From b622d4d11d27fd290f7732c6a65f40c054796c1f Mon Sep 17 00:00:00 2001 From: Thomas Rast Date: Mon, 30 Jul 2012 21:25:40 +0200 Subject: send-email: improve RFC2047 quote parsing The RFC2047 unquoting, used to parse email addresses in From and Cc headers, is broken in several ways: * It erroneously substitutes ' ' for '_' in *the whole* header, even outside the quoted field. [Noticed by Christoph.] * It is too liberal in its matching, and happily matches the start of one quoted chunk against the end of another, or even just something that looks like such an end. [Noticed by Junio.] * It fundamentally cannot cope with encodings that are not a superset of ASCII, nor several (incompatible) encodings in the same header. This patch fixes the first two by doing a more careful decoding of the outer quoting (e.g. "=AB" to represent an octet whose value is 0xAB). Fixing the fundamental issues is left for a future, more intrusive, patch. Noticed-by: Christoph Miebach Helped-by: Junio C Hamano Signed-off-by: Thomas Rast Signed-off-by: Junio C Hamano --- git-send-email.perl | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'git-send-email.perl') diff --git a/git-send-email.perl b/git-send-email.perl index ef30c557c7..664713709c 100755 --- a/git-send-email.perl +++ b/git-send-email.perl @@ -862,11 +862,13 @@ $time = time - scalar $#files; sub unquote_rfc2047 { local ($_) = @_; my $encoding; - if (s/=\?([^?]+)\?q\?(.*)\?=/$2/g) { + s{=\?([^?]+)\?q\?(.*?)\?=}{ $encoding = $1; - s/_/ /g; - s/=([0-9A-F]{2})/chr(hex($1))/eg; - } + my $e = $2; + $e =~ s/_/ /g; + $e =~ s/=([0-9A-F]{2})/chr(hex($1))/eg; + $e; + }eg; return wantarray ? ($_, $encoding) : $_; } -- cgit v1.2.3