/**
* Object constructor
*
* @param string $data
* @param boolean $storeContent
* @throws NotIndexedException
*/
private function __construct($data, $storeContent)
{
//TODO check PDF >1.5 metadata extraction
//do the content extraction
$parser = new Parser();
try {
$pdf = $parser->parseContent($data);
$body = $pdf->getText();
// Store contents
if ($storeContent) {
$this->addField(Document\Field::Text('body', $body, 'UTF-8'));
} else {
$this->addField(Document\Field::UnStored('body', $body, 'UTF-8'));
}
$details = $pdf->getDetails();
// Store meta data properties
foreach ($details as $key => $value) {
$key = strtolower($key);
if ($key === 'author') {
$key = 'creator';
}
$this->addField(Document\Field::Text($key, $value, 'UTF-8'));
}
} catch (\Exception $ex) {
throw new NotIndexedException(null, null, $ex);
}
}
public static function analyze($pdf_data)
{
$parser = new PdfParser\Parser();
return new self($parser->parseContent($pdf_data));
}
/**
* Handle action related to mime type detection.
* These action can be exclude or link to handle custom content (like image, video, pdf, etc ..).
*
* @param array $mimeInfo From getMimeActionInfo() function
* @param string $effective_url Current content url
* @param string $body Content from the response
*
* @return array|null
*/
private function handleMimeAction($mimeInfo, $effective_url, $body = '')
{
if (!isset($mimeInfo['action'])) {
return;
}
$infos = array('status' => 200, 'title' => $mimeInfo['name'], 'language' => '', 'html' => '', 'url' => $effective_url, 'content_type' => $mimeInfo['mime'], 'open_graph' => array());
switch ($mimeInfo['action']) {
case 'exclude':
throw new \Exception(sprintf('This is url "%s" is blocked by mime action.', $effective_url));
case 'link':
$infos['html'] = '<a href="' . $effective_url . '">Download ' . $mimeInfo['name'] . '</a>';
if ($mimeInfo['type'] == 'image') {
$infos['html'] = '<a href="' . $effective_url . '"><img src="' . $effective_url . '" alt="' . $mimeInfo['name'] . '" /></a>';
}
if ($mimeInfo['mime'] == 'application/pdf') {
$parser = new PdfParser();
$pdf = $parser->parseContent($body);
$infos['html'] = nl2br($pdf->getText());
// update title in case of details are present
$details = $pdf->getDetails();
if (isset($details['Title']) && '' !== trim($details['Title'])) {
$infos['title'] = $details['Title'];
}
}
if ($mimeInfo['mime'] == 'text/plain') {
$infos['html'] = '<pre>' . $body . '</pre>';
}
return $infos;
}
return;
}
/**
*
* Extract content from resource
*
* @param \VDB\Spider\Resource $resource
*
* @return string
*/
public function extractContentFromResource(Resource $resource)
{
$pdf = $this->pdfParser->parseContent($resource->getResponse()->getBody(true));
return $this->stripBinaryContent($pdf->getText());
}
