pack-objects: add list-objects filtering

jeffhostetler · gitster · commit 9535ce7337b9 · 2017-11-22T14:11:57.000+09:00
Teach pack-objects to use the filtering provided by the
traverse_commit_list_filtered() interface to omit unwanted
objects from the resulting packfile.

Filtering requires the use of the "--stdout" option.

Add t5317 test.

In the future, we will introduce a "partial clone" mechanism
wherein an object in a repo, obtained from a remote, may
reference a missing object that can be dynamically fetched from
that remote once needed.  This "partial clone" mechanism will
have a way, sometimes slow, of determining if a missing link
is one of the links expected to be produced by this mechanism.

This patch introduces handling of missing objects to help
debugging and development of the "partial clone" mechanism,
and once the mechanism is implemented, for a power user to
perform operations that are missing-object aware without
incurring the cost of checking if a missing link is expected.

Signed-off-by: Jeff Hostetler &lt;jeffhost@microsoft.com&gt;
Reviewed-by: Jonathan Tan &lt;jonathantanmy@google.com&gt;
Signed-off-by: Junio C Hamano &lt;gitster@pobox.com&gt;
diff --git a/Documentation/git-pack-objects.txt b/Documentation/git-pack-objects.txt
@@ -12,7 +12,8 @@ SYNOPSIS
 'git pack-objects' [-q | --progress | --all-progress] [--all-progress-implied]
 	[--no-reuse-delta] [--delta-base-offset] [--non-empty]
 	[--local] [--incremental] [--window=<n>] [--depth=<n>]
-	[--revs [--unpacked | --all]] [--stdout | base-name]
+	[--revs [--unpacked | --all]]
+	[--stdout [--filter=<filter-spec>] | base-name]
 	[--shallow] [--keep-true-parents] < object-list
 
 
@@ -236,6 +237,22 @@ So does `git bundle` (see linkgit:git-bundle[1]) when it creates a bundle.
 	With this option, parents that are hidden by grafts are packed
 	nevertheless.
 
+--filter=<filter-spec>::
+	Requires `--stdout`.  Omits certain objects (usually blobs) from
+	the resulting packfile.  See linkgit:git-rev-list[1] for valid
+	`<filter-spec>` forms.
+
+--missing=<missing-action>::
+	A debug option to help with future "partial clone" development.
+	This option specifies how missing objects are handled.
++
+The form '--missing=error' requests that pack-objects stop with an error if
+a missing object is encountered.  This is the default action.
++
+The form '--missing=allow-any' will allow object traversal to continue
+if a missing object is encountered.  Missing objects will silently be
+omitted from the results.
+
 SEE ALSO
 --------
 linkgit:git-rev-list[1]
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
@@ -15,6 +15,8 @@
 #include "diff.h"
 #include "revision.h"
 #include "list-objects.h"
+#include "list-objects-filter.h"
+#include "list-objects-filter-options.h"
 #include "pack-objects.h"
 #include "progress.h"
 #include "refs.h"
@@ -79,6 +81,15 @@ static unsigned long cache_max_small_delta_size = 1000;
 
 static unsigned long window_memory_limit = 0;
 
+static struct list_objects_filter_options filter_options;
+
+enum missing_action {
+	MA_ERROR = 0,    /* fail if any missing objects are encountered */
+	MA_ALLOW_ANY,    /* silently allow ALL missing objects */
+};
+static enum missing_action arg_missing_action;
+static show_object_fn fn_show_object;
+
 /*
  * stats
  */
@@ -2552,6 +2563,42 @@ static void show_object(struct object *obj, const char *name, void *data)
 	obj->flags |= OBJECT_ADDED;
 }
 
+static void show_object__ma_allow_any(struct object *obj, const char *name, void *data)
+{
+	assert(arg_missing_action == MA_ALLOW_ANY);
+
+	/*
+	 * Quietly ignore ALL missing objects.  This avoids problems with
+	 * staging them now and getting an odd error later.
+	 */
+	if (!has_object_file(&obj->oid))
+		return;
+
+	show_object(obj, name, data);
+}
+
+static int option_parse_missing_action(const struct option *opt,
+				       const char *arg, int unset)
+{
+	assert(arg);
+	assert(!unset);
+
+	if (!strcmp(arg, "error")) {
+		arg_missing_action = MA_ERROR;
+		fn_show_object = show_object;
+		return 0;
+	}
+
+	if (!strcmp(arg, "allow-any")) {
+		arg_missing_action = MA_ALLOW_ANY;
+		fn_show_object = show_object__ma_allow_any;
+		return 0;
+	}
+
+	die(_("invalid value for --missing"));
+	return 0;
+}
+
 static void show_edge(struct commit *commit)
 {
 	add_preferred_base(commit->object.oid.hash);
@@ -2816,7 +2863,12 @@ static void get_object_list(int ac, const char **av)
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed");
 	mark_edges_uninteresting(&revs, show_edge);
-	traverse_commit_list(&revs, show_commit, show_object, NULL);
+
+	if (!fn_show_object)
+		fn_show_object = show_object;
+	traverse_commit_list_filtered(&filter_options, &revs,
+				      show_commit, fn_show_object, NULL,
+				      NULL);
 
 	if (unpack_unreachable_expiration) {
 		revs.ignore_missing_links = 1;
@@ -2952,6 +3004,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 			 N_("use a bitmap index if available to speed up counting objects")),
 		OPT_BOOL(0, "write-bitmap-index", &write_bitmap_index,
 			 N_("write a bitmap index together with the pack index")),
+		OPT_PARSE_LIST_OBJECTS_FILTER(&filter_options),
+		{ OPTION_CALLBACK, 0, "missing", NULL, N_("action"),
+		  N_("handling for missing objects"), PARSE_OPT_NONEG,
+		  option_parse_missing_action },
 		OPT_END(),
 	};
 
@@ -3028,6 +3084,12 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (!rev_list_all || !rev_list_reflog || !rev_list_index)
 		unpack_unreachable_expiration = 0;
 
+	if (filter_options.choice) {
+		if (!pack_to_stdout)
+			die("cannot use --filter without --stdout.");
+		use_bitmap_index = 0;
+	}
+
 	/*
 	 * "soft" reasons not to use bitmaps - for on-disk repack by default we want
 	 *
diff --git a/t/t5317-pack-objects-filter-objects.sh b/t/t5317-pack-objects-filter-objects.sh
