summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
authorKirill Smelkov <kirr@mns.spb.ru>2013-03-07 14:55:07 +0400
committerJunio C Hamano <gitster@pobox.com>2013-03-09 11:11:19 -0800
commit6cd3c0532772749bcf6c4688f34c8ecc65ecb655 (patch)
treee9cbd620a7e93668a04d87b2c0fd1a2017e2b3d5 /utf8.c
parent15999998fbda60552742275570947431b57108ae (diff)
downloadgit-6cd3c0532772749bcf6c4688f34c8ecc65ecb655.tar.gz
format-patch: RFC 2047 says multi-octet character may not be split
Even though an earlier attempt (bafc478..41dd00bad) cleaned up RFC 2047 encoding, pretty.c::add_rfc2047() still decides where to split the output line by going through the input one byte at a time, and potentially splits a character in the middle. A subject line may end up showing like this: ".... fö?? bar". (instead of ".... föö bar".) if split incorrectly. RFC 2047, section 5 (3) explicitly forbids such beaviour Each 'encoded-word' MUST represent an integral number of characters. A multi-octet character may not be split across adjacent 'encoded- word's. that means that e.g. for Subject: .... föö bar encoding Subject: =?UTF-8?q?....=20f=C3=B6=C3=B6?= =?UTF-8?q?=20bar?= is correct, and Subject: =?UTF-8?q?....=20f=C3=B6=C3?= <-- NOTE ö is broken here =?UTF-8?q?=B6=20bar?= is not, because "ö" character UTF-8 encoding C3 B6 is split here across adjacent encoded words. To fix the problem, make the loop grab one _character_ at a time and determine its output length to see where to break the output line. Note that this version only knows about UTF-8, but the logic to grab one character is abstracted out in mbs_chrlen() function to make it possible to extend it to other encodings with the help of iconv in the future. Signed-off-by: Kirill Smelkov <kirr@mns.spb.ru> Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c39
1 files changed, 39 insertions, 0 deletions
diff --git a/utf8.c b/utf8.c
index 5c61bbe113..0b30b54847 100644
--- a/utf8.c
+++ b/utf8.c
@@ -495,3 +495,42 @@ char *reencode_string(const char *in, const char *out_encoding, const char *in_e
return out;
}
#endif
+
+/*
+ * Returns first character length in bytes for multi-byte `text` according to
+ * `encoding`.
+ *
+ * - The `text` pointer is updated to point at the next character.
+ * - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes
+ * we can consume from text, and on exit `*remainder_p` is reduced by returned
+ * character length. Otherwise `text` is treated as limited by NUL.
+ */
+int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
+{
+ int chrlen;
+ const char *p = *text;
+ size_t r = (remainder_p ? *remainder_p : SIZE_MAX);
+
+ if (r < 1)
+ return 0;
+
+ if (is_encoding_utf8(encoding)) {
+ pick_one_utf8_char(&p, &r);
+
+ chrlen = p ? (p - *text)
+ : 1 /* not valid UTF-8 -> raw byte sequence */;
+ }
+ else {
+ /*
+ * TODO use iconv to decode one char and obtain its chrlen
+ * for now, let's treat encodings != UTF-8 as one-byte
+ */
+ chrlen = 1;
+ }
+
+ *text += chrlen;
+ if (remainder_p)
+ *remainder_p -= chrlen;
+
+ return chrlen;
+}