Github user dbtsai commented on a diff in the pull request:
https://github.com/apache/spark/pull/21847#discussion_r206356838
--- Diff:
external/avro/src/main/scala/org/apache/spark/sql/avro/AvroSerializer.scala ---
@@ -146,9 +159,13 @@ class AvroSerializer(rootCatalystType: DataType,
rootAvroType: Schema, nullable:
private def newStructConverter(
catalystStruct: StructType, avroStruct: Schema): InternalRow =>
Record = {
val avroFields = avroStruct.getFields
- assert(avroFields.size() == catalystStruct.length)
+ if (avroFields.size != catalystStruct.length) {
+ throw new IncompatibleSchemaException(
+ s"Field list length of ${catalystStruct} does not correspond to
length of ${avroStruct}")
+ }
val fieldConverters = catalystStruct.zip(avroFields.asScala).map {
- case (f1, f2) => newConverter(f1.dataType,
resolveNullableType(f2.schema(), f1.nullable))
+ case (f1, f2) =>
+ newConverter(f1.dataType, resolveUnionType(f2.schema(),
f1.dataType, f1.nullable))
--- End diff --
```scala
val fieldConverters = catalystStruct.zip(avroFields.asScala).map { case
(f1, f2) =>
newConverter(f1.dataType, resolveUnionType(f2.schema(), f1.dataType,
f1.nullable))
}
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
