Minor Description
This ticket aims at fixing a minor bug when normalizing floats for struct types;
scala> import org.apache.spark.sql.execution.aggregate.HashAggregateExec scala> val df = Seq(Tuple1(Tuple1(-0.0d)), Tuple1(Tuple1(0.0d))).toDF("k") scala> val agg = df.distinct() scala> agg.explain() == Physical Plan == *(2) HashAggregate(keys=[k#40], functions=[]) +- Exchange hashpartitioning(k#40, 200), true, [id=#62] +- *(1) HashAggregate(keys=[knownfloatingpointnormalized(if (isnull(k#40)) null else named_struct(col1, knownfloatingpointnormalized(normalizenanandzero(k#40._1)))) AS k#40], functions=[]) +- *(1) LocalTableScan [k#40] scala> val aggOutput = agg.queryExecution.sparkPlan.collect { case a: HashAggregateExec => a.output.head } scala> aggOutput.foreach { attr => println(attr.prettyJson) } ### Final Aggregate ### [ { "class" : "org.apache.spark.sql.catalyst.expressions.AttributeReference", "num-children" : 0, "name" : "k", "dataType" : { "type" : "struct", "fields" : [ { "name" : "_1", ^^^ "type" : "double", "nullable" : false, "metadata" : { } } ] }, "nullable" : true, "metadata" : { }, "exprId" : { "product-class" : "org.apache.spark.sql.catalyst.expressions.ExprId", "id" : 40, "jvmId" : "a824e83f-933e-4b85-a1ff-577b5a0e2366" }, "qualifier" : [ ] } ] ### Partial Aggregate ### [ { "class" : "org.apache.spark.sql.catalyst.expressions.AttributeReference", "num-children" : 0, "name" : "k", "dataType" : { "type" : "struct", "fields" : [ { "name" : "col1", ^^^^ "type" : "double", "nullable" : true, "metadata" : { } } ] }, "nullable" : true, "metadata" : { }, "exprId" : { "product-class" : "org.apache.spark.sql.catalyst.expressions.ExprId", "id" : 40, "jvmId" : "a824e83f-933e-4b85-a1ff-577b5a0e2366" }, "qualifier" : [ ] } ]
