From f45a286b8d62f710b519a98c7d4b75a0c34d5d10 Mon Sep 17 00:00:00 2001 From: Andrew Dolgov Date: Mon, 22 Jun 2009 13:56:49 +0400 Subject: strip_tags_long: use htmlpurifier to properly reformat html content --- .../library/HTMLPurifier/Lexer/DOMLex.php | 213 +++++++++++++++++++++ 1 file changed, 213 insertions(+) create mode 100755 lib/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php (limited to 'lib/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php') diff --git a/lib/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php b/lib/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php new file mode 100755 index 000000000..0db3974bf --- /dev/null +++ b/lib/htmlpurifier/library/HTMLPurifier/Lexer/DOMLex.php @@ -0,0 +1,213 @@ +factory = new HTMLPurifier_TokenFactory(); + } + + 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(); + + $tokens = array(); + $this->tokenizeDOM( + $doc->getElementsByTagName('html')->item(0)-> // + getElementsByTagName('body')->item(0)-> // + getElementsByTagName('div')->item(0) //

+ , $tokens); + return $tokens; + } + + /** + * Recursive function that tokenizes a node, putting it into an accumulator. + * + * @param $node DOMNode to be tokenized. + * @param $tokens Array-list of already tokenized tokens. + * @param $collect Says whether or start and close are collected, set to + * false at first recursion because it's the implicit DIV + * tag you're dealing with. + * @returns Tokens of node appended to previously passed tokens. + */ + protected function tokenizeDOM($node, &$tokens, $collect = false) { + + // intercept non element nodes. WE MUST catch all of them, + // but we're not getting the character reference nodes because + // those should have been preprocessed + if ($node->nodeType === XML_TEXT_NODE) { + $tokens[] = $this->factory->createText($node->data); + return; + } elseif ($node->nodeType === XML_CDATA_SECTION_NODE) { + // undo libxml's special treatment of