1 files changed, 118 insertions, 158 deletions

diff --git a/builtin/fsck.c b/builtin/fsck.c
index 4e8e2ee5b7..8b8bb42c51 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -23,8 +23,11 @@ static int show_tags;
 static int show_unreachable;
 static int include_reflogs = 1;
 static int check_full = 1;
+static int connectivity_only;
 static int check_strict;
 static int keep_cache_objects;
+static struct fsck_options fsck_walk_options = FSCK_OPTIONS_DEFAULT;
+static struct fsck_options fsck_obj_options = FSCK_OPTIONS_DEFAULT;
 static struct object_id head_oid;
 static const char *head_points_at;
 static int errors_found;
@@ -35,48 +38,54 @@ static int show_dangling = 1;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 #define ERROR_PACK 04
+#define ERROR_REFS 010
 
-#ifdef NO_D_INO_IN_DIRENT
-#define SORT_DIRENT 0
-#define DIRENT_SORT_HINT(de) 0
-#else
-#define SORT_DIRENT 1
-#define DIRENT_SORT_HINT(de) ((de)->d_ino)
-#endif
+static int fsck_config(const char *var, const char *value, void *cb)
+{
+	if (strcmp(var, "fsck.skiplist") == 0) {
+		const char *path;
+		struct strbuf sb = STRBUF_INIT;
+
+		if (git_config_pathname(&path, var, value))
+			return 1;
+		strbuf_addf(&sb, "skiplist=%s", path);
+		free((char *)path);
+		fsck_set_msg_types(&fsck_obj_options, sb.buf);
+		strbuf_release(&sb);
+		return 0;
+	}
+
+	if (skip_prefix(var, "fsck.", &var)) {
+		fsck_set_msg_type(&fsck_obj_options, var, value);
+		return 0;
+	}
+
+	return git_default_config(var, value, cb);
+}
 
-static void objreport(struct object *obj, const char *severity,
-                      const char *err, va_list params)
+static void objreport(struct object *obj, const char *msg_type,
+			const char *err)
 {
-	fprintf(stderr, "%s in %s %s: ",
-	        severity, typename(obj->type), sha1_to_hex(obj->sha1));
-	vfprintf(stderr, err, params);
-	fputs("\n", stderr);
+	fprintf(stderr, "%s in %s %s: %s\n",
+		msg_type, typename(obj->type), sha1_to_hex(obj->sha1), err);
 }
 
-__attribute__((format (printf, 2, 3)))
-static int objerror(struct object *obj, const char *err, ...)
+static int objerror(struct object *obj, const char *err)
 {
-	va_list params;
-	va_start(params, err);
 	errors_found |= ERROR_OBJECT;
-	objreport(obj, "error", err, params);
-	va_end(params);
+	objreport(obj, "error", err);
 	return -1;
 }
 
-__attribute__((format (printf, 3, 4)))
-static int fsck_error_func(struct object *obj, int type, const char *err, ...)
+static int fsck_error_func(struct object *obj, int type, const char *message)
 {
-	va_list params;
-	va_start(params, err);
-	objreport(obj, (type == FSCK_WARN) ? "warning" : "error", err, params);
-	va_end(params);
+	objreport(obj, (type == FSCK_WARN) ? "warning" : "error", message);
 	return (type == FSCK_WARN) ? 0 : 1;
 }
 
 static struct object_array pending;
 
-static int mark_object(struct object *obj, int type, void *data)
+static int mark_object(struct object *obj, int type, void *data, struct fsck_options *options)
 {
 	struct object *parent = data;
 
@@ -119,7 +128,7 @@ static int mark_object(struct object *obj, int type, void *data)
 
 static void mark_object_reachable(struct object *obj)
 {
-	mark_object(obj, OBJ_ANY, NULL);
+	mark_object(obj, OBJ_ANY, NULL, NULL);
 }
 
 static int traverse_one_object(struct object *obj)
@@ -132,7 +141,7 @@ static int traverse_one_object(struct object *obj)
 		if (parse_tree(tree) < 0)
 			return 1; /* error already displayed */
 	}
-	result = fsck_walk(obj, mark_object, obj);
+	result = fsck_walk(obj, obj, &fsck_walk_options);
 	if (tree)
 		free_tree_buffer(tree);
 	return result;
@@ -158,7 +167,7 @@ static int traverse_reachable(void)
 	return !!result;
 }
 
-static int mark_used(struct object *obj, int type, void *data)
+static int mark_used(struct object *obj, int type, void *data, struct fsck_options *options)
 {
 	if (!obj)
 		return 1;
@@ -179,6 +188,8 @@ static void check_reachable_object(struct object *obj)
 	if (!(obj->flags & HAS_OBJ)) {
 		if (has_sha1_pack(obj->sha1))
 			return; /* it is in pack - forget about it */
+		if (connectivity_only && has_sha1_file(obj->sha1))
+			return;
 		printf("missing %s %s\n", typename(obj->type), sha1_to_hex(obj->sha1));
 		errors_found |= ERROR_REACHABLE;
 		return;
@@ -225,13 +236,14 @@ static void check_unreachable_object(struct object *obj)
 			printf("dangling %s %s\n", typename(obj->type),
 			       sha1_to_hex(obj->sha1));
 		if (write_lost_and_found) {
-			const char *filename = git_path("lost-found/%s/%s",
+			char *filename = git_pathdup("lost-found/%s/%s",
 				obj->type == OBJ_COMMIT ? "commit" : "other",
 				sha1_to_hex(obj->sha1));
 			FILE *f;
 
 			if (safe_create_leading_directories_const(filename)) {
 				error("Could not create lost-found");
+				free(filename);
 				return;
 			}
 			if (!(f = fopen(filename, "w")))
@@ -244,6 +256,7 @@ static void check_unreachable_object(struct object *obj)
 			if (fclose(f))
 				die_errno("Could not finish '%s'",
 					  filename);
+			free(filename);
 		}
 		return;
 	}
@@ -296,9 +309,9 @@ static int fsck_obj(struct object *obj)
 		fprintf(stderr, "Checking %s %s\n",
 			typename(obj->type), sha1_to_hex(obj->sha1));
 
-	if (fsck_walk(obj, mark_used, NULL))
+	if (fsck_walk(obj, NULL, &fsck_obj_options))
 		objerror(obj, "broken links");
-	if (fsck_object(obj, NULL, 0, check_strict, fsck_error_func))
+	if (fsck_object(obj, NULL, 0, &fsck_obj_options))
 		return -1;
 
 	if (obj->type == OBJ_TREE) {
@@ -353,133 +366,43 @@ static int fsck_obj_buffer(const unsigned char *sha1, enum object_type type,
 	return fsck_obj(obj);
 }
 
-/*
- * This is the sorting chunk size: make it reasonably
- * big so that we can sort well..
- */
-#define MAX_SHA1_ENTRIES (1024)
-
-struct sha1_entry {
-	unsigned long ino;
-	unsigned char sha1[20];
-};
-
-static struct {
-	unsigned long nr;
-	struct sha1_entry *entry[MAX_SHA1_ENTRIES];
-} sha1_list;
-
-static int ino_compare(const void *_a, const void *_b)
-{
-	const struct sha1_entry *a = _a, *b = _b;
-	unsigned long ino1 = a->ino, ino2 = b->ino;
-	return ino1 < ino2 ? -1 : ino1 > ino2 ? 1 : 0;
-}
-
-static void fsck_sha1_list(void)
-{
-	int i, nr = sha1_list.nr;
-
-	if (SORT_DIRENT)
-		qsort(sha1_list.entry, nr,
-		      sizeof(struct sha1_entry *), ino_compare);
-	for (i = 0; i < nr; i++) {
-		struct sha1_entry *entry = sha1_list.entry[i];
-		unsigned char *sha1 = entry->sha1;
-
-		sha1_list.entry[i] = NULL;
-		if (fsck_sha1(sha1))
-			errors_found |= ERROR_OBJECT;
-		free(entry);
-	}
-	sha1_list.nr = 0;
-}
-
-static void add_sha1_list(unsigned char *sha1, unsigned long ino)
-{
-	struct sha1_entry *entry = xmalloc(sizeof(*entry));
-	int nr;
-
-	entry->ino = ino;
-	hashcpy(entry->sha1, sha1);
-	nr = sha1_list.nr;
-	if (nr == MAX_SHA1_ENTRIES) {
-		fsck_sha1_list();
-		nr = 0;
-	}
-	sha1_list.entry[nr] = entry;
-	sha1_list.nr = ++nr;
-}
-
-static inline int is_loose_object_file(struct dirent *de,
-				       char *name, unsigned char *sha1)
-{
-	if (strlen(de->d_name) != 38)
-		return 0;
-	memcpy(name + 2, de->d_name, 39);
-	return !get_sha1_hex(name, sha1);
-}
+static int default_refs;
 
-static void fsck_dir(int i, char *path)
+static void fsck_handle_reflog_sha1(const char *refname, unsigned char *sha1)
 {
-	DIR *dir = opendir(path);
-	struct dirent *de;
-	char name[100];
-
-	if (!dir)
-		return;
-
-	if (verbose)
-		fprintf(stderr, "Checking directory %s\n", path);
-
-	sprintf(name, "%02x", i);
-	while ((de = readdir(dir)) != NULL) {
-		unsigned char sha1[20];
+	struct object *obj;
 
-		if (is_dot_or_dotdot(de->d_name))
-			continue;
-		if (is_loose_object_file(de, name, sha1)) {
-			add_sha1_list(sha1, DIRENT_SORT_HINT(de));
-			continue;
+	if (!is_null_sha1(sha1)) {
+		obj = lookup_object(sha1);
+		if (obj) {
+			obj->used = 1;
+			mark_object_reachable(obj);
+		} else {
+			error("%s: invalid reflog entry %s", refname, sha1_to_hex(sha1));
+			errors_found |= ERROR_REACHABLE;
 		}
-		if (starts_with(de->d_name, "tmp_obj_"))
-			continue;
-		fprintf(stderr, "bad sha1 file: %s/%s\n", path, de->d_name);
 	}
-	closedir(dir);
 }
 
-static int default_refs;
-
 static int fsck_handle_reflog_ent(unsigned char *osha1, unsigned char *nsha1,
 		const char *email, unsigned long timestamp, int tz,
 		const char *message, void *cb_data)
 {
-	struct object *obj;
+	const char *refname = cb_data;
 
 	if (verbose)
 		fprintf(stderr, "Checking reflog %s->%s\n",
 			sha1_to_hex(osha1), sha1_to_hex(nsha1));
 
-	if (!is_null_sha1(osha1)) {
-		obj = lookup_object(osha1);
-		if (obj) {
-			obj->used = 1;
-			mark_object_reachable(obj);
-		}
-	}
-	obj = lookup_object(nsha1);
-	if (obj) {
-		obj->used = 1;
-		mark_object_reachable(obj);
-	}
+	fsck_handle_reflog_sha1(refname, osha1);
+	fsck_handle_reflog_sha1(refname, nsha1);
 	return 0;
 }
 
 static int fsck_handle_reflog(const char *logname, const struct object_id *oid,
 			      int flag, void *cb_data)
 {
-	for_each_reflog_ent(logname, fsck_handle_reflog_ent, NULL);
+	for_each_reflog_ent(logname, fsck_handle_reflog_ent, (void *)logname);
 	return 0;
 }
 
@@ -495,8 +418,10 @@ static int fsck_handle_ref(const char *refname, const struct object_id *oid,
 		/* We'll continue with the rest despite the error.. */
 		return 0;
 	}
-	if (obj->type != OBJ_COMMIT && is_branch(refname))
+	if (obj->type != OBJ_COMMIT && is_branch(refname)) {
 		error("%s: not a commit", refname);
+		errors_found |= ERROR_REFS;
+	}
 	default_refs++;
 	obj->used = 1;
 	mark_object_reachable(obj);
@@ -530,9 +455,28 @@ static void get_default_heads(void)
 	}
 }
 
+static int fsck_loose(const unsigned char *sha1, const char *path, void *data)
+{
+	if (fsck_sha1(sha1))
+		errors_found |= ERROR_OBJECT;
+	return 0;
+}
+
+static int fsck_cruft(const char *basename, const char *path, void *data)
+{
+	if (!starts_with(basename, "tmp_obj_"))
+		fprintf(stderr, "bad sha1 file: %s\n", path);
+	return 0;
+}
+
+static int fsck_subdir(int nr, const char *path, void *progress)
+{
+	display_progress(progress, nr + 1);
+	return 0;
+}
+
 static void fsck_object_dir(const char *path)
 {
-	int i;
 	struct progress *progress = NULL;
 
 	if (verbose)
@@ -540,14 +484,11 @@ static void fsck_object_dir(const char *path)
 
 	if (show_progress)
 		progress = start_progress(_("Checking object directories"), 256);
-	for (i = 0; i < 256; i++) {
-		static char dir[4096];
-		sprintf(dir, "%s/%02x", path, i);
-		fsck_dir(i, dir);
-		display_progress(progress, i+1);
-	}
+
+	for_each_loose_file_in_objdir(path, fsck_loose, fsck_cruft, fsck_subdir,
+				      progress);
+	display_progress(progress, 256);
 	stop_progress(&progress);
-	fsck_sha1_list();
 }
 
 static int fsck_head_link(void)
@@ -559,17 +500,23 @@ static int fsck_head_link(void)
 		fprintf(stderr, "Checking HEAD link\n");
 
 	head_points_at = resolve_ref_unsafe("HEAD", 0, head_oid.hash, &flag);
-	if (!head_points_at)
+	if (!head_points_at) {
+		errors_found |= ERROR_REFS;
 		return error("Invalid HEAD");
+	}
 	if (!strcmp(head_points_at, "HEAD"))
 		/* detached HEAD */
 		null_is_error = 1;
-	else if (!starts_with(head_points_at, "refs/heads/"))
+	else if (!starts_with(head_points_at, "refs/heads/")) {
+		errors_found |= ERROR_REFS;
 		return error("HEAD points to something strange (%s)",
 			     head_points_at);
+	}
 	if (is_null_oid(&head_oid)) {
-		if (null_is_error)
+		if (null_is_error) {
+			errors_found |= ERROR_REFS;
 			return error("HEAD: detached HEAD points at nothing");
+		}
 		fprintf(stderr, "notice: HEAD points to an unborn branch (%s)\n",
 			head_points_at + 11);
 	}
@@ -589,6 +536,7 @@ static int fsck_cache_tree(struct cache_tree *it)
 		if (!obj) {
 			error("%s: invalid sha1 pointer in cache-tree",
 			      sha1_to_hex(it->sha1));
+			errors_found |= ERROR_REFS;
 			return 1;
 		}
 		obj->used = 1;
@@ -615,6 +563,7 @@ static struct option fsck_opts[] = {
 	OPT_BOOL(0, "cache", &keep_cache_objects, N_("make index objects head nodes")),
 	OPT_BOOL(0, "reflogs", &include_reflogs, N_("make reflogs head nodes (default)")),
 	OPT_BOOL(0, "full", &check_full, N_("also consider packs and alternate objects")),
+	OPT_BOOL(0, "connectivity-only", &connectivity_only, N_("check only connectivity")),
 	OPT_BOOL(0, "strict", &check_strict, N_("enable more strict checking")),
 	OPT_BOOL(0, "lost-found", &write_lost_and_found,
 				N_("write dangling objects in .git/lost-found")),
@@ -632,6 +581,12 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 
 	argc = parse_options(argc, argv, prefix, fsck_opts, fsck_usage, 0);
 
+	fsck_walk_options.walk = mark_object;
+	fsck_obj_options.walk = mark_used;
+	fsck_obj_options.error_func = fsck_error_func;
+	if (check_strict)
+		fsck_obj_options.strict = 1;
+
 	if (show_progress == -1)
 		show_progress = isatty(2);
 	if (verbose)
@@ -642,16 +597,21 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 		include_reflogs = 0;
 	}
 
+	git_config(fsck_config, NULL);
+
 	fsck_head_link();
-	fsck_object_dir(get_object_directory());
-
-	prepare_alt_odb();
-	for (alt = alt_odb_list; alt; alt = alt->next) {
-		char namebuf[PATH_MAX];
-		int namelen = alt->name - alt->base;
-		memcpy(namebuf, alt->base, namelen);
-		namebuf[namelen - 1] = 0;
-		fsck_object_dir(namebuf);
+	if (!connectivity_only) {
+		fsck_object_dir(get_object_directory());
+
+		prepare_alt_odb();
+		for (alt = alt_odb_list; alt; alt = alt->next) {
+			/* directory name, minus trailing slash */
+			size_t namelen = alt->name - alt->base - 1;
+			struct strbuf name = STRBUF_INIT;
+			strbuf_add(&name, alt->base, namelen);
+			fsck_object_dir(name.buf);
+			strbuf_release(&name);
+		}
 	}
 
 	if (check_full) {