Introduce an fsck API

Documentation/config.txt

@@ -1250,6 +1250,25 @@ filter.<driver>.smudge::
 	object to a worktree file upon checkout.  See
 	linkgit:gitattributes[5] for details.
 
+fsck.<msg-id>::
+	Allows overriding the message type (error, warn or ignore) of a
+	specific message ID such as `missingEmail`.
++
+For convenience, fsck prefixes the error/warning with the message ID,
+e.g.  "missingEmail: invalid author/committer line - missing email" means
+that setting `fsck.missingEmail = ignore` will hide that issue.
++
+This feature is intended to support working with legacy repositories
+which cannot be repaired without disruptive changes.
+
+fsck.skipList::
+	The path to a sorted list of object names (i.e. one SHA-1 per
+	line) that are known to be broken in a non-fatal way and should
+	be ignored. This feature is useful when an established project
+	should be accepted despite early commits containing errors that
+	can be safely ignored such as invalid committer email addresses.
+	Note: corrupt objects cannot be skipped with this setting.
+
 gc.aggressiveDepth::
 	The depth parameter used in the delta compression
 	algorithm used by 'git gc --aggressive'.  This defaults
@@ -2205,6 +2224,28 @@ receive.fsckObjects::
 	Defaults to false. If not set, the value of `transfer.fsckObjects`
 	is used instead.
 
+receive.fsck.<msg-id>::
+	When `receive.fsckObjects` is set to true, errors can be switched
+	to warnings and vice versa by configuring the `receive.fsck.<msg-id>`
+	setting where the `<msg-id>` is the fsck message ID and the value
+	is one of `error`, `warn` or `ignore`. For convenience, fsck prefixes
+	the error/warning with the message ID, e.g. "missingEmail: invalid
+	author/committer line - missing email" means that setting
+	`receive.fsck.missingEmail = ignore` will hide that issue.
++
+This feature is intended to support working with legacy repositories
+which would not pass pushing when `receive.fsckObjects = true`, allowing
+the host to accept repositories with certain known issues but still catch
+other issues.
+
+receive.fsck.skipList::
+	The path to a sorted list of object names (i.e. one SHA-1 per
+	line) that are known to be broken in a non-fatal way and should
+	be ignored. This feature is useful when an established project
+	should be accepted despite early commits containing errors that
+	can be safely ignored such as invalid committer email addresses.
+	Note: corrupt objects cannot be skipped with this setting.
+
 receive.unpackLimit::
 	If the number of objects received in a push is below this
 	limit then the objects will be unpacked into loose object

Documentation/git-fsck.txt

@@ -11,7 +11,7 @@ SYNOPSIS
 [verse]
 'git fsck' [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]
 	 [--[no-]full] [--strict] [--verbose] [--lost-found]
-	 [--[no-]dangling] [--[no-]progress] [<object>*]
+	 [--[no-]dangling] [--[no-]progress] [--connectivity-only] [<object>*]
 
 DESCRIPTION
 -----------
@@ -60,6 +60,11 @@ index file, all SHA-1 references in `refs` namespace, and all reflogs
 	object pools.  This is now default; you can turn it off
 	with --no-full.
 
+--connectivity-only::
+	Check only the connectivity of tags, commits and tree objects. By
+	avoiding to unpack blobs, this speeds up the operation, at the
+	expense of missing corrupt objects or other problematic issues.
+
 --strict::
 	Enable more strict checking, namely to catch a file mode
 	recorded with g+w bit set, which was created by older

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;
@@ -44,39 +47,52 @@ static int show_dangling = 1;
 #define DIRENT_SORT_HINT(de) ((de)->d_ino)
 #endif
 
-static void objreport(struct object *obj, const char *severity,
-                      const char *err, va_list params)
+static int fsck_config(const char *var, const char *value, void *cb)
 {
-	fprintf(stderr, "%s in %s %s: ",
-	        severity, typename(obj->type), sha1_to_hex(obj->sha1));
-	vfprintf(stderr, err, params);
-	fputs("\n", stderr);
+	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 *msg_type,
+			const char *err)
+{
+	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 +135,7 @@ 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 +148,7 @@ 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 +174,7 @@ 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 +195,8 @@ 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;
@@ -296,9 +314,9 @@ 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) {
@@ -621,6 +639,7 @@ 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")),
@@ -638,6 +657,12 @@ 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)
@@ -648,8 +673,11 @@ 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());
+	if (!connectivity_only)
+		fsck_object_dir(get_object_directory());
 
 	prepare_alt_odb();
 	for (alt = alt_odb_list; alt; alt = alt->next) {

builtin/index-pack.c

@@ -75,6 +75,7 @@ static int nr_threads;
 static int from_stdin;
 static int strict;
 static int do_fsck_object;
+static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;
 static int verbose;
 static int show_stat;
 static int check_self_contained_and_connected;
@@ -192,7 +193,7 @@ static void cleanup_thread(void)
 #endif
 
 
-static int mark_link(struct object *obj, int type, void *data)
+static int mark_link(struct object *obj, int type, void *data, struct fsck_options *options)
 {
 	if (!obj)
 		return -1;
@@ -838,10 +839,9 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 			if (!obj)
 				die(_("invalid %s"), typename(type));
 			if (do_fsck_object &&
-			    fsck_object(obj, buf, size, 1,
-				    fsck_error_function))
+			    fsck_object(obj, buf, size, &fsck_options))
 				die(_("Error in object"));
-			if (fsck_walk(obj, mark_link, NULL))
+			if (fsck_walk(obj, NULL, &fsck_options))
 				die(_("Not all child objects of %s are reachable"), sha1_to_hex(obj->sha1));
 
 			if (obj->type == OBJ_TREE) {
@@ -1615,6 +1615,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 		usage(index_pack_usage);
 
 	check_replace_refs = 0;
+	fsck_options.walk = mark_link;
 
 	reset_pack_idx_option(&opts);
 	git_config(git_index_pack_config, &opts);
@@ -1632,6 +1633,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 			} else if (!strcmp(arg, "--strict")) {
 				strict = 1;
 				do_fsck_object = 1;
+			} else if (skip_prefix(arg, "--strict=", &arg)) {
+				strict = 1;
+				do_fsck_object = 1;
+				fsck_set_msg_types(&fsck_options, arg);
 			} else if (!strcmp(arg, "--check-self-contained-and-connected")) {
 				strict = 1;
 				check_self_contained_and_connected = 1;

builtin/receive-pack.c

@@ -19,6 +19,7 @@
 #include "tag.h"
 #include "gpg-interface.h"
 #include "sigchain.h"
+#include "fsck.h"
 
 static const char receive_pack_usage[] = "git receive-pack <git-dir>";
 
@@ -36,6 +37,7 @@ static enum deny_action deny_current_branch = DENY_UNCONFIGURED;
 static enum deny_action deny_delete_current = DENY_UNCONFIGURED;
 static int receive_fsck_objects = -1;
 static int transfer_fsck_objects = -1;
+static struct strbuf fsck_msg_types = STRBUF_INIT;
 static int receive_unpack_limit = -1;
 static int transfer_unpack_limit = -1;
 static int advertise_atomic_push = 1;
@@ -115,6 +117,26 @@ static int receive_pack_config(const char *var, const char *value, void *cb)
 		return 0;
 	}
 
+	if (strcmp(var, "receive.fsck.skiplist") == 0) {
+		const char *path;
+
+		if (git_config_pathname(&path, var, value))
+			return 1;
+		strbuf_addf(&fsck_msg_types, "%cskiplist=%s",
+			fsck_msg_types.len ? ',' : '=', path);
+		free((char *)path);
+		return 0;
+	}
+
+	if (skip_prefix(var, "receive.fsck.", &var)) {
+		if (is_valid_msg_type(var, value))
+			strbuf_addf(&fsck_msg_types, "%c%s=%s",
+				fsck_msg_types.len ? ',' : '=', var, value);
+		else
+			warning("Skipping unknown msg id '%s'", var);
+		return 0;
+	}
+
 	if (strcmp(var, "receive.fsckobjects") == 0) {
 		receive_fsck_objects = git_config_bool(var, value);
 		return 0;
@@ -1490,7 +1512,8 @@ static const char *unpack(int err_fd, struct shallow_info *si)
 		if (quiet)
 			argv_array_push(&child.args, "-q");
 		if (fsck_objects)
-			argv_array_push(&child.args, "--strict");
+			argv_array_pushf(&child.args, "--strict%s",
+				fsck_msg_types.buf);
 		child.no_stdout = 1;
 		child.err = err_fd;
 		child.git_cmd = 1;
@@ -1508,7 +1531,8 @@ static const char *unpack(int err_fd, struct shallow_info *si)
 		argv_array_pushl(&child.args, "index-pack",
 				 "--stdin", hdr_arg, keep_arg, NULL);
 		if (fsck_objects)
-			argv_array_push(&child.args, "--strict");
+			argv_array_pushf(&child.args, "--strict%s",
+				fsck_msg_types.buf);
 		if (fix_thin)
 			argv_array_push(&child.args, "--fix-thin");
 		child.out = -1;