1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-11-01 23:07:55 +01:00
git/list-objects.c
Jeff King 2824e1841b list-objects: pass full pathname to callbacks
When we find a blob at "a/b/c", we currently pass this to
our show_object_fn callbacks as two components: "a/b/" and
"c". Callbacks which want the full value then call
path_name(), which concatenates the two. But this is an
inefficient interface; the path is a strbuf, and we could
simply append "c" to it temporarily, then roll back the
length, without creating a new copy.

So we could improve this by teaching the callsites of
path_name() this trick (and there are only 3). But we can
also notice that no callback actually cares about the
broken-down representation, and simply pass each callback
the full path "a/b/c" as a string. The callback code becomes
even simpler, then, as we do not have to worry about freeing
an allocated buffer, nor rolling back our modification to
the strbuf.

This is theoretically less efficient, as some callbacks
would not bother to format the final path component. But in
practice this is not measurable. Since we use the same
strbuf over and over, our work to grow it is amortized, and
we really only pay to memcpy a few bytes.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2016-03-16 10:41:04 -07:00

234 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 strbuf *path,
const char *name,
void *cb_data)
{
struct object *obj = &blob->object;
size_t pathlen;
if (!revs->blob_objects)
return;
if (!obj)
die("bad blob object");
if (obj->flags & (UNINTERESTING | SEEN))
return;
obj->flags |= SEEN;
pathlen = path->len;
strbuf_addstr(path, name);
show(obj, path->buf, cb_data);
strbuf_setlen(path, pathlen);
}
/*
* 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 strbuf *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;
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", sha1_to_hex(obj->sha1));
}
obj->flags |= SEEN;
strbuf_addstr(base, name);
show(obj, base->buf, cb_data);
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, base, entry.path,
cb_data);
else
process_blob(revs,
lookup_blob(entry.sha1),
show, base, 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, 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,
&base, path, data);
continue;
}
die("unknown pending object %s (%s)",
sha1_to_hex(obj->sha1), name);
}
object_array_clear(&revs->pending);
strbuf_release(&base);
}