YGGo/config/app.php.txt

<?php

/*
 * YGGo! - Distributed & Open Source Web Search Engine
 *
 * MIT License

 * Copyright (c) 2023 YGGverse

 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:

 * The above copyright notice and this permission notice shall be included in all
 * copies or substantial portions of the Software.

 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 *
 * Default configuration file example
 * Production name: app.php
 *
 * Project home page
 * https://github.com/YGGverse/YGGo
 *
 * Get support
 * https://github.com/YGGverse/YGGo/issues
 *
 */

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

// Website

/*
 * Project domain, without slash on postfix
 *
 */
define('WEBSITE_DOMAIN', '');

/*
 * Page search results before show the read more link
 *
 */
define('WEBSITE_PAGINATION_SEARCH_PAGE_RESULTS_LIMIT', 100);

/*
 * Save ident icons to the static webp cache (placed in storage/cache) to prevent CPU overload
 *
 * or false - to generate every time on request
 *
 */
define('WEBSITE_IDENTICON_IMAGE_CACHE', true);

// Database
define('DB_HOST', '127.0.0.1');
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);

// Memcached
define('MEMCACHED_HOST', '127.0.0.1');
define('MEMCACHED_PORT', 11211);

// Snaps

/*
 * Storage nodes configuration
 *
 * Supports optional single 'localhost' and multiple 'FTP' servers
 *
 * Comment specified node to disable specified connection
 *
 * Make empty array to disable snaps or set quote.mime = false or quote.size = 0 to disable specified instance
 *
 */
define('SNAP_STORAGE', json_encode((object)
        [
                'localhost' => [ // @TODO see https://github.com/YGGverse/YGGo#roadmap
                        'storage-1' => [
                                'directory' => __DIR__ . '/../storage/snap/hps/',
                                'quota'     => [
                                        'mime' => false,
                                        'size' => 10000000024, // @TODO
                                        'request' => [ // @TODO
                                                'download' => [
                                                        'size'    => 10000024,
                                                        'seconds' => 60*60
                                                ]
                                        ]
                                ]
                        ],
                        // ...
                ],
                'ftp'       => [
                        'storage-1' => [
                                'port'      => 21,
                                'host'      => '',
                                'username'  => '',
                                'password'  => '',
                                'directory' => '/snap',
                                'timeout'   => 30,
                                'passive'   => true,
                                'quota'     => [
                                        'mime' => 'text/html,application/xhtml+xml,text/plain,image/webp,image/png,image/gif,image/jpeg,image/ico',
                                        'size' => 10000000024, // @TODO
                                        'request' => [ // @TODO
                                                'download' => [
                                                        'size'    => 10000024,
                                                        'seconds' => 60*60
                                                ]
                                        ]
                                ],
                        ],
                        // ...
                ]
        ]
));

// Proxy settings

/*
 * Search proxy User Agent name
 *
 * Shared to other hosts through CURL requests by search proxy
 *
 */
define('PROXY_CURLOPT_USERAGENT', 'YGGo Search Proxy ( https://github.com/YGGverse/YGGo )');

// Crawl settings

/*
 * Save crawler debug to `logCrawler` table
 *
 */
define('CRAWL_LOG_ENABLED', true);

/*
 * Auto clean `logCrawler` items older seconds offset
 *
 */
define('CRAWL_LOG_SECONDS_OFFSET', 60*60*24*30);

/*
 * Crawler / Bot User Agent name
 *
 * Shared to other hosts through CURL requests by crawler
 *
 */
define('CRAWL_CURLOPT_USERAGENT', 'YGGo Search Crawler / Bot ( https://github.com/YGGverse/YGGo )');

/*
 * Skip curl download on response data size reached
 *
 * See also: CURLOPT_TIMEOUT (library/curl.php)
 *
 */
define('CRAWL_CURLOPT_PROGRESSFUNCTION_DOWNLOAD_SIZE_LIMIT', 10485760);

/*
 * Stop crawler on disk quota reached (Mb)
 *
 */
define('CRAWL_STOP_DISK_QUOTA_MB_LEFT', 500);

/*
 * 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
 *
 * Set 0 to disable
 *
 */
define('CRAWL_PAGE_LIMIT', 20);

/*
 * Manifest (URI) processing limit in the crawler.php queue
 *
 * Used to collect distributed data index
 * that match CRAWL_URL_REGEXP & CRAWL_MANIFEST_API_VERSION
 *
 * This option related to CRAWL_MANIFEST_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
 *
 * Set 0 to disable
 *
 */
define('CRAWL_MANIFEST_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 enough value to crawl all pages collected in the DB index
 *
 * or the crawler can stuck in queue
 *
 */
define('CRAWL_PAGE_SECONDS_OFFSET', 60*60*24*30*12);

/*
 * Renew home page index by timing offset provided
 *
 * Used for new pages scanning in highter priority
 *
 * This option works with CRAWL_PAGE_SECONDS_OFFSET and CRAWL_PAGE_LIMIT step queue
 *
 * Pay attention, that CRAWL_PAGE_LIMIT + CRAWL_PAGE_SECONDS_OFFSET pair
 * must have enough value to crawl all pages collected in the DB index
 *
 * or the crawler can stuck in queue
 *
 */
define('CRAWL_PAGE_HOME_SECONDS_OFFSET', 60*60*24*7*30);

/*
 * Index pages match MIME types
 *
 * comma separated
 *
 */
define('CRAWL_PAGE_MIME_INDEX', 'text/html,application/xhtml+xml,text/plain,image/webp,image/png,image/gif,image/jpeg,image/ico,image/svg+xml,video/mp4,video/ogg,video/webm,audio/mpeg,audio/ogg,audio/wav,audio/mp4,audio/aac,audio/aacp,audio/webm,audio/x-caf,audio/x-mpegurl,audio/flac');

/*
 * Renew manifests index by timing offset provided
 *
 * This option works with CRAWL_MANIFEST_LIMIT step queue
 *
 * Pay attention, that CRAWL_MANIFEST_LIMIT + CRAWL_MANIFEST_SECONDS_OFFSET pair
 * must have enough value to crawl all manifests collected in the DB index
 *
 * or the crawler can stuck in queue
 *
 */
define('CRAWL_MANIFEST_SECONDS_OFFSET', 60*60*24*30);

/*
 * Only URL addresses match this rule will be auto-crawled
 *
 */
define('CRAWL_URL_REGEXP', '/^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', 100000);

/*
 * 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
 * or false to save meta tags + base64 encoded page content in the `hostPage`.`data` field
 *
 * Custom rule for specified host could be provided in the DB `host`.`crawlMetaOnly` field
 *
 * Warning!
 * this option disabled requires huge disk storage,
 * it's experimental feature, oriented for index operations
 *
 */
define('CRAWL_HOST_DEFAULT_META_ONLY', true);

/*
 * Not suitable/safe for work status for new host by default
 *
 * Could be filtered in search results
 *
 * Custom rule for specified host could be provided in the DB `host`.`nsfw` field
 *
 */
define('CRAWL_HOST_DEFAULT_NSFW', false);

/*
 * Collect sitemap index when available
 *
 * At this moment, works with CRAWL_ROBOTS_SECONDS_OFFSET/CRAWL_ROBOTS_LIMIT options enabled only
 *
 * When sitemap path not provided in robots.txt, crawler scans default /sitemap.xml
 *
 * true|false
 *
 */
define('CRAWL_SITEMAPS', true);

/*
 * Renew robots.txt index by timing offset provided
 *
 */
define('CRAWL_ROBOTS_SECONDS_OFFSET', 60*60*24*7);

/*
 * Hosts Robots.txt processing limit in the crawler.php queue
 *
 * Set 0 to disable
 *
 */
define('CRAWL_ROBOTS_LIMIT', 1);

/*
 * 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

/*
 * Generates hostPageDom index based on hostPage.data field
 *
 * Could be useful for building semantical index query (config/sphinx.conf.txt)
 *
 * At this moment feature available in the CLI only (cli/yggo.php)
 *
 */
define('CRAWL_HOST_PAGE_DOM_SELECTORS', 'h1;h2;h3;h4;h5;h6');

/*
 * Strip HTML in the CRAWL_HOST_PAGE_DOM_SELECTORS content
 *
 */
define('CRAWL_HOST_PAGE_DOM_STRIP_TAGS', true);

/*
 * Look for third-party manifests to collect distributed index
 *
 * API address provided in yggo meta tag
 * will be stored in the `manifest` DB table
 *
 * Collecting URL that match CRAWL_URL_REGEXP condition
 *
 */
define('CRAWL_MANIFEST', true);

/*
 * Manifest API version compatibility
 *
 */
define('CRAWL_MANIFEST_API_VERSION', 0.10);

/*
 * Set default auto-crawl status for new manifest added
 *
 * true  - crawler autostart manifest indexer
 * false - requires manual validation by the moderator in the DB `manifest`.`status` field
 *
 * This option applying on CRAWL_MANIFEST enabled
 *
 */
define('CRAWL_MANIFEST_DEFAULT_STATUS', true);

// Cleaner settings

/*
 * Save cleaner debug to `logCleaner` table
 *
 */
define('CLEAN_LOG_ENABLED', true);

/*
 * Auto clean `logCleaner` items older seconds offset
 *
 */
define('CLEAN_LOG_SECONDS_OFFSET', 60*60*24*30);

/*
 * Hosts limit per crontab execution step (https://github.com/YGGverse/YGGo#crontab)
 *
 * This option works with CLEAN_HOST_SECONDS_OFFSET
 *
 * The value depends of CPU resources available
 *
 */
define('CLEAN_HOST_LIMIT', 20);

/*
 * Apply cleaning rules to page older than value provided
 *
 * This option works with CLEAN_HOST_LIMIT step queue
 *
 * Pay attention, that CLEAN_HOST_LIMIT + CLEAN_HOST_SECONDS_OFFSET pair
 * must have enough value to process all pages in the DB index
 *
 * or the cleaner can stuck in queue
 *
 */
define('CLEAN_HOST_SECONDS_OFFSET', 60*60*24*30);

/*
 * Remove page ban after following time
 *
 * This option used in crawler and search page
 * to prevent extra http requests to unavailable or not condition resources
 *
 */
define('CLEAN_PAGE_BAN_SECONDS_OFFSET', 60*60*24*30);

/*
 * Remove page description history after following time
 *
 */
define('CLEAN_PAGE_DESCRIPTION_OFFSET', 60*60*24*30*12*10);

/*
 * Remove page DOM history after following time
 *
 */
define('CLEAN_PAGE_DOM_OFFSET', 60*60*24*30*12*10);

/*
 * Database tables optimization
 *
 * Reorganizes the physical storage of table data and associated index data,
 * to reduce storage space and improve I/O efficiency when accessing the tables.
 * Read more: https://www.forknerds.com/reduce-the-size-of-mysql/#Shrink_and_Optimize_MySQL
 *
 * When enabled - requires enough of RAM
 *
 */
define('CLEAN_DB_TABLES_OPTIMIZATION', false);

// API settings

/*
 * JSON API features
 *
 * When false - every the actions settings below will be ignored
 *
 */
define('API_ENABLED', true);

/*
 * Search API
 *
 * When false - API_SEARCH_PAGINATION_RESULTS_LIMIT will be ignored
 *
 */
define('API_SEARCH_ENABLED', true);

/*
 * Search results per page
 *
 */
define('API_SEARCH_PAGINATION_RESULTS_LIMIT', 20);

/*
 * Hosts distribution API
 *
 * When false - API_HOSTS_FIELDS will be ignored
 *
 */
define('API_HOSTS_ENABLED', true);

/*
 * Database host fields comma separated or * to share all the fields
 *
 */
define('API_HOSTS_FIELDS',
       '`host`.`scheme`,
        `host`.`name`,
        `host`.`port`,
        `host`.`crawlPageLimit`,
        `host`.`robots`,
        `host`.`robotsPostfix`,
        `host`.`nsfw`,
        `host`.`timeAdded`,
        `host`.`timeUpdated`,
        (SELECT COUNT(*) FROM `hostPage` WHERE `hostPage`.`hostId` = `host`.`hostId`) AS `hostPagesTotal`');

/*
 * Manifest API
 *
 * Application meta sharing between YGGo remote nodes
 *
 * When true - make this node public for distributed index sharing
 *
 */
define('API_MANIFEST_ENABLED', true);