1 files changed, 186 insertions, 38 deletions

diff --git a/builtin-reflog.c b/builtin-reflog.c
index d3f2f50..a967117 100644
--- a/builtin-reflog.c
+++ b/builtin-reflog.c
@@ -4,43 +4,169 @@
 #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;
 };
 
+#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;
+
+	if (complete)
+		tree->object.flags |= SEEN;
+	return complete;
+}
+
+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" array have all the
+		 * necessary objects.
+		 */
+		for (i = 0; i < found.nr; i++) {
+			struct commit *c =
+				(struct commit *)found.objects[i].item;
+			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 */
+			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;
+	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);
+	return !is_incomplete;
 }
 
 static int keep_entry(struct commit **it, unsigned char *sha1)
@@ -54,9 +180,15 @@ 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 +208,14 @@ 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 +224,15 @@ 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 +263,7 @@ 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 +292,6 @@ 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 +311,12 @@ 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 +325,12 @@ 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 +340,15 @@ 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 +363,10 @@ 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 | ...)";