X-Git-Url: https://git.ladys.computer/Gitweb/blobdiff_plain/9af94dc3f43f1ed2424146d93fccad69f9f9021fa2aa9792b19436dcdbc217ba..403b88e6b103b4c667c3c2cb5470583181b4d42eec03b27c11a58e7c7dd67a0d:/gitweb.perl

diff --git a/gitweb.perl b/gitweb.perl
index 2179bc4..df52a72 100755
--- a/gitweb.perl
+++ b/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();
@@ -222,6 +222,42 @@ 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 $maxload = 300;
+
+# syntax highlighting
+our %highlight_type = (
+	# match by basename
+	'SConstruct' => 'py',
+	'Program' => 'py',
+	'Library' => 'py',
+	'Makefile' => 'make',
+	# match by extension
+	'\.py$' => 'py', # Python
+	'\.c$' => 'c',
+	'\.h$' => 'c',
+	'\.cpp$' => 'cpp',
+	'\.cxx$' => 'cpp',
+	'\.rb$' => 'ruby',
+	'\.java$' => 'java',
+	'\.css$' => 'css',
+	'\.php3?$' => 'php',
+	'\.sh$' => 'sh', # Bash / shell script
+	'\.pl$' => 'pl', # Perl
+	'\.js$' => 'js', # JavaScript
+	'\.tex$' => 'tex', # TeX and LaTeX
+	'\.bib$' => 'bib', # BibTeX
+	'\.x?html$' => 'xml',
+	'\.xml$' => 'xml',
+	'\.awk$' => 'awk',
+	'\.bat$' => 'bat', # DOS Batch script
+	'\.ini$' => 'ini',
+	'\.spec$' => 'spec', # RPM Spec
+);
+
 # You define site-wide feature defaults here; override them with
 # $GITWEB_CONFIG as necessary.
 our %feature = (
@@ -440,6 +476,19 @@ 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, 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 {
@@ -449,7 +498,11 @@ 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;
@@ -545,11 +598,36 @@ sub filter_snapshot_fmts {
 }
 
 our $GITWEB_CONFIG = $ENV{'GITWEB_CONFIG'} || "++GITWEB_CONFIG++";
+our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++";
+# die if there are errors parsing config file
 if (-e $GITWEB_CONFIG) {
 	do $GITWEB_CONFIG;
-} else {
-	our $GITWEB_CONFIG_SYSTEM = $ENV{'GITWEB_CONFIG_SYSTEM'} || "++GITWEB_CONFIG_SYSTEM++";
-	do $GITWEB_CONFIG_SYSTEM if -e $GITWEB_CONFIG_SYSTEM;
+	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
@@ -558,6 +636,10 @@ $number_of_git_cmds++;
 
 $projects_list ||= $projectroot;
 
+if (defined $maxload && get_loadavg() > $maxload) {
+	die_error(503, "The load average on the server is too high");
+}
+
 # ======================================================================
 # input validation and dispatch
 
@@ -914,6 +996,21 @@ if ($git_avatar eq 'gravatar') {
 	$git_avatar = '';
 }
 
+# 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
 if (!defined $action) {
 	if (defined $hash) {
@@ -934,11 +1031,16 @@ if ($action !~ m/^(?:opml|project_list|project_index)$/ &&
 	die_error(400, "Project needed");
 }
 $actions{$action}->();
-exit;
+DONE_GITWEB:
+1;
 
 ## ======================================================================
 ## 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
@@ -955,7 +1057,8 @@ 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
@@ -1112,6 +1215,7 @@ 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;
@@ -1124,6 +1228,7 @@ 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;
@@ -1132,6 +1237,7 @@ sub esc_param {
 # quote unsafe chars in whole URL, so some charactrs 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/ /\+/g;
@@ -1143,6 +1249,8 @@ sub esc_html {
 	my $str = shift;
 	my %opts = @_;
 
+	return undef unless defined $str;
+
 	$str = to_utf8($str);
 	$str = $cgi->escapeHTML($str);
 	if ($opts{'-nbsp'}) {
@@ -1157,6 +1265,8 @@ sub esc_path {
 	my $str = shift;
 	my %opts = @_;
 
+	return undef unless defined $str;
+
 	$str = to_utf8($str);
 	$str = $cgi->escapeHTML($str);
 	if ($opts{'-nbsp'}) {
@@ -1299,7 +1409,6 @@ sub chop_str {
 		$str =~ m/^(.*?)($begre)$/;
 		my ($lead, $body) = ($1, $2);
 		if (length($lead) > 4) {
-			$body =~ s/^[^;]*;// if ($lead =~ m/&[^;]*$/);
 			$lead = " ...";
 		}
 		return "$lead$body";
@@ -1310,8 +1419,6 @@ 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";
@@ -1321,7 +1428,6 @@ sub chop_str {
 		my $body = $1;
 		my $tail = $2;
 		if (length($tail) > 4) {
-			$body =~ s/&[^;]*$//;
 			$tail = "... ";
 		}
 		return "$body$tail";
@@ -2175,6 +2281,8 @@ sub config_to_multi {
 sub git_get_project_config {
 	my ($key, $type) = @_;
 
+	return unless defined $git_dir;
+
 	# key sanity check
 	return unless ($key);
 	$key =~ s/^gitweb\.//;
@@ -2377,6 +2485,9 @@ 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
@@ -3115,23 +3226,30 @@ sub blob_contenttype {
 ## ======================================================================
 ## 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'.
@@ -3145,7 +3263,8 @@ 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_headers'});
 	my $mod_perl_version = $ENV{'MOD_PERL'} ? " $ENV{'MOD_PERL'}" : '';
 	print <<EOF;
 <?xml version="1.0" encoding="utf-8"?>
@@ -3223,7 +3342,7 @@ EOF
 	print "</head>\n" .
 	      "<body>\n";
 
-	if (-f $site_header) {
+	if (defined $site_header && -f $site_header) {
 		insert_file($site_header);
 	}
 
@@ -3324,12 +3443,13 @@ 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!.
@@ -3344,7 +3464,7 @@ 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
@@ -3355,24 +3475,37 @@ 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'});
 }
 
 ## ----------------------------------------------------------------------
@@ -3472,14 +3605,21 @@ 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
@@ -4303,17 +4443,24 @@ 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 {
@@ -4744,7 +4891,7 @@ 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";
@@ -5007,6 +5154,17 @@ sub git_blame_common {
 	my $formats_nav =
 		$cgi->a({-href => href(action=>"blob", -replay=>1)},
 		        "blob") .
+		" | ";
+	if ($format eq 'incremental') {
+		$formats_nav .=
+			$cgi->a({-href => href(action=>"blame", javascript=>0, -replay=>1)},
+			        "blame") . " (non-incremental)";
+	} else {
+		$formats_nav .=
+			$cgi->a({-href => href(action=>"blame_incremental", -replay=>1)},
+			        "blame") . " (incremental)";
+	}
+	$formats_nav .=
 		" | " .
 		$cgi->a({-href => href(action=>"history", -replay=>1)},
 		        "history") .
@@ -5266,6 +5424,7 @@ 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);
@@ -5273,6 +5432,25 @@ sub git_blob {
 	# we can have blame only for text/* mimetype
 	$have_blame &&= ($mimetype =~ m!^text/!);
 
+	my $have_highlight = gitweb_check_feature('highlight');
+	my $syntax;
+	if ($have_highlight && defined($file_name)) {
+		my $basename = basename($file_name, '.in');
+		foreach my $regexp (keys %highlight_type) {
+			if ($basename =~ /$regexp/) {
+				$syntax = $highlight_type{$regexp};
+				last;
+			}
+		}
+
+		if ($syntax) {
+			close $fd;
+			open $fd, quote_command(git_cmd(), "cat-file", "blob", $hash)." | ".
+			          "highlight --xhtml --fragment -t 8 --syntax $syntax |"
+				or die_error(500, "Couldn't open file or run syntax highlighter");
+		}
+	}
+
 	git_header_html(undef, $expires);
 	my $formats_nav = '';
 	if (defined $hash_base && (my %co = parse_commit($hash_base))) {
@@ -5324,7 +5502,7 @@ sub git_blob {
 			$line = untabify($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);
+			       $nr, $nr, $nr, $syntax ? $line : esc_html($line, -nbsp=>1);
 		}
 	}
 	close $fd