UNINTERESTING))
continue;
mark_tree_uninteresting(parent->tree);
if (revs->edge_hint && !(parent->object.flags & SHOWN)) {
parent->object.flags |= SHOWN;
show_edge(parent);
}
}
}
void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge)
{
struct commit_list *list;
int i;
for (list = revs->commits; list; list = list->next) {
struct commit *commit = list->item;
if (commit->object.flags & UNINTERESTING) {
mark_tree_uninteresting(commit->tree);
if (revs->edge_hint_aggressive && !(commit->object.flags & SHOWN)) {
commit->object.flags |= SHOWN;
show_edge(commit);
}
continue;
}
mark_edge_parents_uninteresting(commit, revs, show_edge);
}
if (revs->edge_hint_aggressive) {
for (i = 0; i < revs->cmdline.nr; i++) {
struct object *obj = revs->cmdline.rev[i].item;
struct commit *commit = (struct commit *)obj;
if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING))
continue;
mark_tree_uninteresting(commit->tree);
if (!(obj->flags & SHOWN)) {
obj->flags |= SHOWN;
show_edge(commit);
}
}
}
}
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,
show_commit_fn show_commit,
show_object_fn show_object,
void *data)
{
int i;
struct commit *commit;
struct strbuf base;
strbuf_init(&base, PATH_MAX);
while ((commit = get_revision(revs)) != NULL) {
/*
* an uninteresting boundary commit may not have its tree
* parsed yet, but we are not going to show them anyway
*/
if (commit->tree)
add_pending_tree(revs, commit->tree);
show_commit(commit, data);
}
for (i = 0; i < revs->pending.nr; i++) {
struct object_array_entry *pending = revs->pending.objects + i;
struct object *obj = pending->item;
const char *name = pending->name;
const char *path = pending->path;
if (obj->flags & (UNINTERESTING | SEEN))
continue;
if (obj->type == OBJ_TAG) {
obj->flags |= SEEN;
show_object(obj, NULL, name, data);
continue;
}
if (!path)
path = "";
if (obj->type == OBJ_TREE) {
process_tree(revs, (struct tree *)obj, show_object,
&base, path, data);
continue;
}
if (obj->type == OBJ_BLOB) {
process_blob(revs, (struct blob *)obj, show_object,
NULL, path, data);
continue;
}
die("unknown pending object %s (%s)",
oid_to_hex(&obj->oid), name);
}
object_array_clear(&revs->pending);
strbuf_release(&base);
}