Github user gatorsmile commented on a diff in the pull request: https://github.com/apache/spark/pull/14531#discussion_r76720777 --- Diff: sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala --- @@ -620,6 +623,219 @@ class HiveDDLSuite } } + test("CREATE TABLE LIKE a temporary table") { + val sourceTabName = "tab1" + val targetTabName = "tab2" + withTable(sourceTabName, targetTabName) { + spark.range(10).select('id as 'a, 'id as 'b, 'id as 'c, 'id as 'd) + .createTempView(sourceTabName) + sql(s"CREATE TABLE $targetTabName LIKE $sourceTabName") + + val sourceTable = + spark.sessionState.catalog.getTableMetadata(TableIdentifier(sourceTabName, None)) + val targetTable = + spark.sessionState.catalog.getTableMetadata(TableIdentifier(targetTabName, Some("default"))) + + assert(targetTable.storage.serde == + Option(classOf[LazySimpleSerDe].getCanonicalName)) + + checkCreateTableLike(sourceTable, targetTable) + } + } + + test("CREATE TABLE LIKE a data source table") { + val sourceTabName = "tab1" + val targetTabName = "tab2" + withTable(sourceTabName, targetTabName) { + spark.range(10).select('id as 'a, 'id as 'b, 'id as 'c, 'id as 'd) + .write.format("json").saveAsTable(sourceTabName) + sql(s"CREATE TABLE $targetTabName LIKE $sourceTabName") + + val sourceTable = + spark.sessionState.catalog.getTableMetadata(TableIdentifier(sourceTabName, Some("default"))) + val targetTable = + spark.sessionState.catalog.getTableMetadata(TableIdentifier(targetTabName, Some("default"))) + // The table type of the source table should be a Hive-managed data source table + assert(DDLUtils.isDatasourceTable(sourceTable)) + assert(sourceTable.tableType == CatalogTableType.MANAGED) + + checkCreateTableLike(sourceTable, targetTable) + } + } + + test("CREATE TABLE LIKE an external data source table") { + val sourceTabName = "tab1" + val targetTabName = "tab2" + withTable(sourceTabName, targetTabName) { + withTempPath { dir => + val path = dir.getCanonicalPath + spark.range(10).select('id as 'a, 'id as 'b, 'id as 'c, 'id as 'd) + .write.format("parquet").save(path) + sql(s"CREATE TABLE $sourceTabName USING parquet OPTIONS (PATH '$path')") + sql(s"CREATE TABLE $targetTabName LIKE $sourceTabName") + + // The source table should be an external data source table + val sourceTable = spark.sessionState.catalog.getTableMetadata( + TableIdentifier(sourceTabName, Some("default"))) + val targetTable = spark.sessionState.catalog.getTableMetadata( + TableIdentifier(targetTabName, Some("default"))) + // The table type of the source table should be an external data source table + assert(DDLUtils.isDatasourceTable(sourceTable)) + assert(sourceTable.tableType == CatalogTableType.EXTERNAL) + + checkCreateTableLike(sourceTable, targetTable) + } + } + } + + test("CREATE TABLE LIKE a managed Hive serde table") { + val catalog = spark.sessionState.catalog + val sourceTabName = "tab1" + val targetTabName = "tab2" + withTable(sourceTabName, targetTabName) { + sql(s"CREATE TABLE $sourceTabName TBLPROPERTIES('prop1'='value1') AS SELECT 1 key, 'a'") + sql(s"CREATE TABLE $targetTabName LIKE $sourceTabName") + + val sourceTable = catalog.getTableMetadata(TableIdentifier(sourceTabName, Some("default"))) + assert(sourceTable.tableType == CatalogTableType.MANAGED) + assert(sourceTable.properties.get("prop1").nonEmpty) + val targetTable = catalog.getTableMetadata(TableIdentifier(targetTabName, Some("default"))) + + checkCreateTableLike(sourceTable, targetTable) + } + } + + test("CREATE TABLE LIKE an external Hive serde table") { + val catalog = spark.sessionState.catalog + withTempDir { tmpDir => + val basePath = tmpDir.getCanonicalPath + val sourceTabName = "tab1" + val targetTabName = "tab2" + withTable(sourceTabName, targetTabName) { + assert(tmpDir.listFiles.isEmpty) + sql( + s""" + |CREATE EXTERNAL TABLE $sourceTabName (key INT comment 'test', value STRING) + |COMMENT 'Apache Spark' + |PARTITIONED BY (ds STRING, hr STRING) + |LOCATION '$basePath' + """.stripMargin) + for (ds <- Seq("2008-04-08", "2008-04-09"); hr <- Seq("11", "12")) { + sql( + s""" + |INSERT OVERWRITE TABLE $sourceTabName + |partition (ds='$ds',hr='$hr') + |SELECT 1, 'a' + """.stripMargin) + } + sql(s"CREATE TABLE $targetTabName LIKE $sourceTabName") + + val sourceTable = catalog.getTableMetadata(TableIdentifier(sourceTabName, Some("default"))) + assert(sourceTable.tableType == CatalogTableType.EXTERNAL) + assert(sourceTable.comment == Option("Apache Spark")) + val targetTable = catalog.getTableMetadata(TableIdentifier(targetTabName, Some("default"))) + + checkCreateTableLike(sourceTable, targetTable) + } + } + } + + test("CREATE TABLE LIKE a view") { + val sourceTabName = "tab1" + val sourceViewName = "view" + val targetTabName = "tab2" + withTable(sourceTabName, targetTabName) { + withView(sourceViewName) { + spark.range(10).select('id as 'a, 'id as 'b, 'id as 'c, 'id as 'd) + .write.format("json").saveAsTable(sourceTabName) + sql(s"CREATE VIEW $sourceViewName AS SELECT * FROM $sourceTabName") + sql(s"CREATE TABLE $targetTabName LIKE $sourceViewName") + + val sourceView = spark.sessionState.catalog.getTableMetadata( + TableIdentifier(sourceViewName, Some("default"))) + // The original source should be a VIEW with an empty path + assert(sourceView.tableType == CatalogTableType.VIEW) + assert(sourceView.viewText.nonEmpty && sourceView.viewOriginalText.nonEmpty) + val targetTable = spark.sessionState.catalog.getTableMetadata( + TableIdentifier(targetTabName, Some("default"))) + + checkCreateTableLike(sourceView, targetTable) + } + } + } + + private def getTablePath(table: CatalogTable): Option[String] = { + if (DDLUtils.isDatasourceTable(table)) { + new CaseInsensitiveMap(table.storage.properties).get("path") + } else { + table.storage.locationUri + } + } + + private def checkCreateTableLike(sourceTable: CatalogTable, targetTable: CatalogTable): Unit = { + // The original source should be a MANAGED table with empty view text and original text + // The location of table should not be empty. + assert(targetTable.tableType == CatalogTableType.MANAGED, + "the created table must be a Hive managed table") + assert(targetTable.viewText.isEmpty && targetTable.viewOriginalText.isEmpty, + "the view text and original text in the created table must be empty") + assert(targetTable.comment.isEmpty, + "the comment in the created table must be empty") + + val metastoreGeneratedProperties = Seq( + "CreateTime", + "transient_lastDdlTime", + "grantTime", + "lastUpdateTime", + "last_modified_by", + "last_modified_time", + "Owner:", + "COLUMN_STATS_ACCURATE", + "numFiles", + "numRows", + "rawDataSize", + "totalSize", + "totalNumberFiles", + "maxFileSize", + "minFileSize" + ) + assert(targetTable.properties.filterKeys(!metastoreGeneratedProperties.contains(_)).isEmpty, + "the table properties of source tables should not be copied in the created table") + + if (DDLUtils.isDatasourceTable(sourceTable)) { + assert(DDLUtils.isDatasourceTable(targetTable), + "the target table should be a data source table") + } else { + assert(!DDLUtils.isDatasourceTable(targetTable), + "the target table should be a Hive serde table") + } + + val sourceTablePath = getTablePath(sourceTable) + val targetTablePath = getTablePath(targetTable) + assert(targetTablePath.nonEmpty, "target table path should not be empty") + assert(sourceTablePath != targetTablePath, + "source table/view path should be different from target table path") + + // The source table contents should not been seen in the target table. + assert(spark.table(sourceTable.identifier).count() != 0, "the source table should be nonempty") --- End diff -- This is just for checking the source table is non-empty but the target table is empty. We definitely can CREATE TABLE LIKE an empty source table.
--- 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