X-Git-Url: http://git.vanrenterghem.biz/git.ikiwiki.info.git/blobdiff_plain/d7e0c035e55e8b47a9ea7e993c9332a7ce9930e1..769be3d48e5612a73232b868cbd6cd35ab3515df:/IkiWiki/Plugin/htmlscrubber.pm?ds=sidebyside diff --git a/IkiWiki/Plugin/htmlscrubber.pm b/IkiWiki/Plugin/htmlscrubber.pm index 25caa8a50..7398c8478 100644 --- a/IkiWiki/Plugin/htmlscrubber.pm +++ b/IkiWiki/Plugin/htmlscrubber.pm @@ -5,23 +5,18 @@ 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 $safe_url_regexp; + sub import { #{{{ + hook(type => "getsetup", id => "htmlscrubber", call => \&getsetup); hook(type => "sanitize", id => "htmlscrubber", call => \&sanitize); -} # }}} - -sub sanitize (@) { #{{{ - my %params=@_; - return scrubber()->scrub($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", @@ -29,16 +24,49 @@ sub scrubber { #{{{ "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/, 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", + "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", ); - my $link=qr/^(?:$uri_schemes:|[^:]+$)/i; + # 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; +} # }}} + +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 $@; @@ -59,24 +87,27 @@ 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;