X-Git-Url: https://sipb.mit.edu/gitweb.cgi/ikiwiki.git/blobdiff_plain/a7be7bdf56b60a08a7ae23a17e20d2bad4cc2971..43c647edd31c224e0ca07785ef1ac7e856639c09:/IkiWiki/Plugin/htmlscrubber.pm diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm index e02a8591e..3bdaccea1 100644 --- a/IkiWiki/Plugin/htmlscrubber.pm +++ b/IkiWiki/Plugin/htmlscrubber.pm @@ -5,23 +5,17 @@ use warnings; use strict; use IkiWiki 2.00; +# This regexp matches urls that are in a known safe scheme. +# Feel free to use it from other plugins. +our $safe_url_regexp; + sub import { #{{{ hook(type => "sanitize", id => "htmlscrubber", call => \&sanitize); -} # }}} - -sub sanitize (@) { #{{{ - my %params=@_; - return scrubber()->scrub($params{content}); -} # }}} -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 +27,21 @@ 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\/|[^:]+(?:$|\/))/i; +} # }}} + +sub sanitize (@) { #{{{ + my %params=@_; + return scrubber()->scrub($params{content}); +} # }}} + +my $_scrubber; +sub scrubber { #{{{ + return $_scrubber if defined $_scrubber; eval q{use HTML::Scrubber}; error($@) if $@; @@ -58,24 +62,27 @@ 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
XHTML - href => $link, - src => $link, - action => $link, - poster => $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;