From 24304816141d16aacdc63612797faa1426222ef7 Mon Sep 17 00:00:00 2001
From: Junio C Hamano <junkio@cox.net>
Date: Sat, 6 Jan 2007 02:16:10 -0800
Subject: builtin-prune: make file-scope static struct to an argument.

I want to make the first part of 'git prune' that marks the
reachable objects callable as a library, so this starts the
first step toward the goal by making the callchain to pass
rev_info structure as an argument.

No functionality change should be in this step.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/builtin-prune.c b/builtin-prune.c
index b469c43..9522864 100644
--- a/builtin-prune.c
+++ b/builtin-prune.c
@@ -12,7 +12,6 @@
 
 static const char prune_usage[] = "git-prune [-n]";
 static int show_only;
-static struct rev_info revs;
 
 static int prune_object(char *path, const char *filename, const unsigned char *sha1)
 {
@@ -184,45 +183,48 @@ static void walk_commit_list(struct rev_info *revs)
 static int add_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1, char *datail, void *cb_data)
 {
 	struct object *object;
+	struct rev_info *revs = (struct rev_info *)cb_data;
 
 	object = parse_object(osha1);
 	if (object)
-		add_pending_object(&revs, object, "");
+		add_pending_object(revs, object, "");
 	object = parse_object(nsha1);
 	if (object)
-		add_pending_object(&revs, object, "");
+		add_pending_object(revs, object, "");
 	return 0;
 }
 
 static int add_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data)
 {
 	struct object *object = parse_object(sha1);
+	struct rev_info *revs = (struct rev_info *)cb_data;
+
 	if (!object)
 		die("bad object ref: %s:%s", path, sha1_to_hex(sha1));
-	add_pending_object(&revs, object, "");
+	add_pending_object(revs, object, "");
 
-	for_each_reflog_ent(path, add_one_reflog_ent, NULL);
+	for_each_reflog_ent(path, add_one_reflog_ent, cb_data);
 
 	return 0;
 }
 
-static void add_one_tree(const unsigned char *sha1)
+static void add_one_tree(const unsigned char *sha1, struct rev_info *revs)
 {
 	struct tree *tree = lookup_tree(sha1);
-	add_pending_object(&revs, &tree->object, "");
+	add_pending_object(revs, &tree->object, "");
 }
 
-static void add_cache_tree(struct cache_tree *it)
+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);
+		add_one_tree(it->sha1, revs);
 	for (i = 0; i < it->subtree_nr; i++)
-		add_cache_tree(it->down[i]->cache_tree);
+		add_cache_tree(it->down[i]->cache_tree, revs);
 }
 
-static void add_cache_refs(void)
+static void add_cache_refs(struct rev_info *revs)
 {
 	int i;
 
@@ -237,12 +239,13 @@ static void add_cache_refs(void)
 		 */
 	}
 	if (active_cache_tree)
-		add_cache_tree(active_cache_tree);
+		add_cache_tree(active_cache_tree, revs);
 }
 
 int cmd_prune(int argc, const char **argv, const char *prefix)
 {
 	int i;
+	struct rev_info revs;
 
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
@@ -264,11 +267,11 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 	revs.blob_objects = 1;
 	revs.tree_objects = 1;
 
-	/* Add all external refs */
-	for_each_ref(add_one_ref, NULL);
+	/* Add all external refs, along with its reflog info */
+	for_each_ref(add_one_ref, &revs);
 
 	/* Add all refs from the index file */
-	add_cache_refs();
+	add_cache_refs(&revs);
 
 	/*
 	 * Set up the revision walk - this will move all commits
-- 
cgit v0.10.2-6-g49f6


From ca4f293fb492efdd2b984b992796b075c30e230d Mon Sep 17 00:00:00 2001
From: Junio C Hamano <junkio@cox.net>
Date: Sat, 6 Jan 2007 02:16:14 -0800
Subject: builtin-prune: separate ref walking from reflog walking.

This is necessary for the next step, because the reason I am
making the connectivity walker into a library is because I want
to use it for cleaning up stale reflog entries.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/builtin-prune.c b/builtin-prune.c
index 9522864..cd079b4 100644
--- a/builtin-prune.c
+++ b/builtin-prune.c
@@ -203,8 +203,12 @@ static int add_one_ref(const char *path, const unsigned char *sha1, int flag, vo
 		die("bad object ref: %s:%s", path, sha1_to_hex(sha1));
 	add_pending_object(revs, object, "");
 
-	for_each_reflog_ent(path, add_one_reflog_ent, cb_data);
+	return 0;
+}
 
+static int add_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data)
+{
+	for_each_reflog_ent(path, add_one_reflog_ent, cb_data);
 	return 0;
 }
 
@@ -267,12 +271,15 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 	revs.blob_objects = 1;
 	revs.tree_objects = 1;
 
-	/* Add all external refs, along with its reflog info */
+	/* Add all external refs */
 	for_each_ref(add_one_ref, &revs);
 
 	/* Add all refs from the index file */
 	add_cache_refs(&revs);
 
+	/* Add all reflog info from refs */
+	for_each_ref(add_one_reflog, &revs);
+
 	/*
 	 * Set up the revision walk - this will move all commits
 	 * from the pending list to the commit walking list.
-- 
cgit v0.10.2-6-g49f6


From 94421474e068c2f0a7bef3d658216a0f1e75b906 Mon Sep 17 00:00:00 2001
From: Junio C Hamano <junkio@cox.net>
Date: Sat, 6 Jan 2007 02:16:17 -0800
Subject: Move traversal of reachable objects into a separate library.

This moves major part of builtin-prune into a separate file,
reachable.c.  It is used to mark the objects that are reachable
from refs, and optionally from reflogs.

The patch looks very large, but if you look at it with diff -C,
which this message is formatted in, most of them are copied
lines and there are very little additions.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/Makefile b/Makefile
index 180e1e0..d8bfb6b 100644
--- a/Makefile
+++ b/Makefile
@@ -251,6 +251,7 @@ LIB_OBJS = \
 	interpolate.o \
 	lockfile.o \
 	object.o pack-check.o patch-delta.o path.o pkt-line.o sideband.o \
+	reachable.o \
 	quote.o read-cache.o refs.o run-command.o dir.o object-refs.o \
 	server-info.o setup.o sha1_file.o sha1_name.o strbuf.o \
 	tag.o tree.o usage.o config.o environment.o ctype.o copy.o \
diff --git a/builtin-prune.c b/builtin-prune.c
index cd079b4..6f0ba0d 100644
--- a/builtin-prune.c
+++ b/builtin-prune.c
@@ -1,14 +1,9 @@
 #include "cache.h"
-#include "refs.h"
-#include "tag.h"
 #include "commit.h"
-#include "tree.h"
-#include "blob.h"
-#include "tree-walk.h"
 #include "diff.h"
 #include "revision.h"
 #include "builtin.h"
-#include "cache-tree.h"
+#include "reachable.h"
 
 static const char prune_usage[] = "git-prune [-n]";
 static int show_only;
@@ -84,168 +79,6 @@ static void prune_object_dir(const char *path)
 	}
 }
 
-static void process_blob(struct blob *blob,
-			 struct object_array *p,
-			 struct name_path *path,
-			 const char *name)
-{
-	struct object *obj = &blob->object;
-
-	if (obj->flags & SEEN)
-		return;
-	obj->flags |= SEEN;
-	/* Nothing to do, really .. The blob lookup was the important part */
-}
-
-static void process_tree(struct tree *tree,
-			 struct object_array *p,
-			 struct name_path *path,
-			 const char *name)
-{
-	struct object *obj = &tree->object;
-	struct tree_desc desc;
-	struct name_entry entry;
-	struct name_path me;
-
-	if (obj->flags & SEEN)
-		return;
-	obj->flags |= SEEN;
-	if (parse_tree(tree) < 0)
-		die("bad tree object %s", sha1_to_hex(obj->sha1));
-	name = xstrdup(name);
-	add_object(obj, p, path, name);
-	me.up = path;
-	me.elem = name;
-	me.elem_len = strlen(name);
-
-	desc.buf = tree->buffer;
-	desc.size = tree->size;
-
-	while (tree_entry(&desc, &entry)) {
-		if (S_ISDIR(entry.mode))
-			process_tree(lookup_tree(entry.sha1), p, &me, entry.path);
-		else
-			process_blob(lookup_blob(entry.sha1), p, &me, entry.path);
-	}
-	free(tree->buffer);
-	tree->buffer = NULL;
-}
-
-static void process_tag(struct tag *tag, struct object_array *p, const char *name)
-{
-	struct object *obj = &tag->object;
-	struct name_path me;
-
-	if (obj->flags & SEEN)
-		return;
-	obj->flags |= SEEN;
-
-	me.up = NULL;
-	me.elem = "tag:/";
-	me.elem_len = 5;
-
-	if (parse_tag(tag) < 0)
-		die("bad tag object %s", sha1_to_hex(obj->sha1));
-	add_object(tag->tagged, p, NULL, name);
-}
-
-static void walk_commit_list(struct rev_info *revs)
-{
-	int i;
-	struct commit *commit;
-	struct object_array objects = { 0, 0, NULL };
-
-	/* Walk all commits, process their trees */
-	while ((commit = get_revision(revs)) != NULL)
-		process_tree(commit->tree, &objects, NULL, "");
-
-	/* Then walk all the pending objects, recursively processing them too */
-	for (i = 0; i < revs->pending.nr; i++) {
-		struct object_array_entry *pending = revs->pending.objects + i;
-		struct object *obj = pending->item;
-		const char *name = pending->name;
-		if (obj->type == OBJ_TAG) {
-			process_tag((struct tag *) obj, &objects, name);
-			continue;
-		}
-		if (obj->type == OBJ_TREE) {
-			process_tree((struct tree *)obj, &objects, NULL, name);
-			continue;
-		}
-		if (obj->type == OBJ_BLOB) {
-			process_blob((struct blob *)obj, &objects, NULL, name);
-			continue;
-		}
-		die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name);
-	}
-}
-
-static int add_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1, char *datail, void *cb_data)
-{
-	struct object *object;
-	struct rev_info *revs = (struct rev_info *)cb_data;
-
-	object = parse_object(osha1);
-	if (object)
-		add_pending_object(revs, object, "");
-	object = parse_object(nsha1);
-	if (object)
-		add_pending_object(revs, object, "");
-	return 0;
-}
-
-static int add_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data)
-{
-	struct object *object = parse_object(sha1);
-	struct rev_info *revs = (struct rev_info *)cb_data;
-
-	if (!object)
-		die("bad object ref: %s:%s", path, sha1_to_hex(sha1));
-	add_pending_object(revs, object, "");
-
-	return 0;
-}
-
-static int add_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data)
-{
-	for_each_reflog_ent(path, add_one_reflog_ent, cb_data);
-	return 0;
-}
-
-static void add_one_tree(const unsigned char *sha1, struct rev_info *revs)
-{
-	struct tree *tree = lookup_tree(sha1);
-	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++) {
-		lookup_blob(active_cache[i]->sha1);
-		/*
-		 * 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);
-}
-
 int cmd_prune(int argc, const char **argv, const char *prefix)
 {
 	int i;
@@ -261,32 +94,8 @@ int cmd_prune(int argc, const char **argv, const char *prefix)
 	}
 
 	save_commit_buffer = 0;
-
-	/*
-	 * Set up revision parsing, and mark us as being interested
-	 * in all object types, not just commits.
-	 */
 	init_revisions(&revs, prefix);
-	revs.tag_objects = 1;
-	revs.blob_objects = 1;
-	revs.tree_objects = 1;
-
-	/* Add all external refs */
-	for_each_ref(add_one_ref, &revs);
-
-	/* Add all refs from the index file */
-	add_cache_refs(&revs);
-
-	/* Add all reflog info from refs */
-	for_each_ref(add_one_reflog, &revs);
-
-	/*
-	 * Set up the revision walk - this will move all commits
-	 * from the pending list to the commit walking list.
-	 */
-	prepare_revision_walk(&revs);
-
-	walk_commit_list(&revs);
+	mark_reachable_objects(&revs, 1);
 
 	prune_object_dir(get_object_directory());
 
diff --git a/reachable.c b/reachable.c
new file mode 100644
index 0000000..4dfee1d
--- /dev/null
+++ b/reachable.c
@@ -0,0 +1,199 @@
+#include "cache.h"
+#include "refs.h"
+#include "tag.h"
+#include "commit.h"
+#include "blob.h"
+#include "diff.h"
+#include "revision.h"
+#include "reachable.h"
+#include "cache-tree.h"
+
+static void process_blob(struct blob *blob,
+			 struct object_array *p,
+			 struct name_path *path,
+			 const char *name)
+{
+	struct object *obj = &blob->object;
+
+	if (obj->flags & SEEN)
+		return;
+	obj->flags |= SEEN;
+	/* Nothing to do, really .. The blob lookup was the important part */
+}
+
+static void process_tree(struct tree *tree,
+			 struct object_array *p,
+			 struct name_path *path,
+			 const char *name)
+{
+	struct object *obj = &tree->object;
+	struct tree_desc desc;
+	struct name_entry entry;
+	struct name_path me;
+
+	if (obj->flags & SEEN)
+		return;
+	obj->flags |= SEEN;
+	if (parse_tree(tree) < 0)
+		die("bad tree object %s", sha1_to_hex(obj->sha1));
+	name = xstrdup(name);
+	add_object(obj, p, path, name);
+	me.up = path;
+	me.elem = name;
+	me.elem_len = strlen(name);
+
+	desc.buf = tree->buffer;
+	desc.size = tree->size;
+
+	while (tree_entry(&desc, &entry)) {
+		if (S_ISDIR(entry.mode))
+			process_tree(lookup_tree(entry.sha1), p, &me, entry.path);
+		else
+			process_blob(lookup_blob(entry.sha1), p, &me, entry.path);
+	}
+	free(tree->buffer);
+	tree->buffer = NULL;
+}
+
+static void process_tag(struct tag *tag, struct object_array *p, const char *name)
+{
+	struct object *obj = &tag->object;
+	struct name_path me;
+
+	if (obj->flags & SEEN)
+		return;
+	obj->flags |= SEEN;
+
+	me.up = NULL;
+	me.elem = "tag:/";
+	me.elem_len = 5;
+
+	if (parse_tag(tag) < 0)
+		die("bad tag object %s", sha1_to_hex(obj->sha1));
+	add_object(tag->tagged, p, NULL, name);
+}
+
+static void walk_commit_list(struct rev_info *revs)
+{
+	int i;
+	struct commit *commit;
+	struct object_array objects = { 0, 0, NULL };
+
+	/* Walk all commits, process their trees */
+	while ((commit = get_revision(revs)) != NULL)
+		process_tree(commit->tree, &objects, NULL, "");
+
+	/* Then walk all the pending objects, recursively processing them too */
+	for (i = 0; i < revs->pending.nr; i++) {
+		struct object_array_entry *pending = revs->pending.objects + i;
+		struct object *obj = pending->item;
+		const char *name = pending->name;
+		if (obj->type == OBJ_TAG) {
+			process_tag((struct tag *) obj, &objects, name);
+			continue;
+		}
+		if (obj->type == OBJ_TREE) {
+			process_tree((struct tree *)obj, &objects, NULL, name);
+			continue;
+		}
+		if (obj->type == OBJ_BLOB) {
+			process_blob((struct blob *)obj, &objects, NULL, name);
+			continue;
+		}
+		die("unknown pending object %s (%s)", sha1_to_hex(obj->sha1), name);
+	}
+}
+
+static int add_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1, char *datail, void *cb_data)
+{
+	struct object *object;
+	struct rev_info *revs = (struct rev_info *)cb_data;
+
+	object = parse_object(osha1);
+	if (object)
+		add_pending_object(revs, object, "");
+	object = parse_object(nsha1);
+	if (object)
+		add_pending_object(revs, object, "");
+	return 0;
+}
+
+static int add_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data)
+{
+	struct object *object = parse_object(sha1);
+	struct rev_info *revs = (struct rev_info *)cb_data;
+
+	if (!object)
+		die("bad object ref: %s:%s", path, sha1_to_hex(sha1));
+	add_pending_object(revs, object, "");
+
+	return 0;
+}
+
+static int add_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data)
+{
+	for_each_reflog_ent(path, add_one_reflog_ent, cb_data);
+	return 0;
+}
+
+static void add_one_tree(const unsigned char *sha1, struct rev_info *revs)
+{
+	struct tree *tree = lookup_tree(sha1);
+	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++) {
+		lookup_blob(active_cache[i]->sha1);
+		/*
+		 * 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);
+}
+
+void mark_reachable_objects(struct rev_info *revs, int mark_reflog)
+{
+	/*
+	 * Set up revision parsing, and mark us as being interested
+	 * in all object types, not just commits.
+	 */
+	revs->tag_objects = 1;
+	revs->blob_objects = 1;
+	revs->tree_objects = 1;
+
+	/* Add all refs from the index file */
+	add_cache_refs(revs);
+
+	/* Add all external refs */
+	for_each_ref(add_one_ref, revs);
+
+	/* Add all reflog info from refs */
+	if (mark_reflog)
+		for_each_ref(add_one_reflog, revs);
+
+	/*
+	 * Set up the revision walk - this will move all commits
+	 * from the pending list to the commit walking list.
+	 */
+	prepare_revision_walk(revs);
+	walk_commit_list(revs);
+}
diff --git a/reachable.h b/reachable.h
new file mode 100644
index 0000000..4075181
--- /dev/null
+++ b/reachable.h
@@ -0,0 +1,6 @@
+#ifndef REACHEABLE_H
+#define REACHEABLE_H
+
+extern void mark_reachable_objects(struct rev_info *revs, int mark_reflog);
+
+#endif
-- 
cgit v0.10.2-6-g49f6


From 1389d9ddaa68a4cbf5018d88f971b9bbb7aaa3c9 Mon Sep 17 00:00:00 2001
From: Junio C Hamano <junkio@cox.net>
Date: Sat, 6 Jan 2007 02:16:19 -0800
Subject: reflog expire --fix-stale

The logic in an earlier round to detect reflog entries that
point at a broken commit was not sufficient.  Just like we do
not trust presense of a commit during pack transfer (we trust
only our refs), we should not trust a commit's presense, even if
the tree of that commit is complete.

A repository that had reflog enabled on some of the refs that
was rewound and then run git-repack or git-prune from older
versions of git can have reflog entries that point at a commit
that still exist but lack commits (or trees and blobs needed for
that commit) between it and some commit that is reachable from
one of the refs.

This revamps the logic -- the definition of "broken commit"
becomes: a commit that is not reachable from any of the refs and
there is a missing object among the commit, tree, or blob
objects reachable from it that is not reachable from any of the
refs.  Entries in the reflog that refer to such a commit are
expired.

Since this computation involves traversing all the reachable
objects, i.e. it has the same cost as 'git prune', it is enabled
only when a new option --fix-stale.  Fortunately, once this is
run, we should not have to ever worry about missing objects,
because the current prune and pack-objects know about reflogs
and protect objects referred by them.

Unfortunately, this will be absolutely necessary to help people
migrate to the newer prune and repack.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/builtin-reflog.c b/builtin-reflog.c
index d3f2f50..1da7da0 100644
--- a/builtin-reflog.c
+++ b/builtin-reflog.c
@@ -4,16 +4,34 @@
 #include "refs.h"
 #include "dir.h"
 #include "tree-walk.h"
+#include "diff.h"
+#include "revision.h"
+#include "reachable.h"
+
+/*
+ * reflog expire
+ */
+
+static const char reflog_expire_usage[] =
+"git-reflog expire [--verbose] [--dry-run] [--fix-stale] [--expire=<time>] [--expire-unreachable=<time>] [--all] <refs>...";
 
 static unsigned long default_reflog_expire;
 static unsigned long default_reflog_expire_unreachable;
 
+struct cmd_reflog_expire_cb {
+	struct rev_info revs;
+	int dry_run;
+	int stalefix;
+	int verbose;
+	unsigned long expire_total;
+	unsigned long expire_unreachable;
+};
+
 struct expire_reflog_cb {
 	FILE *newlog;
 	const char *ref;
 	struct commit *ref_commit;
-	unsigned long expire_total;
-	unsigned long expire_unreachable;
+	struct cmd_reflog_expire_cb *cmd;
 };
 
 static int tree_is_complete(const unsigned char *sha1)
@@ -43,6 +61,83 @@ static int tree_is_complete(const unsigned char *sha1)
 	return 1;
 }
 
+#define INCOMPLETE	(1u<<10)
+#define STUDYING	(1u<<11)
+
+static int commit_is_complete(struct commit *commit)
+{
+	struct object_array study;
+	struct object_array found;
+	int is_incomplete = 0;
+	int i;
+
+	/* early return */
+	if (commit->object.flags & SEEN)
+		return 1;
+	if (commit->object.flags & INCOMPLETE)
+		return 0;
+	/*
+	 * Find all commits that are reachable and are not marked as
+	 * SEEN.  Then make sure the trees and blobs contained are
+	 * complete.  After that, mark these commits also as SEEN.
+	 * If some of the objects that are needed to complete this
+	 * commit are missing, mark this commit as INCOMPLETE.
+	 */
+	memset(&study, 0, sizeof(study));
+	memset(&found, 0, sizeof(found));
+	add_object_array(&commit->object, NULL, &study);
+	add_object_array(&commit->object, NULL, &found);
+	commit->object.flags |= STUDYING;
+	while (study.nr) {
+		struct commit *c;
+		struct commit_list *parent;
+
+		c = (struct commit *)study.objects[--study.nr].item;
+		if (!c->object.parsed && !parse_object(c->object.sha1))
+			c->object.flags |= INCOMPLETE;
+
+		if (c->object.flags & INCOMPLETE) {
+			is_incomplete = 1;
+			break;
+		}
+		else if (c->object.flags & SEEN)
+			continue;
+		for (parent = c->parents; parent; parent = parent->next) {
+			struct commit *p = parent->item;
+			if (p->object.flags & STUDYING)
+				continue;
+			p->object.flags |= STUDYING;
+			add_object_array(&p->object, NULL, &study);
+			add_object_array(&p->object, NULL, &found);
+		}
+	}
+	if (!is_incomplete) {
+		/* make sure all commits in found have all the
+		 * necessary objects.
+		 */
+		for (i = 0; !is_incomplete && i < found.nr; i++) {
+			struct commit *c =
+				(struct commit *)found.objects[i].item;
+			if (!tree_is_complete(c->tree->object.sha1))
+				is_incomplete = 1;
+		}
+		if (!is_incomplete) {
+			/* mark all found commits as complete, iow SEEN */
+			for (i = 0; i < found.nr; i++)
+				found.objects[i].item->flags |= SEEN;
+		}
+	}
+	/* clear flags from the objects we traversed */
+	for (i = 0; i < found.nr; i++)
+		found.objects[i].item->flags &= ~STUDYING;
+	if (is_incomplete)
+		commit->object.flags |= INCOMPLETE;
+	/* free object arrays */
+	free(study.objects);
+	free(found.objects);
+	return !is_incomplete;
+}
+
 static int keep_entry(struct commit **it, unsigned char *sha1)
 {
 	struct commit *commit;
@@ -54,9 +149,15 @@ static int keep_entry(struct commit **it, unsigned char *sha1)
 	if (!commit)
 		return 0;
 
-	/* Make sure everything in this commit exists. */
-	parse_object(commit->object.sha1);
-	if (!tree_is_complete(commit->tree->object.sha1))
+	/*
+	 * Make sure everything in this commit exists.
+	 *
+	 * We have walked all the objects reachable from the refs
+	 * and cache earlier.  The commits reachable by this commit
+	 * must meet SEEN commits -- and then we should mark them as
+	 * SEEN as well.
+	 */
+	if (!commit_is_complete(commit))
 		return 0;
 	*it = commit;
 	return 1;
@@ -76,13 +177,14 @@ static int expire_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
 	timestamp = strtoul(cp, &ep, 10);
 	if (*ep != ' ')
 		goto prune;
-	if (timestamp < cb->expire_total)
+	if (timestamp < cb->cmd->expire_total)
 		goto prune;
 
-	if (!keep_entry(&old, osha1) || !keep_entry(&new, nsha1))
+	if (cb->cmd->stalefix &&
+	    (!keep_entry(&old, osha1) || !keep_entry(&new, nsha1)))
 		goto prune;
 
-	if ((timestamp < cb->expire_unreachable) &&
+	if ((timestamp < cb->cmd->expire_unreachable) &&
 	    (!cb->ref_commit ||
 	     (old && !in_merge_bases(old, cb->ref_commit)) ||
 	     (new && !in_merge_bases(new, cb->ref_commit))))
@@ -91,19 +193,15 @@ static int expire_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
 	if (cb->newlog)
 		fprintf(cb->newlog, "%s %s %s",
 			sha1_to_hex(osha1), sha1_to_hex(nsha1), data);
+	if (cb->cmd->verbose)
+		printf("keep %s", data);
 	return 0;
  prune:
-	if (!cb->newlog)
-		fprintf(stderr, "would prune %s", data);
+	if (!cb->newlog || cb->cmd->verbose)
+		printf("%sprune %s", cb->newlog ? "" : "would ", data);
 	return 0;
 }
 
-struct cmd_reflog_expire_cb {
-	int dry_run;
-	unsigned long expire_total;
-	unsigned long expire_unreachable;
-};
-
 static int expire_reflog(const char *ref, const unsigned char *sha1, int unused, void *cb_data)
 {
 	struct cmd_reflog_expire_cb *cmd = cb_data;
@@ -134,8 +232,7 @@ static int expire_reflog(const char *ref, const unsigned char *sha1, int unused,
 		fprintf(stderr,
 			"warning: ref '%s' does not point at a commit\n", ref);
 	cb.ref = ref;
-	cb.expire_total = cmd->expire_total;
-	cb.expire_unreachable = cmd->expire_unreachable;
+	cb.cmd = cmd;
 	for_each_reflog_ent(ref, expire_reflog_ent, &cb);
  finish:
 	if (cb.newlog) {
@@ -164,9 +261,6 @@ static int reflog_expire_config(const char *var, const char *value)
 	return 0;
 }
 
-static const char reflog_expire_usage[] =
-"git-reflog expire [--dry-run] [--expire=<time>] [--expire-unreachable=<time>] [--all] <refs>...";
-
 static int cmd_reflog_expire(int argc, const char **argv, const char *prefix)
 {
 	struct cmd_reflog_expire_cb cb;
@@ -186,6 +280,12 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix)
 	cb.expire_total = default_reflog_expire;
 	cb.expire_unreachable = default_reflog_expire_unreachable;
 
+	/*
+	 * We can trust the commits and objects reachable from refs
+	 * even in older repository.  We cannot trust what's reachable
+	 * from reflog if the repository was pruned with older git.
+	 */
+
 	for (i = 1; i < argc; i++) {
 		const char *arg = argv[i];
 		if (!strcmp(arg, "--dry-run") || !strcmp(arg, "-n"))
@@ -194,8 +294,12 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix)
 			cb.expire_total = approxidate(arg + 9);
 		else if (!strncmp(arg, "--expire-unreachable=", 21))
 			cb.expire_unreachable = approxidate(arg + 21);
+		else if (!strcmp(arg, "--stale-fix"))
+			cb.stalefix = 1;
 		else if (!strcmp(arg, "--all"))
 			do_all = 1;
+		else if (!strcmp(arg, "--verbose"))
+			cb.verbose = 1;
 		else if (!strcmp(arg, "--")) {
 			i++;
 			break;
@@ -205,6 +309,15 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix)
 		else
 			break;
 	}
+	if (cb.stalefix) {
+		init_revisions(&cb.revs, prefix);
+		if (cb.verbose)
+			printf("Marking reachable objects...");
+		mark_reachable_objects(&cb.revs, 0);
+		if (cb.verbose)
+			putchar('\n');
+	}
+
 	if (do_all)
 		status |= for_each_ref(expire_reflog, &cb);
 	while (i < argc) {
@@ -219,6 +332,10 @@ static int cmd_reflog_expire(int argc, const char **argv, const char *prefix)
 	return status;
 }
 
+/*
+ * main "reflog"
+ */
+
 static const char reflog_usage[] =
 "git-reflog (expire | ...)";
 
diff --git a/t/t1410-reflog.sh b/t/t1410-reflog.sh
new file mode 100755
index 0000000..738d151
--- /dev/null
+++ b/t/t1410-reflog.sh
@@ -0,0 +1,176 @@
+#!/bin/sh
+#
+# Copyright (c) 2007 Junio C Hamano
+#
+
+test_description='Test prune and reflog expiration'
+. ./test-lib.sh
+
+check_have () {
+	gaah= &&
+	for N in "$@"
+	do
+		eval "o=\$$N" && git cat-file -t $o || {
+			echo Gaah $N
+			gaah=$N
+			break
+		}
+	done &&
+	test -z "$gaah"
+}
+
+check_fsck () {
+	output=$(git fsck-objects --full)
+	case "$1" in
+	'')
+		test -z "$output" ;;
+	*)
+		echo "$output" | grep "$1" ;;
+	esac
+}
+
+corrupt () {
+	aa=${1%??????????????????????????????????????} zz=${1#??}
+	mv .git/objects/$aa/$zz .git/$aa$zz
+}
+
+recover () {
+	aa=${1%??????????????????????????????????????} zz=${1#??}
+	mkdir -p .git/objects/$aa
+	mv .git/$aa$zz .git/objects/$aa/$zz
+}
+
+check_dont_have () {
+	gaah= &&
+	for N in "$@"
+	do
+		eval "o=\$$N"
+		git cat-file -t $o && {
+			echo Gaah $N
+			gaah=$N
+			break
+		}
+	done
+	test -z "$gaah"
+}
+
+test_expect_success setup '
+	mkdir -p A/B &&
+	echo rat >C &&
+	echo ox >A/D &&
+	echo tiger >A/B/E &&
+	git add . &&
+
+	test_tick && git commit -m rabbit &&
+	H=`git rev-parse --verify HEAD` &&
+	A=`git rev-parse --verify HEAD:A` &&
+	B=`git rev-parse --verify HEAD:A/B` &&
+	C=`git rev-parse --verify HEAD:C` &&
+	D=`git rev-parse --verify HEAD:A/D` &&
+	E=`git rev-parse --verify HEAD:A/B/E` &&
+	check_fsck &&
+
+	chmod +x C &&
+	git add C &&
+	test_tick && git commit -m dragon &&
+	L=`git rev-parse --verify HEAD` &&
+	check_fsck &&
+
+	rm -f C A/B/E &&
+	echo snake >F &&
+	echo horse >A/G &&
+	git add F A/G &&
+	test_tick && git commit -a -m sheep &&
+	F=`git rev-parse --verify HEAD:F` &&
+	G=`git rev-parse --verify HEAD:A/G` &&
+	I=`git rev-parse --verify HEAD:A` &&
+	J=`git rev-parse --verify HEAD` &&
+	check_fsck &&
+
+	rm -f A/G &&
+	test_tick && git commit -a -m monkey &&
+	K=`git rev-parse --verify HEAD` &&
+	check_fsck &&
+
+	check_have A B C D E F G H I J K L &&
+
+	git prune &&
+
+	check_have A B C D E F G H I J K L &&
+
+	check_fsck &&
+
+	loglen=$(wc -l <.git/logs/refs/heads/master) &&
+	test $loglen = 4
+'
+
+test_expect_success rewind '
+	test_tick && git reset --hard HEAD~2 &&
+	test -f C &&
+	test -f A/B/E &&
+	! test -f F &&
+	! test -f A/G &&
+
+	check_have A B C D E F G H I J K L &&
+
+	git prune &&
+
+	check_have A B C D E F G H I J K L &&
+
+	loglen=$(wc -l <.git/logs/refs/heads/master) &&
+	test $loglen = 5
+'
+
+test_expect_success 'corrupt and check' '
+
+	corrupt $F &&
+	check_fsck "missing blob $F"
+
+'
+
+test_expect_success 'reflog expire --dry-run should not touch reflog' '
+
+	git reflog expire --dry-run \
+		--expire=$(($test_tick - 10000)) \
+		--expire-unreachable=$(($test_tick - 10000)) \
+		--stale-fix \
+		--all &&
+
+	loglen=$(wc -l <.git/logs/refs/heads/master) &&
+	test $loglen = 5 &&
+
+	check_fsck "missing blob $F"
+'
+
+test_expect_success 'reflog expire' '
+
+	git reflog expire --verbose \
+		--expire=$(($test_tick - 10000)) \
+		--expire-unreachable=$(($test_tick - 10000)) \
+		--stale-fix \
+		--all &&
+
+	loglen=$(wc -l <.git/logs/refs/heads/master) &&
+	test $loglen = 2 &&
+
+	check_fsck "dangling commit $K"
+'
+
+test_expect_success 'prune and fsck' '
+
+	git prune &&
+	check_fsck &&
+
+	check_have A B C D E H L &&
+	check_dont_have F G I J K
+
+'
+
+test_expect_success 'recover and check' '
+
+	recover $F &&
+	check_fsck "dangling blob $F"
+
+'
+
+test_done
-- 
cgit v0.10.2-6-g49f6


From cd1f9c36beeafd3dea4672494a98e1ed39ae63f1 Mon Sep 17 00:00:00 2001
From: Junio C Hamano <junkio@cox.net>
Date: Sat, 6 Jan 2007 22:32:41 -0800
Subject: reflog --fix-stale: do not check the same trees and commits
 repeatedly.

Since we use the reachability tracking machinery now, we should
keep the already checked trees and commits whose completeness is
known, to avoid checking the same thing over and over again.

Signed-off-by: Junio C Hamano <junkio@cox.net>

diff --git a/builtin-reflog.c b/builtin-reflog.c
index 1da7da0..a967117 100644
--- a/builtin-reflog.c
+++ b/builtin-reflog.c
@@ -34,35 +34,51 @@ struct expire_reflog_cb {
 	struct cmd_reflog_expire_cb *cmd;
 };
 
+#define INCOMPLETE	(1u<<10)
+#define STUDYING	(1u<<11)
+
 static int tree_is_complete(const unsigned char *sha1)
 {
 	struct tree_desc desc;
-	void *buf;
-	char type[20];
+	struct name_entry entry;
+	int complete;
+	struct tree *tree;
 
-	buf = read_sha1_file(sha1, type, &desc.size);
-	if (!buf)
+	tree = lookup_tree(sha1);
+	if (!tree)
+		return 0;
+	if (tree->object.flags & SEEN)
+		return 1;
+	if (tree->object.flags & INCOMPLETE)
 		return 0;
-	desc.buf = buf;
-	while (desc.size) {
-		const unsigned char *elem;
-		const char *name;
-		unsigned mode;
-
-		elem = tree_entry_extract(&desc, &name, &mode);
-		if (!has_sha1_file(elem) ||
-		    (S_ISDIR(mode) && !tree_is_complete(elem))) {
-			free(buf);
+
+	desc.buf = tree->buffer;
+	desc.size = tree->size;
+	if (!desc.buf) {
+		char type[20];
+		void *data = read_sha1_file(sha1, type, &desc.size);
+		if (!data) {
+			tree->object.flags |= INCOMPLETE;
 			return 0;
 		}
-		update_tree_entry(&desc);
+		desc.buf = data;
+		tree->buffer = data;
 	}
-	free(buf);
-	return 1;
-}
+	complete = 1;
+	while (tree_entry(&desc, &entry)) {
+		if (!has_sha1_file(entry.sha1) ||
+		    (S_ISDIR(entry.mode) && !tree_is_complete(entry.sha1))) {
+			tree->object.flags |= INCOMPLETE;
+			complete = 0;
+		}
+	}
+	free(tree->buffer);
+	tree->buffer = NULL;
 
-#define INCOMPLETE	(1u<<10)
-#define STUDYING	(1u<<11)
+	if (complete)
+		tree->object.flags |= SEEN;
+	return complete;
+}
 
 static int commit_is_complete(struct commit *commit)
 {
@@ -112,14 +128,17 @@ static int commit_is_complete(struct commit *commit)
 		}
 	}
 	if (!is_incomplete) {
-		/* make sure all commits in found have all the
+		/*
+		 * make sure all commits in "found" array have all the
 		 * necessary objects.
 		 */
-		for (i = 0; !is_incomplete && i < found.nr; i++) {
+		for (i = 0; i < found.nr; i++) {
 			struct commit *c =
 				(struct commit *)found.objects[i].item;
-			if (!tree_is_complete(c->tree->object.sha1))
+			if (!tree_is_complete(c->tree->object.sha1)) {
 				is_incomplete = 1;
+				c->object.flags |= INCOMPLETE;
+			}
 		}
 		if (!is_incomplete) {
 			/* mark all found commits as complete, iow SEEN */
@@ -132,6 +151,18 @@ static int commit_is_complete(struct commit *commit)
 		found.objects[i].item->flags &= ~STUDYING;
 	if (is_incomplete)
 		commit->object.flags |= INCOMPLETE;
+	else {
+		/*
+		 * If we come here, we have (1) traversed the ancestry chain
+		 * from the "commit" until we reach SEEN commits (which are
+		 * known to be complete), and (2) made sure that the commits
+		 * encountered during the above traversal refer to trees that
+		 * are complete.  Which means that we know *all* the commits
+		 * we have seen during this process are complete.
+		 */
+		for (i = 0; i < found.nr; i++)
+			found.objects[i].item->flags |= SEEN;
+	}
 	/* free object arrays */
 	free(study.objects);
 	free(found.objects);
-- 
cgit v0.10.2-6-g49f6