From e82c663564bfe73c705ada1c28bc21da6ff138cc Mon Sep 17 00:00:00 2001
From: Tobias Bachert <git@b-privat.de>
Date: Wed, 13 Mar 2024 23:30:50 +0100
Subject: [PATCH] Fix conversion of non-utf8 sequences to `AnyValue` (#1253)

String values which are not valid Unicode sequences SHOULD be converted to AnyValue's bytes_value with the bytes representing the string in the original order and format of the source string.
---
 AttributesConverter.php | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/AttributesConverter.php b/AttributesConverter.php
index 4a349ab..bca663f 100644
--- a/AttributesConverter.php
+++ b/AttributesConverter.php
@@ -46,12 +46,23 @@ public static function convertAnyValue($value): AnyValue
             $result->setDoubleValue($value);
         }
         if (is_string($value)) {
-            $result->setStringValue($value);
+            if (self::isUtf8($value)) {
+                $result->setStringValue($value);
+            } else {
+                $result->setBytesValue($value);
+            }
         }
 
         return $result;
     }
 
+    private static function isUtf8(string $value): bool
+    {
+        return \extension_loaded('mbstring')
+            ? \mb_check_encoding($value, 'UTF-8')
+            : (bool) \preg_match('//u', $value);
+    }
+
     /**
      * Test whether an array is simple (non-KeyValue)
      */