dongjoon-hyun commented on a change in pull request #24682: [SPARK-27838][SQL]
Support user provided non-nullable avro schema for nullable catalyst schema
without any null record
URL: https://github.com/apache/spark/pull/24682#discussion_r287513226
##########
File path:
external/avro/src/main/scala/org/apache/spark/sql/avro/AvroSerializer.scala
##########
@@ -234,14 +236,18 @@ class AvroSerializer(rootCatalystType: DataType,
rootAvroType: Schema, nullable:
}
private def resolveNullableType(avroType: Schema, nullable: Boolean): Schema
= {
- if (nullable && avroType.getType != NULL) {
+ if (avroType.getType == Type.UNION && nullable) {
// avro uses union to represent nullable type.
val fields = avroType.getTypes.asScala
assert(fields.length == 2)
val actualType = fields.filter(_.getType != Type.NULL)
assert(actualType.length == 1)
actualType.head
} else {
+ if (nullable) {
+ logWarning(s"Writing avro files with non-nullable avro schema with
nullable catalyst " +
Review comment:
nit. Shall we remove `s` at `s"` (line 248 and 249)?
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
