summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2013-03-25 14:00:46 -0700
committerJunio C Hamano <gitster@pobox.com>2013-03-25 14:00:46 -0700
commit573f1a9cf163365637a36a6d95c670883a918352 (patch)
treeeffc3020b28a5f60dfb0f20151bd47a315f342da
parentfb3b7b1f95ce3c39f1116ebabf0bbcbfd3bb8796 (diff)
parent6cd3c0532772749bcf6c4688f34c8ecc65ecb655 (diff)
downloadgit-573f1a9cf163365637a36a6d95c670883a918352.tar.gz
Merge branch 'ks/rfc2047-one-char-at-a-time'
When "format-patch" quoted a non-ascii strings on the header files, it incorrectly applied rfc2047 and chopped a single character in the middle of it. * ks/rfc2047-one-char-at-a-time: format-patch: RFC 2047 says multi-octet character may not be split
-rw-r--r--pretty.c34
-rwxr-xr-xt/t4014-format-patch.sh27
-rw-r--r--utf8.c39
-rw-r--r--utf8.h2
4 files changed, 77 insertions, 25 deletions
diff --git a/pretty.c b/pretty.c
index b57adefdd2..41f04e669d 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 +355,22 @@ 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);
+
+ /* "=%02X" * chrlen, or the byte itself */
+ const char *encoded_fmt = is_special ? "=%02X" : "%c";
+ int encoded_len = is_special ? 3 * chrlen : 1;
/*
* According to RFC 2047, we could encode the special character
@@ -367,18 +380,15 @@ 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 + encoded_len + 2 > max_encoded_length) {
+ /* It won't fit with trailing "?=" --- break the line */
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;
- } else {
- strbuf_addch(sb, ch);
- line_len++;
- }
+ for (i = 0; i < chrlen; i++)
+ strbuf_addf(sb, encoded_fmt, p[i]);
+ line_len += encoded_len;
}
strbuf_addstr(sb, "?=");
}
diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh
index 7fa3647514..bb1fc47fe8 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 8f6e84b7b3..7f648574a5 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 : 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;
+}
diff --git a/utf8.h b/utf8.h
index 501b2bd9c4..1f8ecad1e8 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