diff options
author | Jakub Narębski <jnareb@gmail.com> | 2014-05-27 16:22:42 +0200 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2014-05-27 15:11:49 -0700 |
commit | d49c08256b41e27879454a1f872bcfb80877acad (patch) | |
tree | 0b033ddcdd794dc3a8b3d6dbb58e1ce019234a93 | |
parent | eea591373e139fc8aab89a78ccb0b1512a2bf0de (diff) | |
download | git-jn/gitweb-utf8-in-links.tar.gz |
gitweb: Harden UTF-8 handling in generated linksjn/gitweb-utf8-in-links
esc_html() ensures that its input is properly UTF-8 encoded and marked
as UTF-8 with to_utf8(). Make esc_param() (used for query parameters
in generated URLs), esc_path_info() (for escaping path_info
components) and esc_url() use it too.
This hardens gitweb against errors in UTF-8 handling; because
to_utf8() is idempotent it won't change correct output.
Reported-by: Michael Wagner <accounts@mwagner.org>
Signed-off-by: Jakub Narębski <jnareb@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
-rwxr-xr-x | gitweb/gitweb.perl | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 52108b9255..006cd80c3e 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -1548,8 +1548,11 @@ sub to_utf8 { sub esc_param { my $str = shift; return undef unless defined $str; + + $str = to_utf8($str); $str =~ s/([^A-Za-z0-9\-_.~()\/:@ ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; + return $str; } @@ -1558,6 +1561,7 @@ sub esc_path_info { my $str = shift; return undef unless defined $str; + $str = to_utf8($str); # path_info doesn't treat '+' as space (specially), but '?' must be escaped $str =~ s/([^A-Za-z0-9\-_.~();\/;:@&= +]+)/CGI::escape($1)/eg; @@ -1568,8 +1572,11 @@ sub esc_path_info { sub esc_url { my $str = shift; return undef unless defined $str; + + $str = to_utf8($str); $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&= ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; + return $str; } |