Better sizing BytesRefs for Strings in Queries

piergm · Oct 25, 2024 · 3a56144 · 3a56144
1 parent 6e0bdbe
commit 3a56144
Showing 1 changed file with 7 additions and 6 deletions.
diff --git a/server/src/main/java/org/elasticsearch/index/query/AbstractQueryBuilder.java b/server/src/main/java/org/elasticsearch/index/query/AbstractQueryBuilder.java
@@ -14,6 +14,7 @@
 import org.apache.lucene.search.NamedMatches;
 import org.apache.lucene.search.Query;
 import org.apache.lucene.util.BytesRef;
+import org.apache.lucene.util.UnicodeUtil;
 import org.elasticsearch.common.ParsingException;
 import org.elasticsearch.common.Strings;
 import org.elasticsearch.common.io.stream.StreamInput;
@@ -216,12 +217,12 @@ public final int hashCode() {
      * @return the same input object or a {@link BytesRef} representation if input was of type string
      */
     static Object maybeConvertToBytesRef(Object obj) {
-        if (obj instanceof String) {
-            return BytesRefs.checkIndexableLength(BytesRefs.toBytesRef(obj));
-        } else if (obj instanceof CharBuffer) {
-            return BytesRefs.checkIndexableLength(new BytesRef((CharBuffer) obj));
-        } else if (obj instanceof BigInteger) {
-            return BytesRefs.toBytesRef(obj);
+        if (obj instanceof String v) {
+            return BytesRefs.checkIndexableLength(new BytesRef(new byte[UnicodeUtil.calcUTF16toUTF8Length(v, 0, v.length())]));
+        } else if (obj instanceof CharBuffer v) {
+            return BytesRefs.checkIndexableLength(new BytesRef(v));
+        } else if (obj instanceof BigInteger v) {
+            return BytesRefs.toBytesRef(v);
         }
         return obj;
     }