X-Git-Url: https://scripts.mit.edu/gitweb/autoinstalls/wordpress.git/blobdiff_plain/177fd6fefd2e3d5a0ea6591c71d660cabdb3c1a4..7f1521bf193b382565eb753043c161f4cb3fcda7:/wp-includes/kses.php diff --git a/wp-includes/kses.php b/wp-includes/kses.php index ae37fc26..ba96b089 100644 --- a/wp-includes/kses.php +++ b/wp-includes/kses.php @@ -1,337 +1,515 @@ + * @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. + * + * The wp_kses_allowed_html filter is more powerful and supplies context. + * CUSTOM_TAGS is not recommended and should be considered deprecated. + * + * @see wp_kses_allowed_html() * * @since 1.2.0 */ -if (!defined('CUSTOM_TAGS')) - define('CUSTOM_TAGS', false); +if ( ! defined( 'CUSTOM_TAGS' ) ) + define( 'CUSTOM_TAGS', false ); + +// Ensure that these variables are added to the global namespace +// (e.g. if using namespaces / autoload in the current PHP environment). +global $allowedposttags, $allowedtags, $allowedentitynames; -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 */ $allowedposttags = array( 'address' => array(), 'a' => array( - 'class' => array (), - 'href' => array (), - 'id' => array (), - 'title' => array (), - 'rel' => array (), - 'rev' => array (), - 'name' => array (), - 'target' => array()), - 'abbr' => array( - 'class' => array (), - 'title' => array ()), - 'acronym' => array( - 'title' => array ()), + 'href' => true, + 'rel' => true, + 'rev' => true, + 'name' => true, + 'target' => true, + ), + 'abbr' => array(), + 'acronym' => array(), + 'area' => array( + 'alt' => true, + 'coords' => true, + 'href' => true, + 'nohref' => true, + 'shape' => true, + 'target' => true, + ), + 'article' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), + 'aside' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), + 'audio' => array( + 'autoplay' => true, + 'controls' => true, + 'loop' => true, + 'muted' => true, + 'preload' => true, + 'src' => true, + ), 'b' => array(), 'big' => array(), 'blockquote' => array( - 'id' => array (), - 'cite' => array (), - 'class' => array(), - 'lang' => array(), - 'xml:lang' => array()), - 'br' => array ( - 'class' => array ()), + 'cite' => true, + 'lang' => true, + 'xml:lang' => true, + ), + 'br' => array(), 'button' => array( - 'disabled' => array (), - 'name' => array (), - 'type' => array (), - 'value' => array ()), + 'disabled' => true, + 'name' => true, + 'type' => true, + 'value' => true, + ), 'caption' => array( - 'align' => array (), - 'class' => array ()), - 'cite' => array ( - 'class' => array(), - 'dir' => array(), - 'lang' => array(), - 'title' => array ()), - 'code' => array ( - 'style' => array()), + 'align' => true, + ), + 'cite' => array( + 'dir' => true, + 'lang' => true, + ), + 'code' => array(), 'col' => array( - 'align' => array (), - 'char' => array (), - 'charoff' => array (), - 'span' => array (), - 'dir' => array(), - 'style' => array (), - 'valign' => array (), - 'width' => array ()), + 'align' => true, + 'char' => true, + 'charoff' => true, + 'span' => true, + 'dir' => true, + 'valign' => true, + 'width' => true, + ), + 'colgroup' => array( + 'align' => true, + 'char' => true, + 'charoff' => true, + 'span' => true, + 'valign' => true, + 'width' => true, + ), 'del' => array( - 'datetime' => array ()), + 'datetime' => true, + ), 'dd' => array(), + 'dfn' => array(), + 'details' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'open' => true, + 'xml:lang' => true, + ), 'div' => array( - 'align' => array (), - 'class' => array (), - 'dir' => array (), - 'lang' => array(), - 'style' => array (), - 'xml:lang' => array()), + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), 'dl' => array(), 'dt' => array(), 'em' => array(), 'fieldset' => array(), + 'figure' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), + 'figcaption' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), 'font' => array( - 'color' => array (), - 'face' => array (), - 'size' => array ()), + 'color' => true, + 'face' => true, + 'size' => true, + ), + 'footer' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), 'form' => array( - 'action' => array (), - 'accept' => array (), - 'accept-charset' => array (), - 'enctype' => array (), - 'method' => array (), - 'name' => array (), - 'target' => array ()), + 'action' => true, + 'accept' => true, + 'accept-charset' => true, + 'enctype' => true, + 'method' => true, + 'name' => true, + 'target' => true, + ), 'h1' => array( - 'align' => array (), - 'class' => array ()), + 'align' => true, + ), 'h2' => array( - 'align' => array (), - 'class' => array ()), + 'align' => true, + ), 'h3' => array( - 'align' => array (), - 'class' => array ()), + 'align' => true, + ), 'h4' => array( - 'align' => array (), - 'class' => array ()), + 'align' => true, + ), 'h5' => array( - 'align' => array (), - 'class' => array ()), + 'align' => true, + ), 'h6' => array( - 'align' => array (), - 'class' => array ()), + 'align' => true, + ), + 'header' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), + 'hgroup' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), 'hr' => array( - 'align' => array (), - 'class' => array (), - 'noshade' => array (), - 'size' => array (), - 'width' => array ()), + 'align' => true, + 'noshade' => true, + 'size' => true, + 'width' => true, + ), 'i' => array(), 'img' => array( - 'alt' => array (), - 'align' => array (), - 'border' => array (), - 'class' => array (), - 'height' => array (), - 'hspace' => array (), - 'longdesc' => array (), - 'vspace' => array (), - 'src' => array (), - 'style' => array (), - 'width' => array ()), + 'alt' => true, + 'align' => true, + 'border' => true, + 'height' => true, + 'hspace' => true, + 'longdesc' => true, + 'vspace' => true, + 'src' => true, + 'usemap' => true, + 'width' => true, + ), 'ins' => array( - 'datetime' => array (), - 'cite' => array ()), + 'datetime' => true, + 'cite' => true, + ), 'kbd' => array(), 'label' => array( - 'for' => array ()), + 'for' => true, + ), 'legend' => array( - 'align' => array ()), - 'li' => array ( - 'align' => array (), - 'class' => array ()), + 'align' => true, + ), + 'li' => array( + 'align' => true, + 'value' => true, + ), + 'map' => array( + 'name' => true, + ), + 'mark' => array(), + 'menu' => array( + 'type' => true, + ), + 'nav' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), 'p' => array( - 'class' => array (), - 'align' => array (), - 'dir' => array(), - 'lang' => array(), - 'style' => array (), - 'xml:lang' => array()), + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), 'pre' => array( - 'style' => array(), - 'width' => array ()), + 'width' => true, + ), 'q' => array( - 'cite' => array ()), + 'cite' => true, + ), 's' => array(), - 'span' => array ( - 'class' => array (), - 'dir' => array (), - 'align' => array (), - 'style' => array (), - 'title' => array ()), + 'samp' => array(), + 'span' => array( + 'dir' => true, + 'align' => true, + 'lang' => true, + 'xml:lang' => true, + ), + 'section' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), + 'small' => array(), 'strike' => array(), 'strong' => array(), 'sub' => array(), + 'summary' => array( + 'align' => true, + 'dir' => true, + 'lang' => true, + 'xml:lang' => true, + ), 'sup' => array(), 'table' => array( - 'align' => array (), - 'bgcolor' => array (), - 'border' => array (), - 'cellpadding' => array (), - 'cellspacing' => array (), - 'class' => array (), - 'dir' => array(), - 'id' => array(), - 'rules' => array (), - 'style' => array (), - 'summary' => array (), - 'width' => array ()), + 'align' => true, + 'bgcolor' => true, + 'border' => true, + 'cellpadding' => true, + 'cellspacing' => true, + 'dir' => true, + 'rules' => true, + 'summary' => true, + 'width' => true, + ), 'tbody' => array( - 'align' => array (), - 'char' => array (), - 'charoff' => array (), - 'valign' => array ()), + 'align' => true, + 'char' => true, + 'charoff' => true, + 'valign' => true, + ), 'td' => array( - 'abbr' => array (), - 'align' => array (), - 'axis' => array (), - 'bgcolor' => array (), - 'char' => array (), - 'charoff' => array (), - 'class' => array (), - 'colspan' => array (), - 'dir' => array(), - 'headers' => array (), - 'height' => array (), - 'nowrap' => array (), - 'rowspan' => array (), - 'scope' => array (), - 'style' => array (), - 'valign' => array (), - 'width' => array ()), + 'abbr' => true, + 'align' => true, + 'axis' => true, + 'bgcolor' => true, + 'char' => true, + 'charoff' => true, + 'colspan' => true, + 'dir' => true, + 'headers' => true, + 'height' => true, + 'nowrap' => true, + 'rowspan' => true, + 'scope' => true, + 'valign' => true, + 'width' => true, + ), 'textarea' => array( - 'cols' => array (), - 'rows' => array (), - 'disabled' => array (), - 'name' => array (), - 'readonly' => array ()), + 'cols' => true, + 'rows' => true, + 'disabled' => true, + 'name' => true, + 'readonly' => true, + ), 'tfoot' => array( - 'align' => array (), - 'char' => array (), - 'class' => array (), - 'charoff' => array (), - 'valign' => array ()), + 'align' => true, + 'char' => true, + 'charoff' => true, + 'valign' => true, + ), 'th' => array( - 'abbr' => array (), - 'align' => array (), - 'axis' => array (), - 'bgcolor' => array (), - 'char' => array (), - 'charoff' => array (), - 'class' => array (), - 'colspan' => array (), - 'headers' => array (), - 'height' => array (), - 'nowrap' => array (), - 'rowspan' => array (), - 'scope' => array (), - 'valign' => array (), - 'width' => array ()), + 'abbr' => true, + 'align' => true, + 'axis' => true, + 'bgcolor' => true, + 'char' => true, + 'charoff' => true, + 'colspan' => true, + 'headers' => true, + 'height' => true, + 'nowrap' => true, + 'rowspan' => true, + 'scope' => true, + 'valign' => true, + 'width' => true, + ), 'thead' => array( - 'align' => array (), - 'char' => array (), - 'charoff' => array (), - 'class' => array (), - 'valign' => array ()), + 'align' => true, + 'char' => true, + 'charoff' => true, + 'valign' => true, + ), 'title' => array(), 'tr' => array( - 'align' => array (), - 'bgcolor' => array (), - 'char' => array (), - 'charoff' => array (), - 'class' => array (), - 'style' => array (), - 'valign' => array ()), + 'align' => true, + 'bgcolor' => true, + 'char' => true, + 'charoff' => true, + 'valign' => true, + ), + 'track' => array( + 'default' => true, + 'kind' => true, + 'label' => true, + 'src' => true, + 'srclang' => true, + ), 'tt' => array(), 'u' => array(), - 'ul' => array ( - 'class' => array (), - 'style' => array (), - 'type' => array ()), - 'ol' => array ( - 'class' => array (), - 'start' => array (), - 'style' => array (), - 'type' => array ()), - 'var' => array ()); + 'ul' => array( + 'type' => true, + ), + 'ol' => array( + 'start' => true, + 'type' => true, + ), + 'var' => array(), + 'video' => array( + 'autoplay' => true, + 'controls' => true, + 'height' => true, + 'loop' => true, + 'muted' => true, + 'poster' => true, + 'preload' => true, + 'src' => true, + 'width' => true, + ), + ); + /** - * Kses allowed HTML elements + * Kses allowed HTML elements. * * @global array $allowedtags * @since 1.0.0 */ $allowedtags = array( 'a' => array( - 'href' => array (), - 'title' => array ()), + 'href' => true, + 'title' => true, + ), 'abbr' => array( - 'title' => array ()), + 'title' => true, + ), 'acronym' => array( - 'title' => array ()), + 'title' => true, + ), 'b' => array(), 'blockquote' => array( - 'cite' => array ()), - // 'br' => array(), - 'cite' => array (), + 'cite' => true, + ), + '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(), + 'datetime' => true, + ), + 'em' => array(), + 'i' => array(), 'q' => array( - 'cite' => array ()), + 'cite' => true, + ), + 's' => array(), 'strike' => array(), 'strong' => array(), - // 'sub' => array(), - // 'sup' => array(), - // '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', + 'sup1', 'sup2', 'sup3', 'frac14', 'frac12', 'frac34', + 'there4', + ); + + $allowedposttags = array_map( '_wp_add_global_attributes', $allowedposttags ); +} else { + $allowedtags = wp_kses_array_lc( $allowedtags ); + $allowedposttags = wp_kses_array_lc( $allowedposttags ); } /** - * 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 * @@ -340,21 +518,73 @@ 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() ) { + if ( empty( $allowed_protocols ) ) + $allowed_protocols = wp_allowed_protocols(); $string = wp_kses_no_null($string); $string = wp_kses_js_entities($string); $string = wp_kses_normalize_entities($string); - $allowed_html_fixed = wp_kses_array_lc($allowed_html); - $string = wp_kses_hook($string, $allowed_html_fixed, $allowed_protocols); // WP changed the order of these funcs and added args to wp_kses_hook - return wp_kses_split($string, $allowed_html_fixed, $allowed_protocols); + $string = wp_kses_hook($string, $allowed_html, $allowed_protocols); // WP changed the order of these funcs and added args to wp_kses_hook + return wp_kses_split($string, $allowed_html, $allowed_protocols); } /** - * wp_kses_hook() - You add any kses hooks here. + * Return a list of allowed tags and attributes for a given context. * - * 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. + * @since 3.5.0 + * + * @param string $context The context for which to retrieve tags. Allowed values are + * post | strip | data | entities or the name of a field filter such as pre_user_description. + * @return array List of allowed tags and their allowed attributes. + */ +function wp_kses_allowed_html( $context = '' ) { + global $allowedposttags, $allowedtags, $allowedentitynames; + + if ( is_array( $context ) ) { + /** + * Filter HTML elements allowed for a given context. + * + * @since 3.5.0 + * + * @param string $tags Allowed tags, attributes, and/or entities. + * @param string $context Context to judge allowed tags by. Allowed values are 'post', + * 'data', 'strip', 'entities', 'explicit', or the name of a filter. + */ + return apply_filters( 'wp_kses_allowed_html', $context, 'explicit' ); + } + + switch ( $context ) { + case 'post': + /** This filter is documented in wp-includes/kses.php */ + return apply_filters( 'wp_kses_allowed_html', $allowedposttags, $context ); + + case 'user_description': + case 'pre_user_description': + $tags = $allowedtags; + $tags['a']['rel'] = true; + /** This filter is documented in wp-includes/kses.php */ + return apply_filters( 'wp_kses_allowed_html', $tags, $context ); + + case 'strip': + /** This filter is documented in wp-includes/kses.php */ + return apply_filters( 'wp_kses_allowed_html', array(), $context ); + + case 'entities': + /** This filter is documented in wp-includes/kses.php */ + return apply_filters( 'wp_kses_allowed_html', $allowedentitynames, $context); + + case 'data': + default: + /** This filter is documented in wp-includes/kses.php */ + return apply_filters( 'wp_kses_allowed_html', $allowedtags, $context ); + } +} + +/** + * You add any kses hooks here. + * + * There is currently only one kses WordPress hook and it is called here. All + * parameters are passed to the hooks and expected to receive a string. * * @since 1.0.0 * @@ -363,24 +593,33 @@ function wp_kses($string, $allowed_html, $allowed_protocols = array ('http', 'ht * @param array $allowed_protocols Allowed protocol in links * @return string Filtered content through 'pre_kses' hook */ -function wp_kses_hook($string, $allowed_html, $allowed_protocols) { - $string = apply_filters('pre_kses', $string, $allowed_html, $allowed_protocols); +function wp_kses_hook( $string, $allowed_html, $allowed_protocols ) { + /** + * Filter content to be run through kses. + * + * @since 2.3.0 + * + * @param string $string Content to run through kses. + * @param array $allowed_html Allowed HTML elements. + * @param array $allowed_protocols Allowed protocol in links. + */ + $string = apply_filters( 'pre_kses', $string, $allowed_html, $allowed_protocols ); return $string; } /** - * 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. * @@ -391,25 +630,38 @@ function wp_kses_version() { * @param array $allowed_protocols Allowed protocols to keep * @return string Content with fixed HTML tags */ -function wp_kses_split($string, $allowed_html, $allowed_protocols) { - return preg_replace('%((|$))|(<[^>]*(>|$)|>))%e', - "wp_kses_split2('\\1', \$allowed_html, ".'$allowed_protocols)', $string); +function wp_kses_split( $string, $allowed_html, $allowed_protocols ) { + 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 ); } /** - * wp_kses_split2() - Callback for wp_kses_split for fixing malformed HTML tags + * Callback for wp_kses_split. * - * 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. + * @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 ); +} + +/** + * 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. * * 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() * * @param string $string Content to filter * @param array $allowed_html Allowed HTML elements @@ -421,45 +673,52 @@ function wp_kses_split2($string, $allowed_html, $allowed_protocols) { if (substr($string, 0, 1) != '<') return '>'; - # It matched a ">" character + // 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 ''; + // prevent multiple dashes in comments + $string = preg_replace('/--+/', '-', $string); + // prevent three dashes closing a comment + $string = preg_replace('/-$/', '', $string); return ""; } - # Allow HTML comments + // Allow HTML comments if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches)) return ''; - # It's seriously malformed + // It's seriously malformed $slash = trim($matches[1]); $elem = $matches[2]; $attrlist = $matches[3]; - if (!@isset($allowed_html[strtolower($elem)])) + if ( ! is_array( $allowed_html ) ) + $allowed_html = wp_kses_allowed_html( $allowed_html ); + + if ( ! isset($allowed_html[strtolower($elem)]) ) return ''; - # They are using a not allowed HTML element + // They are using a not allowed HTML element if ($slash != '') - return "<$slash$elem>"; - # No attributes are allowed for closing elements + 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, $allowed_protocols ); } /** - * wp_kses_attr() - Removes all attributes, if none are allowed for this element + * Removes all attributes, if none are allowed for this element. * * If some are allowed it calls wp_kses_hair() to split them further, and then * it builds up new HTML code from the data that kses_hair() returns. It also - * removes "<" and ">" characters, if there are any left. One more thing it - * does is to check if the tag has a closing XHTML slash, and if it does, it - * puts one in the returned code as well. + * removes "<" and ">" characters, if there are any left. One more thing it does + * is to check if the tag has a closing XHTML slash, and if it does, it puts one + * in the returned code as well. * * @since 1.0.0 * @@ -470,68 +729,81 @@ function wp_kses_split2($string, $allowed_html, $allowed_protocols) { * @return string Sanitized HTML element */ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) { - # Is there a closing XHTML slash at the end of the attributes? + // Is there a closing XHTML slash at the end of the attributes? + + if ( ! is_array( $allowed_html ) ) + $allowed_html = wp_kses_allowed_html( $allowed_html ); $xhtml_slash = ''; - if (preg_match('%\s/\s*$%', $attr)) + if (preg_match('%\s*/\s*$%', $attr)) $xhtml_slash = ' /'; - # Are any attributes allowed at all for this element? - - if (@ count($allowed_html[strtolower($element)]) == 0) + // Are any attributes allowed at all for this element? + if ( ! isset($allowed_html[strtolower($element)]) || count($allowed_html[strtolower($element)]) == 0 ) return "<$element$xhtml_slash>"; - # Split it - + // Split it $attrarr = wp_kses_hair($attr, $allowed_protocols); - # Go through $attrarr, and save the allowed attributes for this element - # in $attr2 - + // 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'])])) - continue; # the attribute is not allowed + if ( ! isset( $allowed_attr[strtolower($arreach['name'])] ) ) + continue; // the attribute is not allowed + + $current = $allowed_attr[strtolower($arreach['name'])]; + if ( $current == '' ) + continue; // the attribute is not allowed - $current = $allowed_html[strtolower($element)][strtolower($arreach['name'])]; - if ($current == '') - continue; # the attribute is not allowed + if ( strtolower( $arreach['name'] ) == 'style' ) { + $orig_value = $arreach['value']; + $value = safecss_filter_attr( $orig_value ); - if (!is_array($current)) + if ( empty( $value ) ) + continue; + + $arreach['value'] = $value; + $arreach['whole'] = str_replace( $orig_value, $value, $arreach['whole'] ); + } + + if ( ! is_array($current) ) { $attr2 .= ' '.$arreach['whole']; - # there are no checks + // there are no checks - else { - # there are some checks + } else { + // there are some checks $ok = true; - foreach ($current as $currkey => $currval) - if (!wp_kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval)) { + foreach ($current as $currkey => $currval) { + if ( ! wp_kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval) ) { $ok = false; break; } + } - if ($ok) - $attr2 .= ' '.$arreach['whole']; # it passed them - } # if !is_array($current) - } # foreach - - # Remove any "<" or ">" characters + 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>"; } /** - * 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 * 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. + * from attribute values. It also reduces duplicate attributes by using the + * attribute defined first (foo='bar' foo='baz' will result in foo='bar'). * * @since 1.0.0 * @@ -540,29 +812,30 @@ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) { * @return array List of attributes after parsing */ function wp_kses_hair($attr, $allowed_protocols) { - $attrarr = array (); + $attrarr = array(); $mode = 0; $attrname = ''; + $uris = array('xmlns', 'profile', 'href', 'src', 'cite', 'classid', 'codebase', 'data', 'usemap', 'longdesc', 'action'); - # Loop through the whole attribute list + // Loop through the whole attribute list while (strlen($attr) != 0) { - $working = 0; # Was the last operation successful? + $working = 0; // Was the last operation successful? switch ($mode) { - case 0 : # attribute name, href for instance + case 0 : // attribute name, href for instance - if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) { + if ( preg_match('/^([-a-zA-Z:]+)/', $attr, $match ) ) { $attrname = $match[1]; $working = $mode = 1; - $attr = preg_replace('/^[-a-zA-Z]+/', '', $attr); + $attr = preg_replace( '/^[-a-zA-Z:]+/', '', $attr ); } break; - case 1 : # equals sign or valueless ("selected") + case 1 : // equals sign or valueless ("selected") - if (preg_match('/^\s*=\s*/', $attr)) # equals sign + if (preg_match('/^\s*=\s*/', $attr)) // equals sign { $working = 1; $mode = 2; @@ -570,113 +843,127 @@ function wp_kses_hair($attr, $allowed_protocols) { break; } - if (preg_match('/^\s+/', $attr)) # valueless + if (preg_match('/^\s+/', $attr)) // valueless { $working = 1; $mode = 0; - $attrarr[] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); + if(false === array_key_exists($attrname, $attrarr)) { + $attrarr[$attrname] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); + } $attr = preg_replace('/^\s+/', '', $attr); } break; - case 2 : # attribute value, a URL after href= for instance + case 2 : // attribute value, a URL after href= for instance - if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) - # "value" + if (preg_match('%^"([^"]*)"(\s+|/?$)%', $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); - $attrarr[] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname=\"$thisval\"", 'vless' => 'n'); + if(false === array_key_exists($attrname, $attrarr)) { + $attrarr[$attrname] = 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, $match)) - # 'value' + if (preg_match("%^'([^']*)'(\s+|/?$)%", $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); - $attrarr[] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname='$thisval'", 'vless' => 'n'); + if(false === array_key_exists($attrname, $attrarr)) { + $attrarr[$attrname] = 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, $match)) - # value + if (preg_match("%^([^\s\"']+)(\s+|/?$)%", $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. + $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'); + } + // We add quotes to conform to W3C's HTML spec. $working = 1; $mode = 0; $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr); } break; - } # switch + } // switch - if ($working == 0) # not well formed, remove and try again + if ($working == 0) // not well formed, remove and try again { $attr = wp_kses_html_error($attr); $mode = 0; } - } # while + } // while - if ($mode == 1) - # special case, for when the attribute list ends with a valueless - # attribute like "selected" - $attrarr[] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); + if ($mode == 1 && false === array_key_exists($attrname, $attrarr)) + // special case, for when the attribute list ends with a valueless + // attribute like "selected" + $attrarr[$attrname] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); return $attrarr; } /** - * 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. + * and "valueless". * * @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) { $ok = true; switch (strtolower($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. + // 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) $ok = false; break; case 'minlen' : - # The minlen check makes sure that the attribute value has a length not - # smaller than the given value. + // The minlen check makes sure that the attribute value has a length not + // smaller than the given value. if (strlen($value) < $checkvalue) $ok = false; break; case 'maxval' : - # The maxval check does two things: it checks that the attribute value is - # an integer from 0 and up, without an excessive amount of zeroes or - # whitespace (to avoid Buffer Overflows). It also checks that the attribute - # value is not greater than the given value. - # This check can be used to avoid Denial of Service attacks. + // The maxval check does two things: it checks that the attribute value is + // an integer from 0 and up, without an excessive amount of zeroes or + // whitespace (to avoid Buffer Overflows). It also checks that the attribute + // value is not greater than the given value. + // This check can be used to avoid Denial of Service attacks. if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) $ok = false; @@ -685,8 +972,8 @@ function wp_kses_check_attr_val($value, $vless, $checkname, $checkvalue) { break; case 'minval' : - # The minval check checks that the attribute value is a positive integer, - # and that it is not smaller than the given value. + // The minval check makes sure that the attribute value is a positive integer, + // and that it is not smaller than the given value. if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) $ok = false; @@ -695,26 +982,26 @@ function wp_kses_check_attr_val($value, $vless, $checkname, $checkvalue) { break; case 'valueless' : - # The valueless check checks if the attribute has a value - # (like ) or not () or not (