wp_kses_hair

wp_kses_hair: 这个函数用来对一串HTML内容进行净化，同时允许某些安全的HTML标签和属性。

从包含属性的字符串建立一个属性列表。

这个函数做了大量的工作。它将一个属性列表解析成一个包含属性数据的数组，并尝试做正确的事情，即使它得到奇怪的输入。它将在没有任何引号或撇号的属性值周围添加引号，以使生成的HTML代码更容易符合W3C的HTML规范。它还会从属性值中删除不良的URL协议
属性值中的不良URL协议。它还通过使用首先定义的属性来减少重复的属性（”foo=’bar’ foo=’baz'”将导致”foo=’bar'”）。

function wp_kses_hair( $attr, $allowed_protocols ) {
	$attrarr  = array();
	$mode     = 0;
	$attrname = '';
	$uris     = wp_kses_uri_attributes();

	// 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][-_a-zA-Z0-9:.]*)/', $attr, $match ) ) {
					$attrname = $match[1];
					$working  = 1;
					$mode     = 1;
					$attr     = preg_replace( '/^[_a-zA-Z][-_a-zA-Z0-9:.]*/', '', $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, true ) ) {
						$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, true ) ) {
						$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, true ) ) {
						$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;
		} // End switch.

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

	if ( 1 == $mode && 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;
}