dtenedor commented on a change in pull request #35855: URL: https://github.com/apache/spark/pull/35855#discussion_r832422708
########## File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/ResolveDefaultColumns.scala ########## @@ -0,0 +1,354 @@ +/* + * 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 org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst.TableIdentifier +import org.apache.spark.sql.catalyst.analysis.ResolveDefaultColumns._ +import org.apache.spark.sql.catalyst.catalog._ +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.optimizer.ConstantFolding +import org.apache.spark.sql.catalyst.parser.{CatalystSqlParser, ParseException} +import org.apache.spark.sql.catalyst.plans.logical._ +import org.apache.spark.sql.catalyst.rules.Rule +import org.apache.spark.sql.catalyst.trees.AlwaysProcess +import org.apache.spark.sql.internal.SQLConf +import org.apache.spark.sql.types._ + +/** + * This is a rule to process DEFAULT columns in statements such as CREATE/REPLACE TABLE. + * + * Background: CREATE TABLE and ALTER TABLE invocations support setting column default values for + * later operations. Following INSERT, and INSERT MERGE commands may then reference the value + * using the DEFAULT keyword as needed. + * + * Example: + * CREATE TABLE T(a INT DEFAULT 4, b INT NOT NULL DEFAULT 5); + * INSERT INTO T VALUES (1, 2); + * INSERT INTO T VALUES (1, DEFAULT); + * INSERT INTO T VALUES (DEFAULT, 6); + * SELECT * FROM T; + * (1, 2) + * (1, 5) + * (4, 6) + * + * @param catalog the catalog to use for looking up the schema of INSERT INTO table objects. + * @param insert the enclosing INSERT statement for which this rule is processing the query, if any. + */ +case class ResolveDefaultColumns( + catalog: SessionCatalog, insert: Option[InsertIntoStatement] = None) extends Rule[LogicalPlan] { + override def apply(plan: LogicalPlan): LogicalPlan = plan.resolveOperatorsWithPruning( + AlwaysProcess.fn, ruleId) { + + case i@InsertIntoStatement(_, _, _, _, _, _) + if SQLConf.get.enableDefaultColumns && + i.query.collectFirst { case u: UnresolvedInlineTable => u }.isDefined => + val newQuery = ResolveDefaultColumns(catalog, Some(i)).apply(i.query) Review comment: Good question: this is actually the intent to transform recursively, specifically only on the subplan in `i.query`. In this way, the following case matching against `UnresolvedInlineTable` may trigger anywhere that the corresponding `values` list appears in that subplan (e.g. `insert into t select * from values(...)` or more complex cases ending in `values`). I left a comment explaining this here. Otherwise in the more complex cases, the analyzer simply errors that `default` was not found in those cases. If this SG to you, we can leave it as-is. Otherwise, if you prefer to only match the `i.query` against (`UnresolvedInlineTable` or `Project <- UnresolvedInlineTable`), let me know and I can make that change. We could possibly add another `case` then to `find` if any unresolved `default` references exist in any nested `values`, and return a more specific error message in that case to help guide the user. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
