[PATCH v2 2/2] 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).
---
git-send-email.perl | 26 ++++++++++++++++----------
t/t9001-send-email.sh | 7 +++++++
2 files changed, 23 insertions(+), 10 deletions(-)
diff --git a/git-send-email.perl b/git-send-email.perl
index d461ffb..7d5cc8a 100755
--- a/git-send-email.perl
+++ b/git-send-email.perl
@@ -919,17 +919,23 @@ $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 19a3ced..fa965ff 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'
--
2.1.1
Роман Донченко <dpb@corrigendum.ru>