htmlscrubber: Allow html5 semantic tags: section nav article aside hgroup header...

[ikiwiki.git] / IkiWiki / Plugin / htmlscrubber.pm

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index bc613f92477ef55ef384f8a1bbf2887670c0e7a7..1604d776a646af2487eeeb4dd7be8d6fc8c0d89e 100644 (file)
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -3,25 +3,76 @@ package IkiWiki::Plugin::htmlscrubber;
 
 use warnings;
 use strict;
-use IkiWiki 2.00;
+use IkiWiki 3.00;
 
-sub import { #{{{
+# 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 => "getsetup", id => "htmlscrubber", call => \&getsetup);
        hook(type => "sanitize", id => "htmlscrubber", call => \&sanitize);
-} # }}}
 
-sub 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 $params{destpage} &&
+           pagespec_match($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/
@@ -31,29 +82,39 @@ 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{
-                               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
-                               playcount controls 
+
+                               autoplay loopstart loopend end
+                               playcount controls pubdate
                        } ),
                        "/" => 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;
-} # }}}
+}
 
 1