$page = $rr($kid);
$resources = $rr($page->get('/Resources'));
$font = $rr($resources->get('/Font'));
$fontmap = array();
$toUnicodeMap = array();
foreach ($font->getKeys() as $key) {
$fontmap[$key] = $rr($font->get($key));
$tmp = $rr($font->get($key));
if ($tmp->has('/ToUnicode')) {
$toUnicodeMap[$key] = $rr($tmp->get('/ToUnicode'));
}
}
$charMaps = array();
foreach ($toUnicodeMap as $key => $data) {
$charMapParser = new CharMapParser();
$charMaps[$key] = $charMapParser->parse(new PdfStream($stringToStream($pdf->decodeStream($data))));
}
$contents = $rr($page->get('/Contents'));
$textObjectParser = new TextObjectParser();
echo '<pre>';
echo $textObjectParser->getText(new PdfStream($stringToStream($pdf->decodeStream($contents))), $charMaps);
echo '</pre>';
}
?>
<style>
/*<![CDATA[*/
body {
background: #eee;
padding: 10px 50px;
}
{
/**
* @todo There are still cases that will make htmlspecialchars fail without
* ENT_SUBSTITUTE
*/
return htmlspecialchars($s, ENT_QUOTES | ENT_SUBSTITUTE, 'UTF-8');
}
require __DIR__ . '/../../bootstrap.php';
$pdf = new PdfDocument();
$file = __DIR__ . '/../../../tests/mermshaus/Tests/Pdf/Parser/data/pdfs/writer-lorem.pdf';
$pdf->loadFromStream(new PdfStream(fopen($file, 'rb')));
$decodedStreams = array();
foreach ($pdf->getObjects() as $object) {
$value = $object->getValue();
if ($value instanceof PdfStreamObject) {
$decodedStreams[] = array('title' => 'Object (' . $object->getId() . ' ' . $object->getRevision() . ')', 'content' => convertInvalidUtf8CharacersToHex($pdf->decodeStream($value)));
}
}
header('Content-Type: text/html; charset=UTF-8');
?>
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<title>title</title>
<style>
/*<
