From b342d5c7b883b620ee4b1929926dd0ffca391d3b Mon Sep 17 00:00:00 2001
From: dmsnell <dmsnell@git.wordpress.org>
Date: Tue, 6 Feb 2024 19:23:13 +0000
Subject: [PATCH] HTML API: Join text nodes on invalid-tag-name boundaries.

A fix was introduced to the Tag Processor to ensure that contiguous text
in an HTML document emerges as a single text node spanning the full
sequence. Unfortunately, that patch was marginally over-zealous in
checking if a "<" started a syntax token or not. It used the following:

{{{
<?php
if ( 'A' <= $c && 'z' >= $c ) { ... }
}}}

This was based on the assumption that the A-Z and a-z letters are
contiguous in the ASCII range; they aren't, and there's a gap of
several characters in between. The result of this is that in some
cases the parser created a text boundary when it didn't need to.
Text boundaries can be surprising and can be created when reaching
invalid syntax, HTML comments, and more hidden elements, so
semantically this wasn't a major bug, but it was an aesthetic
challenge.

In this patch the check is properly compared for both upper- and
lower-case variants that could potentially form tag names.

{{{
<?php
if ( ( 'A' <= $c && 'Z' >= $c ) || ( 'a' <= $c && 'z' >= $c ) ) { ... }
}}}

This solves the problem and ensures that contiguous text appears
as a single text node when scanning tokens.

Developed in https://github.com/WordPress/wordpress-develop/pull/6041
Discussed in https://core.trac.wordpress.org/ticket/60385

Follow-up to [57489]
Props dmsnell, jonsurrell
Fixes #60385


Built from https://develop.svn.wordpress.org/trunk@57542


git-svn-id: http://core.svn.wordpress.org/trunk@57043 1a063a9b-81f0-0310-95a4-ce76da25c4cd
---
 .../html-api/class-wp-html-tag-processor.php   | 18 ++++++++++++------
 wp-includes/version.php                        |  2 +-
 2 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/wp-includes/html-api/class-wp-html-tag-processor.php b/wp-includes/html-api/class-wp-html-tag-processor.php
index b437595bd9..447f4dac1b 100644
--- a/wp-includes/html-api/class-wp-html-tag-processor.php
+++ b/wp-includes/html-api/class-wp-html-tag-processor.php
@@ -1528,20 +1528,26 @@ class WP_HTML_Tag_Processor {
 
 			if ( $at > $was_at ) {
 				/*
-				 * A "<" has been found in the document. That may be the start of another node, or
-				 * it may be an "ivalid-first-character-of-tag-name" error. If this is not the start
-				 * of another node the "<" should be included in this text node and another
-				 * termination point should be found for the text node.
+				 * A "<" normally starts a new HTML tag or syntax token, but in cases where the
+				 * following character can't produce a valid token, the "<" is instead treated
+				 * as plaintext and the parser should skip over it. This avoids a problem when
+				 * following earlier practices of typing emoji with text, e.g. "<3". This
+				 * should be a heart, not a tag. It's supposed to be rendered, not hidden.
+				 *
+				 * At this point the parser checks if this is one of those cases and if it is
+				 * will continue searching for the next "<" in search of a token boundary.
 				 *
 				 * @see https://html.spec.whatwg.org/#tag-open-state
 				 */
 				if ( strlen( $html ) > $at + 1 ) {
 					$next_character  = $html[ $at + 1 ];
-					$at_another_node =
+					$at_another_node = (
 						'!' === $next_character ||
 						'/' === $next_character ||
 						'?' === $next_character ||
-						( 'A' <= $next_character && $next_character <= 'z' );
+						( 'A' <= $next_character && $next_character <= 'Z' ) ||
+						( 'a' <= $next_character && $next_character <= 'z' )
+					);
 					if ( ! $at_another_node ) {
 						++$at;
 						continue;
diff --git a/wp-includes/version.php b/wp-includes/version.php
index 138d449087..1b722b937c 100644
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -16,7 +16,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '6.5-alpha-57541';
+$wp_version = '6.5-alpha-57542';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.