[MINOR] pass the avro exception for better information (#11925)

apache · Sep 18, 2024 · 461e58b · 461e58b
1 parent 6d6d778
commit 461e58b
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 1 deletion.
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
@@ -25,7 +25,7 @@ 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 +149,7 @@ 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/...-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestAvroConversionUtils.scala b/...-spark-datasource/hudi-spark/src/test/scala/org/apache/hudi/TestAvroConversionUtils.scala
@@ -20,6 +20,7 @@ package org.apache.hudi
 
 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}
@@ -445,4 +446,13 @@ 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."
+  }
 }