[PATCH] commit: reject non-characters

[Peter Krefting <peter@softwolves.pp.se>]

Unicode clause D14 defines all characters U+nFFFE and U+nFFFF (where
0 <= n <= 10h) as well as the range U+FDD0..U+FDEF as non-characters,
reserved for internal use only.  Disallow these characters in commit
messages as they are normally not recommended for interchange.

Signed-off-by: Peter Krefting <peter@softwolves.pp.se>
---
Junio C Hamano:

> Yeah, while we are at it, doing this may not hurt.  I think Brian's
> two patches are in fairly good shape otherwise, so perhaps you can
> do this as a follow-up patch on top of the tip of the topic,
> e82bd6cc (commit: reject overlong UTF-8 sequences, 2013-07-04)?

OK, here you are. Enjoy :)

  commit.c               |  7 +++++--
  t/t3900-i18n-commit.sh | 18 ++++++++++++++++++
  2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/commit.c b/commit.c
index 5097dba..0587732 100644
--- a/commit.c
+++ b/commit.c
@@ -1305,8 +1305,11 @@ static int find_invalid_utf8(const char *buf, int len)
  		/* Surrogates are only for UTF-16 and cannot be encoded in UTF-8. */
  		if ((codepoint & 0x1ff800) == 0xd800)
  			return bad_offset;
-		/* U+FFFE and U+FFFF are guaranteed non-characters. */
-		if ((codepoint & 0x1ffffe) == 0xfffe)
+		/* U+xxFFFE and U+xxFFFF are guaranteed non-characters. */
+		if ((codepoint & 0xffffe) == 0xfffe)
+			return bad_offset;
+		/* So are anything in the range U+FDD0..U+FDEF. */
+		if (codepoint >= 0xfdd0 && codepoint <= 0xfdef)
  			return bad_offset;
  	}
  	return -1;
diff --git a/t/t3900-i18n-commit.sh b/t/t3900-i18n-commit.sh
index 051ea9d..38b00c3 100755
--- a/t/t3900-i18n-commit.sh
+++ b/t/t3900-i18n-commit.sh
@@ -58,6 +58,24 @@ test_expect_success 'UTF-8 overlong sequences rejected' '
  	grep "did not conform" "$HOME"/stderr
  '

+test_expect_success 'UTF-8 non-characters refused' '
+	test_when_finished "rm -f $HOME/stderr $HOME/invalid" &&
+	echo "UTF-8 non-character 1" >F &&
+	printf "Commit message\n\nNon-character:\364\217\277\276\n" \
+		>"$HOME/invalid" &&
+	git commit -a -F "$HOME/invalid" 2>"$HOME"/stderr &&
+	grep "did not conform" "$HOME"/stderr
+'
+
+test_expect_success 'UTF-8 non-characters refused' '
+	test_when_finished "rm -f $HOME/stderr $HOME/invalid" &&
+	echo "UTF-8 non-character 2." >F &&
+	printf "Commit message\n\nNon-character:\357\267\220\n" \
+		>"$HOME/invalid" &&
+	git commit -a -F "$HOME/invalid" 2>"$HOME"/stderr &&
+	grep "did not conform" "$HOME"/stderr
+'
+
  for H in ISO8859-1 eucJP ISO-2022-JP
  do
  	test_expect_success "$H setup" '
-- 
1.8.3.1