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 05/13] list-objects-filter-large: add large blob filter to list-objects
Date: Fri, 22 Sep 2017 20:30:09 +0000 [thread overview]
Message-ID: <20170922203017.53986-6-git@jeffhostetler.com> (raw)
From: Jeff Hostetler <jeffhost@microsoft.com>
Create a filter for traverse_commit_list_worker() to omit blobs
larger than a requested size from the result, but always include
".git*" special files.
Signed-off-by: Jeff Hostetler <jeffhost>@microsoft.com>
---
Makefile | 1 +
list-objects-filter-large.c | 108 ++++++++++++++++++++++++++++++++++++++++++++
list-objects-filter-large.h | 18 ++++++++
3 files changed, 127 insertions(+)
create mode 100644 list-objects-filter-large.c
create mode 100644 list-objects-filter-large.h
diff --git a/Makefile b/Makefile
index b98e3dc..f1f3979 100644
--- a/Makefile
+++ b/Makefile
@@ -799,6 +799,7 @@ LIB_OBJS += line-log.o
LIB_OBJS += line-range.o
LIB_OBJS += list-objects.o
LIB_OBJS += list-objects-filter-all.o
+LIB_OBJS += list-objects-filter-large.o
LIB_OBJS += ll-merge.o
LIB_OBJS += lockfile.o
LIB_OBJS += log-tree.o
diff --git a/list-objects-filter-large.c b/list-objects-filter-large.c
new file mode 100644
index 0000000..1af39b6
--- /dev/null
+++ b/list-objects-filter-large.c
@@ -0,0 +1,108 @@
+#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-large.h"
+
+/*
+ * A filter for list-objects to omit large blobs,
+ * but always include ".git*" special files.
+ */
+struct filter_omit_large_blobs_data {
+ struct oidset2 omits;
+ int64_t max_bytes;
+};
+
+static list_objects_filter_result filter_omit_large_blobs(
+ list_objects_filter_type filter_type,
+ struct object *obj,
+ const char *pathname,
+ const char *filename,
+ void *filter_data_)
+{
+ struct filter_omit_large_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);
+
+ /*
+ * If previously provisionally omitted (because of size), see if the
+ * current filename is special and force it to be included.
+ */
+ if (oidset2_contains(&filter_data->omits, &obj->oid)) {
+ if ((strncmp(filename, ".git", 4) == 0) && filename[4]) {
+ oidset2_remove(&filter_data->omits, &obj->oid);
+ return LOFR_MARK_SEEN | LOFR_SHOW;
+ }
+ return LOFR_ZERO; /* continue provisionally omitting it */
+ }
+
+ t = sha1_object_info(obj->oid.hash, &s);
+ assert(t == OBJ_BLOB);
+ object_length = (int64_t)((uint64_t)(s));
+
+ if (object_length < filter_data->max_bytes)
+ return LOFR_MARK_SEEN | LOFR_SHOW;
+
+ /*
+ * Provisionally omit it. We've already established that this blob
+ * is too big and doesn't have a special filename, so we WANT to
+ * omit it. However, there may be a special file elsewhere in the
+ * tree that references 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.
+ *
+ * No need for a pathname, since we only test for special filenames
+ * above.
+ */
+ oidset2_insert(&filter_data->omits, &obj->oid, t, object_length,
+ NULL);
+ return LOFR_ZERO;
+ }
+}
+
+void traverse_commit_list_omit_large_blobs(
+ struct rev_info *revs,
+ show_commit_fn show_commit,
+ show_object_fn show_object,
+ oidset2_foreach_cb print_omitted_object,
+ void *ctx_data,
+ int64_t large_byte_limit)
+{
+ struct filter_omit_large_blobs_data d;
+
+ memset(&d, 0, sizeof(d));
+ d.max_bytes = large_byte_limit;
+
+ traverse_commit_list_worker(revs, show_commit, show_object, ctx_data,
+ filter_omit_large_blobs, &d);
+
+ if (print_omitted_object)
+ oidset2_foreach(&d.omits, print_omitted_object, ctx_data);
+
+ oidset2_clear(&d.omits);
+}
diff --git a/list-objects-filter-large.h b/list-objects-filter-large.h
new file mode 100644
index 0000000..4a5c772
--- /dev/null
+++ b/list-objects-filter-large.h
@@ -0,0 +1,18 @@
+#ifndef LIST_OBJECTS_FILTER_LARGE_H
+#define LIST_OBJECTS_FILTER_LARGE_H
+
+#include "oidset2.h"
+
+/*
+ * A filter for list-objects to omit large blobs,
+ * but always include ".git*" special files.
+ */
+void traverse_commit_list_omit_large_blobs(
+ struct rev_info *revs,
+ show_commit_fn show_commit,
+ show_object_fn show_object,
+ oidset2_foreach_cb print_omitted_object,
+ void *ctx_data,
+ int64_t large_byte_limit);
+
+#endif /* LIST_OBJECTS_FILTER_LARGE_H */
--
2.9.3
next reply other threads:[~2017-09-22 20:31 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-22 20:30 Jeff Hostetler [this message]
2017-09-22 20:30 ` [PATCH 06/13] list-objects-filter-sparse: add sparse-checkout based filter Jeff Hostetler
2017-09-22 20:30 ` [PATCH 07/13] object-filter: common declarations for object filtering Jeff Hostetler
2017-09-26 22:39 ` Jonathan Tan
2017-09-27 17:09 ` Jeff Hostetler
2017-09-28 0:05 ` Jonathan Tan
2017-09-28 14:33 ` Jeff Hostetler
2017-09-29 19:47 ` Jonathan Tan
2017-09-22 20:30 ` [PATCH 08/13] list-objects: add traverse_commit_list_filtered method Jeff Hostetler
2017-09-22 20:30 ` [PATCH 09/13] rev-list: add object filtering support Jeff Hostetler
2017-09-26 22:44 ` Jonathan Tan
2017-09-27 17:26 ` Jeff Hostetler
2017-09-22 20:30 ` [PATCH 10/13] rev-list: add filtering help text Jeff Hostetler
2017-09-22 20:30 ` [PATCH 11/13] t6112: rev-list object filtering test Jeff Hostetler
2017-09-22 20:30 ` [PATCH 12/13] pack-objects: add object filtering support Jeff Hostetler
2017-09-22 20:30 ` [PATCH 13/13] pack-objects: add filtering help text Jeff Hostetler
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=20170922203017.53986-6-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).