array (), 'a' => array ( 'class' => array (), 'href' => array (), 'title' => array (), 'rel' => array (), 'rev' => array (), 'name' => array (), 'target' => array()), 'abbr' => array ( 'title' => array ()), 'acronym' => array ( 'title' => array ()), 'b' => array (), 'big' => array (), 'blockquote' => array ( 'cite' => array ()), 'br' => array (), 'button' => array ( 'disabled' => array (), 'name' => array (), 'type' => array (), 'value' => array ()), 'caption' => array ( 'align' => array ()), 'cite' => array ( 'dir' => array(), 'lang' => array(), 'title' => array ()), 'code' => array (), 'col' => array ( 'align' => array (), 'char' => array (), 'charoff' => array (), 'span' => array (), 'dir' => array(), 'valign' => array (), 'width' => array ()), 'del' => array ( 'datetime' => array ()), 'dd' => array (), 'div' => array ( 'align' => array (), 'class' => array (), 'dir' => array ()), 'dl' => array (), 'dt' => array (), 'em' => array (), 'fieldset' => array (), 'font' => array ( 'color' => array (), 'face' => array (), 'size' => array ()), 'form' => array ( 'action' => array (), 'accept' => array (), 'accept-charset' => array (), 'enctype' => array (), 'method' => array (), 'name' => array (), 'target' => array ()), 'h1' => array ( 'align' => array ()), 'h2' => array ( 'align' => array ()), 'h3' => array ( 'align' => array ()), 'h4' => array ( 'align' => array ()), 'h5' => array ( 'align' => array ()), 'h6' => array ( 'align' => array ()), 'hr' => array ( 'align' => array (), 'noshade' => array (), 'size' => array (), 'width' => array ()), 'i' => array (), 'iframe' => array ( // This is filtered to whitelisted domains later according to Andy 'longdesc' => array(), 'name' => array(), 'src' => array(), 'frameborder' => array(), 'marginwidth' => array(), 'marginheight' => array(), 'scroll' => array(), 'scrolling' => array(), 'align' => array(), 'height' => array(), 'width' => array ()), 'img' => array ( 'alt' => array (), 'align' => array (), 'border' => array (), 'height' => array (), 'hspace' => array (), 'longdesc' => array (), 'vspace' => array (), 'src' => array (), 'width' => array ()), 'ins' => array ( 'datetime' => array (), 'cite' => array ()), 'kbd' => array (), 'label' => array ( 'for' => array ()), 'legend' => array ( 'align' => array ()), 'li' => array ( 'align' => array (), 'class' => array ()), 'p' => array ( 'class' => array (), 'align' => array (), 'dir' => array()), 'pre' => array ( 'width' => array ()), 'q' => array ( 'cite' => array ()), 's' => array (), 'strike' => array (), 'strong' => array (), 'sub' => array (), 'sup' => array (), 'table' => array ( 'align' => array (), 'bgcolor' => array (), 'border' => array (), 'cellpadding' => array (), 'cellspacing' => array (), 'dir' => array(), 'rules' => array (), 'summary' => array (), 'width' => array ()), 'tbody' => array ( 'align' => array (), 'char' => array (), 'charoff' => array (), 'valign' => array ()), 'td' => array ( 'abbr' => array (), 'align' => array (), 'axis' => array (), 'bgcolor' => array (), 'char' => array (), 'charoff' => array (), 'colspan' => array (), 'dir' => array(), 'headers' => array (), 'height' => array (), 'nowrap' => array (), 'rowspan' => array (), 'scope' => array (), 'valign' => array (), 'width' => array ()), 'textarea' => array ( 'cols' => array (), 'rows' => array (), 'disabled' => array (), 'name' => array (), 'readonly' => array ()), 'tfoot' => array ( 'align' => array (), 'char' => array (), 'charoff' => array (), 'valign' => array ()), 'th' => array ( 'abbr' => array (), 'align' => array (), 'axis' => array (), 'bgcolor' => array (), 'char' => array (), 'charoff' => array (), 'colspan' => array (), 'headers' => array (), 'height' => array (), 'nowrap' => array (), 'rowspan' => array (), 'scope' => array (), 'valign' => array (), 'width' => array ()), 'thead' => array ( 'align' => array (), 'char' => array (), 'charoff' => array (), 'valign' => array ()), 'title' => array (), 'tr' => array ( 'align' => array (), 'bgcolor' => array (), 'char' => array (), 'charoff' => array (), 'valign' => array ()), 'tt' => array (), 'u' => array (), 'ul' => array (), 'ol' => array (), 'var' => array ()); $allowedtags = array ( 'a' => array ( 'href' => array (), 'title' => array ()), 'abbr' => array ( 'title' => array ()), 'acronym' => array ( 'title' => array ()), 'b' => array (), 'blockquote' => array ( 'cite' => array ()), // 'br' => array(), 'cite' => array (), 'code' => array (), 'del' => array( 'datetime' => array ()), // 'dd' => array(), // 'dl' => array(), // 'dt' => array(), 'em' => array (), 'i' => array (), // 'ins' => array('datetime' => array(), 'cite' => array()), // 'li' => array(), // 'ol' => array(), // 'p' => array(), 'q' => array( 'cite' => array ()), 'strike' => array (), 'strong' => array (), // 'sub' => array(), // 'sup' => array(), // 'u' => array(), // 'ul' => array(), ); } function wp_kses($string, $allowed_html, $allowed_protocols = array ('http', 'https', 'ftp', 'news', 'nntp', 'telnet', 'feed', 'gopher', 'mailto')) ############################################################################### # This function makes sure that only the allowed HTML element names, attribute # names and attribute values plus only sane HTML entities will occur in # $string. You have to remove any slashes from PHP's magic quotes before you # call this function. ############################################################################### { $string = wp_kses_no_null($string); $string = wp_kses_js_entities($string); $string = wp_kses_normalize_entities($string); $string = wp_kses_hook($string); $allowed_html_fixed = wp_kses_array_lc($allowed_html); return wp_kses_split($string, $allowed_html_fixed, $allowed_protocols); } # function wp_kses function wp_kses_hook($string) ############################################################################### # You add any kses hooks here. ############################################################################### { $string = apply_filters('pre_kses', $string); return $string; } # function wp_kses_hook function wp_kses_version() ############################################################################### # This function returns kses' version number. ############################################################################### { return '0.2.2'; } # function wp_kses_version function wp_kses_split($string, $allowed_html, $allowed_protocols) ############################################################################### # This function searches for HTML tags, no matter how malformed. It also # matches stray ">" characters. ############################################################################### { return preg_replace('%((|$))|(<[^>]*(>|$)|>))%e', "wp_kses_split2('\\1', \$allowed_html, ".'$allowed_protocols)', $string); } # function wp_kses_split function wp_kses_split2($string, $allowed_html, $allowed_protocols) ############################################################################### # This function does a lot of work. It rejects some very malformed things # like <:::>. It returns an empty string, if the element isn't allowed (look # ma, no strip_tags()!). Otherwise it splits the tag into an element and an # attribute list. ############################################################################### { $string = wp_kses_stripslashes($string); if (substr($string, 0, 1) != '<') return '>'; # It matched a ">" character if (preg_match('%^)?$%', $string, $matches)) { $string = str_replace(array(''), '', $matches[1]); while ( $string != $newstring = wp_kses($string, $allowed_html, $allowed_protocols) ) $string = $newstring; if ( $string == '' ) return ''; return ""; } # Allow HTML comments if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches)) { wp_kses_reject(__('Seriously malformed HTML removed')); return ''; # It's seriously malformed } $slash = trim($matches[1]); $elem = $matches[2]; $attrlist = $matches[3]; if (!@isset($allowed_html[strtolower($elem)])) { wp_kses_reject(sprintf(__('Removed <%1$s%2$s> tag'), $slash, $elem)); return ''; # They are using a not allowed HTML element } if ($slash != '') return "<$slash$elem>"; # No attributes are allowed for closing elements return wp_kses_attr("$slash$elem", $attrlist, $allowed_html, $allowed_protocols); } # function wp_kses_split2 $kses_messages = array(); function wp_kses_reject($message) { global $kses_messages; return; // Disabled if ( count($kses_messages) == 0 ) add_action('save_post', 'wp_kses_save_message'); $kses_messages[] = $message; return ''; } function wp_kses_save_message($id) { global $kses_messages; foreach ( $kses_messages as $text ) $message .= "$text\n"; $kses_messages[] = ""; update_option('kses_message', $message); } function wp_kses_show_message() { $message = get_option('kses_message'); if ( empty($message) ) return; echo "
\n"; echo nl2br($message); echo "
\n"; update_option('kses_message', ''); } function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) ############################################################################### # This function removes all attributes, if none are allowed for this element. # If some are allowed it calls wp_kses_hair() to split them further, and then it # builds up new HTML code from the data that kses_hair() returns. It also # removes "<" and ">" characters, if there are any left. One more thing it # does is to check if the tag has a closing XHTML slash, and if it does, # it puts one in the returned code as well. ############################################################################### { # Is there a closing XHTML slash at the end of the attributes? $xhtml_slash = ''; if (preg_match('%\s/\s*$%', $attr)) $xhtml_slash = ' /'; # Are any attributes allowed at all for this element? if (@ count($allowed_html[strtolower($element)]) == 0) { if ( ! empty($attr) ) wp_kses_reject(sprintf(__('All attributes removed from <%s> tag'), $element)); return "<$element$xhtml_slash>"; } # Split it $attrarr = wp_kses_hair($attr, $allowed_protocols); # Go through $attrarr, and save the allowed attributes for this element # in $attr2 $attr2 = ''; foreach ($attrarr as $arreach) { if (!@ isset ($allowed_html[strtolower($element)][strtolower($arreach['name'])])) { wp_kses_reject(sprintf(__('Attribute %1$s removed from <%2$s> tag'), $arreach['name'], $element)); continue; # the attribute is not allowed } $current = $allowed_html[strtolower($element)][strtolower($arreach['name'])]; if ($current == '') { wp_kses_reject(sprintf(__('Attribute %1$s removed from <%2$s> tag'), $arreach['name'], $element)); continue; # the attribute is not allowed } if (!is_array($current)) $attr2 .= ' '.$arreach['whole']; # there are no checks else { # there are some checks $ok = true; foreach ($current as $currkey => $currval) if (!wp_kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval)) { wp_kses_reject(sprintf(__('Attribute %1$s removed from <%2$s> tag due to illegal value'), $arreach['name'], $element)); $ok = false; break; } if ($ok) $attr2 .= ' '.$arreach['whole']; # it passed them } # if !is_array($current) } # foreach # Remove any "<" or ">" characters $attr2 = preg_replace('/[<>]/', '', $attr2); return "<$element$attr2$xhtml_slash>"; } # function wp_kses_attr function wp_kses_hair($attr, $allowed_protocols) ############################################################################### # This function does a lot of work. It parses an attribute list into an array # with attribute data, and tries to do the right thing even if it gets weird # input. It will add quotes around attribute values that don't have any quotes # or apostrophes around them, to make it easier to produce HTML code that will # conform to W3C's HTML specification. It will also remove bad URL protocols # from attribute values. ############################################################################### { $attrarr = array (); $mode = 0; $attrname = ''; # Loop through the whole attribute list while (strlen($attr) != 0) { $working = 0; # Was the last operation successful? switch ($mode) { case 0 : # attribute name, href for instance if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) { $attrname = $match[1]; $working = $mode = 1; $attr = preg_replace('/^[-a-zA-Z]+/', '', $attr); } break; case 1 : # equals sign or valueless ("selected") if (preg_match('/^\s*=\s*/', $attr)) # equals sign { $working = 1; $mode = 2; $attr = preg_replace('/^\s*=\s*/', '', $attr); break; } if (preg_match('/^\s+/', $attr)) # valueless { $working = 1; $mode = 0; $attrarr[] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); $attr = preg_replace('/^\s+/', '', $attr); } break; case 2 : # attribute value, a URL after href= for instance if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) # "value" { $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols); $attrarr[] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname=\"$thisval\"", 'vless' => 'n'); $working = 1; $mode = 0; $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr); break; } if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) # 'value' { $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols); $attrarr[] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname='$thisval'", 'vless' => 'n'); $working = 1; $mode = 0; $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr); break; } if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) # value { $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols); $attrarr[] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname=\"$thisval\"", 'vless' => 'n'); # We add quotes to conform to W3C's HTML spec. $working = 1; $mode = 0; $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr); } break; } # switch if ($working == 0) # not well formed, remove and try again { $attr = wp_kses_html_error($attr); $mode = 0; } } # while if ($mode == 1) # special case, for when the attribute list ends with a valueless # attribute like "selected" $attrarr[] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); return $attrarr; } # function wp_kses_hair function wp_kses_check_attr_val($value, $vless, $checkname, $checkvalue) ############################################################################### # This function performs different checks for attribute values. The currently # implemented checks are "maxlen", "minlen", "maxval", "minval" and "valueless" # with even more checks to come soon. ############################################################################### { $ok = true; switch (strtolower($checkname)) { case 'maxlen' : # The maxlen check makes sure that the attribute value has a length not # greater than the given value. This can be used to avoid Buffer Overflows # in WWW clients and various Internet servers. if (strlen($value) > $checkvalue) $ok = false; break; case 'minlen' : # The minlen check makes sure that the attribute value has a length not # smaller than the given value. if (strlen($value) < $checkvalue) $ok = false; break; case 'maxval' : # The maxval check does two things: it checks that the attribute value is # an integer from 0 and up, without an excessive amount of zeroes or # whitespace (to avoid Buffer Overflows). It also checks that the attribute # value is not greater than the given value. # This check can be used to avoid Denial of Service attacks. if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) $ok = false; if ($value > $checkvalue) $ok = false; break; case 'minval' : # The minval check checks that the attribute value is a positive integer, # and that it is not smaller than the given value. if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) $ok = false; if ($value < $checkvalue) $ok = false; break; case 'valueless' : # The valueless check checks if the attribute has a value # (like ) or not (