[PATCH] send-email: handle adjacent RFC 2047-encoded words properly

["Роман Донченко" <dpb@corrigendum.ru>]

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

I change the sender's name to an all-Cyrillic string in the tests so that
its encoded form goes over the 76 characters in a line limit, forcing
format-patch to split it into multiple encoded words.

Since I have to modify the regular expression for an encoded word anyway,
I take the opportunity to bring it closer to the spec, most notably
disallowing embedded spaces and making it case-insensitive (thus allowing
the encoding to be specified as both "q" and "Q").

Signed-off-by: Роман Донченко <dpb@corrigendum.ru>
---
 git-send-email.perl   | 21 +++++++++++++++------
 t/t9001-send-email.sh | 18 +++++++++---------
 2 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/git-send-email.perl b/git-send-email.perl
index 9949db0..4bb9f6f 100755
--- a/git-send-email.perl
+++ b/git-send-email.perl
@@ -913,13 +913,22 @@ $time = time - scalar $#files;
 
 sub unquote_rfc2047 {
 	local ($_) = @_;
+
+	my $et = qr/[!->@-~]+/; # encoded-text from RFC 2047
+	my $sep = qr/[ \t]+/;
+	my $encoded_word = qr/=\?($et)\?q\?($et)\?=/i;
+
 	my $encoding;
-	s{=\?([^?]+)\?q\?(.*?)\?=}{
-		$encoding = $1;
-		my $e = $2;
-		$e =~ s/_/ /g;
-		$e =~ s/=([0-9A-F]{2})/chr(hex($1))/eg;
-		$e;
+	s{$encoded_word(?:$sep$encoded_word)+}{
+		my @words = split $sep, $&;
+		foreach (@words) {
+			m/$encoded_word/;
+			$encoding = $1;
+			$_ = $2;
+			s/_/ /g;
+			s/=([0-9A-F]{2})/chr(hex($1))/eg;
+		}
+		join '', @words;
 	}eg;
 	return wantarray ? ($_, $encoding) : $_;
 }
diff --git a/t/t9001-send-email.sh b/t/t9001-send-email.sh
index 19a3ced..318b870 100755
--- a/t/t9001-send-email.sh
+++ b/t/t9001-send-email.sh
@@ -236,7 +236,7 @@ test_expect_success $PREREQ 'self name with dot is suppressed' "
 "
 
 test_expect_success $PREREQ 'non-ascii self name is suppressed' "
-	test_suppress_self_quoted 'Füñný Nâmé' 'odd_?=mail@example.com' \
+	test_suppress_self_quoted 'Кириллическое Имя' 'odd_?=mail@example.com' \
 		'non_ascii_self_suppressed'
 "
 
@@ -946,25 +946,25 @@ test_expect_success $PREREQ 'utf8 author is correctly passed on' '
 	clean_fake_sendmail &&
 	test_commit weird_author &&
 	test_when_finished "git reset --hard HEAD^" &&
-	git commit --amend --author "Füñný Nâmé <odd_?=mail@example.com>" &&
-	git format-patch --stdout -1 >funny_name.patch &&
+	git commit --amend --author "Кириллическое Имя <odd_?=mail@example.com>" &&
+	git format-patch --stdout -1 >nonascii_name.patch &&
 	git send-email --from="Example <nobody@example.com>" \
 	  --to=nobody@example.com \
 	  --smtp-server="$(pwd)/fake.sendmail" \
-	  funny_name.patch &&
-	grep "^From: Füñný Nâmé <odd_?=mail@example.com>" msgtxt1
+	  nonascii_name.patch &&
+	grep "^From: Кириллическое Имя <odd_?=mail@example.com>" msgtxt1
 '
 
 test_expect_success $PREREQ 'utf8 sender is not duplicated' '
 	clean_fake_sendmail &&
 	test_commit weird_sender &&
 	test_when_finished "git reset --hard HEAD^" &&
-	git commit --amend --author "Füñný Nâmé <odd_?=mail@example.com>" &&
-	git format-patch --stdout -1 >funny_name.patch &&
-	git send-email --from="Füñný Nâmé <odd_?=mail@example.com>" \
+	git commit --amend --author "Кириллическое Имя <odd_?=mail@example.com>" &&
+	git format-patch --stdout -1 >nonascii_name.patch &&
+	git send-email --from="Кириллическое Имя <odd_?=mail@example.com>" \
 	  --to=nobody@example.com \
 	  --smtp-server="$(pwd)/fake.sendmail" \
-	  funny_name.patch &&
+	  nonascii_name.patch &&
 	grep "^From: " msgtxt1 >msgfrom &&
 	test_line_count = 1 msgfrom
 '
-- 
2.1.1