X-Git-Url: https://sipb.mit.edu/gitweb.cgi/ikiwiki.git/blobdiff_plain/4bfdbd4858bc7842df97902e0bc9bd5d2bef861e..80f2042464f9d14bcaed999e9769c71618bf5252:/IkiWiki/Plugin/htmlscrubber.pm

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index 8c37f1be6..1604d776a 100644
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -3,19 +3,20 @@ package IkiWiki::Plugin::htmlscrubber;
 
 use warnings;
 use strict;
-use IkiWiki 2.00;
+use IkiWiki 3.00;
 
 # This regexp matches urls that are in a known safe scheme.
 # Feel free to use it from other plugins.
 our $safe_url_regexp;
 
-sub import { #{{{
+sub import {
+	hook(type => "getsetup", id => "htmlscrubber", call => \&getsetup);
 	hook(type => "sanitize", id => "htmlscrubber", call => \&sanitize);
 
 	# Only known uri schemes are allowed to avoid all the ways of
 	# embedding javascrpt.
 	# List at http://en.wikipedia.org/wiki/URI_scheme
-	my $uri_schemes=join("|",
+	my $uri_schemes=join("|", map quotemeta,
 		# IANA registered schemes
 		"http", "https", "ftp", "mailto", "file", "telnet", "gopher",
 		"aaa", "aaas", "acap", 	"cap", "cid", "crid", 
@@ -27,26 +28,51 @@ sub import { #{{{
 		"aim", "callto", "cvs", "ed2k", "feed", "fish", "gg",
 		"irc", "ircs", "lastfm", "ldaps", "magnet", "mms",
 		"msnim", "notes", "rsync", "secondlife", "skype", "ssh",
-		"sftp", "sms", "steam", "webcal", "ymsgr",
+		"sftp", "smb", "sms", "snews", "webcal", "ymsgr",
 	);
-	# data is a special case. Allow data:image/*, but
-	# disallow data:text/javascript and everything else.
-	$safe_url_regexp=qr/^(?:(?:$uri_schemes):|data:image\/|[^:]+$)/i;
-} # }}}
+	# data is a special case. Allow a few data:image/ types,
+	# but disallow data:text/javascript and everything else.
+	$safe_url_regexp=qr/^(?:(?:$uri_schemes):|data:image\/(?:png|jpeg|gif)|[^:]+(?:$|[\/\?]))/i;
+}
 
-sub sanitize (@) { #{{{
+sub getsetup () {
+	return
+		plugin => {
+			safe => 1,
+			rebuild => undef,
+			section => "core",
+		},
+		htmlscrubber_skip => {
+			type => "pagespec",
+			example => "!*/Discussion",
+			description => "PageSpec specifying pages not to scrub",
+			link => "ikiwiki/PageSpec",
+			safe => 1,
+			rebuild => undef,
+		},
+}
+
+sub sanitize (@) {
 	my %params=@_;
+
+	if (exists $config{htmlscrubber_skip} &&
+	    length $config{htmlscrubber_skip} &&
+	    exists $params{destpage} &&
+	    pagespec_match($params{destpage}, $config{htmlscrubber_skip})) {
+		return $params{content};
+	}
+
 	return scrubber()->scrub($params{content});
-} # }}}
+}
 
 my $_scrubber;
-sub scrubber { #{{{
+sub scrubber {
 	return $_scrubber if defined $_scrubber;
 
 	eval q{use HTML::Scrubber};
 	error($@) if $@;
 	# Lists based on http://feedparser.org/docs/html-sanitization.html
-	# With html 5 video and audio tags added.
+	# With html5 tags added.
 	$_scrubber = HTML::Scrubber->new(
 		allow => [qw{
 			a abbr acronym address area b big blockquote br br/
@@ -56,7 +82,9 @@ sub scrubber { #{{{
 			menu ol optgroup option p p/ pre q s samp select small
 			span strike strong sub sup table tbody td textarea
 			tfoot th thead tr tt u ul var
-			video audio
+
+			video audio section nav article aside hgroup header
+			footer time mark
 		}],
 		default => [undef, { (
 			map { $_ => 1 } qw{
@@ -72,8 +100,9 @@ sub scrubber { #{{{
 				selected shape size span start summary
 				tabindex target title type valign
 				value vspace width
+
 				autoplay loopstart loopend end
-				playcount controls 
+				playcount controls pubdate
 			} ),
 			"/" => 1, # emit proper <hr /> XHTML
 			href => $safe_url_regexp,
@@ -86,6 +115,6 @@ sub scrubber { #{{{
 		}],
 	);
 	return $_scrubber;
-} # }}}
+}
 
 1