Provide revision content to PagePropertyProviderContext

docs/reference/extending.md

@@ -87,7 +87,16 @@ class StaticPagePropertyProvider implements PagePropertyProvider {
 ```
 
 Register with `NeoWikiRegistrar::addPagePropertyProvider()`. The context exposes the page id, title,
-creation and modification times, categories, and last editor. Example:
+creation and modification times, categories, and last editor, so providers can derive Page Properties
+from the page content without re-fetching or re-parsing it.
+
+To derive Page Properties from the content, prefer the parse products: `categories`, and
+`parserProperties` — the MediaWiki page properties recorded during parsing (e.g. those a parser hook
+sets via `ParserOutput::setPageProperty`). These are template-expansion-safe and robust. (Note that
+`parserProperties` are an input from MediaWiki's parse; they are not the NeoWiki Page Properties this
+provider returns.) The raw main slot `content` and its `contentModel` are also exposed, but scraping
+raw wikitext is fragile — reach for them mainly when handling a custom, non-wikitext content model that
+the parse products do not cover. Example:
 [`src/StaticPagePropertyProvider.php`](https://github.com/ProfessionalWiki/NeoWiki/blob/master/tests/RedHerb/src/StaticPagePropertyProvider.php).
 
 ### Reading NeoWiki data and authorization

src/Domain/Page/PagePropertyProviderContext.php

@@ -13,6 +13,14 @@
 	 * @param string $modificationTime In the standard MediaWiki format, ie 20230726163439
 	 * @param string[] $categories
 	 * @param string $lastEditor Plain username of the last editor, e.g. "JohnDoe". Empty string if unknown.
+	 * @param string $content Serialized main slot content of the revision, e.g. the wikitext.
+	 *   Empty string if the content is unavailable.
+	 * @param string $contentModel Content model of the main slot, e.g. "wikitext".
+	 *   Empty string if the content is unavailable.
+	 * @param array<string, int|float|string|bool|null> $parserProperties Properties recorded during parsing of the
+	 *   content (MediaWiki page properties, e.g. "defaultsort" or values set by parser hooks via
+	 *   ParserOutput::setPageProperty). These are inputs from the parse, not to be confused with the NeoWiki
+	 *   Page Properties that providers return.
 	 */
 	public function __construct(
 		public PageId $pageId,
@@ -22,6 +30,9 @@ public function __construct(
 		public string $modificationTime,
 		public array $categories,
 		public string $lastEditor,
+		public string $content,
+		public string $contentModel,
+		public array $parserProperties,
 	) {
 	}
 

src/PagePropertiesBuilder.php

@@ -4,8 +4,10 @@
 
 namespace ProfessionalWiki\NeoWiki;
 
+use MediaWiki\Content\Content;
 use MediaWiki\Content\IContentHandlerFactory;
 use MediaWiki\Content\Renderer\ContentParseParams;
+use MediaWiki\Parser\ParserOutput;
 use MediaWiki\Revision\RevisionRecord;
 use MediaWiki\Revision\RevisionStore;
 use MediaWiki\Revision\SlotRecord;
@@ -40,18 +42,28 @@ public function getPagePropertiesFor( RevisionRecord $revision, ?UserIdentity $u
 
 	private function buildContext( RevisionRecord $revision, ?UserIdentity $user ): PagePropertyProviderContext {
 		$linkTarget = $revision->getPageAsLinkTarget();
+		$content = $revision->getContent( SlotRecord::MAIN );
+		$parserOutput = $content === null ? null : $this->parse( $content, $revision );
 
 		return new PagePropertyProviderContext(
 			pageId: new PageId( $revision->getPageId() ),
 			pageTitle: $this->titleFormatter->getPrefixedText( $linkTarget ),
 			namespaceId: $linkTarget->getNamespace(),
 			creationTime: $this->getCreationTime( $revision ),
 			modificationTime: $this->getModificationTime( $revision ),
-			categories: $this->getCategories( $revision ),
+			categories: $parserOutput === null ? [] : $parserOutput->getCategoryNames(),
 			lastEditor: $user?->getName() ?? '',
+			content: $content === null ? '' : $content->serialize(),
+			contentModel: $content === null ? '' : $content->getModel(),
+			parserProperties: $parserOutput === null ? [] : $parserOutput->getPageProperties(),
 		);
 	}
 
+	private function parse( Content $content, RevisionRecord $revision ): ParserOutput {
+		return $this->contentHandlerFactory->getContentHandler( $content->getModel() )
+			->getParserOutput( $content, new ContentParseParams( $revision->getPage() ) );
+	}
+
 	private function getCreationTime( RevisionRecord $revision ): string {
 		$time = $this->revisionStore->getFirstRevision( $revision->getPage() )?->getTimestamp();
 
@@ -72,19 +84,4 @@ private function getModificationTime( RevisionRecord $revision ): string {
 		return $time;
 	}
 
-	/**
-	 * @return string[]
-	 */
-	private function getCategories( RevisionRecord $revision ): array {
-		$content = $revision->getContent( SlotRecord::MAIN );
-
-		if ( $content === null ) {
-			return [];
-		}
-
-		return $this->contentHandlerFactory->getContentHandler( $content->getModel() )
-			->getParserOutput( $content, new ContentParseParams( $revision->getPage() ) )
-			->getCategoryNames();
-	}
-
 }

tests/phpunit/PagePropertiesBuilderTest.php

@@ -0,0 +1,66 @@
+<?php
+
+declare( strict_types = 1 );
+
+namespace ProfessionalWiki\NeoWiki\Tests;
+
+use ProfessionalWiki\NeoWiki\Domain\Page\PagePropertyProviderContext;
+use ProfessionalWiki\NeoWiki\Domain\Page\PagePropertyProviderRegistry;
+use ProfessionalWiki\NeoWiki\PagePropertiesBuilder;
+use ProfessionalWiki\NeoWiki\Tests\TestDoubles\SpyPagePropertyProvider;
+
+/**
+ * @covers \ProfessionalWiki\NeoWiki\PagePropertiesBuilder
+ * @group Database
+ */
+class PagePropertiesBuilderTest extends NeoWikiIntegrationTestCase {
+
+	public function testProviderReceivesContent(): void {
+		$context = $this->getContextForNewPageWithContent( 'Some text [[Category:Cats]]' );
+
+		$this->assertSame( 'Some text [[Category:Cats]]', $context->content );
+	}
+
+	public function testProviderReceivesContentModel(): void {
+		$context = $this->getContextForNewPageWithContent( 'Whatever wikitext' );
+
+		$this->assertSame( CONTENT_MODEL_WIKITEXT, $context->contentModel );
+	}
+
+	public function testProviderReceivesParserRecordedProperties(): void {
+		$context = $this->getContextForNewPageWithContent( 'Sorted {{DEFAULTSORT:Zebra}}' );
+
+		$this->assertSame( 'Zebra', $context->parserProperties['defaultsort'] );
+	}
+
+	public function testProviderReceivesCategoriesFromParsedContent(): void {
+		$context = $this->getContextForNewPageWithContent( 'Some text [[Category:Cats]]' );
+
+		$this->assertSame( [ 'Cats' ], $context->categories );
+	}
+
+	private function getContextForNewPageWithContent( string $wikitext ): PagePropertyProviderContext {
+		$revision = $this->editPage( 'PagePropertiesBuilderTestPage', $wikitext )->getNewRevision();
+
+		$spy = new SpyPagePropertyProvider();
+
+		$this->newPagePropertiesBuilder( $spy )->getPagePropertiesFor( $revision, null );
+
+		return $spy->getReceivedContext();
+	}
+
+	private function newPagePropertiesBuilder( SpyPagePropertyProvider $provider ): PagePropertiesBuilder {
+		$registry = new PagePropertyProviderRegistry();
+		$registry->addProvider( $provider );
+
+		$services = $this->getServiceContainer();
+
+		return new PagePropertiesBuilder(
+			revisionStore: $services->getRevisionStore(),
+			contentHandlerFactory: $services->getContentHandlerFactory(),
+			titleFormatter: $services->getTitleFormatter(),
+			providerRegistry: $registry,
+		);
+	}
+
+}

tests/phpunit/Persistence/CorePagePropertyProviderTest.php

@@ -82,6 +82,9 @@ private function getPropertiesForContext(
 				modificationTime: $modificationTime,
 				categories: $categories,
 				lastEditor: $lastEditor,
+				content: 'Whatever content',
+				contentModel: 'wikitext',
+				parserProperties: [],
 			)
 		);
 	}

tests/phpunit/TestDoubles/SpyPagePropertyProvider.php

@@ -0,0 +1,27 @@
+<?php
+
+declare( strict_types = 1 );
+
+namespace ProfessionalWiki\NeoWiki\Tests\TestDoubles;
+
+use ProfessionalWiki\NeoWiki\Domain\Page\PagePropertyProvider;
+use ProfessionalWiki\NeoWiki\Domain\Page\PagePropertyProviderContext;
+
+class SpyPagePropertyProvider implements PagePropertyProvider {
+
+	private ?PagePropertyProviderContext $receivedContext = null;
+
+	public function getProperties( PagePropertyProviderContext $context ): array {
+		$this->receivedContext = $context;
+		return [];
+	}
+
+	public function getReceivedContext(): PagePropertyProviderContext {
+		if ( $this->receivedContext === null ) {
+			throw new \LogicException( 'getProperties was not called' );
+		}
+
+		return $this->receivedContext;
+	}
+
+}