format-patch: do not wrap rfc2047 encoded headers too late

Encoded characters add more than one character at once to an encoded
header. Include all characters that are about to be added in the length
calculation for wrapping.

Additionally, RFC 2047 imposes a maximum line length of 76 characters
if that line contains an rfc2047 encoded word.

Signed-off-by: Jan H. Schönherr <schnhrr@cs.tu-berlin.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/pretty.c b/pretty.c
index 71e402466305fc1e5352187a053ba5d107dace48..da758799993b8b4869d01be6375186c1378d7df5 100644 (file)
--- a/pretty.c
+++ b/pretty.c
@@ -263,6 +263,9 @@ static void add_rfc822_quoted(struct strbuf *out, const char *s, int len)
 
 static int is_rfc2047_special(char ch)
 {
+       if (ch == ' ' || ch == '\n')
+               return 1;
+
        return (non_ascii(ch) || (ch == '=') || (ch == '?') || (ch == '_'));
 }
 
@@ -270,6 +273,7 @@ static void add_rfc2047(struct strbuf *sb, const char *line, int len,
                       const char *encoding)
 {
        static const int max_length = 78; /* per rfc2822 */
+       static const int max_encoded_length = 76; /* per rfc2047 */
        int i;
        int line_len;
 
@@ -295,23 +299,25 @@ needquote:
        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);
+
+               /*
+                * According to RFC 2047, we could encode the special character
+                * ' ' (space) with '_' (underscore) for readability. But many
+                * programs do not understand this and just leave the
+                * underscore in place. Thus, we do nothing special here, which
+                * causes ' ' to be encoded as '=20', avoiding this problem.
+                */
 
-               if (line_len >= max_length - 2) {
+               if (line_len + 2 + (is_special ? 3 : 1) > max_encoded_length) {
                        strbuf_addf(sb, "?=\n =?%s?q?", encoding);
                        line_len = strlen(encoding) + 5 + 1; /* =??q? plus SP */
                }
 
-               /*
-                * We encode ' ' using '=20' even though rfc2047
-                * allows using '_' for readability.  Unfortunately,
-                * many programs do not understand this and just
-                * leave the underscore in place.
-                */
-               if (is_rfc2047_special(ch) || ch == ' ' || ch == '\n') {
+               if (is_special) {
                        strbuf_addf(sb, "=%02X", ch);
                        line_len += 3;
-               }
-               else {
+               } else {
                        strbuf_addch(sb, ch);
                        line_len++;
                }

diff --git a/t/t4014-format-patch.sh b/t/t4014-format-patch.sh
index d66e358301589ab5f72dcef502baacb0b8c94b4f..1d5636d8a047b7a411f244413dab026a4b1bb1b5 100755 (executable)
--- a/t/t4014-format-patch.sh
+++ b/t/t4014-format-patch.sh
@@ -772,30 +772,31 @@ M8="föö bar "
 M64=$M8$M8$M8$M8$M8$M8$M8$M8
 M512=$M64$M64$M64$M64$M64$M64$M64$M64
 cat >expect <<'EOF'
-Subject: [PATCH] =?UTF-8?q?f=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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=B6?=
- =?UTF-8?q?=C3=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?=
+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?=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=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?=
 EOF
-test_expect_success 'format-patch wraps extremely long headers (rfc2047)' '
+test_expect_success 'format-patch wraps extremely long subject (rfc2047)' '
        rm -rf patches/ &&
        echo content >>file &&
        git add file &&
@@ -861,6 +862,17 @@ test_expect_success 'format-patch wraps extremely long from-header (rfc822)' '
        check_author "Foo.Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar"
 '
 
+cat >expect <<'EOF'
+From: =?UTF-8?q?Fo=C3=B6=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo?=
+ =?UTF-8?q?=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20?=
+ =?UTF-8?q?Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar?=
+ =?UTF-8?q?=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20Foo=20Bar=20?=
+ =?UTF-8?q?Foo=20Bar=20Foo=20Bar?= <author@example.com>
+EOF
+test_expect_success 'format-patch wraps extremely long from-header (rfc2047)' '
+       check_author "Foö Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar Foo Bar"
+'
+
 cat >expect <<'EOF'
 Subject: header with . in it
 EOF