Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/2226#discussion_r17703914
--- Diff:
sql/hive/src/main/scala/org/apache/spark/sql/hive/SparkHadoopWriter.scala ---
@@ -0,0 +1,213 @@
+/*
+ * 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.hive
+
+import java.io.IOException
+import java.text.NumberFormat
+import java.util.Date
+
+import scala.collection.mutable
+
+import org.apache.hadoop.fs.Path
+import org.apache.hadoop.hive.conf.HiveConf.ConfVars
+import org.apache.hadoop.hive.ql.exec.{FileSinkOperator, Utilities}
+import org.apache.hadoop.hive.ql.io.{HiveFileFormatUtils, HiveOutputFormat}
+import org.apache.hadoop.hive.ql.plan.FileSinkDesc
+import org.apache.hadoop.io.Writable
+import org.apache.hadoop.mapred._
+
+import org.apache.spark.sql.Row
+import org.apache.spark.{Logging, SerializableWritable, SparkHadoopWriter}
+
+/**
+ * Internal helper class that saves an RDD using a Hive OutputFormat.
+ * It is based on [[SparkHadoopWriter]].
+ */
+private[hive] class SparkHiveWriterContainer(
+ @transient jobConf: JobConf,
+ fileSinkConf: FileSinkDesc)
+ extends Logging
+ with SparkHadoopMapRedUtil
+ with Serializable {
+
+ private val now = new Date()
+ protected val conf = new SerializableWritable(jobConf)
+
+ private var jobID = 0
+ private var splitID = 0
+ private var attemptID = 0
+ private var jID: SerializableWritable[JobID] = null
+ private var taID: SerializableWritable[TaskAttemptID] = null
+
+ @transient private var writer: FileSinkOperator.RecordWriter = null
+ @transient private lazy val committer = conf.value.getOutputCommitter
+ @transient private lazy val jobContext = newJobContext(conf.value,
jID.value)
+ @transient private lazy val taskContext =
newTaskAttemptContext(conf.value, taID.value)
+ @transient private lazy val outputFormat =
+
conf.value.getOutputFormat.asInstanceOf[HiveOutputFormat[AnyRef,Writable]]
+
+ def driverSideSetup() {
+ setIDs(0, 0, 0)
+ setConfParams()
+ committer.setupJob(jobContext)
+ }
+
+ def executorSideSetup(jobId: Int, splitId: Int, attemptId: Int) {
+ setIDs(jobId, splitId, attemptId)
+ setConfParams()
+ committer.setupTask(taskContext)
+ }
+
+ /**
+ * Create a `HiveRecordWriter`. A relative dynamic partition path can be
used to create a writer
+ * for writing data to a dynamic partition.
+ */
+ def open() {
--- End diff --
Is it always called after `executorSideSetup`? If so, can we rename it to
something like `setupWriter` (or `initWriter`) and call it at the end of
`executorSideSetup` instead of call it in `writeToFile`?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
