From 5a77aa959befc01327ecdc9f977767ab148db69f Mon Sep 17 00:00:00 2001
From: Subramanya Sastry <ssastry@wikimedia.org>
Date: Thu, 8 Jun 2023 19:26:38 +0530
Subject: [PATCH] ParsoidExtensionAPI: Add method to process HTML embedded in
 attributes

* Parsoid core cannot know anything about how extensions represent
  information in their DOM. We were missing an extension API method
  and config that lets extensions specify this information along with
  handlers to process embedded content.

* This patch fills that above gap.

* There is a FIXME in ContentUtils::shiftDSR which will be addressed
  in followup patches with this new functionality.

Change-Id: If921ca471f25f21671a60c3f796fdf145267364d
---
 src/Parsoid/Cite.php       |  8 +++++++-
 src/Parsoid/Ref.php        | 11 +++++++++++
 src/Parsoid/References.php | 11 +++++++++++
 3 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/src/Parsoid/Cite.php b/src/Parsoid/Cite.php
index d2045952c..94198dad2 100644
--- a/src/Parsoid/Cite.php
+++ b/src/Parsoid/Cite.php
@@ -22,7 +22,10 @@ class Cite implements ExtensionModule {
 					'name' => 'ref',
 					'handler' => Ref::class,
 					'options' => [
-						'wt2html' => [ 'unpackOutput' => false ],
+						'wt2html' => [
+							'unpackOutput' => false,
+							'embedsHTMLInAttributes' => true
+						],
 						'outputHasCoreMwDomSpecMarkup' => true
 					],
 				],
@@ -30,6 +33,9 @@ class Cite implements ExtensionModule {
 					'name' => 'references',
 					'handler' => References::class,
 					'options' => [
+						'wt2html' => [
+							'embedsHTMLInAttributes' => true
+						],
 						'html2wt' => [ 'format' => 'block' ],
 						'outputHasCoreMwDomSpecMarkup' => true
 					],
diff --git a/src/Parsoid/Ref.php b/src/Parsoid/Ref.php
index 8e36cd2f9..01c40b2af 100644
--- a/src/Parsoid/Ref.php
+++ b/src/Parsoid/Ref.php
@@ -3,6 +3,7 @@ declare( strict_types = 1 );
 
 namespace Wikimedia\Parsoid\Ext\Cite;
 
+use Closure;
 use Exception;
 use Wikimedia\Parsoid\DOM\DocumentFragment;
 use Wikimedia\Parsoid\DOM\Element;
@@ -54,6 +55,16 @@ class Ref extends ExtensionTagHandler {
 		);
 	}
 
+	/** @inheritDoc */
+	public function processAttributeEmbeddedHTML(
+		ParsoidExtensionAPI $extApi, Element $elt, Closure $proc
+	): void {
+		$dataMw = DOMDataUtils::getDataMw( $elt );
+		if ( isset( $dataMw->body->html ) ) {
+			$dataMw->body->html = $proc( $dataMw->body->html );
+		}
+	}
+
 	/** @inheritDoc */
 	public function lintHandler(
 		ParsoidExtensionAPI $extApi, Element $ref, callable $defaultHandler
diff --git a/src/Parsoid/References.php b/src/Parsoid/References.php
index 28a2307e6..e39be4430 100644
--- a/src/Parsoid/References.php
+++ b/src/Parsoid/References.php
@@ -3,6 +3,7 @@ declare( strict_types = 1 );
 
 namespace Wikimedia\Parsoid\Ext\Cite;
 
+use Closure;
 use stdClass;
 use Wikimedia\Parsoid\Core\DomSourceRange;
 use Wikimedia\Parsoid\DOM\DocumentFragment;
@@ -795,6 +796,16 @@ class References extends ExtensionTagHandler {
 		return $domFragment;
 	}
 
+	/** @inheritDoc */
+	public function processAttributeEmbeddedHTML(
+		ParsoidExtensionAPI $extApi, Element $elt, Closure $proc
+	): void {
+		$dataMw = DOMDataUtils::getDataMw( $elt );
+		if ( isset( $dataMw->body->html ) ) {
+			$dataMw->body->html = $proc( $dataMw->body->html );
+		}
+	}
+
 	/** @inheritDoc */
 	public function domToWikitext(
 		ParsoidExtensionAPI $extApi, Element $node, bool $wrapperUnmodified