aokolnychyi commented on code in PR #40308: URL: https://github.com/apache/spark/pull/40308#discussion_r1128943386
########## sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/AssignmentUtils.scala: ########## @@ -0,0 +1,275 @@ +/* + * 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 +import org.apache.spark.sql.catalyst.SQLConfHelper +import org.apache.spark.sql.catalyst.expressions.{Alias, Attribute, AttributeReference, CreateNamedStruct, Expression, ExtractValue, GetStructField, Literal, NamedExpression} +import org.apache.spark.sql.catalyst.plans.logical.Assignment +import org.apache.spark.sql.catalyst.util.CharVarcharUtils +import org.apache.spark.sql.connector.catalog.CatalogV2Implicits._ +import org.apache.spark.sql.errors.QueryCompilationErrors +import org.apache.spark.sql.internal.SQLConf.StoreAssignmentPolicy +import org.apache.spark.sql.types.{ArrayType, DataType, MapType, StructType} + +object AssignmentUtils extends SQLConfHelper with CastSupport { + + private case class ColumnUpdate(ref: Seq[String], expr: Expression) + + /** + * Aligns assignments to match table columns. + * <p> + * This method processes and reorders given assignments so that each target column gets + * an expression it should be set to. If a column does not have a matching assignment, + * it will be set to its current value. For example, if one passes table attributes c1, c2 + * and an assignment c2 = 1, this method will return c1 = c1, c2 = 1. + * <p> + * This method also handles updates to nested columns. If there is an assignment to a particular + * nested field, this method will construct a new struct with one field updated preserving other + * fields that have not been modified. For example, if one passes table attributes c1, c2 + * where c2 is a struct with fields n1 and n2 and an assignment c2.n2 = 1, this method will + * return c1 = c1, c2 = struct(c2.n1, 1). + * + * @param attrs table attributes + * @param assignments assignments to align + * @return aligned assignments that match table columns + */ + def alignAssignments( + attrs: Seq[Attribute], + assignments: Seq[Assignment]): Seq[Assignment] = { + + val errors = new mutable.ArrayBuffer[String]() + + val output = applyUpdates( + updates = assignments.map(toColumnUpdate), + cols = attrs.map(restoreActualType), + colExprs = attrs, + addError = err => errors += err) + + if (errors.nonEmpty) { + throw QueryCompilationErrors.invalidRowLevelOperationAssignments(assignments, errors.toSeq) + } + + attrs.zip(output).map { case (attr, expr) => Assignment(attr, expr) } + } + + private def toColumnUpdate(assignment: Assignment): ColumnUpdate = { + ColumnUpdate(toRef(assignment.key), assignment.value) + } + + private def restoreActualType(attr: Attribute): Attribute = { + attr.withDataType(CharVarcharUtils.getRawType(attr.metadata).getOrElse(attr.dataType)) + } + + private def applyUpdates( + updates: Seq[ColumnUpdate], + cols: Seq[Attribute], + colExprs: Seq[Expression], + addError: String => Unit, + colPath: Seq[String] = Nil): Seq[Expression] = { + + // iterate through columns at the current level and find matching updates + cols.zip(colExprs).map { case (col, colExpr) => + // find matches for this column or any of its children + val prefixMatchedUpdates = updates.filter(update => conf.resolver(update.ref.head, col.name)) + prefixMatchedUpdates match { + // if there is no exact match and no match for children, return the column expr as is + case matchedUpdates if matchedUpdates.isEmpty => + colExpr Review Comment: Note: I am skipping char/varchar length checks when a field is assigned to itself (i.e. did not change). -- 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