Put newly aggregated pages in the transient underlay

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

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index d795da3a93565929e5468672705662e259f812f0..a58a27d5221acc50e932057b9fabaffcf38c7b97 100644 (file)
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -3,50 +3,76 @@ 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", 
                "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",
+               "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", "sms", "snews", "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 $params{page} &&
+           pagespec_match($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 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 +82,10 @@ 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 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{
@@ -72,13 +101,19 @@ sub scrubber { #{{{
                                selected shape size span start summary
                                tabindex target title type valign
                                value vspace width
-                               autoplay loopstart loopend end
-                               playcount controls 
+
+                               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,
@@ -86,6 +121,6 @@ sub scrubber { #{{{
                }],
        );
        return $_scrubber;
-} # }}}
+}
 
 1