This can greatly '. 'improve readability for editors who are hand-editing the HTML, but is '. 'by no means necessary as HTML Purifier has already fixed all major '. 'errors the HTML may have had. Tidy is a non-default extension, and this directive '. 'will silently fail if Tidy is not available.
If you are looking to make '. 'the overall look of your page\'s source better, I recommend running Tidy '. 'on the entire page rather than just user-content (after all, the '. 'indentation relative to the containing blocks will be incorrect).
This '. 'directive was available since 1.1.1.
' ); /** * Generates HTML from tokens. */ class HTMLPurifier_Generator { /** * Bool cache of %Core.CleanUTF8DuringGeneration * @private */ var $_clean_utf8 = false; /** * Bool cache of %Core.XHTML * @private */ var $_xhtml = true; /** * Bool cache of %Core.CommentScriptContents * @private */ var $_scriptFix = false; /** * Generates HTML from an array of tokens. * @param $tokens Array of HTMLPurifier_Token * @param $config HTMLPurifier_Config object * @return Generated HTML */ function generateFromTokens($tokens, $config, &$context) { $html = ''; if (!$config) $config = HTMLPurifier_Config::createDefault(); $this->_clean_utf8 = $config->get('Core', 'CleanUTF8DuringGeneration'); $this->_xhtml = $config->get('Core', 'XHTML'); $this->_scriptFix = $config->get('Core', 'CommentScriptContents'); if (!$tokens) return ''; for ($i = 0, $size = count($tokens); $i < $size; $i++) { if ($this->_scriptFix && $tokens[$i]->name === 'script') { // script special case $html .= $this->generateFromToken($tokens[$i++]); $html .= $this->generateScriptFromToken($tokens[$i++]); while ($tokens[$i]->name != 'script') { $html .= $this->generateScriptFromToken($tokens[$i++]); } } $html .= $this->generateFromToken($tokens[$i]); } if ($config->get('Core', 'TidyFormat') && extension_loaded('tidy')) { $tidy_options = array( 'indent'=> true, 'output-xhtml' => $this->_xhtml, 'show-body-only' => true, 'indent-spaces' => 2, 'wrap' => 68, ); if (version_compare(PHP_VERSION, '5', '<')) { tidy_set_encoding('utf8'); foreach ($tidy_options as $key => $value) { tidy_setopt($key, $value); } tidy_parse_string($html); tidy_clean_repair(); $html = tidy_get_output(); } else { $tidy = new Tidy; $tidy->parseString($html, $tidy_options, 'utf8'); $tidy->cleanRepair(); $html = (string) $tidy; } } return $html; } /** * Generates HTML from a single token. * @param $token HTMLPurifier_Token object. * @return Generated HTML */ function generateFromToken($token) { if (!isset($token->type)) return ''; if ($token->type == 'start') { $attr = $this->generateAttributes($token->attr); return '<' . $token->name . ($attr ? ' ' : '') . $attr . '>'; } elseif ($token->type == 'end') { return 'name . '>'; } elseif ($token->type == 'empty') { $attr = $this->generateAttributes($token->attr); return '<' . $token->name . ($attr ? ' ' : '') . $attr . ( $this->_xhtml ? ' /': '' ) . '>'; } elseif ($token->type == 'text') { return $this->escape($token->data); } else { return ''; } } /** * Special case processor for the contents of script tags * @warning This runs into problems if there's already a literal * --> somewhere inside the script contents. */ function generateScriptFromToken($token) { if (!$token->type == 'text') return $this->generateFromToken($token); return ''; // more advanced version: // return ''; } /** * Generates attribute declarations from attribute array. * @param $assoc_array_of_attributes Attribute array * @return Generate HTML fragment for insertion. */ function generateAttributes($assoc_array_of_attributes) { $html = ''; foreach ($assoc_array_of_attributes as $key => $value) { if (!$this->_xhtml) { // remove namespaced attributes if (strpos($key, ':') !== false) continue; // also needed: check for attribute minimization } $html .= $key.'="'.$this->escape($value).'" '; } return rtrim($html); } /** * Escapes raw text data. * @param $string String data to escape for HTML. * @return String escaped data. */ function escape($string) { if ($this->_clean_utf8) $string = HTMLPurifier_Lexer::cleanUTF8($string); return htmlspecialchars($string, ENT_COMPAT, 'UTF-8'); } } ?>