factory = new HTMLPurifier_TokenFactory(); } /** * @param string $html * @param HTMLPurifier_Config $config * @param HTMLPurifier_Context $context * @return HTMLPurifier_Token[] */ public function tokenizeHTML($html, $config, $context) { $html = $this->normalize($html, $config, $context); // attempt to armor stray angled brackets that cannot possibly // form tags and thus are probably being used as emoticons if ($config->get('Core.AggressivelyFixLt')) { $char = '[^a-z!\/]'; $comment = "/|\z)/is"; $html = preg_replace_callback($comment, array($this, 'callbackArmorCommentEntities'), $html); do { $old = $html; $html = preg_replace("/<($char)/i", '<\\1', $html); } while ($html !== $old); $html = preg_replace_callback($comment, array($this, 'callbackUndoCommentSubst'), $html); // fix comments } // preprocess html, essential for UTF-8 $html = $this->wrapHTML($html, $config, $context); $doc = new DOMDocument(); $doc->encoding = 'UTF-8'; // theoretically, the above has this covered set_error_handler(array($this, 'muteErrorHandler')); $doc->loadHTML($html); restore_error_handler(); $body = $doc->getElementsByTagName('html')->item(0)-> // getElementsByTagName('body')->item(0); // $div = $body->getElementsByTagName('div')->item(0); //
$tokens = array(); $this->tokenizeDOM($div, $tokens); // If the div has a sibling, that means we tripped across // a premature
tag. So remove the div we parsed, // and then tokenize the rest of body. We can't tokenize // the sibling directly as we'll lose the tags in that case. if ($div->nextSibling) { $body->removeChild($div); $this->tokenizeDOM($body, $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 => new HTMLPurifier_Queue(array($node))); $closingNodes = array(); do { while (!$nodes[$level]->isEmpty()) { $node = $nodes[$level]->shift(); // 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] = new HTMLPurifier_Queue(); foreach ($node->childNodes as $childNode) { $nodes[$level]->push($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