[PATCH v2 2/2] index-pack: --fsck-objects to take an optional argument for fsck msgs

From: John Cai via GitGitGadget <gitgitgadget@gmail.com>
Date: Jan 26, 2024, 17:13 UTC
Message-ID: <cce63c6465fb1e29252d7e0918e03ff0f08d37f4.1706289180.git.gitgitgadget@gmail.com>
In-Reply-To: <pull.1658.v2.git.git.1706289180.gitgitgadget@gmail.com>

From: John Cai <johncai86@gmail.com>

git-index-pack has a --strict option that can take an optional argument to provide a list of fsck issues to change their severity. --fsck-objects does not have such a utility, which would be useful if one would like to be more lenient or strict on data integrity in a repository.

Like --strict, allow --fsck-objects to also take a list of fsck msgs to change the severity.

Remove the "For internal use only" note for --fsck-objects, and document the option. This won't often be used by the normal end user, but it turns out it is useful for Git forges like GitLab.

Signed-off-by: John Cai <johncai86@gmail.com>
---
 Documentation/git-index-pack.txt | 10 ++++++++--
 builtin/index-pack.c             |  5 +++--
 t/t5300-pack-object.sh           | 29 ++++++++++++++++++++++++-----
 3 files changed, 35 insertions(+), 9 deletions(-)

diff --git a/Documentation/git-index-pack.txt b/Documentation/git-index-pack.txt
index f7a98bbf9c8..916652d3b1b 100644
--- a/Documentation/git-index-pack.txt
+++ b/Documentation/git-index-pack.txt
@@ -96,8 +96,14 @@ default and "Indexing objects" when `--stdin` is specified.
 --check-self-contained-and-connected::
 	Die if the pack contains broken links. For internal use only.
 
---fsck-objects::
-	For internal use only.
+--fsck-objects[=<msg-ids>=<severity>...]::
+	Instructs index-pack to check for broken objects, but unlike `--strict`,
+	does not choke on broken links. If `<msg-ids>` is passed, it should be
+	a comma-separated list of `<msg-id>=<severity>` where `<msg-id>` and
+	`<severity>` are used to change the severity of `fsck` errors e.g.,
+	`--strict="missingEmail=ignore,badTagName=ignore"`. See the entry for
+	the `fsck.<msg-id>` configuration options in `linkgit:git-fsck[1] for
+	more information on the possible values of `<msg-id>` and `<severity>`.
 +
 Die if the pack contains broken objects. If the pack contains a tree
 pointing to a .gitmodules blob that does not exist, prints the hash of
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 1e53ca23775..519162f5b91 100644
--- a/builtin/index-pack.c
+++ b/builtin/index-pack.c
@@ -24,7 +24,7 @@
 #include "setup.h"
 
 static const char index_pack_usage[] =
-"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--[no-]rev-index] [--verify] [--strict[=<msg-ids>]] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
+"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--[no-]rev-index] [--verify] [--strict[=<msg-ids>]] [--fsck-objects[=<msg-ids>]] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";
 
 struct object_entry {
 	struct pack_idx_entry idx;
@@ -1785,8 +1785,9 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 			} else if (!strcmp(arg, "--check-self-contained-and-connected")) {
 				strict = 1;
 				check_self_contained_and_connected = 1;
-			} else if (!strcmp(arg, "--fsck-objects")) {
+			} else if (skip_to_optional_arg(arg, "--fsck-objects", &arg)) {
 				do_fsck_object = 1;
+				fsck_set_msg_types(&fsck_options, arg);
 			} else if (!strcmp(arg, "--verify")) {
 				verify = 1;
 			} else if (!strcmp(arg, "--verify-stat")) {
diff --git a/t/t5300-pack-object.sh b/t/t5300-pack-object.sh
index 496fffa0f8a..a58f91035d1 100755
--- a/t/t5300-pack-object.sh
+++ b/t/t5300-pack-object.sh
@@ -441,8 +441,7 @@ test_expect_success 'index-pack with --strict' '
 	)
 '
 
-test_expect_success 'index-pack with --strict downgrading fsck msgs' '
-	test_when_finished rm -rf strict &&
+test_expect_success 'setup for --strict and --fsck-objects downgrading fsck msgs' '
 	git init strict &&
 	(
 		cd strict &&
@@ -457,12 +456,32 @@ test_expect_success 'index-pack with --strict downgrading fsck msgs' '
 
 		EOF
 		git hash-object --literally -t commit -w --stdin <commit >commit_list &&
-		PACK=$(git pack-objects test <commit_list) &&
-		test_must_fail git index-pack --strict "test-$PACK.pack" &&
-		git index-pack --strict="missingEmail=ignore" "test-$PACK.pack"
+		git pack-objects test <commit_list >pack-name
 	)
 '
 
+test_with_bad_commit () {
+	must_fail_arg="$1" &&
+	must_pass_arg="$2" &&
+	(
+		cd strict &&
+		test_expect_fail git index-pack "$must_fail_arg" "test-$(cat pack-name).pack"
+		git index-pack "$must_pass_arg" "test-$(cat pack-name).pack"
+	)
+}
+
+test_expect_success 'index-pack with --strict downgrading fsck msgs' '
+	test_with_bad_commit --strict --strict="missingEmail=ignore"
+'
+
+test_expect_success 'index-pack with --fsck-objects downgrading fsck msgs' '
+	test_with_bad_commit --fsck-objects --fsck-objects="missingEmail=ignore"
+'
+
+test_expect_success 'cleanup for --strict and --fsck-objects downgrading fsck msgs' '
+	rm -rf strict
+'
+
 test_expect_success 'honor pack.packSizeLimit' '
 	git config pack.packSizeLimit 3m &&
 	packname_10=$(git pack-objects test-10 <obj-list) &&

-- 
gitgitgadget