Github user HyukjinKwon commented on a diff in the pull request:

    https://github.com/apache/spark/pull/19448#discussion_r143894782
  
    --- Diff: 
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/parquet/ParquetCommitterSuite.scala
 ---
    @@ -0,0 +1,149 @@
    +/*
    + * 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.parquet
    +
    +import java.io.FileNotFoundException
    +
    +import org.apache.hadoop.conf.Configuration
    +import org.apache.hadoop.fs.{FileStatus, Path}
    +import org.apache.hadoop.mapreduce.{JobContext, TaskAttemptContext}
    +import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter
    +import org.apache.parquet.hadoop.{ParquetOutputCommitter, 
ParquetOutputFormat}
    +
    +import org.apache.spark.{LocalSparkContext, SparkFunSuite}
    +import org.apache.spark.sql.SparkSession
    +import org.apache.spark.sql.internal.SQLConf
    +import org.apache.spark.sql.test.SQLTestUtils
    +
    +/**
    + * Test logic related to choice of output commtters
    + */
    +class ParquetCommitterSuite extends SparkFunSuite with SQLTestUtils
    +  with LocalSparkContext {
    +
    +  private val PARQUET_COMMITTER = 
classOf[ParquetOutputCommitter].getCanonicalName
    +
    +  protected var spark: SparkSession = _
    +
    +  /**
    +   * Create a new [[SparkSession]] running in local-cluster mode with 
unsafe and codegen enabled.
    +   */
    +  override def beforeAll(): Unit = {
    +    super.beforeAll()
    +    spark = SparkSession.builder()
    +      .master("local-cluster[2,1,1024]")
    +      .appName("testing")
    +      .getOrCreate()
    +  }
    +
    +  override def afterAll(): Unit = {
    +    spark.stop()
    +    spark = null
    +  }
    +
    +  test("alternative output committer, merge schema") {
    +    intercept[RuntimeException] {
    +      val stat = writeDataFrame(MarkingFileOutput.COMMITTER, true, true)
    +      logError(s"Created marker file $stat")
    +    }
    +  }
    +
    +  test("alternative output committer, no merge schema") {
    +    writeDataFrame(MarkingFileOutput.COMMITTER, false, true)
    --- End diff --
    
    I think It might be a little bit better to use named arguments for 
readability: `writeDataFrame(MarkingFileOutput.COMMITTER, summary = false, 
check  = true)`


---

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

Reply via email to