Github user ravipesala commented on a diff in the pull request:
https://github.com/apache/carbondata/pull/1583#discussion_r154566404
--- Diff:
integration/spark2/src/main/scala/org/apache/spark/sql/execution/command/management/RefreshCarbonTableCommand.scala
---
@@ -0,0 +1,216 @@
+/*
+ * 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.command.management
+
+import java.util
+
+import scala.collection.JavaConverters._
+
+import org.apache.spark.sql._
+import org.apache.spark.sql.execution.command.MetadataCommand
+import
org.apache.spark.sql.execution.command.table.CarbonCreateTableCommand
+import org.apache.spark.sql.util.CarbonException
+
+import org.apache.carbondata.common.logging.{LogService, LogServiceFactory}
+import org.apache.carbondata.core.constants.CarbonCommonConstants
+import org.apache.carbondata.core.datastore.impl.FileFactory
+import org.apache.carbondata.core.metadata.{AbsoluteTableIdentifier,
CarbonTableIdentifier}
+import org.apache.carbondata.core.metadata.schema.table.{DataMapSchema,
TableInfo}
+import org.apache.carbondata.core.metadata.schema.table.column.ColumnSchema
+import org.apache.carbondata.core.util.CarbonProperties
+import org.apache.carbondata.core.util.path.CarbonStorePath
+import org.apache.carbondata.events.{OperationContext,
OperationListenerBus, RefreshTablePostExecutionEvent,
RefreshTablePreExecutionEvent}
+
+/**
+ * Command to register carbon table from existing carbon table data
+ */
+case class RefreshCarbonTableCommand(
+ dbName: Option[String],
+ tableName: String)
+ extends MetadataCommand {
+ val LOGGER: LogService =
+ LogServiceFactory.getLogService(this.getClass.getName)
+
+ override def processMetadata(sparkSession: SparkSession): Seq[Row] = {
+ val metaStore = CarbonEnv.getInstance(sparkSession).carbonMetastore
+ val databaseName = GetDB.getDatabaseName(dbName, sparkSession)
+ val databaseLocation = GetDB.getDatabaseLocation(databaseName,
sparkSession,
+ CarbonProperties.getStorePath)
+ // Steps
+ // 1. get table path
+ // 2. perform the below steps
+ // 2.1 check if the table already register with hive then ignore and
continue with the next
+ // schema
+ // 2.2 register the table with the hive check if the table being
registered has aggregate table
+ // then do the below steps
+ // 2.2.1 validate that all the aggregate tables are copied at the
store location.
+ // 2.2.2 Register the aggregate tables
+ val tablePath = databaseLocation +
CarbonCommonConstants.FILE_SEPARATOR + tableName
+ val absoluteTableIdentifier = AbsoluteTableIdentifier.from(tablePath,
databaseName, tableName)
+ // 2.1 check if the table already register with hive then ignore and
continue with the next
+ // schema
+ if (!sparkSession.sessionState.catalog.listTables(databaseName)
+ .exists(_.table.equalsIgnoreCase(tableName))) {
+ val carbonTablePath =
CarbonStorePath.getCarbonTablePath(absoluteTableIdentifier)
+ // check the existence of the schema file to know its a carbon table
+ val schemaFilePath = carbonTablePath.getSchemaFilePath
+ // if schema file does not exist then the table will either non
carbon table or stale
+ // carbon table
+ if (FileFactory.isFileExist(schemaFilePath,
FileFactory.getFileType(schemaFilePath))) {
+ // read TableInfo
+ val tableInfo =
metaStore.getWrapperTableInfo(absoluteTableIdentifier)(sparkSession)
+ // 2.2 register the table with the hive check if the table being
registered has
+ // aggregate table then do the below steps
+ // 2.2.1 validate that all the aggregate tables are copied at the
store location.
+ val dataMapSchemaList = tableInfo.getDataMapSchemaList
+ if (null != dataMapSchemaList && dataMapSchemaList.size() != 0) {
+ // validate all the aggregate tables are copied at the
storeLocation
+ val allExists = validateAllAggregateTablePresent(databaseName,
+ dataMapSchemaList, databaseLocation)
+ if (!allExists) {
+ // fail the register operation
+ val msg = s"Table registration with Database name
[$databaseName] and Table name " +
+ s"[$tableName] failed. All the aggregate Tables for
table [$tableName] is" +
--- End diff --
Better print the agg table names which are not copied
---
