/**
* 清理属性
*/
public function attributes($attributes, $elem = '')
{
$return = array();
$mode = 0;
$attrname = '';
$skip = false;
while (strlen($attributes) != 0) {
$working = 0;
switch ($mode) {
//属性名
case 0:
if (preg_match('/^([-a-zA-Z]+)/', $attributes, $match)) {
$working = 1;
$mode = 1;
$attrname = strtolower($match[1]);
$skip = substr($attrname, 0, 2) == 'on';
$attributes = preg_replace('/^[-a-zA-Z]+/', '', $attributes);
}
break;
//单个的属性值
//单个的属性值
case 1:
if (preg_match('/^\\s*=\\s*/', $attributes)) {
$working = 1;
$mode = 2;
$attributes = preg_replace('/^\\s*=\\s*/', '', $attributes);
break;
}
if (preg_match('/^\\s+/', $attributes)) {
$working = 1;
$mode = 0;
if (!$skip) {
$return[$attrname] = array();
}
$attributes = preg_replace('/^\\s+/', '', $attributes);
}
break;
//属性值
//属性值
case 2:
if (preg_match('/^"([^"]*)"(\\s+|$)/', $attributes, $match)) {
$working = 1;
$mode = 0;
if (!$skip) {
$return[$attrname] = array('value' => $match[1], 'delimiter' => '"');
}
$attributes = preg_replace('/^"[^"]*"(\\s+|$)/', '', $attributes);
break;
}
if (preg_match("/^'([^']*)'(\\s+|\$)/", $attributes, $match)) {
$working = 1;
$mode = 0;
if (!$skip) {
$return[$attrname] = array('value' => $match[1], 'delimiter' => "'");
}
$attributes = preg_replace("/^'[^']*'(\\s+|\$)/", '', $attributes);
break;
}
if (preg_match("%^([^\\s\"']+)(\\s+|\$)%", $attributes, $match)) {
$working = 1;
$mode = 0;
if (!$skip) {
$return[$attrname] = array('value' => $match[1], 'delimiter' => '"');
}
$attributes = preg_replace("%^[^\\s\"']+(\\s+|\$)%", '', $attributes);
}
break;
}
//没有匹配到的,直接过滤
if ($working == 0) {
$attributes = preg_replace('/
^
(
"[^"]*("|$) # - a string that starts with a double quote, up until the next double quote or the end of the string
| # or
\'[^\']*(\'|$)| # - a string that starts with a quote, up until the next quote or the end of the string
| # or
\\S # - a non-whitespace character
)* # any number of the above three
\\s* # any number of whitespaces
/x', '', $attributes);
$mode = 0;
}
}
if ($mode == 1 && !$skip) {
$return[$attrname] = array();
}
//执行属性的清理
$tag = isset($this->allowedTags[$elem]) ? $this->allowedTags[$elem] : array();
foreach ($return as $name => $info) {
if (!isset($info['value'])) {
continue;
}
//去掉不允许的
if (isset($tag['disallowed']) && in_array($name, $tag['disallowed'])) {
unset($return[$name]);
continue;
}
//只留允许的
if (isset($tag['allowed']) && !in_array($name, $tag['allowed'])) {
unset($return[$name]);
continue;
}
//对style深度清理
if ($name == 'style') {
$sanitized_properties = array();
$properties = array_filter(array_map('trim', explode(';', StringTool::decodeEntities($info['value']))));
foreach ($properties as $property) {
if (!preg_match('#^([a-zA-Z][-a-zA-Z]*)\\s*:\\s*(.*)$#', $property, $property_matches)) {
continue;
}
$property_name = strtolower($property_matches[1]);
$property_value =& $property_matches[2];
if (!isset($this->allowedStyleProperties[$property_name])) {
continue;
}
if (strpos($property_value, 'url(') !== false) {
if (!preg_match('`url\\(\\s*(([\'"]?)(?:[^)]|(?<=\\\\)\\))+[\'"]?)\\s*\\)`', $property_value, $url) || empty($url[1])) {
continue;
}
if (!empty($url[2])) {
if (substr($url[1], -1) != $url[2]) {
continue;
}
$url[1] = substr($url[1], 1, -1);
}
$url = preg_replace('`\\\\([(),\'"\\s])`', '\\1', $url[1]);
if (StringTool::filterBadProtocol($url) != $url) {
continue;
}
if (!preg_match('`^/[^/]+`', $url)) {
$match = false;
foreach ($this->allowedStyleDomain as $reg) {
if (preg_match($reg, $url)) {
$match = true;
break;
}
}
if (!$match) {
continue;
}
}
}
$sanitized_properties[] = $property_name . ':' . StringTool::checkPlain($property_value);
}
if (empty($sanitized_properties)) {
unset($return[$name]);
continue;
}
$info['value'] = implode('; ', $sanitized_properties);
} else {
$info['value'] = StringTool::filterBadProtocol($info['value']);
}
$return[$name] = $name . '=' . $info['delimiter'] . $info['value'] . $info['delimiter'];
}
return $return;
}