YGGo/config/app.php.txt

<?php

// Debug
ini_set('display_errors', '1');
ini_set('display_startup_errors', '1');
error_reporting(E_ALL);

// Website
define('WEBSITE_DOMAIN', (issue($_SERVER['HTTP_HOST']) ? 'http://' . $_SERVER['HTTP_HOST'] : ''));
define('WEBSITE_PAGINATION_SEARCH_RESULTS_LIMIT', 100);
define('WEBSITE_IDENTICON_IMAGE_CACHE', true);

// Database
define('DB_HOST', 'localhost');
define('DB_PORT', 3306);
define('DB_NAME', '');
define('DB_USERNAME', '');
define('DB_PASSWORD', '');

// Sphinx
define('SPHINX_HOST', '127.0.0.1');
define('SPHINX_PORT', 9306);

// Crawler settings

/*
 * Pages (URI) processing limit in the crawler.php queue
 *
 * This option related to CRAWL_PAGE_SECONDS_OFFSET value
 * and the crontab task frequency (https://github.com/YGGverse/YGGo#crontab)
 *
 * Usually up to 20 pages per minute,
 * to prevent websites overload by sending GET crawling requests
 *
 */
define('CRAWL_PAGE_LIMIT', 10);

/*
 * Renew page index by timing offset provided
 *
 * This option works with CRAWL_PAGE_LIMIT step queue
 *
 * Pay attention, that CRAWL_PAGE_LIMIT + CRAWL_PAGE_SECONDS_OFFSET pair
 * must have enought value to crawl all pages collected in the DB index
 *
 * or the crawler can stuck in queue
 *
 */
define('CRAWL_PAGE_SECONDS_OFFSET', 3600);

/*
 * Only URL addresses match this rule will be auto-crawled
 *
 */
define('CRAWL_URL_REGEXP', '/^.*$/ui'); // ipv6 only '/^http:\/\/\[[\w:]+\].*$/ui'

/*
 * Pages limit per new host by default
 *
 * Crawler stops indexing on this limit reach to prevent disk overuse
 *
 * Custom rule for specified host could be provided in the DB `host`.`crawlPageLimit` field
 *
 */
define('CRAWL_HOST_DEFAULT_PAGES_LIMIT', 1000);

/*
 * Set default auto-crawl status for new host added
 *
 * true  - crawler autostart pages indexer limited by CRAWL_HOST_DEFAULT_PAGES_LIMIT
 * false - requires manual validation by the moderator in the DB `host`.`status` field
 *
 * This option also disable host in the search results
 *
 */
define('CRAWL_HOST_DEFAULT_STATUS', true);

/*
 * Index only meta tags to prevent disk overuse
 * or false to save meta tags + overall plain text page content
 *
 * Custom rule for specified host could be provided in the DB `host`.`crawlPageMetaOnly` field
 *
 * This option able to change search results relevance
 *
 */
define('CRAWL_HOST_DEFAULT_META_ONLY', false);

/*
 * Default robots.txt rules on remote file not exists
 * The crawler able to overwrite these rules
 *
 * Presets
 * yggdrasil: /database/yggdrasil/host.robots.md
 *
 */
define('CRAWL_ROBOTS_DEFAULT_RULES', null); // string|null

/*
 * Permanent rules that append to the robots.txt if exists else CRAWL_ROBOTS_DEFAULT_RULES
 * The crawler does not overwrite these rules
 *
 * Presets
 * yggdrasil: /database/yggdrasil/host.robotsPostfix.md
 *
 */
define('CRAWL_ROBOTS_POSTFIX_RULES', null); // string|null

// Cleaner settings
define('CLEAN_HOST_LIMIT', 20);
define('CLEAN_HOST_SECONDS_OFFSET', 3600);