cherry-pick uri security fix

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

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index d77ab809b7f67ae0e7d3d86842e12ea06a00736b..25caa8a506cdf5ab8ea0c9b0d3e9e935f62bd6f8 100644 (file)
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -3,11 +3,10 @@ package IkiWiki::Plugin::htmlscrubber;
 
 use warnings;
 use strict;
 
 use warnings;
 use strict;

-use IkiWiki;
+use IkiWiki 2.00;

 
 sub import { #{{{
 
 sub import { #{{{

-       IkiWiki::hook(type => "sanitize", id => "htmlscrubber",
-               call => \&sanitize);
+       hook(type => "sanitize", id => "htmlscrubber", call => \&sanitize);

 } # }}}
 
 sub sanitize (@) { #{{{
 } # }}}
 
 sub sanitize (@) { #{{{


@@ -19,32 +18,65 @@ my $_scrubber;
 sub scrubber { #{{{
        return $_scrubber if defined $_scrubber;
        
 sub scrubber { #{{{
        return $_scrubber if defined $_scrubber;
        

+       # 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("|",
+               # 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",
+               # data is a special case. Allow data:text/<image>, but
+               # disallow data:text/javascript and everything else.
+               qr/data:text\/(?:png|gif|jpeg)/,
+               # Selected unofficial schemes
+               "about", "aim", "callto", "cvs", "ed2k", "feed", "fish", "gg",
+               "irc", "ircs", "lastfm", "ldaps", "magnet", "mms",
+               "msnim", "notes", "rsync", "secondlife", "skype", "ssh",
+               "sftp", "sms", "steam", "webcal", "ymsgr",
+       );
+       my $link=qr/^(?:$uri_schemes:|[^:]+$)/i;
+

        eval q{use HTML::Scrubber};
        eval q{use HTML::Scrubber};

+       error($@) if $@;

        # Lists based on http://feedparser.org/docs/html-sanitization.html
        # Lists based on http://feedparser.org/docs/html-sanitization.html

+       # With html 5 video and audio tags added.

        $_scrubber = HTML::Scrubber->new(
                allow => [qw{
        $_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
                        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
                        span strike strong sub sup table tbody td textarea
                        tfoot th thead tr tt u ul var

+                       video audio

                }],
                }],

-               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 cite class
+                               clear cols colspan color compact coords
+                               datetime dir disabled enctype for frame
+                               headers height 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 start summary
+                               tabindex target title type usemap valign
+                               value vspace width
+                               autoplay loopstart loopend end
+                               playcount controls 
+                       } ),
+                       "/" => 1, # emit proper <hr /> XHTML
+                       href => $link,
+                       src => $link,
+                       action => $link,
+                       poster => $link,

                }],
        );
        return $_scrubber;
                }],
        );
        return $_scrubber;