X-Git-Url: https://sipb.mit.edu/gitweb.cgi/ikiwiki.git/blobdiff_plain/efe91335c65b96f3eb8b32d8c58c9cce68db47b4..70df59f7f459d211de9c1073ae93bead51392adb:/IkiWiki/Render.pm

diff --git a/IkiWiki/Render.pm b/IkiWiki/Render.pm
index 9e340c26e..d0d28e802 100644
--- a/IkiWiki/Render.pm
+++ b/IkiWiki/Render.pm
@@ -1,3 +1,5 @@
+#!/usr/bin/perl
+
 package IkiWiki;
 
 use warnings;
@@ -16,6 +18,40 @@ sub linkify ($$) { #{{{
 	return $content;
 } #}}}
 
+my $_scrubber;
+sub scrubber { #{{{
+	return $_scrubber if defined $_scrubber;
+	
+	eval q{use HTML::Scrubber};
+	# Lists based on http://feedparser.org/docs/html-sanitization.html
+	$_scrubber = HTML::Scrubber->new(
+		allow => [qw{
+			a abbr acronym address area b big blockquote br
+			button caption center cite code col colgroup dd del
+			dfn dir div dl dt em fieldset font form h1 h2 h3 h4
+			h5 h6 hr i img input ins kbd label legend li map
+			menu ol optgroup option p pre q s samp select small
+			span strike strong sub sup table tbody td textarea
+			tfoot th thead tr tt u ul var
+		}],
+		default => [undef, { map { $_ => 1 } qw{
+			abbr accept accept-charset accesskey action
+			align alt axis border cellpadding cellspacing
+			char charoff charset checked cite class
+			clear cols colspan color compact coords
+			datetime dir disabled enctype for frame
+			headers height href hreflang hspace id ismap
+			label lang longdesc maxlength media method
+			multiple name nohref noshade nowrap prompt
+			readonly rel rev rows rowspan rules scope
+			selected shape size span src start summary
+			tabindex target title type usemap valign
+			value vspace width
+		}}],
+	);
+	return $_scrubber;
+} # }}}
+
 sub htmlize ($$) { #{{{
 	my $type=shift;
 	my $content=shift;
@@ -28,11 +64,17 @@ sub htmlize ($$) { #{{{
 	}
 	
 	if ($type eq '.mdwn') {
-		return Markdown::Markdown($content);
+		$content=Markdown::Markdown($content);
 	}
 	else {
 		error("htmlization of $type not supported");
 	}
+
+	if ($config{sanitize}) {
+		$content=scrubber()->scrub($content);
+	}
+	
+	return $content;
 } #}}}
 
 sub backlinks ($) { #{{{
@@ -86,12 +128,11 @@ sub rsspage ($) { #{{{
 	return $page.".rss";
 } #}}}
 
-sub postprocess { #{{{
-	# Takes content to postprocess followed by a list of postprocessor
-	# commands and subroutine references to run for the commands.
+sub preprocess ($$) { #{{{
 	my $page=shift;
 	my $content=shift;
-	my %commands=@_;
+
+	my %commands=(inline => \&preprocess_inline);
 	
 	my $handle=sub {
 		my $escape=shift;
@@ -146,7 +187,7 @@ sub get_inline_content ($$) { #{{{
 	}
 } #}}}
 
-sub postprocess_html_inline { #{{{
+sub preprocess_inline ($@) { #{{{
 	my $parentpage=shift;
 	my %params=@_;
 	
@@ -160,7 +201,7 @@ sub postprocess_html_inline { #{{{
 		$params{show}=10;
 	}
 	$inlinepages{$parentpage}=$params{pages};
-	
+
 	my $ret="";
 	
 	if (exists $params{rootpage}) {
@@ -177,8 +218,10 @@ sub postprocess_html_inline { #{{{
 				? "$config{templatedir}/inlinepage.tmpl"
 				: "$config{templatedir}/inlinepagetitle.tmpl"));
 	
+	my @pages;
 	foreach my $page (blog_list($params{pages}, $params{show})) {
 		next if $page eq $parentpage;
+		push @pages, $page;
 		$template->param(pagelink => htmllink($parentpage, $page));
 		$template->param(content => get_inline_content($parentpage, $page))
 			if $params{archive} eq "no";
@@ -186,7 +229,15 @@ sub postprocess_html_inline { #{{{
 		$ret.=$template->output;
 	}
 	
-	return "</p>$ret<p>";
+	# TODO: should really add this to renderedfiles and call
+	# check_overwrite, but currently renderedfiles
+	# only supports listing one file per page.
+	if ($config{rss}) {
+		writefile(rsspage($parentpage), $config{destdir},
+			genrss($parentpage, @pages));
+	}
+	
+	return $ret;
 } #}}}
 
 sub genpage ($$$) { #{{{
@@ -194,8 +245,6 @@ sub genpage ($$$) { #{{{
 	my $page=shift;
 	my $mtime=shift;
 
-	$content = postprocess($page, $content, inline => \&postprocess_html_inline);
-	
 	my $title=pagetitle(basename($page));
 	
 	my $template=HTML::Template->new(blind_cache => 1,
@@ -214,6 +263,9 @@ sub genpage ($$$) { #{{{
 		$u=~s/\[\[file\]\]/$pagesources{$page}/g;
 		$template->param(historyurl => $u);
 	}
+	if ($config{hyperestraier}) {
+		$template->param(hyperestraierurl => cgiurl());
+	}
 
 	if ($config{rss} && $inlinepages{$page}) {
 		$template->param(rssurl => rsspage(basename($page)));
@@ -252,10 +304,9 @@ sub absolute_urls ($$) { #{{{
 	return $content;
 } #}}}
 
-sub genrss ($$$) { #{{{
-	my $content=shift;
+sub genrss ($@) { #{{{
 	my $page=shift;
-	my $mtime=shift;
+	my @pages=@_;
 	
 	my $url="$config{url}/".htmlpage($page);
 	
@@ -263,33 +314,14 @@ sub genrss ($$$) { #{{{
 		filename => "$config{templatedir}/rsspage.tmpl");
 	
 	my @items;
-	my $isblog=0;
-	my $gen_blog=sub {
-		my $parentpage=shift;
-		my %params=@_;
-		
-		if (! exists $params{show}) {
-			$params{show}=10;
-		}
-		if (! exists $params{pages}) {
-			return "";
-		}
-		
-		$isblog=1;
-		foreach my $page (blog_list($params{pages}, $params{show})) {
-			next if $page eq $parentpage;
-			push @items, {
-				itemtitle => pagetitle(basename($page)),
-				itemurl => "$config{url}/$renderedfiles{$page}",
-				itempubdate => date_822($pagectime{$page}),
-				itemcontent => absolute_urls(get_inline_content($parentpage, $page), $url),
-			} if exists $renderedfiles{$page};
-		}
-		
-		return "";
-	};
-	
-	$content = postprocess($page, $content, inline => $gen_blog);
+	foreach my $p (@pages) {
+		push @items, {
+			itemtitle => pagetitle(basename($p)),
+			itemurl => "$config{url}/$renderedfiles{$p}",
+			itempubdate => date_822($pagectime{$p}),
+			itemcontent => absolute_urls(get_inline_content($page, $p), $url),
+		} if exists $renderedfiles{$p};
+	}
 
 	$template->param(
 		title => $config{wikiname},
@@ -338,14 +370,15 @@ sub render ($) { #{{{
 	
 	my $type=pagetype($file);
 	my $srcfile=srcfile($file);
-	my $content=readfile($srcfile);
 	if ($type ne 'unknown') {
+		my $content=readfile($srcfile);
 		my $page=pagename($file);
 		
 		$links{$page}=[findlinks($content, $page)];
 		delete $inlinepages{$page};
 		
 		$content=linkify($content, $page);
+		$content=preprocess($page, $content);
 		$content=htmlize($type, $content);
 		
 		check_overwrite("$config{destdir}/".htmlpage($page), $page);
@@ -353,19 +386,12 @@ sub render ($) { #{{{
 			genpage($content, $page, mtime($srcfile)));
 		$oldpagemtime{$page}=time;
 		$renderedfiles{$page}=htmlpage($page);
-
-		# TODO: should really add this to renderedfiles and call
-		# check_overwrite, as above, but currently renderedfiles
-		# only supports listing one file per page.
-		if ($config{rss} && exists $inlinepages{$page}) {
-			writefile(rsspage($page), $config{destdir},
-				genrss($content, $page, mtime($srcfile)));
-		}
 	}
 	else {
+		my $content=readfile($srcfile, 1);
 		$links{$file}=[];
 		check_overwrite("$config{destdir}/$file", $file);
-		writefile($file, $config{destdir}, $content);
+		writefile($file, $config{destdir}, $content, 1);
 		$oldpagemtime{$file}=time;
 		$renderedfiles{$file}=$file;
 	}
@@ -381,6 +407,57 @@ sub prune ($) { #{{{
 	}
 } #}}}
 
+sub estcfg () { #{{{
+	my $estdir="$config{wikistatedir}/hyperestraier";
+	my $cgi=basename($config{cgiurl});
+	$cgi=~s/\..*$//;
+	open(TEMPLATE, ">$estdir/$cgi.tmpl") ||
+		error("write $estdir/$cgi.tmpl: $!");
+	print TEMPLATE misctemplate("search", 
+		"<!--ESTFORM-->\n\n<!--ESTRESULT-->\n\n<!--ESTINFO-->\n\n");
+	close TEMPLATE;
+	open(TEMPLATE, ">$estdir/$cgi.conf") ||
+		error("write $estdir/$cgi.conf: $!");
+	my $template=HTML::Template->new(
+		filename => "$config{templatedir}/estseek.conf"
+	);
+	eval q{use Cwd 'abs_path'};
+	$template->param(
+		index => $estdir,
+		tmplfile => "$estdir/$cgi.tmpl",
+		destdir => abs_path($config{destdir}),
+		url => $config{url},
+	);
+	print TEMPLATE $template->output;
+	close TEMPLATE;
+	$cgi="$estdir/".basename($config{cgiurl});
+	unlink($cgi);
+	symlink("/usr/lib/estraier/estseek.cgi", $cgi) ||
+		error("symlink $cgi: $!");
+} # }}}
+
+sub estcmd ($;@) { #{{{
+	my @params=split(' ', shift);
+	push @params, "-cl", "$config{wikistatedir}/hyperestraier";
+	if (@_) {
+		push @params, "-";
+	}
+	
+	my $pid=open(CHILD, "|-");
+	if ($pid) {
+		# parent
+		foreach (@_) {
+			print CHILD "$_\n";
+		}
+		close(CHILD) || error("estcmd @params exited nonzero: $?");
+	}
+	else {
+		# child
+		open(STDOUT, "/dev/null"); # shut it up (closing won't work)
+		exec("estcmd", @params) || error("can't run estcmd");
+	}
+} #}}}
+
 sub refresh () { #{{{
 	# find existing pages
 	my %exists;
@@ -505,6 +582,7 @@ FILE:		foreach my $file (@files) {
 					if (globlist_match($page, $inlinepages{$p})) {
 						debug("rendering $f, which inlines $page");
 						render($f);
+						$rendered{$f}=1;
 						last;
 					}
 				}
@@ -539,9 +617,25 @@ FILE:		foreach my $file (@files) {
 			if (defined $linkfile) {
 				debug("rendering $linkfile, to update its backlinks");
 				render($linkfile);
+				$rendered{$linkfile}=1;
 			}
 		}
 	}
+
+	if ($config{hyperestraier} && (%rendered || @del)) {
+		debug("updating hyperestraier search index");
+		if (%rendered) {
+			estcmd("gather -cm -bc -cl -sd", 
+				map { $config{destdir}."/".$renderedfiles{pagename($_)} }
+				keys %rendered);
+		}
+		if (@del) {
+			estcmd("purge -cl");
+		}
+		
+		debug("generating hyperestraier cgi config");
+		estcfg();
+	}
 } #}}}
 
 1