Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/19363#discussion_r144753249
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala ---
@@ -564,4 +564,25 @@ class KeyValueGroupedDataset[K, V] private[sql](
encoder: Encoder[R]): Dataset[R] = {
cogroup(other)((key, left, right) => f.call(key, left.asJava,
right.asJava).asScala)(encoder)
}
+
+ override def toString: String = {
+ val builder = new StringBuilder
+ val kFields = kExprEnc.schema.map {
+ case f => s"${f.name}: ${f.dataType.simpleString(2)}"
+ }
+ val vFields = vExprEnc.schema.map {
+ case f => s"${f.name}: ${f.dataType.simpleString(2)}"
+ }
+ builder.append("KeyValueGroupedDataset: [key: [")
+ builder.append(kFields.take(2).mkString(", "))
+ if (kFields.length > 2) {
+ builder.append(" ... " + (kFields.length - 2) + " more field(s)")
+ }
+ builder.append("], value: [")
+ builder.append(vFields.take(2).mkString(", "))
+ if (vFields.length > 2) {
+ builder.append(" ... " + (vFields.length - 2) + " more field(s)")
+ }
+ builder.append("]]").toString()
--- End diff --
shall we include `df` here?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
