Merge branch 'js/fsck-name-object'

When "git fsck" reports a broken link (e.g. a tree object contains
a blob that does not exist), both containing object and the object
that is referred to were reported with their 40-hex object names.
The command learned the "--name-objects" option to show the path to
the containing object from existing refs (e.g. "HEAD~24^2:file.txt").

* js/fsck-name-object:
  fsck: optionally show more helpful info for broken links
  fsck: give the error function a chance to see the fsck_options
  fsck_walk(): optionally name objects on the go
  fsck: refactor how to describe objects

Documentation/git-fsck.txt

@@ -11,7 +11,8 @@ SYNOPSIS
 [verse]
 'git fsck' [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]
 	 [--[no-]full] [--strict] [--verbose] [--lost-found]
-	 [--[no-]dangling] [--[no-]progress] [--connectivity-only] [<object>*]
+	 [--[no-]dangling] [--[no-]progress] [--connectivity-only]
+	 [--[no-]name-objects] [<object>*]
 
 DESCRIPTION
 -----------
@@ -82,6 +83,12 @@ index file, all SHA-1 references in `refs` namespace, and all reflogs
 	a blob, the contents are written into the file, rather than
 	its object name.
 
+--name-objects::
+	When displaying names of reachable objects, in addition to the
+	SHA-1 also display a name that describes *how* they are reachable,
+	compatible with linkgit:git-rev-parse[1], e.g.
+	`HEAD@{1234567890}~25^2:src/`.
+
 --[no-]progress::
 	Progress status is reported on the standard error stream by
 	default when it is attached to a terminal, unless

builtin/fsck.c

@@ -13,6 +13,7 @@
 #include "dir.h"
 #include "progress.h"
 #include "streaming.h"
+#include "decorate.h"
 
 #define REACHABLE 0x0001
 #define SEEN      0x0002
@@ -35,11 +36,26 @@ static int write_lost_and_found;
 static int verbose;
 static int show_progress = -1;
 static int show_dangling = 1;
+static int name_objects;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 #define ERROR_PACK 04
 #define ERROR_REFS 010
 
+static const char *describe_object(struct object *obj)
+{
+	static struct strbuf buf = STRBUF_INIT;
+	char *name = name_objects ?
+		lookup_decoration(fsck_walk_options.object_names, obj) : NULL;
+
+	strbuf_reset(&buf);
+	strbuf_addstr(&buf, oid_to_hex(&obj->oid));
+	if (name)
+		strbuf_addf(&buf, " (%s)", name);
+
+	return buf.buf;
+}
+
 static int fsck_config(const char *var, const char *value, void *cb)
 {
 	if (strcmp(var, "fsck.skiplist") == 0) {
@@ -67,7 +83,7 @@ static void objreport(struct object *obj, const char *msg_type,
 			const char *err)
 {
 	fprintf(stderr, "%s in %s %s: %s\n",
-		msg_type, typename(obj->type), oid_to_hex(&obj->oid), err);
+		msg_type, typename(obj->type), describe_object(obj), err);
 }
 
 static int objerror(struct object *obj, const char *err)
@@ -77,7 +93,8 @@ static int objerror(struct object *obj, const char *err)
 	return -1;
 }
 
-static int fsck_error_func(struct object *obj, int type, const char *message)
+static int fsck_error_func(struct fsck_options *o,
+	struct object *obj, int type, const char *message)
 {
 	objreport(obj, (type == FSCK_WARN) ? "warning" : "error", message);
 	return (type == FSCK_WARN) ? 0 : 1;
@@ -97,7 +114,7 @@ static int mark_object(struct object *obj, int type, void *data, struct fsck_opt
 	if (!obj) {
 		/* ... these references to parent->fld are safe here */
 		printf("broken link from %7s %s\n",
-			   typename(parent->type), oid_to_hex(&parent->oid));
+			   typename(parent->type), describe_object(parent));
 		printf("broken link from %7s %s\n",
 			   (type == OBJ_ANY ? "unknown" : typename(type)), "unknown");
 		errors_found |= ERROR_REACHABLE;
@@ -114,9 +131,9 @@ static int mark_object(struct object *obj, int type, void *data, struct fsck_opt
 	if (!(obj->flags & HAS_OBJ)) {
 		if (parent && !has_object_file(&obj->oid)) {
 			printf("broken link from %7s %s\n",
-				 typename(parent->type), oid_to_hex(&parent->oid));
+				 typename(parent->type), describe_object(parent));
 			printf("              to %7s %s\n",
-				 typename(obj->type), oid_to_hex(&obj->oid));
+				 typename(obj->type), describe_object(obj));
 			errors_found |= ERROR_REACHABLE;
 		}
 		return 1;
@@ -190,7 +207,8 @@ static void check_reachable_object(struct object *obj)
 			return; /* it is in pack - forget about it */
 		if (connectivity_only && has_object_file(&obj->oid))
 			return;
-		printf("missing %s %s\n", typename(obj->type), oid_to_hex(&obj->oid));
+		printf("missing %s %s\n", typename(obj->type),
+			describe_object(obj));
 		errors_found |= ERROR_REACHABLE;
 		return;
 	}
@@ -215,7 +233,8 @@ static void check_unreachable_object(struct object *obj)
 	 * since this is something that is prunable.
 	 */
 	if (show_unreachable) {
-		printf("unreachable %s %s\n", typename(obj->type), oid_to_hex(&obj->oid));
+		printf("unreachable %s %s\n", typename(obj->type),
+			describe_object(obj));
 		return;
 	}
 
@@ -234,11 +253,11 @@ static void check_unreachable_object(struct object *obj)
 	if (!obj->used) {
 		if (show_dangling)
 			printf("dangling %s %s\n", typename(obj->type),
-			       oid_to_hex(&obj->oid));
+			       describe_object(obj));
 		if (write_lost_and_found) {
 			char *filename = git_pathdup("lost-found/%s/%s",
 				obj->type == OBJ_COMMIT ? "commit" : "other",
-				oid_to_hex(&obj->oid));
+				describe_object(obj));
 			FILE *f;
 
 			if (safe_create_leading_directories_const(filename)) {
@@ -252,7 +271,7 @@ static void check_unreachable_object(struct object *obj)
 				if (stream_blob_to_fd(fileno(f), obj->oid.hash, NULL, 1))
 					die_errno("Could not write '%s'", filename);
 			} else
-				fprintf(f, "%s\n", oid_to_hex(&obj->oid));
+				fprintf(f, "%s\n", describe_object(obj));
 			if (fclose(f))
 				die_errno("Could not finish '%s'",
 					  filename);
@@ -271,7 +290,7 @@ static void check_unreachable_object(struct object *obj)
 static void check_object(struct object *obj)
 {
 	if (verbose)
-		fprintf(stderr, "Checking %s\n", oid_to_hex(&obj->oid));
+		fprintf(stderr, "Checking %s\n", describe_object(obj));
 
 	if (obj->flags & REACHABLE)
 		check_reachable_object(obj);
@@ -307,7 +326,7 @@ static int fsck_obj(struct object *obj)
 
 	if (verbose)
 		fprintf(stderr, "Checking %s %s\n",
-			typename(obj->type), oid_to_hex(&obj->oid));
+			typename(obj->type), describe_object(obj));
 
 	if (fsck_walk(obj, NULL, &fsck_obj_options))
 		objerror(obj, "broken links");
@@ -326,15 +345,17 @@ static int fsck_obj(struct object *obj)
 		free_commit_buffer(commit);
 
 		if (!commit->parents && show_root)
-			printf("root %s\n", oid_to_hex(&commit->object.oid));
+			printf("root %s\n", describe_object(&commit->object));
 	}
 
 	if (obj->type == OBJ_TAG) {
 		struct tag *tag = (struct tag *) obj;
 
 		if (show_tags && tag->tagged) {
-			printf("tagged %s %s", typename(tag->tagged->type), oid_to_hex(&tag->tagged->oid));
+			printf("tagged %s %s", typename(tag->tagged->type),
-			printf(" (%s) in %s\n", tag->tag, oid_to_hex(&tag->object.oid));
+				describe_object(tag->tagged));
+			printf(" (%s) in %s\n", tag->tag,
+				describe_object(&tag->object));
 		}
 	}
 
@@ -368,13 +389,18 @@ static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type,
 
 static int default_refs;
 
-static void fsck_handle_reflog_sha1(const char *refname, unsigned char *sha1)
+static void fsck_handle_reflog_sha1(const char *refname, unsigned char *sha1,
+	unsigned long timestamp)
 {
 	struct object *obj;
 
 	if (!is_null_sha1(sha1)) {
 		obj = lookup_object(sha1);
 		if (obj) {
+			if (timestamp && name_objects)
+				add_decoration(fsck_walk_options.object_names,
+					obj,
+					xstrfmt("%s@{%ld}", refname, timestamp));
 			obj->used = 1;
 			mark_object_reachable(obj);
 		} else {
@@ -394,8 +420,8 @@ static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
 		fprintf(stderr, "Checking reflog %s->%s\n",
 			sha1_to_hex(osha1), sha1_to_hex(nsha1));
 
-	fsck_handle_reflog_sha1(refname, osha1);
+	fsck_handle_reflog_sha1(refname, osha1, 0);
-	fsck_handle_reflog_sha1(refname, nsha1);
+	fsck_handle_reflog_sha1(refname, nsha1, timestamp);
 	return 0;
 }
 
@@ -424,6 +450,9 @@ static int fsck_handle_ref(const char *refname, const struct object_id *oid,
 	}
 	default_refs++;
 	obj->used = 1;
+	if (name_objects)
+		add_decoration(fsck_walk_options.object_names,
+			obj, xstrdup(refname));
 	mark_object_reachable(obj);
 
 	return 0;
@@ -539,6 +568,9 @@ static int fsck_cache_tree(struct cache_tree *it)
 			return 1;
 		}
 		obj->used = 1;
+		if (name_objects)
+			add_decoration(fsck_walk_options.object_names,
+				obj, xstrdup(":"));
 		mark_object_reachable(obj);
 		if (obj->type != OBJ_TREE)
 			err |= objerror(obj, "non-tree in cache-tree");
@@ -567,6 +599,7 @@ static struct option fsck_opts[] = {
 	OPT_BOOL(0, "lost-found", &write_lost_and_found,
 				N_("write dangling objects in .git/lost-found")),
 	OPT_BOOL(0, "progress", &show_progress, N_("show progress")),
+	OPT_BOOL(0, "name-objects", &name_objects, N_("show verbose names for reachable objects")),
 	OPT_END(),
 };
 
@@ -596,6 +629,10 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 		include_reflogs = 0;
 	}
 
+	if (name_objects)
+		fsck_walk_options.object_names =
+			xcalloc(1, sizeof(struct decoration));
+
 	git_config(fsck_config, NULL);
 
 	fsck_head_link();
@@ -651,6 +688,9 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 				continue;
 
 			obj->used = 1;
+			if (name_objects)
+				add_decoration(fsck_walk_options.object_names,
+					obj, xstrdup(arg));
 			mark_object_reachable(obj);
 			heads++;
 			continue;
@@ -683,6 +723,10 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 				continue;
 			obj = &blob->object;
 			obj->used = 1;
+			if (name_objects)
+				add_decoration(fsck_walk_options.object_names,
+					obj,
+					xstrfmt(":%s", active_cache[i]->name));
 			mark_object_reachable(obj);
 		}
 		if (active_cache_tree)

fsck.c

@@ -9,6 +9,7 @@
 #include "refs.h"
 #include "utf8.h"
 #include "sha1-array.h"
+#include "decorate.h"
 
 #define FSCK_FATAL -1
 #define FSCK_INFO -2
@@ -290,35 +291,87 @@ static int report(struct fsck_options *options, struct object *object,
 
 	va_start(ap, fmt);
 	strbuf_vaddf(&sb, fmt, ap);
-	result = options->error_func(object, msg_type, sb.buf);
+	result = options->error_func(options, object, msg_type, sb.buf);
 	strbuf_release(&sb);
 	va_end(ap);
 
 	return result;
 }
 
+static char *get_object_name(struct fsck_options *options, struct object *obj)
+{
+	if (!options->object_names)
+		return NULL;
+	return lookup_decoration(options->object_names, obj);
+}
+
+static void put_object_name(struct fsck_options *options, struct object *obj,
+	const char *fmt, ...)
+{
+	va_list ap;
+	struct strbuf buf = STRBUF_INIT;
+	char *existing;
+
+	if (!options->object_names)
+		return;
+	existing = lookup_decoration(options->object_names, obj);
+	if (existing)
+		return;
+	va_start(ap, fmt);
+	strbuf_vaddf(&buf, fmt, ap);
+	add_decoration(options->object_names, obj, strbuf_detach(&buf, NULL));
+	va_end(ap);
+}
+
+static const char *describe_object(struct fsck_options *o, struct object *obj)
+{
+	static struct strbuf buf = STRBUF_INIT;
+	char *name;
+
+	strbuf_reset(&buf);
+	strbuf_addstr(&buf, oid_to_hex(&obj->oid));
+	if (o->object_names && (name = lookup_decoration(o->object_names, obj)))
+		strbuf_addf(&buf, " (%s)", name);
+
+	return buf.buf;
+}
+
 static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *options)
 {
 	struct tree_desc desc;
 	struct name_entry entry;
 	int res = 0;
+	const char *name;
 
 	if (parse_tree(tree))
 		return -1;
 
+	name = get_object_name(options, &tree->object);
 	init_tree_desc(&desc, tree->buffer, tree->size);
 	while (tree_entry(&desc, &entry)) {
+		struct object *obj;
 		int result;
 
 		if (S_ISGITLINK(entry.mode))
 			continue;
-		if (S_ISDIR(entry.mode))
+
-			result = options->walk(&lookup_tree(entry.oid->hash)->object, OBJ_TREE, data, options);
+		if (S_ISDIR(entry.mode)) {
-		else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode))
+			obj = &lookup_tree(entry.oid->hash)->object;
-			result = options->walk(&lookup_blob(entry.oid->hash)->object, OBJ_BLOB, data, options);
+			if (name)
+				put_object_name(options, obj, "%s%s/", name,
+					entry.path);
+			result = options->walk(obj, OBJ_TREE, data, options);
+		}
+		else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode)) {
+			obj = &lookup_blob(entry.oid->hash)->object;
+			if (name)
+				put_object_name(options, obj, "%s%s", name,
+					entry.path);
+			result = options->walk(obj, OBJ_BLOB, data, options);
+		}
 		else {
 			result = error("in tree %s: entry %s has bad mode %.6o",
-					oid_to_hex(&tree->object.oid), entry.path, entry.mode);
+					describe_object(options, &tree->object), entry.path, entry.mode);
 		}
 		if (result < 0)
 			return result;
@@ -330,20 +383,55 @@ static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *op
 
 static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_options *options)
 {
+	int counter = 0, generation = 0, name_prefix_len = 0;
 	struct commit_list *parents;
 	int res;
 	int result;
+	const char *name;
 
 	if (parse_commit(commit))
 		return -1;
 
+	name = get_object_name(options, &commit->object);
+	if (name)
+		put_object_name(options, &commit->tree->object, "%s:", name);
+
 	result = options->walk((struct object *)commit->tree, OBJ_TREE, data, options);
 	if (result < 0)
 		return result;
 	res = result;
 
 	parents = commit->parents;
+	if (name && parents) {
+		int len = strlen(name), power;
+
+		if (len && name[len - 1] == '^') {
+			generation = 1;
+			name_prefix_len = len - 1;
+		}
+		else { /* parse ~<generation> suffix */
+			for (generation = 0, power = 1;
+			     len && isdigit(name[len - 1]);
+			     power *= 10)
+				generation += power * (name[--len] - '0');
+			if (power > 1 && len && name[len - 1] == '~')
+				name_prefix_len = len - 1;
+		}
+	}
+
 	while (parents) {
+		if (name) {
+			struct object *obj = &parents->item->object;
+
+			if (++counter > 1)
+				put_object_name(options, obj, "%s^%d",
+					name, counter);
+			else if (generation > 0)
+				put_object_name(options, obj, "%.*s~%d",
+					name_prefix_len, name, generation + 1);
+			else
+				put_object_name(options, obj, "%s^", name);
+		}
 		result = options->walk((struct object *)parents->item, OBJ_COMMIT, data, options);
 		if (result < 0)
 			return result;
@@ -356,8 +444,12 @@ static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_optio
 
 static int fsck_walk_tag(struct tag *tag, void *data, struct fsck_options *options)
 {
+	char *name = get_object_name(options, &tag->object);
+
 	if (parse_tag(tag))
 		return -1;
+	if (name)
+		put_object_name(options, tag->tagged, "%s", name);
 	return options->walk(tag->tagged, OBJ_ANY, data, options);
 }
 
@@ -375,7 +467,7 @@ int fsck_walk(struct object *obj, void *data, struct fsck_options *options)
 	case OBJ_TAG:
 		return fsck_walk_tag((struct tag *)obj, data, options);
 	default:
-		error("Unknown object type for %s", oid_to_hex(&obj->oid));
+		error("Unknown object type for %s", describe_object(options, obj));
 		return -1;
 	}
 }
@@ -818,12 +910,13 @@ int fsck_object(struct object *obj, void *data, unsigned long size,
 			  obj->type);
 }
 
-int fsck_error_function(struct object *obj, int msg_type, const char *message)
+int fsck_error_function(struct fsck_options *o,
+	struct object *obj, int msg_type, const char *message)
 {
 	if (msg_type == FSCK_WARN) {
-		warning("object %s: %s", oid_to_hex(&obj->oid), message);
+		warning("object %s: %s", describe_object(o, obj), message);
 		return 0;
 	}
-	error("object %s: %s", oid_to_hex(&obj->oid), message);
+	error("object %s: %s", describe_object(o, obj), message);
 	return 1;
 }

fsck.h

@@ -23,9 +23,11 @@ int is_valid_msg_type(const char *msg_id, const char *msg_type);
 typedef int (*fsck_walk_func)(struct object *obj, int type, void *data, struct fsck_options *options);
 
 /* callback for fsck_object, type is FSCK_ERROR or FSCK_WARN */
-typedef int (*fsck_error)(struct object *obj, int type, const char *message);
+typedef int (*fsck_error)(struct fsck_options *o,
+	struct object *obj, int type, const char *message);
 
-int fsck_error_function(struct object *obj, int type, const char *message);
+int fsck_error_function(struct fsck_options *o,
+	struct object *obj, int type, const char *message);
 
 struct fsck_options {
 	fsck_walk_func walk;
@@ -33,6 +35,7 @@ struct fsck_options {
 	unsigned strict:1;
 	int *msg_type;
 	struct sha1_array *skiplist;
+	struct decoration *object_names;
 };
 
 #define FSCK_OPTIONS_DEFAULT { NULL, fsck_error_function, 0, NULL }

t/t1450-fsck.sh

@@ -523,4 +523,26 @@ test_expect_success 'fsck --connectivity-only' '
 	)
 '
 
+remove_loose_object () {
+	sha1="$(git rev-parse "$1")" &&
+	remainder=${sha1#??} &&
+	firsttwo=${sha1%$remainder} &&
+	rm .git/objects/$firsttwo/$remainder
+}
+
+test_expect_success 'fsck --name-objects' '
+	rm -rf name-objects &&
+	git init name-objects &&
+	(
+		cd name-objects &&
+		test_commit julius caesar.t &&
+		test_commit augustus &&
+		test_commit caesar &&
+		remove_loose_object $(git rev-parse julius:caesar.t) &&
+		test_must_fail git fsck --name-objects >out &&
+		tree=$(git rev-parse --verify julius:) &&
+		grep "$tree (\(refs/heads/master\|HEAD\)@{[0-9]*}:" out
+	)
+'
+
 test_done