A WordPress-centric search engine for devs and theme authors



wp_kses_hair ›

Since1.0.0
Deprecatedn/a
wp_kses_hair ( $attr, $allowed_protocols )
Parameters: (2)
  • (string) $attr Attribute list from HTML element to closing HTML element tag.
    Required: Yes
  • (string[]) $allowed_protocols Array of allowed URL protocols.
    Required: Yes
Returns:
  • (array[]) Array of attribute information after parsing.
Defined at:
Codex:

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. It also reduces duplicate attributes by using the attribute defined first (foo='bar' foo='baz' will result in foo='bar').



Source

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

	while ( strlen( $attr ) != 0 ) {
		$working = 0; // Was the last operation successful?

		switch ( $mode ) {
			case 0:
				if ( preg_match( '/^([-a-zA-Z:]+)/', $attr, $match ) ) {
					$attrname = $match[1];
					$working  = $mode = 1;
					$attr     = preg_replace( '/^[-a-zA-Z:]+/', '', $attr );
				}

				break;

			case 1:
				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;
					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:
				if ( preg_match( '%^"([^"]*)"(\s+|/?$)%', $attr, $match ) ) {
					// "value"
					$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',
						);
					}
					$working = 1;
					$mode    = 0;
					$attr    = preg_replace( '/^"[^"]*"(\s+|$)/', '', $attr );
					break;
				}

				if ( preg_match( "%^'([^']*)'(\s+|/?$)%", $attr, $match ) ) {
					// 'value'
					$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',
						);
					}
					$working = 1;
					$mode    = 0;
					$attr    = preg_replace( "/^'[^']*'(\s+|$)/", '', $attr );
					break;
				}

				if ( preg_match( "%^([^\s\"']+)(\s+|/?$)%", $attr, $match ) ) {
					// value
					$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

		if ( $working == 0 ) { // not well formed, remove and try again
			$attr = wp_kses_html_error( $attr );
			$mode = 0;
		}
	} // while

	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;
}