Code Coverage |
||||||||||
Lines |
Functions and Methods |
Classes and Traits |
||||||||
| Total | |
42.42% |
56 / 132 |
|
25.00% |
3 / 12 |
CRAP | |
0.00% |
0 / 1 |
| DenyListManager | |
42.42% |
56 / 132 |
|
25.00% |
3 / 12 |
547.43 | |
0.00% |
0 / 1 |
| __construct | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
2 | |||
| singleton | |
0.00% |
0 / 8 |
|
0.00% |
0 / 1 |
6 | |||
| isIpDenyListed | |
66.67% |
2 / 3 |
|
0.00% |
0 / 1 |
2.15 | |||
| getCachedIpDenyList | |
0.00% |
0 / 1 |
|
0.00% |
0 / 1 |
2 | |||
| purgeCachedIpDenyList | |
0.00% |
0 / 2 |
|
0.00% |
0 / 1 |
2 | |||
| getIpDenyList | |
96.77% |
30 / 31 |
|
0.00% |
0 / 1 |
7 | |||
| getIpDenyListSet | |
100.00% |
3 / 3 |
|
100.00% |
1 / 1 |
3 | |||
| getDenyListKey | |
100.00% |
1 / 1 |
|
100.00% |
1 / 1 |
1 | |||
| fetchFlatDenyListHexIps | |
44.44% |
4 / 9 |
|
0.00% |
0 / 1 |
4.54 | |||
| fetchFlatDenyListHexIpsLocal | |
83.33% |
15 / 18 |
|
0.00% |
0 / 1 |
9.37 | |||
| fetchFlatDenyListHexIpsRemote | |
0.00% |
0 / 47 |
|
0.00% |
0 / 1 |
306 | |||
| fetchRemoteFile | |
0.00% |
0 / 8 |
|
0.00% |
0 / 1 |
12 | |||
| 1 | <?php |
| 2 | /** |
| 3 | * This program is free software; you can redistribute it and/or modify |
| 4 | * it under the terms of the GNU General Public License as published by |
| 5 | * the Free Software Foundation; either version 2 of the License, or |
| 6 | * (at your option) any later version. |
| 7 | * |
| 8 | * This program is distributed in the hope that it will be useful, |
| 9 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 10 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
| 11 | * GNU General Public License for more details. |
| 12 | * |
| 13 | * You should have received a copy of the GNU General Public License along |
| 14 | * with this program; if not, write to the Free Software Foundation, Inc., |
| 15 | * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. |
| 16 | * https://www.gnu.org/copyleft/gpl.html |
| 17 | * |
| 18 | * @file |
| 19 | */ |
| 20 | |
| 21 | namespace MediaWiki\Extension\StopForumSpam; |
| 22 | |
| 23 | use DomainException; |
| 24 | use MediaWiki\Http\HttpRequestFactory; |
| 25 | use MediaWiki\Logger\LoggerFactory; |
| 26 | use MediaWiki\MediaWikiServices; |
| 27 | use Psr\Log\LoggerInterface; |
| 28 | use Psr\Log\NullLogger; |
| 29 | use RuntimeException; |
| 30 | use Wikimedia\IPSet; |
| 31 | use Wikimedia\IPUtils; |
| 32 | use Wikimedia\ObjectCache\BagOStuff; |
| 33 | use Wikimedia\ObjectCache\IStoreKeyEncoder; |
| 34 | use Wikimedia\ObjectCache\WANObjectCache; |
| 35 | |
| 36 | /** |
| 37 | * @internal |
| 38 | */ |
| 39 | class DenyListManager { |
| 40 | |
| 41 | private const CACHE_VERSION = 1; |
| 42 | |
| 43 | /** @var LoggerInterface */ |
| 44 | private $logger; |
| 45 | |
| 46 | /** @var IPSet|null */ |
| 47 | private $denyListIPSet; |
| 48 | |
| 49 | /** @var self */ |
| 50 | private static $instance = null; |
| 51 | |
| 52 | public function __construct( |
| 53 | private readonly HttpRequestFactory $http, |
| 54 | private readonly BagOStuff $srvCache, |
| 55 | private readonly WANObjectCache $wanCache, |
| 56 | ?LoggerInterface $logger, |
| 57 | ) { |
| 58 | $this->logger = $logger ?: new NullLogger(); |
| 59 | } |
| 60 | |
| 61 | /** |
| 62 | * @todo use MediaWikiServices |
| 63 | * @return DenyListManager |
| 64 | */ |
| 65 | public static function singleton() { |
| 66 | if ( self::$instance == null ) { |
| 67 | $services = MediaWikiServices::getInstance(); |
| 68 | |
| 69 | $srvCache = $services->getLocalServerObjectCache(); |
| 70 | $wanCache = $services->getMainWANObjectCache(); |
| 71 | $http = $services->getHttpRequestFactory(); |
| 72 | $logger = LoggerFactory::getInstance( 'DenyList' ); |
| 73 | |
| 74 | self::$instance = new self( $http, $srvCache, $wanCache, $logger ); |
| 75 | } |
| 76 | |
| 77 | return self::$instance; |
| 78 | } |
| 79 | |
| 80 | /** |
| 81 | * Check whether the IP address is deny-listed |
| 82 | * |
| 83 | * @param string $ip An IP address |
| 84 | * @return bool |
| 85 | */ |
| 86 | public function isIpDenyListed( $ip ) { |
| 87 | if ( IPUtils::isIPAddress( $ip ) === null ) { |
| 88 | return false; |
| 89 | } |
| 90 | |
| 91 | return $this->getIpDenyListSet()->match( $ip ); |
| 92 | } |
| 93 | |
| 94 | /** |
| 95 | * Get the list of deny-listed IPs from cache only |
| 96 | * |
| 97 | * @return string[]|false List of deny-listed IP addresses; false if uncached |
| 98 | */ |
| 99 | public function getCachedIpDenyList() { |
| 100 | return $this->getIpDenyList(); |
| 101 | } |
| 102 | |
| 103 | /** |
| 104 | * Purge cache of deny-list IPs |
| 105 | * |
| 106 | * @return bool Success |
| 107 | */ |
| 108 | public function purgeCachedIpDenyList() { |
| 109 | $wanCache = $this->wanCache; |
| 110 | |
| 111 | return $wanCache->delete( $this->getDenyListKey( $wanCache ) ); |
| 112 | } |
| 113 | |
| 114 | /** |
| 115 | * Fetch the list of IPs from cache, regenerating the cache as needed |
| 116 | * |
| 117 | * @param string|null $recache Use 'recache' to force a recache |
| 118 | * @return string[] List of deny-listed IP addresses |
| 119 | */ |
| 120 | public function getIpDenyList( $recache = null ): array { |
| 121 | global $wgSFSDenyListCacheDuration; |
| 122 | |
| 123 | $srvCache = $this->srvCache; |
| 124 | $srvCacheKey = $this->getDenyListKey( $srvCache ); |
| 125 | if ( $recache === 'recache' ) { |
| 126 | $flatIpList = false; |
| 127 | } else { |
| 128 | $flatIpList = $srvCache->get( $srvCacheKey ); |
| 129 | } |
| 130 | |
| 131 | if ( $flatIpList === false ) { |
| 132 | $wanCache = $this->wanCache; |
| 133 | $flatHexIpList = $wanCache->getWithSetCallback( |
| 134 | $this->getDenyListKey( $wanCache ), |
| 135 | $wgSFSDenyListCacheDuration, |
| 136 | function () { |
| 137 | // This uses hexadecimal IP addresses to reduce network I/O |
| 138 | return $this->fetchFlatDenyListHexIps(); |
| 139 | }, |
| 140 | [ |
| 141 | 'lockTSE' => $wgSFSDenyListCacheDuration, |
| 142 | 'staleTTL' => $wgSFSDenyListCacheDuration, |
| 143 | // placeholder |
| 144 | 'busyValue' => '', |
| 145 | 'minAsOf' => ( $recache === 'recache' ) ? INF : $wanCache::MIN_TIMESTAMP_NONE |
| 146 | ] |
| 147 | ); |
| 148 | |
| 149 | $ips = []; |
| 150 | for ( $hex = strtok( $flatHexIpList, "\n" ); $hex !== false; $hex = strtok( "\n" ) ) { |
| 151 | $ips[] = IPUtils::formatHex( $hex ); |
| 152 | } |
| 153 | |
| 154 | $flatIpList = implode( "\n", $ips ); |
| 155 | |
| 156 | // Refill the local server cache if the list is not empty nor a placeholder |
| 157 | if ( $flatIpList !== '' ) { |
| 158 | $srvCache->set( |
| 159 | $srvCacheKey, |
| 160 | $flatIpList, |
| 161 | mt_rand( $srvCache::TTL_HOUR, $srvCache::TTL_DAY ) |
| 162 | ); |
| 163 | } |
| 164 | } |
| 165 | |
| 166 | return ( $flatIpList != '' ) ? explode( "\n", $flatIpList ) : []; |
| 167 | } |
| 168 | |
| 169 | /** |
| 170 | * @param string|null $recache Use 'recache' to force a recache |
| 171 | * @return IPSet |
| 172 | */ |
| 173 | public function getIpDenyListSet( $recache = null ) { |
| 174 | if ( $this->denyListIPSet === null || $recache === "recache" ) { |
| 175 | $this->denyListIPSet = new IPSet( $this->getIpDenyList( $recache ) ); |
| 176 | } |
| 177 | |
| 178 | return $this->denyListIPSet; |
| 179 | } |
| 180 | |
| 181 | /** |
| 182 | * @param IStoreKeyEncoder $cache |
| 183 | * @return string Cache key for primary deny list |
| 184 | */ |
| 185 | private function getDenyListKey( IStoreKeyEncoder $cache ) { |
| 186 | return $cache->makeGlobalKey( 'sfs-denylist-set', self::CACHE_VERSION ); |
| 187 | } |
| 188 | |
| 189 | /** |
| 190 | * @return string Newline separated list of SFS deny-listed IP addresses |
| 191 | */ |
| 192 | private function fetchFlatDenyListHexIps(): string { |
| 193 | global $wgSFSIPListLocation, $wgSFSValidateIPListLocationMD5; |
| 194 | |
| 195 | if ( $wgSFSIPListLocation === false ) { |
| 196 | throw new DomainException( '$wgSFSIPListLocation has not been configured.' ); |
| 197 | } |
| 198 | |
| 199 | if ( is_file( $wgSFSIPListLocation ) ) { |
| 200 | $ipList = $this->fetchFlatDenyListHexIpsLocal( $wgSFSIPListLocation ); |
| 201 | } else { |
| 202 | $ipList = $this->fetchFlatDenyListHexIpsRemote( |
| 203 | $wgSFSIPListLocation, |
| 204 | $wgSFSValidateIPListLocationMD5 |
| 205 | ); |
| 206 | } |
| 207 | |
| 208 | return $ipList; |
| 209 | } |
| 210 | |
| 211 | /** |
| 212 | * Fetch gunzipped/unzipped SFS deny list from local file |
| 213 | * |
| 214 | * @param string $listFilePath Local file path |
| 215 | * @return string Newline separated list of SFS deny-listed IP addresses |
| 216 | */ |
| 217 | private function fetchFlatDenyListHexIpsLocal( string $listFilePath ): string { |
| 218 | global $wgSFSIPThreshold; |
| 219 | |
| 220 | $fh = fopen( $listFilePath, 'rb' ); |
| 221 | if ( !$fh ) { |
| 222 | throw new DomainException( "wgSFSIPListLocation file handle could not be obtained." ); |
| 223 | } |
| 224 | |
| 225 | $ipList = []; |
| 226 | |
| 227 | while ( !feof( $fh ) ) { |
| 228 | $ipData = fgetcsv( $fh, 4096, ',', '"', "\\" ); |
| 229 | if ( $ipData === false ) { |
| 230 | break; |
| 231 | } |
| 232 | |
| 233 | if ( $ipData === null || $ipData === [ null ] ) { |
| 234 | continue; |
| 235 | } |
| 236 | if ( isset( $ipData[1] ) && $ipData[1] < $wgSFSIPThreshold ) { |
| 237 | continue; |
| 238 | } |
| 239 | |
| 240 | $ip = (string)$ipData[0]; |
| 241 | $hex = IPUtils::toHex( $ip ); |
| 242 | if ( $hex === false ) { |
| 243 | // invalid address |
| 244 | continue; |
| 245 | } |
| 246 | |
| 247 | $ipList[] = $hex; |
| 248 | } |
| 249 | |
| 250 | return implode( "\n", $ipList ); |
| 251 | } |
| 252 | |
| 253 | /** |
| 254 | * Fetch SFS IP deny list file from SFS site and returns an array of IPs |
| 255 | * (https://www.stopforumspam.com/downloads - use gz files) |
| 256 | * |
| 257 | * @param string $uri SFS vendor or third-party URL to the list |
| 258 | * @param string|null $md5uri SFS vendor URL to the MD5 of the list |
| 259 | * @return string Newline-separated list of SFS deny-listed IP addresses |
| 260 | */ |
| 261 | private function fetchFlatDenyListHexIpsRemote( string $uri, ?string $md5uri ): string { |
| 262 | global $wgSFSProxy, $wgSFSIPThreshold; |
| 263 | |
| 264 | // Hacky, but needed to keep a sensible default value of $wgSFSIPListLocation for |
| 265 | // users, whilst also preventing HTTP requests for other extension when they call |
| 266 | // permission related hooks that mean the code here gets executed too... |
| 267 | // So, if we have a URL, and try and do a HTTP request whilst in MW_PHPUNIT_TEST, |
| 268 | // just fallback to loading sample_denylist_all.txt as a file... |
| 269 | // See also: T262443, T265628, T353001. |
| 270 | if ( defined( 'MW_PHPUNIT_TEST' ) || defined( 'MW_QUIBBLE_CI' ) ) { |
| 271 | $filePath = dirname( __DIR__ ) . '/tests/phpunit/sample_denylist_all.txt'; |
| 272 | return $this->fetchFlatDenyListHexIpsLocal( $filePath ); |
| 273 | } |
| 274 | |
| 275 | if ( !filter_var( $uri, FILTER_VALIDATE_URL ) ) { |
| 276 | throw new DomainException( "wgSFSIPListLocation does not appear to be a valid URL." ); |
| 277 | } |
| 278 | |
| 279 | // check for zlib function for later processing |
| 280 | if ( !function_exists( 'gzdecode' ) ) { |
| 281 | throw new RuntimeException( "Zlib does not appear to be configured for php!" ); |
| 282 | } |
| 283 | |
| 284 | $options = [ 'followRedirects' => true ]; |
| 285 | if ( $wgSFSProxy !== false ) { |
| 286 | $options['proxy'] = $wgSFSProxy; |
| 287 | } |
| 288 | |
| 289 | $fileData = $this->fetchRemoteFile( $uri, $options ); |
| 290 | if ( $fileData === '' ) { |
| 291 | $this->logger->error( __METHOD__ . ": SFS IP list could not be fetched!" ); |
| 292 | |
| 293 | return ''; |
| 294 | } |
| 295 | |
| 296 | if ( is_string( $md5uri ) && $md5uri !== '' ) { |
| 297 | // check vendor-provided md5 |
| 298 | $fileDataMD5 = $this->fetchRemoteFile( $md5uri, $options ); |
| 299 | if ( $fileDataMD5 === '' ) { |
| 300 | $this->logger->error( __METHOD__ . ": SFS IP list MD5 could not be fetched!" ); |
| 301 | return ''; |
| 302 | } |
| 303 | |
| 304 | if ( md5( $fileData ) !== $fileDataMD5 ) { |
| 305 | $this->logger->error( __METHOD__ . ": SFS IP list has an unexpected MD5!" ); |
| 306 | return ''; |
| 307 | } |
| 308 | } |
| 309 | |
| 310 | // ungzip and process vendor file |
| 311 | $csvTable = gzdecode( $fileData ); |
| 312 | if ( $csvTable === false ) { |
| 313 | $this->logger->error( __METHOD__ . ": SFS IP file contents could not be decoded!" ); |
| 314 | return ''; |
| 315 | } |
| 316 | |
| 317 | $ipList = []; |
| 318 | $scoreSkipped = 0; |
| 319 | $rows = 0; |
| 320 | |
| 321 | for ( $line = strtok( $csvTable, "\n" ); $line !== false; $line = strtok( "\n" ) ) { |
| 322 | |
| 323 | $rows++; |
| 324 | |
| 325 | $ipData = str_getcsv( $line, ",", "\"", "\\" ); |
| 326 | $ip = (string)$ipData[0]; |
| 327 | $score = (int)$ipData[1]; |
| 328 | |
| 329 | if ( $score && ( $score < $wgSFSIPThreshold ) ) { |
| 330 | $scoreSkipped++; |
| 331 | continue; |
| 332 | } |
| 333 | |
| 334 | $hex = IPUtils::toHex( $ip ); |
| 335 | if ( $hex === false ) { |
| 336 | // invalid address |
| 337 | continue; |
| 338 | } |
| 339 | |
| 340 | $ipList[] = $hex; |
| 341 | } |
| 342 | |
| 343 | if ( $scoreSkipped > 0 ) { |
| 344 | $this->logger->info( |
| 345 | __METHOD__ . ": {$rows} rows were processed. " |
| 346 | . "{$scoreSkipped} were skipped because their score was less than {$wgSFSIPThreshold}." |
| 347 | ); |
| 348 | } |
| 349 | |
| 350 | return implode( "\n", $ipList ); |
| 351 | } |
| 352 | |
| 353 | /** |
| 354 | * Fetch a network file's contents via HttpRequestFactory |
| 355 | * |
| 356 | * @param string $fileUrl |
| 357 | * @param array $httpOptions |
| 358 | * @return string |
| 359 | */ |
| 360 | private function fetchRemoteFile( string $fileUrl, array $httpOptions ): string { |
| 361 | $req = $this->http->create( $fileUrl, $httpOptions, __METHOD__ ); |
| 362 | |
| 363 | $status = $req->execute(); |
| 364 | if ( !$status->isOK() ) { |
| 365 | throw new RuntimeException( "Failed to download resource at {$fileUrl}" ); |
| 366 | } |
| 367 | |
| 368 | $code = $req->getStatus(); |
| 369 | if ( $code !== 200 ) { |
| 370 | throw new RuntimeException( "Unexpected HTTP {$code} response from {$fileUrl}" ); |
| 371 | } |
| 372 | |
| 373 | return (string)$req->getContent(); |
| 374 | } |
| 375 | } |