Merge branch 'js/fsck-opt'

Allow ignoring fsck errors on specific set of known-to-be-bad
objects, and also tweaking warning level of various kinds of non
critical breakages reported.

* js/fsck-opt:
  fsck: support ignoring objects in `git fsck` via fsck.skiplist
  fsck: git receive-pack: support excluding objects from fsck'ing
  fsck: introduce `git fsck --connectivity-only`
  fsck: support demoting errors to warnings
  fsck: document the new receive.fsck.<msg-id> options
  fsck: allow upgrading fsck warnings to errors
  fsck: optionally ignore specific fsck issues completely
  fsck: disallow demoting grave fsck errors to warnings
  fsck: add a simple test for receive.fsck.<msg-id>
  fsck: make fsck_tag() warn-friendly
  fsck: handle multiple authors in commits specially
  fsck: make fsck_commit() warn-friendly
  fsck: make fsck_ident() warn-friendly
  fsck: report the ID of the error/warning
  fsck (receive-pack): allow demoting errors to warnings
  fsck: offer a function to demote fsck errors to warnings
  fsck: provide a function to parse fsck message IDs
  fsck: introduce identifiers for fsck messages
  fsck: introduce fsck options

11 files changed, 693 insertions, 165 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 75c372238d..9358f4c16b 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -1242,6 +1242,25 @@ 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
@@ -2202,6 +2221,28 @@ 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
diff --git a/Documentation/git-fsck.txt b/Documentation/git-fsck.txt
index 25c431d3c5..84ee92e158 100644
--- a/Documentation/git-fsck.txt
+++ b/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
diff --git a/builtin/fsck.c b/builtin/fsck.c
index 2679793049..f4b87e9b33 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;
@@ -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) {
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index f07bc66ed6..3f10840441 100644
--- a/builtin/index-pack.c
+++ b/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;
diff --git a/builtin/receive-pack.c b/builtin/receive-pack.c
index 94d0571776..4ced2eba3c 100644
--- a/builtin/receive-pack.c
+++ b/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;
diff --git a/builtin/unpack-objects.c b/builtin/unpack-objects.c
index ac6667242c..7cc086f5f2 100644
--- a/builtin/unpack-objects.c
+++ b/builtin/unpack-objects.c
@@ -20,6 +20,7 @@ static unsigned char buffer[4096];
 static unsigned int offset, len;
 static off_t consumed_bytes;
 static git_SHA_CTX ctx;
+static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;
 
 /*
  * When running under --strict mode, objects whose reachability are
@@ -178,7 +179,7 @@ static void write_cached_object(struct object *obj, struct obj_buffer *obj_buf)
  * that have reachability requirements and calls this function.
  * Verify its reachability and validity recursively and write it out.
  */
-static int check_object(struct object *obj, int type, void *data)
+static int check_object(struct object *obj, int type, void *data, struct fsck_options *options)
 {
 	struct obj_buffer *obj_buf;
 
@@ -203,10 +204,10 @@ static int check_object(struct object *obj, int type, void *data)
 	obj_buf = lookup_object_buffer(obj);
 	if (!obj_buf)
 		die("Whoops! Cannot find object '%s'", sha1_to_hex(obj->sha1));
-	if (fsck_object(obj, obj_buf->buffer, obj_buf->size, 1,
-			fsck_error_function))
+	if (fsck_object(obj, obj_buf->buffer, obj_buf->size, &fsck_options))
 		die("Error in object");
-	if (fsck_walk(obj, check_object, NULL))
+	fsck_options.walk = check_object;
+	if (fsck_walk(obj, NULL, &fsck_options))
 		die("Error on reachable objects of %s", sha1_to_hex(obj->sha1));
 	write_cached_object(obj, obj_buf);
 	return 0;
@@ -217,7 +218,7 @@ static void write_rest(void)
 	unsigned i;
 	for (i = 0; i < nr_objects; i++) {
 		if (obj_list[i].obj)
-			check_object(obj_list[i].obj, OBJ_ANY, NULL);
+			check_object(obj_list[i].obj, OBJ_ANY, NULL, NULL);
 	}
 }
 
@@ -529,6 +530,11 @@ int cmd_unpack_objects(int argc, const char **argv, const char *prefix)
 				strict = 1;
 				continue;
 			}
+			if (skip_prefix(arg, "--strict=", &arg)) {
+				strict = 1;
+				fsck_set_msg_types(&fsck_options, arg);
+				continue;
+			}
 			if (starts_with(arg, "--pack_header=")) {
 				struct pack_header *hdr;
 				char *c;
diff --git a/fsck.c b/fsck.c
index 24b2a5f36c..e41e753d6d 100644
--- a/fsck.c
+++ b/fsck.c
@@ -8,8 +8,294 @@
 #include "fsck.h"
 #include "refs.h"
 #include "utf8.h"
+#include "sha1-array.h"
+
+#define FSCK_FATAL -1
+#define FSCK_INFO -2
+
+#define FOREACH_MSG_ID(FUNC) \
+	/* fatal errors */ \
+	FUNC(NUL_IN_HEADER, FATAL) \
+	FUNC(UNTERMINATED_HEADER, FATAL) \
+	/* errors */ \
+	FUNC(BAD_DATE, ERROR) \
+	FUNC(BAD_DATE_OVERFLOW, ERROR) \
+	FUNC(BAD_EMAIL, ERROR) \
+	FUNC(BAD_NAME, ERROR) \
+	FUNC(BAD_OBJECT_SHA1, ERROR) \
+	FUNC(BAD_PARENT_SHA1, ERROR) \
+	FUNC(BAD_TAG_OBJECT, ERROR) \
+	FUNC(BAD_TIMEZONE, ERROR) \
+	FUNC(BAD_TREE, ERROR) \
+	FUNC(BAD_TREE_SHA1, ERROR) \
+	FUNC(BAD_TYPE, ERROR) \
+	FUNC(DUPLICATE_ENTRIES, ERROR) \
+	FUNC(MISSING_AUTHOR, ERROR) \
+	FUNC(MISSING_COMMITTER, ERROR) \
+	FUNC(MISSING_EMAIL, ERROR) \
+	FUNC(MISSING_GRAFT, ERROR) \
+	FUNC(MISSING_NAME_BEFORE_EMAIL, ERROR) \
+	FUNC(MISSING_OBJECT, ERROR) \
+	FUNC(MISSING_PARENT, ERROR) \
+	FUNC(MISSING_SPACE_BEFORE_DATE, ERROR) \
+	FUNC(MISSING_SPACE_BEFORE_EMAIL, ERROR) \
+	FUNC(MISSING_TAG, ERROR) \
+	FUNC(MISSING_TAG_ENTRY, ERROR) \
+	FUNC(MISSING_TAG_OBJECT, ERROR) \
+	FUNC(MISSING_TREE, ERROR) \
+	FUNC(MISSING_TYPE, ERROR) \
+	FUNC(MISSING_TYPE_ENTRY, ERROR) \
+	FUNC(MULTIPLE_AUTHORS, ERROR) \
+	FUNC(TAG_OBJECT_NOT_TAG, ERROR) \
+	FUNC(TREE_NOT_SORTED, ERROR) \
+	FUNC(UNKNOWN_TYPE, ERROR) \
+	FUNC(ZERO_PADDED_DATE, ERROR) \
+	/* warnings */ \
+	FUNC(BAD_FILEMODE, WARN) \
+	FUNC(EMPTY_NAME, WARN) \
+	FUNC(FULL_PATHNAME, WARN) \
+	FUNC(HAS_DOT, WARN) \
+	FUNC(HAS_DOTDOT, WARN) \
+	FUNC(HAS_DOTGIT, WARN) \
+	FUNC(NULL_SHA1, WARN) \
+	FUNC(ZERO_PADDED_FILEMODE, WARN) \
+	/* infos (reported as warnings, but ignored by default) */ \
+	FUNC(BAD_TAG_NAME, INFO) \
+	FUNC(MISSING_TAGGER_ENTRY, INFO)
+
+#define MSG_ID(id, msg_type) FSCK_MSG_##id,
+enum fsck_msg_id {
+	FOREACH_MSG_ID(MSG_ID)
+	FSCK_MSG_MAX
+};
+#undef MSG_ID
+
+#define STR(x) #x
+#define MSG_ID(id, msg_type) { STR(id), NULL, FSCK_##msg_type },
+static struct {
+	const char *id_string;
+	const char *downcased;
+	int msg_type;
+} msg_id_info[FSCK_MSG_MAX + 1] = {
+	FOREACH_MSG_ID(MSG_ID)
+	{ NULL, NULL, -1 }
+};
+#undef MSG_ID
+
+static int parse_msg_id(const char *text)
+{
+	int i;
+
+	if (!msg_id_info[0].downcased) {
+		/* convert id_string to lower case, without underscores. */
+		for (i = 0; i < FSCK_MSG_MAX; i++) {
+			const char *p = msg_id_info[i].id_string;
+			int len = strlen(p);
+			char *q = xmalloc(len);
+
+			msg_id_info[i].downcased = q;
+			while (*p)
+				if (*p == '_')
+					p++;
+				else
+					*(q)++ = tolower(*(p)++);
+			*q = '\0';
+		}
+	}
+
+	for (i = 0; i < FSCK_MSG_MAX; i++)
+		if (!strcmp(text, msg_id_info[i].downcased))
+			return i;
+
+	return -1;
+}
+
+static int fsck_msg_type(enum fsck_msg_id msg_id,
+	struct fsck_options *options)
+{
+	int msg_type;
+
+	assert(msg_id >= 0 && msg_id < FSCK_MSG_MAX);
+
+	if (options->msg_type)
+		msg_type = options->msg_type[msg_id];
+	else {
+		msg_type = msg_id_info[msg_id].msg_type;
+		if (options->strict && msg_type == FSCK_WARN)
+			msg_type = FSCK_ERROR;
+	}
+
+	return msg_type;
+}
+
+static void init_skiplist(struct fsck_options *options, const char *path)
+{
+	static struct sha1_array skiplist = SHA1_ARRAY_INIT;
+	int sorted, fd;
+	char buffer[41];
+	unsigned char sha1[20];
+
+	if (options->skiplist)
+		sorted = options->skiplist->sorted;
+	else {
+		sorted = 1;
+		options->skiplist = &skiplist;
+	}
+
+	fd = open(path, O_RDONLY);
+	if (fd < 0)
+		die("Could not open skip list: %s", path);
+	for (;;) {
+		int result = read_in_full(fd, buffer, sizeof(buffer));
+		if (result < 0)
+			die_errno("Could not read '%s'", path);
+		if (!result)
+			break;
+		if (get_sha1_hex(buffer, sha1) || buffer[40] != '\n')
+			die("Invalid SHA-1: %s", buffer);
+		sha1_array_append(&skiplist, sha1);
+		if (sorted && skiplist.nr > 1 &&
+				hashcmp(skiplist.sha1[skiplist.nr - 2],
+					sha1) > 0)
+			sorted = 0;
+	}
+	close(fd);
+
+	if (sorted)
+		skiplist.sorted = 1;
+}
+
+static int parse_msg_type(const char *str)
+{
+	if (!strcmp(str, "error"))
+		return FSCK_ERROR;
+	else if (!strcmp(str, "warn"))
+		return FSCK_WARN;
+	else if (!strcmp(str, "ignore"))
+		return FSCK_IGNORE;
+	else
+		die("Unknown fsck message type: '%s'", str);
+}
+
+int is_valid_msg_type(const char *msg_id, const char *msg_type)
+{
+	if (parse_msg_id(msg_id) < 0)
+		return 0;
+	parse_msg_type(msg_type);
+	return 1;
+}
+
+void fsck_set_msg_type(struct fsck_options *options,
+		const char *msg_id, const char *msg_type)
+{
+	int id = parse_msg_id(msg_id), type;
+
+	if (id < 0)
+		die("Unhandled message id: %s", msg_id);
+	type = parse_msg_type(msg_type);
+
+	if (type != FSCK_ERROR && msg_id_info[id].msg_type == FSCK_FATAL)
+		die("Cannot demote %s to %s", msg_id, msg_type);
+
+	if (!options->msg_type) {
+		int i;
+		int *msg_type = xmalloc(sizeof(int) * FSCK_MSG_MAX);
+		for (i = 0; i < FSCK_MSG_MAX; i++)
+			msg_type[i] = fsck_msg_type(i, options);
+		options->msg_type = msg_type;
+	}
+
+	options->msg_type[id] = type;
+}
+
+void fsck_set_msg_types(struct fsck_options *options, const char *values)
+{
+	char *buf = xstrdup(values), *to_free = buf;
+	int done = 0;
+
+	while (!done) {
+		int len = strcspn(buf, " ,|"), equal;
+
+		done = !buf[len];
+		if (!len) {
+			buf++;
+			continue;
+		}
+		buf[len] = '\0';
+
+		for (equal = 0;
+		     equal < len && buf[equal] != '=' && buf[equal] != ':';
+		     equal++)
+			buf[equal] = tolower(buf[equal]);
+		buf[equal] = '\0';
+
+		if (!strcmp(buf, "skiplist")) {
+			if (equal == len)
+				die("skiplist requires a path");
+			init_skiplist(options, buf + equal + 1);
+			buf += len + 1;
+			continue;
+		}
+
+		if (equal == len)
+			die("Missing '=': '%s'", buf);
 
-static int fsck_walk_tree(struct tree *tree, fsck_walk_func walk, void *data)
+		fsck_set_msg_type(options, buf, buf + equal + 1);
+		buf += len + 1;
+	}
+	free(to_free);
+}
+
+static void append_msg_id(struct strbuf *sb, const char *msg_id)
+{
+	for (;;) {
+		char c = *(msg_id)++;
+
+		if (!c)
+			break;
+		if (c != '_')
+			strbuf_addch(sb, tolower(c));
+		else {
+			assert(*msg_id);
+			strbuf_addch(sb, *(msg_id)++);
+		}
+	}
+
+	strbuf_addstr(sb, ": ");
+}
+
+__attribute__((format (printf, 4, 5)))
+static int report(struct fsck_options *options, struct object *object,
+	enum fsck_msg_id id, const char *fmt, ...)
+{
+	va_list ap;
+	struct strbuf sb = STRBUF_INIT;
+	int msg_type = fsck_msg_type(id, options), result;
+
+	if (msg_type == FSCK_IGNORE)
+		return 0;
+
+	if (options->skiplist && object &&
+			sha1_array_lookup(options->skiplist, object->sha1) >= 0)
+		return 0;
+
+	if (msg_type == FSCK_FATAL)
+		msg_type = FSCK_ERROR;
+	else if (msg_type == FSCK_INFO)
+		msg_type = FSCK_WARN;
+
+	append_msg_id(&sb, msg_id_info[id].id_string);
+
+	va_start(ap, fmt);
+	strbuf_vaddf(&sb, fmt, ap);
+	result = options->error_func(object, msg_type, sb.buf);
+	strbuf_release(&sb);
+	va_end(ap);
+
+	return result;
+}
+
+static int fsck_walk_tree(struct tree *tree, void *data, struct fsck_options *options)
 {
 	struct tree_desc desc;
 	struct name_entry entry;
@@ -25,9 +311,9 @@ static int fsck_walk_tree(struct tree *tree, fsck_walk_func walk, void *data)
 		if (S_ISGITLINK(entry.mode))
 			continue;
 		if (S_ISDIR(entry.mode))
-			result = walk(&lookup_tree(entry.sha1)->object, OBJ_TREE, data);
+			result = options->walk(&lookup_tree(entry.sha1)->object, OBJ_TREE, data, options);
 		else if (S_ISREG(entry.mode) || S_ISLNK(entry.mode))
-			result = walk(&lookup_blob(entry.sha1)->object, OBJ_BLOB, data);
+			result = options->walk(&lookup_blob(entry.sha1)->object, OBJ_BLOB, data, options);
 		else {
 			result = error("in tree %s: entry %s has bad mode %.6o",
 					sha1_to_hex(tree->object.sha1), entry.path, entry.mode);
@@ -40,7 +326,7 @@ static int fsck_walk_tree(struct tree *tree, fsck_walk_func walk, void *data)
 	return res;
 }
 
-static int fsck_walk_commit(struct commit *commit, fsck_walk_func walk, void *data)
+static int fsck_walk_commit(struct commit *commit, void *data, struct fsck_options *options)
 {
 	struct commit_list *parents;
 	int res;
@@ -49,14 +335,14 @@ static int fsck_walk_commit(struct commit *commit, fsck_walk_func walk, void *da
 	if (parse_commit(commit))
 		return -1;
 
-	result = walk((struct object *)commit->tree, OBJ_TREE, data);
+	result = options->walk((struct object *)commit->tree, OBJ_TREE, data, options);
 	if (result < 0)
 		return result;
 	res = result;
 
 	parents = commit->parents;
 	while (parents) {
-		result = walk((struct object *)parents->item, OBJ_COMMIT, data);
+		result = options->walk((struct object *)parents->item, OBJ_COMMIT, data, options);
 		if (result < 0)
 			return result;
 		if (!res)
@@ -66,14 +352,14 @@ static int fsck_walk_commit(struct commit *commit, fsck_walk_func walk, void *da
 	return res;
 }
 
-static int fsck_walk_tag(struct tag *tag, fsck_walk_func walk, void *data)
+static int fsck_walk_tag(struct tag *tag, void *data, struct fsck_options *options)
 {
 	if (parse_tag(tag))
 		return -1;
-	return walk(tag->tagged, OBJ_ANY, data);
+	return options->walk(tag->tagged, OBJ_ANY, data, options);
 }
 
-int fsck_walk(struct object *obj, fsck_walk_func walk, void *data)
+int fsck_walk(struct object *obj, void *data, struct fsck_options *options)
 {
 	if (!obj)
 		return -1;
@@ -81,11 +367,11 @@ int fsck_walk(struct object *obj, fsck_walk_func walk, void *data)
 	case OBJ_BLOB:
 		return 0;
 	case OBJ_TREE:
-		return fsck_walk_tree((struct tree *)obj, walk, data);
+		return fsck_walk_tree((struct tree *)obj, data, options);
 	case OBJ_COMMIT:
-		return fsck_walk_commit((struct commit *)obj, walk, data);
+		return fsck_walk_commit((struct commit *)obj, data, options);
 	case OBJ_TAG:
-		return fsck_walk_tag((struct tag *)obj, walk, data);
+		return fsck_walk_tag((struct tag *)obj, data, options);
 	default:
 		error("Unknown object type for %s", sha1_to_hex(obj->sha1));
 		return -1;
@@ -138,7 +424,7 @@ static int verify_ordered(unsigned mode1, const char *name1, unsigned mode2, con
 	return c1 < c2 ? 0 : TREE_UNORDERED;
 }
 
-static int fsck_tree(struct tree *item, int strict, fsck_error error_func)
+static int fsck_tree(struct tree *item, struct fsck_options *options)
 {
 	int retval;
 	int has_null_sha1 = 0;
@@ -194,7 +480,7 @@ static int fsck_tree(struct tree *item, int strict, fsck_error error_func)
 		 * bits..
 		 */
 		case S_IFREG | 0664:
-			if (!strict)
+			if (!options->strict)
 				break;
 		default:
 			has_bad_modes = 1;
@@ -219,30 +505,30 @@ static int fsck_tree(struct tree *item, int strict, fsck_error error_func)
 
 	retval = 0;
 	if (has_null_sha1)
-		retval += error_func(&item->object, FSCK_WARN, "contains entries pointing to null sha1");
+		retval += report(options, &item->object, FSCK_MSG_NULL_SHA1, "contains entries pointing to null sha1");
 	if (has_full_path)
-		retval += error_func(&item->object, FSCK_WARN, "contains full pathnames");
+		retval += report(options, &item->object, FSCK_MSG_FULL_PATHNAME, "contains full pathnames");
 	if (has_empty_name)
-		retval += error_func(&item->object, FSCK_WARN, "contains empty pathname");
+		retval += report(options, &item->object, FSCK_MSG_EMPTY_NAME, "contains empty pathname");
 	if (has_dot)
-		retval += error_func(&item->object, FSCK_WARN, "contains '.'");
+		retval += report(options, &item->object, FSCK_MSG_HAS_DOT, "contains '.'");
 	if (has_dotdot)
-		retval += error_func(&item->object, FSCK_WARN, "contains '..'");
+		retval += report(options, &item->object, FSCK_MSG_HAS_DOTDOT, "contains '..'");
 	if (has_dotgit)
-		retval += error_func(&item->object, FSCK_WARN, "contains '.git'");
+		retval += report(options, &item->object, FSCK_MSG_HAS_DOTGIT, "contains '.git'");
 	if (has_zero_pad)
-		retval += error_func(&item->object, FSCK_WARN, "contains zero-padded file modes");
+		retval += report(options, &item->object, FSCK_MSG_ZERO_PADDED_FILEMODE, "contains zero-padded file modes");
 	if (has_bad_modes)
-		retval += error_func(&item->object, FSCK_WARN, "contains bad file modes");
+		retval += report(options, &item->object, FSCK_MSG_BAD_FILEMODE, "contains bad file modes");
 	if (has_dup_entries)
-		retval += error_func(&item->object, FSCK_ERROR, "contains duplicate file entries");
+		retval += report(options, &item->object, FSCK_MSG_DUPLICATE_ENTRIES, "contains duplicate file entries");
 	if (not_properly_sorted)
-		retval += error_func(&item->object, FSCK_ERROR, "not properly sorted");
+		retval += report(options, &item->object, FSCK_MSG_TREE_NOT_SORTED, "not properly sorted");
 	return retval;
 }
 
 static int verify_headers(const void *data, unsigned long size,
-			  struct object *obj, fsck_error error_func)
+			  struct object *obj, struct fsck_options *options)
 {
 	const char *buffer = (const char *)data;
 	unsigned long i;
@@ -250,8 +536,9 @@ static int verify_headers(const void *data, unsigned long size,
 	for (i = 0; i < size; i++) {
 		switch (buffer[i]) {
 		case '\0':
-			return error_func(obj, FSCK_ERROR,
-				"unterminated header: NUL at offset %d", i);
+			return report(options, obj,
+				FSCK_MSG_NUL_IN_HEADER,
+				"unterminated header: NUL at offset %ld", i);
 		case '\n':
 			if (i + 1 < size && buffer[i + 1] == '\n')
 				return 0;
@@ -267,67 +554,79 @@ static int verify_headers(const void *data, unsigned long size,
 	if (size && buffer[size - 1] == '\n')
 		return 0;
 
-	return error_func(obj, FSCK_ERROR, "unterminated header");
+	return report(options, obj,
+		FSCK_MSG_UNTERMINATED_HEADER, "unterminated header");
 }
 
-static int fsck_ident(const char **ident, struct object *obj, fsck_error error_func)
+static int fsck_ident(const char **ident, struct object *obj, struct fsck_options *options)
 {
+	const char *p = *ident;
 	char *end;
 
-	if (**ident == '<')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before email");
-	*ident += strcspn(*ident, "<>\n");
-	if (**ident == '>')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad name");
-	if (**ident != '<')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing email");
-	if ((*ident)[-1] != ' ')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before email");
-	(*ident)++;
-	*ident += strcspn(*ident, "<>\n");
-	if (**ident != '>')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad email");
-	(*ident)++;
-	if (**ident != ' ')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - missing space before date");
-	(*ident)++;
-	if (**ident == '0' && (*ident)[1] != ' ')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - zero-padded date");
-	if (date_overflows(strtoul(*ident, &end, 10)))
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - date causes integer overflow");
-	if (end == *ident || *end != ' ')
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad date");
-	*ident = end + 1;
-	if ((**ident != '+' && **ident != '-') ||
-	    !isdigit((*ident)[1]) ||
-	    !isdigit((*ident)[2]) ||
-	    !isdigit((*ident)[3]) ||
-	    !isdigit((*ident)[4]) ||
-	    ((*ident)[5] != '\n'))
-		return error_func(obj, FSCK_ERROR, "invalid author/committer line - bad time zone");
-	(*ident) += 6;
+	*ident = strchrnul(*ident, '\n');
+	if (**ident == '\n')
+		(*ident)++;
+
+	if (*p == '<')
+		return report(options, obj, FSCK_MSG_MISSING_NAME_BEFORE_EMAIL, "invalid author/committer line - missing space before email");
+	p += strcspn(p, "<>\n");
+	if (*p == '>')
+		return report(options, obj, FSCK_MSG_BAD