Github user rdblue commented on a diff in the pull request:
https://github.com/apache/spark/pull/23086#discussion_r236857220
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2ScanExec.scala
---
@@ -23,29 +23,28 @@ import org.apache.spark.sql.catalyst.expressions._
import org.apache.spark.sql.catalyst.plans.physical
import org.apache.spark.sql.catalyst.plans.physical.SinglePartition
import org.apache.spark.sql.execution.{ColumnarBatchScan, LeafExecNode,
WholeStageCodegenExec}
-import org.apache.spark.sql.execution.streaming.continuous._
import org.apache.spark.sql.sources.v2.DataSourceV2
import org.apache.spark.sql.sources.v2.reader._
-import
org.apache.spark.sql.sources.v2.reader.streaming.{ContinuousPartitionReaderFactory,
ContinuousReadSupport, MicroBatchReadSupport}
/**
- * Physical plan node for scanning data from a data source.
+ * Physical plan node for scanning a batch of data from a data source.
*/
case class DataSourceV2ScanExec(
output: Seq[AttributeReference],
@transient source: DataSourceV2,
--- End diff --
I think we can remove source by updating `equals` and `hashCode` to check
just the `Scan`.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
