includes/content/ContentHandler.php

   1 <?php
   2
   3 /**
   4  * Base class for content handling.
   5  *
   6  * This program is free software; you can redistribute it and/or modify
   7  * it under the terms of the GNU General Public License as published by
   8  * the Free Software Foundation; either version 2 of the License, or
   9  * (at your option) any later version.
  10  *
  11  * This program is distributed in the hope that it will be useful,
  12  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  13  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  14  * GNU General Public License for more details.
  15  *
  16  * You should have received a copy of the GNU General Public License along
  17  * with this program; if not, write to the Free Software Foundation, Inc.,
  18  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  19  * http://www.gnu.org/copyleft/gpl.html
  20  *
  21  * @since 1.21
  22  *
  23  * @file
  24  * @ingroup Content
  25  *
  26  * @author Daniel Kinzler
  27  */
  28
  29 use MediaWiki\Storage\RevisionRecord;
  30 use Wikimedia\Assert\Assert;
  31 use MediaWiki\Logger\LoggerFactory;
  32 use MediaWiki\MediaWikiServices;
  33 use MediaWiki\Revision\SlotRenderingProvider;
  34 use MediaWiki\Search\ParserOutputSearchDataExtractor;
  35
  36 /**
  37  * A content handler knows how do deal with a specific type of content on a wiki
  38  * page. Content is stored in the database in a serialized form (using a
  39  * serialization format a.k.a. MIME type) and is unserialized into its native
  40  * PHP representation (the content model), which is wrapped in an instance of
  41  * the appropriate subclass of Content.
  42  *
  43  * ContentHandler instances are stateless singletons that serve, among other
  44  * things, as a factory for Content objects. Generally, there is one subclass
  45  * of ContentHandler and one subclass of Content for every type of content model.
  46  *
  47  * Some content types have a flat model, that is, their native representation
  48  * is the same as their serialized form. Examples would be JavaScript and CSS
  49  * code. As of now, this also applies to wikitext (MediaWiki's default content
  50  * type), but wikitext content may be represented by a DOM or AST structure in
  51  * the future.
  52  *
  53  * @ingroup Content
  54  */
  55 abstract class ContentHandler {
  56         /**
  57          * Convenience function for getting flat text from a Content object. This
  58          * should only be used in the context of backwards compatibility with code
  59          * that is not yet able to handle Content objects!
  60          *
  61          * If $content is null, this method returns the empty string.
  62          *
  63          * If $content is an instance of TextContent, this method returns the flat
  64          * text as returned by $content->getText().
  65          *
  66          * If $content is not a TextContent object, the behavior of this method
  67          * depends on the global $wgContentHandlerTextFallback:
  68          * - If $wgContentHandlerTextFallback is 'fail' and $content is not a
  69          *   TextContent object, an MWException is thrown.
  70          * - If $wgContentHandlerTextFallback is 'serialize' and $content is not a
  71          *   TextContent object, $content->serialize() is called to get a string
  72          *   form of the content.
  73          * - If $wgContentHandlerTextFallback is 'ignore' and $content is not a
  74          *   TextContent object, this method returns null.
  75          * - otherwise, the behavior is undefined.
  76          *
  77          * @since 1.21
  78          *
  79          * @param Content|null $content
  80          *
  81          * @throws MWException If the content is not an instance of TextContent and
  82          * wgContentHandlerTextFallback was set to 'fail'.
  83          * @return string|null Textual form of the content, if available.
  84          */
  85         public static function getContentText( Content $content = null ) {
  86                 global $wgContentHandlerTextFallback;
  87
  88                 if ( is_null( $content ) ) {
  89                         return '';
  90                 }
  91
  92                 if ( $content instanceof TextContent ) {
  93                         return $content->getText();
  94                 }
  95
  96                 wfDebugLog( 'ContentHandler', 'Accessing ' . $content->getModel() . ' content as text!' );
  97
  98                 if ( $wgContentHandlerTextFallback == 'fail' ) {
  99                         throw new MWException(
 100                                 "Attempt to get text from Content with model " .
 101                                 $content->getModel()
 102                         );
 103                 }
 104
 105                 if ( $wgContentHandlerTextFallback == 'serialize' ) {
 106                         return $content->serialize();
 107                 }
 108
 109                 return null;
 110         }
 111
 112         /**
 113          * Convenience function for creating a Content object from a given textual
 114          * representation.
 115          *
 116          * $text will be deserialized into a Content object of the model specified
 117          * by $modelId (or, if that is not given, $title->getContentModel()) using
 118          * the given format.
 119          *
 120          * @since 1.21
 121          *
 122          * @param string $text The textual representation, will be
 123          *    unserialized to create the Content object
 124          * @param Title|null $title The title of the page this text belongs to.
 125          *    Required if $modelId is not provided.
 126          * @param string|null $modelId The model to deserialize to. If not provided,
 127          *    $title->getContentModel() is used.
 128          * @param string|null $format The format to use for deserialization. If not
 129          *    given, the model's default format is used.
 130          *
 131          * @throws MWException If model ID or format is not supported or if the text can not be
 132          * unserialized using the format.
 133          * @return Content A Content object representing the text.
 134          */
 135         public static function makeContent( $text, Title $title = null,
 136                 $modelId = null, $format = null ) {
 137                 if ( is_null( $modelId ) ) {
 138                         if ( is_null( $title ) ) {
 139                                 throw new MWException( "Must provide a Title object or a content model ID." );
 140                         }
 141
 142                         $modelId = $title->getContentModel();
 143                 }
 144
 145                 $handler = self::getForModelID( $modelId );
 146
 147                 return $handler->unserializeContent( $text, $format );
 148         }
 149
 150         /**
 151          * Returns the name of the default content model to be used for the page
 152          * with the given title.
 153          *
 154          * Note: There should rarely be need to call this method directly.
 155          * To determine the actual content model for a given page, use
 156          * Title::getContentModel().
 157          *
 158          * Which model is to be used by default for the page is determined based
 159          * on several factors:
 160          * - The global setting $wgNamespaceContentModels specifies a content model
 161          *   per namespace.
 162          * - The hook ContentHandlerDefaultModelFor may be used to override the page's default
 163          *   model.
 164          * - Pages in NS_MEDIAWIKI and NS_USER default to the CSS or JavaScript
 165          *   model if they end in .js or .css, respectively.
 166          * - Pages in NS_MEDIAWIKI default to the wikitext model otherwise.
 167          * - The hook TitleIsCssOrJsPage may be used to force a page to use the CSS
 168          *   or JavaScript model. This is a compatibility feature. The ContentHandlerDefaultModelFor
 169          *   hook should be used instead if possible.
 170          * - The hook TitleIsWikitextPage may be used to force a page to use the
 171          *   wikitext model. This is a compatibility feature. The ContentHandlerDefaultModelFor
 172          *   hook should be used instead if possible.
 173          *
 174          * If none of the above applies, the wikitext model is used.
 175          *
 176          * Note: this is used by, and may thus not use, Title::getContentModel()
 177          *
 178          * @since 1.21
 179          * @deprecated since 1.33, use SlotRoleHandler::getDefaultModel() together with
 180          * SlotRoleRegistry::getRoleHandler().
 181          *
 182          * @param Title $title
 183          *
 184          * @return string Default model name for the page given by $title
 185          */
 186         public static function getDefaultModelFor( Title $title ) {
 187                 $slotRoleregistry = MediaWikiServices::getInstance()->getSlotRoleRegistry();
 188                 $mainSlotHandler = $slotRoleregistry->getRoleHandler( 'main' );
 189                 return $mainSlotHandler->getDefaultModel( $title );
 190         }
 191
 192         /**
 193          * Returns the appropriate ContentHandler singleton for the given title.
 194          *
 195          * @since 1.21
 196          *
 197          * @param Title $title
 198          *
 199          * @return ContentHandler
 200          */
 201         public static function getForTitle( Title $title ) {
 202                 $modelId = $title->getContentModel();
 203
 204                 return self::getForModelID( $modelId );
 205         }
 206
 207         /**
 208          * Returns the appropriate ContentHandler singleton for the given Content
 209          * object.
 210          *
 211          * @since 1.21
 212          *
 213          * @param Content $content
 214          *
 215          * @return ContentHandler
 216          */
 217         public static function getForContent( Content $content ) {
 218                 $modelId = $content->getModel();
 219
 220                 return self::getForModelID( $modelId );
 221         }
 222
 223         /**
 224          * @var array A Cache of ContentHandler instances by model id
 225          */
 226         protected static $handlers;
 227
 228         /**
 229          * Returns the ContentHandler singleton for the given model ID. Use the
 230          * CONTENT_MODEL_XXX constants to identify the desired content model.
 231          *
 232          * ContentHandler singletons are taken from the global $wgContentHandlers
 233          * array. Keys in that array are model names, the values are either
 234          * ContentHandler singleton objects, or strings specifying the appropriate
 235          * subclass of ContentHandler.
 236          *
 237          * If a class name is encountered when looking up the singleton for a given
 238          * model name, the class is instantiated and the class name is replaced by
 239          * the resulting singleton in $wgContentHandlers.
 240          *
 241          * If no ContentHandler is defined for the desired $modelId, the
 242          * ContentHandler may be provided by the ContentHandlerForModelID hook.
 243          * If no ContentHandler can be determined, an MWException is raised.
 244          *
 245          * @since 1.21
 246          *
 247          * @param string $modelId The ID of the content model for which to get a
 248          *    handler. Use CONTENT_MODEL_XXX constants.
 249          *
 250          * @throws MWException For internal errors and problems in the configuration.
 251          * @throws MWUnknownContentModelException If no handler is known for the model ID.
 252          * @return ContentHandler The ContentHandler singleton for handling the model given by the ID.
 253          */
 254         public static function getForModelID( $modelId ) {
 255                 global $wgContentHandlers;
 256
 257                 if ( isset( self::$handlers[$modelId] ) ) {
 258                         return self::$handlers[$modelId];
 259                 }
 260
 261                 if ( empty( $wgContentHandlers[$modelId] ) ) {
 262                         $handler = null;
 263
 264                         Hooks::run( 'ContentHandlerForModelID', [ $modelId, &$handler ] );
 265
 266                         if ( $handler === null ) {
 267                                 throw new MWUnknownContentModelException( $modelId );
 268                         }
 269
 270                         if ( !( $handler instanceof ContentHandler ) ) {
 271                                 throw new MWException( "ContentHandlerForModelID must supply a ContentHandler instance" );
 272                         }
 273                 } else {
 274                         $classOrCallback = $wgContentHandlers[$modelId];
 275
 276                         if ( is_callable( $classOrCallback ) ) {
 277                                 $handler = call_user_func( $classOrCallback, $modelId );
 278                         } else {
 279                                 $handler = new $classOrCallback( $modelId );
 280                         }
 281
 282                         if ( !( $handler instanceof ContentHandler ) ) {
 283                                 throw new MWException( "$classOrCallback from \$wgContentHandlers is not " .
 284                                         "compatible with ContentHandler" );
 285                         }
 286                 }
 287
 288                 wfDebugLog( 'ContentHandler', 'Created handler for ' . $modelId
 289                         . ': ' . get_class( $handler ) );
 290
 291                 self::$handlers[$modelId] = $handler;
 292
 293                 return self::$handlers[$modelId];
 294         }
 295
 296         /**
 297          * Clean up handlers cache.
 298          */
 299         public static function cleanupHandlersCache() {
 300                 self::$handlers = [];
 301         }
 302
 303         /**
 304          * Returns the localized name for a given content model.
 305          *
 306          * Model names are localized using system messages. Message keys
 307          * have the form content-model-$name, where $name is getContentModelName( $id ).
 308          *
 309          * @param string $name The content model ID, as given by a CONTENT_MODEL_XXX
 310          *    constant or returned by Revision::getContentModel().
 311          * @param Language|null $lang The language to parse the message in (since 1.26)
 312          *
 313          * @throws MWException If the model ID isn't known.
 314          * @return string The content model's localized name.
 315          */
 316         public static function getLocalizedName( $name, Language $lang = null ) {
 317                 // Messages: content-model-wikitext, content-model-text,
 318                 // content-model-javascript, content-model-css
 319                 $key = "content-model-$name";
 320
 321                 $msg = wfMessage( $key );
 322                 if ( $lang ) {
 323                         $msg->inLanguage( $lang );
 324                 }
 325
 326                 return $msg->exists() ? $msg->plain() : $name;
 327         }
 328
 329         public static function getContentModels() {
 330                 global $wgContentHandlers;
 331
 332                 $models = array_keys( $wgContentHandlers );
 333                 Hooks::run( 'GetContentModels', [ &$models ] );
 334                 return $models;
 335         }
 336
 337         public static function getAllContentFormats() {
 338                 global $wgContentHandlers;
 339
 340                 $formats = [];
 341
 342                 foreach ( $wgContentHandlers as $model => $class ) {
 343                         $handler = self::getForModelID( $model );
 344                         $formats = array_merge( $formats, $handler->getSupportedFormats() );
 345                 }
 346
 347                 $formats = array_unique( $formats );
 348
 349                 return $formats;
 350         }
 351
 352         // ------------------------------------------------------------------------
 353
 354         /**
 355          * @var string
 356          */
 357         protected $mModelID;
 358
 359         /**
 360          * @var string[]
 361          */
 362         protected $mSupportedFormats;
 363
 364         /**
 365          * Constructor, initializing the ContentHandler instance with its model ID
 366          * and a list of supported formats. Values for the parameters are typically
 367          * provided as literals by subclass's constructors.
 368          *
 369          * @param string $modelId (use CONTENT_MODEL_XXX constants).
 370          * @param string[] $formats List for supported serialization formats
 371          *    (typically as MIME types)
 372          */
 373         public function __construct( $modelId, $formats ) {
 374                 $this->mModelID = $modelId;
 375                 $this->mSupportedFormats = $formats;
 376         }
 377
 378         /**
 379          * Serializes a Content object of the type supported by this ContentHandler.
 380          *
 381          * @since 1.21
 382          *
 383          * @param Content $content The Content object to serialize
 384          * @param string|null $format The desired serialization format
 385          *
 386          * @return string Serialized form of the content
 387          */
 388         abstract public function serializeContent( Content $content, $format = null );
 389
 390         /**
 391          * Applies transformations on export (returns the blob unchanged per default).
 392          * Subclasses may override this to perform transformations such as conversion
 393          * of legacy formats or filtering of internal meta-data.
 394          *
 395          * @param string $blob The blob to be exported
 396          * @param string|null $format The blob's serialization format
 397          *
 398          * @return string
 399          */
 400         public function exportTransform( $blob, $format = null ) {
 401                 return $blob;
 402         }
 403
 404         /**
 405          * Unserializes a Content object of the type supported by this ContentHandler.
 406          *
 407          * @since 1.21
 408          *
 409          * @param string $blob Serialized form of the content
 410          * @param string|null $format The format used for serialization
 411          *
 412          * @return Content The Content object created by deserializing $blob
 413          */
 414         abstract public function unserializeContent( $blob, $format = null );
 415
 416         /**
 417          * Apply import transformation (per default, returns $blob unchanged).
 418          * This gives subclasses an opportunity to transform data blobs on import.
 419          *
 420          * @since 1.24
 421          *
 422          * @param string $blob
 423          * @param string|null $format
 424          *
 425          * @return string
 426          */
 427         public function importTransform( $blob, $format = null ) {
 428                 return $blob;
 429         }
 430
 431         /**
 432          * Creates an empty Content object of the type supported by this
 433          * ContentHandler.
 434          *
 435          * @since 1.21
 436          *
 437          * @return Content
 438          */
 439         abstract public function makeEmptyContent();
 440
 441         /**
 442          * Creates a new Content object that acts as a redirect to the given page,
 443          * or null if redirects are not supported by this content model.
 444          *
 445          * This default implementation always returns null. Subclasses supporting redirects
 446          * must override this method.
 447          *
 448          * Note that subclasses that override this method to return a Content object
 449          * should also override supportsRedirects() to return true.
 450          *
 451          * @since 1.21
 452          *
 453          * @param Title $destination The page to redirect to.
 454          * @param string $text Text to include in the redirect, if possible.
 455          *
 456          * @return Content Always null.
 457          */
 458         public function makeRedirectContent( Title $destination, $text = '' ) {
 459                 return null;
 460         }
 461
 462         /**
 463          * Returns the model id that identifies the content model this
 464          * ContentHandler can handle. Use with the CONTENT_MODEL_XXX constants.
 465          *
 466          * @since 1.21
 467          *
 468          * @return string The model ID
 469          */
 470         public function getModelID() {
 471                 return $this->mModelID;
 472         }
 473
 474         /**
 475          * @since 1.21
 476          *
 477          * @param string $model_id The model to check
 478          *
 479          * @throws MWException If the model ID is not the ID of the content model supported by this
 480          * ContentHandler.
 481          */
 482         protected function checkModelID( $model_id ) {
 483                 if ( $model_id !== $this->mModelID ) {
 484                         throw new MWException( "Bad content model: " .
 485                                 "expected {$this->mModelID} " .
 486                                 "but got $model_id." );
 487                 }
 488         }
 489
 490         /**
 491          * Returns a list of serialization formats supported by the
 492          * serializeContent() and unserializeContent() methods of this
 493          * ContentHandler.
 494          *
 495          * @since 1.21
 496          *
 497          * @return string[] List of serialization formats as MIME type like strings
 498          */
 499         public function getSupportedFormats() {
 500                 return $this->mSupportedFormats;
 501         }
 502
 503         /**
 504          * The format used for serialization/deserialization by default by this
 505          * ContentHandler.
 506          *
 507          * This default implementation will return the first element of the array
 508          * of formats that was passed to the constructor.
 509          *
 510          * @since 1.21
 511          *
 512          * @return string The name of the default serialization format as a MIME type
 513          */
 514         public function getDefaultFormat() {
 515                 return $this->mSupportedFormats[0];
 516         }
 517
 518         /**
 519          * Returns true if $format is a serialization format supported by this
 520          * ContentHandler, and false otherwise.
 521          *
 522          * Note that if $format is null, this method always returns true, because
 523          * null means "use the default format".
 524          *
 525          * @since 1.21
 526          *
 527          * @param string $format The serialization format to check
 528          *
 529          * @return bool
 530          */
 531         public function isSupportedFormat( $format ) {
 532                 if ( !$format ) {
 533                         return true; // this means "use the default"
 534                 }
 535
 536                 return in_array( $format, $this->mSupportedFormats );
 537         }
 538
 539         /**
 540          * Convenient for checking whether a format provided as a parameter is actually supported.
 541          *
 542          * @param string $format The serialization format to check
 543          *
 544          * @throws MWException If the format is not supported by this content handler.
 545          */
 546         protected function checkFormat( $format ) {
 547                 if ( !$this->isSupportedFormat( $format ) ) {
 548                         throw new MWException(
 549                                 "Format $format is not supported for content model "
 550                                 . $this->getModelID()
 551                         );
 552                 }
 553         }
 554
 555         /**
 556          * Returns overrides for action handlers.
 557          * Classes listed here will be used instead of the default one when
 558          * (and only when) $wgActions[$action] === true. This allows subclasses
 559          * to override the default action handlers.
 560          *
 561          * @since 1.21
 562          *
 563          * @return array An array mapping action names (typically "view", "edit", "history" etc.) to
 564          *  either the full qualified class name of an Action class, a callable taking ( Page $page,
 565          *  IContextSource $context = null ) as parameters and returning an Action object, or an actual
 566          *  Action object. An empty array in this default implementation.
 567          *
 568          * @see Action::factory
 569          */
 570         public function getActionOverrides() {
 571                 return [];
 572         }
 573
 574         /**
 575          * Factory for creating an appropriate DifferenceEngine for this content model.
 576          * Since 1.32, this is only used for page-level diffs; to diff two content objects,
 577          * use getSlotDiffRenderer.
 578          *
 579          * The DifferenceEngine subclass to use is selected in getDiffEngineClass(). The
 580          * GetDifferenceEngine hook will receive the DifferenceEngine object and can replace or
 581          * wrap it.
 582          * (Note that in older versions of MediaWiki the hook documentation instructed extensions
 583          * to return false from the hook; you should not rely on always being able to decorate
 584          * the DifferenceEngine instance from the hook. If the owner of the content type wants to
 585          * decorare the instance, overriding this method is a safer approach.)
 586          *
 587          * @todo This is page-level functionality so it should not belong to ContentHandler.
 588          *   Move it to a better place once one exists (e.g. PageTypeHandler).
 589          *
 590          * @since 1.21
 591          *
 592          * @param IContextSource $context Context to use, anything else will be ignored.
 593          * @param int $old Revision ID we want to show and diff with.
 594          * @param int|string $new Either a revision ID or one of the strings 'cur', 'prev' or 'next'.
 595          * @param int $rcid FIXME: Deprecated, no longer used. Defaults to 0.
 596          * @param bool $refreshCache If set, refreshes the diff cache. Defaults to false.
 597          * @param bool $unhide If set, allow viewing deleted revs. Defaults to false.
 598          *
 599          * @return DifferenceEngine
 600          */
 601         public function createDifferenceEngine( IContextSource $context, $old = 0, $new = 0,
 602                 $rcid = 0, // FIXME: Deprecated, no longer used
 603                 $refreshCache = false, $unhide = false
 604         ) {
 605                 $diffEngineClass = $this->getDiffEngineClass();
 606                 $differenceEngine = new $diffEngineClass( $context, $old, $new, $rcid, $refreshCache, $unhide );
 607                 Hooks::run( 'GetDifferenceEngine', [ $context, $old, $new, $refreshCache, $unhide,
 608                         &$differenceEngine ] );
 609                 return $differenceEngine;
 610         }
 611
 612         /**
 613          * Get an appropriate SlotDiffRenderer for this content model.
 614          * @since 1.32
 615          * @param IContextSource $context
 616          * @return SlotDiffRenderer
 617          */
 618         final public function getSlotDiffRenderer( IContextSource $context ) {
 619                 $slotDiffRenderer = $this->getSlotDiffRendererInternal( $context );
 620                 if ( get_class( $slotDiffRenderer ) === TextSlotDiffRenderer::class ) {
 621                         //  To keep B/C, when SlotDiffRenderer is not overridden for a given content type
 622                         // but DifferenceEngine is, use that instead.
 623                         $differenceEngine = $this->createDifferenceEngine( $context );
 624                         if ( get_class( $differenceEngine ) !== DifferenceEngine::class ) {
 625                                 // TODO turn this into a deprecation warning in a later release
 626                                 LoggerFactory::getInstance( 'diff' )->info(
 627                                         'Falling back to DifferenceEngineSlotDiffRenderer', [
 628                                                 'modelID' => $this->getModelID(),
 629                                                 'DifferenceEngine' => get_class( $differenceEngine ),
 630                                         ] );
 631                                 $slotDiffRenderer = new DifferenceEngineSlotDiffRenderer( $differenceEngine );
 632                         }
 633                 }
 634                 Hooks::run( 'GetSlotDiffRenderer', [ $this, &$slotDiffRenderer, $context ] );
 635                 return $slotDiffRenderer;
 636         }
 637
 638         /**
 639          * Return the SlotDiffRenderer appropriate for this content handler.
 640          * @param IContextSource $context
 641          * @return SlotDiffRenderer
 642          */
 643         protected function getSlotDiffRendererInternal( IContextSource $context ) {
 644                 $contentLanguage = MediaWikiServices::getInstance()->getContentLanguage();
 645                 $statsdDataFactory = MediaWikiServices::getInstance()->getStatsdDataFactory();
 646                 $slotDiffRenderer = new TextSlotDiffRenderer();
 647                 $slotDiffRenderer->setStatsdDataFactory( $statsdDataFactory );
 648                 // XXX using the page language would be better, but it's unclear how that should be injected
 649                 $slotDiffRenderer->setLanguage( $contentLanguage );
 650
 651                 $engine = DifferenceEngine::getEngine();
 652                 if ( $engine === false ) {
 653                         $slotDiffRenderer->setEngine( TextSlotDiffRenderer::ENGINE_PHP );
 654                 } elseif ( $engine === 'wikidiff2' ) {
 655                         $slotDiffRenderer->setEngine( TextSlotDiffRenderer::ENGINE_WIKIDIFF2 );
 656                 } else {
 657                         $slotDiffRenderer->setEngine( TextSlotDiffRenderer::ENGINE_EXTERNAL, $engine );
 658                 }
 659
 660                 return $slotDiffRenderer;
 661         }
 662
 663         /**
 664          * Get the language in which the content of the given page is written.
 665          *
 666          * This default implementation just returns the content language (except for pages
 667          * in the MediaWiki namespace)
 668          *
 669          * Note that the page's language is not cacheable, since it may in some
 670          * cases depend on user settings.
 671          *
 672          * Also note that the page language may or may not depend on the actual content of the page,
 673          * that is, this method may load the content in order to determine the language.
 674          *
 675          * @since 1.21
 676          *
 677          * @param Title $title The page to determine the language for.
 678          * @param Content|null $content The page's content, if you have it handy, to avoid reloading it.
 679          *
 680          * @return Language The page's language
 681          */
 682         public function getPageLanguage( Title $title, Content $content = null ) {
 683                 global $wgLang;
 684                 $pageLang = MediaWikiServices::getInstance()->getContentLanguage();
 685
 686                 if ( $title->inNamespace( NS_MEDIAWIKI ) ) {
 687                         // Parse mediawiki messages with correct target language
 688                         list( /* $unused */, $lang ) = MessageCache::singleton()->figureMessage( $title->getText() );
 689                         $pageLang = Language::factory( $lang );
 690                 }
 691
 692                 // Simplify hook handlers by only passing objects of one type, in case nothing
 693                 // else has unstubbed the StubUserLang object by now.
 694                 StubObject::unstub( $wgLang );
 695
 696                 Hooks::run( 'PageContentLanguage', [ $title, &$pageLang, $wgLang ] );
 697
 698                 return wfGetLangObj( $pageLang );
 699         }
 700
 701         /**
 702          * Get the language in which the content of this page is written when
 703          * viewed by user. Defaults to $this->getPageLanguage(), but if the user
 704          * specified a preferred variant, the variant will be used.
 705          *
 706          * This default implementation just returns $this->getPageLanguage( $title, $content ) unless
 707          * the user specified a preferred variant.
 708          *
 709          * Note that the pages view language is not cacheable, since it depends on user settings.
 710          *
 711          * Also note that the page language may or may not depend on the actual content of the page,
 712          * that is, this method may load the content in order to determine the language.
 713          *
 714          * @since 1.21
 715          *
 716          * @param Title $title The page to determine the language for.
 717          * @param Content|null $content The page's content, if you have it handy, to avoid reloading it.
 718          *
 719          * @return Language The page's language for viewing
 720          */
 721         public function getPageViewLanguage( Title $title, Content $content = null ) {
 722                 $pageLang = $this->getPageLanguage( $title, $content );
 723
 724                 if ( $title->getNamespace() !== NS_MEDIAWIKI ) {
 725                         // If the user chooses a variant, the content is actually
 726                         // in a language whose code is the variant code.
 727                         $variant = $pageLang->getPreferredVariant();
 728                         if ( $pageLang->getCode() !== $variant ) {
 729                                 $pageLang = Language::factory( $variant );
 730                         }
 731                 }
 732
 733                 return $pageLang;
 734         }
 735
 736         /**
 737          * Determines whether the content type handled by this ContentHandler
 738          * can be used for the main slot of the given page.
 739          *
 740          * This default implementation always returns true.
 741          * Subclasses may override this to restrict the use of this content model to specific locations,
 742          * typically based on the namespace or some other aspect of the title, such as a special suffix
 743          * (e.g. ".svg" for SVG content).
 744          *
 745          * @note this calls the ContentHandlerCanBeUsedOn hook which may be used to override which
 746          * content model can be used where.
 747          *
 748          * @see SlotRoleHandler::isAllowedModel
 749          *
 750          * @param Title $title The page's title.
 751          *
 752          * @return bool True if content of this kind can be used on the given page, false otherwise.
 753          */
 754         public function canBeUsedOn( Title $title ) {
 755                 $ok = true;
 756
 757                 Hooks::run( 'ContentModelCanBeUsedOn', [ $this->getModelID(), $title, &$ok ] );
 758
 759                 return $ok;
 760         }
 761
 762         /**
 763          * Returns the name of the diff engine to use.
 764          *
 765          * @since 1.21
 766          *
 767          * @return string
 768          */
 769         protected function getDiffEngineClass() {
 770                 return DifferenceEngine::class;
 771         }
 772
 773         /**
 774          * Attempts to merge differences between three versions. Returns a new
 775          * Content object for a clean merge and false for failure or a conflict.
 776          *
 777          * This default implementation always returns false.
 778          *
 779          * @since 1.21
 780          *
 781          * @param Content $oldContent The page's previous content.
 782          * @param Content $myContent One of the page's conflicting contents.
 783          * @param Content $yourContent One of the page's conflicting contents.
 784          *
 785          * @return Content|bool Always false.
 786          */
 787         public function merge3( Content $oldContent, Content $myContent, Content $yourContent ) {
 788                 return false;
 789         }
 790
 791         /**
 792          * Return type of change if one exists for the given edit.
 793          *
 794          * @since 1.31
 795          *
 796          * @param Content|null $oldContent The previous text of the page.
 797          * @param Content|null $newContent The submitted text of the page.
 798          * @param int $flags Bit mask: a bit mask of flags submitted for the edit.
 799          *
 800          * @return string|null String key representing type of change, or null.
 801          */
 802         private function getChangeType(
 803                 Content $oldContent = null,
 804                 Content $newContent = null,
 805                 $flags = 0
 806         ) {
 807                 $oldTarget = $oldContent !== null ? $oldContent->getRedirectTarget() : null;
 808                 $newTarget = $newContent !== null ? $newContent->getRedirectTarget() : null;
 809
 810                 // We check for the type of change in the given edit, and return string key accordingly
 811
 812                 // Blanking of a page
 813                 if ( $oldContent && $oldContent->getSize() > 0 &&
 814                         $newContent && $newContent->getSize() === 0
 815                 ) {
 816                         return 'blank';
 817                 }
 818
 819                 // Redirects
 820                 if ( $newTarget ) {
 821                         if ( !$oldTarget ) {
 822                                 // New redirect page (by creating new page or by changing content page)
 823                                 return 'new-redirect';
 824                         } elseif ( !$newTarget->equals( $oldTarget ) ||
 825                                 $oldTarget->getFragment() !== $newTarget->getFragment()
 826                         ) {
 827                                 // Redirect target changed
 828                                 return 'changed-redirect-target';
 829                         }
 830                 } elseif ( $oldTarget ) {
 831                         // Changing an existing redirect into a non-redirect
 832                         return 'removed-redirect';
 833                 }
 834
 835                 // New page created
 836                 if ( $flags & EDIT_NEW && $newContent ) {
 837                         if ( $newContent->getSize() === 0 ) {
 838                                 // New blank page
 839                                 return 'newblank';
 840                         } else {
 841                                 return 'newpage';
 842                         }
 843                 }
 844
 845                 // Removing more than 90% of the page
 846                 if ( $oldContent && $newContent && $oldContent->getSize() > 10 * $newContent->getSize() ) {
 847                         return 'replace';
 848                 }
 849
 850                 // Content model changed
 851                 if ( $oldContent && $newContent && $oldContent->getModel() !== $newContent->getModel() ) {
 852                         return 'contentmodelchange';
 853                 }
 854
 855                 return null;
 856         }
 857
 858         /**
 859          * Return an applicable auto-summary if one exists for the given edit.
 860          *
 861          * @since 1.21
 862          *
 863          * @param Content|null $oldContent The previous text of the page.
 864          * @param Content|null $newContent The submitted text of the page.
 865          * @param int $flags Bit mask: a bit mask of flags submitted for the edit.
 866          *
 867          * @return string An appropriate auto-summary, or an empty string.
 868          */
 869         public function getAutosummary(
 870                 Content $oldContent = null,
 871                 Content $newContent = null,
 872                 $flags = 0
 873         ) {
 874                 $changeType = $this->getChangeType( $oldContent, $newContent, $flags );
 875
 876                 // There's no applicable auto-summary for our case, so our auto-summary is empty.
 877                 if ( !$changeType ) {
 878                         return '';
 879                 }
 880
 881                 // Decide what kind of auto-summary is needed.
 882                 switch ( $changeType ) {
 883                         case 'new-redirect':
 884                                 $newTarget = $newContent->getRedirectTarget();
 885                                 $truncatedtext = $newContent->getTextForSummary(
 886                                         250
 887                                         - strlen( wfMessage( 'autoredircomment' )->inContentLanguage()->text() )
 888                                         - strlen( $newTarget->getFullText() )
 889                                 );
 890
 891                                 return wfMessage( 'autoredircomment', $newTarget->getFullText() )
 892                                         ->plaintextParams( $truncatedtext )->inContentLanguage()->text();
 893                         case 'changed-redirect-target':
 894                                 $oldTarget = $oldContent->getRedirectTarget();
 895                                 $newTarget = $newContent->getRedirectTarget();
 896
 897                                 $truncatedtext = $newContent->getTextForSummary(
 898                                         250
 899                                         - strlen( wfMessage( 'autosumm-changed-redirect-target' )
 900                                                 ->inContentLanguage()->text() )
 901                                         - strlen( $oldTarget->getFullText() )
 902                                         - strlen( $newTarget->getFullText() )
 903                                 );
 904
 905                                 return wfMessage( 'autosumm-changed-redirect-target',
 906                                                 $oldTarget->getFullText(),
 907                                                 $newTarget->getFullText() )
 908                                         ->rawParams( $truncatedtext )->inContentLanguage()->text();
 909                         case 'removed-redirect':
 910                                 $oldTarget = $oldContent->getRedirectTarget();
 911                                 $truncatedtext = $newContent->getTextForSummary(
 912                                         250
 913                                         - strlen( wfMessage( 'autosumm-removed-redirect' )
 914                                                 ->inContentLanguage()->text() )
 915                                         - strlen( $oldTarget->getFullText() ) );
 916
 917                                 return wfMessage( 'autosumm-removed-redirect', $oldTarget->getFullText() )
 918                                         ->rawParams( $truncatedtext )->inContentLanguage()->text();
 919                         case 'newpage':
 920                                 // If they're making a new article, give its text, truncated, in the summary.
 921                                 $truncatedtext = $newContent->getTextForSummary(
 922                                         200 - strlen( wfMessage( 'autosumm-new' )->inContentLanguage()->text() ) );
 923
 924                                 return wfMessage( 'autosumm-new' )->rawParams( $truncatedtext )
 925                                         ->inContentLanguage()->text();
 926                         case 'blank':
 927                                 return wfMessage( 'autosumm-blank' )->inContentLanguage()->text();
 928                         case 'replace':
 929                                 $truncatedtext = $newContent->getTextForSummary(
 930                                         200 - strlen( wfMessage( 'autosumm-replace' )->inContentLanguage()->text() ) );
 931
 932                                 return wfMessage( 'autosumm-replace' )->rawParams( $truncatedtext )
 933                                         ->inContentLanguage()->text();
 934                         case 'newblank':
 935                                 return wfMessage( 'autosumm-newblank' )->inContentLanguage()->text();
 936                         default:
 937                                 return '';
 938                 }
 939         }
 940
 941         /**
 942          * Return an applicable tag if one exists for the given edit or return null.
 943          *
 944          * @since 1.31
 945          *
 946          * @param Content|null $oldContent The previous text of the page.
 947          * @param Content|null $newContent The submitted text of the page.
 948          * @param int $flags Bit mask: a bit mask of flags submitted for the edit.
 949          *
 950          * @return string|null An appropriate tag, or null.
 951          */
 952         public function getChangeTag(
 953                 Content $oldContent = null,
 954                 Content $newContent = null,
 955                 $flags = 0
 956         ) {
 957                 $changeType = $this->getChangeType( $oldContent, $newContent, $flags );
 958
 959                 // There's no applicable tag for this change.
 960                 if ( !$changeType ) {
 961                         return null;
 962                 }
 963
 964                 // Core tags use the same keys as ones returned from $this->getChangeType()
 965                 // but prefixed with pseudo namespace 'mw-', so we add the prefix before checking
 966                 // if this type of change should be tagged
 967                 $tag = 'mw-' . $changeType;
 968
 969                 // Not all change types are tagged, so we check against the list of defined tags.
 970                 if ( in_array( $tag, ChangeTags::getSoftwareTags() ) ) {
 971                         return $tag;
 972                 }
 973
 974                 return null;
 975         }
 976
 977         /**
 978          * Auto-generates a deletion reason
 979          *
 980          * @since 1.21
 981          *
 982          * @param Title $title The page's title
 983          * @param bool &$hasHistory Whether the page has a history
 984          *
 985          * @return mixed String containing deletion reason or empty string, or
 986          *    boolean false if no revision occurred
 987          *
 988          * @todo &$hasHistory is extremely ugly, it's here because
 989          * WikiPage::getAutoDeleteReason() and Article::generateReason()
 990          * have it / want it.
 991          */
 992         public function getAutoDeleteReason( Title $title, &$hasHistory ) {
 993                 $dbr = wfGetDB( DB_REPLICA );
 994
 995                 // Get the last revision
 996                 $rev = Revision::newFromTitle( $title );
 997
 998                 if ( is_null( $rev ) ) {
 999                         return false;
1000                 }
1001
1002                 // Get the article's contents
1003                 $content = $rev->getContent();
1004                 $blank = false;
1005
1006                 // If the page is blank, use the text from the previous revision,
1007                 // which can only be blank if there's a move/import/protect dummy
1008                 // revision involved
1009                 if ( !$content || $content->isEmpty() ) {
1010                         $prev = $rev->getPrevious();
1011
1012                         if ( $prev ) {
1013                                 $rev = $prev;
1014                                 $content = $rev->getContent();
1015                                 $blank = true;
1016                         }
1017                 }
1018
1019                 $this->checkModelID( $rev->getContentModel() );
1020
1021                 // Find out if there was only one contributor
1022                 // Only scan the last 20 revisions
1023                 $revQuery = Revision::getQueryInfo();
1024                 $res = $dbr->select(
1025                         $revQuery['tables'],
1026                         [ 'rev_user_text' => $revQuery['fields']['rev_user_text'] ],
1027                         [
1028                                 'rev_page' => $title->getArticleID(),
1029                                 $dbr->bitAnd( 'rev_deleted', RevisionRecord::DELETED_USER ) . ' = 0'
1030                         ],
1031                         __METHOD__,
1032                         [ 'LIMIT' => 20 ],
1033                         $revQuery['joins']
1034                 );
1035
1036                 if ( $res === false ) {
1037                         // This page has no revisions, which is very weird
1038                         return false;
1039                 }
1040
1041                 $hasHistory = ( $res->numRows() > 1 );
1042                 $row = $dbr->fetchObject( $res );
1043
1044                 if ( $row ) { // $row is false if the only contributor is hidden
1045                         $onlyAuthor = $row->rev_user_text;
1046                         // Try to find a second contributor
1047                         foreach ( $res as $row ) {
1048                                 if ( $row->rev_user_text != $onlyAuthor ) { // T24999
1049                                         $onlyAuthor = false;
1050                                         break;
1051                                 }
1052                         }
1053                 } else {
1054                         $onlyAuthor = false;
1055                 }
1056
1057                 // Generate the summary with a '$1' placeholder
1058                 if ( $blank ) {
1059                         // The current revision is blank and the one before is also
1060                         // blank. It's just not our lucky day
1061                         $reason = wfMessage( 'exbeforeblank', '$1' )->inContentLanguage()->text();
1062                 } else {
1063                         if ( $onlyAuthor ) {
1064                                 $reason = wfMessage(
1065                                         'excontentauthor',
1066                                         '$1',
1067                                         $onlyAuthor
1068                                 )->inContentLanguage()->text();
1069                         } else {
1070                                 $reason = wfMessage( 'excontent', '$1' )->inContentLanguage()->text();
1071                         }
1072                 }
1073
1074                 if ( $reason == '-' ) {
1075                         // Allow these UI messages to be blanked out cleanly
1076                         return '';
1077                 }
1078
1079                 // Max content length = max comment length - length of the comment (excl. $1)
1080                 $text = $content ? $content->getTextForSummary( 255 - ( strlen( $reason ) - 2 ) ) : '';
1081
1082                 // Now replace the '$1' placeholder
1083                 $reason = str_replace( '$1', $text, $reason );
1084
1085                 return $reason;
1086         }
1087
1088         /**
1089          * Get the Content object that needs to be saved in order to undo all revisions
1090          * between $undo and $undoafter. Revisions must belong to the same page,
1091          * must exist and must not be deleted.
1092          *
1093          * @since 1.21
1094          * @since 1.32 accepts Content objects for all parameters instead of Revision objects.
1095          *  Passing Revision objects is deprecated.
1096          *
1097          * @param Revision|Content $current The current text
1098          * @param Revision|Content $undo The content of the revision to undo
1099          * @param Revision|Content $undoafter Must be from an earlier revision than $undo
1100          * @param bool $undoIsLatest Set true if $undo is from the current revision (since 1.32)
1101          *
1102          * @return mixed Content on success, false on failure
1103          */
1104         public function getUndoContent( $current, $undo, $undoafter, $undoIsLatest = false ) {
1105                 Assert::parameterType( Revision::class . '|' . Content::class, $current, '$current' );
1106                 if ( $current instanceof Content ) {
1107                         Assert::parameter( $undo instanceof Content, '$undo',
1108                                 'Must be Content when $current is Content' );
1109                         Assert::parameter( $undoafter instanceof Content, '$undoafter',
1110                                 'Must be Content when $current is Content' );
1111                         $cur_content = $current;
1112                         $undo_content = $undo;
1113                         $undoafter_content = $undoafter;
1114                 } else {
1115                         Assert::parameter( $undo instanceof Revision, '$undo',
1116                                 'Must be Revision when $current is Revision' );
1117                         Assert::parameter( $undoafter instanceof Revision, '$undoafter',
1118                                 'Must be Revision when $current is Revision' );
1119
1120                         $cur_content = $current->getContent();
1121
1122                         if ( empty( $cur_content ) ) {
1123                                 return false; // no page
1124                         }
1125
1126                         $undo_content = $undo->getContent();
1127                         $undoafter_content = $undoafter->getContent();
1128
1129                         if ( !$undo_content || !$undoafter_content ) {
1130                                 return false; // no content to undo
1131                         }
1132
1133                         $undoIsLatest = $current->getId() === $undo->getId();
1134                 }
1135
1136                 try {
1137                         $this->checkModelID( $cur_content->getModel() );
1138                         $this->checkModelID( $undo_content->getModel() );
1139                         if ( !$undoIsLatest ) {
1140                                 // If we are undoing the most recent revision,
1141                                 // its ok to revert content model changes. However
1142                                 // if we are undoing a revision in the middle, then
1143                                 // doing that will be confusing.
1144                                 $this->checkModelID( $undoafter_content->getModel() );
1145                         }
1146                 } catch ( MWException $e ) {
1147                         // If the revisions have different content models
1148                         // just return false
1149                         return false;
1150                 }
1151
1152                 if ( $cur_content->equals( $undo_content ) ) {
1153                         // No use doing a merge if it's just a straight revert.
1154                         return $undoafter_content;
1155                 }
1156
1157                 $undone_content = $this->merge3( $undo_content, $undoafter_content, $cur_content );
1158
1159                 return $undone_content;
1160         }
1161
1162         /**
1163          * Get parser options suitable for rendering and caching the article
1164          *
1165          * @deprecated since 1.32, use WikiPage::makeParserOptions() or
1166          *  ParserOptions::newCanonical() instead.
1167          * @param IContextSource|User|string $context One of the following:
1168          *        - IContextSource: Use the User and the Language of the provided
1169          *                                            context
1170          *        - User: Use the provided User object and $wgLang for the language,
1171          *                                            so use an IContextSource object if possible.
1172          *        - 'canonical': Canonical options (anonymous user with default
1173          *                                            preferences and content language).
1174          *
1175          * @throws MWException
1176          * @return ParserOptions
1177          */
1178         public function makeParserOptions( $context ) {
1179                 wfDeprecated( __METHOD__, '1.32' );
1180                 return ParserOptions::newCanonical( $context );
1181         }
1182
1183         /**
1184          * Returns true for content models that support caching using the
1185          * ParserCache mechanism. See WikiPage::shouldCheckParserCache().
1186          *
1187          * @since 1.21
1188          *
1189          * @return bool Always false.
1190          */
1191         public function isParserCacheSupported() {
1192                 return false;
1193         }
1194
1195         /**
1196          * Returns true if this content model supports sections.
1197          * This default implementation returns false.
1198          *
1199          * Content models that return true here should also implement
1200          * Content::getSection, Content::replaceSection, etc. to handle sections..
1201          *
1202          * @return bool Always false.
1203          */
1204         public function supportsSections() {
1205                 return false;
1206         }
1207
1208         /**
1209          * Returns true if this content model supports categories.
1210          * The default implementation returns true.
1211          *
1212          * @return bool Always true.
1213          */
1214         public function supportsCategories() {
1215                 return true;
1216         }
1217
1218         /**
1219          * Returns true if this content model supports redirects.
1220          * This default implementation returns false.
1221          *
1222          * Content models that return true here should also implement
1223          * ContentHandler::makeRedirectContent to return a Content object.
1224          *
1225          * @return bool Always false.
1226          */
1227         public function supportsRedirects() {
1228                 return false;
1229         }
1230
1231         /**
1232          * Return true if this content model supports direct editing, such as via EditPage.
1233          *
1234          * @return bool Default is false, and true for TextContent and it's derivatives.
1235          */
1236         public function supportsDirectEditing() {
1237                 return false;
1238         }
1239
1240         /**
1241          * Whether or not this content model supports direct editing via ApiEditPage
1242          *
1243          * @return bool Default is false, and true for TextContent and derivatives.
1244          */
1245         public function supportsDirectApiEditing() {
1246                 return $this->supportsDirectEditing();
1247         }
1248
1249         /**
1250          * Get fields definition for search index
1251          *
1252          * @todo Expose title, redirect, namespace, text, source_text, text_bytes
1253          *       field mappings here. (see T142670 and T143409)
1254          *
1255          * @param SearchEngine $engine
1256          * @return SearchIndexField[] List of fields this content handler can provide.
1257          * @since 1.28
1258          */
1259         public function getFieldsForSearchIndex( SearchEngine $engine ) {
1260                 $fields['category'] = $engine->makeSearchFieldMapping(
1261                         'category',
1262                         SearchIndexField::INDEX_TYPE_TEXT
1263                 );
1264                 $fields['category']->setFlag( SearchIndexField::FLAG_CASEFOLD );
1265
1266                 $fields['external_link'] = $engine->makeSearchFieldMapping(
1267                         'external_link',
1268                         SearchIndexField::INDEX_TYPE_KEYWORD
1269                 );
1270
1271                 $fields['outgoing_link'] = $engine->makeSearchFieldMapping(
1272                         'outgoing_link',
1273                         SearchIndexField::INDEX_TYPE_KEYWORD
1274                 );
1275
1276                 $fields['template'] = $engine->makeSearchFieldMapping(
1277                         'template',
1278                         SearchIndexField::INDEX_TYPE_KEYWORD
1279                 );
1280                 $fields['template']->setFlag( SearchIndexField::FLAG_CASEFOLD );
1281
1282                 $fields['content_model'] = $engine->makeSearchFieldMapping(
1283                         'content_model',
1284                         SearchIndexField::INDEX_TYPE_KEYWORD
1285                 );
1286
1287                 return $fields;
1288         }
1289
1290         /**
1291          * Add new field definition to array.
1292          * @param SearchIndexField[] &$fields
1293          * @param SearchEngine $engine
1294          * @param string $name
1295          * @param int $type
1296          * @return SearchIndexField[] new field defs
1297          * @since 1.28
1298          */
1299         protected function addSearchField( &$fields, SearchEngine $engine, $name, $type ) {
1300                 $fields[$name] = $engine->makeSearchFieldMapping( $name, $type );
1301                 return $fields;
1302         }
1303
1304         /**
1305          * Return fields to be indexed by search engine
1306          * as representation of this document.
1307          * Overriding class should call parent function or take care of calling
1308          * the SearchDataForIndex hook.
1309          * @param WikiPage $page Page to index
1310          * @param ParserOutput $output
1311          * @param SearchEngine $engine Search engine for which we are indexing
1312          * @return array Map of name=>value for fields
1313          * @since 1.28
1314          */
1315         public function getDataForSearchIndex(
1316                 WikiPage $page,
1317                 ParserOutput $output,
1318                 SearchEngine $engine
1319         ) {
1320                 $fieldData = [];
1321                 $content = $page->getContent();
1322
1323                 if ( $content ) {
1324                         $searchDataExtractor = new ParserOutputSearchDataExtractor();
1325
1326                         $fieldData['category'] = $searchDataExtractor->getCategories( $output );
1327                         $fieldData['external_link'] = $searchDataExtractor->getExternalLinks( $output );
1328                         $fieldData['outgoing_link'] = $searchDataExtractor->getOutgoingLinks( $output );
1329                         $fieldData['template'] = $searchDataExtractor->getTemplates( $output );
1330
1331                         $text = $content->getTextForSearchIndex();
1332
1333                         $fieldData['text'] = $text;
1334                         $fieldData['source_text'] = $text;
1335                         $fieldData['text_bytes'] = $content->getSize();
1336                         $fieldData['content_model'] = $content->getModel();
1337                 }
1338
1339                 Hooks::run( 'SearchDataForIndex', [ &$fieldData, $this, $page, $output, $engine ] );
1340                 return $fieldData;
1341         }
1342
1343         /**
1344          * Produce page output suitable for indexing.
1345          *
1346          * Specific content handlers may override it if they need different content handling.
1347          *
1348          * @param WikiPage $page
1349          * @param ParserCache|null $cache
1350          * @return ParserOutput
1351          */
1352         public function getParserOutputForIndexing( WikiPage $page, ParserCache $cache = null ) {
1353                 // TODO: MCR: ContentHandler should be called per slot, not for the whole page.
1354                 // See T190066.
1355                 $parserOptions = $page->makeParserOptions( 'canonical' );
1356                 if ( $cache ) {
1357                         $parserOutput = $cache->get( $page, $parserOptions );
1358                 }
1359
1360                 if ( empty( $parserOutput ) ) {
1361                         $renderer = MediaWikiServices::getInstance()->getRevisionRenderer();
1362                         $parserOutput =
1363                                 $renderer->getRenderedRevision(
1364                                         $page->getRevision()->getRevisionRecord(),
1365                                         $parserOptions
1366                                 )->getRevisionParserOutput();
1367                         if ( $cache ) {
1368                                 $cache->save( $parserOutput, $page, $parserOptions );
1369                         }
1370                 }
1371                 return $parserOutput;
1372         }
1373
1374         /**
1375          * Returns a list of DeferrableUpdate objects for recording information about the
1376          * given Content in some secondary data store.
1377          *
1378          * Application logic should not call this method directly. Instead, it should call
1379          * DerivedPageDataUpdater::getSecondaryDataUpdates().
1380          *
1381          * @note Implementations must not return a LinksUpdate instance. Instead, a LinksUpdate
1382          * is created by the calling code in DerivedPageDataUpdater, on the combined ParserOutput
1383          * of all slots, not for each slot individually. This is in contrast to the old
1384          * getSecondaryDataUpdates method defined by AbstractContent, which returned a LinksUpdate.
1385          *
1386          * @note Implementations should not call $content->getParserOutput, they should call
1387          * $slotOutput->getSlotRendering( $role, false ) instead if they need to access a ParserOutput
1388          * of $content. This allows existing ParserOutput objects to be re-used, while avoiding
1389          * creating a ParserOutput when none is needed.
1390          *
1391          * @param Title $title The title of the page to supply the updates for
1392          * @param Content $content The content to generate data updates for.
1393          * @param string $role The role (slot) in which the content is being used. Which updates
1394          *        are performed should generally not depend on the role the content has, but the
1395          *        DeferrableUpdates themselves may need to know the role, to track to which slot the
1396          *        data refers, and to avoid overwriting data of the same kind from another slot.
1397          * @param SlotRenderingProvider $slotOutput A provider that can be used to gain access to
1398          *        a ParserOutput of $content by calling $slotOutput->getSlotParserOutput( $role, false ).
1399          * @return DeferrableUpdate[] A list of DeferrableUpdate objects for putting information
1400          *        about this content object somewhere. The default implementation returns an empty
1401          *        array.
1402          * @since 1.32
1403          */
1404         public function getSecondaryDataUpdates(
1405                 Title $title,
1406                 Content $content,
1407                 $role,
1408                 SlotRenderingProvider $slotOutput
1409         ) {
1410                 return [];
1411         }
1412
1413         /**
1414          * Returns a list of DeferrableUpdate objects for removing information about content
1415          * in some secondary data store. This is used when a page is deleted, and also when
1416          * a slot is removed from a page.
1417          *
1418          * Application logic should not call this method directly. Instead, it should call
1419          * WikiPage::getSecondaryDataUpdates().
1420          *
1421          * @note Implementations must not return a LinksDeletionUpdate instance. Instead, a
1422          * LinksDeletionUpdate is created by the calling code in WikiPage.
1423          * This is in contrast to the old getDeletionUpdates method defined by AbstractContent,
1424          * which returned a LinksUpdate.
1425          *
1426          * @note Implementations should not rely on the page's current content, but rather the current
1427          * state of the secondary data store.
1428          *
1429          * @param Title $title The title of the page to supply the updates for
1430          * @param string $role The role (slot) in which the content is being used. Which updates
1431          *        are performed should generally not depend on the role the content has, but the
1432          *        DeferrableUpdates themselves may need to know the role, to track to which slot the
1433          *        data refers, and to avoid overwriting data of the same kind from another slot.
1434          *
1435          * @return DeferrableUpdate[] A list of DeferrableUpdate objects for putting information
1436          *        about this content object somewhere. The default implementation returns an empty
1437          *        array.
1438          *
1439          * @since 1.32
1440          */
1441         public function getDeletionUpdates( Title $title, $role ) {
1442                 return [];
1443         }
1444
1445 }