X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/951ab0fa0d1d93d476b4387c97bd85fe5a071eeeb2d6afaeaf2303b6a71b6953..b9beab12361f9882f089fd46c7c13c74151ab283f8a43c533fb184e50cea7259:/gitweb.perl diff --git a/gitweb.perl b/gitweb.perl index 7ee310e..a1138c1 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -52,8 +52,13 @@ sub evaluate_uri { # 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"}; + our $path_info = decode_utf8($ENV{"PATH_INFO"}); if ($path_info) { + # $path_info has already been URL-decoded by the web server, but + # $my_url and $my_uri have not. URL-decode them so we can properly + # strip $path_info. + $my_url = unescape($my_url); + $my_uri = unescape($my_uri); if ($my_url =~ s,\Q$path_info\E$,, && $my_uri =~ s,\Q$path_info\E$,, && defined $ENV{'SCRIPT_NAME'}) { @@ -80,11 +85,16 @@ our $project_maxdepth = "++GITWEB_PROJECT_MAXDEPTH++"; # string of the home link on top of all pages our $home_link_str = "++GITWEB_HOME_LINK_STR++"; +# extra breadcrumbs preceding the home link +our @extra_breadcrumbs = (); + # name of your site or organization to appear in page titles # replace this with something more descriptive for clearer bookmarks 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 @@ -116,6 +126,14 @@ our $projects_list = "++GITWEB_LIST++"; # the width (in characters) of the projects list "Description" column our $projects_list_description_width = 25; +# group projects by category on the projects list +# (enabled if this variable evaluates to true) +our $projects_list_group_categories = 0; + +# default category if none specified +# (leave the empty string for no category) +our $project_list_default_category = ""; + # default order of projects list # valid values are none, project, descr, owner, and age our $default_projects_order = "project"; @@ -124,6 +142,12 @@ our $default_projects_order = "project"; # (only effective if this variable evaluates to true) our $export_ok = "++GITWEB_EXPORT_OK++"; +# don't generate age column on the projects list page +our $omit_age_column = 0; + +# don't generate information about owners of repositories +our $omit_owner=0; + # show repository only if this subroutine returns true # when given the path to the project, for example: # sub { return -e "$_[0]/git-daemon-export-ok"; } @@ -250,16 +274,15 @@ our %highlight_basename = ( our %highlight_ext = ( # main extensions, defining name of syntax; # see files in /usr/share/highlight/langDefs/ directory - map { $_ => $_ } - qw(py c cpp rb java css php sh pl js tex bib xml awk bat ini spec tcl sql make), + (map { $_ => $_ } qw(py rb java css js tex bib xml awk bat ini spec tcl sql)), # alternate extensions, see /etc/highlight/filetypes.conf - 'h' => 'c', - map { $_ => 'sh' } qw(bash zsh ksh), - map { $_ => 'cpp' } qw(cxx c++ cc), - map { $_ => 'php' } qw(php3 php4 php5 phps), - map { $_ => 'pl' } qw(perl pm), # perhaps also 'cgi' - map { $_ => 'make'} qw(mak mk), - map { $_ => 'xml' } qw(xhtml html htm), + (map { $_ => 'c' } qw(c h)), + (map { $_ => 'sh' } qw(sh bash zsh ksh)), + (map { $_ => 'cpp' } qw(cpp cxx c++ cc)), + (map { $_ => 'php' } qw(php php3 php4 php5 phps)), + (map { $_ => 'pl' } qw(pl perl pm)), # perhaps also 'cgi' + (map { $_ => 'make'} qw(make mak mk)), + (map { $_ => 'xml' } qw(xml xhtml html htm)), ); # You define site-wide feature defaults here; override them with @@ -314,6 +337,10 @@ our %feature = ( # Enable text search, which will list the commits which match author, # committer or commit text to a given string. Enabled by default. # Project specific override is not supported. + # + # Note that this controls all search features, which means that if + # it is disabled, then 'grep' and 'pickaxe' search would also be + # disabled. 'search' => { 'override' => 0, 'default' => [1]}, @@ -321,6 +348,7 @@ our %feature = ( # Enable grep search, which will list the files in currently selected # tree containing the given string. Enabled by default. This can be # potentially CPU-intensive, of course. + # Note that you need to have 'search' feature enabled too. # To enable system wide have in $GITWEB_CONFIG # $feature{'grep'}{'default'} = [1]; @@ -335,6 +363,7 @@ our %feature = ( # Enable the pickaxe search, which will list the commits that modified # a given string in a file. This can be practical and quite faster # alternative to 'blame', but still potentially CPU-intensive. + # Note that you need to have 'search' feature enabled too. # To enable system wide have in $GITWEB_CONFIG # $feature{'pickaxe'}{'default'} = [1]; @@ -484,6 +513,18 @@ our %feature = ( 'override' => 0, 'default' => [0]}, + # Enable and configure ability to change common timezone for dates + # in gitweb output via JavaScript. Enabled by default. + # Project specific override is not supported. + 'javascript-timezone' => { + 'override' => 0, + 'default' => [ + 'local', # default timezone: 'utc', 'local', or '(-|+)HHMM' format, + # or undef to turn off this feature + 'gitweb_tz', # name of cookie where to store selected timezone + 'datetime', # CSS class used to mark up dates for manipulation + ]}, + # Syntax highlighting support. This is based on Daniel Svensson's # and Sham Chukoury's work in gitweb-xmms2.git. # It requires the 'highlight' program present in $PATH, @@ -503,7 +544,7 @@ our %feature = ( # $feature{'remote_heads'}{'default'} = [1]; # To have project specific config enable override in $GITWEB_CONFIG # $feature{'remote_heads'}{'override'} = 1; - # and in project config gitweb.remote_heads = 0|1; + # and in project config gitweb.remoteheads = 0|1; 'remote_heads' => { 'sub' => sub { feature_bool('remote_heads', @_) }, 'override' => 0, @@ -624,18 +665,42 @@ sub filter_snapshot_fmts { # if it is true then gitweb config would be run for each request. our $per_request_config = 1; -our ($GITWEB_CONFIG, $GITWEB_CONFIG_SYSTEM); -sub evaluate_gitweb_config { - our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; - our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++"; +# read and parse gitweb config file given by its parameter. +# returns true on success, false on recoverable error, allowing +# to chain this subroutine, using first file that exists. +# dies on errors during parsing config file, as it is unrecoverable. +sub read_config_file { + my $filename = shift; + return unless defined $filename; # die if there are errors parsing config file - if (-e $GITWEB_CONFIG) { - do $GITWEB_CONFIG; - die $@ if $@; - } elsif (-e $GITWEB_CONFIG_SYSTEM) { - do $GITWEB_CONFIG_SYSTEM; + if (-e $filename) { + do $filename; die $@ if $@; + return 1; } + return; +} + +our ($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++"; + + # Protect against 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); } # Get loadavg of system, to compare against $maxload. @@ -708,6 +773,8 @@ our @cgi_param_mapping = ( extra_options => "opt", search_use_regexp => "sr", ctag => "by_tag", + diff_style => "ds", + project_filter => "pf", # this must be last entry (for manipulation from JavaScript) javascript => "js" ); @@ -764,9 +831,9 @@ sub evaluate_query_params { while (my ($name, $symbol) = each %cgi_param_mapping) { if ($symbol eq 'opt') { - $input_params{$name} = [ $cgi->param($symbol) ]; + $input_params{$name} = [ map { decode_utf8($_) } $cgi->param($symbol) ]; } else { - $input_params{$name} = $cgi->param($symbol); + $input_params{$name} = decode_utf8($cgi->param($symbol)); } } } @@ -924,7 +991,7 @@ sub evaluate_path_info { our ($action, $project, $file_name, $file_parent, $hash, $hash_parent, $hash_base, $hash_parent_base, @extra_options, $page, $searchtype, $search_use_regexp, - $searchtext, $search_regexp); + $searchtext, $search_regexp, $project_filter); sub evaluate_and_validate_params { our $action = $input_params{'action'}; if (defined $action) { @@ -942,6 +1009,13 @@ sub evaluate_and_validate_params { } } + our $project_filter = $input_params{'project_filter'}; + if (defined $project_filter) { + if (!validate_pathname($project_filter)) { + die_error(404, "Invalid project_filter parameter"); + } + } + our $file_name = $input_params{'file_name'}; if (defined $file_name) { if (!validate_pathname($file_name)) { @@ -1016,12 +1090,21 @@ sub evaluate_and_validate_params { our $search_use_regexp = $input_params{'search_use_regexp'}; our $searchtext = $input_params{'searchtext'}; - our $search_regexp; + our $search_regexp = undef; if (defined $searchtext) { if (length($searchtext) < 2) { die_error(403, "At least two characters are required for search parameter"); } - $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext; + if ($search_use_regexp) { + $search_regexp = $searchtext; + if (!eval { qr/$search_regexp/; 1; }) { + (my $error = $@) =~ s/ at \S+ line \d+.*\n?//; + die_error(400, "Invalid search regexp '$search_regexp'", + esc_html($error)); + } + } else { + $search_regexp = quotemeta $searchtext; + } } } @@ -1057,7 +1140,7 @@ sub handle_errors_html { # to avoid infinite loop where error occurs in die_error, # change handler to default handler, disabling handle_errors_html - set_message("Error occured when inside die_error:\n$msg"); + set_message("Error occurred when inside die_error:\n$msg"); # you cannot jump out of die_error when called as error handler; # the subroutine set via CGI::Carp::set_message is called _after_ @@ -1071,8 +1154,10 @@ sub dispatch { if (!defined $action) { if (defined $hash) { $action = git_get_type($hash); + $action or die_error(404, "Object does not exist"); } elsif (defined $hash_base && defined $file_name) { $action = git_get_type("$hash_base:$file_name"); + $action or die_error(404, "File or directory does not exist"); } elsif (defined $project) { $action = 'summary'; } else { @@ -1391,8 +1476,8 @@ sub validate_refname { sub to_utf8 { my $str = shift; return undef unless defined $str; - if (utf8::valid($str)) { - utf8::decode($str); + + if (utf8::is_utf8($str) || utf8::decode($str)) { return $str; } else { return decode($fallback_encoding, $str, Encode::FB_DEFAULT); @@ -1468,6 +1553,17 @@ 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:]])|(index("\t\n\r", $1) != -1 ? $1 : quot_cec($1))|eg; + return $str; +} + # Make control characters "printable", using character escape codes (CEC) sub quot_cec { my $cntrl = shift; @@ -1633,6 +1729,7 @@ sub chop_and_escape_str { my ($str) = @_; my $chopped = chop_str(@_); + $str = to_utf8($str); if ($chopped eq $str) { return esc_html($chopped); } else { @@ -1641,6 +1738,97 @@ sub chop_and_escape_str { } } +# Highlight selected fragments of string, using given CSS class, +# and escape HTML. It is assumed that fragments do not overlap. +# Regions are passed as list of pairs (array references). +# +# Example: esc_html_hl_regions("foobar", "mark", [ 0, 3 ]) returns +# 'foobar' +sub esc_html_hl_regions { + my ($str, $css_class, @sel) = @_; + my %opts = grep { ref($_) ne 'ARRAY' } @sel; + @sel = grep { ref($_) eq 'ARRAY' } @sel; + return esc_html($str, %opts) unless @sel; + + my $out = ''; + my $pos = 0; + + for my $s (@sel) { + my ($begin, $end) = @$s; + + # Don't create empty elements. + next if $end <= $begin; + + my $escaped = esc_html(substr($str, $begin, $end - $begin), + %opts); + + $out .= esc_html(substr($str, $pos, $begin - $pos), %opts) + if ($begin - $pos > 0); + $out .= $cgi->span({-class => $css_class}, $escaped); + + $pos = $end; + } + $out .= esc_html(substr($str, $pos), %opts) + if ($pos < length($str)); + + return $out; +} + +# return positions of beginning and end of each match +sub matchpos_list { + my ($str, $regexp) = @_; + return unless (defined $str && defined $regexp); + + my @matches; + while ($str =~ /$regexp/g) { + push @matches, [$-[0], $+[0]]; + } + return @matches; +} + +# highlight match (if any), and escape HTML +sub esc_html_match_hl { + my ($str, $regexp) = @_; + return esc_html($str) unless defined $regexp; + + my @matches = matchpos_list($str, $regexp); + return esc_html($str) unless @matches; + + return esc_html_hl_regions($str, 'match', @matches); +} + + +# highlight match (if any) of shortened string, and escape HTML +sub esc_html_match_hl_chopped { + my ($str, $chopped, $regexp) = @_; + return esc_html_match_hl($str, $regexp) unless defined $chopped; + + my @matches = matchpos_list($str, $regexp); + return esc_html($chopped) unless @matches; + + # filter matches so that we mark chopped string + my $tail = "... "; # see chop_str + unless ($chopped =~ s/\Q$tail\E$//) { + $tail = ''; + } + my $chop_len = length($chopped); + my $tail_len = length($tail); + my @filtered; + + for my $m (@matches) { + if ($m->[0] > $chop_len) { + push @filtered, [ $chop_len, $chop_len + $tail_len ] if ($tail_len > 0); + last; + } elsif ($m->[1] > $chop_len) { + push @filtered, [ $m->[0], $chop_len + $tail_len ]; + last; + } + push @filtered, $m; + } + + return esc_html_hl_regions($chopped . $tail, 'match', @filtered); +} + ## ---------------------------------------------------------------------- ## functions returning short strings @@ -1884,7 +2072,7 @@ sub picon_url { if (!$avatar_cache{$email}) { my ($user, $domain) = split('@', $email); $avatar_cache{$email} = - "http://www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . + "//www.cs.indiana.edu/cgi-pub/kinzler/piconsearch.cgi/" . "$domain/$user/" . "users+domains+unknown/up/single"; } @@ -1899,7 +2087,7 @@ sub gravatar_url { my $email = lc shift; my $size = shift; $avatar_cache{$email} ||= - "http://www.gravatar.com/avatar/" . + "//www.gravatar.com/avatar/" . Digest::MD5::md5_hex($email) . "?s="; return $avatar_cache{$email} . $size; } @@ -2163,93 +2351,125 @@ sub format_diff_cc_simplified { return $result; } -# 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 $line; +sub diff_line_class { + my ($line, $from, $to) = @_; + # ordinary diff + my $num_sign = 1; + # combined diff if ($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"; - } - } - $line = untabify($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; + $num_sign = scalar @{$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 =~ $clsfy->{'regexp'}); + } - if ($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 "