dtenedor commented on code in PR #38823: URL: https://github.com/apache/spark/pull/38823#discussion_r1116016749
########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/GeneratedColumn.scala: ########## @@ -0,0 +1,160 @@ +/* + * 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.util + +import org.apache.spark.sql.AnalysisException +import org.apache.spark.sql.catalyst.analysis.Analyzer +import org.apache.spark.sql.catalyst.expressions.{Alias, Expression} +import org.apache.spark.sql.catalyst.parser.{CatalystSqlParser, ParseException} +import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, Project} +import org.apache.spark.sql.catalyst.util.ResolveDefaultColumns.BuiltInFunctionCatalog +import org.apache.spark.sql.connector.catalog.CatalogManager +import org.apache.spark.sql.errors.QueryCompilationErrors.toSQLId +import org.apache.spark.sql.types.{StructField, StructType} + +/** + * This object contains utility methods and values for Generated Columns + */ +object GeneratedColumn { + + /** + * The metadata key for saving a generation expression in a generated column's metadata. This is + * only used internally and connectors should access generation expressions from the V2 columns. + */ + val GENERATION_EXPRESSION_METADATA_KEY = "generationExpression" + + /** Parser for parsing generation expression SQL strings */ + private lazy val parser = new CatalystSqlParser() + + /** + * Whether the given `field` is a generated column + */ + def isGeneratedColumn(field: StructField): Boolean = { + field.metadata.contains(GENERATION_EXPRESSION_METADATA_KEY) + } + + /** + * Returns the generation expression stored in the column metadata if it exists + */ + def getGenerationExpression(field: StructField): Option[String] = { + if (isGeneratedColumn(field)) { + Some(field.metadata.getString(GENERATION_EXPRESSION_METADATA_KEY)) + } else { + None + } + } + + /** + * Whether the `schema` has one or more generated columns + */ + def hasGeneratedColumns(schema: StructType): Boolean = { + schema.exists(isGeneratedColumn) + } + + /** + * Parse and analyze `expressionStr` and perform verification. This means: + * - The expression cannot refer to itself + * - No user-defined expressions Review Comment: Yes. Currently it would just return a generic "function not found" error. Originally I forwarded the original analyzer in there in hopes of returning a more explicit "UDF not supported" error message instead in that case. But we found the code to do that to be very complex, and ended up preferring the separate analyzer instead. -- 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: reviews-unsubscr...@spark.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org
