Use RFC3066 instead of the obsoleted RFC1766

Author: tvdijen

src/XML/Assert/LanguageTrait.php

@@ -11,7 +11,26 @@
  */
 trait LanguageTrait
 {
-    private static string $language_regex = '/^([a-z]{2}|[i]-[a-z]+|[x]-[a-z]{1,8})(-[a-z]{1,8})*$/Di';
+    /**
+     * BCP 47 language tag validator (RFC 5646)
+     * - Full syntax validation including grandfathered and private-use tags
+     * - Named capture groups for easy subtag extraction
+     * - 'x' flag + comments + whitespace for maximum readability
+     * - Case-insensitive (/i)
+     */
+    private static string $language_regex = '/^
+        (?:
+            (
+                en-GB-oed|i-ami|i-bnn|i-default|i-enochian|i-hak|i-klingon|i-lux
+                |i-mingo|i-navajo|i-pwn|i-tao|i-tay|i-tsu|sgn-BE-FR|sgn-BE-NL|sgn-CH-DE
+            )
+            |(art-lojban|cel-gaulish|no-bok|no-nyn|zh-guoyu|zh-hakka|zh-min|zh-min-nan|zh-xiang)
+        )$
+        |^((?:[a-z]{2,3}(?:(?:-[a-z]{3}){1,3})?)|[a-z]{4}|[a-z]{5,8})(?:-([a-z]{4}))?(?:-([a-z]{2}|\d{3}))
+          ?((?:-(?:[\da-z]{5,8}|\d[\da-z]{3}))*)
+          ?((?:-[\da-wy-z](?:-[\da-z]{2,8})+)*)
+          ?(-x(?:-[\da-z]{1,8})+)?$
+        |^(x(?:-[\da-z]{1,8})+)$/mxi';
 
 
     /**

tests/XML/Assert/LanguageTest.php

@@ -43,9 +43,10 @@ public static function provideValidLanguage(): array
         return [
             'one part' => [true, 'es'],
             'two parts' => [true, 'en-US'],
-            'many parts' => [true, 'es-this-goes-on-forever'],
-            'x-case' => [true, 'x-klingon'],
-            'i-case' => [true, 'i-sami-no'],
+            'many parts' => [true, 'tlh-Kore-AQ-fonipa'],
+            'three-letter primary code' => [true, 'nso'],
+            'x-case' => [true, 'x-my-custom-language'],
+            'i-case' => [true, 'i-klingon'],
         ];
     }
 
@@ -59,6 +60,7 @@ public static function provideInvalidLanguage(): array
             'empty string' => [false, ''],
             'whitespace' => [false, 'en- us'],
             'too long' => [false, 'toolongLanguageCode'],
+            'not-grandfathered' => [false, 'i-sami-no'],
         ];
     }
 }