fsck: support comments & empty lines in skipList

It's annoying not to be able to put comments and empty lines in the
skipList, when e.g. keeping a big central list of commits to skip in
/etc/gitconfig, which was my motivation for 1362df0d41 ("fetch:
implement fetch.fsck.*", 2018-07-27).

Implement that, and document what version of Git this was changed in,
since this on-disk format can be expected to be used by multiple
versions of git.

There is no notable performance impact from this change, using the
test setup described a couple of commits back:

    Test                                             HEAD~             HEAD
    ----------------------------------------------------------------------------------------
    1450.3: fsck with 0 skipped bad commits          7.69(7.27+0.42)   7.86(7.48+0.37) +2.2%
    1450.5: fsck with 1 skipped bad commits          7.69(7.30+0.38)   7.83(7.47+0.36) +1.8%
    1450.7: fsck with 10 skipped bad commits         7.76(7.38+0.38)   7.79(7.38+0.41) +0.4%
    1450.9: fsck with 100 skipped bad commits        7.76(7.38+0.38)   7.74(7.36+0.38) -0.3%
    1450.11: fsck with 1000 skipped bad commits      7.71(7.30+0.41)   7.72(7.34+0.38) +0.1%
    1450.13: fsck with 10000 skipped bad commits     7.74(7.34+0.40)   7.72(7.34+0.38) -0.3%
    1450.15: fsck with 100000 skipped bad commits    7.75(7.40+0.35)   7.70(7.29+0.40) -0.6%
    1450.17: fsck with 1000000 skipped bad commits   7.12(6.86+0.26)   7.13(6.87+0.26) +0.1%

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/config.txt

@@ -1712,8 +1712,9 @@ will only cause git to warn.
 fsck.skipList::
 	The path to a list of object names (i.e. one unabbreviated SHA-1 per
 	line) that are known to be broken in a non-fatal way and should
-	be ignored. Comments ('#') and empty lines are not supported, and
-	will error out.
+	be ignored. On versions of Git 2.20 and later comments ('#'), empty
+	lines, and any leading and trailing whitespace is ignored. Everything
+	but a SHA-1 per line will error out on older versions.
 +
 This feature is useful when an established project should be accepted
 despite early commits containing errors that can be safely ignored

fsck.c

@@ -190,6 +190,20 @@ static void init_skiplist(struct fsck_options *options, const char *path)
 		die("Could not open skip list: %s", path);
 	while (!strbuf_getline(&sb, fp)) {
 		const char *p;
+		const char *hash;
+
+		/*
+		 * Allow trailing comments, leading whitespace
+		 * (including before commits), and empty or whitespace
+		 * only lines.
+		 */
+		hash = strchr(sb.buf, '#');
+		if (hash)
+			strbuf_setlen(&sb, hash - sb.buf);
+		strbuf_trim(&sb);
+		if (!sb.len)
+			continue;
+
 		if (parse_oid_hex(sb.buf, &oid, &p) || *p != '\0')
 			die("Invalid SHA-1: %s", sb.buf);
 		oidset_insert(&options->skiplist, &oid);

t/t5504-fetch-receive-strict.sh

@@ -169,20 +169,20 @@ test_expect_success 'fsck with invalid or bogus skipList input' '
 	test_i18ngrep "Invalid SHA-1: \[core\]" err
 '
 
-test_expect_success 'fsck with invalid or bogus skipList input (comments & empty lines)' '
+test_expect_success 'fsck with other accepted skipList input (comments & empty lines)' '
 	cat >SKIP.with-comment <<-EOF &&
 	# Some bad commit
 	0000000000000000000000000000000000000001
 	EOF
 	test_must_fail git -c fsck.skipList=SKIP.with-comment fsck 2>err-with-comment &&
-	test_i18ngrep "^fatal: Invalid SHA-1: # Some bad commit$" err-with-comment &&
+	test_i18ngrep "missingEmail" err-with-comment &&
 	cat >SKIP.with-empty-line <<-EOF &&
 	0000000000000000000000000000000000000001
 
 	0000000000000000000000000000000000000002
 	EOF
 	test_must_fail git -c fsck.skipList=SKIP.with-empty-line fsck 2>err-with-empty-line &&
-	test_i18ngrep "^fatal: Invalid SHA-1: " err-with-empty-line
+	test_i18ngrep "missingEmail" err-with-empty-line
 '
 
 test_expect_success 'fsck no garbage output from comments & empty lines errors' '
@@ -196,6 +196,19 @@ test_expect_success 'fsck with invalid abbreviated skipList input' '
 	test_i18ngrep "^fatal: Invalid SHA-1: " err-abbreviated
 '
 
+test_expect_success 'fsck with exhaustive accepted skipList input (various types of comments etc.)' '
+	>SKIP.exhaustive &&
+	echo "# A commented line" >>SKIP.exhaustive &&
+	echo "" >>SKIP.exhaustive &&
+	echo " " >>SKIP.exhaustive &&
+	echo " # Comment after whitespace" >>SKIP.exhaustive &&
+	echo "$commit # Our bad commit (with leading whitespace and trailing comment)" >>SKIP.exhaustive &&
+	echo "# Some bad commit (leading whitespace)" >>SKIP.exhaustive &&
+	echo "  0000000000000000000000000000000000000001" >>SKIP.exhaustive &&
+	git -c fsck.skipList=SKIP.exhaustive fsck 2>err &&
+	test_must_be_empty err
+'
+
 test_expect_success 'push with receive.fsck.skipList' '
 	git push . $commit:refs/heads/bogus &&
 	rm -rf dst &&