Github user wangyum commented on a diff in the pull request:
https://github.com/apache/spark/pull/21682#discussion_r199986187
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala
---
@@ -42,6 +42,14 @@ private[parquet] class ParquetFilters(pushDownDate:
Boolean, pushDownStartWith:
private val makeEq: PartialFunction[DataType, (String, Any) =>
FilterPredicate] = {
case BooleanType =>
(n: String, v: Any) => FilterApi.eq(booleanColumn(n),
v.asInstanceOf[java.lang.Boolean])
+ case ByteType =>
+ (n: String, v: Any) => FilterApi.eq(
+ intColumn(n),
+ Option(v).map(b =>
b.asInstanceOf[java.lang.Byte].toInt.asInstanceOf[Integer]).orNull)
--- End diff --
```scala
scala> null.asInstanceOf[Short].toInt.asInstanceOf[Integer]
res49: Integer = 0
scala> null.asInstanceOf[java.lang.Short].toInt.asInstanceOf[Integer]
java.lang.NullPointerException
at scala.Predef$.Short2short(Predef.scala:360)
... 51 elided
```
That's why I use `Option.map` here.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
