[PATCH v2 1/2] send-email: align RFC 2047 decoding more closely with the spec
More specifically:
* Add "\" to the list of characters not allowed in a token (see RFC 2047
errata).
* Share regexes between unquote_rfc2047 and is_rfc2047_quoted. Besides
removing duplication, this also makes unquote_rfc2047 more stringent.
* Allow both "q" and "Q" to identify the encoding.
* Allow lowercase hexadecimal digits in the "Q" encoding.
And, more on the cosmetic side:
* Change the "encoded-text" regex to exclude rather than include characters,
for clarity and consistency with "token".
Signed-off-by: Роман Донченко <dpb@corrigendum.ru>
Acked-by: Jeff King <peff@peff.net>
---
git-send-email.perl | 30 +++++++++++++++++++-----------
1 file changed, 19 insertions(+), 11 deletions(-)
diff --git a/git-send-email.perl b/git-send-email.perl
index 9949db0..d461ffb 100755
--- a/git-send-email.perl
+++ b/git-send-email.perl
@@ -145,6 +145,11 @@ my $have_mail_address = eval { require Mail::Address; 1 };
my $smtp;
my $auth;
+# Regexes for RFC 2047 productions.
+my $re_token = qr/[^][()<>@,;:\\"\/?.= \000-\037\177-\377]+/;
+my $re_encoded_text = qr/[^? \000-\037\177-\377]+/;
+my $re_encoded_word = qr/=\?($re_token)\?($re_token)\?($re_encoded_text)\?=/;
+
# Variables we fill in automatically, or via prompting:
my (@to,$no_to,@initial_to,@cc,$no_cc,@initial_cc,@bcclist,$no_bcc,@xh,
$initial_reply_to,$initial_subject,@files,
@@ -913,15 +918,20 @@ $time = time - scalar $#files;
sub unquote_rfc2047 {
local ($_) = @_;
- my $encoding;
- s{=\?([^?]+)\?q\?(.*?)\?=}{
- $encoding = $1;
- my $e = $2;
- $e =~ s/_/ /g;
- $e =~ s/=([0-9A-F]{2})/chr(hex($1))/eg;
- $e;
+ 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 {
+ $&; # other encodings not supported yet
+ }
}eg;
- return wantarray ? ($_, $encoding) : $_;
+ return wantarray ? ($_, $charset) : $_;
}
sub quote_rfc2047 {
@@ -934,10 +944,8 @@ sub quote_rfc2047 {
sub is_rfc2047_quoted {
my $s = shift;
- my $token = qr/[^][()<>@,;:"\/?.= \000-\037\177-\377]+/;
- my $encoded_text = qr/[!->@-~]+/;
length($s) <= 75 &&
- $s =~ m/^(?:"[[:ascii:]]*"|=\?$token\?$token\?$encoded_text\?=)$/o;
+ $s =~ m/^(?:"[[:ascii:]]*"|$re_encoded_word)$/o;
}
sub subject_needs_rfc2047_quoting {
--
2.1.1
Роман Донченко <dpb@corrigendum.ru>