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\Revision\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(
 284                                         var_export( $classOrCallback, true ) . " from \$wgContentHandlers is not " .
 285                                         "compatible with ContentHandler"
 286                                 );
 287                         }
 288                 }
 289
 290                 wfDebugLog( 'ContentHandler', 'Created handler for ' . $modelId
 291                         . ': ' . get_class( $handler ) );
 292
 293                 self::$handlers[$modelId] = $handler;
 294
 295                 return self::$handlers[$modelId];
 296         }
 297
 298         /**
 299          * Clean up handlers cache.
 300          */
 301         public static function cleanupHandlersCache() {
 302                 self::$handlers = [];
 303         }
 304
 305         /**
 306          * Returns the localized name for a given content model.
 307          *
 308          * Model names are localized using system messages. Message keys
 309          * have the form content-model-$name, where $name is getContentModelName( $id ).
 310          *
 311          * @param string $name The content model ID, as given by a CONTENT_MODEL_XXX
 312          *    constant or returned by Revision::getContentModel().
 313          * @param Language|null $lang The language to parse the message in (since 1.26)
 314          *
 315          * @throws MWException If the model ID isn't known.
 316          * @return string The content model's localized name.
 317          */
 318         public static function getLocalizedName( $name, Language $lang = null ) {
 319                 // Messages: content-model-wikitext, content-model-text,
 320                 // content-model-javascript, content-model-css
 321                 $key = "content-model-$name";
 322
 323                 $msg = wfMessage( $key );
 324                 if ( $lang ) {
 325                         $msg->inLanguage( $lang );
 326                 }
 327
 328                 return $msg->exists() ? $msg->plain() : $name;
 329         }
 330
 331         public static function getContentModels() {
 332                 global $wgContentHandlers;
 333
 334                 $models = array_keys( $wgContentHandlers );
 335                 Hooks::run( 'GetContentModels', [ &$models ] );
 336                 return $models;
 337         }
 338
 339         public static function getAllContentFormats() {
 340                 global $wgContentHandlers;
 341
 342                 $formats = [];
 343
 344                 foreach ( $wgContentHandlers as $model => $class ) {
 345                         $handler = self::getForModelID( $model );
 346                         $formats = array_merge( $formats, $handler->getSupportedFormats() );
 347                 }
 348
 349                 $formats = array_unique( $formats );
 350
 351                 return $formats;
 352         }
 353
 354         // ------------------------------------------------------------------------
 355
 356         /**
 357          * @var string
 358          */
 359         protected $mModelID;
 360
 361         /**
 362          * @var string[]
 363          */
 364         protected $mSupportedFormats;
 365
 366         /**
 367          * Constructor, initializing the ContentHandler instance with its model ID
 368          * and a list of supported formats. Values for the parameters are typically
 369          * provided as literals by subclass's constructors.
 370          *
 371          * @param string $modelId (use CONTENT_MODEL_XXX constants).
 372          * @param string[] $formats List for supported serialization formats
 373          *    (typically as MIME types)
 374          */
 375         public function __construct( $modelId, $formats ) {
 376                 $this->mModelID = $modelId;
 377                 $this->mSupportedFormats = $formats;
 378         }
 379
 380         /**
 381          * Serializes a Content object of the type supported by this ContentHandler.
 382          *
 383          * @since 1.21
 384          *
 385          * @param Content $content The Content object to serialize
 386          * @param string|null $format The desired serialization format
 387          *
 388          * @return string Serialized form of the content
 389          */
 390         abstract public function serializeContent( Content $content, $format = null );
 391
 392         /**
 393          * Applies transformations on export (returns the blob unchanged per default).
 394          * Subclasses may override this to perform transformations such as conversion
 395          * of legacy formats or filtering of internal meta-data.
 396          *
 397          * @param string $blob The blob to be exported
 398          * @param string|null $format The blob's serialization format
 399          *
 400          * @return string
 401          */
 402         public function exportTransform( $blob, $format = null ) {
 403                 return $blob;
 404         }
 405
 406         /**
 407          * Unserializes a Content object of the type supported by this ContentHandler.
 408          *
 409          * @since 1.21
 410          *
 411          * @param string $blob Serialized form of the content
 412          * @param string|null $format The format used for serialization
 413          *
 414          * @return Content The Content object created by deserializing $blob
 415          */
 416         abstract public function unserializeContent( $blob, $format = null );
 417
 418         /**
 419          * Apply import transformation (per default, returns $blob unchanged).
 420          * This gives subclasses an opportunity to transform data blobs on import.
 421          *
 422          * @since 1.24
 423          *
 424          * @param string $blob
 425          * @param string|null $format
 426          *
 427          * @return string
 428          */
 429         public function importTransform( $blob, $format = null ) {
 430                 return $blob;
 431         }
 432
 433         /**
 434          * Creates an empty Content object of the type supported by this
 435          * ContentHandler.
 436          *
 437          * @since 1.21
 438          *
 439          * @return Content
 440          */
 441         abstract public function makeEmptyContent();
 442
 443         /**
 444          * Creates a new Content object that acts as a redirect to the given page,
 445          * or null if redirects are not supported by this content model.
 446          *
 447          * This default implementation always returns null. Subclasses supporting redirects
 448          * must override this method.
 449          *
 450          * Note that subclasses that override this method to return a Content object
 451          * should also override supportsRedirects() to return true.
 452          *
 453          * @since 1.21
 454          *
 455          * @param Title $destination The page to redirect to.
 456          * @param string $text Text to include in the redirect, if possible.
 457          *
 458          * @return Content Always null.
 459          */
 460         public function makeRedirectContent( Title $destination, $text = '' ) {
 461                 return null;
 462         }
 463
 464         /**
 465          * Returns the model id that identifies the content model this
 466          * ContentHandler can handle. Use with the CONTENT_MODEL_XXX constants.
 467          *
 468          * @since 1.21
 469          *
 470          * @return string The model ID
 471          */
 472         public function getModelID() {
 473                 return $this->mModelID;
 474         }
 475
 476         /**
 477          * @since 1.21
 478          *
 479          * @param string $model_id The model to check
 480          *
 481          * @throws MWException If the model ID is not the ID of the content model supported by this
 482          * ContentHandler.
 483          */
 484         protected function checkModelID( $model_id ) {
 485                 if ( $model_id !== $this->mModelID ) {
 486                         throw new MWException( "Bad content model: " .
 487                                 "expected {$this->mModelID} " .
 488                                 "but got $model_id." );
 489                 }
 490         }
 491
 492         /**
 493          * Returns a list of serialization formats supported by the
 494          * serializeContent() and unserializeContent() methods of this
 495          * ContentHandler.
 496          *
 497          * @since 1.21
 498          *
 499          * @return string[] List of serialization formats as MIME type like strings
 500          */
 501         public function getSupportedFormats() {
 502                 return $this->mSupportedFormats;
 503         }
 504
 505         /**
 506          * The format used for serialization/deserialization by default by this
 507          * ContentHandler.
 508          *
 509          * This default implementation will return the first element of the array
 510          * of formats that was passed to the constructor.
 511          *
 512          * @since 1.21
 513          *
 514          * @return string The name of the default serialization format as a MIME type
 515          */
 516         public function getDefaultFormat() {
 517                 return $this->mSupportedFormats[0];
 518         }
 519
 520         /**
 521          * Returns true if $format is a serialization format supported by this
 522          * ContentHandler, and false otherwise.
 523          *
 524          * Note that if $format is null, this method always returns true, because
 525          * null means "use the default format".
 526          *
 527          * @since 1.21
 528          *
 529          * @param string $format The serialization format to check
 530          *
 531          * @return bool
 532          */
 533         public function isSupportedFormat( $format ) {
 534                 if ( !$format ) {
 535                         return true; // this means "use the default"
 536                 }
 537
 538                 return in_array( $format, $this->mSupportedFormats );
 539         }
 540
 541         /**
 542          * Convenient for checking whether a format provided as a parameter is actually supported.
 543          *
 544          * @param string $format The serialization format to check
 545          *
 546          * @throws MWException If the format is not supported by this content handler.
 547          */
 548         protected function checkFormat( $format ) {
 549                 if ( !$this->isSupportedFormat( $format ) ) {
 550                         throw new MWException(
 551                                 "Format $format is not supported for content model "
 552                                 . $this->getModelID()
 553                         );
 554                 }
 555         }
 556
 557         /**
 558          * Returns overrides for action handlers.
 559          * Classes listed here will be used instead of the default one when
 560          * (and only when) $wgActions[$action] === true. This allows subclasses
 561          * to override the default action handlers.
 562          *
 563          * @since 1.21
 564          *
 565          * @return array An array mapping action names (typically "view", "edit", "history" etc.) to
 566          *  either the full qualified class name of an Action class, a callable taking ( Page $page,
 567          *  IContextSource $context = null ) as parameters and returning an Action object, or an actual
 568          *  Action object. An empty array in this default implementation.
 569          *
 570          * @see Action::factory
 571          */
 572         public function getActionOverrides() {
 573                 return [];
 574         }
 575
 576         /**
 577          * Factory for creating an appropriate DifferenceEngine for this content model.
 578          * Since 1.32, this is only used for page-level diffs; to diff two content objects,
 579          * use getSlotDiffRenderer.
 580          *
 581          * The DifferenceEngine subclass to use is selected in getDiffEngineClass(). The
 582          * GetDifferenceEngine hook will receive the DifferenceEngine object and can replace or
 583          * wrap it.
 584          * (Note that in older versions of MediaWiki the hook documentation instructed extensions
 585          * to return false from the hook; you should not rely on always being able to decorate
 586          * the DifferenceEngine instance from the hook. If the owner of the content type wants to
 587          * decorare the instance, overriding this method is a safer approach.)
 588          *
 589          * @todo This is page-level functionality so it should not belong to ContentHandler.
 590          *   Move it to a better place once one exists (e.g. PageTypeHandler).
 591          *
 592          * @since 1.21
 593          *
 594          * @param IContextSource $context Context to use, anything else will be ignored.
 595          * @param int $old Revision ID we want to show and diff with.
 596          * @param int|string $new Either a revision ID or one of the strings 'cur', 'prev' or 'next'.
 597          * @param int $rcid FIXME: Deprecated, no longer used. Defaults to 0.
 598          * @param bool $refreshCache If set, refreshes the diff cache. Defaults to false.
 599          * @param bool $unhide If set, allow viewing deleted revs. Defaults to false.
 600          *
 601          * @return DifferenceEngine
 602          */
 603         public function createDifferenceEngine( IContextSource $context, $old = 0, $new = 0,
 604                 $rcid = 0, // FIXME: Deprecated, no longer used
 605                 $refreshCache = false, $unhide = false
 606         ) {
 607                 $diffEngineClass = $this->getDiffEngineClass();
 608                 $differenceEngine = new $diffEngineClass( $context, $old, $new, $rcid, $refreshCache, $unhide );
 609                 Hooks::run( 'GetDifferenceEngine', [ $context, $old, $new, $refreshCache, $unhide,
 610                         &$differenceEngine ] );
 611                 return $differenceEngine;
 612         }
 613
 614         /**
 615          * Get an appropriate SlotDiffRenderer for this content model.
 616          * @since 1.32
 617          * @param IContextSource $context
 618          * @return SlotDiffRenderer
 619          */
 620         final public function getSlotDiffRenderer( IContextSource $context ) {
 621                 $slotDiffRenderer = $this->getSlotDiffRendererInternal( $context );
 622                 if ( get_class( $slotDiffRenderer ) === TextSlotDiffRenderer::class ) {
 623                         //  To keep B/C, when SlotDiffRenderer is not overridden for a given content type
 624                         // but DifferenceEngine is, use that instead.
 625                         $differenceEngine = $this->createDifferenceEngine( $context );
 626                         if ( get_class( $differenceEngine ) !== DifferenceEngine::class ) {
 627                                 // TODO turn this into a deprecation warning in a later release
 628                                 LoggerFactory::getInstance( 'diff' )->info(
 629                                         'Falling back to DifferenceEngineSlotDiffRenderer', [
 630                                                 'modelID' => $this->getModelID(),
 631                                                 'DifferenceEngine' => get_class( $differenceEngine ),
 632                                         ] );
 633                                 $slotDiffRenderer = new DifferenceEngineSlotDiffRenderer( $differenceEngine );
 634                         }
 635                 }
 636                 Hooks::run( 'GetSlotDiffRenderer', [ $this, &$slotDiffRenderer, $context ] );
 637                 return $slotDiffRenderer;
 638         }
 639
 640         /**
 641          * Return the SlotDiffRenderer appropriate for this content handler.
 642          * @param IContextSource $context
 643          * @return SlotDiffRenderer
 644          */
 645         protected function getSlotDiffRendererInternal( IContextSource $context ) {
 646                 $contentLanguage = MediaWikiServices::getInstance()->getContentLanguage();
 647                 $statsdDataFactory = MediaWikiServices::getInstance()->getStatsdDataFactory();
 648                 $slotDiffRenderer = new TextSlotDiffRenderer();
 649                 $slotDiffRenderer->setStatsdDataFactory( $statsdDataFactory );
 650                 // XXX using the page language would be better, but it's unclear how that should be injected
 651                 $slotDiffRenderer->setLanguage( $contentLanguage );
 652
 653                 $engine = DifferenceEngine::getEngine();
 654                 if ( $engine === 'php' ) {
 655                         $slotDiffRenderer->setEngine( TextSlotDiffRenderer::ENGINE_PHP );
 656                 } elseif ( $engine === 'wikidiff2' ) {
 657                         $slotDiffRenderer->setEngine( TextSlotDiffRenderer::ENGINE_WIKIDIFF2 );
 658                 } else {
 659                         $slotDiffRenderer->setEngine( TextSlotDiffRenderer::ENGINE_EXTERNAL, $engine );
 660                 }
 661
 662                 return $slotDiffRenderer;
 663         }
 664
 665         /**
 666          * Get the language in which the content of the given page is written.
 667          *
 668          * This default implementation just returns the content language (except for pages
 669          * in the MediaWiki namespace)
 670          *
 671          * Note that the page's language is not cacheable, since it may in some
 672          * cases depend on user settings.
 673          *
 674          * Also note that the page language may or may not depend on the actual content of the page,
 675          * that is, this method may load the content in order to determine the language.
 676          *
 677          * @since 1.21
 678          *
 679          * @param Title $title The page to determine the language for.
 680          * @param Content|null $content The page's content, if you have it handy, to avoid reloading it.
 681          *
 682          * @return Language The page's language
 683          */
 684         public function getPageLanguage( Title $title, Content $content = null ) {
 685                 global $wgLang;
 686                 $pageLang = MediaWikiServices::getInstance()->getContentLanguage();
 687
 688                 if ( $title->inNamespace( NS_MEDIAWIKI ) ) {
 689                         // Parse mediawiki messages with correct target language
 690                         list( /* $unused */, $lang ) = MessageCache::singleton()->figureMessage( $title->getText() );
 691                         $pageLang = Language::factory( $lang );
 692                 }
 693
 694                 // Simplify hook handlers by only passing objects of one type, in case nothing
 695                 // else has unstubbed the StubUserLang object by now.
 696                 StubObject::unstub( $wgLang );
 697
 698                 Hooks::run( 'PageContentLanguage', [ $title, &$pageLang, $wgLang ] );
 699
 700                 return wfGetLangObj( $pageLang );
 701         }
 702
 703         /**
 704          * Get the language in which the content of this page is written when
 705          * viewed by user. Defaults to $this->getPageLanguage(), but if the user
 706          * specified a preferred variant, the variant will be used.
 707          *
 708          * This default implementation just returns $this->getPageLanguage( $title, $content ) unless
 709          * the user specified a preferred variant.
 710          *
 711          * Note that the pages view language is not cacheable, since it depends on user settings.
 712          *
 713          * Also note that the page language may or may not depend on the actual content of the page,
 714          * that is, this method may load the content in order to determine the language.
 715          *
 716          * @since 1.21
 717          *
 718          * @param Title $title The page to determine the language for.
 719          * @param Content|null $content The page's content, if you have it handy, to avoid reloading it.
 720          *
 721          * @return Language The page's language for viewing
 722          */
 723         public function getPageViewLanguage( Title $title, Content $content = null ) {
 724                 $pageLang = $this->getPageLanguage( $title, $content );
 725
 726                 if ( $title->getNamespace() !== NS_MEDIAWIKI ) {
 727                         // If the user chooses a variant, the content is actually
 728                         // in a language whose code is the variant code.
 729                         $variant = $pageLang->getPreferredVariant();
 730                         if ( $pageLang->getCode() !== $variant ) {
 731                                 $pageLang = Language::factory( $variant );
 732                         }
 733                 }
 734
 735                 return $pageLang;
 736         }
 737
 738         /**
 739          * Determines whether the content type handled by this ContentHandler
 740          * can be used for the main slot of the given page.
 741          *
 742          * This default implementation always returns true.
 743          * Subclasses may override this to restrict the use of this content model to specific locations,
 744          * typically based on the namespace or some other aspect of the title, such as a special suffix
 745          * (e.g. ".svg" for SVG content).
 746          *
 747          * @note this calls the ContentHandlerCanBeUsedOn hook which may be used to override which
 748          * content model can be used where.
 749          *
 750          * @see SlotRoleHandler::isAllowedModel
 751          *
 752          * @param Title $title The page's title.
 753          *
 754          * @return bool True if content of this kind can be used on the given page, false otherwise.
 755          */
 756         public function canBeUsedOn( Title $title ) {
 757                 $ok = true;
 758
 759                 Hooks::run( 'ContentModelCanBeUsedOn', [ $this->getModelID(), $title, &$ok ] );
 760
 761                 return $ok;
 762         }
 763
 764         /**
 765          * Returns the name of the diff engine to use.
 766          *
 767          * @since 1.21
 768          *
 769          * @return string
 770          */
 771         protected function getDiffEngineClass() {
 772                 return DifferenceEngine::class;
 773         }
 774
 775         /**
 776          * Attempts to merge differences between three versions. Returns a new
 777          * Content object for a clean merge and false for failure or a conflict.
 778          *
 779          * This default implementation always returns false.
 780          *
 781          * @since 1.21
 782          *
 783          * @param Content $oldContent The page's previous content.
 784          * @param Content $myContent One of the page's conflicting contents.
 785          * @param Content $yourContent One of the page's conflicting contents.
 786          *
 787          * @return Content|bool Always false.
 788          */
 789         public function merge3( Content $oldContent, Content $myContent, Content $yourContent ) {
 790                 return false;
 791         }
 792
 793         /**
 794          * Return type of change if one exists for the given edit.
 795          *
 796          * @since 1.31
 797          *
 798          * @param Content|null $oldContent The previous text of the page.
 799          * @param Content|null $newContent The submitted text of the page.
 800          * @param int $flags Bit mask: a bit mask of flags submitted for the edit.
 801          *
 802          * @return string|null String key representing type of change, or null.
 803          */
 804         private function getChangeType(
 805                 Content $oldContent = null,
 806                 Content $newContent = null,
 807                 $flags = 0
 808         ) {
 809                 $oldTarget = $oldContent !== null ? $oldContent->getRedirectTarget() : null;
 810                 $newTarget = $newContent !== null ? $newContent->getRedirectTarget() : null;
 811
 812                 // We check for the type of change in the given edit, and return string key accordingly
 813
 814                 // Blanking of a page
 815                 if ( $oldContent && $oldContent->getSize() > 0 &&
 816                         $newContent && $newContent->getSize() === 0
 817                 ) {
 818                         return 'blank';
 819                 }
 820
 821                 // Redirects
 822                 if ( $newTarget ) {
 823                         if ( !$oldTarget ) {
 824                                 // New redirect page (by creating new page or by changing content page)
 825                                 return 'new-redirect';
 826                         } elseif ( !$newTarget->equals( $oldTarget ) ||
 827                                 $oldTarget->getFragment() !== $newTarget->getFragment()
 828                         ) {
 829                                 // Redirect target changed
 830                                 return 'changed-redirect-target';
 831                         }
 832                 } elseif ( $oldTarget ) {
 833                         // Changing an existing redirect into a non-redirect
 834                         return 'removed-redirect';
 835                 }
 836
 837                 // New page created
 838                 if ( $flags & EDIT_NEW && $newContent ) {
 839                         if ( $newContent->getSize() === 0 ) {
 840                                 // New blank page
 841                                 return 'newblank';
 842                         } else {
 843                                 return 'newpage';
 844                         }
 845                 }
 846
 847                 // Removing more than 90% of the page
 848                 if ( $oldContent && $newContent && $oldContent->getSize() > 10 * $newContent->getSize() ) {
 849                         return 'replace';
 850                 }
 851
 852                 // Content model changed
 853                 if ( $oldContent && $newContent && $oldContent->getModel() !== $newContent->getModel() ) {
 854                         return 'contentmodelchange';
 855                 }
 856
 857                 return null;
 858         }
 859
 860         /**
 861          * Return an applicable auto-summary if one exists for the given edit.
 862          *
 863          * @since 1.21
 864          *
 865          * @param Content|null $oldContent The previous text of the page.
 866          * @param Content|null $newContent The submitted text of the page.
 867          * @param int $flags Bit mask: a bit mask of flags submitted for the edit.
 868          *
 869          * @return string An appropriate auto-summary, or an empty string.
 870          */
 871         public function getAutosummary(
 872                 Content $oldContent = null,
 873                 Content $newContent = null,
 874                 $flags = 0
 875         ) {
 876                 $changeType = $this->getChangeType( $oldContent, $newContent, $flags );
 877
 878                 // There's no applicable auto-summary for our case, so our auto-summary is empty.
 879                 if ( !$changeType ) {
 880                         return '';
 881                 }
 882
 883                 // Decide what kind of auto-summary is needed.
 884                 switch ( $changeType ) {
 885                         case 'new-redirect':
 886                                 $newTarget = $newContent->getRedirectTarget();
 887                                 $truncatedtext = $newContent->getTextForSummary(
 888                                         250
 889                                         - strlen( wfMessage( 'autoredircomment' )->inContentLanguage()->text() )
 890                                         - strlen( $newTarget->getFullText() )
 891                                 );
 892
 893                                 return wfMessage( 'autoredircomment', $newTarget->getFullText() )
 894                                         ->plaintextParams( $truncatedtext )->inContentLanguage()->text();
 895                         case 'changed-redirect-target':
 896                                 $oldTarget = $oldContent->getRedirectTarget();
 897                                 $newTarget = $newContent->getRedirectTarget();
 898
 899                                 $truncatedtext = $newContent->getTextForSummary(
 900                                         250
 901                                         - strlen( wfMessage( 'autosumm-changed-redirect-target' )
 902                                                 ->inContentLanguage()->text() )
 903                                         - strlen( $oldTarget->getFullText() )
 904                                         - strlen( $newTarget->getFullText() )
 905                                 );
 906
 907                                 return wfMessage( 'autosumm-changed-redirect-target',
 908                                                 $oldTarget->getFullText(),
 909                                                 $newTarget->getFullText() )
 910                                         ->rawParams( $truncatedtext )->inContentLanguage()->text();
 911                         case 'removed-redirect':
 912                                 $oldTarget = $oldContent->getRedirectTarget();
 913                                 $truncatedtext = $newContent->getTextForSummary(
 914                                         250
 915                                         - strlen( wfMessage( 'autosumm-removed-redirect' )
 916                                                 ->inContentLanguage()->text() )
 917                                         - strlen( $oldTarget->getFullText() ) );
 918
 919                                 return wfMessage( 'autosumm-removed-redirect', $oldTarget->getFullText() )
 920                                         ->rawParams( $truncatedtext )->inContentLanguage()->text();
 921                         case 'newpage':
 922                                 // If they're making a new article, give its text, truncated, in the summary.
 923                                 $truncatedtext = $newContent->getTextForSummary(
 924                                         200 - strlen( wfMessage( 'autosumm-new' )->inContentLanguage()->text() ) );
 925
 926                                 return wfMessage( 'autosumm-new' )->rawParams( $truncatedtext )
 927                                         ->inContentLanguage()->text();
 928                         case 'blank':
 929                                 return wfMessage( 'autosumm-blank' )->inContentLanguage()->text();
 930                         case 'replace':
 931                                 $truncatedtext = $newContent->getTextForSummary(
 932                                         200 - strlen( wfMessage( 'autosumm-replace' )->inContentLanguage()->text() ) );
 933
 934                                 return wfMessage( 'autosumm-replace' )->rawParams( $truncatedtext )
 935                                         ->inContentLanguage()->text();
 936                         case 'newblank':
 937                                 return wfMessage( 'autosumm-newblank' )->inContentLanguage()->text();
 938                         default:
 939                                 return '';
 940                 }
 941         }
 942
 943         /**
 944          * Return an applicable tag if one exists for the given edit or return null.
 945          *
 946          * @since 1.31
 947          *
 948          * @param Content|null $oldContent The previous text of the page.
 949          * @param Content|null $newContent The submitted text of the page.
 950          * @param int $flags Bit mask: a bit mask of flags submitted for the edit.
 951          *
 952          * @return string|null An appropriate tag, or null.
 953          */
 954         public function getChangeTag(
 955                 Content $oldContent = null,
 956                 Content $newContent = null,
 957                 $flags = 0
 958         ) {
 959                 $changeType = $this->getChangeType( $oldContent, $newContent, $flags );
 960
 961                 // There's no applicable tag for this change.
 962                 if ( !$changeType ) {
 963                         return null;
 964                 }
 965
 966                 // Core tags use the same keys as ones returned from $this->getChangeType()
 967                 // but prefixed with pseudo namespace 'mw-', so we add the prefix before checking
 968                 // if this type of change should be tagged
 969                 $tag = 'mw-' . $changeType;
 970
 971                 // Not all change types are tagged, so we check against the list of defined tags.
 972                 if ( in_array( $tag, ChangeTags::getSoftwareTags() ) ) {
 973                         return $tag;
 974                 }
 975
 976                 return null;
 977         }
 978
 979         /**
 980          * Auto-generates a deletion reason
 981          *
 982          * @since 1.21
 983          *
 984          * @param Title $title The page's title
 985          * @param bool &$hasHistory Whether the page has a history
 986          *
 987          * @return mixed String containing deletion reason or empty string, or
 988          *    boolean false if no revision occurred
 989          *
 990          * @todo &$hasHistory is extremely ugly, it's here because
 991          * WikiPage::getAutoDeleteReason() and Article::generateReason()
 992          * have it / want it.
 993          */
 994         public function getAutoDeleteReason( Title $title, &$hasHistory ) {
 995                 $dbr = wfGetDB( DB_REPLICA );
 996
 997                 // Get the last revision
 998                 $rev = Revision::newFromTitle( $title );
 999
1000                 if ( is_null( $rev ) ) {
1001                         return false;
1002                 }
1003
1004                 // Get the article's contents
1005                 $content = $rev->getContent();
1006                 $blank = false;
1007
1008                 // If the page is blank, use the text from the previous revision,
1009                 // which can only be blank if there's a move/import/protect dummy
1010                 // revision involved
1011                 if ( !$content || $content->isEmpty() ) {
1012                         $prev = $rev->getPrevious();
1013
1014                         if ( $prev ) {
1015                                 $rev = $prev;
1016                                 $content = $rev->getContent();
1017                                 $blank = true;
1018                         }
1019                 }
1020
1021                 $this->checkModelID( $rev->getContentModel() );
1022
1023                 // Find out if there was only one contributor
1024                 // Only scan the last 20 revisions
1025                 $revQuery = Revision::getQueryInfo();
1026                 $res = $dbr->select(
1027                         $revQuery['tables'],
1028                         [ 'rev_user_text' => $revQuery['fields']['rev_user_text'] ],
1029                         [
1030                                 'rev_page' => $title->getArticleID(),
1031                                 $dbr->bitAnd( 'rev_deleted', RevisionRecord::DELETED_USER ) . ' = 0'
1032                         ],
1033                         __METHOD__,
1034                         [ 'LIMIT' => 20 ],
1035                         $revQuery['joins']
1036                 );
1037
1038                 if ( $res === false ) {
1039                         // This page has no revisions, which is very weird
1040                         return false;
1041                 }
1042
1043                 $hasHistory = ( $res->numRows() > 1 );
1044                 $row = $dbr->fetchObject( $res );
1045
1046                 if ( $row ) { // $row is false if the only contributor is hidden
1047                         $onlyAuthor = $row->rev_user_text;
1048                         // Try to find a second contributor
1049                         foreach ( $res as $row ) {
1050                                 if ( $row->rev_user_text != $onlyAuthor ) { // T24999
1051                                         $onlyAuthor = false;
1052                                         break;
1053                                 }
1054                         }
1055                 } else {
1056                         $onlyAuthor = false;
1057                 }
1058
1059                 // Generate the summary with a '$1' placeholder
1060                 if ( $blank ) {
1061                         // The current revision is blank and the one before is also
1062                         // blank. It's just not our lucky day
1063                         $reason = wfMessage( 'exbeforeblank', '$1' )->inContentLanguage()->text();
1064                 } else {
1065                         if ( $onlyAuthor ) {
1066                                 $reason = wfMessage(
1067                                         'excontentauthor',
1068                                         '$1',
1069                                         $onlyAuthor
1070                                 )->inContentLanguage()->text();
1071                         } else {
1072                                 $reason = wfMessage( 'excontent', '$1' )->inContentLanguage()->text();
1073                         }
1074                 }
1075
1076                 if ( $reason == '-' ) {
1077                         // Allow these UI messages to be blanked out cleanly
1078                         return '';
1079                 }
1080
1081                 // Max content length = max comment length - length of the comment (excl. $1)
1082                 $maxLength = CommentStore::COMMENT_CHARACTER_LIMIT - ( strlen( $reason ) - 2 );
1083                 $text = $content ? $content->getTextForSummary( $maxLength ) : '';
1084
1085                 // Now replace the '$1' placeholder
1086                 $reason = str_replace( '$1', $text, $reason );
1087
1088                 return $reason;
1089         }
1090
1091         /**
1092          * Get the Content object that needs to be saved in order to undo all revisions
1093          * between $undo and $undoafter. Revisions must belong to the same page,
1094          * must exist and must not be deleted.
1095          *
1096          * @since 1.21
1097          * @since 1.32 accepts Content objects for all parameters instead of Revision objects.
1098          *  Passing Revision objects is deprecated.
1099          *
1100          * @param Revision|Content $current The current text
1101          * @param Revision|Content $undo The content of the revision to undo
1102          * @param Revision|Content $undoafter Must be from an earlier revision than $undo
1103          * @param bool $undoIsLatest Set true if $undo is from the current revision (since 1.32)
1104          *
1105          * @return Content|false Content on success, false on failure
1106          */
1107         public function getUndoContent( $current, $undo, $undoafter, $undoIsLatest = false ) {
1108                 Assert::parameterType( Revision::class . '|' . Content::class, $current, '$current' );
1109                 if ( $current instanceof Content ) {
1110                         Assert::parameter( $undo instanceof Content, '$undo',
1111                                 'Must be Content when $current is Content' );
1112                         Assert::parameter( $undoafter instanceof Content, '$undoafter',
1113                                 'Must be Content when $current is Content' );
1114                         $cur_content = $current;
1115                         $undo_content = $undo;
1116                         $undoafter_content = $undoafter;
1117                 } else {
1118                         Assert::parameter( $undo instanceof Revision, '$undo',
1119                                 'Must be Revision when $current is Revision' );
1120                         Assert::parameter( $undoafter instanceof Revision, '$undoafter',
1121                                 'Must be Revision when $current is Revision' );
1122
1123                         $cur_content = $current->getContent();
1124
1125                         if ( empty( $cur_content ) ) {
1126                                 return false; // no page
1127                         }
1128
1129                         $undo_content = $undo->getContent();
1130                         $undoafter_content = $undoafter->getContent();
1131
1132                         if ( !$undo_content || !$undoafter_content ) {
1133                                 return false; // no content to undo
1134                         }
1135
1136                         $undoIsLatest = $current->getId() === $undo->getId();
1137                 }
1138
1139                 try {
1140                         $this->checkModelID( $cur_content->getModel() );
1141                         $this->checkModelID( $undo_content->getModel() );
1142                         if ( !$undoIsLatest ) {
1143                                 // If we are undoing the most recent revision,
1144                                 // its ok to revert content model changes. However
1145                                 // if we are undoing a revision in the middle, then
1146                                 // doing that will be confusing.
1147                                 $this->checkModelID( $undoafter_content->getModel() );
1148                         }
1149                 } catch ( MWException $e ) {
1150                         // If the revisions have different content models
1151                         // just return false
1152                         return false;
1153                 }
1154
1155                 if ( $cur_content->equals( $undo_content ) ) {
1156                         // No use doing a merge if it's just a straight revert.
1157                         return $undoafter_content;
1158                 }
1159
1160                 $undone_content = $this->merge3( $undo_content, $undoafter_content, $cur_content );
1161
1162                 return $undone_content;
1163         }
1164
1165         /**
1166          * Get parser options suitable for rendering and caching the article
1167          *
1168          * @deprecated since 1.32, use WikiPage::makeParserOptions() or
1169          *  ParserOptions::newCanonical() instead.
1170          * @param IContextSource|User|string $context One of the following:
1171          *        - IContextSource: Use the User and the Language of the provided
1172          *                                            context
1173          *        - User: Use the provided User object and $wgLang for the language,
1174          *                                            so use an IContextSource object if possible.
1175          *        - 'canonical': Canonical options (anonymous user with default
1176          *                                            preferences and content language).
1177          *
1178          * @throws MWException
1179          * @return ParserOptions
1180          */
1181         public function makeParserOptions( $context ) {
1182                 wfDeprecated( __METHOD__, '1.32' );
1183                 return ParserOptions::newCanonical( $context );
1184         }
1185
1186         /**
1187          * Returns true for content models that support caching using the
1188          * ParserCache mechanism. See WikiPage::shouldCheckParserCache().
1189          *
1190          * @since 1.21
1191          *
1192          * @return bool Always false.
1193          */
1194         public function isParserCacheSupported() {
1195                 return false;
1196         }
1197
1198         /**
1199          * Returns true if this content model supports sections.
1200          * This default implementation returns false.
1201          *
1202          * Content models that return true here should also implement
1203          * Content::getSection, Content::replaceSection, etc. to handle sections..
1204          *
1205          * @return bool Always false.
1206          */
1207         public function supportsSections() {
1208                 return false;
1209         }
1210
1211         /**
1212          * Returns true if this content model supports categories.
1213          * The default implementation returns true.
1214          *
1215          * @return bool Always true.
1216          */
1217         public function supportsCategories() {
1218                 return true;
1219         }
1220
1221         /**
1222          * Returns true if this content model supports redirects.
1223          * This default implementation returns false.
1224          *
1225          * Content models that return true here should also implement
1226          * ContentHandler::makeRedirectContent to return a Content object.
1227          *
1228          * @return bool Always false.
1229          */
1230         public function supportsRedirects() {
1231                 return false;
1232         }
1233
1234         /**
1235          * Return true if this content model supports direct editing, such as via EditPage.
1236          *
1237          * @return bool Default is false, and true for TextContent and it's derivatives.
1238          */
1239         public function supportsDirectEditing() {
1240                 return false;
1241         }
1242
1243         /**
1244          * Whether or not this content model supports direct editing via ApiEditPage
1245          *
1246          * @return bool Default is false, and true for TextContent and derivatives.
1247          */
1248         public function supportsDirectApiEditing() {
1249                 return $this->supportsDirectEditing();
1250         }
1251
1252         /**
1253          * Get fields definition for search index
1254          *
1255          * @todo Expose title, redirect, namespace, text, source_text, text_bytes
1256          *       field mappings here. (see T142670 and T143409)
1257          *
1258          * @param SearchEngine $engine
1259          * @return SearchIndexField[] List of fields this content handler can provide.
1260          * @since 1.28
1261          */
1262         public function getFieldsForSearchIndex( SearchEngine $engine ) {
1263                 $fields = [];
1264                 $fields['category'] = $engine->makeSearchFieldMapping(
1265                         'category',
1266                         SearchIndexField::INDEX_TYPE_TEXT
1267                 );
1268                 $fields['category']->setFlag( SearchIndexField::FLAG_CASEFOLD );
1269
1270                 $fields['external_link'] = $engine->makeSearchFieldMapping(
1271                         'external_link',
1272                         SearchIndexField::INDEX_TYPE_KEYWORD
1273                 );
1274
1275                 $fields['outgoing_link'] = $engine->makeSearchFieldMapping(
1276                         'outgoing_link',
1277                         SearchIndexField::INDEX_TYPE_KEYWORD
1278                 );
1279
1280                 $fields['template'] = $engine->makeSearchFieldMapping(
1281                         'template',
1282                         SearchIndexField::INDEX_TYPE_KEYWORD
1283                 );
1284                 $fields['template']->setFlag( SearchIndexField::FLAG_CASEFOLD );
1285
1286                 $fields['content_model'] = $engine->makeSearchFieldMapping(
1287                         'content_model',
1288                         SearchIndexField::INDEX_TYPE_KEYWORD
1289                 );
1290
1291                 return $fields;
1292         }
1293
1294         /**
1295          * Add new field definition to array.
1296          * @param SearchIndexField[] &$fields
1297          * @param SearchEngine $engine
1298          * @param string $name
1299          * @param int $type
1300          * @return SearchIndexField[] new field defs
1301          * @since 1.28
1302          */
1303         protected function addSearchField( &$fields, SearchEngine $engine, $name, $type ) {
1304                 $fields[$name] = $engine->makeSearchFieldMapping( $name, $type );
1305                 return $fields;
1306         }
1307
1308         /**
1309          * Return fields to be indexed by search engine
1310          * as representation of this document.
1311          * Overriding class should call parent function or take care of calling
1312          * the SearchDataForIndex hook.
1313          * @param WikiPage $page Page to index
1314          * @param ParserOutput $output
1315          * @param SearchEngine $engine Search engine for which we are indexing
1316          * @return array Map of name=>value for fields
1317          * @since 1.28
1318          */
1319         public function getDataForSearchIndex(
1320                 WikiPage $page,
1321                 ParserOutput $output,
1322                 SearchEngine $engine
1323         ) {
1324                 $fieldData = [];
1325                 $content = $page->getContent();
1326
1327                 if ( $content ) {
1328                         $searchDataExtractor = new ParserOutputSearchDataExtractor();
1329
1330                         $fieldData['category'] = $searchDataExtractor->getCategories( $output );
1331                         $fieldData['external_link'] = $searchDataExtractor->getExternalLinks( $output );
1332                         $fieldData['outgoing_link'] = $searchDataExtractor->getOutgoingLinks( $output );
1333                         $fieldData['template'] = $searchDataExtractor->getTemplates( $output );
1334
1335                         $text = $content->getTextForSearchIndex();
1336
1337                         $fieldData['text'] = $text;
1338                         $fieldData['source_text'] = $text;
1339                         $fieldData['text_bytes'] = $content->getSize();
1340                         $fieldData['content_model'] = $content->getModel();
1341                 }
1342
1343                 Hooks::run( 'SearchDataForIndex', [ &$fieldData, $this, $page, $output, $engine ] );
1344                 return $fieldData;
1345         }
1346
1347         /**
1348          * Produce page output suitable for indexing.
1349          *
1350          * Specific content handlers may override it if they need different content handling.
1351          *
1352          * @param WikiPage $page
1353          * @param ParserCache|null $cache
1354          * @return ParserOutput
1355          */
1356         public function getParserOutputForIndexing( WikiPage $page, ParserCache $cache = null ) {
1357                 // TODO: MCR: ContentHandler should be called per slot, not for the whole page.
1358                 // See T190066.
1359                 $parserOptions = $page->makeParserOptions( 'canonical' );
1360                 if ( $cache ) {
1361                         $parserOutput = $cache->get( $page, $parserOptions );
1362                 }
1363
1364                 if ( empty( $parserOutput ) ) {
1365                         $renderer = MediaWikiServices::getInstance()->getRevisionRenderer();
1366                         $parserOutput =
1367                                 $renderer->getRenderedRevision(
1368                                         $page->getRevision()->getRevisionRecord(),
1369                                         $parserOptions
1370                                 )->getRevisionParserOutput();
1371                         if ( $cache ) {
1372                                 $cache->save( $parserOutput, $page, $parserOptions );
1373                         }
1374                 }
1375                 return $parserOutput;
1376         }
1377
1378         /**
1379          * Returns a list of DeferrableUpdate objects for recording information about the
1380          * given Content in some secondary data store.
1381          *
1382          * Application logic should not call this method directly. Instead, it should call
1383          * DerivedPageDataUpdater::getSecondaryDataUpdates().
1384          *
1385          * @note Implementations must not return a LinksUpdate instance. Instead, a LinksUpdate
1386          * is created by the calling code in DerivedPageDataUpdater, on the combined ParserOutput
1387          * of all slots, not for each slot individually. This is in contrast to the old
1388          * getSecondaryDataUpdates method defined by AbstractContent, which returned a LinksUpdate.
1389          *
1390          * @note Implementations should not call $content->getParserOutput, they should call
1391          * $slotOutput->getSlotRendering( $role, false ) instead if they need to access a ParserOutput
1392          * of $content. This allows existing ParserOutput objects to be re-used, while avoiding
1393          * creating a ParserOutput when none is needed.
1394          *
1395          * @param Title $title The title of the page to supply the updates for
1396          * @param Content $content The content to generate data updates for.
1397          * @param string $role The role (slot) in which the content is being used. Which updates
1398          *        are performed should generally not depend on the role the content has, but the
1399          *        DeferrableUpdates themselves may need to know the role, to track to which slot the
1400          *        data refers, and to avoid overwriting data of the same kind from another slot.
1401          * @param SlotRenderingProvider $slotOutput A provider that can be used to gain access to
1402          *        a ParserOutput of $content by calling $slotOutput->getSlotParserOutput( $role, false ).
1403          * @return DeferrableUpdate[] A list of DeferrableUpdate objects for putting information
1404          *        about this content object somewhere. The default implementation returns an empty
1405          *        array.
1406          * @since 1.32
1407          */
1408         public function getSecondaryDataUpdates(
1409                 Title $title,
1410                 Content $content,
1411                 $role,
1412                 SlotRenderingProvider $slotOutput
1413         ) {
1414                 return [];
1415         }
1416
1417         /**
1418          * Returns a list of DeferrableUpdate objects for removing information about content
1419          * in some secondary data store. This is used when a page is deleted, and also when
1420          * a slot is removed from a page.
1421          *
1422          * Application logic should not call this method directly. Instead, it should call
1423          * WikiPage::getSecondaryDataUpdates().
1424          *
1425          * @note Implementations must not return a LinksDeletionUpdate instance. Instead, a
1426          * LinksDeletionUpdate is created by the calling code in WikiPage.
1427          * This is in contrast to the old getDeletionUpdates method defined by AbstractContent,
1428          * which returned a LinksUpdate.
1429          *
1430          * @note Implementations should not rely on the page's current content, but rather the current
1431          * state of the secondary data store.
1432          *
1433          * @param Title $title The title of the page to supply the updates for
1434          * @param string $role The role (slot) in which the content is being used. Which updates
1435          *        are performed should generally not depend on the role the content has, but the
1436          *        DeferrableUpdates themselves may need to know the role, to track to which slot the
1437          *        data refers, and to avoid overwriting data of the same kind from another slot.
1438          *
1439          * @return DeferrableUpdate[] A list of DeferrableUpdate objects for putting information
1440          *        about this content object somewhere. The default implementation returns an empty
1441          *        array.
1442          *
1443          * @since 1.32
1444          */
1445         public function getDeletionUpdates( Title $title, $role ) {
1446                 return [];
1447         }
1448
1449 }