Github user rdblue commented on a diff in the pull request:
https://github.com/apache/spark/pull/20387#discussion_r163913161
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala
---
@@ -17,15 +17,149 @@
package org.apache.spark.sql.execution.datasources.v2
-import org.apache.spark.sql.catalyst.expressions.AttributeReference
+import java.util.UUID
+
+import scala.collection.JavaConverters._
+import scala.collection.mutable
+
+import org.apache.spark.sql.{AnalysisException, SaveMode}
+import org.apache.spark.sql.catalyst.TableIdentifier
+import org.apache.spark.sql.catalyst.expressions.{AttributeReference,
Expression}
import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, Statistics}
+import org.apache.spark.sql.execution.datasources.DataSourceStrategy
+import org.apache.spark.sql.sources.{DataSourceRegister, Filter}
+import org.apache.spark.sql.sources.v2.{DataSourceV2, DataSourceV2Options,
ReadSupport, ReadSupportWithSchema, WriteSupport}
import org.apache.spark.sql.sources.v2.reader._
+import org.apache.spark.sql.sources.v2.writer.DataSourceV2Writer
+import org.apache.spark.sql.types.StructType
case class DataSourceV2Relation(
- fullOutput: Seq[AttributeReference],
- reader: DataSourceV2Reader) extends LeafNode with
DataSourceReaderHolder {
+ source: DataSourceV2,
+ options: Map[String, String],
+ path: Option[String] = None,
+ table: Option[TableIdentifier] = None,
--- End diff --
I guess another way to say this is that it's better to set reliable path,
database, and table parameters after passing the explicitly, than to require
all the places where DataSourceV2Relations are created do the same thing.
Better to standardize passing these options in `v2Options`, and it would be
even better to pass these directly to the readers and writers.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
