+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",
+ "bitcoin", "git", "svn", "bzr", "darcs", "hg"
+ );
+ # 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 (@) {