Re: [PATCH v2 21/25] rev-list: add --index-objects option

@@ -172,12 +172,10 @@ explicitly.
 	Pretend as if all objects mentioned by reflogs are listed on the
 	command line as `<commit>`.
 
---index-objects::
-	Pretend as if all objects used by the index (any blobs, and any
-	trees which are mentioned by the index's cache-tree extension)
-	ad listed on the command line. Note that you probably want to
-	use `--objects`, too, as there are by definition no commits in
-	the index.
+--indexed-objects::
+	Pretend as if all trees and blobs used by the index are listed
+	on the command line.  Note that you probably want to use
+	`--objects`, too.
 
 --ignore-missing::
 	Upon seeing an invalid object name in the input, pretend as if

@@ -172,6 +172,11 @@ explicitly.
 	Pretend as if all objects mentioned by reflogs are listed on the
 	command line as `<commit>`.
 
+--indexed-objects::
+	Pretend as if all trees and blobs used by the index are listed
+	on the command line.  Note that you probably want to use
+	`--objects`, too.
+
 --ignore-missing::
 	Upon seeing an invalid object name in the input, pretend as if
 	the bad input was not given.

@@ -17,6 +17,7 @@
 #include "mailmap.h"
 #include "commit-slab.h"
 #include "dir.h"
+#include "cache-tree.h"
 
 volatile show_early_output_fn_t show_early_output;
 

@@ -1303,6 +1304,53 @@ void add_reflogs_to_pending(struct rev_info *revs, unsigned flags)
 	for_each_reflog(handle_one_reflog, &cb);
 }
 
+static void add_cache_tree(struct cache_tree *it, struct rev_info *revs,
+			   struct strbuf *path)
+{
+	size_t baselen = path->len;
+	int i;
+
+	if (it->entry_count >= 0) {
+		struct tree *tree = lookup_tree(it->sha1);
+		add_pending_object_with_path(revs, &tree->object, "",
+					     040000, path->buf);
+	}
+
+	for (i = 0; i < it->subtree_nr; i++) {
+		struct cache_tree_sub *sub = it->down[i];
+		strbuf_addf(path, "%s%s", baselen ? "/" : "", sub->name);
+		add_cache_tree(sub->cache_tree, revs, path);
+		strbuf_setlen(path, baselen);
+	}
+
+}
+
+void add_index_objects_to_pending(struct rev_info *revs, unsigned flags)
+{
+	int i;
+
+	read_cache();
+	for (i = 0; i < active_nr; i++) {
+		struct cache_entry *ce = active_cache[i];
+		struct blob *blob;
+
+		if (S_ISGITLINK(ce->ce_mode))
+			continue;
+
+		blob = lookup_blob(ce->sha1);
+		if (!blob)
+			die("unable to add index blob to traversal");
+		add_pending_object_with_path(revs, &blob->object, "",
+					     ce->ce_mode, ce->name);
+	}
+
+	if (active_cache_tree) {
+		struct strbuf path = STRBUF_INIT;
+		add_cache_tree(active_cache_tree, revs, &path);
+		strbuf_release(&path);
+	}
+}
+
 static int add_parents_only(struct rev_info *revs, const char *arg_, int flags)
 {
 	unsigned char sha1[20];

@@ -1653,6 +1701,7 @@ static int handle_revision_opt(struct rev_info *revs, int argc, const char **arg
 	    !strcmp(arg, "--reflog") || !strcmp(arg, "--not") ||
 	    !strcmp(arg, "--no-walk") || !strcmp(arg, "--do-walk") ||
 	    !strcmp(arg, "--bisect") || starts_with(arg, "--glob=") ||
+	    !strcmp(arg, "--indexed-objects") ||
 	    starts_with(arg, "--exclude=") ||
 	    starts_with(arg, "--branches=") || starts_with(arg, "--tags=") ||
 	    starts_with(arg, "--remotes=") || starts_with(arg, "--no-walk="))

@@ -2082,6 +2131,8 @@ static int handle_revision_pseudo_opt(const char *submodule,
 		clear_ref_exclusion(&revs->ref_excludes);
 	} else if (!strcmp(arg, "--reflog")) {
 		add_reflogs_to_pending(revs, *flags);
+	} else if (!strcmp(arg, "--indexed-objects")) {
+		add_index_objects_to_pending(revs, *flags);
 	} else if (!strcmp(arg, "--not")) {
 		*flags ^= UNINTERESTING | BOTTOM;
 	} else if (!strcmp(arg, "--no-walk")) {

@@ -277,6 +277,7 @@ extern void add_pending_sha1(struct rev_info *revs,
 
 extern void add_head_to_pending(struct rev_info *);
 extern void add_reflogs_to_pending(struct rev_info *, unsigned int flags);
+extern void add_index_objects_to_pending(struct rev_info *, unsigned int flags);
 
 enum commit_action {
 	commit_ignore,

@@ -73,4 +73,27 @@ test_expect_success 'symleft flag bit is propagated down from tag' '
 	test_cmp expect actual
 '
 
+test_expect_success 'rev-list can show index objects' '
+	# Of the blobs and trees in the index, note:
+	#
+	#   - we do not show two/three, because it is the
+	#     same blob as "one", and we show objects only once
+	#
+	#   - we do show the tree "two", because it has a valid cache tree
+	#     from the last commit
+	#
+	#   - we do not show the root tree; since we updated the index, it
+	#     does not have a valid cache tree
+	#
+	cat >expect <<-\EOF
+	8e4020bb5a8d8c873b25de15933e75cc0fc275df one
+	d9d3a7417b9605cfd88ee6306b28dadc29e6ab08 only-in-index
+	9200b628cf9dc883a85a7abc8d6e6730baee589c two
+	EOF
+	echo only-in-index >only-in-index &&
+	git add only-in-index &&
+	git rev-list --objects --indexed-objects >actual &&
+	test_cmp expect actual
+'
+
 test_done

@@ -32,56 +32,6 @@ static int add_one_ref(const char *path, const unsigned char *sha1, int flag, vo
 	return 0;
 }
 
-static void add_one_tree(const unsigned char *sha1, struct rev_info *revs)
-{
-	struct tree *tree = lookup_tree(sha1);
-	if (tree)
-		add_pending_object(revs, &tree->object, "");
-}
-
-static void add_cache_tree(struct cache_tree *it, struct rev_info *revs)
-{
-	int i;
-
-	if (it->entry_count >= 0)
-		add_one_tree(it->sha1, revs);
-	for (i = 0; i < it->subtree_nr; i++)
-		add_cache_tree(it->down[i]->cache_tree, revs);
-}
-
-static void add_cache_refs(struct rev_info *revs)
-{
-	int i;
-
-	read_cache();
-	for (i = 0; i < active_nr; i++) {
-		struct blob *blob;
-
-		/*
-		 * The index can contain blobs and GITLINKs, GITLINKs are hashes
-		 * that don't actually point to objects in the repository, it's
-		 * almost guaranteed that they are NOT blobs, so we don't call
-		 * lookup_blob() on them, to avoid populating the hash table
-		 * with invalid information
-		 */
-		if (S_ISGITLINK(active_cache[i]->ce_mode))
-			continue;
-
-		blob = lookup_blob(active_cache[i]->sha1);
-		if (blob)
-			blob->object.flags |= SEEN;
-
-		/*
-		 * We could add the blobs to the pending list, but quite
-		 * frankly, we don't care. Once we've looked them up, and
-		 * added them as objects, we've really done everything
-		 * there is to do for a blob
-		 */
-	}
-	if (active_cache_tree)
-		add_cache_tree(active_cache_tree, revs);
-}
-
 /*
  * The traversal will have already marked us as SEEN, so we
  * only need to handle any progress reporting here.

@@ -213,7 +163,7 @@ void mark_reachable_objects(struct rev_info *revs, int mark_reflog,
 	revs->tree_objects = 1;
 
 	/* Add all refs from the index file */
-	add_cache_refs(revs);
+	add_index_objects_to_pending(revs, 0);
 
 	/* Add all external refs */
 	for_each_ref(add_one_ref, revs);

@@ -22,6 +22,7 @@
 #include "pack-bitmap.h"
 #include "reachable.h"
 #include "sha1-array.h"
+#include "argv-array.h"
 
 static const char *pack_usage[] = {
 	N_("git pack-objects --stdout [options...] [< ref-list | < object-list]"),

@@ -2614,8 +2615,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	int use_internal_rev_list = 0;
 	int thin = 0;
 	int all_progress_implied = 0;
-	const char *rp_av[6];
-	int rp_ac = 0;
+	struct argv_array rp = ARGV_ARRAY_INIT;
 	int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;
 	struct option pack_objects_options[] = {
 		OPT_SET_INT('q', "quiet", &progress,

@@ -2705,24 +2705,24 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (pack_to_stdout != !base_name || argc)
 		usage_with_options(pack_usage, pack_objects_options);
 
-	rp_av[rp_ac++] = "pack-objects";
+	argv_array_push(&rp, "pack-objects");
 	if (thin) {
 		use_internal_rev_list = 1;
-		rp_av[rp_ac++] = "--objects-edge";
+		argv_array_push(&rp, "--objects-edge");
 	} else
-		rp_av[rp_ac++] = "--objects";
+		argv_array_push(&rp, "--objects");
 
 	if (rev_list_all) {
 		use_internal_rev_list = 1;
-		rp_av[rp_ac++] = "--all";
+		argv_array_push(&rp, "--all");
 	}
 	if (rev_list_reflog) {
 		use_internal_rev_list = 1;
-		rp_av[rp_ac++] = "--reflog";
+		argv_array_push(&rp, "--reflog");
 	}
 	if (rev_list_unpacked) {
 		use_internal_rev_list = 1;
-		rp_av[rp_ac++] = "--unpacked";
+		argv_array_push(&rp, "--unpacked");
 	}
 
 	if (!reuse_object)

@@ -2766,8 +2766,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	if (!use_internal_rev_list)
 		read_object_list_from_stdin();
 	else {
-		rp_av[rp_ac] = NULL;
-		get_object_list(rp_ac, rp_av);
+		get_object_list(rp.argc, rp.argv);
+		argv_array_clear(&rp);
 	}
 	cleanup_preferred_base();
 	if (include_tag && nr_result)

@@ -2617,6 +2617,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 	int all_progress_implied = 0;
 	struct argv_array rp = ARGV_ARRAY_INIT;
 	int rev_list_unpacked = 0, rev_list_all = 0, rev_list_reflog = 0;
+	int rev_list_index = 0;
 	struct option pack_objects_options[] = {
 		OPT_SET_INT('q', "quiet", &progress,
 			    N_("do not show progress meter"), 0),

@@ -2663,6 +2664,9 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		{ OPTION_SET_INT, 0, "reflog", &rev_list_reflog, NULL,
 		  N_("include objects referred by reflog entries"),
 		  PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
+		{ OPTION_SET_INT, 0, "indexed-objects", &rev_list_index, NULL,
+		  N_("include objects referred to by the index"),
+		  PARSE_OPT_NOARG | PARSE_OPT_NONEG, NULL, 1 },
 		OPT_BOOL(0, "stdout", &pack_to_stdout,
 			 N_("output pack to stdout")),
 		OPT_BOOL(0, "include-tag", &include_tag,

@@ -2720,6 +2724,10 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		use_internal_rev_list = 1;
 		argv_array_push(&rp, "--reflog");
 	}
+	if (rev_list_index) {
+		use_internal_rev_list = 1;
+		argv_array_push(&rp, "--indexed-objects");
+	}
 	if (rev_list_unpacked) {
 		use_internal_rev_list = 1;
 		argv_array_push(&rp, "--unpacked");

@@ -209,6 +209,7 @@ int cmd_repack(int argc, const char **argv, const char *prefix)
 	argv_array_push(&cmd_args, "--non-empty");
 	argv_array_push(&cmd_args, "--all");
 	argv_array_push(&cmd_args, "--reflog");
+	argv_array_push(&cmd_args, "--indexed-objects");
 	if (window)
 		argv_array_pushf(&cmd_args, "--window=%s", window);
 	if (window_memory)

@@ -109,4 +109,17 @@ test_expect_success 'do not bother loosening old objects' '
 	test_must_fail git cat-file -p $obj2
 '
 
+test_expect_success 'keep packed objects found only in index' '
+	echo my-unique-content >file &&
+	git add file &&
+	git commit -m "make it reachable" &&
+	git gc &&
+	git reset HEAD^ &&
+	git reflog expire --expire=now --all &&
+	git add file &&
+	test-chmtime =-86400 .git/objects/pack/* &&
+	git gc --prune=1.hour.ago &&
+	git cat-file blob :file
+'
+
 test_done

@@ -2757,6 +2757,8 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 
 	if (keep_unreachable && unpack_unreachable)
 		die("--keep-unreachable and --unpack-unreachable are incompatible.");
+	if (!rev_list_all || !rev_list_reflog || !rev_list_index)
+		unpack_unreachable_expiration = 0;
 
 	if (!use_internal_rev_list || !pack_to_stdout || is_repository_shallow())
 		use_bitmap_index = 0;