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 06/13] list-objects-filter-sparse: add sparse filter
Date: Tue, 24 Oct 2017 18:53:25 +0000 [thread overview]
Message-ID: <20171024185332.57261-7-git@jeffhostetler.com> (raw)
In-Reply-To: <20171024185332.57261-1-git@jeffhostetler.com>
From: Jeff Hostetler <jeffhost@microsoft.com>
Create a filter for traverse_commit_list_worker() to only include
the blobs the would be referenced by a sparse-checkout using the
given specification.
Signed-off-by: Jeff Hostetler <jeffhost@microsoft.com>
---
Makefile | 1 +
list-objects-filter-sparse.c | 241 +++++++++++++++++++++++++++++++++++++++++++
list-objects-filter-sparse.h | 30 ++++++
3 files changed, 272 insertions(+)
create mode 100644 list-objects-filter-sparse.c
create mode 100644 list-objects-filter-sparse.h
diff --git a/Makefile b/Makefile
index 0fdeabb..fc82664 100644
--- a/Makefile
+++ b/Makefile
@@ -810,6 +810,7 @@ LIB_OBJS += list-objects.o
LIB_OBJS += list-objects-filter-blobs-limit.o
LIB_OBJS += list-objects-filter-blobs-none.o
LIB_OBJS += list-objects-filter-map.o
+LIB_OBJS += list-objects-filter-sparse.o
LIB_OBJS += ll-merge.o
LIB_OBJS += lockfile.o
LIB_OBJS += log-tree.o
diff --git a/list-objects-filter-sparse.c b/list-objects-filter-sparse.c
new file mode 100644
index 0000000..386b667
--- /dev/null
+++ b/list-objects-filter-sparse.c
@@ -0,0 +1,241 @@
+#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-filter-sparse.h"
+
+#define DEFAULT_MAP_SIZE (16*1024)
+
+/*
+ * A filter driven by a sparse-checkout specification to only
+ * include blobs that a sparse checkout would populate.
+ *
+ * The sparse-checkout spec can be loaded from a blob with the
+ * given OID or from a local pathname. We allow an OID because
+ * the repo may be bare or we may be doing the filtering on the
+ * server.
+ */
+struct frame {
+ int defval;
+ int child_prov_omit : 1;
+};
+
+struct filter_use_sparse_data {
+ struct oidmap *omits;
+ struct exclude_list el;
+
+ size_t nr, alloc;
+ struct frame *array_frame;
+};
+
+static list_objects_filter_result filter_use_sparse(
+ list_objects_filter_type filter_type,
+ struct object *obj,
+ const char *pathname,
+ const char *filename,
+ void *filter_data_)
+{
+ struct filter_use_sparse_data *filter_data = filter_data_;
+ struct list_objects_filter_map_entry *entry_prev = NULL;
+ int val, dtype;
+ struct frame *frame;
+
+ switch (filter_type) {
+ default:
+ die("unkown filter_type");
+ return LOFR_ZERO;
+
+ case LOFT_BEGIN_TREE:
+ assert(obj->type == OBJ_TREE);
+ dtype = DT_DIR;
+ val = is_excluded_from_list(pathname, strlen(pathname),
+ filename, &dtype, &filter_data->el,
+ &the_index);
+ if (val < 0)
+ val = filter_data->array_frame[filter_data->nr].defval;
+
+ ALLOC_GROW(filter_data->array_frame, filter_data->nr + 1,
+ filter_data->alloc);
+ filter_data->nr++;
+ filter_data->array_frame[filter_data->nr].defval = val;
+ filter_data->array_frame[filter_data->nr].child_prov_omit = 0;
+
+ /*
+ * A directory with this tree OID may appear in multiple
+ * places in the tree. (Think of a directory move, with
+ * no other changes.) And with a different pathname, the
+ * is_excluded...() results for this directory and items
+ * contained within it may be different. So we cannot
+ * mark it SEEN (yet), since that will prevent process_tree()
+ * from revisiting this tree object with other pathnames.
+ *
+ * Only SHOW the tree object the first time we visit this
+ * tree object.
+ *
+ * We always show all tree objects. A future optimization
+ * may want to attempt to narrow this.
+ */
+ if (obj->flags & FILTER_REVISIT)
+ return LOFR_ZERO;
+ obj->flags |= FILTER_REVISIT;
+ return LOFR_SHOW;
+
+ case LOFT_END_TREE:
+ assert(obj->type == OBJ_TREE);
+ assert(filter_data->nr > 0);
+
+ frame = &filter_data->array_frame[filter_data->nr];
+ filter_data->nr--;
+
+ /*
+ * Tell our parent directory if any of our children were
+ * provisionally omitted.
+ */
+ filter_data->array_frame[filter_data->nr].child_prov_omit |=
+ frame->child_prov_omit;
+
+ /*
+ * If there are NO provisionally omitted child objects (ALL child
+ * objects in this folder were INCLUDED), then we can mark the
+ * folder as SEEN (so we will not have to revisit it again).
+ */
+ if (!frame->child_prov_omit)
+ return LOFR_MARK_SEEN;
+ return LOFR_ZERO;
+
+ case LOFT_BLOB:
+ assert(obj->type == OBJ_BLOB);
+ assert((obj->flags & SEEN) == 0);
+
+ frame = &filter_data->array_frame[filter_data->nr];
+
+ /*
+ * If we are keeping a list of the omitted objects
+ * for the caller *AND* we previsously provisionally
+ * omitted this object (because the THEN pathname
+ * is excluded) *AND* it has the same pathname, we
+ * can avoid duplicating the is_excluded lookup
+ * costs and continue provisionally omitting it.
+ */
+ if (filter_data->omits) {
+ entry_prev = oidmap_get(
+ filter_data->omits, &obj->oid);
+ if (entry_prev &&
+ !strcmp(pathname, entry_prev->pathname)) {
+ frame->child_prov_omit = 1;
+ return LOFR_ZERO;
+ }
+ }
+
+ dtype = DT_REG;
+ val = is_excluded_from_list(pathname, strlen(pathname),
+ filename, &dtype, &filter_data->el,
+ &the_index);
+ if (val < 0)
+ val = frame->defval;
+ if (val > 0) {
+ if (entry_prev) {
+ entry_prev = oidmap_remove(filter_data->omits,
+ &obj->oid);
+ free(entry_prev);
+ }
+ return LOFR_MARK_SEEN | LOFR_SHOW;
+ }
+
+ /*
+ * Provisionally omit it. We've already established that
+ * this pathname is not in the sparse-checkout specification
+ * with the CURRENT pathname, so we *WANT* to omit this blob.
+ *
+ * However, a pathname elsewhere in the tree may also
+ * reference this same blob, so we cannot reject it yet.
+ * Leave the LOFR_ bits unset so that if the blob appears
+ * again in the traversal, we will be asked again.
+ *
+ * The pathname that we associate with this omit is just
+ * the first one we saw for this blob. Other instances of
+ * this blob may have other pathnames and that is fine.
+ * We just use it for perf to do the entry_prev lookup
+ * above (because most of the time, the blob will be in
+ * the same place as we walk the commits).
+ */
+ if (filter_data->omits)
+ list_objects_filter_map_insert(filter_data->omits,
+ &obj->oid, pathname,
+ obj->type);
+
+ frame->child_prov_omit = 1;
+ return LOFR_ZERO;
+ }
+}
+
+static void do_sparse(
+ struct filter_use_sparse_data *d,
+ struct rev_info *revs,
+ show_commit_fn show_commit,
+ show_object_fn show_object,
+ list_objects_filter_map_foreach_cb print_omitted_object,
+ void *ctx_data)
+{
+ ALLOC_GROW(d->array_frame, d->nr + 1, d->alloc);
+ d->array_frame[d->nr].defval = 0; /* default to include */
+ d->array_frame[d->nr].child_prov_omit = 0;
+
+ traverse_commit_list_worker(revs, show_commit, show_object, ctx_data,
+ filter_use_sparse, d);
+
+ if (print_omitted_object) {
+ list_objects_filter_map_foreach(d->omits, print_omitted_object, ctx_data);
+ oidmap_free(d->omits, 1);
+ }
+}
+
+void traverse_commit_list__sparse_oid(
+ struct rev_info *revs,
+ show_commit_fn show_commit,
+ show_object_fn show_object,
+ list_objects_filter_map_foreach_cb print_omitted_object,
+ void *ctx_data,
+ struct object_id *oid)
+{
+ struct filter_use_sparse_data d;
+
+ memset(&d, 0, sizeof(d));
+ if (print_omitted_object) {
+ d.omits = xcalloc(1, sizeof(*d.omits));
+ oidmap_init(d.omits, DEFAULT_MAP_SIZE);
+ }
+ if (add_excludes_from_blob_to_list(oid, NULL, 0, &d.el) < 0)
+ die("could not load filter specification");
+
+ do_sparse(&d, revs, show_commit, show_object, print_omitted_object,
+ ctx_data);
+}
+
+void traverse_commit_list__sparse_path(
+ struct rev_info *revs,
+ show_commit_fn show_commit,
+ show_object_fn show_object,
+ list_objects_filter_map_foreach_cb print_omitted_object,
+ void *ctx_data,
+ const char *path)
+{
+ struct filter_use_sparse_data d;
+
+ memset(&d, 0, sizeof(d));
+ if (print_omitted_object) {
+ d.omits = xcalloc(1, sizeof(*d.omits));
+ oidmap_init(d.omits, DEFAULT_MAP_SIZE);
+ }
+ if (add_excludes_from_file_to_list(path, NULL, 0, &d.el, NULL) < 0)
+ die("could not load filter specification");
+
+ do_sparse(&d, revs, show_commit, show_object, print_omitted_object,
+ ctx_data);
+}
diff --git a/list-objects-filter-sparse.h b/list-objects-filter-sparse.h
new file mode 100644
index 0000000..6c715bf
--- /dev/null
+++ b/list-objects-filter-sparse.h
@@ -0,0 +1,30 @@
+#ifndef LIST_OBJECTS_FILTERS_SPARSE_H
+#define LIST_OBJECTS_FILTERS_SPARSE_H
+
+#include "list-objects-filter-map.h"
+
+/*
+ * A filter driven by a sparse-checkout specification to only
+ * include blobs that a sparse checkout would populate.
+ *
+ * The sparse-checkout spec can be loaded from a blob with the
+ * given OID, a blob with a blob-ish path, or from a local pathname.
+ * We allow an OID because the repo may be bare or we may be doing
+ * the filtering on the server.
+ */
+void traverse_commit_list__sparse_oid(
+ struct rev_info *revs,
+ show_commit_fn show_commit,
+ show_object_fn show_object,
+ list_objects_filter_map_foreach_cb print_omitted_object,
+ void *ctx_data,
+ struct object_id *oid);
+void traverse_commit_list__sparse_path(
+ struct rev_info *revs,
+ show_commit_fn show_commit,
+ show_object_fn show_object,
+ list_objects_filter_map_foreach_cb print_omitted_object,
+ void *ctx_data,
+ const char *path);
+
+#endif /* LIST_OBJECTS_FILTERS_SPARSE_H */
--
2.9.3
next prev parent reply other threads:[~2017-10-24 18:54 UTC|newest]
Thread overview: 37+ 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 ` [PATCH 03/13] list-objects: filter objects in traverse_commit_list Jeff Hostetler
2017-10-25 4:05 ` 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 ` Jeff Hostetler [this message]
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
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=20171024185332.57261-7-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).