diff --git a/library/HTMLPurifier/Lexer/DOMLex.php b/library/HTMLPurifier/Lexer/DOMLex.php index 22ab5820..6238a99e 100644 --- a/library/HTMLPurifier/Lexer/DOMLex.php +++ b/library/HTMLPurifier/Lexer/DOMLex.php @@ -126,6 +126,41 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer } while ($level > 0); } + /** + * Portably retrieve the tag name of a node; deals with older versions + * of libxml like 2.7.6 + * @param DOMNode $node + */ + protected function getTagName($node) + { + if (property_exists($node, 'tagName')) { + return $node->tagName; + } else if (property_exists($node, 'nodeName')) { + return $node->nodeName; + } else if (property_exists($node, 'localName')) { + return $node->localName; + } + return null; + } + + /** + * Portably retrieve the data of a node; deals with older versions + * of libxml like 2.7.6 + * @param DOMNode $node + */ + protected function getData($node) + { + if (property_exists($node, 'data')) { + return $node->data; + } else if (property_exists($node, 'nodeValue')) { + return $node->nodeValue; + } else if (property_exists($node, 'textContent')) { + return $node->textContent; + } + return null; + } + + /** * @param DOMNode $node DOMNode to be tokenized. * @param HTMLPurifier_Token[] $tokens Array-list of already tokenized tokens. @@ -141,7 +176,10 @@ class HTMLPurifier_Lexer_DOMLex extends HTMLPurifier_Lexer // but we're not getting the character reference nodes because // those should have been preprocessed if ($node->nodeType === XML_TEXT_NODE) { - $tokens[] = $this->factory->createText($node->data); + $data = $this->getData($node); // Handle variable data property + if ($data !== null) { + $tokens[] = $this->factory->createText($data); + } return false; } elseif ($node->nodeType === XML_CDATA_SECTION_NODE) { // undo libxml's special treatment of