X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/76aea3697c6043c1613370f172395b4f65ee71f0..99a64b9fd0d5ebb21c33c3a0b5865e9c412b430c:/wp-includes/kses.php diff --git a/wp-includes/kses.php b/wp-includes/kses.php index c7538b98..3a4da1e3 100644 --- a/wp-includes/kses.php +++ b/wp-includes/kses.php @@ -1,43 +1,50 @@ + * @author Ulf Harnhammar * * @package External * @subpackage KSES * - * @internal - * *** CONTACT INFORMATION *** - * E-mail: metaur at users dot sourceforge dot net - * Web page: http://sourceforge.net/projects/kses - * Paper mail: Ulf Harnhammar - * Ymergatan 17 C - * 753 25 Uppsala - * SWEDEN - * - * [kses strips evil scripts!] */ /** - * You can override this in your my-hacks.php file - * You can also override this in a plugin file. The - * my-hacks.php is deprecated in its usage. + * You can override this in a plugin. * * @since 1.2.0 */ -if (!defined('CUSTOM_TAGS')) - define('CUSTOM_TAGS', false); +if ( ! defined( 'CUSTOM_TAGS' ) ) + define( 'CUSTOM_TAGS', false ); -if (!CUSTOM_TAGS) { +if ( ! CUSTOM_TAGS ) { /** - * Kses global for default allowable HTML tags + * Kses global for default allowable HTML tags. + * + * Can be override by using CUSTOM_TAGS constant. * - * Can be override by using CUSTOM_TAGS constant * @global array $allowedposttags * @since 2.0.0 */ @@ -57,6 +64,22 @@ if (!CUSTOM_TAGS) { 'title' => array ()), 'acronym' => array( 'title' => array ()), + 'article' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), + 'aside' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), 'b' => array(), 'big' => array(), 'blockquote' => array( @@ -94,6 +117,15 @@ if (!CUSTOM_TAGS) { 'del' => array( 'datetime' => array ()), 'dd' => array(), + 'details' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'open' => array (), + 'style' => array (), + 'xml:lang' => array(), + ), 'div' => array( 'align' => array (), 'class' => array (), @@ -105,10 +137,34 @@ if (!CUSTOM_TAGS) { 'dt' => array(), 'em' => array(), 'fieldset' => array(), + 'figure' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), + 'figcaption' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), 'font' => array( 'color' => array (), 'face' => array (), 'size' => array ()), + 'footer' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), 'form' => array( 'action' => array (), 'accept' => array (), @@ -119,23 +175,51 @@ if (!CUSTOM_TAGS) { 'target' => array ()), 'h1' => array( 'align' => array (), - 'class' => array ()), - 'h2' => array( + 'class' => array (), + 'id' => array (), + 'style' => array ()), + 'h2' => array ( 'align' => array (), - 'class' => array ()), - 'h3' => array( + 'class' => array (), + 'id' => array (), + 'style' => array ()), + 'h3' => array ( 'align' => array (), - 'class' => array ()), - 'h4' => array( + 'class' => array (), + 'id' => array (), + 'style' => array ()), + 'h4' => array ( 'align' => array (), - 'class' => array ()), - 'h5' => array( + 'class' => array (), + 'id' => array (), + 'style' => array ()), + 'h5' => array ( 'align' => array (), - 'class' => array ()), - 'h6' => array( + 'class' => array (), + 'id' => array (), + 'style' => array ()), + 'h6' => array ( 'align' => array (), - 'class' => array ()), - 'hr' => array( + 'class' => array (), + 'id' => array (), + 'style' => array ()), + 'header' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), + 'hgroup' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), + 'hr' => array ( 'align' => array (), 'class' => array (), 'noshade' => array (), @@ -165,6 +249,18 @@ if (!CUSTOM_TAGS) { 'li' => array ( 'align' => array (), 'class' => array ()), + 'menu' => array ( + 'class' => array (), + 'style' => array (), + 'type' => array ()), + 'nav' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), 'p' => array( 'class' => array (), 'align' => array (), @@ -186,9 +282,25 @@ if (!CUSTOM_TAGS) { 'style' => array (), 'title' => array (), 'xml:lang' => array()), + 'section' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), 'strike' => array(), 'strong' => array(), 'sub' => array(), + 'summary' => array( + 'align' => array (), + 'class' => array (), + 'dir' => array (), + 'lang' => array(), + 'style' => array (), + 'xml:lang' => array(), + ), 'sup' => array(), 'table' => array( 'align' => array (), @@ -273,16 +385,17 @@ if (!CUSTOM_TAGS) { 'u' => array(), 'ul' => array ( 'class' => array (), - 'style' => array (), + 'style' => array (), 'type' => array ()), 'ol' => array ( 'class' => array (), 'start' => array (), - 'style' => array (), + 'style' => array (), 'type' => array ()), 'var' => array ()); + /** - * Kses allowed HTML elements + * Kses allowed HTML elements. * * @global array $allowedtags * @since 1.0.0 @@ -320,20 +433,64 @@ if (!CUSTOM_TAGS) { // 'u' => array(), // 'ul' => array(), ); + + $allowedentitynames = array( + 'nbsp', 'iexcl', 'cent', 'pound', 'curren', 'yen', + 'brvbar', 'sect', 'uml', 'copy', 'ordf', 'laquo', + 'not', 'shy', 'reg', 'macr', 'deg', 'plusmn', + 'acute', 'micro', 'para', 'middot', 'cedil', 'ordm', + 'raquo', 'iquest', 'Agrave', 'Aacute', 'Acirc', 'Atilde', + 'Auml', 'Aring', 'AElig', 'Ccedil', 'Egrave', 'Eacute', + 'Ecirc', 'Euml', 'Igrave', 'Iacute', 'Icirc', 'Iuml', + 'ETH', 'Ntilde', 'Ograve', 'Oacute', 'Ocirc', 'Otilde', + 'Ouml', 'times', 'Oslash', 'Ugrave', 'Uacute', 'Ucirc', + 'Uuml', 'Yacute', 'THORN', 'szlig', 'agrave', 'aacute', + 'acirc', 'atilde', 'auml', 'aring', 'aelig', 'ccedil', + 'egrave', 'eacute', 'ecirc', 'euml', 'igrave', 'iacute', + 'icirc', 'iuml', 'eth', 'ntilde', 'ograve', 'oacute', + 'ocirc', 'otilde', 'ouml', 'divide', 'oslash', 'ugrave', + 'uacute', 'ucirc', 'uuml', 'yacute', 'thorn', 'yuml', + 'quot', 'amp', 'lt', 'gt', 'apos', 'OElig', + 'oelig', 'Scaron', 'scaron', 'Yuml', 'circ', 'tilde', + 'ensp', 'emsp', 'thinsp', 'zwnj', 'zwj', 'lrm', + 'rlm', 'ndash', 'mdash', 'lsquo', 'rsquo', 'sbquo', + 'ldquo', 'rdquo', 'bdquo', 'dagger', 'Dagger', 'permil', + 'lsaquo', 'rsaquo', 'euro', 'fnof', 'Alpha', 'Beta', + 'Gamma', 'Delta', 'Epsilon', 'Zeta', 'Eta', 'Theta', + 'Iota', 'Kappa', 'Lambda', 'Mu', 'Nu', 'Xi', + 'Omicron', 'Pi', 'Rho', 'Sigma', 'Tau', 'Upsilon', + 'Phi', 'Chi', 'Psi', 'Omega', 'alpha', 'beta', + 'gamma', 'delta', 'epsilon', 'zeta', 'eta', 'theta', + 'iota', 'kappa', 'lambda', 'mu', 'nu', 'xi', + 'omicron', 'pi', 'rho', 'sigmaf', 'sigma', 'tau', + 'upsilon', 'phi', 'chi', 'psi', 'omega', 'thetasym', + 'upsih', 'piv', 'bull', 'hellip', 'prime', 'Prime', + 'oline', 'frasl', 'weierp', 'image', 'real', 'trade', + 'alefsym', 'larr', 'uarr', 'rarr', 'darr', 'harr', + 'crarr', 'lArr', 'uArr', 'rArr', 'dArr', 'hArr', + 'forall', 'part', 'exist', 'empty', 'nabla', 'isin', + 'notin', 'ni', 'prod', 'sum', 'minus', 'lowast', + 'radic', 'prop', 'infin', 'ang', 'and', 'or', + 'cap', 'cup', 'int', 'sim', 'cong', 'asymp', + 'ne', 'equiv', 'le', 'ge', 'sub', 'sup', + 'nsub', 'sube', 'supe', 'oplus', 'otimes', 'perp', + 'sdot', 'lceil', 'rceil', 'lfloor', 'rfloor', 'lang', + 'rang', 'loz', 'spades', 'clubs', 'hearts', 'diams', + ); } /** - * wp_kses() - Filters content and keeps only allowable HTML elements. + * Filters content and keeps only allowable HTML elements. * - * 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. + * 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. * - * The default allowed protocols are 'http', 'https', 'ftp', 'mailto', - * 'news', 'irc', 'gopher', 'nntp', 'feed', and finally 'telnet. This - * covers all common link protocols, except for 'javascript' which - * should not be allowed for untrusted users. + * The default allowed protocols are 'http', 'https', 'ftp', 'mailto', 'news', + * 'irc', 'gopher', 'nntp', 'feed', 'telnet, 'mms', 'rtsp' and 'svn'. This + * covers all common link protocols, except for 'javascript' which should not + * be allowed for untrusted users. * * @since 1.0.0 * @@ -342,7 +499,8 @@ if (!CUSTOM_TAGS) { * @param array $allowed_protocols Optional. Allowed protocol in links. * @return string Filtered content with only allowed HTML elements */ -function wp_kses($string, $allowed_html, $allowed_protocols = array ('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet')) { +function wp_kses($string, $allowed_html, $allowed_protocols = array ()) { + $allowed_protocols = wp_parse_args( $allowed_protocols, apply_filters('kses_allowed_protocols', array ('http', 'https', 'ftp', 'ftps', 'mailto', 'news', 'irc', 'gopher', 'nntp', 'feed', 'telnet', 'mms', 'rtsp', 'svn') )); $string = wp_kses_no_null($string); $string = wp_kses_js_entities($string); $string = wp_kses_normalize_entities($string); @@ -352,11 +510,10 @@ function wp_kses($string, $allowed_html, $allowed_protocols = array ('http', 'ht } /** - * wp_kses_hook() - You add any kses hooks here. + * You add any kses hooks here. * - * There is currently only one kses WordPress hook and it is - * called here. All parameters are passed to the hooks and - * expected to recieve a string. + * There is currently only one kses WordPress hook and it is called here. All + * parameters are passed to the hooks and expected to receive a string. * * @since 1.0.0 * @@ -371,18 +528,18 @@ function wp_kses_hook($string, $allowed_html, $allowed_protocols) { } /** - * wp_kses_version() - This function returns kses' version number. + * This function returns kses' version number. * * @since 1.0.0 * - * @return string Version Number + * @return string KSES Version Number */ function wp_kses_version() { return '0.2.2'; } /** - * wp_kses_split() - Searches for HTML tags, no matter how malformed + * Searches for HTML tags, no matter how malformed. * * It also matches stray ">" characters. * @@ -394,22 +551,36 @@ function wp_kses_version() { * @return string Content with fixed HTML tags */ function wp_kses_split($string, $allowed_html, $allowed_protocols) { - return preg_replace('%((|$))|(<[^>]*(>|$)|>))%e', - "wp_kses_split2('\\1', \$allowed_html, ".'$allowed_protocols)', $string); + global $pass_allowed_html, $pass_allowed_protocols; + $pass_allowed_html = $allowed_html; + $pass_allowed_protocols = $allowed_protocols; + return preg_replace_callback( '%(|$))|(<[^>]*(>|$)|>)%', '_wp_kses_split_callback', $string ); +} + +/** + * Callback for wp_kses_split. + * + * @since 3.1.0 + * @access private + */ +function _wp_kses_split_callback( $match ) { + global $pass_allowed_html, $pass_allowed_protocols; + return wp_kses_split2( $match[0], $pass_allowed_html, $pass_allowed_protocols ); } /** - * wp_kses_split2() - Callback for wp_kses_split for fixing malformed HTML tags + * Callback for wp_kses_split for fixing malformed HTML tags. * - * This function does a lot of work. It rejects some very malformed things - * like <:::>. It returns an empty string, if the element isn't allowed (look - * ma, no strip_tags()!). Otherwise it splits the tag into an element and an - * attribute list. + * This function does a lot of work. It rejects some very malformed things like + * <:::>. It returns an empty string, if the element isn't allowed (look ma, no + * strip_tags()!). Otherwise it splits the tag into an element and an attribute + * list. * * After the tag is split into an element and an attribute list, it is run - * through another filter which will remove illegal attributes and once - * that is completed, will be returned. + * through another filter which will remove illegal attributes and once that is + * completed, will be returned. * + * @access private * @since 1.0.0 * @uses wp_kses_attr() * @@ -425,9 +596,9 @@ function wp_kses_split2($string, $allowed_html, $allowed_protocols) { return '>'; # It matched a ">" character - if (preg_match('%^)?$%', $string, $matches)) { - $string = str_replace(array(''), '', $matches[1]); - while ( $string != $newstring = wp_kses($string, $allowed_html, $allowed_protocols) ) + if ( ''), '', $string ); + while ( $string != ($newstring = wp_kses($string, $allowed_html, $allowed_protocols)) ) $string = $newstring; if ( $string == '' ) return ''; @@ -447,25 +618,25 @@ function wp_kses_split2($string, $allowed_html, $allowed_protocols) { $elem = $matches[2]; $attrlist = $matches[3]; - if (!@isset($allowed_html[strtolower($elem)])) + if ( ! isset($allowed_html[strtolower($elem)]) ) return ''; # They are using a not allowed HTML element if ($slash != '') - return "<$slash$elem>"; + return ""; # No attributes are allowed for closing elements - return wp_kses_attr("$slash$elem", $attrlist, $allowed_html, $allowed_protocols); + return wp_kses_attr( $elem, $attrlist, $allowed_html, $allowed_protocols ); } /** - * wp_kses_attr() - Removes all attributes, if none are allowed for this element + * Removes all attributes, if none are allowed for this element. * * If some are allowed it calls wp_kses_hair() to split them further, and then * it builds up new HTML code from the data that kses_hair() returns. It also - * removes "<" and ">" characters, if there are any left. One more thing it - * does is to check if the tag has a closing XHTML slash, and if it does, it - * puts one in the returned code as well. + * removes "<" and ">" characters, if there are any left. One more thing it does + * is to check if the tag has a closing XHTML slash, and if it does, it puts one + * in the returned code as well. * * @since 1.0.0 * @@ -479,43 +650,53 @@ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) { # Is there a closing XHTML slash at the end of the attributes? $xhtml_slash = ''; - if (preg_match('%\s/\s*$%', $attr)) + if (preg_match('%\s*/\s*$%', $attr)) $xhtml_slash = ' /'; # Are any attributes allowed at all for this element? - - if (@ count($allowed_html[strtolower($element)]) == 0) + if ( ! isset($allowed_html[strtolower($element)]) || count($allowed_html[strtolower($element)]) == 0 ) return "<$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 = ''; + $allowed_attr = $allowed_html[strtolower($element)]; foreach ($attrarr as $arreach) { - if (!@ isset ($allowed_html[strtolower($element)][strtolower($arreach['name'])])) + if ( ! isset( $allowed_attr[strtolower($arreach['name'])] ) ) continue; # the attribute is not allowed - $current = $allowed_html[strtolower($element)][strtolower($arreach['name'])]; - if ($current == '') + $current = $allowed_attr[strtolower($arreach['name'])]; + if ( $current == '' ) continue; # the attribute is not allowed - if (!is_array($current)) + if ( ! is_array($current) ) { $attr2 .= ' '.$arreach['whole']; # there are no checks - else { + } else { # there are some checks $ok = true; - foreach ($current as $currkey => $currval) - if (!wp_kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval)) { + foreach ($current as $currkey => $currval) { + if ( ! wp_kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval) ) { $ok = false; break; } + } + + if ( strtolower($arreach['name']) == 'style' ) { + $orig_value = $arreach['value']; + $value = safecss_filter_attr($orig_value); + + if ( empty($value) ) + continue; + + $arreach['value'] = $value; + $arreach['whole'] = str_replace($orig_value, $value, $arreach['whole']); + } if ($ok) $attr2 .= ' '.$arreach['whole']; # it passed them @@ -523,14 +704,13 @@ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) { } # foreach # Remove any "<" or ">" characters - $attr2 = preg_replace('/[<>]/', '', $attr2); return "<$element$attr2$xhtml_slash>"; } /** - * wp_kses_hair() - Builds an attribute list from string containing attributes. + * Builds an attribute list from string containing attributes. * * 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 @@ -550,6 +730,7 @@ function wp_kses_hair($attr, $allowed_protocols) { $attrarr = array (); $mode = 0; $attrname = ''; + $uris = array('xmlns', 'profile', 'href', 'src', 'cite', 'classid', 'codebase', 'data', 'usemap', 'longdesc', 'action'); # Loop through the whole attribute list @@ -591,10 +772,12 @@ function wp_kses_hair($attr, $allowed_protocols) { case 2 : # attribute value, a URL after href= for instance - if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) + if (preg_match('%^"([^"]*)"(\s+|/?$)%', $attr, $match)) # "value" { - $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols); + $thisval = $match[1]; + if ( in_array(strtolower($attrname), $uris) ) + $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(FALSE === array_key_exists($attrname, $attrarr)) { $attrarr[$attrname] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname=\"$thisval\"", 'vless' => 'n'); @@ -605,10 +788,12 @@ function wp_kses_hair($attr, $allowed_protocols) { break; } - if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) + if (preg_match("%^'([^']*)'(\s+|/?$)%", $attr, $match)) # 'value' { - $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols); + $thisval = $match[1]; + if ( in_array(strtolower($attrname), $uris) ) + $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(FALSE === array_key_exists($attrname, $attrarr)) { $attrarr[$attrname] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname='$thisval'", 'vless' => 'n'); @@ -619,10 +804,12 @@ function wp_kses_hair($attr, $allowed_protocols) { break; } - if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) + if (preg_match("%^([^\s\"']+)(\s+|/?$)%", $attr, $match)) # value { - $thisval = wp_kses_bad_protocol($match[1], $allowed_protocols); + $thisval = $match[1]; + if ( in_array(strtolower($attrname), $uris) ) + $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(FALSE === array_key_exists($attrname, $attrarr)) { $attrarr[$attrname] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname=\"$thisval\"", 'vless' => 'n'); @@ -652,7 +839,7 @@ function wp_kses_hair($attr, $allowed_protocols) { } /** - * wp_kses_check_attr_val() - Performs different checks for attribute values. + * Performs different checks for attribute values. * * The currently implemented checks are "maxlen", "minlen", "maxval", "minval" * and "valueless" with even more checks to come soon. @@ -660,10 +847,10 @@ function wp_kses_hair($attr, $allowed_protocols) { * @since 1.0.0 * * @param string $value Attribute value - * @param string $vless Whether the value is valueless or not. Use 'y' or 'n' + * @param string $vless Whether the value is valueless. Use 'y' or 'n' * @param string $checkname What $checkvalue is checking for. * @param mixed $checkvalue What constraint the value should pass - * @return bool Whether check passes (true) or not (false) + * @return bool Whether check passes */ function wp_kses_check_attr_val($value, $vless, $checkname, $checkvalue) { $ok = true; @@ -724,12 +911,12 @@ function wp_kses_check_attr_val($value, $vless, $checkname, $checkvalue) { } /** - * wp_kses_bad_protocol() - Sanitize string from bad protocols + * Sanitize string from bad protocols. * - * This function removes all non-allowed protocols from the beginning - * of $string. It ignores whitespace and the case of the letters, and - * it does understand HTML entities. It does its work in a while loop, - * so it won't be fooled by a string like "javascript:javascript:alert(57)". + * This function removes all non-allowed protocols from the beginning of + * $string. It ignores whitespace and the case of the letters, and it does + * understand HTML entities. It does its work in a while loop, so it won't be + * fooled by a string like "javascript:javascript:alert(57)". * * @since 1.0.0 * @@ -739,7 +926,6 @@ function wp_kses_check_attr_val($value, $vless, $checkname, $checkvalue) { */ function wp_kses_bad_protocol($string, $allowed_protocols) { $string = wp_kses_no_null($string); - $string = preg_replace('/\xad+/', '', $string); # deals with Opera "feature" $string2 = $string.'a'; while ($string != $string2) { @@ -751,7 +937,7 @@ function wp_kses_bad_protocol($string, $allowed_protocols) { } /** - * wp_kses_no_null() - Removes any NULL characters in $string. + * Removes any NULL characters in $string. * * @since 1.0.0 * @@ -766,11 +952,11 @@ function wp_kses_no_null($string) { } /** - * wp_kses_stripslashes() - Strips slashes from in front of quotes + * Strips slashes from in front of quotes. * - * This function changes the character sequence \" to just " - * It leaves all other slashes alone. It's really weird, but the - * quoting from preg_replace(//e) seems to require this. + * This function changes the character sequence \" to just ". It leaves all + * other slashes alone. It's really weird, but the quoting from + * preg_replace(//e) seems to require this. * * @since 1.0.0 * @@ -782,7 +968,7 @@ function wp_kses_stripslashes($string) { } /** - * wp_kses_array_lc() - Goes through an array and changes the keys to all lower case. + * Goes through an array and changes the keys to all lower case. * * @since 1.0.0 * @@ -792,11 +978,11 @@ function wp_kses_stripslashes($string) { function wp_kses_array_lc($inarray) { $outarray = array (); - foreach ($inarray as $inkey => $inval) { + foreach ( (array) $inarray as $inkey => $inval) { $outkey = strtolower($inkey); $outarray[$outkey] = array (); - foreach ($inval as $inkey2 => $inval2) { + foreach ( (array) $inval as $inkey2 => $inval2) { $outkey2 = strtolower($inkey2); $outarray[$outkey][$outkey2] = $inval2; } # foreach $inval @@ -806,7 +992,7 @@ function wp_kses_array_lc($inarray) { } /** - * wp_kses_js_entities() - Removes the HTML JavaScript entities found in early versions of Netscape 4. + * Removes the HTML JavaScript entities found in early versions of Netscape 4. * * @since 1.0.0 * @@ -818,10 +1004,10 @@ function wp_kses_js_entities($string) { } /** - * wp_kses_html_error() - Handles parsing errors in wp_kses_hair() + * Handles parsing errors in wp_kses_hair(). * - * The general plan is to remove everything to and including some - * whitespace, but it deals with quotes and apostrophes as well. + * The general plan is to remove everything to and including some whitespace, + * but it deals with quotes and apostrophes as well. * * @since 1.0.0 * @@ -833,10 +1019,10 @@ function wp_kses_html_error($string) { } /** - * wp_kses_bad_protocol_once() - Sanitizes content from bad protocols and other characters + * Sanitizes content from bad protocols and other characters. * - * This function searches for URL protocols at the beginning of $string, - * while handling whitespace and HTML entities. + * This function searches for URL protocols at the beginning of $string, while + * handling whitespace and HTML entities. * * @since 1.0.0 * @@ -845,41 +1031,35 @@ function wp_kses_html_error($string) { * @return string Sanitized content */ function wp_kses_bad_protocol_once($string, $allowed_protocols) { - global $_kses_allowed_protocols; - $_kses_allowed_protocols = $allowed_protocols; - - $string2 = preg_split('/:|:|:/i', $string, 2); - if ( isset($string2[1]) && !preg_match('%/\?%', $string2[0]) ) - $string = wp_kses_bad_protocol_once2($string2[0], $allowed_protocols) . trim($string2[1]); - else - $string = preg_replace_callback('/^((&[^;]*;|[\sA-Za-z0-9])*)'.'(:|:|&#[Xx]3[Aa];)\s*/', create_function('$matches', 'global $_kses_allowed_protocols; return wp_kses_bad_protocol_once2($matches[1], $_kses_allowed_protocols);'), $string); + $string2 = preg_split( '/:|�*58;|�*3a;/i', $string, 2 ); + if ( isset($string2[1]) && ! preg_match('%/\?%', $string2[0]) ) + $string = wp_kses_bad_protocol_once2( $string2[0], $allowed_protocols ) . trim( $string2[1] ); return $string; } /** - * wp_kses_bad_protocol_once2() - Callback for wp_kses_bad_protocol_once() regular expression. + * Callback for wp_kses_bad_protocol_once() regular expression. * * This function processes URL protocols, checks to see if they're in the * white-list or not, and returns different data depending on the answer. * + * @access private * @since 1.0.0 * - * @param string $string Content to check for bad protocols - * @param array $allowed_protocols Allowed protocols + * @param string $string URI scheme to check against the whitelist + * @param string $allowed_protocols Allowed protocols * @return string Sanitized content */ -function wp_kses_bad_protocol_once2($string, $allowed_protocols) { +function wp_kses_bad_protocol_once2( $string, $allowed_protocols ) { $string2 = wp_kses_decode_entities($string); $string2 = preg_replace('/\s/', '', $string2); $string2 = wp_kses_no_null($string2); - $string2 = preg_replace('/\xad+/', '', $string2); - # deals with Opera "feature" $string2 = strtolower($string2); $allowed = false; - foreach ($allowed_protocols as $one_protocol) - if (strtolower($one_protocol) == $string2) { + foreach ( (array) $allowed_protocols as $one_protocol ) + if ( strtolower($one_protocol) == $string2 ) { $allowed = true; break; } @@ -891,11 +1071,10 @@ function wp_kses_bad_protocol_once2($string, $allowed_protocols) { } /** - * wp_kses_normalize_entities() - Converts and fixes HTML entities + * Converts and fixes HTML entities. * - * This function normalizes HTML entities. It will convert "AT&T" to the - * correct "AT&T", ":" to ":", "&#XYZZY;" to "&#XYZZY;" - * and so on. + * This function normalizes HTML entities. It will convert "AT&T" to the correct + * "AT&T", ":" to ":", "&#XYZZY;" to "&#XYZZY;" and so on. * * @since 1.0.0 * @@ -909,34 +1088,99 @@ function wp_kses_normalize_entities($string) { # Change back the allowed entities in our entity whitelist - $string = preg_replace('/&([A-Za-z][A-Za-z0-9]{0,19});/', '&\\1;', $string); - $string = preg_replace_callback('/&#0*([0-9]{1,5});/', create_function('$matches', 'return wp_kses_normalize_entities2($matches[1]);'), $string); - $string = preg_replace('/&#([Xx])0*(([0-9A-Fa-f]{2}){1,2});/', '&#\\1\\2;', $string); + $string = preg_replace_callback('/&([A-Za-z]{2,8});/', 'wp_kses_named_entities', $string); + $string = preg_replace_callback('/&#(0*[0-9]{1,7});/', 'wp_kses_normalize_entities2', $string); + $string = preg_replace_callback('/&#[Xx](0*[0-9A-Fa-f]{1,6});/', 'wp_kses_normalize_entities3', $string); return $string; } /** - * wp_kses_normalize_entities2() - Callback for wp_kses_normalize_entities() regular expression + * Callback for wp_kses_normalize_entities() regular expression. + * + * This function only accepts valid named entity references, which are finite, + * case-sensitive, and highly scrutinized by HTML and XML validators. + * + * @since 3.0.0 + * + * @param array $matches preg_replace_callback() matches array + * @return string Correctly encoded entity + */ +function wp_kses_named_entities($matches) { + global $allowedentitynames; + + if ( empty($matches[1]) ) + return ''; + + $i = $matches[1]; + return ( ( ! in_array($i, $allowedentitynames) ) ? "&$i;" : "&$i;" ); +} + +/** + * Callback for wp_kses_normalize_entities() regular expression. * - * This function helps wp_kses_normalize_entities() to only accept 16 bit - * values and nothing more for &#number; entities. + * This function helps wp_kses_normalize_entities() to only accept 16 bit values + * and nothing more for &#number; entities. * + * @access private * @since 1.0.0 * - * @param int $i Number encoded entity + * @param array $matches preg_replace_callback() matches array * @return string Correctly encoded entity */ -function wp_kses_normalize_entities2($i) { - return (($i > 65535) ? "&#$i;" : "&#$i;"); +function wp_kses_normalize_entities2($matches) { + if ( empty($matches[1]) ) + return ''; + + $i = $matches[1]; + if (valid_unicode($i)) { + $i = str_pad(ltrim($i,'0'), 3, '0', STR_PAD_LEFT); + $i = "&#$i;"; + } else { + $i = "&#$i;"; + } + + return $i; +} + +/** + * Callback for wp_kses_normalize_entities() for regular expression. + * + * This function helps wp_kses_normalize_entities() to only accept valid Unicode + * numeric entities in hex form. + * + * @access private + * + * @param array $matches preg_replace_callback() matches array + * @return string Correctly encoded entity + */ +function wp_kses_normalize_entities3($matches) { + if ( empty($matches[1]) ) + return ''; + + $hexchars = $matches[1]; + return ( ( ! valid_unicode(hexdec($hexchars)) ) ? "&#x$hexchars;" : '&#x'.ltrim($hexchars,'0').';' ); } /** - * wp_kses_decode_entities() - Convert all entities to their character counterparts. + * Helper function to determine if a Unicode value is valid. * - * This function decodes numeric HTML entities (A and A). It - * doesn't do anything with other entities like ä, but we don't need - * them in the URL protocol whitelisting system anyway. + * @param int $i Unicode value + * @return bool true if the value was a valid Unicode number + */ +function valid_unicode($i) { + return ( $i == 0x9 || $i == 0xa || $i == 0xd || + ($i >= 0x20 && $i <= 0xd7ff) || + ($i >= 0xe000 && $i <= 0xfffd) || + ($i >= 0x10000 && $i <= 0x10ffff) ); +} + +/** + * Convert all entities to their character counterparts. + * + * This function decodes numeric HTML entities (A and A). It doesn't do + * anything with other entities like ä, but we don't need them in the URL + * protocol whitelisting system anyway. * * @since 1.0.0 * @@ -944,19 +1188,39 @@ function wp_kses_normalize_entities2($i) { * @return string Content after decoded entities */ function wp_kses_decode_entities($string) { - $string = preg_replace('/&#([0-9]+);/e', 'chr("\\1")', $string); - $string = preg_replace('/&#[Xx]([0-9A-Fa-f]+);/e', 'chr(hexdec("\\1"))', $string); + $string = preg_replace_callback('/&#([0-9]+);/', '_wp_kses_decode_entities_chr', $string); + $string = preg_replace_callback('/&#[Xx]([0-9A-Fa-f]+);/', '_wp_kses_decode_entities_chr_hexdec', $string); return $string; } /** - * wp_filter_kses() - Sanitize content with allowed HTML Kses rules + * Regex callback for wp_kses_decode_entities() + * + * @param array $match preg match + * @return string + */ +function _wp_kses_decode_entities_chr( $match ) { + return chr( $match[1] ); +} + +/** + * Regex callback for wp_kses_decode_entities() + * + * @param array $match preg match + * @return string + */ +function _wp_kses_decode_entities_chr_hexdec( $match ) { + return chr( hexdec( $match[1] ) ); +} + +/** + * Sanitize content with allowed HTML Kses rules. * * @since 1.0.0 * @uses $allowedtags * - * @param string $data Content to filter + * @param string $data Content to filter, expected to be escaped with slashes * @return string Filtered content */ function wp_filter_kses($data) { @@ -965,15 +1229,29 @@ function wp_filter_kses($data) { } /** - * wp_filter_post_kses() - Sanitize content for allowed HTML tags for post content + * Sanitize content with allowed HTML Kses rules. + * + * @since 2.9.0 + * @uses $allowedtags + * + * @param string $data Content to filter, expected to not be escaped + * @return string Filtered content + */ +function wp_kses_data($data) { + global $allowedtags; + return wp_kses( $data , $allowedtags ); +} + +/** + * Sanitize content for allowed HTML tags for post content. * - * Post content refers to the page contents of the 'post' type and not - * $_POST data from forms. + * Post content refers to the page contents of the 'post' type and not $_POST + * data from forms. * * @since 2.0.0 * @uses $allowedposttags * - * @param string $data Post content to filter + * @param string $data Post content to filter, expected to be escaped with slashes * @return string Filtered post content with allowed HTML tags and attributes intact. */ function wp_filter_post_kses($data) { @@ -982,7 +1260,24 @@ function wp_filter_post_kses($data) { } /** - * wp_filter_nohtml_kses() - Strips all of the HTML in the content + * Sanitize content for allowed HTML tags for post content. + * + * Post content refers to the page contents of the 'post' type and not $_POST + * data from forms. + * + * @since 2.9.0 + * @uses $allowedposttags + * + * @param string $data Post content to filter + * @return string Filtered post content with allowed HTML tags and attributes intact. + */ +function wp_kses_post($data) { + global $allowedposttags; + return wp_kses( $data , $allowedposttags ); +} + +/** + * Strips all of the HTML in the content. * * @since 2.1.0 * @@ -994,13 +1289,13 @@ function wp_filter_nohtml_kses($data) { } /** - * kses_init_filters() - Adds all Kses input form content filters + * Adds all Kses input form content filters. + * + * All hooks have default priority. The wp_filter_kses() function is added to + * the 'pre_comment_content' and 'title_save_pre' hooks. * - * All hooks have default priority. The wp_filter_kses() fucntion - * is added to the 'pre_comment_content' and 'title_save_pre' - * hooks. The wp_filter_post_kses() function is added to the - * 'content_save_pre', 'excerpt_save_pre', and 'content_filtered_save_pre' - * hooks. + * The wp_filter_post_kses() function is added to the 'content_save_pre', + * 'excerpt_save_pre', and 'content_filtered_save_pre' hooks. * * @since 2.0.0 * @uses add_filter() See description for what functions are added to what hooks. @@ -1017,15 +1312,14 @@ function kses_init_filters() { } /** - * kses_remove_filters() - Removes all Kses input form content filters + * Removes all Kses input form content filters. * - * A quick procedural method to removing all of the filters - * that kses uses for content in WordPress Loop. + * A quick procedural method to removing all of the filters that kses uses for + * content in WordPress Loop. * - * Does not remove the kses_init() function from 'init' hook - * (priority is default). Also does not remove kses_init() - * function from 'set_current_user' hook (priority is also - * default). + * Does not remove the kses_init() function from 'init' hook (priority is + * default). Also does not remove kses_init() function from 'set_current_user' + * hook (priority is also default). * * @since 2.0.6 */ @@ -1041,15 +1335,15 @@ function kses_remove_filters() { } /** - * kses_init() - Sets up most of the Kses filters for input form content + * Sets up most of the Kses filters for input form content. * * If you remove the kses_init() function from 'init' hook and - * 'set_current_user' (priority is default), then none of the - * Kses filter hooks will be added. + * 'set_current_user' (priority is default), then none of the Kses filter hooks + * will be added. * - * First removes all of the Kses filters in case the current user - * does not need to have Kses filter the content. If the user does - * not have unfiltered html capability, then Kses filters are added. + * First removes all of the Kses filters in case the current user does not need + * to have Kses filter the content. If the user does not have unfiltered html + * capability, then Kses filters are added. * * @uses kses_remove_filters() Removes the Kses filters * @uses kses_init_filters() Adds the Kses filters back if the user @@ -1065,4 +1359,57 @@ function kses_init() { add_action('init', 'kses_init'); add_action('set_current_user', 'kses_init'); -?> + +/** + * Inline CSS filter + * + * @since 2.8.1 + */ +function safecss_filter_attr( $css, $deprecated = '' ) { + if ( !empty( $deprecated ) ) + _deprecated_argument( __FUNCTION__, '2.8.1' ); // Never implemented + + $css = wp_kses_no_null($css); + $css = str_replace(array("\n","\r","\t"), '', $css); + + if ( preg_match( '%[\\(&=}]|/\*%', $css ) ) // remove any inline css containing \ ( & } = or comments + return ''; + + $css_array = explode( ';', trim( $css ) ); + $allowed_attr = apply_filters( 'safe_style_css', array( 'text-align', 'margin', 'color', 'float', + 'border', 'background', 'background-color', 'border-bottom', 'border-bottom-color', + 'border-bottom-style', 'border-bottom-width', 'border-collapse', 'border-color', 'border-left', + 'border-left-color', 'border-left-style', 'border-left-width', 'border-right', 'border-right-color', + 'border-right-style', 'border-right-width', 'border-spacing', 'border-style', 'border-top', + 'border-top-color', 'border-top-style', 'border-top-width', 'border-width', 'caption-side', + 'clear', 'cursor', 'direction', 'font', 'font-family', 'font-size', 'font-style', + 'font-variant', 'font-weight', 'height', 'letter-spacing', 'line-height', 'margin-bottom', + 'margin-left', 'margin-right', 'margin-top', 'overflow', 'padding', 'padding-bottom', + 'padding-left', 'padding-right', 'padding-top', 'text-decoration', 'text-indent', 'vertical-align', + 'width' ) ); + + if ( empty($allowed_attr) ) + return $css; + + $css = ''; + foreach ( $css_array as $css_item ) { + if ( $css_item == '' ) + continue; + $css_item = trim( $css_item ); + $found = false; + if ( strpos( $css_item, ':' ) === false ) { + $found = true; + } else { + $parts = split( ':', $css_item ); + if ( in_array( trim( $parts[0] ), $allowed_attr ) ) + $found = true; + } + if ( $found ) { + if( $css != '' ) + $css .= ';'; + $css .= $css_item; + } + } + + return $css; +}