diff options
Diffstat (limited to 'gitweb/gitweb.perl')
-rwxr-xr-x | gitweb/gitweb.perl | 710 |
1 files changed, 503 insertions, 207 deletions
diff --git a/gitweb/gitweb.perl b/gitweb/gitweb.perl index 7e477af956..a85e2f6319 100755 --- a/gitweb/gitweb.perl +++ b/gitweb/gitweb.perl @@ -11,7 +11,7 @@ use strict; use warnings; use CGI qw(:standard :escapeHTML -nosticky); use CGI::Util qw(unescape); -use CGI::Carp qw(fatalsToBrowser); +use CGI::Carp qw(fatalsToBrowser set_message); use Encode; use Fcntl ':mode'; use File::Find qw(); @@ -28,34 +28,42 @@ BEGIN { CGI->compile() if $ENV{'MOD_PERL'}; } -our $cgi = new CGI; our $version = "++GIT_VERSION++"; -our $my_url = $cgi->url(); -our $my_uri = $cgi->url(-absolute => 1); -# Base URL for relative URLs in gitweb ($logo, $favicon, ...), -# needed and used only for URLs with nonempty PATH_INFO -our $base_url = $my_url; +our ($my_url, $my_uri, $base_url, $path_info, $home_link); +sub evaluate_uri { + our $cgi; -# 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) { - 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'}; + our $my_url = $cgi->url(); + our $my_uri = $cgi->url(-absolute => 1); + + # Base URL for relative URLs in gitweb ($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) { + 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'}; + } } + + # target of the home link on top of all pages + our $home_link = $my_uri || "/"; } # core git executable to use @@ -70,9 +78,6 @@ our $projectroot = "++GITWEB_PROJECTROOT++"; # the number is relative to the projectroot our $project_maxdepth = "++GITWEB_PROJECT_MAXDEPTH++"; -# target of the home link on top of all pages -our $home_link = $my_uri || "/"; - # string of the home link on top of all pages our $home_link_str = "++GITWEB_HOME_LINK_STR++"; @@ -221,6 +226,35 @@ our %avatar_size = ( 'double' => 32 ); +# Used to set the maximum load that we will still respond to gitweb queries. +# If server load exceed this value then return "503 server busy" error. +# If gitweb cannot determined server load, it is taken to be 0. +# 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), + # 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), +); + # You define site-wide feature defaults here; override them with # $GITWEB_CONFIG as necessary. our %feature = ( @@ -234,7 +268,7 @@ 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(<feature>) to retrieve the <feature> value # (an array) or gitweb_check_feature(<feature>) to check if <feature> @@ -439,6 +473,19 @@ our %feature = ( 'javascript-actions' => { 'override' => 0, 'default' => [0]}, + + # 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, + # and therefore is disabled by default. + + # To enable system wide have in $GITWEB_CONFIG + # $feature{'highlight'}{'default'} = [1]; + + 'highlight' => { + 'sub' => sub { feature_bool('highlight', @_) }, + 'override' => 0, + 'default' => [0]}, ); sub gitweb_get_feature { @@ -448,7 +495,11 @@ sub gitweb_get_feature { $feature{$name}{'sub'}, $feature{$name}{'override'}, @{$feature{$name}{'default'}}); - if (!$override) { return @defaults; } + # project specific override is possible only if we have project + our $git_dir; # global variable, declared later + if (!$override || !defined $git_dir) { + return @defaults; + } if (!defined $sub) { warn "feature $name is not overridable"; return @defaults; @@ -543,19 +594,54 @@ sub filter_snapshot_fmts { !$known_snapshot_formats{$_}{'disabled'}} @fmts; } -our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++"; -if (-e $GITWEB_CONFIG) { - do $GITWEB_CONFIG; -} else { +our ($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++"; - do $GITWEB_CONFIG_SYSTEM if -e $GITWEB_CONFIG_SYSTEM; + # 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; + die $@ if $@; + } +} + +# Get loadavg of system, to compare against $maxload. +# Currently it requires '/proc/loadavg' present to get loadavg; +# if it is not present it returns 0, which means no load checking. +sub get_loadavg { + if( -e '/proc/loadavg' ){ + open my $fd, '<', '/proc/loadavg' + or return 0; + my @load = split(/\s+/, scalar <$fd>); + close $fd; + + # The first three columns measure CPU and IO utilization of the last one, + # five, and 10 minute periods. The fourth column shows the number of + # currently running processes and the total number of processes in the m/n + # format. The last column displays the last process ID used. + return $load[0] || 0; + } + # additional checks for load average should go here for things that don't export + # /proc/loadavg + + return 0; } # version of the core git binary -our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; -$number_of_git_cmds++; +our $git_version; +sub evaluate_git_version { + our $git_version = qx("$GIT" --version) =~ m/git version (.*)$/ ? $1 : "unknown"; + $number_of_git_cmds++; +} -$projects_list ||= $projectroot; +sub check_loadavg { + if (defined $maxload && get_loadavg() > $maxload) { + die_error(503, "The load average on the server is too high"); + } +} # ====================================================================== # input validation and dispatch @@ -641,11 +727,15 @@ our %allowed_options = ( # should be single values, but opt can be an array. We should probably # build an array of parameters that can be multi-valued, but since for the time # being it's only this one, we just single it out -while (my ($name, $symbol) = each %cgi_param_mapping) { - if ($symbol eq 'opt') { - $input_params{$name} = [ $cgi->param($symbol) ]; - } else { - $input_params{$name} = $cgi->param($symbol); +sub evaluate_query_params { + our $cgi; + + while (my ($name, $symbol) = each %cgi_param_mapping) { + if ($symbol eq 'opt') { + $input_params{$name} = [ $cgi->param($symbol) ]; + } else { + $input_params{$name} = $cgi->param($symbol); + } } } @@ -792,152 +882,277 @@ sub evaluate_path_info { } } } -evaluate_path_info(); -our $action = $input_params{'action'}; -if (defined $action) { - if (!validate_action($action)) { - die_error(400, "Invalid action parameter"); +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); +sub evaluate_and_validate_params { + our $action = $input_params{'action'}; + if (defined $action) { + if (!validate_action($action)) { + die_error(400, "Invalid action parameter"); + } } -} -# parameters which are pathnames -our $project = $input_params{'project'}; -if (defined $project) { - if (!validate_project($project)) { - undef $project; - die_error(404, "No such project"); + # parameters which are pathnames + our $project = $input_params{'project'}; + if (defined $project) { + if (!validate_project($project)) { + undef $project; + die_error(404, "No such project"); + } } -} -our $file_name = $input_params{'file_name'}; -if (defined $file_name) { - if (!validate_pathname($file_name)) { - die_error(400, "Invalid file parameter"); + our $file_name = $input_params{'file_name'}; + if (defined $file_name) { + if (!validate_pathname($file_name)) { + die_error(400, "Invalid file parameter"); + } } -} -our $file_parent = $input_params{'file_parent'}; -if (defined $file_parent) { - if (!validate_pathname($file_parent)) { - die_error(400, "Invalid file parent parameter"); + our $file_parent = $input_params{'file_parent'}; + if (defined $file_parent) { + if (!validate_pathname($file_parent)) { + die_error(400, "Invalid file parent parameter"); + } } -} -# parameters which are refnames -our $hash = $input_params{'hash'}; -if (defined $hash) { - if (!validate_refname($hash)) { - die_error(400, "Invalid hash parameter"); + # parameters which are refnames + our $hash = $input_params{'hash'}; + if (defined $hash) { + if (!validate_refname($hash)) { + die_error(400, "Invalid hash parameter"); + } } -} -our $hash_parent = $input_params{'hash_parent'}; -if (defined $hash_parent) { - if (!validate_refname($hash_parent)) { - die_error(400, "Invalid hash parent parameter"); + our $hash_parent = $input_params{'hash_parent'}; + if (defined $hash_parent) { + if (!validate_refname($hash_parent)) { + die_error(400, "Invalid hash parent parameter"); + } } -} -our $hash_base = $input_params{'hash_base'}; -if (defined $hash_base) { - if (!validate_refname($hash_base)) { - die_error(400, "Invalid hash base parameter"); + our $hash_base = $input_params{'hash_base'}; + if (defined $hash_base) { + if (!validate_refname($hash_base)) { + die_error(400, "Invalid hash base parameter"); + } } -} -our @extra_options = @{$input_params{'extra_options'}}; -# @extra_options is always defined, since it can only be (currently) set from -# CGI, and $cgi->param() returns the empty array in array context if the param -# is not set -foreach my $opt (@extra_options) { - if (not exists $allowed_options{$opt}) { - die_error(400, "Invalid option parameter"); - } - if (not grep(/^$action$/, @{$allowed_options{$opt}})) { - die_error(400, "Invalid option parameter for this action"); + our @extra_options = @{$input_params{'extra_options'}}; + # @extra_options is always defined, since it can only be (currently) set from + # CGI, and $cgi->param() returns the empty array in array context if the param + # is not set + foreach my $opt (@extra_options) { + if (not exists $allowed_options{$opt}) { + die_error(400, "Invalid option parameter"); + } + if (not grep(/^$action$/, @{$allowed_options{$opt}})) { + die_error(400, "Invalid option parameter for this action"); + } } -} -our $hash_parent_base = $input_params{'hash_parent_base'}; -if (defined $hash_parent_base) { - if (!validate_refname($hash_parent_base)) { - die_error(400, "Invalid hash parent base parameter"); + our $hash_parent_base = $input_params{'hash_parent_base'}; + if (defined $hash_parent_base) { + if (!validate_refname($hash_parent_base)) { + die_error(400, "Invalid hash parent base parameter"); + } } -} -# other parameters -our $page = $input_params{'page'}; -if (defined $page) { - if ($page =~ m/[^0-9]/) { - die_error(400, "Invalid page parameter"); + # other parameters + our $page = $input_params{'page'}; + if (defined $page) { + if ($page =~ m/[^0-9]/) { + die_error(400, "Invalid page parameter"); + } } -} -our $searchtype = $input_params{'searchtype'}; -if (defined $searchtype) { - if ($searchtype =~ m/[^a-z]/) { - die_error(400, "Invalid searchtype parameter"); + our $searchtype = $input_params{'searchtype'}; + if (defined $searchtype) { + if ($searchtype =~ m/[^a-z]/) { + die_error(400, "Invalid searchtype parameter"); + } } -} -our $search_use_regexp = $input_params{'search_use_regexp'}; + our $search_use_regexp = $input_params{'search_use_regexp'}; -our $searchtext = $input_params{'searchtext'}; -our $search_regexp; -if (defined $searchtext) { - if (length($searchtext) < 2) { - die_error(403, "At least two characters are required for search parameter"); + our $searchtext = $input_params{'searchtext'}; + our $search_regexp; + 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; } - $search_regexp = $search_use_regexp ? $searchtext : quotemeta $searchtext; } # path to the current git repository our $git_dir; -$git_dir = "$projectroot/$project" if $project; - -# list of supported snapshot formats -our @snapshot_fmts = gitweb_get_feature('snapshot'); -@snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); - -# check that the avatar feature is set to a known provider name, -# and for each provider check if the dependencies are satisfied. -# if the provider name is invalid or the dependencies are not met, -# reset $git_avatar to the empty string. -our ($git_avatar) = gitweb_get_feature('avatar'); -if ($git_avatar eq 'gravatar') { - $git_avatar = '' unless (eval { require Digest::MD5; 1; }); -} elsif ($git_avatar eq 'picon') { - # no dependencies -} else { - $git_avatar = ''; +sub evaluate_git_dir { + our $git_dir = "$projectroot/$project" if $project; } -# dispatch -if (!defined $action) { - if (defined $hash) { - $action = git_get_type($hash); - } elsif (defined $hash_base && defined $file_name) { - $action = git_get_type("$hash_base:$file_name"); - } elsif (defined $project) { - $action = 'summary'; +our (@snapshot_fmts, $git_avatar); +sub configure_gitweb_features { + # list of supported snapshot formats + our @snapshot_fmts = gitweb_get_feature('snapshot'); + @snapshot_fmts = filter_snapshot_fmts(@snapshot_fmts); + + # check that the avatar feature is set to a known provider name, + # and for each provider check if the dependencies are satisfied. + # if the provider name is invalid or the dependencies are not met, + # reset $git_avatar to the empty string. + our ($git_avatar) = gitweb_get_feature('avatar'); + if ($git_avatar eq 'gravatar') { + $git_avatar = '' unless (eval { require Digest::MD5; 1; }); + } elsif ($git_avatar eq 'picon') { + # no dependencies } else { - $action = 'project_list'; + $git_avatar = ''; } } -if (!defined($actions{$action})) { - die_error(400, "Unknown action"); + +# custom error handler: 'die <message>' is Internal Server Error +sub handle_errors_html { + my $msg = shift; # it is already HTML escaped + + # to avoid infinite loop where error occurs in die_error, + # change handler to default handler, disabling handle_errors_html + set_message("Error occured when inside die_error:\n$msg"); + + # you cannot jump out of die_error when called as error handler; + # the subroutine set via CGI::Carp::set_message is called _after_ + # HTTP headers are already written, so it cannot write them itself + die_error(undef, undef, $msg, -error_handler => 1, -no_http_header => 1); +} +set_message(\&handle_errors_html); + +# dispatch +sub dispatch { + if (!defined $action) { + if (defined $hash) { + $action = git_get_type($hash); + } elsif (defined $hash_base && defined $file_name) { + $action = git_get_type("$hash_base:$file_name"); + } elsif (defined $project) { + $action = 'summary'; + } else { + $action = 'project_list'; + } + } + if (!defined($actions{$action})) { + die_error(400, "Unknown action"); + } + if ($action !~ m/^(?:opml|project_list|project_index)$/ && + !$project) { + die_error(400, "Project needed"); + } + $actions{$action}->(); +} + +sub reset_timer { + our $t0 = [Time::HiRes::gettimeofday()] + if defined $t0; + our $number_of_git_cmds = 0; +} + +sub run_request { + reset_timer(); + + evaluate_uri(); + evaluate_gitweb_config(); + check_loadavg(); + + # $projectroot and $projects_list might be set in gitweb config file + $projects_list ||= $projectroot; + + evaluate_query_params(); + evaluate_path_info(); + evaluate_and_validate_params(); + evaluate_git_dir(); + + configure_gitweb_features(); + + dispatch(); +} + +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 }; } -if ($action !~ m/^(?:opml|project_list|project_index)$/ && - !$project) { - die_error(400, "Project needed"); +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' => \&configure_as_fcgi, + 'nproc|n=i' => sub { + my ($arg, $val) = @_; + return unless eval { require FCGI::ProcManager; 1; }; + my $proc_manager = FCGI::ProcManager->new({ + n_processes => $val, + }); + our $pre_listen_hook = sub { $proc_manager->pm_manage() }; + our $pre_dispatch_hook = sub { $proc_manager->pm_pre_dispatch() }; + our $post_dispatch_hook = sub { $proc_manager->pm_post_dispatch() }; + }, + ); +} + +sub run { + evaluate_argv(); + evaluate_git_version(); + + $pre_listen_hook->() + if $pre_listen_hook; + + REQUEST: + while ($cgi = $CGI->new()) { + $pre_dispatch_hook->() + if $pre_dispatch_hook; + + run_request(); + + $post_dispatch_hook->() + if $post_dispatch_hook; + + last REQUEST if ($is_last_request->()); + } + + DONE_GITWEB: + 1; +} + +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; } -$actions{$action}->(); -exit; ## ====================================================================== ## action links +# possible values of extra options +# -full => 0|1 - use absolute/full URL ($my_uri/$my_url as base) +# -replay => 1 - start from a current view (replay with modifications) +# -path_info => 0|1 - don't use/use path_info URL (if possible) sub href { my %params = @_; # default is to use -absolute url() i.e. $my_uri @@ -954,7 +1169,8 @@ sub href { } my $use_pathinfo = gitweb_check_feature('pathinfo'); - if ($use_pathinfo and defined $params{'project'}) { + if (defined $params{'project'} && + (exists $params{-path_info} ? $params{-path_info} : $use_pathinfo)) { # try to put as many parameters as possible in PATH_INFO: # - project name # - action @@ -1111,6 +1327,7 @@ sub validate_refname { # in utf-8 thanks to "binmode STDOUT, ':utf8'" at beginning sub to_utf8 { my $str = shift; + return undef unless defined $str; if (utf8::valid($str)) { utf8::decode($str); return $str; @@ -1123,16 +1340,17 @@ sub to_utf8 { # correct, but quoted slashes look too horrible in bookmarks sub esc_param { my $str = shift; + return undef unless defined $str; $str =~ s/([^A-Za-z0-9\-_.~()\/:@ ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; return $str; } -# quote unsafe chars in whole URL, so some charactrs cannot be quoted +# quote unsafe chars in whole URL, so some characters cannot be quoted sub esc_url { my $str = shift; - $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&=])/sprintf("%%%02X", ord($1))/eg; - $str =~ s/\+/%2B/g; + return undef unless defined $str; + $str =~ s/([^A-Za-z0-9\-_.~();\/;?:@&= ]+)/CGI::escape($1)/eg; $str =~ s/ /\+/g; return $str; } @@ -1142,6 +1360,8 @@ sub esc_html { my $str = shift; my %opts = @_; + return undef unless defined $str; + $str = to_utf8($str); $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { @@ -1156,6 +1376,8 @@ sub esc_path { my $str = shift; my %opts = @_; + return undef unless defined $str; + $str = to_utf8($str); $str = $cgi->escapeHTML($str); if ($opts{'-nbsp'}) { @@ -1298,7 +1520,6 @@ sub chop_str { $str =~ m/^(.*?)($begre)$/; my ($lead, $body) = ($1, $2); if (length($lead) > 4) { - $body =~ s/^[^;]*;// if ($lead =~ m/&[^;]*$/); $lead = " ..."; } return "$lead$body"; @@ -1309,8 +1530,6 @@ sub chop_str { $str =~ m/^(.*?)($begre)$/; my ($mid, $right) = ($1, $2); if (length($mid) > 5) { - $left =~ s/&[^;]*$//; - $right =~ s/^[^;]*;// if ($mid =~ m/&[^;]*$/); $mid = " ... "; } return "$left$mid$right"; @@ -1320,7 +1539,6 @@ sub chop_str { my $body = $1; my $tail = $2; if (length($tail) > 4) { - $body =~ s/&[^;]*$//; $tail = "... "; } return "$body$tail"; @@ -2174,6 +2392,8 @@ sub config_to_multi { sub git_get_project_config { my ($key, $type) = @_; + return unless defined $git_dir; + # key sanity check return unless ($key); $key =~ s/^gitweb\.//; @@ -2376,6 +2596,9 @@ sub git_get_projects_list { follow_skip => 2, # ignore duplicates dangling_symlinks => 0, # ignore dangling symlinks, silently wanted => sub { + # global variables + our $project_maxdepth; + our $projectroot; # skip project-list toplevel, if we get it. return if (m!^[/.]$!); # only directories can be git repositories @@ -3111,26 +3334,64 @@ sub blob_contenttype { return $type; } +# guess file syntax for syntax highlighting; return undef if no highlighting +# the name of syntax can (in the future) depend on syntax highlighter used +sub guess_file_syntax { + my ($highlight, $mimetype, $file_name) = @_; + return undef unless ($highlight && defined $file_name); + my $basename = basename($file_name, '.in'); + return $highlight_basename{$basename} + if exists $highlight_basename{$basename}; + + $basename =~ /\.([^.]*)$/; + my $ext = $1 or return undef; + return $highlight_ext{$ext} + if exists $highlight_ext{$ext}; + + return undef; +} + +# run highlighter and return FD of its output, +# or return original FD if no highlighting +sub run_highlighter { + my ($fd, $highlight, $syntax) = @_; + return $fd unless ($highlight && defined $syntax); + + close $fd + or die_error(404, "Reading blob failed"); + open $fd, quote_command(git_cmd(), "cat-file", "blob", $hash)." | ". + "highlight --xhtml --fragment --syntax $syntax |" + or die_error(500, "Couldn't open file or run syntax highlighter"); + return $fd; +} + ## ====================================================================== ## functions printing HTML: header, footer, error page +sub get_page_title { + my $title = to_utf8($site_name); + + return $title unless (defined $project); + $title .= " - " . to_utf8($project); + + return $title unless (defined $action); + $title .= "/$action"; # $action is US-ASCII (7bit ASCII) + + return $title unless (defined $file_name); + $title .= " - " . esc_path($file_name); + if ($action eq "tree" && $file_name !~ m|/$|) { + $title .= "/"; + } + + return $title; +} + sub git_header_html { my $status = shift || "200 OK"; my $expires = shift; + my %opts = @_; - my $title = "$site_name"; - if (defined $project) { - $title .= " - " . to_utf8($project); - if (defined $action) { - $title .= "/$action"; - if (defined $file_name) { - $title .= " - " . esc_path($file_name); - if ($action eq "tree" && $file_name !~ m|/$|) { - $title .= "/"; - } - } - } - } + my $title = get_page_title(); my $content_type; # require explicit support from the UA if we are to send the page as # 'application/xhtml+xml', otherwise send it as plain old 'text/html'. @@ -3144,7 +3405,8 @@ sub git_header_html { $content_type = 'text/html'; } print $cgi->header(-type=>$content_type, -charset => 'utf-8', - -status=> $status, -expires => $expires); + -status=> $status, -expires => $expires) + unless ($opts{'-no_http_header'}); my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : ''; print <<EOF; <?xml version="1.0" encoding="utf-8"?> @@ -3222,7 +3484,7 @@ EOF print "</head>\n" . "<body>\n"; - if (-f $site_header) { + if (defined $site_header && -f $site_header) { insert_file($site_header); } @@ -3323,12 +3585,13 @@ sub git_footer_html { print "</div>\n"; # class="page_footer" } - if (-f $site_footer) { + if (defined $site_footer && -f $site_footer) { insert_file($site_footer); } print qq!<script type="text/javascript" src="$javascript"></script>\n!; - if ($action eq 'blame_incremental') { + if (defined $action && + $action eq 'blame_incremental') { print qq!<script type="text/javascript">\n!. qq!startBlame("!. href(action=>"blame_data", -replay=>1) .qq!",\n!. qq! "!. href() .qq!");\n!. @@ -3343,7 +3606,7 @@ sub git_footer_html { "</html>"; } -# die_error(<http_status_code>, <error_message>) +# die_error(<http_status_code>, <error_message>[, <detailed_html_description>]) # Example: die_error(404, 'Hash not found') # By convention, use the following status codes (as defined in RFC 2616): # 400: Invalid or missing CGI parameters, or @@ -3354,24 +3617,37 @@ sub git_footer_html { # 500: The server isn't configured properly, or # an internal error occurred (e.g. failed assertions caused by bugs), or # an unknown error occurred (e.g. the git binary died unexpectedly). +# 503: The server is currently unavailable (because it is overloaded, +# or down for maintenance). Generally, this is a temporary state. sub die_error { my $status = shift || 500; - my $error = shift || "Internal server error"; + my $error = esc_html(shift) || "Internal Server Error"; + my $extra = shift; + my %opts = @_; - my %http_responses = (400 => '400 Bad Request', - 403 => '403 Forbidden', - 404 => '404 Not Found', - 500 => '500 Internal Server Error'); - git_header_html($http_responses{$status}); + my %http_responses = ( + 400 => '400 Bad Request', + 403 => '403 Forbidden', + 404 => '404 Not Found', + 500 => '500 Internal Server Error', + 503 => '503 Service Unavailable', + ); + git_header_html($http_responses{$status}, undef, %opts); print <<EOF; <div class="page_body"> <br /><br /> $status - $error <br /> -</div> EOF + if (defined $extra) { + print "<hr />\n" . + "$extra\n"; + } + print "</div>\n"; + git_footer_html(); - exit; + goto DONE_GITWEB + unless ($opts{'-error_handler'}); } ## ---------------------------------------------------------------------- @@ -3471,14 +3747,21 @@ sub git_print_header_div { } sub print_local_time { + print format_local_time(@_); +} + +sub format_local_time { + my $localtime = ''; my %date = @_; if ($date{'hour_local'} < 6) { - printf(" (<span class=\"atnight\">%02d:%02d</span> %s)", + $localtime .= sprintf(" (<span class=\"atnight\">%02d:%02d</span> %s)", $date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'}); } else { - printf(" (%02d:%02d %s)", + $localtime .= sprintf(" (%02d:%02d %s)", $date{'hour_local'}, $date{'minute_local'}, $date{'tz_local'}); } + + return $localtime; } # Outputs the author name and date in long form @@ -3498,9 +3781,9 @@ sub git_print_authorship { } # Outputs table rows containing the full author or committer information, -# in the format expected for 'commit' view (& similia). +# in the format expected for 'commit' view (& similar). # Parameters are a commit hash reference, followed by the list of people -# to output information for. If the list is empty it defalts to both +# to output information for. If the list is empty it defaults to both # author and committer. sub git_print_authorship_rows { my $co = shift; @@ -4229,8 +4512,8 @@ sub git_patchset_body { print "</div>\n"; # class="patch" } - # for compact combined (--cc) format, with chunk and patch simpliciaction - # patchset might be empty, but there might be unprocessed raw lines + # for compact combined (--cc) format, with chunk and patch simplification + # the patchset might be empty, but there might be unprocessed raw lines for (++$patch_idx if $patch_number > 0; $patch_idx < @$difftree; ++$patch_idx) { @@ -4302,17 +4585,24 @@ sub fill_project_list_info { # print 'sort by' <th> element, generating 'sort by $name' replay link # if that order is not selected sub print_sort_th { + print format_sort_th(@_); +} + +sub format_sort_th { my ($name, $order, $header) = @_; + my $sort_th = ""; $header ||= ucfirst($name); if ($order eq $name) { - print "<th>$header</th>\n"; + $sort_th .= "<th>$header</th>\n"; } else { - print "<th>" . - $cgi->a({-href => href(-replay=>1, order=>$name), - -class => "header"}, $header) . - "</th>\n"; + $sort_th .= "<th>" . + $cgi->a({-href => href(-replay=>1, order=>$name), + -class => "header"}, $header) . + "</th>\n"; } + + return $sort_th; } sub git_project_list_body { @@ -4743,7 +5033,7 @@ sub git_project_list { } git_header_html(); - if (-f $home_text) { + if (defined $home_text && -f $home_text) { print "<div class=\"index_include\">\n"; insert_file($home_text); print "</div>\n"; @@ -4901,15 +5191,15 @@ sub git_summary { } sub git_tag { - my $head = git_get_head_hash($project); - git_header_html(); - git_print_page_nav('','', $head,undef,$head); my %tag = parse_tag($hash); if (! %tag) { die_error(404, "Unknown tag object"); } + my $head = git_get_head_hash($project); + git_header_html(); + git_print_page_nav('','', $head,undef,$head); git_print_header_div('commit', esc_html($tag{'name'}), $hash); print "<div class=\"title_text\">\n" . "<table class=\"object_header\">\n" . @@ -5276,6 +5566,7 @@ sub git_blob { open my $fd, "-|", git_cmd(), "cat-file", "blob", $hash or die_error(500, "Couldn't cat $file_name, $hash"); my $mimetype = blob_mimetype($fd, $file_name); + # use 'blob_plain' (aka 'raw') view for files that cannot be displayed if ($mimetype !~ m!^(?:text/|image/(?:gif|png|jpeg)$)! && -B $fd) { close $fd; return git_blob_plain($mimetype); @@ -5283,6 +5574,11 @@ sub git_blob { # we can have blame only for text/* mimetype $have_blame &&= ($mimetype =~ m!^text/!); + my $highlight = gitweb_check_feature('highlight'); + my $syntax = guess_file_syntax($highlight, $mimetype, $file_name); + $fd = run_highlighter($fd, $highlight, $syntax) + if $syntax; + git_header_html(undef, $expires); my $formats_nav = ''; if (defined $hash_base && (my %co = parse_commit($hash_base))) { @@ -5332,9 +5628,8 @@ sub git_blob { chomp $line; $nr++; $line = untabify($line); - printf "<div class=\"pre\"><a id=\"l%i\" href=\"" . href(-replay => 1) - . "#l%i\" class=\"linenr\">%4i</a> %s</div>\n", - $nr, $nr, $nr, esc_html($line, -nbsp=>1); + printf qq!<div class="pre"><a id="l%i" href="%s#l%i" class="linenr">%4i</a> %s</div>\n!, + $nr, href(-replay => 1), $nr, $nr, $syntax ? $line : esc_html($line, -nbsp=>1); } } close $fd @@ -6047,8 +6342,8 @@ sub git_commitdiff { } push @commit_spec, '--root', $hash; } - open $fd, "-|", git_cmd(), "format-patch", '--encoding=utf8', - '--stdout', @commit_spec + open $fd, "-|", git_cmd(), "format-patch", @diff_opts, + '--encoding=utf8', '--stdout', @commit_spec or die_error(500, "Open git-format-patch failed"); } else { die_error(400, "Unknown commitdiff format"); @@ -6226,12 +6521,13 @@ sub git_search { $paging_nav .= " ⋅ next"; } - if ($#commitlist >= 100) { - } - git_print_page_nav('','', $hash,$co{'tree'},$hash, $paging_nav); git_print_header_div('commit', esc_html($co{'title'}), $hash); - git_search_grep_body(\@commitlist, 0, 99, $next_link); + if ($page == 0 && !@commitlist) { + print "<p>No match.</p>\n"; + } else { + git_search_grep_body(\@commitlist, 0, 99, $next_link); + } } if ($searchtype eq 'pickaxe') { |