Merge branch 'master' into alter-lcase-vol3

common/unsafe/src/main/java/org/apache/spark/sql/catalyst/util/CollationAwareUTF8String.java

@@ -482,6 +482,7 @@ public static int findInSet(final UTF8String match, final UTF8String set, int co
       byteIndex += UTF8String.numBytesForFirstByte(nextByte);
       ++charIndex;
     }
+    // TODO(SPARK-48715): All UTF8String -> String conversions should use `makeValid`
     if (set.substring(lastComma + 1, set.numBytes()).semanticEquals(match, collationId)) {
       return wordCount;
     }