function searchwp_extract_pdf_text($post_id)
{
$indexer = new SearchWPIndexer();
return $indexer->extract_pdf_text(absint($post_id));
}
/**
* Tap in to the SearchWP indexing process and check if a WP Document Revisions post is being indexed. If it is, we're
* going to retrieve the most recent revision and extract the PDF content of that file. We'll store that data as a
* pseudo Custom Field called wp_document_revision, allowing SearchWP to search for that content
*
* @param $post_metadata
* @param $post_to_index
*
* @return bool
*/
function index_wp_document_revisions($post_metadata, $post_to_index)
{
// make sure it's a WP Document Revisions Document
if ('document' !== $post_to_index->post_type) {
return $post_metadata;
}
if (!class_exists('SearchWPIndexer')) {
return $post_metadata;
}
// get the latest Revision
$rev_id = $this->mywpdr_get_latest_revision($post_to_index);
$rev_post = get_post($rev_id);
$revision = get_post($rev_post->post_content);
// grab the PDF content from Xpdf
$indexer = new SearchWPIndexer();
$indexer->set_post($revision);
$pdf_content = $indexer->extract_pdf_text(absint($revision->ID));
// add it to the pseudo-metadata array
$post_metadata['swp_wp_document_revision'] = $pdf_content;
return $post_metadata;
}