X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/8ce125f5d6b5de3bad1a30b2217d0ef60bef4b4b61f72ddc0332b84efcbe16d2..380041003dbbb664fea83ed8a63c2f073e4f01dda3e512f26115a01b09db26aa:/gitweb.perl diff --git a/gitweb.perl b/gitweb.perl index 1f1842a..ccb06cd 100755 --- a/gitweb.perl +++ b/gitweb.perl @@ -7,6 +7,7 @@ # # This program is licensed under the GPLv2 +use 5.008; use strict; use warnings; use CGI qw(:standard :escapeHTML -nosticky); @@ -16,12 +17,10 @@ use Encode; use Fcntl ':mode'; use File::Find qw(); use File::Basename qw(basename); +use Time::HiRes qw(gettimeofday tv_interval); binmode STDOUT, ':utf8'; -our $t0; -if (eval { require Time::HiRes; 1; }) { - $t0 = [Time::HiRes::gettimeofday()]; -} +our $t0 = [ gettimeofday() ]; our $number_of_git_cmds = 0; BEGIN { @@ -166,6 +165,12 @@ our @diff_opts = ('-M'); # taken from git_commit # the gitweb domain. our $prevent_xss = 0; +# Path to the highlight executable to use (must be the one from +# http://www.andre-simon.de due to assumptions about parameters and output). +# Useful if highlight is not installed on your webserver's PATH. +# [Default: highlight] +our $highlight_bin = "++HIGHLIGHT_BIN++"; + # information about snapshot formats that gitweb is capable of serving our %known_snapshot_formats = ( # name => { @@ -233,6 +238,30 @@ our %avatar_size = ( # Leave it undefined (or set to 'undef') to turn off load checking. our $maxload = 300; +# configuration for 'highlight' (http://www.andre-simon.de/) +# match by basename +our %highlight_basename = ( + #'Program' => 'py', + #'Library' => 'py', + 'SConstruct' => 'py', # SCons equivalent of Makefile + 'Makefile' => 'make', +); +# match by extension +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), + # 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), +); + # You define site-wide feature defaults here; override them with # $GITWEB_CONFIG as necessary. our %feature = ( @@ -246,7 +275,7 @@ our %feature = ( # return value of feature-sub indicates if to enable specified feature # # if there is no 'sub' key (no feature-sub), then feature cannot be - # overriden + # overridden # # use gitweb_get_feature() to retrieve the value # (an array) or gitweb_check_feature() to check if @@ -464,6 +493,18 @@ our %feature = ( 'sub' => sub { feature_bool('highlight', @_) }, 'override' => 0, 'default' => [0]}, + + # Enable displaying of remote heads in the heads list + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'remote_heads'}{'default'} = [1]; + # To have project specific config enable override in $GITWEB_CONFIG + # $feature{'remote_heads'}{'override'} = 1; + # and in project config gitweb.remote_heads = 0|1; + 'remote_heads' => { + 'sub' => sub { feature_bool('remote_heads', @_) }, + 'override' => 0, + 'default' => [0]}, ); sub gitweb_get_feature { @@ -572,6 +613,14 @@ sub filter_snapshot_fmts { !$known_snapshot_formats{$_}{'disabled'}} @fmts; } +# If it is set to code reference, it is code that it is to be run once per +# request, allowing updating configurations that change with each request, +# while running other code in config file only once. +# +# Otherwise, if it is false then gitweb would process config file only once; +# 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 = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; @@ -678,6 +727,7 @@ our %actions = ( "log" => \&git_log, "patch" => \&git_patch, "patches" => \&git_patches, + "remotes" => \&git_remotes, "rss" => \&git_rss, "atom" => \&git_atom, "search" => \&git_search, @@ -752,10 +802,10 @@ sub evaluate_path_info { 'history', ); - # we want to catch + # we want to catch, among others # [$hash_parent_base[:$file_parent]..]$hash_parent[:$file_name] my ($parentrefname, $parentpathname, $refname, $pathname) = - ($path_info =~ /^(?:(.+?)(?::(.+))?\.\.)?(.+?)(?::(.+))?$/); + ($path_info =~ /^(?:(.+?)(?::(.+))?\.\.)?([^:]+?)?(?::(.+))?$/); # first, analyze the 'current' part if (defined $pathname) { @@ -791,8 +841,15 @@ sub evaluate_path_info { # hash_base instead. It should also be noted that hand-crafted # links having 'history' as an action and no pathname or hash # set will fail, but that happens regardless of PATH_INFO. - $input_params{'action'} ||= "shortlog"; - if (grep { $_ eq $input_params{'action'} } @wants_base) { + if (defined $parentrefname) { + # if there is parent let the default be 'shortlog' action + # (for http://git.example.com/repo.git/A..B links); if there + # is no parent, dispatch will detect type of object and set + # action appropriately if required (if action is not set) + $input_params{'action'} ||= "shortlog"; + } + if ($input_params{'action'} && + grep { $_ eq $input_params{'action'} } @wants_base) { $input_params{'hash_base'} ||= $refname; } else { $input_params{'hash'} ||= $refname; @@ -1028,13 +1085,28 @@ sub dispatch { $actions{$action}->(); } -sub run_request { - our $t0 = [Time::HiRes::gettimeofday()] +sub reset_timer { + our $t0 = [ gettimeofday() ] if defined $t0; + our $number_of_git_cmds = 0; +} + +our $first_request = 1; +sub run_request { + reset_timer(); evaluate_uri(); - evaluate_gitweb_config(); - evaluate_git_version(); + if ($first_request) { + evaluate_gitweb_config(); + evaluate_git_version(); + } + if ($per_request_config) { + if (ref($per_request_config) eq 'CODE') { + $per_request_config->(); + } elsif (!$first_request) { + evaluate_gitweb_config(); + } + } check_loadavg(); # $projectroot and $projects_list might be set in gitweb config file @@ -1054,19 +1126,24 @@ our $is_last_request = sub { 1 }; our ($pre_dispatch_hook, $post_dispatch_hook, $pre_listen_hook); our $CGI = 'CGI'; our $cgi; +sub configure_as_fcgi { + require CGI::Fast; + our $CGI = 'CGI::Fast'; + + my $request_number = 0; + # let each child service 100 requests + our $is_last_request = sub { ++$request_number > 100 }; +} sub evaluate_argv { + my $script_name = $ENV{'SCRIPT_NAME'} || $ENV{'SCRIPT_FILENAME'} || __FILE__; + configure_as_fcgi() + if $script_name =~ /\.fcgi$/; + return unless (@ARGV); require Getopt::Long; Getopt::Long::GetOptions( - 'fastcgi|fcgi|f' => sub { - require CGI::Fast; - our $CGI = 'CGI::Fast'; - - my $request_number = 0; - # let each child service 100 requests - our $is_last_request = sub { ++$request_number > 100 }; - }, + 'fastcgi|fcgi|f' => \&configure_as_fcgi, 'nproc|n=i' => sub { my ($arg, $val) = @_; return unless eval { require FCGI::ProcManager; 1; }; @@ -1083,6 +1160,7 @@ sub evaluate_argv { sub run { evaluate_argv(); + $first_request = 1; $pre_listen_hook->() if $pre_listen_hook; @@ -1093,8 +1171,9 @@ sub run { run_request(); - $pre_dispatch_hook->() + $post_dispatch_hook->() if $post_dispatch_hook; + $first_request = 0; last REQUEST if ($is_last_request->()); } @@ -1105,6 +1184,15 @@ sub run { run(); +if (defined caller) { + # wrapped in a subroutine processing requests, + # e.g. mod_perl with ModPerl::Registry, or PSGI with Plack::App::WrapCGI + return; +} else { + # pure CGI script, serving single request + exit; +} + ## ====================================================================== ## action links @@ -1144,7 +1232,7 @@ sub href { $href =~ s,/$,,; # Then add the project name, if present - $href .= "/".esc_url($params{'project'}); + $href .= "/".esc_path_info($params{'project'}); delete $params{'project'}; # since we destructively absorb parameters, we keep this @@ -1154,7 +1242,8 @@ sub href { # Summary just uses the project path URL, any other action is # added to the URL if (defined $params{'action'}) { - $href .= "/".esc_url($params{'action'}) unless $params{'action'} eq 'summary'; + $href .= "/".esc_path_info($params{'action'}) + unless $params{'action'} eq 'summary'; delete $params{'action'}; } @@ -1164,13 +1253,13 @@ sub href { || $params{'hash_parent'} || $params{'hash'}); if (defined $params{'hash_base'}) { if (defined $params{'hash_parent_base'}) { - $href .= esc_url($params{'hash_parent_base'}); + $href .= esc_path_info($params{'hash_parent_base'}); # skip the file_parent if it's the same as the file_name if (defined $params{'file_parent'}) { if (defined $params{'file_name'} && $params{'file_parent'} eq $params{'file_name'}) { delete $params{'file_parent'}; } elsif ($params{'file_parent'} !~ /\.\./) { - $href .= ":/".esc_url($params{'file_parent'}); + $href .= ":/".esc_path_info($params{'file_parent'}); delete $params{'file_parent'}; } } @@ -1178,19 +1267,19 @@ sub href { delete $params{'hash_parent'}; delete $params{'hash_parent_base'}; } elsif (defined $params{'hash_parent'}) { - $href .= esc_url($params{'hash_parent'}). ".."; + $href .= esc_path_info($params{'hash_parent'}). ".."; delete $params{'hash_parent'}; } - $href .= esc_url($params{'hash_base'}); + $href .= esc_path_info($params{'hash_base'}); if (defined $params{'file_name'} && $params{'file_name'} !~ /\.\./) { - $href .= ":/".esc_url($params{'file_name'}); + $href .= ":/".esc_path_info($params{'file_name'}); delete $params{'file_name'}; } delete $params{'hash'}; delete $params{'hash_base'}; } elsif (defined $params{'hash'}) { - $href .= esc_url($params{'hash'}); + $href .= esc_path_info($params{'hash'}); delete $params{'hash'}; } @@ -1223,6 +1312,9 @@ sub href { } $href .= "?" . join(';', @result) if scalar @result; + # final transformation: trailing spaces must be escaped (URI-encoded) + $href =~ s/(\s+)$/CGI::escape($1)/e; + return $href; } @@ -1305,16 +1397,33 @@ sub esc_param { return $str; } -# quote unsafe chars in whole URL, so some charactrs cannot be quoted +# the quoting rules for path_info fragment are slightly different +sub esc_path_info { + my $str = shift; + return undef unless defined $str; + + # path_info doesn't treat '+' as space (specially), but '?' must be escaped + $str =~ s/([^A-Za-z0-9\-_.~();\/;:@&= +]+)/CGI::escape($1)/eg; + + return $str; +} + +# quote unsafe chars in whole URL, so some characters cannot be quoted sub esc_url { my $str = shift; return undef unless defined $str; - $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&=])/sprintf("%%%02X", ord($1))/eg; - $str =~ s/\+/%2B/g; + $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&= ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; return $str; } +# quote unsafe characters in HTML attributes +sub esc_attr { + + # for XHTML conformance escaping '"' to '"' is not enough + return esc_html(@_); +} + # replace invalid utf8 character with SUBSTITUTION sequence sub esc_html { my $str = shift; @@ -1720,7 +1829,7 @@ sub format_ref_marker { hash=>$dest )}, $name); - $markers .= " " . + $markers .= " " . $link . ""; } } @@ -1804,7 +1913,7 @@ sub git_get_avatar { return $pre_white . "" . $post_white; } else { @@ -2515,7 +2624,7 @@ sub git_show_project_tagcloud { } else { my @tags = sort { $cloud->{$a}->{count} <=> $cloud->{$b}->{count} } keys %$cloud; return '

' . join (', ', map { - "$cloud->{$_}->{topname}" + $cgi->a({-href=>"$home_link?by_tag=$_"}, $cloud->{$_}->{topname}) } splice(@tags, 0, $count)) . '

'; } } @@ -2705,6 +2814,44 @@ sub git_get_last_activity { return (undef, undef); } +# Implementation note: when a single remote is wanted, we cannot use 'git +# remote show -n' because that command always work (assuming it's a remote URL +# if it's not defined), and we cannot use 'git remote show' because that would +# try to make a network roundtrip. So the only way to find if that particular +# remote is defined is to walk the list provided by 'git remote -v' and stop if +# and when we find what we want. +sub git_get_remotes_list { + my $wanted = shift; + my %remotes = (); + + open my $fd, '-|' , git_cmd(), 'remote', '-v'; + return unless $fd; + while (my $remote = <$fd>) { + chomp $remote; + $remote =~ s!\t(.*?)\s+\((\w+)\)$!!; + next if $wanted and not $remote eq $wanted; + my ($url, $key) = ($1, $2); + + $remotes{$remote} ||= { 'heads' => () }; + $remotes{$remote}{$key} = $url; + } + close $fd or return; + return wantarray ? %remotes : \%remotes; +} + +# Takes a hash of remotes as first parameter and fills it by adding the +# available remote heads for each of the indicated remotes. +sub fill_remote_heads { + my $remotes = shift; + my @heads = map { "remotes/$_" } keys %$remotes; + my @remoteheads = git_get_heads_list(undef, @heads); + foreach my $remote (keys %$remotes) { + $remotes->{$remote}{'heads'} = [ grep { + $_->{'name'} =~ s!^$remote/!! + } @remoteheads ]; + } +} + sub git_get_references { my $type = shift || ""; my %refs; @@ -3103,13 +3250,15 @@ sub parse_from_to_diffinfo { ## parse to array of hashes functions sub git_get_heads_list { - my $limit = shift; + my ($limit, @classes) = @_; + @classes = ('heads') unless @classes; + my @patterns = map { "refs/$_" } @classes; my @headslist; open my $fd, '-|', git_cmd(), 'for-each-ref', ($limit ? '--count='.($limit+1) : ()), '--sort=-committerdate', '--format=%(objectname) %(refname) %(subject)%00%(committer)', - 'refs/heads' + @patterns or return; while (my $line = <$fd>) { my %ref_item; @@ -3120,7 +3269,7 @@ sub git_get_heads_list { my ($committer, $epoch, $tz) = ($committerinfo =~ /^(.*) ([0-9]+) (.*)$/); $ref_item{'fullname'} = $name; - $name =~ s!^refs/heads/!!; + $name =~ s!^refs/(?:head|remote)s/!!; $ref_item{'name'} = $name; $ref_item{'id'} = $hash; @@ -3299,30 +3448,6 @@ sub blob_contenttype { sub guess_file_syntax { my ($highlight, $mimetype, $file_name) = @_; return undef unless ($highlight && defined $file_name); - - # configuration for 'highlight' (http://www.andre-simon.de/) - # match by basename - my %highlight_basename = ( - #'Program' => 'py', - #'Library' => 'py', - 'SConstruct' => 'py', # SCons equivalent of Makefile - 'Makefile' => 'make', - ); - # match by extension - my %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), - # alternate extensions, see /etc/highlight/filetypes.conf - 'h' => 'c', - map { $_ => 'cpp' } qw(cxx c++ cc), - map { $_ => 'php' } qw(php3 php4), - map { $_ => 'pl' } qw(perl pm), # perhaps also 'cgi' - 'mak' => 'make', - map { $_ => 'xml' } qw(xhtml html htm), - ); - my $basename = basename($file_name, '.in'); return $highlight_basename{$basename} if exists $highlight_basename{$basename}; @@ -3341,10 +3466,10 @@ sub run_highlighter { my ($fd, $highlight, $syntax) = @_; return $fd unless ($highlight && defined $syntax); - close $fd - or die_error(404, "Reading blob failed"); + close $fd; open $fd, quote_command(git_cmd(), "cat-file", "blob", $hash)." | ". - "highlight --xhtml --fragment --syntax $syntax |" + quote_command($highlight_bin). + " --fragment --syntax $syntax |" or die_error(500, "Couldn't open file or run syntax highlighter"); return $fd; } @@ -3370,6 +3495,51 @@ sub get_page_title { return $title; } +sub print_feed_meta { + if (defined $project) { + my %href_params = get_feed_info(); + if (!exists $href_params{'-title'}) { + $href_params{'-title'} = 'log'; + } + + foreach my $format (qw(RSS Atom)) { + my $type = lc($format); + my %link_attr = ( + '-rel' => 'alternate', + '-title' => esc_attr("$project - $href_params{'-title'} - $format feed"), + '-type' => "application/$type+xml" + ); + + $href_params{'action'} = $type; + $link_attr{'-href'} = href(%href_params); + print "\n"; + + $href_params{'extra_options'} = '--no-merges'; + $link_attr{'-href'} = href(%href_params); + $link_attr{'-title'} .= ' (no merges)'; + print "\n"; + } + + } else { + printf(''."\n", + esc_attr($site_name), href(project=>undef, action=>"project_index")); + printf(''."\n", + esc_attr($site_name), href(project=>undef, action=>"opml")); + } +} + sub git_header_html { my $status = shift || "200 OK"; my $expires = shift; @@ -3390,7 +3560,7 @@ sub git_header_html { } print $cgi->header(-type=>$content_type, -charset => 'utf-8', -status=> $status, -expires => $expires) - unless ($opts{'-no_http_headers'}); + unless ($opts{'-no_http_header'}); my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : ''; print < @@ -3412,57 +3582,17 @@ EOF # print out each stylesheet that exist, providing backwards capability # for those people who defined $stylesheet in a config file if (defined $stylesheet) { - print ''."\n"; + print ''."\n"; } else { foreach my $stylesheet (@stylesheets) { next unless $stylesheet; - print ''."\n"; + print ''."\n"; } } - if (defined $project) { - my %href_params = get_feed_info(); - if (!exists $href_params{'-title'}) { - $href_params{'-title'} = 'log'; - } - - foreach my $format qw(RSS Atom) { - my $type = lc($format); - my %link_attr = ( - '-rel' => 'alternate', - '-title' => "$project - $href_params{'-title'} - $format feed", - '-type' => "application/$type+xml" - ); - - $href_params{'action'} = $type; - $link_attr{'-href'} = href(%href_params); - print "\n"; - - $href_params{'extra_options'} = '--no-merges'; - $link_attr{'-href'} = href(%href_params); - $link_attr{'-title'} .= ' (no merges)'; - print "\n"; - } - - } else { - printf(''."\n", - $site_name, href(project=>undef, action=>"project_index")); - printf(''."\n", - $site_name, href(project=>undef, action=>"opml")); - } + print_feed_meta() + if ($status eq '200 OK'); if (defined $favicon) { - print qq(\n); + print qq(\n); } print "\n" . @@ -3472,15 +3602,28 @@ EOF insert_file($site_header); } - print "
\n" . - $cgi->a({-href => esc_url($logo_url), - -title => $logo_label}, - qq()); + print "
\n"; + if (defined $logo) { + print $cgi->a({-href => esc_url($logo_url), + -title => $logo_label}, + $cgi->img({-src => esc_url($logo), + -width => 72, -height => 27, + -alt => "git", + -class => "logo"})); + } print $cgi->a({-href => esc_url($home_link)}, $home_link_str) . " / "; if (defined $project) { print $cgi->a({-href => href(action=>"summary")}, esc_html($project)); if (defined $action) { - print " / $action"; + my $action_print = $action ; + if (defined $opts{-action_extra}) { + $action_print = $cgi->a({-href => href(action=>$action)}, + $action); + } + print " / $action_print"; + } + if (defined $opts{-action_extra}) { + print " / $opts{-action_extra}"; } print "\n"; } @@ -3540,7 +3683,7 @@ sub git_footer_html { } $href_params{'-title'} ||= 'log'; - foreach my $format qw(RSS Atom) { + foreach my $format (qw(RSS Atom)) { $href_params{'action'} = lc($format); print $cgi->a({-href => href(%href_params), -title => "$href_params{'-title'} $format feed", @@ -3559,7 +3702,7 @@ sub git_footer_html { print "
\n"; print 'This page took '. ''. - Time::HiRes::tv_interval($t0, [Time::HiRes::gettimeofday()]). + tv_interval($t0, [ gettimeofday() ]). ' seconds '. ' and '. ''. @@ -3573,7 +3716,7 @@ sub git_footer_html { insert_file($site_footer); } - print qq!\n!; + print qq!\n!; if (defined $action && $action eq 'blame_incremental') { print qq!