X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/3f5685912e89eb3b0534acd85aa0946b1ca2bbe3..refs/tags/wordpress-3.0.5:/wp-includes/kses.php diff --git a/wp-includes/kses.php b/wp-includes/kses.php index 56176b46..7ca692f5 100644 --- a/wp-includes/kses.php +++ b/wp-includes/kses.php @@ -1,38 +1,44 @@ + * @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. * @@ -57,6 +63,22 @@ 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 +116,15 @@ 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 +136,34 @@ 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 (), @@ -147,6 +202,22 @@ if (!CUSTOM_TAGS) { '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 (), @@ -177,6 +248,18 @@ 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 (), @@ -198,9 +281,25 @@ 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 (), @@ -333,6 +432,50 @@ 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', + ); } /** @@ -344,9 +487,9 @@ if (!CUSTOM_TAGS) { * 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. + * '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 * @@ -355,7 +498,8 @@ 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); @@ -495,7 +639,7 @@ 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)) $xhtml_slash = ' /'; # Are any attributes allowed at all for this element? @@ -533,7 +677,7 @@ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) { break; } - if ( $arreach['name'] == 'style' ) { + if ( strtolower($arreach['name']) == 'style' ) { $orig_value = $arreach['value']; $value = safecss_filter_attr($orig_value); @@ -621,11 +765,11 @@ 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 = $match[1]; - if ( in_array($attrname, $uris) ) + if ( in_array(strtolower($attrname), $uris) ) $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(FALSE === array_key_exists($attrname, $attrarr)) { @@ -637,11 +781,11 @@ function wp_kses_hair($attr, $allowed_protocols) { break; } - if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) + if (preg_match("%^'([^']*)'(\s+|/?$)%", $attr, $match)) # 'value' { $thisval = $match[1]; - if ( in_array($attrname, $uris) ) + if ( in_array(strtolower($attrname), $uris) ) $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(FALSE === array_key_exists($attrname, $attrarr)) { @@ -653,11 +797,11 @@ function wp_kses_hair($attr, $allowed_protocols) { break; } - if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) + if (preg_match("%^([^\s\"']+)(\s+|/?$)%", $attr, $match)) # value { $thisval = $match[1]; - if ( in_array($attrname, $uris) ) + if ( in_array(strtolower($attrname), $uris) ) $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(FALSE === array_key_exists($attrname, $attrarr)) { @@ -696,10 +840,10 @@ function wp_kses_hair($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) { $ok = true; @@ -880,14 +1024,9 @@ function wp_kses_html_error($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]) . trim($string2[1]); - else - $string = preg_replace_callback('/^((&[^;]*;|[\sA-Za-z0-9])*)'.'(:|:|&#[Xx]3[Aa];)\s*/', 'wp_kses_bad_protocol_once2', $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 $string; } @@ -901,29 +1040,19 @@ function wp_kses_bad_protocol_once($string, $allowed_protocols) { * @access private * @since 1.0.0 * - * @param mixed $matches string or preg_replace_callback() matches array to check for bad protocols + * @param string $string URI scheme to check against the whitelist + * @param string $allowed_protocols Allowed protocols * @return string Sanitized content */ -function wp_kses_bad_protocol_once2($matches) { - global $_kses_allowed_protocols; - - if ( is_array($matches) ) { - if ( ! isset($matches[1]) || empty($matches[1]) ) - return ''; - - $string = $matches[1]; - } else { - $string = $matches; - } - +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); $string2 = strtolower($string2); $allowed = false; - foreach ( (array) $_kses_allowed_protocols as $one_protocol) - if (strtolower($one_protocol) == $string2) { + foreach ( (array) $allowed_protocols as $one_protocol ) + if ( strtolower($one_protocol) == $string2 ) { $allowed = true; break; } @@ -952,13 +1081,34 @@ function wp_kses_normalize_entities($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});/', 'wp_kses_normalize_entities2', $string); - $string = preg_replace_callback('/&#([Xx])0*(([0-9A-Fa-f]{2}){1,2});/', 'wp_kses_normalize_entities3', $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; } +/** + * 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;" : "&$i;" ); +} + /** * Callback for wp_kses_normalize_entities() regular expression. * @@ -972,11 +1122,18 @@ function wp_kses_normalize_entities($string) { * @return string Correctly encoded entity */ function wp_kses_normalize_entities2($matches) { - if ( ! isset($matches[1]) || empty($matches[1]) ) + if ( empty($matches[1]) ) return ''; $i = $matches[1]; - return ( ( ! valid_unicode($i) ) || ($i > 65535) ? "&#$i;" : "&#$i;" ); + if (valid_unicode($i)) { + $i = str_pad(ltrim($i,'0'), 3, '0', STR_PAD_LEFT); + $i = "&#$i;"; + } else { + $i = "&#$i;"; + } + + return $i; } /** @@ -991,11 +1148,11 @@ function wp_kses_normalize_entities2($matches) { * @return string Correctly encoded entity */ function wp_kses_normalize_entities3($matches) { - if ( ! isset($matches[2]) || empty($matches[2]) ) + if ( empty($matches[1]) ) return ''; - $hexchars = $matches[2]; - return ( ( ! valid_unicode(hexdec($hexchars)) ) ? "&#x$hexchars;" : "&#x$hexchars;" ); + $hexchars = $matches[1]; + return ( ( ! valid_unicode(hexdec($hexchars)) ) ? "&#x$hexchars;" : '&#x'.ltrim($hexchars,'0').';' ); } /** @@ -1196,14 +1353,22 @@ 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 + if ( preg_match( '%[\\(&=}]|/\*%', $css ) ) // remove any inline css containing \ ( & } = or comments return ''; - $css_array = split( ';', trim( $css ) ); + $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',