From db4f1dac314365a172da038aa2cfd5e0cead2bd9 Mon Sep 17 00:00:00 2001
From: xiarixiaoyao <mengtao0326@qq.com>
Date: Wed, 19 Oct 2022 10:55:41 +0800
Subject: [PATCH] fixed the bug, string should convert to utf8 for avro record

---
 .../org/apache/hudi/hadoop/utils/HiveAvroSerializer.java     | 5 +++--
 1 file changed, 3 insertions(+), 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
index 15781edb26aeb..ff17fd10fc7fa 100644
--- 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: