rev-list: add list-objects filtering support

Teach rev-list to use the filtering provided by the
traverse_commit_list_filtered() interface to omit
unwanted objects from the result.

Object filtering is only allowed when one of the "--objects*"
options are used.

When the "--filter-print-omitted" option is used, the omitted
objects are printed at the end.  These are marked with a "~".
This option can be combined with "--quiet" to get a list of
just the omitted objects.

Add t6112 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 <[email protected]>
Reviewed-by: Jonathan Tan <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: jeffhostetler

Documentation/git-rev-list.txt

@@ -47,7 +47,9 @@ SYNOPSIS
 	     [ --fixed-strings | -F ]
 	     [ --date=<format>]
 	     [ [ --objects | --objects-edge | --objects-edge-aggressive ]
-	       [ --unpacked ] ]
+	       [ --unpacked ]
+	       [ --filter=<filter-spec> [ --filter-print-omitted ] ] ]
+	     [ --missing=<missing-action> ]
 	     [ --pretty | --header ]
 	     [ --bisect ]
 	     [ --bisect-vars ]

Documentation/rev-list-options.txt

@@ -706,6 +706,42 @@ ifdef::git-rev-list[]
 --unpacked::
 	Only useful with `--objects`; print the object IDs that are not
 	in packs.
+
+--filter=<filter-spec>::
+	Only useful with one of the `--objects*`; omits objects (usually
+	blobs) from the list of printed objects.  The '<filter-spec>'
+	may be one of the following:
++
+The form '--filter=blob:none' omits all blobs.
++
+The form '--filter=blob:limit=<n>[kmg]' omits blobs larger than n bytes
+or units.  The value may be zero.
++
+The form '--filter=sparse:oid=<oid-ish>' uses a sparse-checkout
+specification contained in the object (or the object that the expression
+evaluates to) to omit blobs that would not be not required for a
+sparse checkout on the requested refs.
++
+The form '--filter=sparse:path=<path>' similarly uses a sparse-checkout
+specification contained in <path>.
+
+--filter-print-omitted::
+	Only useful with `--filter=`; prints a list of the objects omitted
+	by the filter.	Object IDs are prefixed with a ``~'' character.
+
+--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 rev-list 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.
++
+The form '--missing=print' is like 'allow-any', but will also print a
+list of the missing objects.  Object IDs are prefixed with a ``?'' character.
 endif::git-rev-list[]
 
 --no-walk[=(sorted|unsorted)]::

builtin/rev-list.c

@@ -4,6 +4,8 @@
 #include "diff.h"
 #include "revision.h"
 #include "list-objects.h"
+#include "list-objects-filter.h"
+#include "list-objects-filter-options.h"
 #include "pack.h"
 #include "pack-bitmap.h"
 #include "builtin.h"
@@ -12,6 +14,7 @@
 #include "bisect.h"
 #include "progress.h"
 #include "reflog-walk.h"
+#include "oidset.h"
 
 static const char rev_list_usage[] =
 "git rev-list [OPTION] <commit-id>... [ -- paths... ]\n"
@@ -55,6 +58,20 @@ static const char rev_list_usage[] =
 static struct progress *progress;
 static unsigned progress_counter;
 
+static struct list_objects_filter_options filter_options;
+static struct oidset omitted_objects;
+static int arg_print_omitted; /* print objects omitted by filter */
+
+static struct oidset missing_objects;
+enum missing_action {
+	MA_ERROR = 0,    /* fail if any missing objects are encountered */
+	MA_ALLOW_ANY,    /* silently allow ALL missing objects */
+	MA_PRINT,        /* print ALL missing objects in special section */
+};
+static enum missing_action arg_missing_action;
+
+#define DEFAULT_OIDSET_SIZE     (16*1024)
+
 static void finish_commit(struct commit *commit, void *data);
 static void show_commit(struct commit *commit, void *data)
 {
@@ -178,11 +195,31 @@ static void finish_commit(struct commit *commit, void *data)
 	free_commit_buffer(commit);
 }
 
+static inline void finish_object__ma(struct object *obj)
+{
+	switch (arg_missing_action) {
+	case MA_ERROR:
+		die("missing blob object '%s'", oid_to_hex(&obj->oid));
+		return;
+
+	case MA_ALLOW_ANY:
+		return;
+
+	case MA_PRINT:
+		oidset_insert(&missing_objects, &obj->oid);
+		return;
+
+	default:
+		BUG("unhandled missing_action");
+		return;
+	}
+}
+
 static void finish_object(struct object *obj, const char *name, void *cb_data)
 {
 	struct rev_list_info *info = cb_data;
 	if (obj->type == OBJ_BLOB && !has_object_file(&obj->oid))
-		die("missing blob object '%s'", oid_to_hex(&obj->oid));
+		finish_object__ma(obj);
 	if (info->revs->verify_objects && !obj->parsed && obj->type != OBJ_COMMIT)
 		parse_object(&obj->oid);
 }
@@ -269,6 +306,26 @@ static int show_object_fast(
 	return 1;
 }
 
+static inline int parse_missing_action_value(const char *value)
+{
+	if (!strcmp(value, "error")) {
+		arg_missing_action = MA_ERROR;
+		return 1;
+	}
+
+	if (!strcmp(value, "allow-any")) {
+		arg_missing_action = MA_ALLOW_ANY;
+		return 1;
+	}
+
+	if (!strcmp(value, "print")) {
+		arg_missing_action = MA_PRINT;
+		return 1;
+	}
+
+	return 0;
+}
+
 int cmd_rev_list(int argc, const char **argv, const char *prefix)
 {
 	struct rev_info revs;
@@ -335,6 +392,26 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			show_progress = arg;
 			continue;
 		}
+
+		if (skip_prefix(arg, ("--" CL_ARG__FILTER "="), &arg)) {
+			parse_list_objects_filter(&filter_options, arg);
+			if (filter_options.choice && !revs.blob_objects)
+				die(_("object filtering requires --objects"));
+			if (filter_options.choice == LOFC_SPARSE_OID &&
+			    !filter_options.sparse_oid_value)
+				die(_("invalid sparse value '%s'"),
+				    filter_options.filter_spec);
+			continue;
+		}
+		if (!strcmp(arg, "--filter-print-omitted")) {
+			arg_print_omitted = 1;
+			continue;
+		}
+
+		if (skip_prefix(arg, "--missing=", &arg) &&
+		    parse_missing_action_value(arg))
+			continue;
+
 		usage(rev_list_usage);
 
 	}
@@ -360,6 +437,9 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 	if (revs.show_notes)
 		die(_("rev-list does not support display of notes"));
 
+	if (filter_options.choice && use_bitmap_index)
+		die(_("cannot combine --use-bitmap-index with object filtering"));
+
 	save_commit_buffer = (revs.verbose_header ||
 			      revs.grep_filter.pattern_list ||
 			      revs.grep_filter.header_list);
@@ -404,7 +484,31 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 			return show_bisect_vars(&info, reaches, all);
 	}
 
-	traverse_commit_list(&revs, show_commit, show_object, &info);
+	if (arg_print_omitted)
+		oidset_init(&omitted_objects, DEFAULT_OIDSET_SIZE);
+	if (arg_missing_action == MA_PRINT)
+		oidset_init(&missing_objects, DEFAULT_OIDSET_SIZE);
+
+	traverse_commit_list_filtered(
+		&filter_options, &revs, show_commit, show_object, &info,
+		(arg_print_omitted ? &omitted_objects : NULL));
+
+	if (arg_print_omitted) {
+		struct oidset_iter iter;
+		struct object_id *oid;
+		oidset_iter_init(&omitted_objects, &iter);
+		while ((oid = oidset_iter_next(&iter)))
+			printf("~%s\n", oid_to_hex(oid));
+		oidset_clear(&omitted_objects);
+	}
+	if (arg_missing_action == MA_PRINT) {
+		struct oidset_iter iter;
+		struct object_id *oid;
+		oidset_iter_init(&missing_objects, &iter);
+		while ((oid = oidset_iter_next(&iter)))
+			printf("?%s\n", oid_to_hex(oid));
+		oidset_clear(&missing_objects);
+	}
 
 	stop_progress(&progress);