includes/filebackend/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)
  41  * notation, though any particular backend may not actually be using a local
  42  * filesystem. 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 of subclasses 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          * @throws MWException
  92          */
  93         public function __construct( array $config ) {
  94                 $this->name = $config['name'];
  95                 if ( !preg_match( '!^[a-zA-Z0-9-_]{1,255}$!', $this->name ) ) {
  96                         throw new MWException( "Backend name `{$this->name}` is invalid." );
  97                 }
  98                 $this->wikiId = isset( $config['wikiId'] )
  99                         ? $config['wikiId']
 100                         : wfWikiID(); // e.g. "my_wiki-en_"
 101                 $this->lockManager = ( $config['lockManager'] instanceof LockManager )
 102                         ? $config['lockManager']
 103                         : LockManagerGroup::singleton()->get( $config['lockManager'] );
 104                 $this->fileJournal = isset( $config['fileJournal'] )
 105                         ? ( ( $config['fileJournal'] instanceof FileJournal )
 106                                 ? $config['fileJournal']
 107                                 : FileJournal::factory( $config['fileJournal'], $this->name ) )
 108                         : FileJournal::factory( array( 'class' => 'NullFileJournal' ), $this->name );
 109                 $this->readOnly = isset( $config['readOnly'] )
 110                         ? (string)$config['readOnly']
 111                         : '';
 112                 $this->parallelize = isset( $config['parallelize'] )
 113                         ? (string)$config['parallelize']
 114                         : 'off';
 115                 $this->concurrency = isset( $config['concurrency'] )
 116                         ? (int)$config['concurrency']
 117                         : 50;
 118         }
 119
 120         /**
 121          * Get the unique backend name.
 122          * We may have multiple different backends of the same type.
 123          * For example, we can have two Swift backends using different proxies.
 124          *
 125          * @return string
 126          */
 127         final public function getName() {
 128                 return $this->name;
 129         }
 130
 131         /**
 132          * Get the wiki identifier used for this backend (possibly empty).
 133          * Note that this might *not* be in the same format as wfWikiID().
 134          *
 135          * @return string
 136          * @since 1.20
 137          */
 138         final public function getWikiId() {
 139                 return $this->wikiId;
 140         }
 141
 142         /**
 143          * Check if this backend is read-only
 144          *
 145          * @return bool
 146          */
 147         final public function isReadOnly() {
 148                 return ( $this->readOnly != '' );
 149         }
 150
 151         /**
 152          * Get an explanatory message if this backend is read-only
 153          *
 154          * @return string|bool Returns false if the backend is not read-only
 155          */
 156         final public function getReadOnlyReason() {
 157                 return ( $this->readOnly != '' ) ? $this->readOnly : false;
 158         }
 159
 160         /**
 161          * This is the main entry point into the backend for write operations.
 162          * Callers supply an ordered list of operations to perform as a transaction.
 163          * Files will be locked, the stat cache cleared, and then the operations attempted.
 164          * If any serious errors occur, all attempted operations will be rolled back.
 165          *
 166          * $ops is an array of arrays. The outer array holds a list of operations.
 167          * Each inner array is a set of key value pairs that specify an operation.
 168          *
 169          * Supported operations and their parameters. The supported actions are:
 170          *  - create
 171          *  - store
 172          *  - copy
 173          *  - move
 174          *  - delete
 175          *  - null
 176          *
 177          * a) Create a new file in storage with the contents of a string
 178          * @code
 179          *     array(
 180          *         'op'                  => 'create',
 181          *         'dst'                 => <storage path>,
 182          *         'content'             => <string of new file contents>,
 183          *         'overwrite'           => <boolean>,
 184          *         'overwriteSame'       => <boolean>,
 185          *         'disposition'         => <Content-Disposition header value>
 186          *     );
 187          * @endcode
 188          *
 189          * b) Copy a file system file into storage
 190          * @code
 191          *     array(
 192          *         'op'                  => 'store',
 193          *         'src'                 => <file system path>,
 194          *         'dst'                 => <storage path>,
 195          *         'overwrite'           => <boolean>,
 196          *         'overwriteSame'       => <boolean>,
 197          *         'disposition'         => <Content-Disposition header value>
 198          *     )
 199          * @endcode
 200          *
 201          * c) Copy a file within storage
 202          * @code
 203          *     array(
 204          *         'op'                  => 'copy',
 205          *         'src'                 => <storage path>,
 206          *         'dst'                 => <storage path>,
 207          *         'overwrite'           => <boolean>,
 208          *         'overwriteSame'       => <boolean>,
 209          *         'ignoreMissingSource' => <boolean>, # since 1.21
 210          *         'disposition'         => <Content-Disposition header value>
 211          *     )
 212          * @endcode
 213          *
 214          * d) Move a file within storage
 215          * @code
 216          *     array(
 217          *         'op'                  => 'move',
 218          *         'src'                 => <storage path>,
 219          *         'dst'                 => <storage path>,
 220          *         'overwrite'           => <boolean>,
 221          *         'overwriteSame'       => <boolean>,
 222          *         'ignoreMissingSource' => <boolean>, # since 1.21
 223          *         'disposition'         => <Content-Disposition header value>
 224          *     )
 225          * @endcode
 226          *
 227          * e) Delete a file within storage
 228          * @code
 229          *     array(
 230          *         'op'                  => 'delete',
 231          *         'src'                 => <storage path>,
 232          *         'ignoreMissingSource' => <boolean>
 233          *     )
 234          * @endcode
 235          *
 236          * f) Do nothing (no-op)
 237          * @code
 238          *     array(
 239          *         'op'                  => 'null',
 240          *     )
 241          * @endcode
 242          *
 243          * Boolean flags for operations (operation-specific):
 244          *   - ignoreMissingSource : The operation will simply succeed and do
 245          *                           nothing if the source file does not exist.
 246          *   - overwrite           : Any destination file will be overwritten.
 247          *   - overwriteSame       : An error will not be given if a file already
 248          *                           exists at the destination that has the same
 249          *                           contents as the new contents to be written there.
 250          *   - disposition         : When supplied, the backend will add a Content-Disposition
 251          *                           header when GETs/HEADs of the destination file are made.
 252          *                           Backends that don't support file metadata will ignore this.
 253          *                           See http://tools.ietf.org/html/rfc6266 (since 1.20).
 254          *
 255          * $opts is an associative of boolean flags, including:
 256          *   - force               : Operation precondition errors no longer trigger an abort.
 257          *                           Any remaining operations are still attempted. Unexpected
 258          *                           failures may still cause remaning operations to be aborted.
 259          *   - nonLocking          : No locks are acquired for the operations.
 260          *                           This can increase performance for non-critical writes.
 261          *                           This has no effect unless the 'force' flag is set.
 262          *   - allowStale          : Don't require the latest available data.
 263          *                           This can increase performance for non-critical writes.
 264          *                           This has no effect unless the 'force' flag is set.
 265          *   - nonJournaled        : Don't log this operation batch in the file journal.
 266          *                           This limits the ability of recovery scripts.
 267          *   - parallelize         : Try to do operations in parallel when possible.
 268          *   - bypassReadOnly      : Allow writes in read-only mode (since 1.20).
 269          *   - preserveCache       : Don't clear the process cache before checking files.
 270          *                           This should only be used if all entries in the process
 271          *                           cache were added after the files were already locked (since 1.20).
 272          *
 273          * @remarks Remarks on locking:
 274          * File system paths given to operations should refer to files that are
 275          * already locked or otherwise safe from modification from other processes.
 276          * Normally these files will be new temp files, which should be adequate.
 277          *
 278          * @par Return value:
 279          *
 280          * This returns a Status, which contains all warnings and fatals that occurred
 281          * during the operation. The 'failCount', 'successCount', and 'success' members
 282          * will reflect each operation attempted.
 283          *
 284          * The status will be "OK" unless:
 285          *   - a) unexpected operation errors occurred (network partitions, disk full...)
 286          *   - b) significant operation errors occurred and 'force' was not set
 287          *
 288          * @param $ops Array List of operations to execute in order
 289          * @param $opts Array Batch operation options
 290          * @return Status
 291          */
 292         final public function doOperations( array $ops, array $opts = array() ) {
 293                 if ( empty( $opts['bypassReadOnly'] ) && $this->isReadOnly() ) {
 294                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 295                 }
 296                 if ( empty( $opts['force'] ) ) { // sanity
 297                         unset( $opts['nonLocking'] );
 298                         unset( $opts['allowStale'] );
 299                 }
 300                 return $this->doOperationsInternal( $ops, $opts );
 301         }
 302
 303         /**
 304          * @see FileBackend::doOperations()
 305          */
 306         abstract protected function doOperationsInternal( array $ops, array $opts );
 307
 308         /**
 309          * Same as doOperations() except it takes a single operation.
 310          * If you are doing a batch of operations that should either
 311          * all succeed or all fail, then use that function instead.
 312          *
 313          * @see FileBackend::doOperations()
 314          *
 315          * @param $op Array Operation
 316          * @param $opts Array Operation options
 317          * @return Status
 318          */
 319         final public function doOperation( array $op, array $opts = array() ) {
 320                 return $this->doOperations( array( $op ), $opts );
 321         }
 322
 323         /**
 324          * Performs a single create operation.
 325          * This sets $params['op'] to 'create' 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 create( array $params, array $opts = array() ) {
 334                 return $this->doOperation( array( 'op' => 'create' ) + $params, $opts );
 335         }
 336
 337         /**
 338          * Performs a single store operation.
 339          * This sets $params['op'] to 'store' and passes it to doOperation().
 340          *
 341          * @see FileBackend::doOperation()
 342          *
 343          * @param $params Array Operation parameters
 344          * @param $opts Array Operation options
 345          * @return Status
 346          */
 347         final public function store( array $params, array $opts = array() ) {
 348                 return $this->doOperation( array( 'op' => 'store' ) + $params, $opts );
 349         }
 350
 351         /**
 352          * Performs a single copy operation.
 353          * This sets $params['op'] to 'copy' and passes it to doOperation().
 354          *
 355          * @see FileBackend::doOperation()
 356          *
 357          * @param $params Array Operation parameters
 358          * @param $opts Array Operation options
 359          * @return Status
 360          */
 361         final public function copy( array $params, array $opts = array() ) {
 362                 return $this->doOperation( array( 'op' => 'copy' ) + $params, $opts );
 363         }
 364
 365         /**
 366          * Performs a single move operation.
 367          * This sets $params['op'] to 'move' and passes it to doOperation().
 368          *
 369          * @see FileBackend::doOperation()
 370          *
 371          * @param $params Array Operation parameters
 372          * @param $opts Array Operation options
 373          * @return Status
 374          */
 375         final public function move( array $params, array $opts = array() ) {
 376                 return $this->doOperation( array( 'op' => 'move' ) + $params, $opts );
 377         }
 378
 379         /**
 380          * Performs a single delete operation.
 381          * This sets $params['op'] to 'delete' and passes it to doOperation().
 382          *
 383          * @see FileBackend::doOperation()
 384          *
 385          * @param $params Array Operation parameters
 386          * @param $opts Array Operation options
 387          * @return Status
 388          */
 389         final public function delete( array $params, array $opts = array() ) {
 390                 return $this->doOperation( array( 'op' => 'delete' ) + $params, $opts );
 391         }
 392
 393         /**
 394          * Perform a set of independent file operations on some files.
 395          *
 396          * This does no locking, nor journaling, and possibly no stat calls.
 397          * Any destination files that already exist will be overwritten.
 398          * This should *only* be used on non-original files, like cache files.
 399          *
 400          * Supported operations and their parameters:
 401          *  - create
 402          *  - store
 403          *  - copy
 404          *  - move
 405          *  - delete
 406          *  - null
 407          *
 408          * a) Create a new file in storage with the contents of a string
 409          * @code
 410          *     array(
 411          *         'op'                  => 'create',
 412          *         'dst'                 => <storage path>,
 413          *         'content'             => <string of new file contents>,
 414          *         'disposition'         => <Content-Disposition header value>
 415          *     )
 416          * @endcode
 417          * b) Copy a file system file into storage
 418          * @code
 419          *     array(
 420          *         'op'                  => 'store',
 421          *         'src'                 => <file system path>,
 422          *         'dst'                 => <storage path>,
 423          *         'disposition'         => <Content-Disposition header value>
 424          *     )
 425          * @endcode
 426          * c) Copy a file within storage
 427          * @code
 428          *     array(
 429          *         'op'                  => 'copy',
 430          *         'src'                 => <storage path>,
 431          *         'dst'                 => <storage path>,
 432          *         'ignoreMissingSource' => <boolean>, # since 1.21
 433          *         'disposition'         => <Content-Disposition header value>
 434          *     )
 435          * @endcode
 436          * d) Move a file within storage
 437          * @code
 438          *     array(
 439          *         'op'                  => 'move',
 440          *         'src'                 => <storage path>,
 441          *         'dst'                 => <storage path>,
 442          *         'ignoreMissingSource' => <boolean>, # since 1.21
 443          *         'disposition'         => <Content-Disposition header value>
 444          *     )
 445          * @endcode
 446          * e) Delete a file within storage
 447          * @code
 448          *     array(
 449          *         'op'                  => 'delete',
 450          *         'src'                 => <storage path>,
 451          *         'ignoreMissingSource' => <boolean>
 452          *     )
 453          * @endcode
 454          * f) Do nothing (no-op)
 455          * @code
 456          *     array(
 457          *         'op'                  => 'null',
 458          *     )
 459          * @endcode
 460          *
 461          * @par Boolean flags for operations (operation-specific):
 462          *   - ignoreMissingSource : The operation will simply succeed and do
 463          *                           nothing if the source file does not exist.
 464          *   - disposition         : When supplied, the backend will add a Content-Disposition
 465          *                           header when GETs/HEADs of the destination file are made.
 466          *                           Backends that don't support file metadata will ignore this.
 467          *                           See http://tools.ietf.org/html/rfc6266 (since 1.20).
 468          *
 469          * $opts is an associative of boolean flags, including:
 470          *   - bypassReadOnly      : Allow writes in read-only mode (since 1.20)
 471          *
 472          * @par Return value:
 473          * This returns a Status, which contains all warnings and fatals that occurred
 474          * during the operation. The 'failCount', 'successCount', and 'success' members
 475          * will reflect each operation attempted for the given files. The status will be
 476          * considered "OK" as long as no fatal errors occurred.
 477          *
 478          * @param $ops Array Set of operations to execute
 479          * @param $opts Array Batch operation options
 480          * @return Status
 481          * @since 1.20
 482          */
 483         final public function doQuickOperations( array $ops, array $opts = array() ) {
 484                 if ( empty( $opts['bypassReadOnly'] ) && $this->isReadOnly() ) {
 485                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 486                 }
 487                 foreach ( $ops as &$op ) {
 488                         $op['overwrite'] = true; // avoids RTTs in key/value stores
 489                 }
 490                 return $this->doQuickOperationsInternal( $ops );
 491         }
 492
 493         /**
 494          * @see FileBackend::doQuickOperations()
 495          * @since 1.20
 496          */
 497         abstract protected function doQuickOperationsInternal( array $ops );
 498
 499         /**
 500          * Same as doQuickOperations() except it takes a single operation.
 501          * If you are doing a batch of operations, then use that function instead.
 502          *
 503          * @see FileBackend::doQuickOperations()
 504          *
 505          * @param $op Array Operation
 506          * @return Status
 507          * @since 1.20
 508          */
 509         final public function doQuickOperation( array $op ) {
 510                 return $this->doQuickOperations( array( $op ) );
 511         }
 512
 513         /**
 514          * Performs a single quick create operation.
 515          * This sets $params['op'] to 'create' and passes it to doQuickOperation().
 516          *
 517          * @see FileBackend::doQuickOperation()
 518          *
 519          * @param $params Array Operation parameters
 520          * @return Status
 521          * @since 1.20
 522          */
 523         final public function quickCreate( array $params ) {
 524                 return $this->doQuickOperation( array( 'op' => 'create' ) + $params );
 525         }
 526
 527         /**
 528          * Performs a single quick store operation.
 529          * This sets $params['op'] to 'store' and passes it to doQuickOperation().
 530          *
 531          * @see FileBackend::doQuickOperation()
 532          *
 533          * @param $params Array Operation parameters
 534          * @return Status
 535          * @since 1.20
 536          */
 537         final public function quickStore( array $params ) {
 538                 return $this->doQuickOperation( array( 'op' => 'store' ) + $params );
 539         }
 540
 541         /**
 542          * Performs a single quick copy operation.
 543          * This sets $params['op'] to 'copy' and passes it to doQuickOperation().
 544          *
 545          * @see FileBackend::doQuickOperation()
 546          *
 547          * @param $params Array Operation parameters
 548          * @return Status
 549          * @since 1.20
 550          */
 551         final public function quickCopy( array $params ) {
 552                 return $this->doQuickOperation( array( 'op' => 'copy' ) + $params );
 553         }
 554
 555         /**
 556          * Performs a single quick move operation.
 557          * This sets $params['op'] to 'move' and passes it to doQuickOperation().
 558          *
 559          * @see FileBackend::doQuickOperation()
 560          *
 561          * @param $params Array Operation parameters
 562          * @return Status
 563          * @since 1.20
 564          */
 565         final public function quickMove( array $params ) {
 566                 return $this->doQuickOperation( array( 'op' => 'move' ) + $params );
 567         }
 568
 569         /**
 570          * Performs a single quick delete operation.
 571          * This sets $params['op'] to 'delete' and passes it to doQuickOperation().
 572          *
 573          * @see FileBackend::doQuickOperation()
 574          *
 575          * @param $params Array Operation parameters
 576          * @return Status
 577          * @since 1.20
 578          */
 579         final public function quickDelete( array $params ) {
 580                 return $this->doQuickOperation( array( 'op' => 'delete' ) + $params );
 581         }
 582
 583         /**
 584          * Concatenate a list of storage files into a single file system file.
 585          * The target path should refer to a file that is already locked or
 586          * otherwise safe from modification from other processes. Normally,
 587          * the file will be a new temp file, which should be adequate.
 588          *
 589          * If a callback function is given, it will be called each time a segment is
 590          * appended and when the overall concatenate operation completes or fails.
 591          * The arguments passed in are:
 592          *   - 1) A Status object containing errors if any problems occurred.
 593          *   - 2) The index of the relevant segment (starting at 1) if a segment was appended
 594          *        (including the last one) or null in the case of overall success or failure.
 595          * When a good Status is returned with a null segment, then the operation completed.
 596          * Callbacks should generally avoid throwing exceptions.
 597          *
 598          * @param $params Array Operation parameters
 599          * $params include:
 600          *   - srcs        : ordered source storage paths (e.g. chunk1, chunk2, ...)
 601          *   - dst         : file system path to 0-byte temp file
 602          *   - parallelize : try to do operations in parallel when possible
 603          *   - callback    : closure called when chunks are appended and on success/failure
 604          * @return Status
 605          */
 606         abstract public function concatenate( array $params );
 607
 608         /**
 609          * Prepare a storage directory for usage.
 610          * This will create any required containers and parent directories.
 611          * Backends using key/value stores only need to create the container.
 612          *
 613          * The 'noAccess' and 'noListing' parameters works the same as in secure(),
 614          * except they are only applied *if* the directory/container had to be created.
 615          * These flags should always be set for directories that have private files.
 616          *
 617          * @param $params Array
 618          * $params include:
 619          *   - dir            : storage directory
 620          *   - noAccess       : try to deny file access (since 1.20)
 621          *   - noListing      : try to deny file listing (since 1.20)
 622          *   - bypassReadOnly : allow writes in read-only mode (since 1.20)
 623          * @return Status
 624          */
 625         final public function prepare( array $params ) {
 626                 if ( empty( $params['bypassReadOnly'] ) && $this->isReadOnly() ) {
 627                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 628                 }
 629                 return $this->doPrepare( $params );
 630         }
 631
 632         /**
 633          * @see FileBackend::prepare()
 634          */
 635         abstract protected function doPrepare( array $params );
 636
 637         /**
 638          * Take measures to block web access to a storage directory and
 639          * the container it belongs to. FS backends might add .htaccess
 640          * files whereas key/value store backends might revoke container
 641          * access to the storage user representing end-users in web requests.
 642          * This is not guaranteed to actually do anything.
 643          *
 644          * @param $params Array
 645          * $params include:
 646          *   - dir            : storage directory
 647          *   - noAccess       : try to deny file access
 648          *   - noListing      : try to deny file listing
 649          *   - bypassReadOnly : allow writes in read-only mode (since 1.20)
 650          * @return Status
 651          */
 652         final public function secure( array $params ) {
 653                 if ( empty( $params['bypassReadOnly'] ) && $this->isReadOnly() ) {
 654                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 655                 }
 656                 return $this->doSecure( $params );
 657         }
 658
 659         /**
 660          * @see FileBackend::secure()
 661          */
 662         abstract protected function doSecure( array $params );
 663
 664         /**
 665          * Remove measures to block web access to a storage directory and
 666          * the container it belongs to. FS backends might remove .htaccess
 667          * files whereas key/value store backends might grant container
 668          * access to the storage user representing end-users in web requests.
 669          * This essentially can undo the result of secure() calls.
 670          *
 671          * @param $params Array
 672          * $params include:
 673          *   - dir            : storage directory
 674          *   - access         : try to allow file access
 675          *   - listing        : try to allow file listing
 676          *   - bypassReadOnly : allow writes in read-only mode (since 1.20)
 677          * @return Status
 678          * @since 1.20
 679          */
 680         final public function publish( array $params ) {
 681                 if ( empty( $params['bypassReadOnly'] ) && $this->isReadOnly() ) {
 682                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 683                 }
 684                 return $this->doPublish( $params );
 685         }
 686
 687         /**
 688          * @see FileBackend::publish()
 689          */
 690         abstract protected function doPublish( array $params );
 691
 692         /**
 693          * Delete a storage directory if it is empty.
 694          * Backends using key/value stores may do nothing unless the directory
 695          * is that of an empty container, in which case it will be deleted.
 696          *
 697          * @param $params Array
 698          * $params include:
 699          *   - dir            : storage directory
 700          *   - recursive      : recursively delete empty subdirectories first (since 1.20)
 701          *   - bypassReadOnly : allow writes in read-only mode (since 1.20)
 702          * @return Status
 703          */
 704         final public function clean( array $params ) {
 705                 if ( empty( $params['bypassReadOnly'] ) && $this->isReadOnly() ) {
 706                         return Status::newFatal( 'backend-fail-readonly', $this->name, $this->readOnly );
 707                 }
 708                 return $this->doClean( $params );
 709         }
 710
 711         /**
 712          * @see FileBackend::clean()
 713          */
 714         abstract protected function doClean( array $params );
 715
 716         /**
 717          * Check if a file exists at a storage path in the backend.
 718          * This returns false if only a directory exists at the path.
 719          *
 720          * @param $params Array
 721          * $params include:
 722          *   - src    : source storage path
 723          *   - latest : use the latest available data
 724          * @return bool|null Returns null on failure
 725          */
 726         abstract public function fileExists( array $params );
 727
 728         /**
 729          * Get the last-modified timestamp of the file at a storage path.
 730          *
 731          * @param $params Array
 732          * $params include:
 733          *   - src    : source storage path
 734          *   - latest : use the latest available data
 735          * @return string|bool TS_MW timestamp or false on failure
 736          */
 737         abstract public function getFileTimestamp( array $params );
 738
 739         /**
 740          * Get the contents of a file at a storage path in the backend.
 741          * This should be avoided for potentially large files.
 742          *
 743          * @param $params Array
 744          * $params include:
 745          *   - src    : source storage path
 746          *   - latest : use the latest available data
 747          * @return string|bool Returns false on failure
 748          */
 749         final public function getFileContents( array $params ) {
 750                 $contents = $this->getFileContentsMulti(
 751                         array( 'srcs' => array( $params['src'] ) ) + $params );
 752
 753                 return $contents[$params['src']];
 754         }
 755
 756         /**
 757          * Like getFileContents() except it takes an array of storage paths
 758          * and returns a map of storage paths to strings (or null on failure).
 759          * The map keys (paths) are in the same order as the provided list of paths.
 760          *
 761          * @see FileBackend::getFileContents()
 762          *
 763          * @param $params Array
 764          * $params include:
 765          *   - srcs        : list of source storage paths
 766          *   - latest      : use the latest available data
 767          *   - parallelize : try to do operations in parallel when possible
 768          * @return Array Map of (path name => string or false on failure)
 769          * @since 1.20
 770          */
 771         abstract public function getFileContentsMulti( array $params );
 772
 773         /**
 774          * Get the size (bytes) of a file at a storage path in the backend.
 775          *
 776          * @param $params Array
 777          * $params include:
 778          *   - src    : source storage path
 779          *   - latest : use the latest available data
 780          * @return integer|bool Returns false on failure
 781          */
 782         abstract public function getFileSize( array $params );
 783
 784         /**
 785          * Get quick information about a file at a storage path in the backend.
 786          * If the file does not exist, then this returns false.
 787          * Otherwise, the result is an associative array that includes:
 788          *   - mtime  : the last-modified timestamp (TS_MW)
 789          *   - size   : the file size (bytes)
 790          * Additional values may be included for internal use only.
 791          *
 792          * @param $params Array
 793          * $params include:
 794          *   - src    : source storage path
 795          *   - latest : use the latest available data
 796          * @return Array|bool|null Returns null on failure
 797          */
 798         abstract public function getFileStat( array $params );
 799
 800         /**
 801          * Get a SHA-1 hash of the file at a storage path in the backend.
 802          *
 803          * @param $params Array
 804          * $params include:
 805          *   - src    : source storage path
 806          *   - latest : use the latest available data
 807          * @return string|bool Hash string or false on failure
 808          */
 809         abstract public function getFileSha1Base36( array $params );
 810
 811         /**
 812          * Get the properties of the file at a storage path in the backend.
 813          * Returns FSFile::placeholderProps() on failure.
 814          *
 815          * @param $params Array
 816          * $params include:
 817          *   - src    : source storage path
 818          *   - latest : use the latest available data
 819          * @return Array
 820          */
 821         abstract public function getFileProps( array $params );
 822
 823         /**
 824          * Stream the file at a storage path in the backend.
 825          * If the file does not exists, an HTTP 404 error will be given.
 826          * Appropriate HTTP headers (Status, Content-Type, Content-Length)
 827          * will be sent if streaming began, while none will be sent otherwise.
 828          * Implementations should flush the output buffer before sending data.
 829          *
 830          * @param $params Array
 831          * $params include:
 832          *   - src     : source storage path
 833          *   - headers : list of additional HTTP headers to send on success
 834          *   - latest  : use the latest available data
 835          * @return Status
 836          */
 837         abstract public function streamFile( array $params );
 838
 839         /**
 840          * Returns a file system file, identical to the file at a storage path.
 841          * The file returned is either:
 842          *   - a) A local copy of the file at a storage path in the backend.
 843          *        The temporary copy will have the same extension as the source.
 844          *   - b) An original of the file at a storage path in the backend.
 845          * Temporary files may be purged when the file object falls out of scope.
 846          *
 847          * Write operations should *never* be done on this file as some backends
 848          * may do internal tracking or may be instances of FileBackendMultiWrite.
 849          * In that later case, there are copies of the file that must stay in sync.
 850          * Additionally, further calls to this function may return the same file.
 851          *
 852          * @param $params Array
 853          * $params include:
 854          *   - src    : source storage path
 855          *   - latest : use the latest available data
 856          * @return FSFile|null Returns null on failure
 857          */
 858         final public function getLocalReference( array $params ) {
 859                 $fsFiles = $this->getLocalReferenceMulti(
 860                         array( 'srcs' => array( $params['src'] ) ) + $params );
 861
 862                 return $fsFiles[$params['src']];
 863         }
 864
 865         /**
 866          * Like getLocalReference() except it takes an array of storage paths
 867          * and returns a map of storage paths to FSFile objects (or null on failure).
 868          * The map keys (paths) are in the same order as the provided list of paths.
 869          *
 870          * @see FileBackend::getLocalReference()
 871          *
 872          * @param $params Array
 873          * $params include:
 874          *   - srcs        : list of source storage paths
 875          *   - latest      : use the latest available data
 876          *   - parallelize : try to do operations in parallel when possible
 877          * @return Array Map of (path name => FSFile or null on failure)
 878          * @since 1.20
 879          */
 880         abstract public function getLocalReferenceMulti( array $params );
 881
 882         /**
 883          * Get a local copy on disk of the file at a storage path in the backend.
 884          * The temporary copy will have the same file extension as the source.
 885          * Temporary files may be purged when the file object falls out of scope.
 886          *
 887          * @param $params Array
 888          * $params include:
 889          *   - src    : source storage path
 890          *   - latest : use the latest available data
 891          * @return TempFSFile|null Returns null on failure
 892          */
 893         final public function getLocalCopy( array $params ) {
 894                 $tmpFiles = $this->getLocalCopyMulti(
 895                         array( 'srcs' => array( $params['src'] ) ) + $params );
 896
 897                 return $tmpFiles[$params['src']];
 898         }
 899
 900         /**
 901          * Like getLocalCopy() except it takes an array of storage paths and
 902          * returns a map of storage paths to TempFSFile objects (or null on failure).
 903          * The map keys (paths) are in the same order as the provided list of paths.
 904          *
 905          * @see FileBackend::getLocalCopy()
 906          *
 907          * @param $params Array
 908          * $params include:
 909          *   - srcs        : list of source storage paths
 910          *   - latest      : use the latest available data
 911          *   - parallelize : try to do operations in parallel when possible
 912          * @return Array Map of (path name => TempFSFile or null on failure)
 913          * @since 1.20
 914          */
 915         abstract public function getLocalCopyMulti( array $params );
 916
 917         /**
 918          * Return an HTTP URL to a given file that requires no authentication to use.
 919          * The URL may be pre-authenticated (via some token in the URL) and temporary.
 920          * This will return null if the backend cannot make an HTTP URL for the file.
 921          *
 922          * This is useful for key/value stores when using scripts that seek around
 923          * large files and those scripts (and the backend) support HTTP Range headers.
 924          * Otherwise, one would need to use getLocalReference(), which involves loading
 925          * the entire file on to local disk.
 926          *
 927          * @param $params Array
 928          * $params include:
 929          *   - src : source storage path
 930          * @return string|null
 931          * @since 1.21
 932          */
 933         abstract public function getFileHttpUrl( array $params );
 934
 935         /**
 936          * Check if a directory exists at a given storage path.
 937          * Backends using key/value stores will check if the path is a
 938          * virtual directory, meaning there are files under the given directory.
 939          *
 940          * Storage backends with eventual consistency might return stale data.
 941          *
 942          * @param $params array
 943          * $params include:
 944          *   - dir : storage directory
 945          * @return bool|null Returns null on failure
 946          * @since 1.20
 947          */
 948         abstract public function directoryExists( array $params );
 949
 950         /**
 951          * Get an iterator to list *all* directories under a storage directory.
 952          * If the directory is of the form "mwstore://backend/container",
 953          * then all directories in the container will be listed.
 954          * If the directory is of form "mwstore://backend/container/dir",
 955          * then all directories directly under that directory will be listed.
 956          * Results will be storage directories relative to the given directory.
 957          *
 958          * Storage backends with eventual consistency might return stale data.
 959          *
 960          * @param $params array
 961          * $params include:
 962          *   - dir     : storage directory
 963          *   - topOnly : only return direct child dirs of the directory
 964          * @return Traversable|Array|null Returns null on failure
 965          * @since 1.20
 966          */
 967         abstract public function getDirectoryList( array $params );
 968
 969         /**
 970          * Same as FileBackend::getDirectoryList() except only lists
 971          * directories that are immediately under the given directory.
 972          *
 973          * Storage backends with eventual consistency might return stale data.
 974          *
 975          * @param $params array
 976          * $params include:
 977          *   - dir : storage directory
 978          * @return Traversable|Array|null Returns null on failure
 979          * @since 1.20
 980          */
 981         final public function getTopDirectoryList( array $params ) {
 982                 return $this->getDirectoryList( array( 'topOnly' => true ) + $params );
 983         }
 984
 985         /**
 986          * Get an iterator to list *all* stored files under a storage directory.
 987          * If the directory is of the form "mwstore://backend/container",
 988          * then all files in the container will be listed.
 989          * If the directory is of form "mwstore://backend/container/dir",
 990          * then all files under that directory will be listed.
 991          * Results will be storage paths relative to the given directory.
 992          *
 993          * Storage backends with eventual consistency might return stale data.
 994          *
 995          * @param $params array
 996          * $params include:
 997          *   - dir     : storage directory
 998          *   - topOnly : only return direct child files of the directory (since 1.20)
 999          * @return Traversable|Array|null Returns null on failure
1000          */
1001         abstract public function getFileList( array $params );
1002
1003         /**
1004          * Same as FileBackend::getFileList() except only lists
1005          * files that are immediately under the given directory.
1006          *
1007          * Storage backends with eventual consistency might return stale data.
1008          *
1009          * @param $params array
1010          * $params include:
1011          *   - dir : storage directory
1012          * @return Traversable|Array|null Returns null on failure
1013          * @since 1.20
1014          */
1015         final public function getTopFileList( array $params ) {
1016                 return $this->getFileList( array( 'topOnly' => true ) + $params );
1017         }
1018
1019         /**
1020          * Preload persistent file stat and property cache into in-process cache.
1021          * This should be used when stat calls will be made on a known list of a many files.
1022          *
1023          * @param $paths Array Storage paths
1024          * @return void
1025          */
1026         public function preloadCache( array $paths ) {}
1027
1028         /**
1029          * Invalidate any in-process file stat and property cache.
1030          * If $paths is given, then only the cache for those files will be cleared.
1031          *
1032          * @param $paths Array Storage paths (optional)
1033          * @return void
1034          */
1035         public function clearCache( array $paths = null ) {}
1036
1037         /**
1038          * Lock the files at the given storage paths in the backend.
1039          * This will either lock all the files or none (on failure).
1040          *
1041          * Callers should consider using getScopedFileLocks() instead.
1042          *
1043          * @param $paths Array Storage paths
1044          * @param $type integer LockManager::LOCK_* constant
1045          * @return Status
1046          */
1047         final public function lockFiles( array $paths, $type ) {
1048                 return $this->lockManager->lock( $paths, $type );
1049         }
1050
1051         /**
1052          * Unlock the files at the given storage paths in the backend.
1053          *
1054          * @param $paths Array Storage paths
1055          * @param $type integer LockManager::LOCK_* constant
1056          * @return Status
1057          */
1058         final public function unlockFiles( array $paths, $type ) {
1059                 return $this->lockManager->unlock( $paths, $type );
1060         }
1061
1062         /**
1063          * Lock the files at the given storage paths in the backend.
1064          * This will either lock all the files or none (on failure).
1065          * On failure, the status object will be updated with errors.
1066          *
1067          * Once the return value goes out scope, the locks will be released and
1068          * the status updated. Unlock fatals will not change the status "OK" value.
1069          *
1070          * @param $paths Array Storage paths
1071          * @param $type integer LockManager::LOCK_* constant
1072          * @param $status Status Status to update on lock/unlock
1073          * @return ScopedLock|null Returns null on failure
1074          */
1075         final public function getScopedFileLocks( array $paths, $type, Status $status ) {
1076                 return ScopedLock::factory( $this->lockManager, $paths, $type, $status );
1077         }
1078
1079         /**
1080          * Get an array of scoped locks needed for a batch of file operations.
1081          *
1082          * Normally, FileBackend::doOperations() handles locking, unless
1083          * the 'nonLocking' param is passed in. This function is useful if you
1084          * want the files to be locked for a broader scope than just when the
1085          * files are changing. For example, if you need to update DB metadata,
1086          * you may want to keep the files locked until finished.
1087          *
1088          * @see FileBackend::doOperations()
1089          *
1090          * @param $ops Array List of file operations to FileBackend::doOperations()
1091          * @param $status Status Status to update on lock/unlock
1092          * @return Array List of ScopedFileLocks or null values
1093          * @since 1.20
1094          */
1095         abstract public function getScopedLocksForOps( array $ops, Status $status );
1096
1097         /**
1098          * Get the root storage path of this backend.
1099          * All container paths are "subdirectories" of this path.
1100          *
1101          * @return string Storage path
1102          * @since 1.20
1103          */
1104         final public function getRootStoragePath() {
1105                 return "mwstore://{$this->name}";
1106         }
1107
1108         /**
1109          * Get the storage path for the given container for this backend
1110          *
1111          * @param $container string Container name
1112          * @return string Storage path
1113          * @since 1.21
1114          */
1115         final public function getContainerStoragePath( $container ) {
1116                 return $this->getRootStoragePath() . "/{$container}";
1117         }
1118
1119         /**
1120          * Get the file journal object for this backend
1121          *
1122          * @return FileJournal
1123          */
1124         final public function getJournal() {
1125                 return $this->fileJournal;
1126         }
1127
1128         /**
1129          * Check if a given path is a "mwstore://" path.
1130          * This does not do any further validation or any existence checks.
1131          *
1132          * @param $path string
1133          * @return bool
1134          */
1135         final public static function isStoragePath( $path ) {
1136                 return ( strpos( $path, 'mwstore://' ) === 0 );
1137         }
1138
1139         /**
1140          * Split a storage path into a backend name, a container name,
1141          * and a relative file path. The relative path may be the empty string.
1142          * This does not do any path normalization or traversal checks.
1143          *
1144          * @param $storagePath string
1145          * @return Array (backend, container, rel object) or (null, null, null)
1146          */
1147         final public static function splitStoragePath( $storagePath ) {
1148                 if ( self::isStoragePath( $storagePath ) ) {
1149                         // Remove the "mwstore://" prefix and split the path
1150                         $parts = explode( '/', substr( $storagePath, 10 ), 3 );
1151                         if ( count( $parts ) >= 2 && $parts[0] != '' && $parts[1] != '' ) {
1152                                 if ( count( $parts ) == 3 ) {
1153                                         return $parts; // e.g. "backend/container/path"
1154                                 } else {
1155                                         return array( $parts[0], $parts[1], '' ); // e.g. "backend/container"
1156                                 }
1157                         }
1158                 }
1159                 return array( null, null, null );
1160         }
1161
1162         /**
1163          * Normalize a storage path by cleaning up directory separators.
1164          * Returns null if the path is not of the format of a valid storage path.
1165          *
1166          * @param $storagePath string
1167          * @return string|null
1168          */
1169         final public static function normalizeStoragePath( $storagePath ) {
1170                 list( $backend, $container, $relPath ) = self::splitStoragePath( $storagePath );
1171                 if ( $relPath !== null ) { // must be for this backend
1172                         $relPath = self::normalizeContainerPath( $relPath );
1173                         if ( $relPath !== null ) {
1174                                 return ( $relPath != '' )
1175                                         ? "mwstore://{$backend}/{$container}/{$relPath}"
1176                                         : "mwstore://{$backend}/{$container}";
1177                         }
1178                 }
1179                 return null;
1180         }
1181
1182         /**
1183          * Get the parent storage directory of a storage path.
1184          * This returns a path like "mwstore://backend/container",
1185          * "mwstore://backend/container/...", or null if there is no parent.
1186          *
1187          * @param $storagePath string
1188          * @return string|null
1189          */
1190         final public static function parentStoragePath( $storagePath ) {
1191                 $storagePath = dirname( $storagePath );
1192                 list( $b, $cont, $rel ) = self::splitStoragePath( $storagePath );
1193                 return ( $rel === null ) ? null : $storagePath;
1194         }
1195
1196         /**
1197          * Get the final extension from a storage or FS path
1198          *
1199          * @param $path string
1200          * @return string
1201          */
1202         final public static function extensionFromPath( $path ) {
1203                 $i = strrpos( $path, '.' );
1204                 return strtolower( $i ? substr( $path, $i + 1 ) : '' );
1205         }
1206
1207         /**
1208          * Check if a relative path has no directory traversals
1209          *
1210          * @param $path string
1211          * @return bool
1212          * @since 1.20
1213          */
1214         final public static function isPathTraversalFree( $path ) {
1215                 return ( self::normalizeContainerPath( $path ) !== null );
1216         }
1217
1218         /**
1219          * Build a Content-Disposition header value per RFC 6266.
1220          *
1221          * @param $type string One of (attachment, inline)
1222          * @param $filename string Suggested file name (should not contain slashes)
1223          * @throws MWException
1224          * @return string
1225          * @since 1.20
1226          */
1227         final public static function makeContentDisposition( $type, $filename = '' ) {
1228                 $parts = array();
1229
1230                 $type = strtolower( $type );
1231                 if ( !in_array( $type, array( 'inline', 'attachment' ) ) ) {
1232                         throw new MWException( "Invalid Content-Disposition type '$type'." );
1233                 }
1234                 $parts[] = $type;
1235
1236                 if ( strlen( $filename ) ) {
1237                         $parts[] = "filename*=UTF-8''" . rawurlencode( basename( $filename ) );
1238                 }
1239
1240                 return implode( ';', $parts );
1241         }
1242
1243         /**
1244          * Validate and normalize a relative storage path.
1245          * Null is returned if the path involves directory traversal.
1246          * Traversal is insecure for FS backends and broken for others.
1247          *
1248          * This uses the same traversal protection as Title::secureAndSplit().
1249          *
1250          * @param $path string Storage path relative to a container
1251          * @return string|null
1252          */
1253         final protected static function normalizeContainerPath( $path ) {
1254                 // Normalize directory separators
1255                 $path = strtr( $path, '\\', '/' );
1256                 // Collapse any consecutive directory separators
1257                 $path = preg_replace( '![/]{2,}!', '/', $path );
1258                 // Remove any leading directory separator
1259                 $path = ltrim( $path, '/' );
1260                 // Use the same traversal protection as Title::secureAndSplit()
1261                 if ( strpos( $path, '.' ) !== false ) {
1262                         if (
1263                                 $path === '.' ||
1264                                 $path === '..' ||
1265                                 strpos( $path, './' ) === 0 ||
1266                                 strpos( $path, '../' ) === 0 ||
1267                                 strpos( $path, '/./' ) !== false ||
1268                                 strpos( $path, '/../' ) !== false
1269                         ) {
1270                                 return null;
1271                         }
1272                 }
1273                 return $path;
1274         }
1275 }