fsck: git receive-pack: support excluding objects from fsck'ing

The optional new config option `receive.fsck.skipList` specifies the path
to a file listing the names, i.e. SHA-1s, one per line, of objects that
are to be ignored by `git receive-pack` when `receive.fsckObjects = true`.

This is extremely handy in case of legacy repositories where it would
cause more pain to change incorrect objects than to live with them
(e.g. a duplicate 'author' line in an early commit object).

The intended use case is for server administrators to inspect objects
that are reported by `git push` as being too problematic to enter the
repository, and to add the objects' SHA-1 to a (preferably sorted) file
when the objects are legitimate, i.e. when it is determined that those
problematic objects should be allowed to enter the server.

Signed-off-by: Johannes Schindelin <johannes.schindelin@gmx.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

5 files changed, 82 insertions, 0 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 1c657675a7..f6cbd6de8e 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -2222,6 +2222,14 @@ 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/builtin/receive-pack.c b/builtin/receive-pack.c
index 3afe8f80c1..4ced2eba3c 100644
--- a/builtin/receive-pack.c
+++ b/builtin/receive-pack.c
@@ -117,6 +117,17 @@ 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",
diff --git a/fsck.c b/fsck.c
index 7a614bba82..1523243f1b 100644
--- a/fsck.c
+++ b/fsck.c
@@ -8,6 +8,7 @@
 #include "fsck.h"
 #include "refs.h"
 #include "utf8.h"
+#include "sha1-array.h"
 
 #define FSCK_FATAL -1
 #define FSCK_INFO -2
@@ -127,6 +128,43 @@ static int fsck_msg_type(enum fsck_msg_id msg_id,
 	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"))
@@ -191,6 +229,14 @@ void fsck_set_msg_types(struct fsck_options *options, const char *values)
 			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);
 
@@ -229,6 +275,10 @@ static int report(struct fsck_options *options, struct object *object,
 	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)
diff --git a/fsck.h b/fsck.h
index 1dab276899..dded84b5f9 100644
--- a/fsck.h
+++ b/fsck.h
@@ -32,6 +32,7 @@ struct fsck_options {
 	fsck_error error_func;
 	unsigned strict:1;
 	int *msg_type;
+	struct sha1_array *skiplist;
 };
 
 #define FSCK_OPTIONS_DEFAULT { NULL, fsck_error_function, 0, NULL }
diff --git a/t/t5504-fetch-receive-strict.sh b/t/t5504-fetch-receive-strict.sh
index 720c121522..44f3d5fb28 100755
--- a/t/t5504-fetch-receive-strict.sh
+++ b/t/t5504-fetch-receive-strict.sh
@@ -123,6 +123,18 @@ committer Bugs Bunny <bugs@bun.ni> 1234567890 +0000
 This commit object intentionally broken
 EOF
 
+test_expect_success 'push with receive.fsck.skipList' '
+	commit="$(git hash-object -t commit -w --stdin <bogus-commit)" &&
+	git push . $commit:refs/heads/bogus &&
+	rm -rf dst &&
+	git init dst &&
+	git --git-dir=dst/.git config receive.fsckObjects true &&
+	test_must_fail git push --porcelain dst bogus &&
+	git --git-dir=dst/.git config receive.fsck.skipList SKIP &&
+	echo $commit >dst/.git/SKIP &&
+	git push --porcelain dst bogus
+'
+
 test_expect_success 'push with receive.fsck.missingEmail=warn' '
 	commit="$(git hash-object -t commit -w --stdin <bogus-commit)" &&
 	git push . $commit:refs/heads/bogus &&