X-Git-Url: http://git.vanrenterghem.biz/git.ikiwiki.info.git/blobdiff_plain/4895955ceaf264c5f17b10c4009e1ab1afcc55ee..84a0b15eb68917829267bacac005f2bcefee914a:/IkiWiki/Plugin/htmlscrubber.pm?ds=sidebyside

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index d77ab809b..a58a27d52 100644
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -3,51 +3,124 @@ package IkiWiki::Plugin::htmlscrubber;
 
 use warnings;
 use strict;
-use IkiWiki;
+use IkiWiki 3.00;
 
-sub import { #{{{
-	IkiWiki::hook(type => "sanitize", id => "htmlscrubber",
-		call => \&sanitize);
-} # }}}
+# This regexp matches urls that are in a known safe scheme.
+# Feel free to use it from other plugins.
+our $safe_url_regexp;
 
-sub sanitize (@) { #{{{
+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("|", map quotemeta,
+		# IANA registered schemes
+		"http", "https", "ftp", "mailto", "file", "telnet", "gopher",
+		"aaa", "aaas", "acap", 	"cap", "cid", "crid", 
+		"dav", "dict", "dns", "fax", "go", "h323", "im", "imap",
+		"ldap", "mid", "news", "nfs", "nntp", "pop", "pres",
+		"sip", "sips", "snmp", "tel", "urn", "wais", "xmpp",
+		"z39.50r", "z39.50s",
+		# Selected unofficial schemes
+		"aim", "callto", "cvs", "ed2k", "feed", "fish", "gg",
+		"irc", "ircs", "lastfm", "ldaps", "magnet", "mms",
+		"msnim", "notes", "rsync", "secondlife", "skype", "ssh",
+		"sftp", "smb", "sms", "snews", "webcal", "ymsgr",
+	);
+	# 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 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 $params{page} &&
+	    pagespec_match($params{page}, $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 html5 tags added.
 	$_scrubber = HTML::Scrubber->new(
 		allow => [qw{
-			a abbr acronym address area b big blockquote br
+			a abbr acronym address area b big blockquote br 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
+			h5 h6 hr hr/ i img input ins kbd label legend li map
+			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 source section nav article aside hgroup
+			header footer figure figcaption time mark canvas
+			datalist progress meter ruby rt rp details summary
 		}],
-		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
-		}, "/" => 1, # emit proper <hr /> XHTML
+		default => [undef, { (
+			map { $_ => 1 } qw{
+				abbr accept accept-charset accesskey
+				align alt axis border cellpadding cellspacing
+				char charoff charset checked class
+				clear cols colspan color compact coords
+				datetime dir disabled enctype for frame
+				headers height hreflang hspace id ismap
+				label lang maxlength media method
+				multiple name nohref noshade nowrap prompt
+				readonly rel rev rows rowspan rules scope
+				selected shape size span start summary
+				tabindex target title type valign
+				value vspace width
+
+				autofocus autoplay preload loopstart
+				loopend end playcount controls pubdate
+				placeholder min max step low high optimum
+				form required autocomplete novalidate pattern
+				list formenctype formmethod formnovalidate
+				formtarget reversed spellcheck open hidden
+			} ),
+			"/" => 1, # emit proper <hr /> XHTML
+			href => $safe_url_regexp,
+			src => $safe_url_regexp,
+			action => $safe_url_regexp,
+			formaction => $safe_url_regexp,
+			cite => $safe_url_regexp,
+			longdesc => $safe_url_regexp,
+			poster => $safe_url_regexp,
+			usemap => $safe_url_regexp,
 		}],
 	);
 	return $_scrubber;
-} # }}}
+}
 
 1