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                 return $this->doOperation( array( 'op' => 'create' ) + $params, $opts );
 290         }
 291
 292         /**
 293          * Performs a single store operation.
 294          * This sets $params['op'] to 'store' and passes it to doOperation().
 295          *
 296          * @see FileBackend::doOperation()
 297          *
 298          * @param $params Array Operation parameters
 299          * @param $opts Array Operation options
 300          * @return Status
 301          */
 302         final public function store( array $params, array $opts = array() ) {
 303                 return $this->doOperation( array( 'op' => 'store' ) + $params, $opts );
 304         }
 305
 306         /**
 307          * Performs a single copy operation.
 308          * This sets $params['op'] to 'copy' and passes it to doOperation().
 309          *
 310          * @see FileBackend::doOperation()
 311          *
 312          * @param $params Array Operation parameters
 313          * @param $opts Array Operation options
 314          * @return Status
 315          */
 316         final public function copy( array $params, array $opts = array() ) {
 317                 return $this->doOperation( array( 'op' => 'copy' ) + $params, $opts );
 318         }
 319
 320         /**
 321          * Performs a single move operation.
 322          * This sets $params['op'] to 'move' and passes it to doOperation().
 323          *
 324          * @see FileBackend::doOperation()
 325          *
 326          * @param $params Array Operation parameters
 327          * @param $opts Array Operation options
 328          * @return Status
 329          */
 330         final public function move( array $params, array $opts = array() ) {
 331                 return $this->doOperation( array( 'op' => 'move' ) + $params, $opts );
 332         }
 333
 334         /**
 335          * Performs a single delete operation.
 336          * This sets $params['op'] to 'delete' and passes it to doOperation().
 337          *
 338          * @see FileBackend::doOperation()
 339          *
 340          * @param $params Array Operation parameters
 341          * @param $opts Array Operation options
 342          * @return Status
 343          */
 344         final public function delete( array $params, array $opts = array() ) {
 345                 return $this->doOperation( array( 'op' => 'delete' ) + $params, $opts );
 346         }
 347
 348         /**
 349          * Perform a set of independent file operations on some files.
 350          *
 351          * This does no locking, nor journaling, and possibly no stat calls.
 352          * Any destination files that already exist will be overwritten.
 353          * This should *only* be used on non-original files, like cache files.
 354          *
 355          * Supported operations and their parameters:
 356          * a) Create a new file in storage with the contents of a string
 357          *     array(
 358          *         'op'                  => 'create',
 359          *         'dst'                 => <storage path>,
 360          *         'content'             => <string of new file contents>
 361          *     )
 362          * b) Copy a file system file into storage
 363          *     array(
 364          *         'op'                  => 'store',
 365          *         'src'                 => <file system path>,
 366          *         'dst'                 => <storage path>
 367          *     )
 368          * c) Copy a file within storage
 369          *     array(
 370          *         'op'                  => 'copy',
 371          *         'src'                 => <storage path>,
 372          *         'dst'                 => <storage path>
 373          *     )
 374          * d) Move a file within storage
 375          *     array(
 376          *         'op'                  => 'move',
 377          *         'src'                 => <storage path>,
 378          *         'dst'                 => <storage path>
 379          *     )
 380          * e) Delete a file within storage
 381          *     array(
 382          *         'op'                  => 'delete',
 383          *         'src'                 => <storage path>,
 384          *         'ignoreMissingSource' => <boolean>
 385          *     )
 386          * f) Do nothing (no-op)
 387          *     array(
 388          *         'op'                  => 'null',
 389          *     )
 390          *
 391          * Boolean flags for operations (operation-specific):
 392          * 'ignoreMissingSource' : The operation will simply succeed and do
 393          *                         nothing if the source file does not exist.
 394          *
 395          * Return value:
 396          * This returns a Status, which contains all warnings and fatals that occured
 397          * during the operation. The 'failCount', 'successCount', and 'success' members
 398          * will reflect each operation attempted for the given files. The status will be
 399          * considered "OK" as long as no fatal errors occured.
 400          *
 401          * @param $ops Array Set of operations to execute
 402          * @return Status
 403          */
 404         final public function doQuickOperations( array $ops ) {
 405                 if ( $this->isReadOnly() ) {
 406                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 407                 }
 408                 foreach ( $ops as &$op ) {
 409                         $op['overwrite'] = true; // avoids RTTs in key/value stores
 410                 }
 411                 return $this->doQuickOperationsInternal( $ops );
 412         }
 413
 414         /**
 415          * @see FileBackend::doQuickOperations()
 416          */
 417         abstract protected function doQuickOperationsInternal( array $ops );
 418
 419         /**
 420          * Concatenate a list of storage files into a single file system file.
 421          * The target path should refer to a file that is already locked or
 422          * otherwise safe from modification from other processes. Normally,
 423          * the file will be a new temp file, which should be adequate.
 424          * $params include:
 425          *     srcs : ordered source storage paths (e.g. chunk1, chunk2, ...)
 426          *     dst  : file system path to 0-byte temp file
 427          *
 428          * @param $params Array Operation parameters
 429          * @return Status
 430          */
 431         abstract public function concatenate( array $params );
 432
 433         /**
 434          * Prepare a storage directory for usage.
 435          * This will create any required containers and parent directories.
 436          * Backends using key/value stores only need to create the container.
 437          *
 438          * $params include:
 439          *     dir : storage directory
 440          *
 441          * @param $params Array
 442          * @return Status
 443          */
 444         final public function prepare( array $params ) {
 445                 if ( $this->isReadOnly() ) {
 446                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 447                 }
 448                 return $this->doPrepare( $params );
 449         }
 450
 451         /**
 452          * @see FileBackend::prepare()
 453          */
 454         abstract protected function doPrepare( array $params );
 455
 456         /**
 457          * Take measures to block web access to a storage directory and
 458          * the container it belongs to. FS backends might add .htaccess
 459          * files whereas key/value store backends might restrict container
 460          * access to the auth user that represents end-users in web request.
 461          * This is not guaranteed to actually do anything.
 462          *
 463          * $params include:
 464          *     dir       : storage directory
 465          *     noAccess  : try to deny file access
 466          *     noListing : try to deny file listing
 467          *
 468          * @param $params Array
 469          * @return Status
 470          */
 471         final public function secure( array $params ) {
 472                 if ( $this->isReadOnly() ) {
 473                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 474                 }
 475                 $status = $this->doPrepare( $params ); // dir must exist to restrict it
 476                 if ( $status->isOK() ) {
 477                         $status->merge( $this->doSecure( $params ) );
 478                 }
 479                 return $status;
 480         }
 481
 482         /**
 483          * @see FileBackend::secure()
 484          */
 485         abstract protected function doSecure( array $params );
 486
 487         /**
 488          * Delete a storage directory if it is empty.
 489          * Backends using key/value stores may do nothing unless the directory
 490          * is that of an empty container, in which case it should be deleted.
 491          *
 492          * $params include:
 493          *     dir       : storage directory
 494          *     recursive : recursively delete empty subdirectories first (@since 1.20)
 495          *
 496          * @param $params Array
 497          * @return Status
 498          */
 499         final public function clean( array $params ) {
 500                 if ( $this->isReadOnly() ) {
 501                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 502                 }
 503                 return $this->doClean( $params );
 504         }
 505
 506         /**
 507          * @see FileBackend::clean()
 508          */
 509         abstract protected function doClean( array $params );
 510
 511         /**
 512          * Check if a file exists at a storage path in the backend.
 513          * This returns false if only a directory exists at the path.
 514          *
 515          * $params include:
 516          *     src    : source storage path
 517          *     latest : use the latest available data
 518          *
 519          * @param $params Array
 520          * @return bool|null Returns null on failure
 521          */
 522         abstract public function fileExists( array $params );
 523
 524         /**
 525          * Get the last-modified timestamp of the file at a storage path.
 526          *
 527          * $params include:
 528          *     src    : source storage path
 529          *     latest : use the latest available data
 530          *
 531          * @param $params Array
 532          * @return string|bool TS_MW timestamp or false on failure
 533          */
 534         abstract public function getFileTimestamp( array $params );
 535
 536         /**
 537          * Get the contents of a file at a storage path in the backend.
 538          * This should be avoided for potentially large files.
 539          *
 540          * $params include:
 541          *     src    : source storage path
 542          *     latest : use the latest available data
 543          *
 544          * @param $params Array
 545          * @return string|bool Returns false on failure
 546          */
 547         abstract public function getFileContents( array $params );
 548
 549         /**
 550          * Get the size (bytes) of a file at a storage path in the backend.
 551          *
 552          * $params include:
 553          *     src    : source storage path
 554          *     latest : use the latest available data
 555          *
 556          * @param $params Array
 557          * @return integer|bool Returns false on failure
 558          */
 559         abstract public function getFileSize( array $params );
 560
 561         /**
 562          * Get quick information about a file at a storage path in the backend.
 563          * If the file does not exist, then this returns false.
 564          * Otherwise, the result is an associative array that includes:
 565          *     mtime  : the last-modified timestamp (TS_MW)
 566          *     size   : the file size (bytes)
 567          * Additional values may be included for internal use only.
 568          *
 569          * $params include:
 570          *     src    : source storage path
 571          *     latest : use the latest available data
 572          *
 573          * @param $params Array
 574          * @return Array|bool|null Returns null on failure
 575          */
 576         abstract public function getFileStat( array $params );
 577
 578         /**
 579          * Get a SHA-1 hash of the file at a storage path in the backend.
 580          *
 581          * $params include:
 582          *     src    : source storage path
 583          *     latest : use the latest available data
 584          *
 585          * @param $params Array
 586          * @return string|bool Hash string or false on failure
 587          */
 588         abstract public function getFileSha1Base36( array $params );
 589
 590         /**
 591          * Get the properties of the file at a storage path in the backend.
 592          * Returns FSFile::placeholderProps() on failure.
 593          *
 594          * $params include:
 595          *     src    : source storage path
 596          *     latest : use the latest available data
 597          *
 598          * @param $params Array
 599          * @return Array
 600          */
 601         abstract public function getFileProps( array $params );
 602
 603         /**
 604          * Stream the file at a storage path in the backend.
 605          * If the file does not exists, a 404 error will be given.
 606          * Appropriate HTTP headers (Status, Content-Type, Content-Length)
 607          * must be sent if streaming began, while none should be sent otherwise.
 608          * Implementations should flush the output buffer before sending data.
 609          *
 610          * $params include:
 611          *     src     : source storage path
 612          *     headers : additional HTTP headers to send on success
 613          *     latest  : use the latest available data
 614          *
 615          * @param $params Array
 616          * @return Status
 617          */
 618         abstract public function streamFile( array $params );
 619
 620         /**
 621          * Returns a file system file, identical to the file at a storage path.
 622          * The file returned is either:
 623          * a) A local copy of the file at a storage path in the backend.
 624          *    The temporary copy will have the same extension as the source.
 625          * b) An original of the file at a storage path in the backend.
 626          * Temporary files may be purged when the file object falls out of scope.
 627          *
 628          * Write operations should *never* be done on this file as some backends
 629          * may do internal tracking or may be instances of FileBackendMultiWrite.
 630          * In that later case, there are copies of the file that must stay in sync.
 631          * Additionally, further calls to this function may return the same file.
 632          *
 633          * $params include:
 634          *     src    : source storage path
 635          *     latest : use the latest available data
 636          *
 637          * @param $params Array
 638          * @return FSFile|null Returns null on failure
 639          */
 640         abstract public function getLocalReference( array $params );
 641
 642         /**
 643          * Get a local copy on disk of the file at a storage path in the backend.
 644          * The temporary copy will have the same file extension as the source.
 645          * Temporary files may be purged when the file object falls out of scope.
 646          *
 647          * $params include:
 648          *     src    : source storage path
 649          *     latest : use the latest available data
 650          *
 651          * @param $params Array
 652          * @return TempFSFile|null Returns null on failure
 653          */
 654         abstract public function getLocalCopy( array $params );
 655
 656         /**
 657          * Check if a directory exists at a given storage path.
 658          * Backends using key/value stores will check if the path is a
 659          * virtual directory, meaning there are files under the given directory.
 660          *
 661          * Storage backends with eventual consistency might return stale data.
 662          *
 663          * $params include:
 664          *     dir : storage directory
 665          *
 666          * @return bool|null Returns null on failure
 667          * @since 1.20
 668          */
 669         abstract public function directoryExists( array $params );
 670
 671         /**
 672          * Get an iterator to list *all* directories under a storage directory.
 673          * If the directory is of the form "mwstore://backend/container",
 674          * then all directories in the container should be listed.
 675          * If the directory is of form "mwstore://backend/container/dir",
 676          * then all directories directly under that directory should be listed.
 677          * Results should be storage directories relative to the given directory.
 678          *
 679          * Storage backends with eventual consistency might return stale data.
 680          *
 681          * $params include:
 682          *     dir     : storage directory
 683          *     topOnly : only return direct child dirs of the directory
 684          *
 685          * @return Traversable|Array|null Returns null on failure
 686          * @since 1.20
 687          */
 688         abstract public function getDirectoryList( array $params );
 689
 690         /**
 691          * Same as FileBackend::getDirectoryList() except only lists
 692          * directories that are immediately under the given directory.
 693          *
 694          * Storage backends with eventual consistency might return stale data.
 695          *
 696          * $params include:
 697          *     dir : storage directory
 698          *
 699          * @return Traversable|Array|null Returns null on failure
 700          * @since 1.20
 701          */
 702         final public function getTopDirectoryList( array $params ) {
 703                 return $this->getDirectoryList( array( 'topOnly' => true ) + $params );
 704         }
 705
 706         /**
 707          * Get an iterator to list *all* stored files under a storage directory.
 708          * If the directory is of the form "mwstore://backend/container",
 709          * then all files in the container should be listed.
 710          * If the directory is of form "mwstore://backend/container/dir",
 711          * then all files under that directory should be listed.
 712          * Results should be storage paths relative to the given directory.
 713          *
 714          * Storage backends with eventual consistency might return stale data.
 715          *
 716          * $params include:
 717          *     dir     : storage directory
 718          *     topOnly : only return direct child files of the directory (@since 1.20)
 719          *
 720          * @return Traversable|Array|null Returns null on failure
 721          */
 722         abstract public function getFileList( array $params );
 723
 724         /**
 725          * Same as FileBackend::getFileList() except only lists
 726          * files that are immediately under the given directory.
 727          *
 728          * Storage backends with eventual consistency might return stale data.
 729          *
 730          * $params include:
 731          *     dir : storage directory
 732          *
 733          * @return Traversable|Array|null Returns null on failure
 734          * @since 1.20
 735          */
 736         final public function getTopFileList( array $params ) {
 737                 return $this->getFileList( array( 'topOnly' => true ) + $params );
 738         }
 739
 740         /**
 741          * Invalidate any in-process file existence and property cache.
 742          * If $paths is given, then only the cache for those files will be cleared.
 743          *
 744          * @param $paths Array Storage paths (optional)
 745          * @return void
 746          */
 747         public function clearCache( array $paths = null ) {}
 748
 749         /**
 750          * Lock the files at the given storage paths in the backend.
 751          * This will either lock all the files or none (on failure).
 752          *
 753          * Callers should consider using getScopedFileLocks() instead.
 754          *
 755          * @param $paths Array Storage paths
 756          * @param $type integer LockManager::LOCK_* constant
 757          * @return Status
 758          */
 759         final public function lockFiles( array $paths, $type ) {
 760                 return $this->lockManager->lock( $paths, $type );
 761         }
 762
 763         /**
 764          * Unlock the files at the given storage paths in the backend.
 765          *
 766          * @param $paths Array Storage paths
 767          * @param $type integer LockManager::LOCK_* constant
 768          * @return Status
 769          */
 770         final public function unlockFiles( array $paths, $type ) {
 771                 return $this->lockManager->unlock( $paths, $type );
 772         }
 773
 774         /**
 775          * Lock the files at the given storage paths in the backend.
 776          * This will either lock all the files or none (on failure).
 777          * On failure, the status object will be updated with errors.
 778          *
 779          * Once the return value goes out scope, the locks will be released and
 780          * the status updated. Unlock fatals will not change the status "OK" value.
 781          *
 782          * @param $paths Array Storage paths
 783          * @param $type integer LockManager::LOCK_* constant
 784          * @param $status Status Status to update on lock/unlock
 785          * @return ScopedLock|null Returns null on failure
 786          */
 787         final public function getScopedFileLocks( array $paths, $type, Status $status ) {
 788                 return ScopedLock::factory( $this->lockManager, $paths, $type, $status );
 789         }
 790
 791         /**
 792          * Get the root storage path of this backend.
 793          * All container paths are "subdirectories" of this path.
 794          *
 795          * @return string Storage path
 796          * @since 1.20
 797          */
 798         final public function getRootStoragePath() {
 799                 return "mwstore://{$this->name}";
 800         }
 801
 802         /**
 803          * Get the file journal object for this backend
 804          *
 805          * @return FileJournal
 806          */
 807         final public function getJournal() {
 808                 return $this->fileJournal;
 809         }
 810
 811         /**
 812          * Check if a given path is a "mwstore://" path.
 813          * This does not do any further validation or any existence checks.
 814          *
 815          * @param $path string
 816          * @return bool
 817          */
 818         final public static function isStoragePath( $path ) {
 819                 return ( strpos( $path, 'mwstore://' ) === 0 );
 820         }
 821
 822         /**
 823          * Split a storage path into a backend name, a container name,
 824          * and a relative file path. The relative path may be the empty string.
 825          * This does not do any path normalization or traversal checks.
 826          *
 827          * @param $storagePath string
 828          * @return Array (backend, container, rel object) or (null, null, null)
 829          */
 830         final public static function splitStoragePath( $storagePath ) {
 831                 if ( self::isStoragePath( $storagePath ) ) {
 832                         // Remove the "mwstore://" prefix and split the path
 833                         $parts = explode( '/', substr( $storagePath, 10 ), 3 );
 834                         if ( count( $parts ) >= 2 && $parts[0] != '' && $parts[1] != '' ) {
 835                                 if ( count( $parts ) == 3 ) {
 836                                         return $parts; // e.g. "backend/container/path"
 837                                 } else {
 838                                         return array( $parts[0], $parts[1], '' ); // e.g. "backend/container"
 839                                 }
 840                         }
 841                 }
 842                 return array( null, null, null );
 843         }
 844
 845         /**
 846          * Normalize a storage path by cleaning up directory separators.
 847          * Returns null if the path is not of the format of a valid storage path.
 848          *
 849          * @param $storagePath string
 850          * @return string|null
 851          */
 852         final public static function normalizeStoragePath( $storagePath ) {
 853                 list( $backend, $container, $relPath ) = self::splitStoragePath( $storagePath );
 854                 if ( $relPath !== null ) { // must be for this backend
 855                         $relPath = self::normalizeContainerPath( $relPath );
 856                         if ( $relPath !== null ) {
 857                                 return ( $relPath != '' )
 858                                         ? "mwstore://{$backend}/{$container}/{$relPath}"
 859                                         : "mwstore://{$backend}/{$container}";
 860                         }
 861                 }
 862                 return null;
 863         }
 864
 865         /**
 866          * Get the parent storage directory of a storage path.
 867          * This returns a path like "mwstore://backend/container",
 868          * "mwstore://backend/container/...", or null if there is no parent.
 869          *
 870          * @param $storagePath string
 871          * @return string|null
 872          */
 873         final public static function parentStoragePath( $storagePath ) {
 874                 $storagePath = dirname( $storagePath );
 875                 list( $b, $cont, $rel ) = self::splitStoragePath( $storagePath );
 876                 return ( $rel === null ) ? null : $storagePath;
 877         }
 878
 879         /**
 880          * Get the final extension from a storage or FS path
 881          *
 882          * @param $path string
 883          * @return string
 884          */
 885         final public static function extensionFromPath( $path ) {
 886                 $i = strrpos( $path, '.' );
 887                 return strtolower( $i ? substr( $path, $i + 1 ) : '' );
 888         }
 889
 890         /**
 891          * Check if a relative path has no directory traversals
 892          *
 893          * @param $path string
 894          * @return bool
 895          * @since 1.20
 896          */
 897         final public static function isPathTraversalFree( $path ) {
 898                 return ( self::normalizeContainerPath( $path ) !== null );
 899         }
 900
 901         /**
 902          * Validate and normalize a relative storage path.
 903          * Null is returned if the path involves directory traversal.
 904          * Traversal is insecure for FS backends and broken for others.
 905          *
 906          * This uses the same traversal protection as Title::secureAndSplit().
 907          *
 908          * @param $path string Storage path relative to a container
 909          * @return string|null
 910          */
 911         final protected static function normalizeContainerPath( $path ) {
 912                 // Normalize directory separators
 913                 $path = strtr( $path, '\\', '/' );
 914                 // Collapse any consecutive directory separators
 915                 $path = preg_replace( '![/]{2,}!', '/', $path );
 916                 // Remove any leading directory separator
 917                 $path = ltrim( $path, '/' );
 918                 // Use the same traversal protection as Title::secureAndSplit()
 919                 if ( strpos( $path, '.' ) !== false ) {
 920                         if (
 921                                 $path === '.' ||
 922                                 $path === '..' ||
 923                                 strpos( $path, './' ) === 0 ||
 924                                 strpos( $path, '../' ) === 0 ||
 925                                 strpos( $path, '/./' ) !== false ||
 926                                 strpos( $path, '/../' ) !== false
 927                         ) {
 928                                 return null;
 929                         }
 930                 }
 931                 return $path;
 932         }
 933 }