Merge branch 'jc/fsck-reflog'

* jc/fsck-reflog:
  Add git-reflog to .gitignore
  reflog expire: do not punt on tags that point at non commits.
  reflog expire: prune commits that are not incomplete
  Don't crash during repack of a reflog with pruned commits.
  git reflog expire
  Move in_merge_bases() to commit.c
  reflog: fix warning message.
  Teach git-repack to preserve objects referred to by reflog entries.
  Protect commits recorded in reflog from pruning.
  add for_each_reflog_ent() iterator

15 files changed, 373 insertions, 32 deletions

diff --git a/.gitignore b/.gitignore
index 98e513de5..60e5002bd 100644
--- a/.gitignore
+++ b/.gitignore
@@ -89,6 +89,7 @@ git-quiltimport
 git-read-tree
 git-rebase
 git-receive-pack
+git-reflog
 git-relink
 git-repack
 git-repo-config
diff --git a/Makefile b/Makefile
index 475047f10..52d4a3a86 100644
--- a/Makefile
+++ b/Makefile
@@ -287,6 +287,7 @@ BUILTIN_OBJS = \
 	builtin-prune-packed.o \
 	builtin-push.o \
 	builtin-read-tree.o \
+	builtin-reflog.o \
 	builtin-repo-config.o \
 	builtin-rerere.o \
 	builtin-rev-list.o \
diff --git a/builtin-branch.c b/builtin-branch.c
index 903d5cf05..745ee04d6 100644
--- a/builtin-branch.c
+++ b/builtin-branch.c
@@ -74,25 +74,6 @@ const char *branch_get_color(enum color_branch ix)
 	return "";
 }
 
-static int in_merge_bases(const unsigned char *sha1,
-			  struct commit *rev1,
-			  struct commit *rev2)
-{
-	struct commit_list *bases, *b;
-	int ret = 0;
-
-	bases = get_merge_bases(rev1, rev2, 1);
-	for (b = bases; b; b = b->next) {
-		if (!hashcmp(sha1, b->item->object.sha1)) {
-			ret = 1;
-			break;
-		}
-	}
-
-	free_commit_list(bases);
-	return ret;
-}
-
 static int delete_branches(int argc, const char **argv, int force, int kinds)
 {
 	struct commit *rev, *head_rev = head_rev;
@@ -153,7 +134,7 @@ static int delete_branches(int argc, const char **argv, int force, int kinds)
 		 */
 
 		if (!force &&
-		    !in_merge_bases(sha1, rev, head_rev)) {
+		    !in_merge_bases(rev, head_rev)) {
 			error("The branch '%s' is not a strict subset of "
 				"your current HEAD.\n"
 				"If you are sure you want to delete it, "
diff --git a/builtin-pack-objects.c b/builtin-pack-objects.c
index 807be8c3f..9e15beb3b 100644
--- a/builtin-pack-objects.c
+++ b/builtin-pack-objects.c
@@ -17,7 +17,7 @@ static const char pack_usage[] = "\
 git-pack-objects [{ -q | --progress | --all-progress }] \n\
 	[--local] [--incremental] [--window=N] [--depth=N] \n\
 	[--no-reuse-delta] [--delta-base-offset] [--non-empty] \n\
-	[--revs [--unpacked | --all]*] [--stdout | base-name] \n\
+	[--revs [--unpacked | --all]*] [--reflog] [--stdout | base-name] \n\
 	[<ref-list | <object-list]";
 
 struct object_entry {
@@ -1575,6 +1575,7 @@ int cmd_pack_objects(int argc, const char **argv, const char *prefix)
 		}
 		if (!strcmp("--unpacked", arg) ||
 		    !strncmp("--unpacked=", arg, 11) ||
+		    !strcmp("--reflog", arg) ||
 		    !strcmp("--all", arg)) {
 			use_internal_rev_list = 1;
 			if (ARRAY_SIZE(rp_av) - 1 <= rp_ac)
diff --git a/builtin-prune.c b/builtin-prune.c
index 8591d28b8..00a53b364 100644
--- a/builtin-prune.c
+++ b/builtin-prune.c
@@ -181,12 +181,28 @@ 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;
+
+	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);
 	if (!object)
 		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, NULL);
+
 	return 0;
 }
 
diff --git a/builtin-reflog.c b/builtin-reflog.c
new file mode 100644
index 000000000..de31967b9
--- /dev/null
+++ b/builtin-reflog.c
@@ -0,0 +1,212 @@
+#include "cache.h"
+#include "builtin.h"
+#include "commit.h"
+#include "refs.h"
+#include "dir.h"
+#include "tree-walk.h"
+
+struct expire_reflog_cb {
+	FILE *newlog;
+	const char *ref;
+	struct commit *ref_commit;
+	unsigned long expire_total;
+	unsigned long expire_unreachable;
+};
+
+static int tree_is_complete(const unsigned char *sha1)
+{
+	struct tree_desc desc;
+	void *buf;
+	char type[20];
+
+	buf = read_sha1_file(sha1, type, &desc.size);
+	if (!buf)
+		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);
+			return 0;
+		}
+		update_tree_entry(&desc);
+	}
+	free(buf);
+	return 1;
+}
+
+static int keep_entry(struct commit **it, unsigned char *sha1)
+{
+	struct commit *commit;
+
+	*it = NULL;
+	if (is_null_sha1(sha1))
+		return 1;
+	commit = lookup_commit_reference_gently(sha1, 1);
+	if (!commit)
+		return 0;
+
+	/* Make sure everything in this commit exists. */
+	parse_object(commit->object.sha1);
+	if (!tree_is_complete(commit->tree->object.sha1))
+		return 0;
+	*it = commit;
+	return 1;
+}
+
+static int expire_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
+			     char *data, void *cb_data)
+{
+	struct expire_reflog_cb *cb = cb_data;
+	unsigned long timestamp;
+	char *cp, *ep;
+	struct commit *old, *new;
+
+	cp = strchr(data, '>');
+	if (!cp || *++cp != ' ')
+		goto prune;
+	timestamp = strtoul(cp, &ep, 10);
+	if (*ep != ' ')
+		goto prune;
+	if (timestamp < cb->expire_total)
+		goto prune;
+
+	if (!keep_entry(&old, osha1) || !keep_entry(&new, nsha1))
+		goto prune;
+
+	if ((timestamp < cb->expire_unreachable) &&
+	    (!cb->ref_commit ||
+	     (old && !in_merge_bases(old, cb->ref_commit)) ||
+	     (new && !in_merge_bases(new, cb->ref_commit))))
+		goto prune;
+
+	if (cb->newlog)
+		fprintf(cb->newlog, "%s %s %s",
+			sha1_to_hex(osha1), sha1_to_hex(nsha1), data);
+	return 0;
+ prune:
+	if (!cb->newlog)
+		fprintf(stderr, "would prune %s", 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;
+	struct expire_reflog_cb cb;
+	struct ref_lock *lock;
+	char *newlog_path = NULL;
+	int status = 0;
+
+	if (strncmp(ref, "refs/", 5))
+		return error("not a ref '%s'", ref);
+
+	memset(&cb, 0, sizeof(cb));
+	/* we take the lock for the ref itself to prevent it from
+	 * getting updated.
+	 */
+	lock = lock_ref_sha1(ref + 5, sha1);
+	if (!lock)
+		return error("cannot lock ref '%s'", ref);
+	if (!file_exists(lock->log_file))
+		goto finish;
+	if (!cmd->dry_run) {
+		newlog_path = xstrdup(git_path("logs/%s.lock", ref));
+		cb.newlog = fopen(newlog_path, "w");
+	}
+
+	cb.ref_commit = lookup_commit_reference_gently(sha1, 1);
+	if (!cb.ref_commit)
+		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;
+	for_each_reflog_ent(ref, expire_reflog_ent, &cb);
+ finish:
+	if (cb.newlog) {
+		if (fclose(cb.newlog))
+			status |= error("%s: %s", strerror(errno),
+					newlog_path);
+		if (rename(newlog_path, lock->log_file)) {
+			status |= error("cannot rename %s to %s",
+					newlog_path, lock->log_file);
+			unlink(newlog_path);
+		}
+	}
+	free(newlog_path);
+	unlock_ref(lock);
+	return status;
+}
+
+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;
+	unsigned long now = time(NULL);
+	int i, status, do_all;
+
+	save_commit_buffer = 0;
+	do_all = status = 0;
+	memset(&cb, 0, sizeof(cb));
+	cb.expire_total = now - 90 * 24 * 3600;
+	cb.expire_unreachable = now - 30 * 24 * 3600;
+
+	for (i = 1; i < argc; i++) {
+		const char *arg = argv[i];
+		if (!strcmp(arg, "--dry-run") || !strcmp(arg, "-n"))
+			cb.dry_run = 1;
+		else if (!strncmp(arg, "--expire=", 9))
+			cb.expire_total = approxidate(arg + 9);
+		else if (!strncmp(arg, "--expire-unreachable=", 21))
+			cb.expire_unreachable = approxidate(arg + 21);
+		else if (!strcmp(arg, "--all"))
+			do_all = 1;
+		else if (!strcmp(arg, "--")) {
+			i++;
+			break;
+		}
+		else if (arg[0] == '-')
+			usage(reflog_expire_usage);
+		else
+			break;
+	}
+	if (do_all)
+		status |= for_each_ref(expire_reflog, &cb);
+	while (i < argc) {
+		const char *ref = argv[i++];
+		unsigned char sha1[20];
+		if (!resolve_ref(ref, sha1, 1, NULL)) {
+			status |= error("%s points nowhere!", ref);
+			continue;
+		}
+		status |= expire_reflog(ref, sha1, 0, &cb);
+	}
+	return status;
+}
+
+static const char reflog_usage[] =
+"git-reflog (expire | ...)";
+
+int cmd_reflog(int argc, const char **argv, const char *prefix)
+{
+	if (argc < 2)
+		usage(reflog_usage);
+	else if (!strcmp(argv[1], "expire"))
+		return cmd_reflog_expire(argc - 1, argv + 1, prefix);
+	else
+		usage(reflog_usage);
+}
diff --git a/builtin.h b/builtin.h
index 8ffd8b265..df72d0944 100644
--- a/builtin.h
+++ b/builtin.h
@@ -51,6 +51,7 @@ extern int cmd_prune(int argc, const char **argv, const char *prefix);
 extern int cmd_prune_packed(int argc, const char **argv, const char *prefix);
 extern int cmd_push(int argc, const char **argv, const char *prefix);
 extern int cmd_read_tree(int argc, const char **argv, const char *prefix);
+extern int cmd_reflog(int argc, const char **argv, const char *prefix);
 extern int cmd_repo_config(int argc, const char **argv, const char *prefix);
 extern int cmd_rerere(int argc, const char **argv, const char *prefix);
 extern int cmd_rev_list(int argc, const char **argv, const char *prefix);
diff --git a/commit.c b/commit.c
index 289ef65eb..3167ce62a 100644
--- a/commit.c
+++ b/commit.c
@@ -1009,3 +1009,20 @@ struct commit_list *get_merge_bases(struct commit *one,
 	free(rslt);
 	return result;
 }
+
+int in_merge_bases(struct commit *rev1, struct commit *rev2)
+{
+	struct commit_list *bases, *b;
+	int ret = 0;
+
+	bases = get_merge_bases(rev1, rev2, 1);
+	for (b = bases; b; b = b->next) {
+		if (!hashcmp(rev1->object.sha1, b->item->object.sha1)) {
+			ret = 1;
+			break;
+		}
+	}
+
+	free_commit_list(bases);
+	return ret;
+}
diff --git a/commit.h b/commit.h
index fc13de978..10eea9f26 100644
--- a/commit.h
+++ b/commit.h
@@ -107,4 +107,5 @@ int read_graft_file(const char *graft_file);
 
 extern struct commit_list *get_merge_bases(struct commit *rev1, struct commit *rev2, int cleanup);
 
+int in_merge_bases(struct commit *rev1, struct commit *rev2);
 #endif /* COMMIT_H */
diff --git a/fsck-objects.c b/fsck-objects.c
index 409aea02b..1cc3b399b 100644
--- a/fsck-objects.c
+++ b/fsck-objects.c
@@ -399,6 +399,25 @@ static void fsck_dir(int i, char *path)
 
 static int default_refs;
 
+static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1, char *datail, void *cb_data)
+{
+	struct object *obj;
+
+	if (!is_null_sha1(osha1)) {
+		obj = lookup_object(osha1);
+		if (obj) {
+			obj->used = 1;
+			mark_reachable(obj, REACHABLE);
+		}
+	}
+	obj = lookup_object(nsha1);
+	if (obj) {
+		obj->used = 1;
+		mark_reachable(obj, REACHABLE);
+	}
+	return 0;
+}
+
 static int fsck_handle_ref(const char *refname, const unsigned char *sha1, int flag, void *cb_data)
 {
 	struct object *obj;
@@ -416,6 +435,9 @@ static int fsck_handle_ref(const char *refname, const unsigned char *sha1, int f
 	default_refs++;
 	obj->used = 1;
 	mark_reachable(obj, REACHABLE);
+
+	for_each_reflog_ent(refname, fsck_handle_reflog_ent, NULL);
+
 	return 0;
 }
 
diff --git a/git-repack.sh b/git-repack.sh
index 067898f12..375434b1d 100755
--- a/git-repack.sh
+++ b/git-repack.sh
@@ -62,7 +62,7 @@ case ",$all_into_one," in
 esac
 
 args="$args $local $quiet $no_reuse_delta$extra"
-name=$(git-pack-objects --non-empty --all $args </dev/null "$PACKTMP") ||
+name=$(git-pack-objects --non-empty --all --reflog $args </dev/null "$PACKTMP") ||
 	exit 1
 if [ -z "$name" ]; then
 	echo Nothing new to pack.
diff --git a/git.c b/git.c
index e732a098f..50ebd869a 100644
--- a/git.c
+++ b/git.c
@@ -246,6 +246,7 @@ static void handle_internal_command(int argc, const char **argv, char **envp)
 		{ "prune-packed", cmd_prune_packed, RUN_SETUP },
 		{ "push", cmd_push, RUN_SETUP },
 		{ "read-tree", cmd_read_tree, RUN_SETUP },
+		{ "reflog", cmd_reflog, RUN_SETUP },
 		{ "repo-config", cmd_repo_config },
 		{ "rerere", cmd_rerere, RUN_SETUP },
 		{ "rev-list", cmd_rev_list, RUN_SETUP },
diff --git a/refs.c b/refs.c
index a101ff3bf..8b2a3c137 100644
--- a/refs.c
+++ b/refs.c
@@ -1013,7 +1013,7 @@ int read_ref_at(const char *ref, unsigned long at_time, int cnt, unsigned char *
 {
 	const char *logfile, *logdata, *logend, *rec, *lastgt, *lastrec;
 	char *tz_c;
-	int logfd, tz;
+	int logfd, tz, reccnt = 0;
 	struct stat st;
 	unsigned long date;
 	unsigned char logged_sha1[20];
@@ -1031,6 +1031,7 @@ int read_ref_at(const char *ref, unsigned long at_time, int cnt, unsigned char *
 	lastrec = NULL;
 	rec = logend = logdata + st.st_size;
 	while (logdata < rec) {
+		reccnt++;
 		if (logdata < rec && *(rec-1) == '\n')
 			rec--;
 		lastgt = NULL;
@@ -1087,7 +1088,37 @@ int read_ref_at(const char *ref, unsigned long at_time, int cnt, unsigned char *
 	if (get_sha1_hex(logdata, sha1))
 		die("Log %s is corrupt.", logfile);
 	munmap((void*)logdata, st.st_size);
-	fprintf(stderr, "warning: Log %s only goes back to %s.\n",
-		logfile, show_rfc2822_date(date, tz));
+	if (at_time)
+		fprintf(stderr, "warning: Log %s only goes back to %s.\n",
+			logfile, show_rfc2822_date(date, tz));
+	else
+		fprintf(stderr, "warning: Log %s only has %d entries.\n",
+			logfile, reccnt);
 	return 0;
 }
+
+void for_each_reflog_ent(const char *ref, each_reflog_ent_fn fn, void *cb_data)
+{
+	const char *logfile;
+	FILE *logfp;
+	char buf[1024];
+
+	logfile = git_path("logs/%s", ref);
+	logfp = fopen(logfile, "r");
+	if (!logfp)
+		return;
+	while (fgets(buf, sizeof(buf), logfp)) {
+		unsigned char osha1[20], nsha1[20];
+		int len;
+
+		/* old SP new SP name <email> SP time TAB msg LF */
+		len = strlen(buf);
+		if (len < 83 || buf[len-1] != '\n' ||
+		    get_sha1_hex(buf, osha1) || buf[40] != ' ' ||
+		    get_sha1_hex(buf + 41, nsha1) || buf[81] != ' ')
+			continue; /* corrupt? */
+		fn(osha1, nsha1, buf+82, cb_data);
+	}
+	fclose(logfp);
+}
+
diff --git a/refs.h b/refs.h
index 51aab1e6b..de43cc768 100644
--- a/refs.h
+++ b/refs.h
@@ -44,6 +44,10 @@ extern int write_ref_sha1(struct ref_lock *lock, const unsigned char *sha1, cons
 /** Reads log for the value of ref during at_time. **/
 extern int read_ref_at(const char *ref, unsigned long at_time, int cnt, unsigned char *sha1);
 
+/* iterate over reflog entries */
+typedef int each_reflog_ent_fn(unsigned char *osha1, unsigned char *nsha1, char *, void *);
+void for_each_reflog_ent(const char *ref, each_reflog_ent_fn fn, void *cb_data);
+
 /** Returns 0 if target has the right format for a ref. **/
 extern int check_ref_format(const char *target);
 
diff --git a/revision.c b/revision.c
index e7eccd918..af9f87418 100644
--- a/revision.c
+++ b/revision.c
@@ -464,21 +464,69 @@ static void limit_list(struct rev_info *revs)
 	revs->commits = newlist;
 }
 
-static int all_flags;
-static struct rev_info *all_revs;
+struct all_refs_cb {
+	int all_flags;
+	int warned_bad_reflog;
+	struct rev_info *all_revs;
+	const char *name_for_errormsg;
+};
 
 static int handle_one_ref(const char *path, const unsigned char *sha1, int flag, void *cb_data)
 {
-	struct object *object = get_reference(all_revs, path, sha1, all_flags);
-	add_pending_object(all_revs, object, "");
+	struct all_refs_cb *cb = cb_data;
+	struct object *object = get_reference(cb->all_revs, path, sha1,
+					      cb->all_flags);
+	add_pending_object(cb->all_revs, object, "");
 	return 0;
 }
 
 static void handle_all(struct rev_info *revs, unsigned flags)
 {
-	all_revs = revs;
-	all_flags = flags;
-	for_each_ref(handle_one_ref, NULL);
+	struct all_refs_cb cb;
+	cb.all_revs = revs;
+	cb.all_flags = flags;
+	for_each_ref(handle_one_ref, &cb);
+}
+
+static void handle_one_reflog_commit(unsigned char *sha1, void *cb_data)
+{
+	struct all_refs_cb *cb = cb_data;
+	if (!is_null_sha1(sha1)) {
+		struct object *o = parse_object(sha1);
+		if (o) {
+			o->flags |= cb->all_flags;
+			add_pending_object(cb->all_revs, o, "");
+		}
+		else if (!cb->warned_bad_reflog) {
+			warn("reflog of '%s' references pruned commits",
+				cb->name_for_errormsg);
+			cb->warned_bad_reflog = 1;
+		}
+	}
+}
+
+static int handle_one_reflog_ent(unsigned char *osha1, unsigned char *nsha1, char *detail, void *cb_data)
+{
+	handle_one_reflog_commit(osha1, cb_data);
+	handle_one_reflog_commit(nsha1, cb_data);
+	return 0;
+}
+
+static int handle_one_reflog(const char *path, const unsigned char *sha1, int flag, void *cb_data)
+{
+	struct all_refs_cb *cb = cb_data;
+	cb->warned_bad_reflog = 0;
+	cb->name_for_errormsg = path;
+	for_each_reflog_ent(path, handle_one_reflog_ent, cb_data);
+	return 0;
+}
+
+static void handle_reflog(struct rev_info *revs, unsigned flags)
+{
+	struct all_refs_cb cb;
+	cb.all_revs = revs;
+	cb.all_flags = flags;
+	for_each_ref(handle_one_reflog, &cb);
 }
 
 static int add_parents_only(struct rev_info *revs, const char *arg, int flags)
@@ -810,6 +858,10 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, const ch
 				handle_all(revs, flags);
 				continue;
 			}
+			if (!strcmp(arg, "--reflog")) {
+				handle_reflog(revs, flags);
+				continue;
+			}
 			if (!strcmp(arg, "--not")) {
 				flags ^= UNINTERESTING;
 				continue;