fixed the bug, string should convert to utf8 for avro record

apache · Oct 19, 2022 · db4f1da · db4f1da
1 parent 3bc9f04
commit db4f1da
Showing 1 changed file with 3 additions and 2 deletions.
diff --git a/hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/utils/HiveAvroSerializer.java b/hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/utils/HiveAvroSerializer.java
@@ -25,6 +25,7 @@
 import org.apache.avro.generic.GenericEnumSymbol;
 import org.apache.avro.generic.GenericRecord;
 import org.apache.avro.specific.SpecificRecordBase;
+import org.apache.avro.util.Utf8;
 import org.apache.hadoop.hive.common.type.HiveChar;
 import org.apache.hadoop.hive.common.type.HiveDecimal;
 import org.apache.hadoop.hive.common.type.HiveVarchar;
@@ -289,10 +290,10 @@ private Object serializePrimitive(PrimitiveObjectInspector fieldOI, Object struc
         return HoodieAvroUtils.DECIMAL_CONVERSION.toFixed(bd, schema, decimal);
       case CHAR:
         HiveChar ch = (HiveChar)fieldOI.getPrimitiveJavaObject(structFieldData);
-        return ch.getStrippedValue();
+        return new Utf8(ch.getStrippedValue());
       case VARCHAR:
         HiveVarchar vc = (HiveVarchar)fieldOI.getPrimitiveJavaObject(structFieldData);
-        return vc.getValue();
+        return new Utf8(vc.getValue());
       case DATE:
         return DateWritable.dateToDays(((DateObjectInspector)fieldOI).getPrimitiveJavaObject(structFieldData));
       case TIMESTAMP: