htmlscrubber: Allow colons in url fragments after '?'

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

diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm
index 8804daf56985fd458ddfb4f598c5c6364cf69443..9f40c752f6b4e96ae2a104231a35b95a0746d4e3 100644 (file)
--- a/IkiWiki/Plugin/htmlscrubber.pm
+++ b/IkiWiki/Plugin/htmlscrubber.pm
@@ -3,44 +3,70 @@ 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", "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 $params{destpage} &&
+           pagespec_match($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};
@@ -86,6 +112,6 @@ sub scrubber { #{{{
                }],
        );
        return $_scrubber;
-} # }}}
+}
 
 1