Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/20087#discussion_r162252520 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/CompressionCodecSuite.scala --- @@ -0,0 +1,321 @@ +/* + * 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.File + +import scala.collection.JavaConverters._ + +import org.apache.hadoop.fs.Path +import org.apache.orc.OrcConf.COMPRESS +import org.apache.parquet.hadoop.ParquetOutputFormat +import org.scalatest.BeforeAndAfterAll + +import org.apache.spark.sql.execution.datasources.orc.OrcOptions +import org.apache.spark.sql.execution.datasources.parquet.{ParquetOptions, ParquetTest} +import org.apache.spark.sql.hive.orc.OrcFileOperator +import org.apache.spark.sql.hive.test.TestHiveSingleton +import org.apache.spark.sql.internal.SQLConf + +class CompressionCodecSuite extends TestHiveSingleton with ParquetTest with BeforeAndAfterAll { + import spark.implicits._ + + override def beforeAll(): Unit = { + super.beforeAll() + (0 until maxRecordNum).toDF("a").createOrReplaceTempView("table_source") + } + + override def afterAll(): Unit = { + try { + spark.catalog.dropTempView("table_source") + } finally { + super.afterAll() + } + } + + private val maxRecordNum = 500 + + private def getConvertMetastoreConfName(format: String): String = format.toLowerCase match { + case "parquet" => HiveUtils.CONVERT_METASTORE_PARQUET.key + case "orc" => HiveUtils.CONVERT_METASTORE_ORC.key + } + + private def getSparkCompressionConfName(format: String): String = format.toLowerCase match { + case "parquet" => SQLConf.PARQUET_COMPRESSION.key + case "orc" => SQLConf.ORC_COMPRESSION.key + } + + private def getHiveCompressPropName(format: String): String = format.toLowerCase match { + case "parquet" => ParquetOutputFormat.COMPRESSION + case "orc" => COMPRESS.getAttribute + } + + private def normalizeCodecName(format: String, name: String): String = { + format.toLowerCase match { + case "parquet" => ParquetOptions.shortParquetCompressionCodecNames(name).name() + case "orc" => OrcOptions.shortOrcCompressionCodecNames(name) + } + } + + private def getTableCompressionCodec(path: String, format: String): Seq[String] = { + val hadoopConf = spark.sessionState.newHadoopConf() + val codecs = format.toLowerCase match { + case "parquet" => for { + footer <- readAllFootersWithoutSummaryFiles(new Path(path), hadoopConf) + block <- footer.getParquetMetadata.getBlocks.asScala + column <- block.getColumns.asScala + } yield column.getCodec.name() + case "orc" => new File(path).listFiles().filter{ file => --- End diff -- Nit: add a space before `{`
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org