X-Git-Url: http://git.vanrenterghem.biz/git.ikiwiki.info.git/blobdiff_plain/4c1a4402f92204abee5a9425e74864825799f5d2..3096c8ea69783b1c1cfbf5b9f940d2939d2a33f5:/IkiWiki/Plugin/htmlscrubber.pm?ds=sidebyside

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index bc613f924..3bdaccea1 100644
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -5,8 +5,33 @@ use warnings;
 use strict;
 use IkiWiki 2.00;
 
+# 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 { #{{{
 	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 data:image/*, but
+	# disallow data:text/javascript and everything else.
+	$safe_url_regexp=qr/^(?:(?:$uri_schemes):|data:image\/|[^:]+(?:$|\/))/i;
 } # }}}
 
 sub sanitize (@) { #{{{
@@ -17,7 +42,7 @@ sub sanitize (@) { #{{{
 my $_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
@@ -35,23 +60,30 @@ sub scrubber { #{{{
 		}],
 		default => [undef, { (
 			map { $_ => 1 } qw{
-				abbr accept accept-charset accesskey action
+				abbr accept accept-charset accesskey
 				align alt axis border cellpadding cellspacing
-				char charoff charset checked cite class
+				char charoff charset checked 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
+				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 src start summary
-				tabindex target title type usemap valign
+				selected shape size span start summary
+				tabindex target title type valign
 				value vspace width
-				poster autoplay loopstart loopend end
+				autoplay loopstart loopend end
 				playcount controls 
 			} ),
 			"/" => 1, # emit proper <hr /> XHTML
-			}],
+			href => $safe_url_regexp,
+			src => $safe_url_regexp,
+			action => $safe_url_regexp,
+			cite => $safe_url_regexp,
+			longdesc => $safe_url_regexp,
+			poster => $safe_url_regexp,
+			usemap => $safe_url_regexp,
+		}],
 	);
 	return $_scrubber;
 } # }}}