Github user rxin commented on a diff in the pull request: https://github.com/apache/spark/pull/14116#discussion_r70323673 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/systemcatalog/InformationSchema.scala --- @@ -0,0 +1,336 @@ +/* + * 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.systemcatalog + +import java.sql.{Date, Timestamp} + +import scala.collection.mutable.ArrayBuffer + +import org.apache.commons.lang3.StringUtils + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql._ +import org.apache.spark.sql.catalyst.dsl.plans._ +import org.apache.spark.sql.catalyst.expressions.Alias +import org.apache.spark.sql.catalyst.plans.logical.Project +import org.apache.spark.sql.execution.datasources._ +import org.apache.spark.sql.sources._ +import org.apache.spark.sql.types._ + +/** + * INFORMATION_SCHEMA is a database consisting views which provide information about all of the + * tables, views, columns in a database. + */ +object InformationSchema { + val INFORMATION_SCHEMA = "information_schema" + /** + * Register INFORMATION_SCHEMA database. + */ + def registerInformationSchema(sparkSession: SparkSession): Unit = { + sparkSession.sql(s"CREATE DATABASE IF NOT EXISTS $INFORMATION_SCHEMA") + registerView(sparkSession, new DatabasesRelationProvider, Seq("schemata", "databases")) + registerView(sparkSession, new TablesRelationProvider, Seq("tables")) + registerView(sparkSession, new ViewsRelationProvider, Seq("views")) + registerView(sparkSession, new ColumnsRelationProvider, Seq("columns")) + registerView(sparkSession, new SessionVariablesRelationProvider, Seq("session_variables")) + } + + /** + * Register a INFORMATION_SCHEMA relation provider as a temporary view of Spark Catalog. + */ + private def registerView( + sparkSession: SparkSession, + relationProvider: SchemaRelationProvider, + names: Seq[String]) { + val plan = + LogicalRelation(relationProvider.createRelation(sparkSession.sqlContext, null, null)).analyze + val projectList = plan.output.zip(plan.schema).map { + case (attr, col) => Alias(attr, col.name)() + } + sparkSession.sessionState.executePlan(Project(projectList, plan)) + for (name <- names) { + // TODO(dongjoon): This is a hack to give a database concept for Spark temporary views. + // We should generalize this later. + sparkSession.sessionState.catalog.createTempView(s"$INFORMATION_SCHEMA.$name", + plan, overrideIfExists = true) + } + } + + /** + * Compile filter array into single string condition. + */ + private[systemcatalog] def getConditionExpressionString(filters: Array[Filter]): String = { + val str = filters.flatMap(InformationSchema.compileFilter).map(p => s"($p)").mkString(" AND ") + if (str.length == 0) "TRUE" else str + } + + /** + * Convert filter into string expression. + */ + private[systemcatalog] def compileFilter(f: Filter): Option[String] = { --- End diff -- Sorry I'm pretty confused. Why do we need this at all? I was thinking just doing some very basic predicate pushdown, e.g. when calling list tables, if the database name is specified, then we don't need to get all the tables that are not part of the database out of the catalog. Same thing with basic pattern matching. I didn't look very closely, but the way this is working is very complicated and does not actually push anything into the catalog. It is basically doing no-op.
--- 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