Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/20214#discussion_r161153123
--- Diff: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala ---
@@ -237,13 +237,18 @@ class Dataset[T] private[sql](
private[sql] def showString(
_numRows: Int, truncate: Int = 20, vertical: Boolean = false):
String = {
val numRows = _numRows.max(0).min(Int.MaxValue - 1)
- val takeResult = toDF().take(numRows + 1)
+ val newDf = toDF()
+ val castExprs = newDf.schema.map { f => f.dataType match {
+ // Since binary types in top-level schema fields have a specific
format to print,
+ // so we do not cast them to strings here.
+ case BinaryType => s"`${f.name}`"
+ case _: UserDefinedType[_] => s"`${f.name}`"
--- End diff --
How about something like:
```scala
case udt: UserDefinedType[_] =>
(c, evPrim, evNull) => {
val udtTerm = ctx.addReferenceObj("udt", udt)
s"$evPrim =
UTF8String.fromString($udtTerm.deserialize($c).toString());"
}
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
