HyukjinKwon commented on a change in pull request #28645: URL: https://github.com/apache/spark/pull/28645#discussion_r440098735
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala ########## @@ -2847,6 +2848,45 @@ class Analyzer( } } + /** + * Resolve the encoders for the UDF by explicitly given the attributes. We give the + * attributes explicitly in order to handle the case where the data type of the input + * value is not the same with the internal schema of the encoder, which could cause + * data loss. For example, the encoder should not cast the input value to Decimal(38, 18) + * if the actual data type is Decimal(30, 0). + * + * The resolved encoders then will be used to deserialize the internal row to Scala value. + */ + object ResolveEncodersInUDF extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan.resolveOperatorsUp { + case p if !p.resolved => p // Skip unresolved nodes. + + case p => p transformExpressionsUp { + + case udf @ ScalaUDF(_, _, inputs, encoders, _, _, _) if encoders.nonEmpty => Review comment: Shall we avoid argument matching? It's actually an anti-pattern - https://github.com/databricks/scala-style-guide#pattern-matching ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org