[GitHub] gatorsmile commented on a change in pull request #23601: [SPARK-26673][SQL] File source V2 writes: create framework and migrate ORC

[GitBox <gi...@apache.org>]

gatorsmile commented on a change in pull request #23601: [SPARK-26673][SQL] File source V2 writes: create framework and migrate ORC
URL: https://github.com/apache/spark/pull/23601#discussion_r259570665
 
 

 ##########
 File path: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/v2/FileWriteBuilder.scala
 ##########
 @@ -0,0 +1,158 @@
+/*
+ * 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 java.util.UUID
+
+import scala.collection.JavaConverters._
+
+import org.apache.hadoop.conf.Configuration
+import org.apache.hadoop.fs.Path
+import org.apache.hadoop.mapreduce.Job
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat
+
+import org.apache.spark.internal.io.FileCommitProtocol
+import org.apache.spark.sql.{AnalysisException, SaveMode, SparkSession}
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.util.{CaseInsensitiveMap, DateTimeUtils}
+import org.apache.spark.sql.execution.datasources.{BasicWriteJobStatsTracker, DataSource, OutputWriterFactory, WriteJobDescription}
+import org.apache.spark.sql.execution.metric.SQLMetric
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.sources.v2.DataSourceOptions
+import org.apache.spark.sql.sources.v2.writer.{BatchWrite, SupportsSaveMode, WriteBuilder}
+import org.apache.spark.sql.types.StructType
+import org.apache.spark.util.SerializableConfiguration
+
+abstract class FileWriteBuilder(options: DataSourceOptions)
+  extends WriteBuilder with SupportsSaveMode {
+  private var schema: StructType = _
+  private var queryId: String = _
+  private var mode: SaveMode = _
+
+  override def withInputDataSchema(schema: StructType): WriteBuilder = {
+    this.schema = schema
+    this
+  }
+
+  override def withQueryId(queryId: String): WriteBuilder = {
+    this.queryId = queryId
+    this
+  }
+
+  override def mode(mode: SaveMode): WriteBuilder = {
+    this.mode = mode
+    this
+  }
+
+  override def buildForBatch(): BatchWrite = {
+    validateInputs()
+    val pathName = options.paths().head
+    val path = new Path(pathName)
+    val sparkSession = SparkSession.active
+    val optionsAsScala = options.asMap().asScala.toMap
+    val hadoopConf = sparkSession.sessionState.newHadoopConfWithOptions(optionsAsScala)
+    val job = getJobInstance(hadoopConf, path)
+    val committer = FileCommitProtocol.instantiate(
+      sparkSession.sessionState.conf.fileCommitProtocolClass,
+      jobId = java.util.UUID.randomUUID().toString,
+      outputPath = pathName)
+    lazy val description =
+      createWriteJobDescription(sparkSession, hadoopConf, job, pathName, optionsAsScala)
+
+    val fs = path.getFileSystem(hadoopConf)
+    mode match {
+      case SaveMode.ErrorIfExists if fs.exists(path) =>
+        val qualifiedOutputPath = path.makeQualified(fs.getUri, fs.getWorkingDirectory)
+        throw new AnalysisException(s"path $qualifiedOutputPath already exists.")
+
+      case SaveMode.Ignore if fs.exists(path) =>
+        null
+
+      case SaveMode.Overwrite =>
+        committer.deleteWithJob(fs, path, true)
 
 Review comment:
   What happened if the path does not exist? It is possible that the underlying committer's deleteWithJob might not handle this case. 

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
users@infra.apache.org


With regards,
Apache Git Services

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