X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/d0fac462fec818fd477199b6a2ef1fa9b49f58cc98c82502ff5fb5f2b0b786c3..cb11a759f179c056d587d03e5d0d0fb2199b317c6761f184a7c1a396d05b225d:/gitweb.perl diff --git a/gitweb.perl b/gitweb.perl index c8d8c75..1cfb78e 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -27,13 +27,29 @@ our $version = "++GIT_VERSION++"; our $my_url = $cgi->url(); our $my_uri = $cgi->url(-absolute => 1); -# if we're called with PATH_INFO, we have to strip that -# from the URL to find our real URL -# we make $path_info global because it's also used later on +# Base URL for relative URLs in gitweb ($logo, $favicon, ...), +# needed and used only for URLs with nonempty PATH_INFO +our $base_url = $my_url; + +# When the script is used as DirectoryIndex, the URL does not contain the name +# of the script file itself, and $cgi->url() fails to strip PATH_INFO, so we +# have to do it ourselves. We make $path_info global because it's also used +# later on. +# +# Another issue with the script being the DirectoryIndex is that the resulting +# $my_url data is not the full script URL: this is good, because we want +# generated links to keep implying the script name if it wasn't explicitly +# indicated in the URL we're handling, but it means that $my_url cannot be used +# as base URL. +# Therefore, if we needed to strip PATH_INFO, then we know that we have +# to build the base URL ourselves: our $path_info = $ENV{"PATH_INFO"}; if ($path_info) { - $my_url =~ s,\Q$path_info\E$,,; - $my_uri =~ s,\Q$path_info\E$,,; + if ($my_url =~ s,\Q$path_info\E$,, && + $my_uri =~ s,\Q$path_info\E$,, && + defined $ENV{'SCRIPT_NAME'}) { + $base_url = $cgi->url(-base => 1) . $ENV{'SCRIPT_NAME'}; + } } # core git executable to use @@ -133,6 +149,10 @@ our $fallback_encoding = 'latin1'; # - one might want to include '-B' option, e.g. '-B', '-M' our @diff_opts = ('-M'); # taken from git_commit +# Disables features that would allow repository owners to inject script into +# the gitweb domain. +our $prevent_xss = 0; + # information about snapshot formats that gitweb is capable of serving our %known_snapshot_formats = ( # name => { @@ -383,13 +403,13 @@ sub feature_bool { my $key = shift; my ($val) = git_get_project_config($key, '--bool'); - if ($val eq 'true') { + if (!defined $val) { + return ($_[0]); + } elsif ($val eq 'true') { return (1); } elsif ($val eq 'false') { return (0); } - - return ($_[0]); } sub feature_snapshot { @@ -669,10 +689,10 @@ sub evaluate_path_info { # extensions. Allowed extensions are both the defined suffix # (which includes the initial dot already) and the snapshot # format key itself, with a prepended dot - while (my ($fmt, %opt) = each %known_snapshot_formats) { + while (my ($fmt, $opt) = each %known_snapshot_formats) { my $hash = $refname; my $sfx; - $hash =~ s/(\Q$opt{'suffix'}\E|\Q.$fmt\E)$//; + $hash =~ s/(\Q$opt->{'suffix'}\E|\Q.$fmt\E)$//; next unless $sfx = $1; # a valid suffix was found, so set the snapshot format # and reset the hash parameter @@ -819,7 +839,7 @@ exit; ## ====================================================================== ## action links -sub href (%) { +sub href { my %params = @_; # default is to use -absolute url() i.e. $my_uri my $href = $params{-full} ? $my_url : $my_uri; @@ -1017,7 +1037,7 @@ sub esc_url { } # replace invalid utf8 character with SUBSTITUTION sequence -sub esc_html ($;%) { +sub esc_html { my $str = shift; my %opts = @_; @@ -1277,7 +1297,7 @@ use constant { }; # submodule/subproject, a commit object reference -sub S_ISGITLINK($) { +sub S_ISGITLINK { my $mode = shift; return (($mode & S_IFMT) == S_IFGITLINK) @@ -1365,13 +1385,11 @@ sub format_log_line_html { my $line = shift; $line = esc_html($line, -nbsp=>1); - if ($line =~ m/([0-9a-fA-F]{8,40})/) { - my $hash_text = $1; - my $link = - $cgi->a({-href => href(action=>"object", hash=>$hash_text), - -class => "text"}, $hash_text); - $line =~ s/$hash_text/$link/; - } + $line =~ s{\b([0-9a-fA-F]{8,40})\b}{ + $cgi->a({-href => href(action=>"object", hash=>$1), + -class => "text"}, $1); + }eg; + return $line; } @@ -1895,18 +1913,19 @@ sub git_parse_project_config { return %config; } -# convert config value to boolean, 'true' or 'false' +# convert config value to boolean: 'true' or 'false' # no value, number > 0, 'true' and 'yes' values are true # rest of values are treated as false (never as error) sub config_to_bool { my $val = shift; + return 1 if !defined $val; # section.key + # strip leading and trailing whitespace $val =~ s/^\s+//; $val =~ s/\s+$//; - return (!defined $val || # section.key - ($val =~ /^\d+$/ && $val) || # section.key = 1 + return (($val =~ /^\d+$/ && $val) || # section.key = 1 ($val =~ /^(?:true|yes)$/i)); # section.key = true } @@ -1959,6 +1978,9 @@ sub git_get_project_config { $config_file = "$git_dir/config"; } + # check if config variable (key) exists + return unless exists $config{"gitweb.$key"}; + # ensure given type if (!defined $type) { return $config{"gitweb.$key"}; @@ -2594,7 +2616,7 @@ sub parsed_difftree_line { } # parse line of git-ls-tree output -sub parse_ls_tree_line ($;%) { +sub parse_ls_tree_line { my $line = shift; my %opts = @_; my %res; @@ -2902,9 +2924,14 @@ sub git_header_html { $title EOF -# print out each stylesheet that exist + # the stylesheet, favicon etc urls won't work correctly with path_info + # unless we set the appropriate base URL + if ($ENV{'PATH_INFO'}) { + print "\n"; + } + # print out each stylesheet that exist, providing backwards capability + # for those people who defined $stylesheet in a config file if (defined $stylesheet) { -#provides backwards capability for those people who define style sheet in a config file print ''."\n"; } else { foreach my $stylesheet (@stylesheets) { @@ -3187,7 +3214,6 @@ sub git_print_header_div { "\n\n"; } -#sub git_print_authorship (\%) { sub git_print_authorship { my $co = shift; @@ -3243,8 +3269,7 @@ sub git_print_page_path { print "
\n"; } -# sub git_print_log (\@;%) { -sub git_print_log ($;%) { +sub git_print_log { my $log = shift; my %opts = @_; @@ -4499,7 +4524,9 @@ sub git_summary { print "\n"; - if (-s "$projectroot/$project/README.html") { + # If XSS prevention is on, we don't include README.html. + # TODO: Allow a readme in some safe format. + if (!$prevent_xss && -s "$projectroot/$project/README.html") { print "
readme
\n" . "
\n"; insert_file("$projectroot/$project/README.html"); @@ -4760,10 +4787,21 @@ sub git_blob_plain { $save_as .= '.txt'; } + # With XSS prevention on, blobs of all types except a few known safe + # ones are served with "Content-Disposition: attachment" to make sure + # they don't run in our security domain. For certain image types, + # blob view writes an tag referring to blob_plain view, and we + # want to be sure not to break that by serving the image as an + # attachment (though Firefox 3 doesn't seem to care). + my $sandbox = $prevent_xss && + $type !~ m!^(?:text/plain|image/(?:gif|png|jpeg))$!; + print $cgi->header( -type => $type, -expires => $expires, - -content_disposition => 'inline; filename="' . $save_as . '"'); + -content_disposition => + ($sandbox ? 'attachment' : 'inline') + . '; filename="' . $save_as . '"'); undef $/; binmode STDOUT, ':raw'; print <$fd>; @@ -6016,7 +6054,25 @@ sub git_feed { } if (defined($commitlist[0])) { %latest_commit = %{$commitlist[0]}; - %latest_date = parse_date($latest_commit{'author_epoch'}); + my $latest_epoch = $latest_commit{'committer_epoch'}; + %latest_date = parse_date($latest_epoch); + my $if_modified = $cgi->http('IF_MODIFIED_SINCE'); + if (defined $if_modified) { + my $since; + if (eval { require HTTP::Date; 1; }) { + $since = HTTP::Date::str2time($if_modified); + } elsif (eval { require Time::ParseDate; 1; }) { + $since = Time::ParseDate::parsedate($if_modified, GMT => 1); + } + if (defined $since && $latest_epoch <= $since) { + print $cgi->header( + -type => $content_type, + -charset => 'utf-8', + -last_modified => $latest_date{'rfc2822'}, + -status => '304 Not Modified'); + return; + } + } print $cgi->header( -type => $content_type, -charset => 'utf-8', @@ -6088,6 +6144,10 @@ XML "$alt_url\n" . "\n"; } + if (%latest_date) { + print "$latest_date{'rfc2822'}\n"; + print "$latest_date{'rfc2822'}\n"; + } print "gitweb v.$version/$git_version\n"; } elsif ($format eq 'atom') { print <