Github user steveloughran commented on a diff in the pull request:
https://github.com/apache/spark/pull/19269#discussion_r142005126
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/WriteToDataSourceV2Command.scala
---
@@ -0,0 +1,113 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.datasources.v2
+
+import org.apache.spark.{SparkException, TaskContext}
+import org.apache.spark.internal.Logging
+import org.apache.spark.sql.{Row, SparkSession}
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.encoders.{ExpressionEncoder,
RowEncoder}
+import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
+import org.apache.spark.sql.execution.SparkPlan
+import org.apache.spark.sql.execution.command.RunnableCommand
+import org.apache.spark.sql.sources.v2.writer._
+import org.apache.spark.sql.types.StructType
+import org.apache.spark.util.Utils
+
+case class WriteToDataSourceV2Command(writer: DataSourceV2Writer, query:
LogicalPlan)
+ extends RunnableCommand {
+ override def children: Seq[LogicalPlan] = query :: Nil
+
+ override def run(sparkSession: SparkSession, children: Seq[SparkPlan]):
Seq[Row] = {
+ assert(children.length == 1)
+
+ val writeTask = writer match {
+ case w: SupportsWriteInternalRow =>
w.createInternalRowWriterFactory()
+ case _ => new
RowToInternalRowDataWriteFactory(writer.createWriterFactory(), query.schema)
+ }
+
+ val rdd = children.head.execute()
+ val messages = new Array[WriterCommitMessage](rdd.partitions.length)
+
+ logInfo(s"Start processing data source writer: $writer")
+
+ try {
+ sparkSession.sparkContext.runJob(
+ rdd,
+ (context: TaskContext, iter: Iterator[InternalRow]) =>
+ DataWritingSparkTask.run(writeTask, context, iter),
+ rdd.partitions.indices,
+ (index, message: WriterCommitMessage) => messages(index) = message
+ )
+
+ writer.commit(messages)
+ logInfo(s"Data source writer $writer committed.")
+ } catch {
+ case cause: Throwable =>
+ writer.abort()
+ logError(s"Data source writer $writer aborted.")
+ throw new SparkException("Writing job aborted.", cause)
+
+ }
+
+ Nil
+ }
+}
+
+object DataWritingSparkTask extends Logging {
+ def run(
+ writeTask: DataWriteFactory[InternalRow],
+ context: TaskContext,
+ iter: Iterator[InternalRow]): WriterCommitMessage = {
+ val dataWriter =
+ writeTask.createWriter(context.stageId(), context.partitionId(),
context.attemptNumber())
+
+ // write the data and commit this writer.
+ Utils.tryWithSafeFinallyAndFailureCallbacks(block = {
+ iter.foreach(dataWriter.write)
+ dataWriter.commit()
--- End diff --
good to log something here, at least @ debug
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
