From 0b71db416c20b49bbbc94ee609f63a104f1e0946 Mon Sep 17 00:00:00 2001
From: Prabodh Agarwal <prabodh1194@gmail.com>
Date: Wed, 11 Sep 2024 23:24:06 +0530
Subject: [PATCH] pass the avro exception for better information

---
 .../scala/org/apache/hudi/AvroConversionUtils.scala    |  4 ++--
 .../org/apache/hudi/TestAvroConversionUtils.scala      | 10 ++++++++++
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/AvroConversionUtils.scala b/hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/AvroConversionUtils.scala
index cd75da3bb5da..a4d506be86e7 100644
--- a/hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/AvroConversionUtils.scala
+++ b/hudi-client/hudi-spark-client/src/main/scala/org/apache/hudi/AvroConversionUtils.scala
@@ -22,10 +22,9 @@ import org.apache.hudi.HoodieSparkUtils.sparkAdapter
 import org.apache.hudi.avro.AvroSchemaUtils
 import org.apache.hudi.exception.SchemaCompatibilityException
 import org.apache.hudi.internal.schema.HoodieSchemaException
-
 import org.apache.avro.Schema.Type
 import org.apache.avro.generic.GenericRecord
-import org.apache.avro.{JsonProperties, Schema}
+import org.apache.avro.{AvroRuntimeException, JsonProperties, Schema}
 import org.apache.spark.rdd.RDD
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.types.{ArrayType, DataType, MapType, StructType}
@@ -149,6 +148,7 @@ object AvroConversionUtils {
       val avroSchema = schemaConverters.toAvroType(structType, nullable = false, structName, recordNamespace)
       getAvroSchemaWithDefaults(avroSchema, structType)
     } catch {
+      case a: AvroRuntimeException => throw new HoodieSchemaException(a.getMessage, a)
       case e: Exception => throw new HoodieSchemaException("Failed to convert struct type to avro schema: " + structType, e)
     }
   }
diff --git a/hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestAvroConversionUtils.scala b/hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestAvroConversionUtils.scala
index 5cd6ac3954ee..fb2a050e1165 100644
--- a/hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestAvroConversionUtils.scala
+++ b/hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestAvroConversionUtils.scala
@@ -22,6 +22,7 @@ import java.nio.ByteBuffer
 import java.util.Objects
 import org.apache.avro.Schema
 import org.apache.avro.generic.GenericData
+import org.apache.hudi.internal.schema.HoodieSchemaException
 import org.apache.spark.sql.catalyst.InternalRow
 import org.apache.spark.sql.catalyst.util.{ArrayData, MapData}
 import org.apache.spark.sql.types.{ArrayType, BinaryType, DataType, DataTypes, MapType, StringType, StructField, StructType}
@@ -444,4 +445,13 @@ class TestAvroConversionUtils extends FunSuite with Matchers {
   private def checkNull(left: Any, right: Any): Boolean = {
     (left == null && right != null) || (left == null && right != null)
   }
+
+  test("convert struct type with duplicate column names") {
+    val struct = new StructType().add("id", DataTypes.LongType, true)
+      .add("name", DataTypes.StringType, true)
+      .add("name", DataTypes.StringType, true)
+    the [HoodieSchemaException] thrownBy {
+      AvroConversionUtils.convertStructTypeToAvroSchema(struct, "SchemaName", "SchemaNS")
+    } should have message "Duplicate field name in record SchemaNS.SchemaName: name type:UNION pos:2 and name type:UNION pos:1."
+  }
 }