Intro
-----
In 'Subject:' characters are encoded in Q encoding, as per RFC 2047, e.g.
föö
becomes
=?UTF-8?q?f=C3=B6=C3=B6?=
. Long encoded lines must be wrapped to be no longer than 76 bytes.
Also RFC 2047, section 5 (3) says:
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 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.
~~~~
As it is now, format-patch does not respect "multi-octet charactes may
not be split" rule, and so sending patches with non-english subject has
issues:
The problematic case shows in mail readers as ".... fö?? bar".
Solution
--------
I introduce mbs_chrlen() function to compute character length in bytes
for multi-byte text according to encoding, and use it appropriately in
add_rfc2047() in pretty.
So far it works correctly only for UTF-8 encoding, because we have
infrastructure for it in place already, but other encoding could be
supported too in the future with the help of iconv. For now they all, except
UTF-8, are treated as being one-byte encodings, which was format-patch
current behaviour, with appropriate TODO put in mbs_chrlen().
Not sure whether mbs_chrlen() is a good name, but otherwise my
understanding is that the patch is ok to go in.
Thanks.
Cc: Jan H. Schönherr <schn...@cs.tu-berlin.de>
Signed-off-by: Kirill Smelkov <k...@mns.spb.ru>
---
pretty.c | 27 +++++++++++++++++++--------
t/t4014-format-patch.sh | 27 ++++++++++++++-------------
utf8.c | 39 +++++++++++++++++++++++++++++++++++++++
utf8.h | 2 ++
4 files changed, 74 insertions(+), 21 deletions(-)
diff --git a/pretty.c b/pretty.c
index b57adef..c9c7ff5 100644
--- a/pretty.c
+++ b/pretty.c
@@ -345,7 +345,7 @@ static int needs_rfc2047_encoding(const char *line, int len,
return 0;
}
-static void add_rfc2047(struct strbuf *sb, const char *line, int len,
+static void add_rfc2047(struct strbuf *sb, const char *line, size_t len,
const char *encoding, enum rfc2047_type type)
{
static const int max_encoded_length = 76; /* per rfc2047 */
@@ -355,9 +355,18 @@ static void add_rfc2047(struct strbuf *sb, const char
*line, int len,
strbuf_grow(sb, len * 3 + strlen(encoding) + 100);
strbuf_addf(sb, "=?%s?q?", encoding);
line_len += strlen(encoding) + 5; /* 5 for =??q? */
- for (i = 0; i < len; i++) {
- unsigned ch = line[i] & 0xFF;
- int is_special = is_rfc2047_special(ch, type);
+
+ while (len) {
+ /*
+ * RFC 2047, section 5 (3):
+ *
+ * Each 'encoded-word' MUST represent an integral number of
+ * characters. A multi-octet character may not be split across
+ * adjacent 'encoded- word's.
+ */
+ const unsigned char *p = (const unsigned char *)line;
+ int chrlen = mbs_chrlen(&line, &len, encoding);
+ int is_special = (chrlen > 1) || is_rfc2047_special(*p, type);
/*
* According to RFC 2047, we could encode the special character
@@ -367,16 +376,18 @@ static void add_rfc2047(struct strbuf *sb, const char
*line, int len,
* causes ' ' to be encoded as '=20', avoiding this problem.
*/
- if (line_len + 2 + (is_special ? 3 : 1) > max_encoded_length) {
+ if (line_len + 2 + (is_special ? 3*chrlen : 1) >
max_encoded_length) {
strbuf_addf(sb, "?=\n =?%s?q?", encoding);
line_len = strlen(encoding) + 5 + 1; /* =??q? plus SP */
}
if (is_special) {
- strbuf_addf(sb, "=%02X", ch);
- line_len += 3;
+ for (i = 0; i < chrlen; i++) {
+ strbuf_addf(sb, "=%02X", p[i]);
+ line_len += 3;
+ }
} else {
- strbuf_addch(sb, ch);
+ strbuf_addch(sb, *p);
line_len++;
}
}
diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh
index 78633cb..b993dae 100755
--- a/t/t4014-format-patch.sh
+++ b/t/t4014-format-patch.sh
@@ -837,25 +837,26 @@ Subject: [PATCH]
=?UTF-8?q?f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
=?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?=
=?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?=
=?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?=
- =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3?=
- =?UTF-8?q?=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?=
- =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3?=
- =?UTF-8?q?=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
+ =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?=
+ =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
=?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?=
=?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?=
=?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?=
- =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3?=
- =?UTF-8?q?=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?=
- =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3?=
- =?UTF-8?q?=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
+ =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?=
+ =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
=?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?=
=?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?=
=?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?=
- =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3?=
- =?UTF-8?q?=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?=
- =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3?=
- =?UTF-8?q?=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
- =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?=
+ =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?=
+ =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
+ =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?=
+ =?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?=
+ =?UTF-8?q?bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6?=
+ =?UTF-8?q?=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6?=
+ =?UTF-8?q?=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f?=
+ =?UTF-8?q?=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar?=
+ =?UTF-8?q?=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20bar=20f=C3=B6=C3=B6=20?=
+ =?UTF-8?q?bar?=
EOF
test_expect_success 'format-patch wraps extremely long subject (rfc2047)' '
rm -rf patches/ &&
diff --git a/utf8.c b/utf8.c
index 8f6e84b..7911b58 100644
--- a/utf8.c
+++ b/utf8.c
@@ -531,3 +531,42 @@ 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 : INT_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;
+}
diff --git a/utf8.h b/utf8.h
index 501b2bd..1f8ecad 100644
--- a/utf8.h
+++ b/utf8.h
@@ -22,4 +22,6 @@ char *reencode_string(const char *in, const char
*out_encoding, const char *in_e
#define reencode_string(a,b,c) NULL
#endif
+int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding);
+
#endif
--
1.8.2.rc2.353.gd2380b4
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
