sbernauer commented on a change in pull request #1760:
URL: https://github.com/apache/hudi/pull/1760#discussion_r452780045
##########
File path: hudi-spark/src/main/scala/org/apache/hudi/AvroConversionUtils.scala
##########
@@ -78,4 +79,21 @@ object AvroConversionUtils {
def convertAvroSchemaToStructType(avroSchema: Schema): StructType = {
SchemaConverters.toSqlType(avroSchema).dataType.asInstanceOf[StructType]
}
+
+ private def deserializeRow(encoder: ExpressionEncoder[Row], internalRow:
InternalRow): Row = {
+ // First attempt to use spark2 API for deserialization, otherwise attempt
with spark3 API
+ try {
+ val spark2method = encoder.getClass.getMethods.filter(method =>
method.getName.equals("fromRow")).last
+ spark2method.invoke(encoder, internalRow).asInstanceOf[Row]
+ } catch {
+ case e: NoSuchElementException => spark3Deserialize(encoder, internalRow)
Review comment:
I would suggest to change the method to something like this
```
import org.apache.spark.SPARK_VERSION
private def deserializeRow(encoder: ExpressionEncoder[Row], internalRow:
InternalRow): Row = {
// TODO remove reflection if Spark 2.x support is dropped
if (SPARK_VERSION.startsWith("2.")) {
val spark2method = encoder.getClass.getMethod("fromRow",
classOf[InternalRow])
spark2method.invoke(encoder, internalRow).asInstanceOf[Row]
} else {
val deserializer =
encoder.getClass.getMethod("createDeserializer").invoke(encoder)
val aboveSpark2method = deserializer.getClass.getMethod("apply",
classOf[InternalRow])
aboveSpark2method.invoke(deserializer, internalRow).asInstanceOf[Row]
}
}
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
