$tokens ); return $tokens; } /** * Iterative function that tokenizes a node, putting it into an accumulator. * To iterate is human, to recurse divine - L. Peter Deutsch * @param DOMNode $node DOMNode to be tokenized. * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. * @return HTMLPurifier_Token of node appended to previously passed tokens. */ protected function tokenizeDOM($node, &$tokens) { $level = 0; $nodes = array($level => array($node)); $closingNodes = array(); do { while (!empty($nodes[$level])) { $node = array_shift($nodes[$level]); // FIFO $collect = $level > 0 ? true : false; $needEndingTag = $this->createStartNode($node, $tokens, $collect); if ($needEndingTag) { $closingNodes[$level][] = $node; } if ($node->childNodes && $node->childNodes->length) { $level++; $nodes[$level] = array(); foreach ($node->childNodes as $childNode) { array_push($nodes[$level], $childNode); } } } $level--; if ($level && isset($closingNodes[$level])) { while ($node = array_pop($closingNodes[$level])) { $this->createEndNode($node, $tokens); } } } while ($level > 0); } /** * @param DOMNode $node DOMNode to be tokenized. * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. * @param bool $collect Says whether or start and close are collected, set to * false at first recursion because it's the implicit DIV * tag you're dealing with. * @return bool if the token needs an endtoken * @todo data and tagName properties don't seem to exist in DOMNode? */ protected function createStartNode($node, &$tokens, $collect) { // intercept non element nodes. WE MUST catch all of them, // but we're not getting the character reference nodes because // those should have been preprocessed if ($node->nodeType === XML_TEXT_NODE) { $tokens[] = $this->factory->createText($node->data); return false; } elseif ($node->nodeType === XML_CDATA_SECTION_NODE) { // undo libxml's special treatment of