Github user rdblue commented on a diff in the pull request: https://github.com/apache/spark/pull/21556#discussion_r202090024 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetFilters.scala --- @@ -248,29 +371,29 @@ private[parquet] class ParquetFilters(pushDownDate: Boolean, pushDownStartWith: // Probably I missed something and obviously this should be changed. predicate match { - case sources.IsNull(name) if canMakeFilterOn(name) => + case sources.IsNull(name) if canMakeFilterOn(name, null) => makeEq.lift(nameToType(name)).map(_(name, null)) - case sources.IsNotNull(name) if canMakeFilterOn(name) => + case sources.IsNotNull(name) if canMakeFilterOn(name, null) => makeNotEq.lift(nameToType(name)).map(_(name, null)) - case sources.EqualTo(name, value) if canMakeFilterOn(name) => + case sources.EqualTo(name, value) if canMakeFilterOn(name, value) => makeEq.lift(nameToType(name)).map(_(name, value)) - case sources.Not(sources.EqualTo(name, value)) if canMakeFilterOn(name) => + case sources.Not(sources.EqualTo(name, value)) if canMakeFilterOn(name, value) => makeNotEq.lift(nameToType(name)).map(_(name, value)) - case sources.EqualNullSafe(name, value) if canMakeFilterOn(name) => + case sources.EqualNullSafe(name, value) if canMakeFilterOn(name, value) => makeEq.lift(nameToType(name)).map(_(name, value)) - case sources.Not(sources.EqualNullSafe(name, value)) if canMakeFilterOn(name) => + case sources.Not(sources.EqualNullSafe(name, value)) if canMakeFilterOn(name, value) => makeNotEq.lift(nameToType(name)).map(_(name, value)) --- End diff -- Maybe I'm missing something, but that returns true for all null values.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org