From: Роман Донченко <dpb@corrigendum.ru>
Date: Sun, 14 Dec 2014 15:59:47 +0000 (+0300)
Subject: send-email: handle adjacent RFC 2047-encoded words properly
X-Git-Tag: v2.3.0-rc0~20^2
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=ab47e2a583917ecef5da269cc640f8359c8467ac;p=thirdparty%2Fgit.git

send-email: handle adjacent RFC 2047-encoded words properly

The RFC says that they are to be concatenated after decoding (i.e. the
intervening whitespace is ignored).

Signed-off-by: Роман Донченко <dpb@corrigendum.ru>
Acked-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---

diff --git a/git-send-email.perl b/git-send-email.perl
index 106c2b065d..cd327d7043 100755
--- a/git-send-email.perl
+++ b/git-send-email.perl
@@ -912,17 +912,23 @@ $time = time - scalar $#files;
 sub unquote_rfc2047 {
 	local ($_) = @_;
 	my $charset;
-	s{$re_encoded_word}{
-		$charset = $1;
-		my $encoding = $2;
-		my $text = $3;
-		if ($encoding eq 'q' || $encoding eq 'Q') {
-			$text =~ s/_/ /g;
-			$text =~ s/=([0-9A-F]{2})/chr(hex($1))/egi;
-			$text;
-		} else {
-			$&; # other encodings not supported yet
+	my $sep = qr/[ \t]+/;
+	s{$re_encoded_word(?:$sep$re_encoded_word)*}{
+		my @words = split $sep, $&;
+		foreach (@words) {
+			m/$re_encoded_word/;
+			$charset = $1;
+			my $encoding = $2;
+			my $text = $3;
+			if ($encoding eq 'q' || $encoding eq 'Q') {
+				$_ = $text;
+				s/_/ /g;
+				s/=([0-9A-F]{2})/chr(hex($1))/egi;
+			} else {
+				# other encodings not supported yet
+			}
 		}
+		join '', @words;
 	}eg;
 	return wantarray ? ($_, $charset) : $_;
 }
diff --git a/t/t9001-send-email.sh b/t/t9001-send-email.sh
index 1ecdacb6fd..f933bc7ec7 100755
--- a/t/t9001-send-email.sh
+++ b/t/t9001-send-email.sh
@@ -240,6 +240,13 @@ test_expect_success $PREREQ 'non-ascii self name is suppressed' "
 		'non_ascii_self_suppressed'
 "
 
+# This name is long enough to force format-patch to split it into multiple
+# encoded-words, assuming it uses UTF-8 with the "Q" encoding.
+test_expect_success $PREREQ 'long non-ascii self name is suppressed' "
+	test_suppress_self_quoted 'Ƒüñníęř €. Nâṁé' 'odd_?=mail@example.com' \
+		'long_non_ascii_self_suppressed'
+"
+
 test_expect_success $PREREQ 'sanitized self name is suppressed' "
 	test_suppress_self_unquoted '\"A U. Thor\"' 'author@example.com' \
 		'self_name_sanitized_suppressed'