cloud-fan commented on a change in pull request #25368: [SPARK-28635][SQL] create CatalogManager to track registered v2 catalogs URL: https://github.com/apache/spark/pull/25368#discussion_r313714259
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalog/v2/CatalogManager.scala ########## @@ -0,0 +1,100 @@ +/* + * 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.catalog.v2 + +import scala.collection.mutable +import scala.util.control.NonFatal + +import org.apache.spark.internal.Logging +import org.apache.spark.sql.internal.SQLConf + +/** + * A thread-safe manager for [[CatalogPlugin]]s. It tracks all the registered catalogs, and allow + * the caller to look up a catalog by name. + */ +class CatalogManager(conf: SQLConf) extends Logging { + + private val catalogs = mutable.HashMap.empty[String, CatalogPlugin] + + def catalog(name: String): CatalogPlugin = synchronized { + catalogs.getOrElseUpdate(name, Catalogs.load(name, conf)) + } + + def defaultCatalog: Option[CatalogPlugin] = { + conf.defaultV2Catalog.flatMap { catalogName => + try { + Some(catalog(catalogName)) + } catch { + case NonFatal(e) => + logError(s"Cannot load default v2 catalog: $catalogName", e) + None + } + } + } + + def v2SessionCatalog: Option[CatalogPlugin] = { + try { + Some(catalog(CatalogManager.SESSION_CATALOG_NAME)) + } catch { + case NonFatal(e) => + logError("Cannot load v2 session catalog", e) + None + } + } + + private def getDefaultNamespace(c: CatalogPlugin) = c match { + case c: SupportsNamespaces => c.defaultNamespace() + case _ => Array.empty[String] + } + + private var _currentNamespace = { + // The builtin catalog use "default" as the default database. Review comment: I think current namespace only make sense to the current catalog, e.g. `SELECT ... FROM t`, `t` can be a table in the current catalog's current namespace. However, for `SELECT ... FROM c1.t`, it's confusing to say `t` is a table in catalog `c1`'s current namespace. When a table identifier starts with a catalog name, it should be a fully qualified identifier, and we can't apply current namespace here. catalog (including `V2SessionCatalog`) can report its default namespace, which will be used as the current namespace when switching to the catalog at the first time. ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
