Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/23124#discussion_r236949897
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetRowConverter.scala
---
@@ -558,8 +558,11 @@ private[parquet] class ParquetRowConverter(
override def getConverter(fieldIndex: Int): Converter =
keyValueConverter
- override def end(): Unit =
+ override def end(): Unit = {
+ // The parquet map may contains null or duplicated map keys. When it
happens, the behavior is
+ // undefined.
--- End diff --
done
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
