includes/filerepo/backend/FileBackend.php

   1 <?php
   2 /**
   3  * @defgroup FileBackend File backend
   4  * @ingroup  FileRepo
   5  *
   6  * File backend is used to interact with file storage systems,
   7  * such as the local file system, NFS, or cloud storage systems.
   8  */
   9
  10 /**
  11  * Base class for all file backends.
  12  *
  13  * This program is free software; you can redistribute it and/or modify
  14  * it under the terms of the GNU General Public License as published by
  15  * the Free Software Foundation; either version 2 of the License, or
  16  * (at your option) any later version.
  17  *
  18  * This program is distributed in the hope that it will be useful,
  19  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  20  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  21  * GNU General Public License for more details.
  22  *
  23  * You should have received a copy of the GNU General Public License along
  24  * with this program; if not, write to the Free Software Foundation, Inc.,
  25  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  26  * http://www.gnu.org/copyleft/gpl.html
  27  *
  28  * @file
  29  * @ingroup FileBackend
  30  * @author Aaron Schulz
  31  */
  32
  33 /**
  34  * @brief Base class for all file backend classes (including multi-write backends).
  35  *
  36  * This class defines the methods as abstract that subclasses must implement.
  37  * Outside callers can assume that all backends will have these functions.
  38  *
  39  * All "storage paths" are of the format "mwstore://<backend>/<container>/<path>".
  40  * The <path> portion is a relative path that uses UNIX file system (FS) notation,
  41  * though any particular backend may not actually be using a local filesystem.
  42  * Therefore, the relative paths are only virtual.
  43  *
  44  * Backend contents are stored under wiki-specific container names by default.
  45  * For legacy reasons, this has no effect for the FS backend class, and per-wiki
  46  * segregation must be done by setting the container paths appropriately.
  47  *
  48  * FS-based backends are somewhat more restrictive due to the existence of real
  49  * directory files; a regular file cannot have the same name as a directory. Other
  50  * backends with virtual directories may not have this limitation. Callers should
  51  * store files in such a way that no files and directories are under the same path.
  52  *
  53  * Methods should avoid throwing exceptions at all costs.
  54  * As a corollary, external dependencies should be kept to a minimum.
  55  *
  56  * @ingroup FileBackend
  57  * @since 1.19
  58  */
  59 abstract class FileBackend {
  60         protected $name; // string; unique backend name
  61         protected $wikiId; // string; unique wiki name
  62         protected $readOnly; // string; read-only explanation message
  63         protected $parallelize; // string; when to do operations in parallel
  64         protected $concurrency; // integer; how many operations can be done in parallel
  65
  66         /** @var LockManager */
  67         protected $lockManager;
  68         /** @var FileJournal */
  69         protected $fileJournal;
  70
  71         /**
  72          * Create a new backend instance from configuration.
  73          * This should only be called from within FileBackendGroup.
  74          *
  75          * $config includes:
  76          *     'name'        : The unique name of this backend.
  77          *                     This should consist of alphanumberic, '-', and '_' characters.
  78          *                     This name should not be changed after use.
  79          *     'wikiId'      : Prefix to container names that is unique to this wiki.
  80          *                     It should only consist of alphanumberic, '-', and '_' characters.
  81          *     'lockManager' : Registered name of a file lock manager to use.
  82          *     'fileJournal' : File journal configuration; see FileJournal::factory().
  83          *                     Journals simply log changes to files stored in the backend.
  84          *     'readOnly'    : Write operations are disallowed if this is a non-empty string.
  85          *                     It should be an explanation for the backend being read-only.
  86          *     'parallelize' : When to do file operations in parallel (when possible).
  87          *                     Allowed values are "implicit", "explicit" and "off".
  88          *     'concurrency' : How many file operations can be done in parallel.
  89          *
  90          * @param $config Array
  91          */
  92         public function __construct( array $config ) {
  93                 $this->name = $config['name'];
  94                 if ( !preg_match( '!^[a-zA-Z0-9-_]{1,255}$!', $this->name ) ) {
  95                         throw new MWException( "Backend name `{$this->name}` is invalid." );
  96                 }
  97                 $this->wikiId = isset( $config['wikiId'] )
  98                         ? $config['wikiId']
  99                         : wfWikiID(); // e.g. "my_wiki-en_"
 100                 $this->lockManager = ( $config['lockManager'] instanceof LockManager )
 101                         ? $config['lockManager']
 102                         : LockManagerGroup::singleton()->get( $config['lockManager'] );
 103                 $this->fileJournal = isset( $config['fileJournal'] )
 104                         ? FileJournal::factory( $config['fileJournal'], $this->name )
 105                         : FileJournal::factory( array( 'class' => 'NullFileJournal' ), $this->name );
 106                 $this->readOnly = isset( $config['readOnly'] )
 107                         ? (string)$config['readOnly']
 108                         : '';
 109                 $this->parallelize = isset( $config['parallelize'] )
 110                         ? (string)$config['parallelize']
 111                         : 'off';
 112                 $this->concurrency = isset( $config['concurrency'] )
 113                         ? (int)$config['concurrency']
 114                         : 50;
 115         }
 116
 117         /**
 118          * Get the unique backend name.
 119          * We may have multiple different backends of the same type.
 120          * For example, we can have two Swift backends using different proxies.
 121          *
 122          * @return string
 123          */
 124         final public function getName() {
 125                 return $this->name;
 126         }
 127
 128         /**
 129          * Check if this backend is read-only
 130          *
 131          * @return bool
 132          */
 133         final public function isReadOnly() {
 134                 return ( $this->readOnly != '' );
 135         }
 136
 137         /**
 138          * Get an explanatory message if this backend is read-only
 139          *
 140          * @return string|bool Returns false if the backend is not read-only
 141          */
 142         final public function getReadOnlyReason() {
 143                 return ( $this->readOnly != '' ) ? $this->readOnly : false;
 144         }
 145
 146         /**
 147          * This is the main entry point into the backend for write operations.
 148          * Callers supply an ordered list of operations to perform as a transaction.
 149          * Files will be locked, the stat cache cleared, and then the operations attempted.
 150          * If any serious errors occur, all attempted operations will be rolled back.
 151          *
 152          * $ops is an array of arrays. The outer array holds a list of operations.
 153          * Each inner array is a set of key value pairs that specify an operation.
 154          *
 155          * Supported operations and their parameters:
 156          * a) Create a new file in storage with the contents of a string
 157          *     array(
 158          *         'op'                  => 'create',
 159          *         'dst'                 => <storage path>,
 160          *         'content'             => <string of new file contents>,
 161          *         'overwrite'           => <boolean>,
 162          *         'overwriteSame'       => <boolean>
 163          *     )
 164          * b) Copy a file system file into storage
 165          *     array(
 166          *         'op'                  => 'store',
 167          *         'src'                 => <file system path>,
 168          *         'dst'                 => <storage path>,
 169          *         'overwrite'           => <boolean>,
 170          *         'overwriteSame'       => <boolean>
 171          *     )
 172          * c) Copy a file within storage
 173          *     array(
 174          *         'op'                  => 'copy',
 175          *         'src'                 => <storage path>,
 176          *         'dst'                 => <storage path>,
 177          *         'overwrite'           => <boolean>,
 178          *         'overwriteSame'       => <boolean>
 179          *     )
 180          * d) Move a file within storage
 181          *     array(
 182          *         'op'                  => 'move',
 183          *         'src'                 => <storage path>,
 184          *         'dst'                 => <storage path>,
 185          *         'overwrite'           => <boolean>,
 186          *         'overwriteSame'       => <boolean>
 187          *     )
 188          * e) Delete a file within storage
 189          *     array(
 190          *         'op'                  => 'delete',
 191          *         'src'                 => <storage path>,
 192          *         'ignoreMissingSource' => <boolean>
 193          *     )
 194          * f) Do nothing (no-op)
 195          *     array(
 196          *         'op'                  => 'null',
 197          *     )
 198          *
 199          * Boolean flags for operations (operation-specific):
 200          * 'ignoreMissingSource' : The operation will simply succeed and do
 201          *                         nothing if the source file does not exist.
 202          * 'overwrite'           : Any destination file will be overwritten.
 203          * 'overwriteSame'       : An error will not be given if a file already
 204          *                         exists at the destination that has the same
 205          *                         contents as the new contents to be written there.
 206          *
 207          * $opts is an associative of boolean flags, including:
 208          * 'force'               : Operation precondition errors no longer trigger an abort.
 209          *                         Any remaining operations are still attempted. Unexpected
 210          *                         failures may still cause remaning operations to be aborted.
 211          * 'nonLocking'          : No locks are acquired for the operations.
 212          *                         This can increase performance for non-critical writes.
 213          *                         This has no effect unless the 'force' flag is set.
 214          * 'allowStale'          : Don't require the latest available data.
 215          *                         This can increase performance for non-critical writes.
 216          *                         This has no effect unless the 'force' flag is set.
 217          * 'nonJournaled'        : Don't log this operation batch in the file journal.
 218          *                         This limits the ability of recovery scripts.
 219          * 'parallelize'         : Try to do operations in parallel when possible.
 220          *
 221          * Remarks on locking:
 222          * File system paths given to operations should refer to files that are
 223          * already locked or otherwise safe from modification from other processes.
 224          * Normally these files will be new temp files, which should be adequate.
 225          *
 226          * Return value:
 227          * This returns a Status, which contains all warnings and fatals that occured
 228          * during the operation. The 'failCount', 'successCount', and 'success' members
 229          * will reflect each operation attempted. The status will be "OK" unless:
 230          *     a) unexpected operation errors occurred (network partitions, disk full...)
 231          *     b) significant operation errors occured and 'force' was not set
 232          *
 233          * @param $ops Array List of operations to execute in order
 234          * @param $opts Array Batch operation options
 235          * @return Status
 236          */
 237         final public function doOperations( array $ops, array $opts = array() ) {
 238                 if ( $this->isReadOnly() ) {
 239                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 240                 }
 241                 if ( empty( $opts['force'] ) ) { // sanity
 242                         unset( $opts['nonLocking'] );
 243                         unset( $opts['allowStale'] );
 244                 }
 245                 $opts['concurrency'] = 1; // off
 246                 if ( $this->parallelize === 'implicit' ) {
 247                         if ( !isset( $opts['parallelize'] ) || $opts['parallelize'] ) {
 248                                 $opts['concurrency'] = $this->concurrency;
 249                         }
 250                 } elseif ( $this->parallelize === 'explicit' ) {
 251                         if ( !empty( $opts['parallelize'] ) ) {
 252                                 $opts['concurrency'] = $this->concurrency;
 253                         }
 254                 }
 255                 return $this->doOperationsInternal( $ops, $opts );
 256         }
 257
 258         /**
 259          * @see FileBackend::doOperations()
 260          */
 261         abstract protected function doOperationsInternal( array $ops, array $opts );
 262
 263         /**
 264          * Same as doOperations() except it takes a single operation.
 265          * If you are doing a batch of operations that should either
 266          * all succeed or all fail, then use that function instead.
 267          *
 268          * @see FileBackend::doOperations()
 269          *
 270          * @param $op Array Operation
 271          * @param $opts Array Operation options
 272          * @return Status
 273          */
 274         final public function doOperation( array $op, array $opts = array() ) {
 275                 return $this->doOperations( array( $op ), $opts );
 276         }
 277
 278         /**
 279          * Performs a single create operation.
 280          * This sets $params['op'] to 'create' and passes it to doOperation().
 281          *
 282          * @see FileBackend::doOperation()
 283          *
 284          * @param $params Array Operation parameters
 285          * @param $opts Array Operation options
 286          * @return Status
 287          */
 288         final public function create( array $params, array $opts = array() ) {
 289                 $params['op'] = 'create';
 290                 return $this->doOperation( $params, $opts );
 291         }
 292
 293         /**
 294          * Performs a single store operation.
 295          * This sets $params['op'] to 'store' and passes it to doOperation().
 296          *
 297          * @see FileBackend::doOperation()
 298          *
 299          * @param $params Array Operation parameters
 300          * @param $opts Array Operation options
 301          * @return Status
 302          */
 303         final public function store( array $params, array $opts = array() ) {
 304                 $params['op'] = 'store';
 305                 return $this->doOperation( $params, $opts );
 306         }
 307
 308         /**
 309          * Performs a single copy operation.
 310          * This sets $params['op'] to 'copy' and passes it to doOperation().
 311          *
 312          * @see FileBackend::doOperation()
 313          *
 314          * @param $params Array Operation parameters
 315          * @param $opts Array Operation options
 316          * @return Status
 317          */
 318         final public function copy( array $params, array $opts = array() ) {
 319                 $params['op'] = 'copy';
 320                 return $this->doOperation( $params, $opts );
 321         }
 322
 323         /**
 324          * Performs a single move operation.
 325          * This sets $params['op'] to 'move' and passes it to doOperation().
 326          *
 327          * @see FileBackend::doOperation()
 328          *
 329          * @param $params Array Operation parameters
 330          * @param $opts Array Operation options
 331          * @return Status
 332          */
 333         final public function move( array $params, array $opts = array() ) {
 334                 $params['op'] = 'move';
 335                 return $this->doOperation( $params, $opts );
 336         }
 337
 338         /**
 339          * Performs a single delete operation.
 340          * This sets $params['op'] to 'delete' and passes it to doOperation().
 341          *
 342          * @see FileBackend::doOperation()
 343          *
 344          * @param $params Array Operation parameters
 345          * @param $opts Array Operation options
 346          * @return Status
 347          */
 348         final public function delete( array $params, array $opts = array() ) {
 349                 $params['op'] = 'delete';
 350                 return $this->doOperation( $params, $opts );
 351         }
 352
 353         /**
 354          * Perform a set of independent file operations on some files.
 355          *
 356          * This does no locking, nor journaling, and possibly no stat calls.
 357          * Any destination files that already exist will be overwritten.
 358          * This should *only* be used on non-original files, like cache files.
 359          *
 360          * Supported operations and their parameters:
 361          * a) Create a new file in storage with the contents of a string
 362          *     array(
 363          *         'op'                  => 'create',
 364          *         'dst'                 => <storage path>,
 365          *         'content'             => <string of new file contents>
 366          *     )
 367          * b) Copy a file system file into storage
 368          *     array(
 369          *         'op'                  => 'store',
 370          *         'src'                 => <file system path>,
 371          *         'dst'                 => <storage path>
 372          *     )
 373          * c) Copy a file within storage
 374          *     array(
 375          *         'op'                  => 'copy',
 376          *         'src'                 => <storage path>,
 377          *         'dst'                 => <storage path>
 378          *     )
 379          * d) Move a file within storage
 380          *     array(
 381          *         'op'                  => 'move',
 382          *         'src'                 => <storage path>,
 383          *         'dst'                 => <storage path>
 384          *     )
 385          * e) Delete a file within storage
 386          *     array(
 387          *         'op'                  => 'delete',
 388          *         'src'                 => <storage path>,
 389          *         'ignoreMissingSource' => <boolean>
 390          *     )
 391          * f) Do nothing (no-op)
 392          *     array(
 393          *         'op'                  => 'null',
 394          *     )
 395          *
 396          * Boolean flags for operations (operation-specific):
 397          * 'ignoreMissingSource' : The operation will simply succeed and do
 398          *                         nothing if the source file does not exist.
 399          *
 400          * Return value:
 401          * This returns a Status, which contains all warnings and fatals that occured
 402          * during the operation. The 'failCount', 'successCount', and 'success' members
 403          * will reflect each operation attempted for the given files. The status will be
 404          * considered "OK" as long as no fatal errors occured.
 405          *
 406          * @param $ops Array Set of operations to execute
 407          * @return Status
 408          */
 409         final public function doQuickOperations( array $ops ) {
 410                 if ( $this->isReadOnly() ) {
 411                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 412                 }
 413                 foreach ( $ops as &$op ) {
 414                         $op['overwrite'] = true; // avoids RTTs in key/value stores
 415                 }
 416                 return $this->doQuickOperationsInternal( $ops );
 417         }
 418
 419         /**
 420          * @see FileBackend::doQuickOperations()
 421          */
 422         abstract protected function doQuickOperationsInternal( array $ops );
 423
 424         /**
 425          * Concatenate a list of storage files into a single file system file.
 426          * The target path should refer to a file that is already locked or
 427          * otherwise safe from modification from other processes. Normally,
 428          * the file will be a new temp file, which should be adequate.
 429          * $params include:
 430          *     srcs : ordered source storage paths (e.g. chunk1, chunk2, ...)
 431          *     dst  : file system path to 0-byte temp file
 432          *
 433          * @param $params Array Operation parameters
 434          * @return Status
 435          */
 436         abstract public function concatenate( array $params );
 437
 438         /**
 439          * Prepare a storage directory for usage.
 440          * This will create any required containers and parent directories.
 441          * Backends using key/value stores only need to create the container.
 442          *
 443          * $params include:
 444          *     dir : storage directory
 445          *
 446          * @param $params Array
 447          * @return Status
 448          */
 449         final public function prepare( array $params ) {
 450                 if ( $this->isReadOnly() ) {
 451                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 452                 }
 453                 return $this->doPrepare( $params );
 454         }
 455
 456         /**
 457          * @see FileBackend::prepare()
 458          */
 459         abstract protected function doPrepare( array $params );
 460
 461         /**
 462          * Take measures to block web access to a storage directory and
 463          * the container it belongs to. FS backends might add .htaccess
 464          * files whereas key/value store backends might restrict container
 465          * access to the auth user that represents end-users in web request.
 466          * This is not guaranteed to actually do anything.
 467          *
 468          * $params include:
 469          *     dir       : storage directory
 470          *     noAccess  : try to deny file access
 471          *     noListing : try to deny file listing
 472          *
 473          * @param $params Array
 474          * @return Status
 475          */
 476         final public function secure( array $params ) {
 477                 if ( $this->isReadOnly() ) {
 478                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 479                 }
 480                 $status = $this->doPrepare( $params ); // dir must exist to restrict it
 481                 if ( $status->isOK() ) {
 482                         $status->merge( $this->doSecure( $params ) );
 483                 }
 484                 return $status;
 485         }
 486
 487         /**
 488          * @see FileBackend::secure()
 489          */
 490         abstract protected function doSecure( array $params );
 491
 492         /**
 493          * Delete a storage directory if it is empty.
 494          * Backends using key/value stores may do nothing unless the directory
 495          * is that of an empty container, in which case it should be deleted.
 496          *
 497          * $params include:
 498          *     dir       : storage directory
 499          *     recursive : recursively delete empty subdirectories first (@since 1.20)
 500          *
 501          * @param $params Array
 502          * @return Status
 503          */
 504         final public function clean( array $params ) {
 505                 if ( $this->isReadOnly() ) {
 506                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 507                 }
 508                 return $this->doClean( $params );
 509         }
 510
 511         /**
 512          * @see FileBackend::clean()
 513          */
 514         abstract protected function doClean( array $params );
 515
 516         /**
 517          * Check if a file exists at a storage path in the backend.
 518          * This returns false if only a directory exists at the path.
 519          *
 520          * $params include:
 521          *     src    : source storage path
 522          *     latest : use the latest available data
 523          *
 524          * @param $params Array
 525          * @return bool|null Returns null on failure
 526          */
 527         abstract public function fileExists( array $params );
 528
 529         /**
 530          * Get the last-modified timestamp of the file at a storage path.
 531          *
 532          * $params include:
 533          *     src    : source storage path
 534          *     latest : use the latest available data
 535          *
 536          * @param $params Array
 537          * @return string|bool TS_MW timestamp or false on failure
 538          */
 539         abstract public function getFileTimestamp( array $params );
 540
 541         /**
 542          * Get the contents of a file at a storage path in the backend.
 543          * This should be avoided for potentially large files.
 544          *
 545          * $params include:
 546          *     src    : source storage path
 547          *     latest : use the latest available data
 548          *
 549          * @param $params Array
 550          * @return string|bool Returns false on failure
 551          */
 552         abstract public function getFileContents( array $params );
 553
 554         /**
 555          * Get the size (bytes) of a file at a storage path in the backend.
 556          *
 557          * $params include:
 558          *     src    : source storage path
 559          *     latest : use the latest available data
 560          *
 561          * @param $params Array
 562          * @return integer|bool Returns false on failure
 563          */
 564         abstract public function getFileSize( array $params );
 565
 566         /**
 567          * Get quick information about a file at a storage path in the backend.
 568          * If the file does not exist, then this returns false.
 569          * Otherwise, the result is an associative array that includes:
 570          *     mtime  : the last-modified timestamp (TS_MW)
 571          *     size   : the file size (bytes)
 572          * Additional values may be included for internal use only.
 573          *
 574          * $params include:
 575          *     src    : source storage path
 576          *     latest : use the latest available data
 577          *
 578          * @param $params Array
 579          * @return Array|bool|null Returns null on failure
 580          */
 581         abstract public function getFileStat( array $params );
 582
 583         /**
 584          * Get a SHA-1 hash of the file at a storage path in the backend.
 585          *
 586          * $params include:
 587          *     src    : source storage path
 588          *     latest : use the latest available data
 589          *
 590          * @param $params Array
 591          * @return string|bool Hash string or false on failure
 592          */
 593         abstract public function getFileSha1Base36( array $params );
 594
 595         /**
 596          * Get the properties of the file at a storage path in the backend.
 597          * Returns FSFile::placeholderProps() on failure.
 598          *
 599          * $params include:
 600          *     src    : source storage path
 601          *     latest : use the latest available data
 602          *
 603          * @param $params Array
 604          * @return Array
 605          */
 606         abstract public function getFileProps( array $params );
 607
 608         /**
 609          * Stream the file at a storage path in the backend.
 610          * If the file does not exists, a 404 error will be given.
 611          * Appropriate HTTP headers (Status, Content-Type, Content-Length)
 612          * must be sent if streaming began, while none should be sent otherwise.
 613          * Implementations should flush the output buffer before sending data.
 614          *
 615          * $params include:
 616          *     src     : source storage path
 617          *     headers : additional HTTP headers to send on success
 618          *     latest  : use the latest available data
 619          *
 620          * @param $params Array
 621          * @return Status
 622          */
 623         abstract public function streamFile( array $params );
 624
 625         /**
 626          * Returns a file system file, identical to the file at a storage path.
 627          * The file returned is either:
 628          * a) A local copy of the file at a storage path in the backend.
 629          *    The temporary copy will have the same extension as the source.
 630          * b) An original of the file at a storage path in the backend.
 631          * Temporary files may be purged when the file object falls out of scope.
 632          *
 633          * Write operations should *never* be done on this file as some backends
 634          * may do internal tracking or may be instances of FileBackendMultiWrite.
 635          * In that later case, there are copies of the file that must stay in sync.
 636          * Additionally, further calls to this function may return the same file.
 637          *
 638          * $params include:
 639          *     src    : source storage path
 640          *     latest : use the latest available data
 641          *
 642          * @param $params Array
 643          * @return FSFile|null Returns null on failure
 644          */
 645         abstract public function getLocalReference( array $params );
 646
 647         /**
 648          * Get a local copy on disk of the file at a storage path in the backend.
 649          * The temporary copy will have the same file extension as the source.
 650          * Temporary files may be purged when the file object falls out of scope.
 651          *
 652          * $params include:
 653          *     src    : source storage path
 654          *     latest : use the latest available data
 655          *
 656          * @param $params Array
 657          * @return TempFSFile|null Returns null on failure
 658          */
 659         abstract public function getLocalCopy( array $params );
 660
 661         /**
 662          * Check if a directory exists at a given storage path.
 663          * Backends using key/value stores will check if the path is a
 664          * virtual directory, meaning there are files under the given directory.
 665          *
 666          * Storage backends with eventual consistency might return stale data.
 667          *
 668          * $params include:
 669          *     dir : storage directory
 670          *
 671          * @return bool|null Returns null on failure
 672          * @since 1.20
 673          */
 674         abstract public function directoryExists( array $params );
 675
 676         /**
 677          * Get an iterator to list *all* directories under a storage directory.
 678          * If the directory is of the form "mwstore://backend/container",
 679          * then all directories in the container should be listed.
 680          * If the directory is of form "mwstore://backend/container/dir",
 681          * then all directories directly under that directory should be listed.
 682          * Results should be storage directories relative to the given directory.
 683          *
 684          * Storage backends with eventual consistency might return stale data.
 685          *
 686          * $params include:
 687          *     dir     : storage directory
 688          *     topOnly : only return direct child dirs of the directory
 689          *
 690          * @return Traversable|Array|null Returns null on failure
 691          * @since 1.20
 692          */
 693         abstract public function getDirectoryList( array $params );
 694
 695         /**
 696          * Same as FileBackend::getDirectoryList() except only lists
 697          * directories that are immediately under the given directory.
 698          *
 699          * Storage backends with eventual consistency might return stale data.
 700          *
 701          * $params include:
 702          *     dir : storage directory
 703          *
 704          * @return Traversable|Array|null Returns null on failure
 705          * @since 1.20
 706          */
 707         final public function getTopDirectoryList( array $params ) {
 708                 return $this->getDirectoryList( array( 'topOnly' => true ) + $params );
 709         }
 710
 711         /**
 712          * Get an iterator to list *all* stored files under a storage directory.
 713          * If the directory is of the form "mwstore://backend/container",
 714          * then all files in the container should be listed.
 715          * If the directory is of form "mwstore://backend/container/dir",
 716          * then all files under that directory should be listed.
 717          * Results should be storage paths relative to the given directory.
 718          *
 719          * Storage backends with eventual consistency might return stale data.
 720          *
 721          * $params include:
 722          *     dir     : storage directory
 723          *     topOnly : only return direct child files of the directory (@since 1.20)
 724          *
 725          * @return Traversable|Array|null Returns null on failure
 726          */
 727         abstract public function getFileList( array $params );
 728
 729         /**
 730          * Same as FileBackend::getFileList() except only lists
 731          * files that are immediately under the given directory.
 732          *
 733          * Storage backends with eventual consistency might return stale data.
 734          *
 735          * $params include:
 736          *     dir : storage directory
 737          *
 738          * @return Traversable|Array|null Returns null on failure
 739          * @since 1.20
 740          */
 741         final public function getTopFileList( array $params ) {
 742                 return $this->getFileList( array( 'topOnly' => true ) + $params );
 743         }
 744
 745         /**
 746          * Invalidate any in-process file existence and property cache.
 747          * If $paths is given, then only the cache for those files will be cleared.
 748          *
 749          * @param $paths Array Storage paths (optional)
 750          * @return void
 751          */
 752         public function clearCache( array $paths = null ) {}
 753
 754         /**
 755          * Lock the files at the given storage paths in the backend.
 756          * This will either lock all the files or none (on failure).
 757          *
 758          * Callers should consider using getScopedFileLocks() instead.
 759          *
 760          * @param $paths Array Storage paths
 761          * @param $type integer LockManager::LOCK_* constant
 762          * @return Status
 763          */
 764         final public function lockFiles( array $paths, $type ) {
 765                 return $this->lockManager->lock( $paths, $type );
 766         }
 767
 768         /**
 769          * Unlock the files at the given storage paths in the backend.
 770          *
 771          * @param $paths Array Storage paths
 772          * @param $type integer LockManager::LOCK_* constant
 773          * @return Status
 774          */
 775         final public function unlockFiles( array $paths, $type ) {
 776                 return $this->lockManager->unlock( $paths, $type );
 777         }
 778
 779         /**
 780          * Lock the files at the given storage paths in the backend.
 781          * This will either lock all the files or none (on failure).
 782          * On failure, the status object will be updated with errors.
 783          *
 784          * Once the return value goes out scope, the locks will be released and
 785          * the status updated. Unlock fatals will not change the status "OK" value.
 786          *
 787          * @param $paths Array Storage paths
 788          * @param $type integer LockManager::LOCK_* constant
 789          * @param $status Status Status to update on lock/unlock
 790          * @return ScopedLock|null Returns null on failure
 791          */
 792         final public function getScopedFileLocks( array $paths, $type, Status $status ) {
 793                 return ScopedLock::factory( $this->lockManager, $paths, $type, $status );
 794         }
 795
 796         /**
 797          * Get the root storage path of this backend.
 798          * All container paths are "subdirectories" of this path.
 799          *
 800          * @return string Storage path
 801          * @since 1.20
 802          */
 803         final public function getRootStoragePath() {
 804                 return "mwstore://{$this->name}";
 805         }
 806
 807         /**
 808          * Get the file journal object for this backend
 809          *
 810          * @return FileJournal
 811          */
 812         final public function getJournal() {
 813                 return $this->fileJournal;
 814         }
 815
 816         /**
 817          * Check if a given path is a "mwstore://" path.
 818          * This does not do any further validation or any existence checks.
 819          *
 820          * @param $path string
 821          * @return bool
 822          */
 823         final public static function isStoragePath( $path ) {
 824                 return ( strpos( $path, 'mwstore://' ) === 0 );
 825         }
 826
 827         /**
 828          * Split a storage path into a backend name, a container name,
 829          * and a relative file path. The relative path may be the empty string.
 830          * This does not do any path normalization or traversal checks.
 831          *
 832          * @param $storagePath string
 833          * @return Array (backend, container, rel object) or (null, null, null)
 834          */
 835         final public static function splitStoragePath( $storagePath ) {
 836                 if ( self::isStoragePath( $storagePath ) ) {
 837                         // Remove the "mwstore://" prefix and split the path
 838                         $parts = explode( '/', substr( $storagePath, 10 ), 3 );
 839                         if ( count( $parts ) >= 2 && $parts[0] != '' && $parts[1] != '' ) {
 840                                 if ( count( $parts ) == 3 ) {
 841                                         return $parts; // e.g. "backend/container/path"
 842                                 } else {
 843                                         return array( $parts[0], $parts[1], '' ); // e.g. "backend/container"
 844                                 }
 845                         }
 846                 }
 847                 return array( null, null, null );
 848         }
 849
 850         /**
 851          * Normalize a storage path by cleaning up directory separators.
 852          * Returns null if the path is not of the format of a valid storage path.
 853          *
 854          * @param $storagePath string
 855          * @return string|null
 856          */
 857         final public static function normalizeStoragePath( $storagePath ) {
 858                 list( $backend, $container, $relPath ) = self::splitStoragePath( $storagePath );
 859                 if ( $relPath !== null ) { // must be for this backend
 860                         $relPath = self::normalizeContainerPath( $relPath );
 861                         if ( $relPath !== null ) {
 862                                 return ( $relPath != '' )
 863                                         ? "mwstore://{$backend}/{$container}/{$relPath}"
 864                                         : "mwstore://{$backend}/{$container}";
 865                         }
 866                 }
 867                 return null;
 868         }
 869
 870         /**
 871          * Get the parent storage directory of a storage path.
 872          * This returns a path like "mwstore://backend/container",
 873          * "mwstore://backend/container/...", or null if there is no parent.
 874          *
 875          * @param $storagePath string
 876          * @return string|null
 877          */
 878         final public static function parentStoragePath( $storagePath ) {
 879                 $storagePath = dirname( $storagePath );
 880                 list( $b, $cont, $rel ) = self::splitStoragePath( $storagePath );
 881                 return ( $rel === null ) ? null : $storagePath;
 882         }
 883
 884         /**
 885          * Get the final extension from a storage or FS path
 886          *
 887          * @param $path string
 888          * @return string
 889          */
 890         final public static function extensionFromPath( $path ) {
 891                 $i = strrpos( $path, '.' );
 892                 return strtolower( $i ? substr( $path, $i + 1 ) : '' );
 893         }
 894
 895         /**
 896          * Check if a relative path has no directory traversals
 897          *
 898          * @param $path string
 899          * @return bool
 900          * @since 1.20
 901          */
 902         final public static function isPathTraversalFree( $path ) {
 903                 return ( self::normalizeContainerPath( $path ) !== null );
 904         }
 905
 906         /**
 907          * Validate and normalize a relative storage path.
 908          * Null is returned if the path involves directory traversal.
 909          * Traversal is insecure for FS backends and broken for others.
 910          *
 911          * This uses the same traversal protection as Title::secureAndSplit().
 912          *
 913          * @param $path string Storage path relative to a container
 914          * @return string|null
 915          */
 916         final protected static function normalizeContainerPath( $path ) {
 917                 // Normalize directory separators
 918                 $path = strtr( $path, '\\', '/' );
 919                 // Collapse any consecutive directory separators
 920                 $path = preg_replace( '![/]{2,}!', '/', $path );
 921                 // Remove any leading directory separator
 922                 $path = ltrim( $path, '/' );
 923                 // Use the same traversal protection as Title::secureAndSplit()
 924                 if ( strpos( $path, '.' ) !== false ) {
 925                         if (
 926                                 $path === '.' ||
 927                                 $path === '..' ||
 928                                 strpos( $path, './' ) === 0 ||
 929                                 strpos( $path, '../' ) === 0 ||
 930                                 strpos( $path, '/./' ) !== false ||
 931                                 strpos( $path, '/../' ) !== false
 932                         ) {
 933                                 return null;
 934                         }
 935                 }
 936                 return $path;
 937         }
 938 }