From 9840f032815c0f427ae729a02d038cd5b0d2c919 Mon Sep 17 00:00:00 2001
From: Carlos Bravo <cbravobernal@git.wordpress.org>
Date: Wed, 27 Nov 2024 09:55:53 +0000
Subject: [PATCH] HTML API: Recognize all uppercase tag names in tag processor.

Fixes a missing "D" in the character list used by strspn to find tag openers, causing tags starting with D to be skipped by the tag processor in some circumstances.

Follow-up to [58613].

Props jonsurrell, santosguillamot, wongjn, cbravobernal.
Fixes #62522.


git-svn-id: https://develop.svn.wordpress.org/trunk@59464 602fd350-edb4-49c9-b593-d223f7449a82
---
 .../html-api/class-wp-html-tag-processor.php  |  2 +-
 .../tests/html-api/wpHtmlTagProcessor.php     | 62 +++++++++++++++++++
 2 files changed, 63 insertions(+), 1 deletion(-)

diff --git a/src/wp-includes/html-api/class-wp-html-tag-processor.php b/src/wp-includes/html-api/class-wp-html-tag-processor.php
index e2632c80f6da5..39390621e86a6 100644
--- a/src/wp-includes/html-api/class-wp-html-tag-processor.php
+++ b/src/wp-includes/html-api/class-wp-html-tag-processor.php
@@ -1668,7 +1668,7 @@ private function parse_next_tag(): bool {
 				 *
 				 * @see https://html.spec.whatwg.org/#tag-open-state
 				 */
-				if ( 1 !== strspn( $html, '!/?abcdefghijklmnopqrstuvwxyzABCEFGHIJKLMNOPQRSTUVWXYZ', $at + 1, 1 ) ) {
+				if ( 1 !== strspn( $html, '!/?abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ', $at + 1, 1 ) ) {
 					++$at;
 					continue;
 				}
diff --git a/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php b/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php
index 393fd2cda06db..cd8faee4ed6a4 100644
--- a/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php
+++ b/tests/phpunit/tests/html-api/wpHtmlTagProcessor.php
@@ -2984,4 +2984,66 @@ public function test_doctype_doc_name() {
 		$this->assertNull( $doctype->public_identifier );
 		$this->assertNull( $doctype->system_identifier );
 	}
+
+	/**
+	 * @ticket 62522
+	 *
+	 * @dataProvider data_alphabet_by_characters_lowercase
+	 */
+	public function test_recognizes_lowercase_tag_name( string $char ) {
+		/*
+		 * The spacing in the HTML string is important to the problematic
+		 * codepath in ticket #62522.
+		 */
+		$html      = " <{$char}> </{$char}>";
+		$processor = new WP_HTML_Tag_Processor( $html );
+		$this->assertTrue( $processor->next_tag(), "Failed to find open tag in '{$html}'." );
+		$this->assertTrue(
+			$processor->next_tag( array( 'tag_closers' => 'visit' ) ),
+			"Failed to find close tag in '{$html}'."
+		);
+	}
+
+	/**
+	 * @ticket 62522
+	 *
+	 * @dataProvider data_alphabet_by_characters_uppercase
+	 */
+	public function test_recognizes_uppercase_tag_name( string $char ) {
+		/*
+		 * The spacing in the HTML string is important to the problematic
+		 * codepath in ticket #62522.
+		 */
+		$html      = " <{$char}> </{$char}>";
+		$processor = new WP_HTML_Tag_Processor( $html );
+		$this->assertTrue( $processor->next_tag(), "Failed to find open tag in '{$html}'." );
+		$this->assertTrue(
+			$processor->next_tag( array( 'tag_closers' => 'visit' ) ),
+			"Failed to find close tag in '{$html}'."
+		);
+	}
+
+	/**
+	 * Data provider.
+	 *
+	 * @return Generator<array>
+	 */
+	public static function data_alphabet_by_characters_lowercase() {
+		$char = 'a';
+		while ( $char <= 'z' ) {
+			yield $char => array( $char );
+			$char = chr( ord( $char ) + 1 );
+		}
+	}
+
+	/**
+	 * Data provider.
+	 *
+	 * @return Generator<array>
+	 */
+	public static function data_alphabet_by_characters_uppercase() {
+		foreach ( self::data_alphabet_by_characters_lowercase() as $data ) {
+			yield strtoupper( $data[0] ) => array( strtoupper( $data[0] ) );
+		}
+	}
 }