git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: Jeff Hostetler <git@jeffhostetler.com>
To: git@vger.kernel.org
Cc: gitster@pobox.com, peff@peff.net, jonathantanmy@google.com,
	Jeff Hostetler <jeffhost@microsoft.com>
Subject: [PATCH 03/13] list-objects: filter objects in traverse_commit_list
Date: Tue, 24 Oct 2017 18:53:22 +0000	[thread overview]
Message-ID: <20171024185332.57261-4-git@jeffhostetler.com> (raw)
In-Reply-To: <20171024185332.57261-1-git@jeffhostetler.com>

From: Jeff Hostetler <jeffhost@microsoft.com>

Create traverse_commit_list_filtered() and add filtering
interface to allow certain objects to be omitted (not shown)
during a traversal.

Update traverse_commit_list() to be a wrapper for the above.

Filtering will be used in a future commit by rev-list and
pack-objects for narrow/partial clone/fetch to omit certain
blobs from the output.

traverse_bitmap_commit_list() does not work with filtering.
If a packfile bitmap is present, it will not be used.

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
---
 list-objects.c | 66 ++++++++++++++++++++++++++++++++++++++++++++--------------
 list-objects.h | 32 +++++++++++++++++++++++++++-
 2 files changed, 81 insertions(+), 17 deletions(-)

diff --git a/list-objects.c b/list-objects.c
index b3931fa..3e86008 100644
--- a/list-objects.c
+++ b/list-objects.c
@@ -13,10 +13,13 @@ static void process_blob(struct rev_info *revs,
 			 show_object_fn show,
 			 struct strbuf *path,
 			 const char *name,
-			 void *cb_data)
+			 void *cb_data,
+			 filter_object_fn filter,
+			 void *filter_data)
 {
 	struct object *obj = &blob->object;
 	size_t pathlen;
+	list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_SHOW;
 
 	if (!revs->blob_objects)
 		return;
@@ -24,11 +27,15 @@ static void process_blob(struct rev_info *revs,
 		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);
+	if (filter)
+		r = filter(LOFT_BLOB, obj, path->buf, &path->buf[pathlen], filter_data);
+	if (r & LOFR_MARK_SEEN)
+		obj->flags |= SEEN;
+	if (r & LOFR_SHOW)
+		show(obj, path->buf, cb_data);
 	strbuf_setlen(path, pathlen);
 }
 
@@ -69,7 +76,9 @@ static void process_tree(struct rev_info *revs,
 			 show_object_fn show,
 			 struct strbuf *base,
 			 const char *name,
-			 void *cb_data)
+			 void *cb_data,
+			 filter_object_fn filter,
+			 void *filter_data)
 {
 	struct object *obj = &tree->object;
 	struct tree_desc desc;
@@ -77,6 +86,7 @@ static void process_tree(struct rev_info *revs,
 	enum interesting match = revs->diffopt.pathspec.nr == 0 ?
 		all_entries_interesting: entry_not_interesting;
 	int baselen = base->len;
+	list_objects_filter_result r = LOFR_MARK_SEEN | LOFR_SHOW;
 
 	if (!revs->tree_objects)
 		return;
@@ -90,9 +100,13 @@ static void process_tree(struct rev_info *revs,
 		die("bad tree object %s", oid_to_hex(&obj->oid));
 	}
 
-	obj->flags |= SEEN;
 	strbuf_addstr(base, name);
-	show(obj, base->buf, cb_data);
+	if (filter)
+		r = filter(LOFT_BEGIN_TREE, obj, base->buf, &base->buf[baselen], filter_data);
+	if (r & LOFR_MARK_SEEN)
+		obj->flags |= SEEN;
+	if (r & LOFR_SHOW)
+		show(obj, base->buf, cb_data);
 	if (base->len)
 		strbuf_addch(base, '/');
 
@@ -112,7 +126,7 @@ static void process_tree(struct rev_info *revs,
 			process_tree(revs,
 				     lookup_tree(entry.oid),
 				     show, base, entry.path,
-				     cb_data);
+				     cb_data, filter, filter_data);
 		else if (S_ISGITLINK(entry.mode))
 			process_gitlink(revs, entry.oid->hash,
 					show, base, entry.path,
@@ -121,8 +135,17 @@ static void process_tree(struct rev_info *revs,
 			process_blob(revs,
 				     lookup_blob(entry.oid),
 				     show, base, entry.path,
-				     cb_data);
+				     cb_data, filter, filter_data);
 	}
+
+	if (filter) {
+		r = filter(LOFT_END_TREE, obj, base->buf, &base->buf[baselen], filter_data);
+		if (r & LOFR_MARK_SEEN)
+			obj->flags |= SEEN;
+		if (r & LOFR_SHOW)
+			show(obj, base->buf, cb_data);
+	}
+
 	strbuf_setlen(base, baselen);
 	free_tree_buffer(tree);
 }
@@ -183,10 +206,10 @@ 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)
+void traverse_commit_list_worker(
+	struct rev_info *revs,
+	show_commit_fn show_commit, show_object_fn show_object, void *show_data,
+	filter_object_fn filter, void *filter_data)
 {
 	int i;
 	struct commit *commit;
@@ -200,7 +223,7 @@ void traverse_commit_list(struct rev_info *revs,
 		 */
 		if (commit->tree)
 			add_pending_tree(revs, commit->tree);
-		show_commit(commit, data);
+		show_commit(commit, show_data);
 	}
 	for (i = 0; i < revs->pending.nr; i++) {
 		struct object_array_entry *pending = revs->pending.objects + i;
@@ -211,19 +234,19 @@ void traverse_commit_list(struct rev_info *revs,
 			continue;
 		if (obj->type == OBJ_TAG) {
 			obj->flags |= SEEN;
-			show_object(obj, name, data);
+			show_object(obj, name, show_data);
 			continue;
 		}
 		if (!path)
 			path = "";
 		if (obj->type == OBJ_TREE) {
 			process_tree(revs, (struct tree *)obj, show_object,
-				     &base, path, data);
+				     &base, path, show_data, filter, filter_data);
 			continue;
 		}
 		if (obj->type == OBJ_BLOB) {
 			process_blob(revs, (struct blob *)obj, show_object,
-				     &base, path, data);
+				     &base, path, show_data, filter, filter_data);
 			continue;
 		}
 		die("unknown pending object %s (%s)",
@@ -232,3 +255,14 @@ void traverse_commit_list(struct rev_info *revs,
 	object_array_clear(&revs->pending);
 	strbuf_release(&base);
 }
+
+void traverse_commit_list(struct rev_info *revs,
+			  show_commit_fn show_commit,
+			  show_object_fn show_object,
+			  void *show_data)
+{
+	traverse_commit_list_worker(
+		revs,
+		show_commit, show_object, show_data,
+		NULL, NULL);
+}
diff --git a/list-objects.h b/list-objects.h
index 0cebf85..43a06fb 100644
--- a/list-objects.h
+++ b/list-objects.h
@@ -8,4 +8,34 @@ void traverse_commit_list(struct rev_info *, show_commit_fn, show_object_fn, voi
 typedef void (*show_edge_fn)(struct commit *);
 void mark_edges_uninteresting(struct rev_info *, show_edge_fn);
 
-#endif
+enum list_objects_filter_result {
+	LOFR_ZERO      = 0,
+	LOFR_MARK_SEEN = 1<<0,
+	LOFR_SHOW      = 1<<1,
+};
+
+/* See object.h and revision.h */
+#define FILTER_REVISIT (1<<25)
+
+enum list_objects_filter_type {
+	LOFT_BEGIN_TREE,
+	LOFT_END_TREE,
+	LOFT_BLOB
+};
+
+typedef enum list_objects_filter_result list_objects_filter_result;
+typedef enum list_objects_filter_type list_objects_filter_type;
+
+typedef list_objects_filter_result (*filter_object_fn)(
+	list_objects_filter_type filter_type,
+	struct object *obj,
+	const char *pathname,
+	const char *filename,
+	void *filter_data);
+
+void traverse_commit_list_worker(
+	struct rev_info *,
+	show_commit_fn, show_object_fn, void *show_data,
+	filter_object_fn filter, void *filter_data);
+
+#endif /* LIST_OBJECTS_H */
-- 
2.9.3


  parent reply	other threads:[~2017-10-24 18:54 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-24 18:53 [PATCH 00/13] WIP Partial clone part 1: object filtering Jeff Hostetler
2017-10-24 18:53 ` [PATCH 01/13] dir: allow exclusions from blob in addition to file Jeff Hostetler
2017-10-25  4:05   ` Eric Sunshine
2017-10-25  6:43   ` Junio C Hamano
2017-10-25 14:54     ` Jeff Hostetler
2017-10-26  3:47       ` Junio C Hamano
2017-10-26 18:11         ` Jeff Hostetler
2017-10-24 18:53 ` [PATCH 02/13] list-objects-filter-map: extend oidmap to collect omitted objects Jeff Hostetler
2017-10-25  7:10   ` Junio C Hamano
2017-10-25 19:22     ` Jeff Hostetler
2017-10-26  4:12       ` Junio C Hamano
2017-10-24 18:53 ` Jeff Hostetler [this message]
2017-10-25  4:05   ` [PATCH 03/13] list-objects: filter objects in traverse_commit_list Jonathan Tan
2017-10-25 19:25     ` Jeff Hostetler
2017-10-24 18:53 ` [PATCH 04/13] list-objects-filter-blobs-none: add filter to omit all blobs Jeff Hostetler
2017-10-24 18:53 ` [PATCH 05/13] list-objects-filter-blobs-limit: add large blob filtering Jeff Hostetler
2017-10-24 18:53 ` [PATCH 06/13] list-objects-filter-sparse: add sparse filter Jeff Hostetler
2017-10-24 18:53 ` [PATCH 07/13] list-objects-filter-options: common argument parsing Jeff Hostetler
2017-10-25  4:14   ` Jonathan Tan
2017-10-25 19:28     ` Jeff Hostetler
2017-10-24 18:53 ` [PATCH 08/13] list-objects: add traverse_commit_list_filtered method Jeff Hostetler
2017-10-25  4:24   ` Jonathan Tan
2017-10-25 19:29     ` Jeff Hostetler
2017-10-24 18:53 ` [PATCH 09/13] extension.partialclone: introduce partial clone extension Jeff Hostetler
2017-10-24 18:53 ` [PATCH 10/13] rev-list: add list-objects filtering support Jeff Hostetler
2017-10-25  4:41   ` Jonathan Tan
2017-10-25 19:37     ` Jeff Hostetler
2017-10-24 18:53 ` [PATCH 11/13] t6112: rev-list object filtering test Jeff Hostetler
2017-10-24 18:53 ` [PATCH 12/13] pack-objects: add list-objects filtering Jeff Hostetler
2017-10-24 18:53 ` [PATCH 13/13] t5317: pack-objects object filtering test Jeff Hostetler
2017-10-25  4:57 ` [PATCH 00/13] WIP Partial clone part 1: object filtering Jonathan Tan
2017-10-25  5:00 ` Junio C Hamano
2017-10-25  6:46   ` Jonathan Tan
2017-10-25 15:39     ` Jeff Hostetler
2017-10-26  2:09       ` Junio C Hamano
2017-10-26  2:01     ` Junio C Hamano
2017-10-30 22:27     ` Jonathan Nieder
  -- strict thread matches above, loose matches on Subject: below --
2017-09-22 20:26 [PATCH 00/13] RFC object filtering for parital clone Jeff Hostetler
2017-09-22 20:26 ` [PATCH 03/13] list-objects: filter objects in traverse_commit_list Jeff Hostetler
2017-09-26 22:31   ` Jonathan Tan
2017-09-27 17:04     ` Jeff Hostetler
2017-09-27 18:00       ` Jonathan Tan
2017-09-27 19:09         ` Jeff Hostetler
2017-09-27 20:49           ` Jonathan Tan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20171024185332.57261-4-git@jeffhostetler.com \
    --to=git@jeffhostetler.com \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=jeffhost@microsoft.com \
    --cc=jonathantanmy@google.com \
    --cc=peff@peff.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).