mirrors/git
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

send-email: align RFC 2047 decoding more closely with the spec

Browse Source 
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>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Роман Донченко
2014-12-14 18:59:46 +03:00
committed by Junio C Hamano
parent 76f8611a5f
commit 11f70a7e29
1 changed files with 19 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
git-send-email.perl
View File

@ -143,6 +143,11 @@ my $have_mail_address = eval { require Mail::Address; 1 };
my $smtp; my $smtp;
my $auth; 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: # Variables we fill in automatically, or via prompting:
my (@to,$no_to,@initial_to,@cc,$no_cc,@initial_cc,@bcclist,$no_bcc,@xh, my (@to,$no_to,@initial_to,@cc,$no_cc,@initial_cc,@bcclist,$no_bcc,@xh,
$initial_reply_to,$initial_subject,@files, $initial_reply_to,$initial_subject,@files,
@ -906,15 +911,20 @@ $time = time - scalar $#files;
sub unquote_rfc2047 { sub unquote_rfc2047 {
local ($_) = @_; local ($_) = @_;
my $encoding; my $charset;
s{=\?([^?]+)\?q\?(.*?)\?=}{ s{$re_encoded_word}{
$encoding = $1; $charset = $1;
my $e = $2; my $encoding = $2;
$e =~ s/_/ /g; my $text = $3;
$e =~ s/=([0-9A-F]{2})/chr(hex($1))/eg; if ($encoding eq 'q' || $encoding eq 'Q') {
$e; $text =~ s/_/ /g;
$text =~ s/=([0-9A-F]{2})/chr(hex($1))/egi;
$text;
} else {
$&; # other encodings not supported yet
}
}eg; }eg;
return wantarray ? ($_, $encoding) : $_; return wantarray ? ($_, $charset) : $_;
} }
sub quote_rfc2047 { sub quote_rfc2047 {
@ -927,10 +937,8 @@ sub quote_rfc2047 {
sub is_rfc2047_quoted { sub is_rfc2047_quoted {
my $s = shift; my $s = shift;
my $token = qr/[^][()<>@,;:"\/?.= \000-\037\177-\377]+/;
my $encoded_text = qr/[!->@-~]+/;
length($s) <= 75 && length($s) <= 75 &&
$s =~ m/^(?:"[[:ascii:]]*"|=\?$token\?$token\?$encoded_text\?=)$/o; $s =~ m/^(?:"[[:ascii:]]*"|$re_encoded_word)$/o;
} }
sub subject_needs_rfc2047_quoting { sub subject_needs_rfc2047_quoting {