From 81050ac604e27395509b5bffe80692a14d6ad3cd Mon Sep 17 00:00:00 2001 From: Peter Krefting Date: Tue, 9 Jul 2013 12:16:33 +0100 Subject: commit: reject non-characters 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 Signed-off-by: Junio C Hamano --- commit.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'commit.c') diff --git a/commit.c b/commit.c index 5097dba39..7dcfeea2d 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; -- cgit v1.2.1