X-Git-Url: http://git.vanrenterghem.biz/git.ikiwiki.info.git/blobdiff_plain/a7be7bdf56b60a08a7ae23a17e20d2bad4cc2971..5c0e56d149c6b33d010561f64f583e7ad1c529da:/IkiWiki/Plugin/htmlscrubber.pm diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm index e02a8591e..a249cdf7a 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", @@ -33,11 +28,45 @@ 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; + $safe_url_regexp=qr/^(?:(?:$uri_schemes):|data:image\/|[^:]+(?:$|\/))/i; +} + +sub getsetup () { + return + plugin => { + safe => 1, + rebuild => undef, + }, + 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 $@; @@ -58,27 +87,30 @@ sub scrubber { #{{{ map { $_ => 1 } qw{ 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 hreflang hspace id ismap - label lang longdesc maxlength media method + label lang 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 + tabindex target title type valign value vspace width autoplay loopstart loopend end playcount controls } ), "/" => 1, # emit proper