sessioncommunities.online/php/utils/utils.php

<?php
	$REGEX_JOIN_LINK = (function(){
		// See https://github.com/oxen-io/session-pysogs/blob/dev/administration.md
		$protocol = 'https?:';
		$hostname = '[^\/]+';
		$room_name = '[0-9A-Za-z-_]+';
		$public_key = '[[:xdigit:]]{64}';
		// Use pipe delimiter for regex to avoid escaping slashes.
		return "|$protocol//$hostname/$room_name\?public_key=$public_key|i";
	})();

	/**
	 * @param CommunityServer[] $servers
	 */
	function count_rooms($servers) {
		$rooms_total = 0;
		foreach ($servers as $server) {
			$rooms_total += count($server->rooms);
		}
		return $rooms_total;
	}
	
	function truncate($url, $len) {
		return (strlen($url) > $len + 3)
			? substr($url, 0, $len).'...'
			: $url;
	}
	
	/*
	 * Helper function for reduce_servers
	 */
	function url_is_reachable($url) {
		global $curl_connecttimeout_ms;
		global $curl_timeout_ms;
		$ch = curl_init($url);
		curl_setopt($ch, CURLOPT_NOBODY, true);
		curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
		curl_setopt($ch, CURLOPT_CONNECTTIMEOUT_MS , $curl_connecttimeout_ms);
		curl_setopt($ch, CURLOPT_TIMEOUT_MS, $curl_timeout_ms);
		curl_exec($ch);
		$retcode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
		curl_close($ch);

		log_debug($url . " is " . $retcode . ".");
		return $retcode != 0;
	}

	/*
	 * Helper function for to decide room preview link
	 */
	function url_is_200($url) {
		global $curl_connecttimeout_ms;
		global $curl_timeout_ms;
		$ch = curl_init($url);
		curl_setopt($ch, CURLOPT_NOBODY, true);
		curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
		curl_setopt($ch, CURLOPT_CONNECTTIMEOUT_MS , $curl_connecttimeout_ms);
		curl_setopt($ch, CURLOPT_TIMEOUT_MS, $curl_timeout_ms);
		curl_exec($ch);
		$retcode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
		curl_close($ch);

		log_debug($url . " is " . $retcode . ".");
		
		return $retcode == 200;
	}

    /**
	 * file_get_contents alternative that circumvents flaky routing to Chinese servers
	 */
	// Low default retries value so this doesn't run for 30 minutes
	// FIXME: Does not seem to handle 308's, behaviour not transparent.
	// TODO: Parallelize & use in CommunityServer::poll_reachable()
	function curl_get_contents(string $url, $retries = 5) {
		// use separate timeouts to reliably get data from Chinese server with repeated tries
		$connecttimeout = 2; // wait at most X seconds to connect
		$timeout = 3; // can't take longer than X seconds for the whole curl process
		$sleep = 2; // sleep between tries in seconds
		// takes at most ($timeout + $sleep) * $retries seconds

		$contents = false;
		$retcode = -1;
		$counter = 1;

		while(!$contents && $counter <= $retries && $retcode != 404) {
			$curl = curl_init($url);
			
			// curl_setopt($curl, CURLOPT_VERBOSE, true);

			curl_setopt($curl, CURLOPT_AUTOREFERER, true);
			curl_setopt($curl, CURLOPT_FOLLOWLOCATION, true);
			curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);

			curl_setopt($curl, CURLOPT_CONNECTTIMEOUT, $connecttimeout);
			curl_setopt($curl, CURLOPT_TIMEOUT, $timeout);

			$contents = curl_exec($curl);
			$retcode = curl_getinfo($curl, CURLINFO_HTTP_CODE);

			curl_close($curl);

			log_debug("Attempt #" . $counter . " for " . $url . " returned code " . $retcode . ".");
			$counter++;
			sleep($sleep);
		}

		if ($retcode != 200) {
			return false;
		} else {
			return $contents;
		}
	}

	/**
	 * Returns the scheme, hostname and optional port of a URL.
	 */
	function url_get_base(string $url, bool $include_scheme = true) {
		$url_components = parse_url($url);
		$scheme = $url_components['scheme'];
		$host = $url_components['host'];

		if (isset($url_components['port'])) {
			$port = $url_components['port'];
			$host .= ":$port";
		}

		return $include_scheme ? "$scheme://$host" : $host;
	}


	/**
	 * Extracts join links that match $REGEX_JOIN_LINK.
	 * @return string[] Sorted array of unique server join links.
	 */
	function parse_join_links($html){
		global $REGEX_JOIN_LINK;
		preg_match_all($REGEX_JOIN_LINK, $html, $match_result);
		$links = $match_result[0];
		sort($links);
		$links = array_unique($links);
		return $links;
	}

?>