fsck: detect and warn a commit with embedded NULjc/fsck-nul-in-commit

Even though a Git commit object is designed to be capable of storing
any binary data as its payload, in practice people use it to describe
the changes in textual form, and tools like "git log" are designed to
treat the payload as text.

Detect and warn when we see any commit object with a NUL byte in
it.

Note that a NUL byte in the header part is already detected as a
grave error.  This change is purely about the message part.

Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 26 insertions, 0 deletions

diff --git a/fsck.c b/fsck.c
index 21dfa5f98c..3366b3fb62 100644
--- a/fsck.c
+++ b/fsck.c
@@ -59,6 +59,7 @@
 	FUNC(HAS_DOTGIT, WARN) \
 	FUNC(NULL_SHA1, WARN) \
 	FUNC(ZERO_PADDED_FILEMODE, WARN) \
+	FUNC(NUL_IN_COMMIT, WARN) \
 	/* infos (reported as warnings, but ignored by default) */ \
 	FUNC(BAD_TAG_NAME, INFO) \
 	FUNC(MISSING_TAGGER_ENTRY, INFO)
@@ -610,6 +611,7 @@ static int fsck_commit_buffer(struct commit *commit, const char *buffer,
 	struct commit_graft *graft;
 	unsigned parent_count, parent_line_count = 0, author_count;
 	int err;
+	const char *buffer_begin = buffer;
 
 	if (verify_headers(buffer, size, &commit->object, options))
 		return -1;
@@ -671,6 +673,12 @@ static int fsck_commit_buffer(struct commit *commit, const char *buffer,
 		if (err)
 			return err;
 	}
+	if (memchr(buffer_begin, '\0', size)) {
+		err = report(options, &commit->object, FSCK_MSG_NUL_IN_COMMIT,
+			     "NUL byte in the commit object body");
+		if (err)
+			return err;
+	}
 	return 0;
 }
 
diff --git a/t/t1450-fsck.sh b/t/t1450-fsck.sh
index e66b7cb697..7ee8ea004f 100755
--- a/t/t1450-fsck.sh
+++ b/t/t1450-fsck.sh
@@ -427,6 +427,24 @@ test_expect_success 'fsck allows .Ňit' '
 	)
 '
 
+test_expect_success 'NUL in commit' '
+	rm -fr nul-in-commit &&
+	git init nul-in-commit &&
+	(
+		cd nul-in-commit &&
+		git commit --allow-empty -m "initial commitQNUL after message" &&
+		git cat-file commit HEAD >original &&
+		q_to_nul <original >munged &&
+		git hash-object -w -t commit --stdin <munged >name &&
+		git branch bad $(cat name) &&
+
+		test_must_fail git -c fsck.nulInCommit=error fsck 2>warn.1 &&
+		grep nulInCommit warn.1 &&
+		git fsck 2>warn.2 &&
+		grep nulInCommit warn.2
+	)
+'
+
 # create a static test repo which is broken by omitting
 # one particular object ($1, which is looked up via rev-parse
 # in the new repository).