X-Git-Url: http://git.vanrenterghem.biz/git.ikiwiki.info.git/blobdiff_plain/819a31ed24cfb95da7e37a7524ecf0655e106903..584c998753ee44b489c85251e41922109bc61aaf:/IkiWiki/Render.pm?ds=sidebyside

diff --git a/IkiWiki/Render.pm b/IkiWiki/Render.pm
index f9da33e30..02dbd34bd 100644
--- a/IkiWiki/Render.pm
+++ b/IkiWiki/Render.pm
@@ -4,74 +4,37 @@ package IkiWiki;
 
 use warnings;
 use strict;
-use File::Spec;
+use IkiWiki;
+use Encode;
 
-sub linkify ($$) { #{{{
+sub linkify ($$$) { #{{{
+	my $lpage=shift; # the page containing the links
+	my $page=shift; # the page the link will end up on (different for inline)
 	my $content=shift;
-	my $page=shift;
 
 	$content =~ s{(\\?)$config{wiki_link_regexp}}{
-		$2 ? ( $1 ? "[[$2|$3]]" : htmllink($page, titlepage($3), 0, 0, pagetitle($2)))
-		   : ( $1 ? "[[$3]]" :    htmllink($page, titlepage($3)))
+		$2 ? ( $1 ? "[[$2|$3]]" : htmllink($lpage, $page, titlepage($3), 0, 0, pagetitle($2)))
+		   : ( $1 ? "[[$3]]" :    htmllink($lpage, $page, titlepage($3)))
 	}eg;
 	
 	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;
 	
-	if (! $INC{"/usr/bin/markdown"}) {
-		no warnings 'once';
-		$blosxom::version="is a proper perl module too much to ask?";
-		use warnings 'all';
-		do "/usr/bin/markdown";
-	}
-	
-	if ($type eq '.mdwn') {
-		$content=Markdown::Markdown($content);
+	if (exists $hooks{htmlize}{$type}) {
+		$content=$hooks{htmlize}{$type}{call}->($content);
 	}
 	else {
 		error("htmlization of $type not supported");
 	}
 
-	if ($config{sanitize}) {
-		$content=scrubber()->scrub($content);
+	if (exists $hooks{sanitize}) {
+		foreach my $id (keys %{$hooks{sanitize}}) {
+			$content=$hooks{sanitize}{$id}{call}->($content);
+		}
 	}
 	
 	return $content;
@@ -84,7 +47,7 @@ sub backlinks ($) { #{{{
 	foreach my $p (keys %links) {
 		next if bestlink($page, $p) eq $page;
 		if (grep { length $_ && bestlink($p, $_) eq $page } @{$links{$p}}) {
-			my $href=File::Spec->abs2rel(htmlpage($p), dirname($page));
+			my $href=abs2rel(htmlpage($p), dirname($page));
 			
 			# Trim common dir prefixes from both pages.
 			my $p_trimmed=$p;
@@ -109,6 +72,7 @@ sub parentlinks ($) { #{{{
 	my $pagelink="";
 	my $path="";
 	my $skip=1;
+	return if $page eq 'index'; # toplevel
 	foreach my $dir (reverse split("/", $page)) {
 		if (! $skip) {
 			$path.="../";
@@ -122,18 +86,12 @@ sub parentlinks ($) { #{{{
 	return @ret;
 } #}}}
 
-sub rsspage ($) { #{{{
-	my $page=shift;
-
-	return $page.".rss";
-} #}}}
-
-sub preprocess ($$) { #{{{
-	my $page=shift;
+sub preprocess ($$$;$) { #{{{
+	my $page=shift; # the page the data comes from
+	my $destpage=shift; # the page the data will appear in (different for inline)
 	my $content=shift;
+	my $onlystrip=shift || 0; # strip directives without processing
 
-	my %commands=(inline => \&preprocess_inline);
-	
 	my $handle=sub {
 		my $escape=shift;
 		my $command=shift;
@@ -141,15 +99,29 @@ sub preprocess ($$) { #{{{
 		if (length $escape) {
 			return "[[$command $params]]";
 		}
-		elsif (exists $commands{$command}) {
-			my %params;
-			while ($params =~ /(\w+)=\"([^"]+)"(\s+|$)/g) {
-				$params{$1}=$2;
+		elsif ($onlystrip) {
+			return "";
+		}
+		elsif (exists $hooks{preprocess}{$command}) {
+			# Note: preserve order of params, some plugins may
+			# consider it significant.
+			my @params;
+			while ($params =~ /(?:(\w+)=)?(?:"([^"]+)"|(\S+))(?:\s+|$)/g) {
+				if (defined $1) {
+					push @params, $1, (defined $2 ? $2 : $3);
+				}
+				else {
+					push @params, (defined $2 ? $2 : $3), '';
+				}
 			}
-			return $commands{$command}->($page, %params);
+			return $hooks{preprocess}{$command}{call}->(
+				@params,
+				page => $page,
+				destpage => $destpage,
+			);
 		}
 		else {
-			return "[[bad directive $command]]";
+			return "[[$command not processed]]";
 		}
 	};
 	
@@ -157,188 +129,92 @@ sub preprocess ($$) { #{{{
 	return $content;
 } #}}}
 
-sub blog_list ($$) { #{{{
-	my $globlist=shift;
-	my $maxitems=shift;
-	
-	my @list;
-	foreach my $page (keys %pagesources) {
-		if (globlist_match($page, $globlist)) {
-			push @list, $page;
-		}
-	}
-
-	@list=sort { $pagectime{$b} <=> $pagectime{$a} } @list;
-	return @list if ! $maxitems || @list <= $maxitems;
-	return @list[0..$maxitems - 1];
-} #}}}
-
-sub get_inline_content ($$) { #{{{
-	my $parentpage=shift;
+sub add_depends ($$) { #{{{
 	my $page=shift;
+	my $globlist=shift;
 	
-	my $file=$pagesources{$page};
-	my $type=pagetype($file);
-	if ($type ne 'unknown') {
-		return htmlize($type, linkify(readfile(srcfile($file)), $parentpage));
+	if (! exists $depends{$page}) {
+		$depends{$page}=$globlist;
 	}
 	else {
-		return "";
+		$depends{$page}=globlist_merge($depends{$page}, $globlist);
 	}
-} #}}}
+} # }}}
 
-sub preprocess_inline ($@) { #{{{
-	my $parentpage=shift;
-	my %params=@_;
-	
-	if (! exists $params{pages}) {
-		return "";
-	}
-	if (! exists $params{archive}) {
-		$params{archive}="no";
-	}
-	if (! exists $params{show} && $params{archive} eq "no") {
-		$params{show}=10;
-	}
-	if (! exists $depends{$parentpage}) {
-		$depends{$parentpage}=$params{pages};
-	}
-	else {
-		$depends{$parentpage}.=" ".$params{pages};
-	}
+sub globlist_merge ($$) { #{{{
+	my $a=shift;
+	my $b=shift;
 
 	my $ret="";
-	
-	if (exists $params{rootpage}) {
-		# Add a blog post form, with a rss link button.
-		my $formtemplate=HTML::Template->new(blind_cache => 1,
-			filename => "$config{templatedir}/blogpost.tmpl");
-		$formtemplate->param(cgiurl => $config{cgiurl});
-		$formtemplate->param(rootpage => $params{rootpage});
-		if ($config{rss}) {
-			$formtemplate->param(rssurl => rsspage(basename($parentpage)));
+	# Only add negated globs if they are not matched by the other globlist.
+	foreach my $i ((map { [ $a, $_ ] } split(" ", $b)), 
+	               (map { [ $b, $_ ] } split(" ", $a))) {
+		if ($i->[1]=~/^!(.*)/) {
+			if (! globlist_match($1, $i->[0])) {
+				$ret.=" ".$i->[1];
+			}
+		}
+		else {
+			$ret.=" ".$i->[1];
 		}
-		$ret.=$formtemplate->output;
-	}
-	elsif ($config{rss}) {
-		# Add a rss link button.
-		my $linktemplate=HTML::Template->new(blind_cache => 1,
-			filename => "$config{templatedir}/rsslink.tmpl");
-		$linktemplate->param(rssurl => rsspage(basename($parentpage)));
-		$ret.=$linktemplate->output;
-	}
-	
-	my $template=HTML::Template->new(blind_cache => 1,
-		filename => (($params{archive} eq "no") 
-				? "$config{templatedir}/inlinepage.tmpl"
-				: "$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";
-		$template->param(ctime => scalar(gmtime($pagectime{$page})));
-		$ret.=$template->output;
-	}
-	
-	# 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 ($$$) { #{{{
-	my $content=shift;
 	my $page=shift;
+	my $content=shift;
 	my $mtime=shift;
 
-	my $title=pagetitle(basename($page));
-	
-	my $template=HTML::Template->new(blind_cache => 1,
-		filename => "$config{templatedir}/page.tmpl");
-	
+	my $template=template("page.tmpl", blind_cache => 1);
+	my $actions=0;
+
 	if (length $config{cgiurl}) {
 		$template->param(editurl => cgiurl(do => "edit", page => $page));
 		$template->param(prefsurl => cgiurl(do => "prefs"));
 		if ($config{rcs}) {
 			$template->param(recentchangesurl => cgiurl(do => "recentchanges"));
 		}
+		$actions++;
 	}
 
 	if (length $config{historyurl}) {
 		my $u=$config{historyurl};
 		$u=~s/\[\[file\]\]/$pagesources{$page}/g;
 		$template->param(historyurl => $u);
+		$actions++;
+	}
+	if ($config{discussion}) {
+		$template->param(discussionlink => htmllink($page, $page, "Discussion", 1, 1));
+		$actions++;
 	}
-	if ($config{hyperestraier}) {
-		$template->param(hyperestraierurl => cgiurl());
+
+	if ($actions) {
+		$template->param(have_actions => 1);
 	}
 
 	$template->param(
-		title => $title,
+		title => $page eq 'index' 
+			? $config{wikiname} 
+			: pagetitle(basename($page)),
 		wikiname => $config{wikiname},
 		parentlinks => [parentlinks($page)],
 		content => $content,
 		backlinks => [backlinks($page)],
-		discussionlink => htmllink($page, "Discussion", 1, 1),
-		mtime => scalar(gmtime($mtime)),
+		mtime => displaytime($mtime),
 		styleurl => styleurl($page),
 	);
-	
-	return $template->output;
-} #}}}
 
-sub date_822 ($) { #{{{
-	my $time=shift;
-
-	eval q{use POSIX};
-	return POSIX::strftime("%a, %d %b %Y %H:%M:%S %z", localtime($time));
-} #}}}
-
-sub absolute_urls ($$) { #{{{
-	# sucky sub because rss sucks
-	my $content=shift;
-	my $url=shift;
-
-	$url=~s/[^\/]+$//;
-	
-	$content=~s/<a\s+href="(?!http:\/\/)([^"]+)"/<a href="$url$1"/ig;
-	$content=~s/<img\s+src="(?!http:\/\/)([^"]+)"/<img src="$url$1"/ig;
-	return $content;
-} #}}}
-
-sub genrss ($@) { #{{{
-	my $page=shift;
-	my @pages=@_;
-	
-	my $url="$config{url}/".htmlpage($page);
-	
-	my $template=HTML::Template->new(blind_cache => 1,
-		filename => "$config{templatedir}/rsspage.tmpl");
-	
-	my @items;
-	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};
+	if (exists $hooks{pagetemplate}) {
+		foreach my $id (keys %{$hooks{pagetemplate}}) {
+			$hooks{pagetemplate}{$id}{call}->(
+				page => $page,
+				destpage => $page,
+				template => $template,
+			);
+		}
 	}
-
-	$template->param(
-		title => $config{wikiname},
-		pageurl => $url,
-		items => \@items,
-	);
 	
 	return $template->output;
 } #}}}
@@ -350,13 +226,20 @@ sub check_overwrite ($$) { #{{{
 	my $src=shift;
 	
 	if (! exists $renderedfiles{$src} && -e $dest && ! $config{rebuild}) {
-		error("$dest already exists and was rendered from ".
-			join(" ",(grep { $renderedfiles{$_} eq $dest } keys
-				%renderedfiles)).
-			", before, so not rendering from $src");
+		error("$dest already exists and was not rendered from $src before");
 	}
 } #}}}
 
+sub displaytime ($) { #{{{
+	my $time=shift;
+
+	eval q{use POSIX};
+	# strftime doesn't know about encodings, so make sure
+	# its output is properly treated as utf8
+	return decode_utf8(POSIX::strftime(
+			$config{timeformat}, localtime($time)));
+} #}}}
+
 sub mtime ($) { #{{{
 	my $file=shift;
 	
@@ -364,43 +247,67 @@ sub mtime ($) { #{{{
 } #}}}
 
 sub findlinks ($$) { #{{{
-	my $content=shift;
 	my $page=shift;
+	my $content=shift;
 
 	my @links;
 	while ($content =~ /(?<!\\)$config{wiki_link_regexp}/g) {
 		push @links, titlepage($2);
 	}
-	# Discussion links are a special case since they're not in the text
-	# of the page, but on its template.
-	return @links, "$page/discussion";
+	if ($config{discussion}) {
+		# Discussion links are a special case since they're not in the
+		# text of the page, but on its template.
+		return @links, "$page/discussion";
+	}
+	else {
+		return @links;
+	}
 } #}}}
 
+sub filter ($$) {
+	my $page=shift;
+	my $content=shift;
+
+	if (exists $hooks{filter}) {
+		foreach my $id (keys %{$hooks{filter}}) {
+			$content=$hooks{filter}{$id}{call}->(
+				page => $page,
+				content => $content
+			);
+		}
+	}
+
+	return $content;
+}
+
 sub render ($) { #{{{
 	my $file=shift;
 	
 	my $type=pagetype($file);
 	my $srcfile=srcfile($file);
-	if ($type ne 'unknown') {
+	if (defined $type) {
 		my $content=readfile($srcfile);
 		my $page=pagename($file);
-		
-		$links{$page}=[findlinks($content, $page)];
 		delete $depends{$page};
 		
-		$content=linkify($content, $page);
-		$content=preprocess($page, $content);
+		$content=filter($page, $content);
+		
+		$links{$page}=[findlinks($page, $content)];
+		
+		$content=linkify($page, $page, $content);
+		$content=preprocess($page, $page, $content);
 		$content=htmlize($type, $content);
 		
 		check_overwrite("$config{destdir}/".htmlpage($page), $page);
 		writefile(htmlpage($page), $config{destdir},
-			genpage($content, $page, mtime($srcfile)));
+			genpage($page, $content, mtime($srcfile)));
 		$oldpagemtime{$page}=time;
 		$renderedfiles{$page}=htmlpage($page);
 	}
 	else {
 		my $content=readfile($srcfile, 1);
 		$links{$file}=[];
+		delete $depends{$file};
 		check_overwrite("$config{destdir}/$file", $file);
 		writefile($file, $config{destdir}, $content, 1);
 		$oldpagemtime{$file}=time;
@@ -418,57 +325,6 @@ 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;
@@ -477,6 +333,7 @@ sub refresh () { #{{{
 	find({
 		no_chdir => 1,
 		wanted => sub {
+			$_=decode_utf8($_);
 			if (/$config{wiki_file_prune_regexp}/) {
 				$File::Find::prune=1;
 			}
@@ -496,6 +353,7 @@ sub refresh () { #{{{
 	find({
 		no_chdir => 1,
 		wanted => sub {
+			$_=decode_utf8($_);
 			if (/$config{wiki_file_prune_regexp}/) {
 				$File::Find::prune=1;
 			}
@@ -529,8 +387,12 @@ sub refresh () { #{{{
 			push @add, $file;
 			$links{$page}=[];
 			$pagesources{$page}=$file;
-			$pagectime{$page}=mtime(srcfile($file))
-				unless exists $pagectime{$page};
+			if ($config{getctime} && -e "$config{srcdir}/$file") {
+				$pagectime{$page}=rcs_getctime("$config{srcdir}/$file");
+			}
+			elsif (! exists $pagectime{$page}) {
+				$pagectime{$page}=mtime(srcfile($file));
+			}
 		}
 	}
 	my @del;
@@ -551,7 +413,7 @@ sub refresh () { #{{{
 		
 		if (! exists $oldpagemtime{$page} ||
 		    mtime(srcfile($file)) > $oldpagemtime{$page}) {
-		    	debug("rendering changed file $file");
+		    	debug("rendering $file");
 			render($file);
 			$rendered{$file}=1;
 		}
@@ -580,7 +442,7 @@ FILE:		foreach my $file (@files) {
 	}
 
 	# Handle backlinks; if a page has added/removed links, update the
-	# pages it links to. Also handles rebuilding dependat pages.
+	# pages it links to. Also handles rebuilding dependant pages.
 	# TODO: inefficient; pages may get rendered above and again here;
 	# problem is the backlinks could be wrong in the first pass render
 	# above
@@ -589,6 +451,7 @@ FILE:		foreach my $file (@files) {
 			my $p=pagename($f);
 			if (exists $depends{$p}) {
 				foreach my $file (keys %rendered, @del) {
+					next if $f eq $file;
 					my $page=pagename($file);
 					if (globlist_match($page, $depends{$p})) {
 						debug("rendering $f, which depends on $page");
@@ -607,8 +470,8 @@ FILE:		foreach my $file (@files) {
 			if (exists $links{$page}) {
 				foreach my $link (map { bestlink($page, $_) } @{$links{$page}}) {
 					if (length $link &&
-					    ! exists $oldlinks{$page} ||
-					    ! grep { $_ eq $link } @{$oldlinks{$page}}) {
+					    (! exists $oldlinks{$page} ||
+					     ! grep { bestlink($page, $_) eq $link } @{$oldlinks{$page}})) {
 						$linkchanged{$link}=1;
 					}
 				}
@@ -616,8 +479,8 @@ FILE:		foreach my $file (@files) {
 			if (exists $oldlinks{$page}) {
 				foreach my $link (map { bestlink($page, $_) } @{$oldlinks{$page}}) {
 					if (length $link &&
-					    ! exists $links{$page} ||
-					    ! grep { $_ eq $link } @{$links{$page}}) {
+					    (! exists $links{$page} || 
+					     ! grep { bestlink($page, $_) eq $link } @{$links{$page}})) {
 						$linkchanged{$link}=1;
 					}
 				}
@@ -633,19 +496,15 @@ FILE:		foreach my $file (@files) {
 		}
 	}
 
-	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 && exists $hooks{delete}) {
+		foreach my $id (keys %{$hooks{delete}}) {
+			$hooks{delete}{$id}{call}->(@del);
 		}
-		if (@del) {
-			estcmd("purge -cl");
+	}
+	if (%rendered && exists $hooks{change}) {
+		foreach my $id (keys %{$hooks{change}}) {
+			$hooks{change}{$id}{call}->(keys %rendered);
 		}
-		
-		debug("generating hyperestraier cgi config");
-		estcfg();
 	}
 } #}}}