pengzhiwei2018 commented on a change in pull request #2645: URL: https://github.com/apache/hudi/pull/2645#discussion_r627057178
########## File path: hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/DeleteHoodieTableCommand.scala ########## @@ -0,0 +1,81 @@ +/* + * 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.hudi.command + +import org.apache.hudi.{DataSourceWriteOptions, SparkSqlAdapterSupport} +import org.apache.hudi.DataSourceWriteOptions.{KEYGENERATOR_CLASS_OPT_KEY, OPERATION_OPT_KEY, PARTITIONPATH_FIELD_OPT_KEY, RECORDKEY_FIELD_OPT_KEY} +import org.apache.hudi.config.HoodieWriteConfig.TABLE_NAME +import org.apache.hudi.keygen.ComplexKeyGenerator +import org.apache.spark.sql._ +import org.apache.spark.sql.catalyst.plans.logical.{DeleteFromTable, SubqueryAlias} +import org.apache.spark.sql.execution.command.RunnableCommand +import org.apache.spark.sql.hudi.HoodieOptionConfig +import org.apache.spark.sql.hudi.HoodieSqlUtils._ + +case class DeleteHoodieTableCommand(deleteTable: DeleteFromTable) extends RunnableCommand + with SparkSqlAdapterSupport { + + private val table = deleteTable.table + + private val tableId = table match { + case SubqueryAlias(name, _) => sparkSqlAdapter.toTableIdentify(name) + case _ => throw new IllegalArgumentException(s"Illegal table: $table") + } + + override def run(sparkSession: SparkSession): Seq[Row] = { + logInfo(s"start execute delete command for $tableId") + + // Remove meta fields from the data frame + var df = removeMetaFields(Dataset.ofRows(sparkSession, table)) + if (deleteTable.condition.isDefined) { + df = df.filter(Column(deleteTable.condition.get)) + } Review comment: Yes, the scan happend via `Hudi datasource` because the table is created as a spark data source table. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
