git/list[1] front-page[2] threads[3] people[4] search[5] about
 

[PATCH 03/13] list-objects: filter objects in traverse_commit_list

From
JHJeff Hostetler <git@jeffhostetler.com>
Date
Oct 24, 2017, 18:53 UTC
Message-ID
<20171024185332.57261-4-git@jeffhostetler.com>
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
Previous: Jeff HostetlerNext: Jonathan Tan
Message 28 of 37 in “WIP Partial clone part 1: object filtering”
  1. 00/13 WIP Partial clone part 1: object filteringJeff Hostetler, Oct 24, 2017
  2. 02/13 list-objects-filter-map: extend oidmap to collect omitted objectsJeff Hostetler, Oct 24, 2017
  3. Junio C HamanoOct 25, 2017
  4. Jeff HostetlerOct 25, 2017
  5. Junio C HamanoOct 26, 2017
  6. 06/13 list-objects-filter-sparse: add sparse filterJeff Hostetler, Oct 24, 2017
  7. 08/13 list-objects: add traverse_commit_list_filtered methodJeff Hostetler, Oct 24, 2017
  8. Jonathan TanOct 25, 2017
  9. Jeff HostetlerOct 25, 2017
  10. 11/13 t6112: rev-list object filtering testJeff Hostetler, Oct 24, 2017
  11. 05/13 list-objects-filter-blobs-limit: add large blob filteringJeff Hostetler, Oct 24, 2017
  12. 13/13 t5317: pack-objects object filtering testJeff Hostetler, Oct 24, 2017
  13. 12/13 pack-objects: add list-objects filteringJeff Hostetler, Oct 24, 2017
  14. 10/13 rev-list: add list-objects filtering supportJeff Hostetler, Oct 24, 2017
  15. Jonathan TanOct 25, 2017
  16. Jeff HostetlerOct 25, 2017
  17. 04/13 list-objects-filter-blobs-none: add filter to omit all blobsJeff Hostetler, Oct 24, 2017
  18. 09/13 extension.partialclone: introduce partial clone extensionJeff Hostetler, Oct 24, 2017
  19. 01/13 dir: allow exclusions from blob in addition to fileJeff Hostetler, Oct 24, 2017
  20. Eric SunshineOct 25, 2017
  21. Junio C HamanoOct 25, 2017
  22. Jeff HostetlerOct 25, 2017
  23. Junio C HamanoOct 26, 2017
  24. Jeff HostetlerOct 26, 2017
  25. 07/13 list-objects-filter-options: common argument parsingJeff Hostetler, Oct 24, 2017
  26. Jonathan TanOct 25, 2017
  27. Jeff HostetlerOct 25, 2017
  28. 03/13 list-objects: filter objects in traverse_commit_listJeff Hostetler, Oct 24, 2017
  29. Jonathan TanOct 25, 2017
  30. Jeff HostetlerOct 25, 2017
  31. Jonathan TanOct 25, 2017
  32. Junio C HamanoOct 25, 2017
  33. Jonathan TanOct 25, 2017
  34. Jeff HostetlerOct 25, 2017
  35. Junio C HamanoOct 26, 2017
  36. Junio C HamanoOct 26, 2017
  37. Jonathan NiederOct 30, 2017

Read the whole thread, see it on lore, or plain text.

$ cat FOOTERMessages come from the public archive at lore.kernel.org/git, fetched every hour. The front page is chosen and written each morning by an AI editor and can be wrong; the threads themselves are the record. About and API. For agents: an MCP server at https://gitlist.dev/mcp, and any thread, story or person page as Markdown by adding .md to its URL (or sending Accept: text/markdown). Details in /llms.txt.