Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/16592#discussion_r104792176 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala --- @@ -27,16 +27,90 @@ import org.scalatest.BeforeAndAfterEach import org.apache.spark.SparkException import org.apache.spark.sql.{AnalysisException, QueryTest, Row, SaveMode} import org.apache.spark.sql.catalyst.analysis.{NoSuchPartitionException, TableAlreadyExistsException} -import org.apache.spark.sql.catalyst.catalog.{CatalogDatabase, CatalogTable, CatalogTableType, CatalogUtils, ExternalCatalogUtils} +import org.apache.spark.sql.catalyst.catalog._ import org.apache.spark.sql.catalyst.TableIdentifier -import org.apache.spark.sql.execution.command.DDLUtils +import org.apache.spark.sql.execution.command.{DDLSuite, DDLUtils} import org.apache.spark.sql.hive.HiveExternalCatalog import org.apache.spark.sql.hive.orc.OrcFileOperator import org.apache.spark.sql.hive.test.TestHiveSingleton import org.apache.spark.sql.internal.SQLConf import org.apache.spark.sql.internal.StaticSQLConf.CATALOG_IMPLEMENTATION import org.apache.spark.sql.test.SQLTestUtils -import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.types.{MetadataBuilder, StructType} + +// TODO(gatorsmile): combine HiveCatalogedDDLSuite and HiveDDLSuite +class HiveCatalogedDDLSuite extends DDLSuite with TestHiveSingleton with BeforeAndAfterEach { + override def afterEach(): Unit = { + try { + // drop all databases, tables and functions after each test + spark.sessionState.catalog.reset() + } finally { + super.afterEach() + } + } + + protected override def generateTable( + catalog: SessionCatalog, + name: TableIdentifier): CatalogTable = { + val storage = + CatalogStorageFormat( + locationUri = Some(catalog.defaultTablePath(name)), + inputFormat = Some("org.apache.hadoop.mapred.SequenceFileInputFormat"), + outputFormat = Some("org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat"), + serde = Some("org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"), + compressed = false, + properties = Map("serialization.format" -> "1")) + val metadata = new MetadataBuilder() + .putString("key", "value") + .build() + CatalogTable( + identifier = name, + tableType = CatalogTableType.EXTERNAL, + storage = storage, + schema = new StructType() + .add("col1", "int", nullable = true, metadata = metadata) + .add("col2", "string") + .add("a", "int") + .add("b", "int"), + provider = Some("hive"), + partitionColumnNames = Seq("a", "b"), + createTime = 0L, + tracksPartitionsInCatalog = true) + } + + protected override def normalizeCatalogTable(table: CatalogTable): CatalogTable = { + val nondeterministicProps = Set( + "CreateTime", + "transient_lastDdlTime", + "grantTime", + "lastUpdateTime", + "last_modified_by", + "last_modified_time", + "Owner:", + "COLUMN_STATS_ACCURATE", + // The following are hive specific schema parameters which we do not need to match exactly. + "numFiles", + "numRows", + "rawDataSize", + "totalSize", + "totalNumberFiles", + "maxFileSize", + "minFileSize", + // EXTERNAL is not non-deterministic, but it is filtered out for external tables. + "EXTERNAL" --- End diff -- this is gone now.
--- 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