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