From 81ef71d605a9027f95f976d243a1cab3dd3ea091 Mon Sep 17 00:00:00 2001
From: Dennis Snell <dennis.snell@automattic.com>
Date: Thu, 19 Oct 2023 15:08:44 -0500
Subject: [PATCH] WIP: HTML API: Add support for H1-H6 elements in HTML
 Processor

---
 src/wp-config.local.php                       | 107 ++++++++++++++++++
 .../html-api/class-wp-html-open-elements.php  |  30 ++++-
 .../html-api/class-wp-html-processor.php      |  59 ++++++++++
 .../tests/html-api/wpHtmlProcessor.php        |   2 -
 .../html-api/wpHtmlProcessorBreadcrumbs.php   |  12 +-
 .../html-api/wpHtmlProcessorSemanticRules.php |  48 +++++---
 6 files changed, 234 insertions(+), 24 deletions(-)
 create mode 100644 src/wp-config.local.php

diff --git a/src/wp-config.local.php b/src/wp-config.local.php
new file mode 100644
index 0000000000000..be204dccf65de
--- /dev/null
+++ b/src/wp-config.local.php
@@ -0,0 +1,107 @@
+<?php
+/**
+ * The base configuration for WordPress
+ *
+ * The wp-config.php creation script uses this file during the installation.
+ * You don't have to use the web site, you can copy this file to "wp-config.php"
+ * and fill in the values.
+ *
+ * This file contains the following configurations:
+ *
+ * * Database settings
+ * * Secret keys
+ * * Database table prefix
+ * * Localized language
+ * * ABSPATH
+ *
+ * @link https://wordpress.org/support/article/editing-wp-config-php/
+ *
+ * @package WordPress
+ */
+
+// ** Database settings - You can get this info from your web host ** //
+/** The name of the database for WordPress */
+define( 'DB_NAME', 'wordpress' );
+
+/** Database username */
+define( 'DB_USER', 'wpuser' );
+
+/** Database password */
+define( 'DB_PASSWORD', 'wpuser' );
+
+/** Database hostname */
+define( 'DB_HOST', 'localhost' );
+
+/** Database charset to use in creating database tables. */
+define( 'DB_CHARSET', 'utf8' );
+
+/** The database collate type. Don't change this if in doubt. */
+define( 'DB_COLLATE', '' );
+
+/**#@+
+ * Authentication unique keys and salts.
+ *
+ * Change these to different unique phrases! You can generate these using
+ * the {@link https://api.wordpress.org/secret-key/1.1/salt/ WordPress.org secret-key service}.
+ *
+ * You can change these at any point in time to invalidate all existing cookies.
+ * This will force all users to have to log in again.
+ *
+ * @since 2.6.0
+ */
+define( 'AUTH_KEY',          'MFk^p/>nn@&%|l0flI6:VON4WelK EeRqf)a&EbFfG8@ ]R} )D`N12^th4_{TNi' );
+define( 'SECURE_AUTH_KEY',   'qD9}:B2$6*w7.{;!pZk]]D?y=D[zz#lpqm4c&+j049^v</e* <RsC=g|z_3#dfz/' );
+define( 'LOGGED_IN_KEY',     '@ cguVQ){hG;:44OKIkU>BVf8 Y]IxSA+2x%n<xSO;vXchw3B*{t_7t9.<02/eaE' );
+define( 'NONCE_KEY',         'N@B>H_[KqJk|nbOyBKF}Ir[VF8`qC Zk+g_$C1XL@C|WMRv*Q<4R,]f6Lbu_)#ml' );
+define( 'AUTH_SALT',         '^o|a:{J &rTHA?qheBwZE?;2xh&P_S{D:nxI!/|+@n[z-C^z*rr,fxhg *,&7vrB' );
+define( 'SECURE_AUTH_SALT',  'fhk&Z4_rl|=U,kC!pMlJz@afe#]uRH>:I6k>Q bcz/3E9TV`JEyN.Rk)baXDJM&8' );
+define( 'LOGGED_IN_SALT',    'w2Dl23NuZNJU<9+ -8F{l%eZAjXN,D,8=k#<x]qD]i:<iZ%5eXw2!minSwH[HeR<' );
+define( 'NONCE_SALT',        '2!<_+:wZY-u}n/3LKW2WQ@/jbznNOp{AQ*W({%v1lK4vUh| 9KBPERun/iWrfp$b' );
+define( 'WP_CACHE_KEY_SALT', ')5>>.k$IuAf/ZtoryWohrIgGRpiv{t<?sg~lLJZu)|+4h(Cu3FBY:E7gl}PPw|/3' );
+
+
+/**#@-*/
+
+/**
+ * WordPress database table prefix.
+ *
+ * You can have multiple installations in one database if you give each
+ * a unique prefix. Only numbers, letters, and underscores please!
+ */
+$table_prefix = 'wp_';
+
+
+/* Add any custom values between this line and the "stop editing" line. */
+
+
+
+/**
+ * For developers: WordPress debugging mode.
+ *
+ * Change this to true to enable the display of notices during development.
+ * It is strongly recommended that plugin and theme developers use WP_DEBUG
+ * in their development environments.
+ *
+ * For information on other constants that can be used for debugging,
+ * visit the documentation.
+ *
+ * @link https://wordpress.org/support/article/debugging-in-wordpress/
+ */
+if ( ! defined( 'WP_DEBUG' ) ) {
+	define( 'WP_DEBUG', true );
+}
+
+define( 'WP_DEBUG_LOG', true );
+define( 'WP_DEBUG_DISPLAY', true );
+define( 'SCRIPT_DEBUG', true );
+define( 'WP_ENVIRONMENT_TYPE', 'local' );
+define( 'WP_DEVELOPMENT_MODE', 'core' );
+/* That's all, stop editing! Happy publishing. */
+
+/** Absolute path to the WordPress directory. */
+if ( ! defined( 'ABSPATH' ) ) {
+	define( 'ABSPATH', __DIR__ . '/' );
+}
+
+/** Sets up WordPress vars and included files. */
+require_once ABSPATH . 'wp-settings.php';
diff --git a/src/wp-includes/html-api/class-wp-html-open-elements.php b/src/wp-includes/html-api/class-wp-html-open-elements.php
index fe5625545b0ac..8fb53e272cdf8 100644
--- a/src/wp-includes/html-api/class-wp-html-open-elements.php
+++ b/src/wp-includes/html-api/class-wp-html-open-elements.php
@@ -106,7 +106,7 @@ public function current_node() {
 	 *
 	 * @see https://html.spec.whatwg.org/#has-an-element-in-the-specific-scope
 	 *
-	 * @param string   $tag_name         Name of tag check.
+	 * @param string   $tag_name         Name of tag check, or the class constant HEADING_ELEMENTS to specify H1-H6.
 	 * @param string[] $termination_list List of elements that terminate the search.
 	 * @return bool Whether the element was found in a specific scope.
 	 */
@@ -116,6 +116,13 @@ public function has_element_in_specific_scope( $tag_name, $termination_list ) {
 				return true;
 			}
 
+			if (
+				self::HEADING_ELEMENTS === $tag_name &&
+				in_array( $node->node_name, array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ), true )
+			) {
+				return true;
+			}
+
 			switch ( $node->node_name ) {
 				case 'HTML':
 					return false;
@@ -263,13 +270,21 @@ public function pop() {
 	 *
 	 * @see WP_HTML_Open_Elements::pop
 	 *
-	 * @param string $tag_name Name of tag that needs to be popped off of the stack of open elements.
+	 * @param string $tag_name Name of tag that needs to be popped off of the stack of open elements,
+	 *                         or the class constant HEADING_ELEMENTS to specify any of H1-H6.
 	 * @return bool Whether a tag of the given name was found and popped off of the stack of open elements.
 	 */
 	public function pop_until( $tag_name ) {
 		foreach ( $this->walk_up() as $item ) {
 			$this->pop();
 
+			if (
+				self::HEADING_ELEMENTS === $tag_name &&
+				in_array( $item->node_name, array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ), true )
+			) {
+				return true;
+			}
+
 			if ( $tag_name === $item->node_name ) {
 				return true;
 			}
@@ -429,4 +444,15 @@ public function after_element_pop( $item ) {
 				break;
 		}
 	}
+
+	/**
+	 * Represents the collection of H1-H6 elements.
+	 *
+	 * @since 6.5.0
+	 *
+	 * @see has_element_in_scope()
+	 *
+	 * @var string
+	 */
+	const HEADING_ELEMENTS = 'heading-elements';
 }
diff --git a/src/wp-includes/html-api/class-wp-html-processor.php b/src/wp-includes/html-api/class-wp-html-processor.php
index f27f83b028cd2..9dd85228e1092 100644
--- a/src/wp-includes/html-api/class-wp-html-processor.php
+++ b/src/wp-includes/html-api/class-wp-html-processor.php
@@ -103,6 +103,7 @@
  *  - The formatting elements: B, BIG, CODE, EM, FONT, I, SMALL, STRIKE, STRONG, TT, U.
  *  - Containers: DIV, FIGCAPTION, FIGURE, SPAN.
  *  - Form elements: BUTTON.
+ *  - Heading elements: H1, H2, H3, H4, H5, H6.
  *  - Paragraph: P.
  *  - Void elements: IMG.
  *
@@ -657,6 +658,64 @@ private function step_in_body() {
 				$this->state->stack_of_open_elements->pop_until( $tag_name );
 				return true;
 
+			/*
+			 * > A start tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+			 */
+			case '+H1':
+			case '+H2':
+			case '+H3':
+			case '+H4':
+			case '+H5':
+			case '+H6':
+				if ( $this->state->stack_of_open_elements->has_p_in_button_scope() ) {
+					$this->close_a_p_element();
+				}
+
+				if (
+					in_array(
+						$this->state->stack_of_open_elements->current_node()->node_name,
+						array( 'H1', 'H2', 'H3', 'H4', 'H5', 'H6' ),
+						true
+					)
+				) {
+					// @TODO: Indicate a parse error once it's possible.
+					$this->state->stack_of_open_elements->pop();
+				}
+
+				$this->insert_html_element( $this->state->current_token );
+				return true;
+
+			/*
+			 * > An end tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
+			 */
+			case '-H1':
+			case '-H2':
+			case '-H3':
+			case '-H4':
+			case '-H5':
+			case '-H6':
+				if (
+					! $this->state->stack_of_open_elements->has_element_in_scope(
+						WP_HTML_Open_Elements::HEADING_ELEMENTS
+					)
+				) {
+					/*
+					 * This is a parse error; ignore the token.
+					 *
+					 * @TODO: Indicate a parse error once it's possible.
+					 */
+					return $this->step();
+				}
+
+				$this->generate_implied_end_tags();
+
+				if ( $this->state->stack_of_open_elements->current_node()->node_name !== $tag_name ) {
+					// @TODO: Record parse error: this error doesn't impact parsing.
+				}
+
+				$this->state->stack_of_open_elements->pop_until( WP_HTML_Open_Elements::HEADING_ELEMENTS );
+				return true;
+
 			/*
 			 * > An end tag whose tag name is "p"
 			 */
diff --git a/tests/phpunit/tests/html-api/wpHtmlProcessor.php b/tests/phpunit/tests/html-api/wpHtmlProcessor.php
index 37e3aa5de87fb..a9af5d790fc53 100644
--- a/tests/phpunit/tests/html-api/wpHtmlProcessor.php
+++ b/tests/phpunit/tests/html-api/wpHtmlProcessor.php
@@ -91,8 +91,6 @@ public function test_stops_processing_after_unsupported_elements() {
 	 *
 	 * @covers WP_HTML_Processor::next_tag
 	 * @covers WP_HTML_Processor::seek
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_clear_to_navigate_after_seeking() {
 		$p = WP_HTML_Processor::create_fragment( '<div one><strong></strong></div><p><strong two></strong></p>' );
diff --git a/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php b/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php
index d454ab4842fbf..c0a7bc46459d3 100644
--- a/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php
+++ b/tests/phpunit/tests/html-api/wpHtmlProcessorBreadcrumbs.php
@@ -46,6 +46,12 @@ public function data_single_tag_of_supported_elements() {
 			'FIGCAPTION',
 			'FIGURE',
 			'FONT',
+			'H1',
+			'H2',
+			'H3',
+			'H4',
+			'H5',
+			'H6',
 			'I',
 			'IMG',
 			'P',
@@ -133,12 +139,6 @@ public function data_unsupported_elements() {
 			'FORM',
 			'FRAME',
 			'FRAMESET',
-			'H1',
-			'H2',
-			'H3',
-			'H4',
-			'H5',
-			'H6',
 			'HEAD',
 			'HEADER',
 			'HGROUP',
diff --git a/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php b/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php
index 01bb41ba844f1..d9f8cb2eeb983 100644
--- a/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php
+++ b/tests/phpunit/tests/html-api/wpHtmlProcessorSemanticRules.php
@@ -21,10 +21,6 @@ class Tests_HtmlApi_WpHtmlProcessorSemanticRules extends WP_UnitTestCase {
 	 * element in scope, that it skips the tag entirely.
 	 *
 	 * @ticket 58961
-	 *
-	 * @since 6.4.0
-	 *
-	 * @throws Exception
 	 */
 	public function test_in_body_skips_unexpected_button_closer() {
 		$p = WP_HTML_Processor::create_fragment( '<div>Test</button></div>' );
@@ -46,10 +42,6 @@ public function test_in_body_skips_unexpected_button_closer() {
 	 * Verifies insertion of a BUTTON element when no existing BUTTON is already in scope.
 	 *
 	 * @ticket 58961
-	 *
-	 * @since 6.4.0
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_in_body_button_with_no_button_in_scope() {
 		$p = WP_HTML_Processor::create_fragment( '<div><p>Click the button <button one>here</button>!</p></div><button two>not here</button>' );
@@ -75,8 +67,6 @@ public function test_in_body_button_with_no_button_in_scope() {
 	 * @ticket 58961
 	 *
 	 * @since 6.4.0
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_in_body_button_with_button_in_scope_as_parent() {
 		$p = WP_HTML_Processor::create_fragment( '<div><p>Click the button <button one>almost<button two>here</button>!</p></div><button three>not here</button>' );
@@ -110,8 +100,6 @@ public function test_in_body_button_with_button_in_scope_as_parent() {
 	 * @ticket 58961
 	 *
 	 * @since 6.4.0
-	 *
-	 * @throws WP_HTML_Unsupported_Exception
 	 */
 	public function test_in_body_button_with_button_in_scope_as_ancestor() {
 		$p = WP_HTML_Processor::create_fragment( '<div><button one><p>Click the button <span><button two>here</button>!</span></p></div><button three>not here</button>' );
@@ -137,7 +125,39 @@ public function test_in_body_button_with_button_in_scope_as_ancestor() {
 		$this->assertSame( array( 'HTML', 'BODY', 'BUTTON' ), $p->get_breadcrumbs(), 'Failed to produce expected DOM nesting for third button.' );
 	}
 
-	/*
+	/**
+	 * Verifies that H1 through H6 elements close an open P element.
+	 *
+	 * @ticket {TICKET_NUMBER}
+	 *
+	 * @dataProvider data_heading_elements
+	 *
+	 * @param string $tag_name Name of H1 - H6 element under test.
+	 */
+	public function test_heading_element_closes_open_p_tag( $tag_name ) {
+		$p = WP_HTML_Processor::create_fragment( "<p>Open<{$tag_name}>Closed P</{$tag_name}></p>" );
+
+		$p->next_tag( $tag_name );
+		$this->assertSame( array( 'HTML', 'BODY', $tag_name ), $p->get_breadcrumbs() );
+	}
+
+	/**
+	 * Data provider.
+	 *
+	 * @return array[].
+	 */
+	public function data_heading_elements() {
+		return array(
+			array( 'H1' ),
+			array( 'H2' ),
+			array( 'H3' ),
+			array( 'H4' ),
+			array( 'H5' ),
+			array( 'H5' ),
+		);
+	}
+
+	/**
 	 * Verifies that when "in body" and encountering "any other end tag"
 	 * that the HTML processor ignores the end tag if there's a special
 	 * element on the stack of open elements before the matching opening.
@@ -160,7 +180,7 @@ public function test_in_body_any_other_end_tag_with_unclosed_special_element() {
 		$this->assertSame( array( 'HTML', 'BODY', 'DIV', 'SPAN', 'DIV' ), $p->get_breadcrumbs(), 'Failed to produce expected DOM nesting: SPAN should still be open and DIV should be its child.' );
 	}
 
-	/*
+	/**
 	 * Verifies that when "in body" and encountering "any other end tag"
 	 * that the HTML processor closes appropriate elements on the stack of
 	 * open elements up to the matching opening.