From b21189e96f0b7f6fd4839a6a8dc0dcf856472690 Mon Sep 17 00:00:00 2001
From: jonsurrell <jonsurrell@git.wordpress.org>
Date: Wed, 2 Jul 2025 12:35:28 +0000
Subject: [PATCH] Docs: Expand valid_unicode function documentation.

The `valid_unicode()` function accepts a limited set of codepoints according to the XML specification. Document the allowed codepoints and link to relevant documentation.

Developed in https://github.com/WordPress/wordpress-develop/pull/9100.

Props jonsurrell, dmsnell.
See #6583, #63166.

Built from https://develop.svn.wordpress.org/trunk@60405


git-svn-id: http://core.svn.wordpress.org/trunk@59741 1a063a9b-81f0-0310-95a4-ce76da25c4cd
---
 wp-includes/kses.php    | 28 ++++++++++++++++++++++++----
 wp-includes/version.php |  2 +-
 2 files changed, 25 insertions(+), 5 deletions(-)

diff --git a/wp-includes/kses.php b/wp-includes/kses.php
index ebb4a761b1..28bbce222a 100644
--- a/wp-includes/kses.php
+++ b/wp-includes/kses.php
@@ -2083,18 +2083,38 @@ function wp_kses_normalize_entities3( $matches ) {
 /**
  * Determines if a Unicode codepoint is valid.
  *
+ * The definition of a valid Unicode codepoint is taken from the XML definition:
+ *
+ * > Characters
+ * >
+ * > …
+ * > Legal characters are tab, carriage return, line feed, and the legal characters of
+ * > Unicode and ISO/IEC 10646.
+ * > …
+ * > Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
+ *
  * @since 2.7.0
  *
+ * @see https://www.w3.org/TR/xml/#charsets
+ *
  * @param int $i Unicode codepoint.
  * @return bool Whether or not the codepoint is a valid Unicode codepoint.
  */
 function valid_unicode( $i ) {
 	$i = (int) $i;
 
-	return ( 0x9 === $i || 0xa === $i || 0xd === $i ||
-		( 0x20 <= $i && $i <= 0xd7ff ) ||
-		( 0xe000 <= $i && $i <= 0xfffd ) ||
-		( 0x10000 <= $i && $i <= 0x10ffff )
+	return (
+		0x9 === $i || // U+0009 HORIZONTAL TABULATION (HT)
+		0xA === $i || // U+000A LINE FEED (LF)
+		0xD === $i || // U+000D CARRIAGE RETURN (CR)
+		/*
+		 * The valid Unicode characters according to the XML specification:
+		 *
+		 * > any Unicode character, excluding the surrogate blocks, FFFE, and FFFF.
+		 */
+		( 0x20 <= $i && $i <= 0xD7FF ) ||
+		( 0xE000 <= $i && $i <= 0xFFFD ) ||
+		( 0x10000 <= $i && $i <= 0x10FFFF )
 	);
 }
 
diff --git a/wp-includes/version.php b/wp-includes/version.php
index 2e6b386391..9bf424bfdc 100644
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -16,7 +16,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '6.9-alpha-60404';
+$wp_version = '6.9-alpha-60405';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.