PHP tidy::cleanRepair方法代码示例

 function tidyClean()
 {
     $tidy = new tidy();
     $tidy->parseString(self::$html, self::$tidy_config, self::$encoding);
     $tidy->cleanRepair();
     self::$html = $tidy;
 }

 /**
  * Detects feed types and instantiate appropriate objects.
  *
  * Our constructor takes care of detecting feed types and instantiating
  * appropriate classes. For now we're going to treat Atom 0.3 as Atom 1.0
  * but raise a warning. I do not intend to introduce full support for 
  * Atom 0.3 as it has been deprecated, but others are welcome to.
  *
  * @param    string    $feed    XML serialization of the feed
  * @param    bool    $strict    Whether or not to validate the feed
  * @param    bool    $suppressWarnings Trigger errors for deprecated feed types?
  * @param    bool    $tidy    Whether or not to try and use the tidy library on input
  */
 function build(DOMDocument $model, $feed, $strict = false, $suppressWarnings = false, $tidy = false)
 {
     $options = 0;
     if ($suppressWarnings) {
         $options |= LIBXML_NOWARNING;
         $options |= LIBXML_NOERROR;
     }
     if (empty($feed)) {
         throw new XML_Feed_Parser_Exception('Invalid input: file is empty');
     }
     if (!$model->loadXML($feed, $options)) {
         if (extension_loaded('tidy') && $tidy) {
             $tidy = new tidy();
             $tidy->parseString($feed, array('input-xml' => true, 'output-xml' => true));
             $tidy->cleanRepair();
             if (!$model->loadXML((string) $tidy)) {
                 throw new XML_Feed_Parser_Exception('Invalid input: this is not ' . 'valid XML');
             }
         } else {
             throw new XML_Feed_Parser_Exception('Invalid input: this is not valid XML');
         }
     }
     /* detect feed type */
     $doc_element = $model->documentElement;
     $class = $this->determineClass($doc_element, $suppressWarnings);
     /* Instantiate feed object */
     $feed = new $class($model, $strict);
     $feed->setSanitizer(new XML_Feed_Parser_Unsafe_Sanitizer());
     return $feed;
 }

 public function repair($markup)
 {
     $tidy = new \tidy();
     $tidy->parseString($markup, self::$config, 'utf8');
     $tidy->cleanRepair();
     return $tidy . '';
 }

 /**
  * Use the HTML tidy extension to use the tidy library in-process,
  * saving the overhead of spawning a new process.
  *
  * @param string $text HTML to check
  * @param bool $stderr Whether to read result from error status instead of output
  * @param int &$retval Exit code (-1 on internal error)
  * @return string|null
  */
 protected function cleanWrapped($text, $stderr = false, &$retval = null)
 {
     if (!class_exists('tidy')) {
         wfWarn("Unable to load internal tidy class.");
         $retval = -1;
         return null;
     }
     $tidy = new \tidy();
     $tidy->parseString($text, $this->config['tidyConfigFile'], 'utf8');
     if ($stderr) {
         $retval = $tidy->getStatus();
         return $tidy->errorBuffer;
     }
     $tidy->cleanRepair();
     $retval = $tidy->getStatus();
     if ($retval == 2) {
         // 2 is magic number for fatal error
         // http://www.php.net/manual/en/function.tidy-get-status.php
         $cleansource = null;
     } else {
         $cleansource = tidy_get_output($tidy);
         if (!empty($this->config['debugComment']) && $retval > 0) {
             $cleansource .= "<!--\nTidy reports:\n" . str_replace('-->', '--&gt;', $tidy->errorBuffer) . "\n-->";
         }
     }
     return $cleansource;
 }

 private static function send_mail($server_cfg, $game_cfg, $report)
 {
     $to = "";
     $random_hash = md5(date('r', time()));
     $mime_boundary = "==Multipart_Boundary_x{$random_hash}x";
     if ($game_cfg === null) {
         $subject = "Instance Utilization Summary";
         $bcc = $server_cfg["instance_report_mail_recipients"];
         $headers = 'From: ' . $server_cfg["sender"] . "\r\n" . 'Bcc: ' . $bcc . "\r\n" . "Content-Type: multipart/mixed;" . " boundary=\"{$mime_boundary}\"" . 'X-Mailer: PHP/' . phpversion();
         $HTMLMessage = file_get_contents($report);
         $tidy = new tidy();
         $tidy->parseString($HTMLMessage);
         $tidy->cleanRepair();
         $message = "\n\n" . "--{$mime_boundary}\n" . "Content-Type:text/html; charset=\"iso-8859-1\"\n" . "Content-Transfer-Encoding: 7bit\n\n" . $tidy . "\n\n";
         $reportClass = new ReportCollector($server_cfg);
         $data = $reportClass->generateCSV();
         $message .= "--{$mime_boundary}\n" . "Content-Type:text/csv; \n" . " name=zPerfmonUtilTrend_" . date("MjY") . ".csv \n" . "Content-Transfer-Encoding: 7bit\n\n" . $data . "\n\n" . "--{$mime_boundary}--\n";
         mail($to, $subject, $message, $headers);
     } else {
         $subject = "Instance Utilization report for {$game_cfg['name']}";
         $bcc = $game_cfg["instance_report_mail_recipients"];
         $headers = 'From: ' . $server_cfg["sender"] . "\r\n" . 'Bcc: ' . $bcc . "\r\n" . 'Content-Type: text/HTML' . "\r\n" . 'X-Mailer: PHP/' . phpversion();
         $message = file_get_contents($report);
         $tidy = new tidy();
         $tidy->parseString($message);
         $tidy->cleanRepair();
         mail($to, $subject, $tidy, $headers);
     }
 }

 /**
  * Filter through Tidy
  * 
  * @param  array
  * @param  string
  * @param  bool
  * @return bool
  */
 public static function tidy(array &$headers, &$body, $uncached)
 {
     $tidy = new tidy();
     $tidy->parseString($body, array('clean' => 1, 'bare' => 1, 'hide-comments' => 1, 'doctype' => 'omit', 'indent-spaces' => 0, 'tab-size' => 0, 'wrap' => 0, 'quote-ampersand' => 0, 'output-xhtml' => true, 'quiet' => 1), 'utf8');
     $tidy->cleanRepair();
     $body = tidy_get_output($tidy);
 }

 public function __construct($content)
 {
     if (extension_loaded('tidy')) {
         // using the tidy php extension
         $tidy = new tidy();
         $tidy->parseString($content, array('output-xhtml' => true, 'numeric-entities' => true, 'wrap' => 0), 'utf8');
         $tidy->cleanRepair();
         $tidy = str_replace('xmlns="http://www.w3.org/1999/xhtml"', '', $tidy);
         $tidy = str_replace(' ', '', $tidy);
     } elseif (@shell_exec('which tidy')) {
         // using tiny through cli
         $CLI_content = escapeshellarg($content);
         $tidy = `echo {$CLI_content} | tidy --force-output 1 -n -q -utf8 -asxhtml -w 0 2> /dev/null`;
         $tidy = str_replace('xmlns="http://www.w3.org/1999/xhtml"', '', $tidy);
         $tidy = str_replace(' ', '', $tidy);
     } else {
         // no tidy library found, hence no sanitizing
         $tidy = $content;
     }
     $this->simpleXML = @simplexml_load_string($tidy, 'SimpleXMLElement', LIBXML_NOWARNING);
     if (!$this->simpleXML) {
         throw new Exception('CSSContentParser::__construct(): Could not parse content.' . ' Please check the PHP extension tidy is installed.');
     }
     parent::__construct();
 }

 public function apply($str)
 {
     if (extension_loaded('tidy') && class_exists('tidy')) {
         $config = array('doctype' => 'strict', 'drop-proprietary-attributes' => true, 'drop-font-tags' => true, 'escape-cdata' => true, 'indent' => false, 'join-classes' => false, 'join-styles' => true, 'lower-literals' => true, 'output-xhtml' => true, 'show-body-only' => true, 'wrap' => 80);
         $str = '<p>tt</p>' . $str;
         // Fixes a big issue
         $tidy = new tidy();
         $tidy->parseString($str, $config, 'utf8');
         $tidy->cleanRepair();
         $str = (string) $tidy;
         $str = preg_replace('#^<p>tt</p>\\s?#', '', $str);
     } else {
         $str = $this->miniTidy($str);
     }
     # Removing open comments, open CDATA and processing instructions
     $str = preg_replace('%<!--.*?-->%msu', '', $str);
     $str = str_replace('<!--', '', $str);
     $str = preg_replace('%<!\\[CDATA\\[.*?\\]\\]>%msu', '', $str);
     $str = str_replace('<![CDATA[', '', $str);
     # Transform processing instructions
     $str = str_replace('<?', '&gt;?', $str);
     $str = str_replace('?>', '?&lt;', $str);
     $str = html::decodeEntities($str, true);
     $this->content = '';
     xml_parse($this->parser, '<all>' . $str . '</all>');
     return $this->content;
 }

function sphsc3()
{
    $results = array();
    $i = 0;
    do {
        // 'https://content.sphsc.washington.edu/sphintra/web2/factoidsaud.asp'; //7-8
        // 'https://content.sphsc.washington.edu/sphintra/web2/res_blurb.asp';  // 11
        // 'https://content.sphsc.washington.edu/sphintra/web2/factoidscore.asp'; // 14
        // 'https://content.sphsc.washington.edu/sphintra/web2/factoidsphd.asp'; //15
        // 'https://content.sphsc.washington.edu/sphintra/web2/factoidspb.asp';  // 16, 19
        // 'https://content.sphsc.washington.edu/sphintra/web2/factoidsmed.asp';  // 17, 20
        // 'https://content.sphsc.washington.edu/sphintra/web2/factoidsug.asp'; // 18
        // 'https://content.sphsc.washington.edu/sphintra/web2/res_stone_blurb.asp';
        //$uri = 'https://content.sphsc.washington.edu/sphintra/web2/factoidscore.asp'; // 19
        // No's:
        // http://content.sphsc.washington.edu/sphintra/web2/clinic_msg.asp
        // http://content.sphsc.washington.edu/sphintra/web2/home_right.asp
        // https://content.sphsc.washington.edu/sphintra/web2/res_stone_blurb.asp
        // http://content.sphsc.washington.edu/sphintra/web2/outreach_msg.asp
        $tids = array();
        $c = array('indent' => true, 'output-xhtml' => true, 'wrap' => 200, 'hide-comments' => true);
        $response = get_page($uri);
        $tidy = new tidy();
        $tidy->parseString($response, $c, 'utf8');
        $tidy->cleanRepair();
        preg_match("/<body[^>]*>(.*?)<\\/body>/is", $tidy, $a);
        $body = str_replace(array("\n", "\r"), '', $a[1]);
        $title = some_words(strip_tags($body));
        $results[$title] = $body;
    } while ($i++ < 20);
    foreach ($results as $k => $v) {
        save_item($k, $v, $tids);
    }
}

 /**
  * 
  * Uses the tidy library to tidy HTML output.
  * 
  * @access public
  * 
  * @param string $buffer The source text to be filtered.
  *
  */
 public function filter($buffer)
 {
     $tidy = new tidy();
     $config = array('indent' => true, 'output-xhtml' => true, 'wrap' => 200);
     $tidy->parseString($buffer, $config);
     $tidy->cleanRepair();
     return $tidy->get_output();
 }

function tidy_html($html)
{
    $config = array('indent' => 2, 'output-xhtml' => true, 'doctype' => 'strict', 'wrap' => 120);
    $tidy = new tidy();
    $tidy->parseString($html, $config, 'utf8');
    $tidy->cleanRepair();
    return $tidy;
}

 public function filter(&$content)
 {
     $config = array('clean' => true, 'enclose-block-text' => true, 'enclose-text' => true, 'preserve-entities' => true, 'logical-emphasis' => true, 'char-encoding' => 'utf8', 'indent' => 'auto', 'output-xhtml' => true, 'wrap' => 200);
     $tidy = new tidy();
     $tidy->parseString($this->gethtml($content), $config, 'utf8');
     $tidy->cleanRepair();
     $content = $this->getbody((string) $tidy);
 }

 /**
  *
  * Cleans the html
  * @param string $html String cotaining the html to clean
  * @return string Cleaned an tidyed
  */
 public static function Clean($html)
 {
     $html = Html::BurnerClean($html);
     $config = array("show-body-only" => true, "alt-text" => "Pic without description", "hide-endtags" => false, "output-xhtml" => true);
     $tidy = new tidy();
     $tidy->parseString($html, $config, 'utf8');
     $tidy->cleanRepair();
     return $tidy;
 }

 protected function tidy($response)
 {
     $response = str_replace(' ', ' ', $response);
     $config = array('output-xhtml' => true);
     $tidy = new tidy();
     $tidy->parseString($response, $config, 'utf8');
     $tidy->cleanRepair();
     return (string) $tidy;
 }

 public function getURL($url)
 {
     $data = "awerawer";
     // in my code, $data is downloaded from a site
     $tidy = new tidy();
     $tidy->parseString($data, $this->tidyconfig, 'utf8');
     $tidy->cleanRepair();
     return $tidy;
 }