From 06a25caf2327bd875a78941c79f4847c2779fce8 Mon Sep 17 00:00:00 2001
From: dmsnell <dmsnell@git.wordpress.org>
Date: Tue, 14 May 2024 18:07:07 +0000
Subject: [PATCH] Quick-fix: Normalize UTF-8 charset slug detection.

In the merge of [58417] the new file was missed. This commit adds the missing required file.

Developed in https://github.com/WordPress/wordpress-develop/pull/6535
Discussed in https://core.trac.wordpress.org/ticket/61182

Fixes #61182.
Follow-up to [58147].
Props dmsnell, jonsurrell.

Built from https://develop.svn.wordpress.org/trunk@58148


git-svn-id: http://core.svn.wordpress.org/trunk@57613 1a063a9b-81f0-0310-95a4-ce76da25c4cd
---
 wp-includes/unicode.php | 51 +++++++++++++++++++++++++++++++++++++++++
 wp-includes/version.php |  2 +-
 2 files changed, 52 insertions(+), 1 deletion(-)
 create mode 100644 wp-includes/unicode.php

diff --git a/wp-includes/unicode.php b/wp-includes/unicode.php
new file mode 100644
index 0000000000..5348e49789
--- /dev/null
+++ b/wp-includes/unicode.php
@@ -0,0 +1,51 @@
+<?php
+/**
+ * WordPress API providing Unicode-relevant utilities.
+ *
+ * @since 6.6.0
+ *
+ * @package WordPress
+ */
+
+/**
+ * Indicates if a given slug for a character set represents the UTF-8
+ * text encoding. If not provided, examines the current blog's charset.
+ *
+ * A charset is considered to represent UTF-8 if it is a case-insensitive
+ * match of "UTF-8" with or without the hyphen.
+ *
+ * Example:
+ *
+ *     true  === is_utf8_charset( 'UTF-8' );
+ *     true  === is_utf8_charset( 'utf8' );
+ *     false === is_utf8_charset( 'latin1' );
+ *     false === is_utf8_charset( 'UTF 8' );
+ *
+ *     // Only strings match.
+ *     false === is_utf8_charset( [ 'charset' => 'utf-8' ] );
+ *
+ *     // Without a given charset, it depends on the site option "blog_charset".
+ *     $is_utf8 = is_utf8_charset();
+ *
+ * @since 6.6.0
+ *
+ * @param ?string $blog_charset Slug representing a text character encoding, or "charset".
+ *                              E.g. "UTF-8", "Windows-1252", "ISO-8859-1", "SJIS".
+ * @return bool Whether the slug represents the UTF-8 encoding.
+ */
+function is_utf8_charset( $blog_charset = null ) {
+	$charset_to_examine = $blog_charset ?? get_option( 'blog_charset' );
+
+	/*
+	 * Only valid string values count: the absence of a charset
+	 * does not imply any charset, let alone UTF-8.
+	 */
+	if ( ! is_string( $charset_to_examine ) ) {
+		return false;
+	}
+
+	return (
+		0 === strcasecmp( 'UTF-8', $charset_to_examine ) ||
+		0 === strcasecmp( 'UTF8', $charset_to_examine )
+	);
+}
diff --git a/wp-includes/version.php b/wp-includes/version.php
index 418dcc4f9a..7cfdf0a6d0 100644
--- a/wp-includes/version.php
+++ b/wp-includes/version.php
@@ -16,7 +16,7 @@
  *
  * @global string $wp_version
  */
-$wp_version = '6.6-alpha-58147';
+$wp_version = '6.6-alpha-58148';
 
 /**
  * Holds the WordPress DB revision, increments when changes are made to the WordPress DB schema.