Github user rdblue commented on a diff in the pull request:
https://github.com/apache/spark/pull/20387#discussion_r164169060
--- 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 --
That's why these are options. Passing either path or table name is the most
common case, which we should have good support for. If tables are identified in
other ways, that's supported.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
