<?php

namespace Drupalsearch_api_attachments_bfPluginsearch_apiprocessor;

use Drupalsearch_apiDatasourceDatasourceInterface;
use Drupalsearch_apiItemItemInterface;
use Drupalsearch_apiProcessorProcessorPluginBase;
use Drupalsearch_apiProcessorProcessorProperty;

/**
 * @SearchApiProcessor(
 *     id = "bodyfield_attachments"
 *  label = @Translation("Body Field Attachments")
 *  description = @Translation("Allows file links inside body fields to be indexed")
 * )
 */
class BodyFieldAttachments extends ProcessorPluginBase{
    /**
     * {@inheritdoc}
     */
    public function getPropertyDefinitions(DatasourceInterface $datasource = NULL){
        $properties = [];

        return $properties;
    }

    /**
     *  {@inheritdoc}
     */
    public function addFieldValues(ItemInterface $item){
        $node = $this->getNode($item->getOriginalObject());
        $body = $node->body->value;
        $files = $this->getFilesFromBody($body);

    }

    protected function getFilesFromBody($text){
        $files = array();
        if (isset($text) && !empty($text)) {
            global $base_url;
            // Parse href attributes in <a> links.
            preg_match_all('/href=['"]([^>'"]*)['"]/', $text, $matches, PREG_SET_ORDER);
            foreach ($matches as $match) {
                // Determine if the file is local. Absolute URL could be local.
                // Beginning double slashes is implicit for the current page's protocol
                // but just apply http.
                if (substr($match[1], 0, 2) == '//') {
                    $url = 'http:' . $match[1];
                }
                elseif (substr($match[1], 0, 1) == '/') {
                    $url = $base_url . $match[1];
                }
                else {
                    $url = $match[1];
                }

                $parse = parse_url($url);
                // Get absolute URL to the file location.
                $path_files = file_create_url('public://');
                if (isset($parse['host']) and $parse['host'] == $_SERVER['HTTP_HOST']) {
                    $uri = 'public://' . str_replace($path_files, '', $url);
                    // Convert back things (such as %20 back to a space).
                    $uri = urldecode($uri);

                    if (file_exists($uri)) {
                        $files_load = file_load_multiple(array(), array('uri' => $uri));
                        $file = reset($files_load);
                        if ($file) {
                            $files[] = (array) $file;
                        }
                    }
                }
            }
        }
        return $files;
    }
}