X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/5a2e5c94a72bced582800308a3a24442a6cb93da9fe0bf0d59b2142b4aebd0b1..7028df23897649c2a5a51b69ef58f4e53e330aa179a95227d5f809c88688f427:/gitweb.perl diff --git a/gitweb.perl b/gitweb.perl index 8c8c293..dcef80a 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -85,6 +85,8 @@ our $home_link_str = "++GITWEB_HOME_LINK_STR++"; our $site_name = "++GITWEB_SITENAME++" || ($ENV{'SERVER_NAME'} || "Untitled") . " Git"; +# html snippet to include in the section of each page +our $site_html_head_string = "++GITWEB_SITE_HTML_HEAD_STRING++"; # filename of html text to include at top of each page our $site_header = "++GITWEB_SITE_HEADER++"; # html text to include at home page @@ -666,13 +668,25 @@ sub read_config_file { return; } -our ($GITWEB_CONFIG, $GITWEB_CONFIG_SYSTEM); +our ($GITWEB_CONFIG, $GITWEB_CONFIG_SYSTEM, $GITWEB_CONFIG_COMMON); sub evaluate_gitweb_config { our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++"; + our $GITWEB_CONFIG_COMMON = $ENV{'GITWEB_CONFIG_COMMON'} || "++GITWEB_CONFIG_COMMON++"; - # use first config file that exists - read_config_file($GITWEB_CONFIG) or + # Protect agains duplications of file names, to not read config twice. + # Only one of $GITWEB_CONFIG and $GITWEB_CONFIG_SYSTEM is used, so + # there possibility of duplication of filename there doesn't matter. + $GITWEB_CONFIG = "" if ($GITWEB_CONFIG eq $GITWEB_CONFIG_COMMON); + $GITWEB_CONFIG_SYSTEM = "" if ($GITWEB_CONFIG_SYSTEM eq $GITWEB_CONFIG_COMMON); + + # Common system-wide settings for convenience. + # Those settings can be ovverriden by GITWEB_CONFIG or GITWEB_CONFIG_SYSTEM. + read_config_file($GITWEB_CONFIG_COMMON); + + # Use first config file that exists. This means use the per-instance + # GITWEB_CONFIG if exists, otherwise use GITWEB_SYSTEM_CONFIG. + read_config_file($GITWEB_CONFIG) and return; read_config_file($GITWEB_CONFIG_SYSTEM); } @@ -1506,6 +1520,17 @@ sub esc_path { return $str; } +# Sanitize for use in XHTML + application/xml+xhtm (valid XML 1.0) +sub sanitize { + my $str = shift; + + return undef unless defined $str; + + $str = to_utf8($str); + $str =~ s|([[:cntrl:]])|($1 =~ /[\t\n\r]/ ? $1 : quot_cec($1))|eg; + return $str; +} + # Make control characters "printable", using character escape codes (CEC) sub quot_cec { my $cntrl = shift; @@ -2201,93 +2226,120 @@ sub format_diff_cc_simplified { return $result; } +sub diff_line_class { + my ($line, $from, $to) = @_; + + # ordinary diff + my $num_sign = 1; + # combined diff + if ($from && $to && ref($from->{'href'}) eq "ARRAY") { + $num_sign = scalar @{$from->{'href'}}; + } + + my @diff_line_classifier = ( + { regexp => qr/^\@\@{$num_sign} /, class => "chunk_header"}, + { regexp => qr/^\\/, class => "incomplete" }, + { regexp => qr/^ {$num_sign}/, class => "ctx" }, + # classifier for context must come before classifier add/rem, + # or we would have to use more complicated regexp, for example + # qr/(?= {0,$m}\+)[+ ]{$num_sign}/, where $m = $num_sign - 1; + { regexp => qr/^[+ ]{$num_sign}/, class => "add" }, + { regexp => qr/^[- ]{$num_sign}/, class => "rem" }, + ); + for my $clsfy (@diff_line_classifier) { + return $clsfy->{'class'} + if ($line =~ $clsfy->{'regexp'}); + } + + # fallback + return ""; +} + +# assumes that $from and $to are defined and correctly filled, +# and that $line holds a line of chunk header for unified diff +sub format_unidiff_chunk_header { + my ($line, $from, $to) = @_; + + my ($from_text, $from_start, $from_lines, $to_text, $to_start, $to_lines, $section) = + $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; + + $from_lines = 0 unless defined $from_lines; + $to_lines = 0 unless defined $to_lines; + + if ($from->{'href'}) { + $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", + -class=>"list"}, $from_text); + } + if ($to->{'href'}) { + $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } + $line = "@@ $from_text $to_text @@" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + +# assumes that $from and $to are defined and correctly filled, +# and that $line holds a line of chunk header for combined diff +sub format_cc_diff_chunk_header { + my ($line, $from, $to) = @_; + + my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; + my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + + @from_text = split(' ', $ranges); + for (my $i = 0; $i < @from_text; ++$i) { + ($from_start[$i], $from_nlines[$i]) = + (split(',', substr($from_text[$i], 1)), 0); + } + + $to_text = pop @from_text; + $to_start = pop @from_start; + $to_nlines = pop @from_nlines; + + $line = "$prefix "; + for (my $i = 0; $i < @from_text; ++$i) { + if ($from->{'href'}[$i]) { + $line .= $cgi->a({-href=>"$from->{'href'}[$i]#l$from_start[$i]", + -class=>"list"}, $from_text[$i]); + } else { + $line .= $from_text[$i]; + } + $line .= " "; + } + if ($to->{'href'}) { + $line .= $cgi->a({-href=>"$to->{'href'}#l$to_start", + -class=>"list"}, $to_text); + } else { + $line .= $to_text; + } + $line .= " $prefix" . + "" . esc_html($section, -nbsp=>1) . ""; + return $line; +} + # format patch (diff) line (not to be used for diff headers) sub format_diff_line { my $line = shift; my ($from, $to) = @_; - my $diff_class = ""; - chomp $line; + my $diff_class = diff_line_class($line, $from, $to); + my $diff_classes = "diff"; + $diff_classes .= " $diff_class" if ($diff_class); - if ($from && $to && ref($from->{'href'}) eq "ARRAY") { - # combined diff - my $prefix = substr($line, 0, scalar @{$from->{'href'}}); - if ($line =~ m/^\@{3}/) { - $diff_class = " chunk_header"; - } elsif ($line =~ m/^\\/) { - $diff_class = " incomplete"; - } elsif ($prefix =~ tr/+/+/) { - $diff_class = " add"; - } elsif ($prefix =~ tr/-/-/) { - $diff_class = " rem"; - } - } else { - # assume ordinary diff - my $char = substr($line, 0, 1); - if ($char eq '+') { - $diff_class = " add"; - } elsif ($char eq '-') { - $diff_class = " rem"; - } elsif ($char eq '@') { - $diff_class = " chunk_header"; - } elsif ($char eq "\\") { - $diff_class = " incomplete"; - } - } + chomp $line; $line = untabify($line); - if ($from && $to && $line =~ m/^\@{2} /) { - my ($from_text, $from_start, $from_lines, $to_text, $to_start, $to_lines, $section) = - $line =~ m/^\@{2} (-(\d+)(?:,(\d+))?) (\+(\d+)(?:,(\d+))?) \@{2}(.*)$/; - $from_lines = 0 unless defined $from_lines; - $to_lines = 0 unless defined $to_lines; + if ($from && $to && $line =~ m/^\@{2} /) { + $line = format_unidiff_chunk_header($line, $from, $to); + return "
$line
\n"; - if ($from->{'href'}) { - $from_text = $cgi->a({-href=>"$from->{'href'}#l$from_start", - -class=>"list"}, $from_text); - } - if ($to->{'href'}) { - $to_text = $cgi->a({-href=>"$to->{'href'}#l$to_start", - -class=>"list"}, $to_text); - } - $line = "@@ $from_text $to_text @@" . - "" . esc_html($section, -nbsp=>1) . ""; - return "
$line
\n"; } elsif ($from && $to && $line =~ m/^\@{3}/) { - my ($prefix, $ranges, $section) = $line =~ m/^(\@+) (.*?) \@+(.*)$/; - my (@from_text, @from_start, @from_nlines, $to_text, $to_start, $to_nlines); + $line = format_cc_diff_chunk_header($line, $from, $to); + return "
$line
\n"; - @from_text = split(' ', $ranges); - for (my $i = 0; $i < @from_text; ++$i) { - ($from_start[$i], $from_nlines[$i]) = - (split(',', substr($from_text[$i], 1)), 0); - } - - $to_text = pop @from_text; - $to_start = pop @from_start; - $to_nlines = pop @from_nlines; - - $line = "$prefix "; - for (my $i = 0; $i < @from_text; ++$i) { - if ($from->{'href'}[$i]) { - $line .= $cgi->a({-href=>"$from->{'href'}[$i]#l$from_start[$i]", - -class=>"list"}, $from_text[$i]); - } else { - $line .= $from_text[$i]; - } - $line .= " "; - } - if ($to->{'href'}) { - $line .= $cgi->a({-href=>"$to->{'href'}#l$to_start", - -class=>"list"}, $to_text); - } else { - $line .= $to_text; - } - $line .= " $prefix" . - "" . esc_html($section, -nbsp=>1) . ""; - return "
$line
\n"; } - return "
" . esc_html($line, -nbsp=>1) . "
\n"; + return "
" . esc_html($line, -nbsp=>1) . "
\n"; } # Generates undef or something like "_snapshot_" or "snapshot (_tbz2_ _zip_)", @@ -2515,6 +2567,13 @@ sub git_get_project_config { # key sanity check return unless ($key); + # only subsection, if exists, is case sensitive, + # and not lowercased by 'git config -z -l' + if (my ($hi, $mi, $lo) = ($key =~ /^([^.]*)\.(.*)\.([^.]*)$/)) { + $key = join(".", lc($hi), $mi, lc($lo)); + } else { + $key = lc($key); + } $key =~ s/^gitweb\.//; return if ($key =~ m/\W/); @@ -2857,7 +2916,7 @@ sub filter_forks_from_projects_list { $path =~ s/\.git$//; # forks of 'repo.git' are in 'repo/' directory next if ($path =~ m!/$!); # skip non-bare repositories, e.g. 'repo/.git' next unless ($path); # skip '.git' repository: tests, git-instaweb - next unless (-d $path); # containing directory exists + next unless (-d "$projectroot/$path"); # containing directory exists $pr->{'forks'} = []; # there can be 0 or more forks of project # add to trie @@ -3850,6 +3909,11 @@ EOF print "\n"; } print_header_links($status); + + if (defined $site_html_head_string) { + print to_utf8($site_html_head_string); + } + print "\n" . "\n"; @@ -6359,7 +6423,16 @@ sub git_blob_plain { # 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 && - $type !~ m!^(?:text/plain|image/(?:gif|png|jpeg))(?:[ ;]|$)!; + $type !~ m!^(?:text/[a-z]+|image/(?:gif|png|jpeg))(?:[ ;]|$)!; + + # serve text/* as text/plain + if ($prevent_xss && + ($type =~ m!^text/[a-z]+\b(.*)$! || + ($type =~ m!^[a-z]+/[a-z]\+xml\b(.*)$! && -T $fd))) { + my $rest = $1; + $rest = defined $rest ? $rest : ''; + $type = "text/plain$rest"; + } print $cgi->header( -type => $type, @@ -6457,7 +6530,8 @@ sub git_blob { $nr++; $line = untabify($line); printf qq!
%4i %s
\n!, - $nr, href(-replay => 1), $nr, $nr, $syntax ? $line : esc_html($line, -nbsp=>1); + $nr, esc_attr(href(-replay => 1)), $nr, $nr, + $syntax ? sanitize($line) : esc_html($line, -nbsp=>1); } } close $fd