rdblue commented on a change in pull request #25747: [SPARK-29039][SQL] centralize the catalog and table lookup logic URL: https://github.com/apache/spark/pull/25747#discussion_r328295828
########## File path: sql/core/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveCatalogsForV1Commands.scala ########## @@ -0,0 +1,252 @@ +/* + * 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.catalyst.analysis + +import scala.collection.mutable + +import org.apache.spark.sql.{AnalysisException, SaveMode} +import org.apache.spark.sql.catalyst.TableIdentifier +import org.apache.spark.sql.catalyst.catalog.{BucketSpec, CatalogTable, CatalogTableType, CatalogUtils} +import org.apache.spark.sql.catalyst.plans.logical.{CreateTableAsSelect, CreateV2Table, LogicalPlan, ReplaceTable, ReplaceTableAsSelect} +import org.apache.spark.sql.catalyst.plans.logical.sql.{CreateTableAsSelectStatement, CreateTableStatement, DropTableStatement, DropViewStatement, ReplaceTableAsSelectStatement, ReplaceTableStatement, ShowNamespacesStatement, ShowTablesStatement} +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.connector.catalog.{CatalogManager, LookupCatalog} +import org.apache.spark.sql.connector.expressions.Transform +import org.apache.spark.sql.execution.command.{DropTableCommand, ShowTablesCommand} +import org.apache.spark.sql.execution.datasources.{CreateTable, DataSource} +import org.apache.spark.sql.execution.datasources.v2.FileDataSourceV2 +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types.StructType + +/** + * Resolves catalogs from the multi-part identifiers in SQL statements, and convert the statements + * to the corresponding v1 commands if the resolved catalog is not the session catalog. + * + * We can remove this rule once we implement all the catalog functionality in `V2SessionCatalog`. + */ +class ResolveCatalogsForV1Commands(val catalogManager: CatalogManager, conf: SQLConf) + extends Rule[LogicalPlan] with LookupCatalog { + import org.apache.spark.sql.connector.catalog.CatalogV2Implicits._ + import org.apache.spark.sql.connector.catalog.CatalogV2Util.isSessionCatalog + + override def apply(plan: LogicalPlan): LogicalPlan = plan.resolveOperatorsUp { + // TODO: we should convert CREATE/REPLACE TABLE statements to v2 commands in the rule + // `ResolveCatalogs`. However, it's not doable right now because we need to look up the + // table provider. Table provider lookup is implemented in sql/core and relies on a v1 + // interface `DataSourceRegister`. Review comment: If the catalog is not the session catalog, then the plan should always be v2. At least that case can be moved into catalyst, right? ---------------------------------------------------------------- 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] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
