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

[PATCH v2 04/19] list-objects-filters: add omit-all-blobs filter

From
JHJeff Hostetler <git@jeffhostetler.com>
Date
Jul 13, 2017, 17:34 UTC
Message-ID
<20170713173459.3559-5-git@jeffhostetler.com>
In-Reply-To
<20170713173459.3559-1-git@jeffhostetler.com>
From: Jeff Hostetler <jeffhost@microsoft.com>

Create a simple filter for traverse_commit_list_filtered() to omit all blobs from the result.

This filter will be used in a future commit by rev-list and pack-objects to create a "commits and trees" result. This is intended for a narrow/partial clone/fetch.

Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
---
 Makefile               |  1 +
 list-objects-filters.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++
 list-objects-filters.h | 17 ++++++++++
 3 files changed, 103 insertions(+)
 create mode 100644 list-objects-filters.c
 create mode 100644 list-objects-filters.h
diff --git a/Makefile b/Makefile
index d590508..48fdcf2 100644
--- a/Makefile
+++ b/Makefile
@@ -773,6 +773,7 @@ LIB_OBJS += levenshtein.o
 LIB_OBJS += line-log.o
 LIB_OBJS += line-range.o
 LIB_OBJS += list-objects.o
+LIB_OBJS += list-objects-filters.o
 LIB_OBJS += ll-merge.o
 LIB_OBJS += lockfile.o
 LIB_OBJS += log-tree.o
diff --git a/list-objects-filters.c b/list-objects-filters.c
new file mode 100644
index 0000000..f29d8bc
--- /dev/null
+++ b/list-objects-filters.c
@@ -0,0 +1,85 @@
+#include "cache.h"
+#include "dir.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"
+#include "list-objects-filters.h"
+
+/*
+ * A filter for list-objects to omit ALL blobs from the traversal.
+ */
+struct filter_omit_all_blobs_data {
+	struct oidset2 omits;
+};
+
+static list_objects_filter_result filter_omit_all_blobs(
+	list_objects_filter_type filter_type,
+	struct object *obj,
+	const char *pathname,
+	const char *filename,
+	void *filter_data_)
+{
+	struct filter_omit_all_blobs_data *filter_data = filter_data_;
+	int64_t object_length = -1;
+	unsigned long s;
+	enum object_type t;
+
+	switch (filter_type) {
+	default:
+		die("unkown filter_type");
+		return LOFR_ZERO;
+
+	case LOFT_BEGIN_TREE:
+		assert(obj->type == OBJ_TREE);
+		/* always include all tree objects */
+		return LOFR_MARK_SEEN | LOFR_SHOW;
+
+	case LOFT_END_TREE:
+		assert(obj->type == OBJ_TREE);
+		return LOFR_ZERO;
+
+	case LOFT_BLOB:
+		assert(obj->type == OBJ_BLOB);
+		assert((obj->flags & SEEN) == 0);
+
+		/*
+		 * Since we always omit all blobs (and never provisionally omit),
+		 * we should never see a blob twice.
+		 */
+		assert(!oidset2_contains(&filter_data->omits, &obj->oid));
+
+		t = sha1_object_info(obj->oid.hash, &s);
+		assert(t == OBJ_BLOB);
+		object_length = (int64_t)((uint64_t)(s));
+
+		/* Insert OID into the omitted list. No need for a pathname. */
+		oidset2_insert(&filter_data->omits, &obj->oid, object_length,
+			       NULL);
+		return LOFR_MARK_SEEN; /* but not LOFR_SHOW (hard omit) */
+	}
+}
+
+void traverse_commit_list_omit_all_blobs(
+	struct rev_info *revs,
+	show_commit_fn show_commit,
+	show_object_fn show_object,
+	oidset2_foreach_cb print_omitted_object,
+	void *ctx_data)
+{
+	struct filter_omit_all_blobs_data d;
+
+	memset(&d, 0, sizeof(d));
+
+	traverse_commit_list_filtered(revs, show_commit, show_object, ctx_data,
+				      filter_omit_all_blobs, &d);
+
+	if (print_omitted_object)
+		oidset2_foreach(&d.omits, print_omitted_object, ctx_data);
+
+	oidset2_clear(&d.omits);
+}
diff --git a/list-objects-filters.h b/list-objects-filters.h
new file mode 100644
index 0000000..b981020
--- /dev/null
+++ b/list-objects-filters.h
@@ -0,0 +1,17 @@
+#ifndef LIST_OBJECTS_FILTERS_H
+#define LIST_OBJECTS_FILTERS_H
+
+#include "oidset2.h"
+
+/*
+ * A filter for list-objects to omit ALL blobs
+ * from the traversal.
+ */
+void traverse_commit_list_omit_all_blobs(
+	struct rev_info *revs,
+	show_commit_fn show_commit,
+	show_object_fn show_object,
+	oidset2_foreach_cb print_omitted_object,
+	void *ctx_data);
+
+#endif /* LIST_OBJECTS_FILTERS_H */
-- 
2.9.3
Previous: Jeff Hostetler
Message 20 of 20 in “WIP object filtering for partial clone”
  1. 00/19 WIP object filtering for partial cloneJeff Hostetler, Jul 13, 2017
  2. 01/19 dir: refactor add_excludes()Jeff Hostetler, Jul 13, 2017
  3. 03/19 list-objects: filter objects in traverse_commit_listJeff Hostetler, Jul 13, 2017
  4. 06/19 list-objects-filters: add use-sparse-checkout filterJeff Hostetler, Jul 13, 2017
  5. 07/19 object-filter: common declarations for object filteringJeff Hostetler, Jul 13, 2017
  6. 11/19 pack-objects: add object filtering supportJeff Hostetler, Jul 13, 2017
  7. 10/19 t6112: rev-list object filtering testJeff Hostetler, Jul 13, 2017
  8. 13/19 upload-pack: add filter-objects to protocol documentationJeff Hostetler, Jul 13, 2017
  9. 17/19 clone: add filter argumentsJeff Hostetler, Jul 13, 2017
  10. 18/19 index-pack: relax consistency checks for omitted objectsJeff Hostetler, Jul 13, 2017
  11. 12/19 pack-objects: add filtering help textJeff Hostetler, Jul 13, 2017
  12. 14/19 upload-pack: add object filteringJeff Hostetler, Jul 13, 2017
  13. 15/19 fetch-pack: add object filtering supportJeff Hostetler, Jul 13, 2017
  14. 16/19 connected: add filter_allow_omitted option to APIJeff Hostetler, Jul 13, 2017
  15. 19/19 fetch: add object filtering to fetchJeff Hostetler, Jul 13, 2017
  16. 08/19 rev-list: add object filtering supportJeff Hostetler, Jul 13, 2017
  17. 09/19 rev-list: add filtering help textJeff Hostetler, Jul 13, 2017
  18. 02/19 oidset2: create oidset subclass with object length and pathnameJeff Hostetler, Jul 13, 2017
  19. 05/19 list-objects-filters: add omit-large-blobs filterJeff Hostetler, Jul 13, 2017
  20. 04/19 list-objects-filters: add omit-all-blobs filterJeff Hostetler, Jul 13, 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.