Use Apache Tika to extract PDF content in SearchWP

searchwp-customizations.php

<?php

// Use Apache Tika to extract PDF content in SearchWP.
add_filter( 'searchwp\parser\pdf', function( $content, $args ) {
  
  // Ensure this path is updated to match your Tika installation path!
  $path_to_tika = '/srv/bin/tika-app-1.18.jar';

  // Execute the command.
  $cmd = "java -jar {$path_to_tika} -t {$args['file']}";
  @exec( $cmd, $output, $exitCode );

  // If there was a problem, send the output to the debug log.
  if ( $exitCode ) {
    do_action( 'searchwp\debug\log', 'Error running Tika, exit code: ' . $exitCode );
  }

  return $output;
}, 20, 2 );