General: Provide _is_utf8_charset() in compat.php for early use

#61182 introduced is_utf8_charset() as a way of standardizing checks for charset slugs referring to UTF-8. This is called by _mb_strlen() inside of compat.php, but is_utf8_charset() is defined in functions.php, which isn't loaded early on. Code calling mb_strlen() early on before functions.php loads in hosts without the multibyte extension therefore may crash.

Props dmsnell, jonsurrell, joemcgill, jorbin.
Fixes #61681.


git-svn-id: https://develop.svn.wordpress.org/trunk@58763 602fd350-edb4-49c9-b593-d223f7449a82

src/wp-includes/compat.php

@@ -40,6 +40,43 @@ function _wp_can_use_pcre_u( $set = null ) {
 	return $utf8_pcre;
 }
 
+/**
+ * Indicates if a given slug for a character set represents the UTF-8 text encoding.
+ *
+ * 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' ] );
+ *
+ * `is_utf8_charset` should be used outside of this file.
+ *
+ * @ignore
+ * @since 6.6.1
+ *
+ * @param string $charset_slug 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( $charset_slug ) {
+	if ( ! is_string( $charset_slug ) ) {
+		return false;
+	}
+
+	return (
+		0 === strcasecmp( 'UTF-8', $charset_slug ) ||
+		0 === strcasecmp( 'UTF8', $charset_slug )
+	);
+}
+
 if ( ! function_exists( 'mb_substr' ) ) :
 	/**
 	 * Compat function to mimic mb_substr().
@@ -91,7 +128,7 @@ function _mb_substr( $str, $start, $length = null, $encoding = null ) {
 	 * The solution below works only for UTF-8, so in case of a different
 	 * charset just use built-in substr().
 	 */
-	if ( ! is_utf8_charset( $encoding ) ) {
+	if ( ! _is_utf8_charset( $encoding ) ) {
 		return is_null( $length ) ? substr( $str, $start ) : substr( $str, $start, $length );
 	}
 
@@ -176,7 +213,7 @@ function _mb_strlen( $str, $encoding = null ) {
 	 * The solution below works only for UTF-8, so in case of a different charset
 	 * just use built-in strlen().
 	 */
-	if ( ! is_utf8_charset( $encoding ) ) {
+	if ( ! _is_utf8_charset( $encoding ) ) {
 		return strlen( $str );
 	}
 

src/wp-includes/functions.php

@@ -7496,27 +7496,17 @@ function get_tag_regex( $tag ) {
  *     $is_utf8 = is_utf8_charset();
  *
  * @since 6.6.0
+ * @since 6.6.1 A wrapper for _is_utf8_charset
+ *
+ * @see _is_utf8_charset
  *
  * @param string|null $blog_charset Optional. Slug representing a text character encoding, or "charset".
  *                                  E.g. "UTF-8", "Windows-1252", "ISO-8859-1", "SJIS".
  *                                  Default value is to infer from "blog_charset" option.
  * @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 )
-	);
+	return _is_utf8_charset( $blog_charset ?? get_option( 'blog_charset' ) );
 }
 
 /**