Github user cloud-fan commented on a diff in the pull request:

    https://github.com/apache/spark/pull/20387#discussion_r167342554
  
    --- Diff: 
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala
 ---
    @@ -17,17 +17,131 @@
     
     package org.apache.spark.sql.execution.datasources.v2
     
    +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.analysis.MultiInstanceRelation
    -import org.apache.spark.sql.catalyst.expressions.AttributeReference
    -import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, Statistics}
    -import org.apache.spark.sql.sources.v2.reader._
    +import org.apache.spark.sql.catalyst.expressions.{AttributeReference, 
Expression, ExprId}
    +import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, LogicalPlan, 
Statistics}
    +import org.apache.spark.sql.execution.datasources.DataSourceStrategy
    +import org.apache.spark.sql.sources.{DataSourceRegister, Filter}
    +import org.apache.spark.sql.sources.v2.{DataSourceOptions, DataSourceV2, 
ReadSupport, ReadSupportWithSchema, WriteSupport}
    +import org.apache.spark.sql.sources.v2.reader.{DataSourceReader, 
SupportsPushDownCatalystFilters, SupportsPushDownFilters, 
SupportsPushDownRequiredColumns, SupportsReportStatistics}
    +import org.apache.spark.sql.sources.v2.writer.DataSourceWriter
    +import org.apache.spark.sql.types.StructType
     
     case class DataSourceV2Relation(
    -    output: Seq[AttributeReference],
    -    reader: DataSourceReader)
    -  extends LeafNode with MultiInstanceRelation with DataSourceReaderHolder {
    +    source: DataSourceV2,
    +    options: Map[String, String],
    +    projection: Option[Seq[AttributeReference]] = None,
    --- End diff --
    
    Since we need to keep the "pushed columns" anyway, can we just use the 
`output` field? The only difference between `output` and `projection` is the 
default value, this can be solved by creating a temp reader and get its schema 
in `DataFrameReader`. We already did this in `DataStreamReader.load`.


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org

Reply via email to