diff options
| author | Peter Krefting <peter@softwolves.pp.se> | 2013-07-09 12:16:33 +0100 |
|---|---|---|
| committer | Junio C Hamano <gitster@pobox.com> | 2013-07-09 09:01:24 -0700 |
| commit | 81050ac604e27395509b5bffe80692a14d6ad3cd (patch) | |
| tree | 3c9035558c03b9d0f80cd75a14617482236e5e86 /commit.c | |
| parent | e82bd6cc70db28dab8d0434e4033013adcd0abfa (diff) | |
| download | git-81050ac604e27395509b5bffe80692a14d6ad3cd.tar.gz | |
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 <peter@softwolves.pp.se>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'commit.c')
| -rw-r--r-- | commit.c | 7 |
1 files changed, 5 insertions, 2 deletions
@@ -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; |