X-Git-Url: https://sipb.mit.edu/gitweb.cgi/ikiwiki.git/blobdiff_plain/d20e24b636c512fb47b2ca42a0677a3bab4d3fcb..73c8209484ac730c82f7c7b749d08a1b3d895ee0:/IkiWiki/Plugin/htmlscrubber.pm diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm index 8136bdadc..cc00fd5ff 100644 --- a/IkiWiki/Plugin/htmlscrubber.pm +++ b/IkiWiki/Plugin/htmlscrubber.pm @@ -3,25 +3,20 @@ package IkiWiki::Plugin::htmlscrubber; use warnings; use strict; -use IkiWiki 2.00; +use IkiWiki 3.00; -sub import { #{{{ - hook(type => "sanitize", id => "htmlscrubber", call => \&sanitize); -} # }}} +# This regexp matches urls that are in a known safe scheme. +# Feel free to use it from other plugins. +our $safe_url_regexp; -sub sanitize (@) { #{{{ - my %params=@_; - return scrubber()->scrub($params{content}); -} # }}} +sub import { + hook(type => "getsetup", id => "htmlscrubber", call => \&getsetup); + hook(type => "sanitize", id => "htmlscrubber", call => \&sanitize); -my $_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("|", + my $uri_schemes=join("|", map quotemeta, # IANA registered schemes "http", "https", "ftp", "mailto", "file", "telnet", "gopher", "aaa", "aaas", "acap", "cap", "cid", "crid", @@ -33,16 +28,51 @@ sub scrubber { #{{{ "aim", "callto", "cvs", "ed2k", "feed", "fish", "gg", "irc", "ircs", "lastfm", "ldaps", "magnet", "mms", "msnim", "notes", "rsync", "secondlife", "skype", "ssh", - "sftp", "sms", "steam", "webcal", "ymsgr", + "sftp", "smb", "sms", "snews", "webcal", "ymsgr", ); - # data is a special case. Allow data:image/*, but - # disallow data:text/javascript and everything else. - my $link=qr/^(?:(?:$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 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 { + 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/ @@ -52,7 +82,9 @@ 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 time mark canvas }], default => [undef, { ( map { $_ => 1 } qw{ @@ -68,20 +100,21 @@ sub scrubber { #{{{ selected shape size span start summary tabindex target title type valign value vspace width - autoplay loopstart loopend end - playcount controls + + autoplay preload loopstart loopend end + playcount controls pubdate } ), "/" => 1, # emit proper
XHTML - href => $link, - src => $link, - action => $link, - cite => $link, - longdesc => $link, - poster => $link, - usemap => $link, + 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