aokolnychyi commented on a change in pull request #3763: URL: https://github.com/apache/iceberg/pull/3763#discussion_r773437090
########## File path: spark/v3.2/spark-extensions/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/WriteDelta.scala ########## @@ -0,0 +1,98 @@ +/* + * 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.plans.logical + +import org.apache.spark.sql.catalyst.analysis.NamedRelation +import org.apache.spark.sql.catalyst.expressions.NamedExpression +import org.apache.spark.sql.catalyst.util.CharVarcharUtils +import org.apache.spark.sql.catalyst.util.RowDeltaUtils.OPERATION_COLUMN +import org.apache.spark.sql.catalyst.util.WriteDeltaProjections +import org.apache.spark.sql.connector.iceberg.write.DeltaWrite +import org.apache.spark.sql.types.DataType +import org.apache.spark.sql.types.IntegerType +import org.apache.spark.sql.types.StructField + +/** + * Writes a delta of rows to an existing table. + */ +case class WriteDelta( + table: NamedRelation, + query: LogicalPlan, + originalTable: NamedRelation, + projections: WriteDeltaProjections, + write: Option[DeltaWrite] = None) extends V2WriteCommandLike { + + override protected lazy val stringArgs: Iterator[Any] = Iterator(table, query, write) + + private def operationResolved: Boolean = { + val attr = query.output.head + attr.name == OPERATION_COLUMN && attr.dataType == IntegerType && !attr.nullable + } + + private def rowAttrsResolved: Boolean = { + table.skipSchemaResolution || (projections.rowProjection match { + case Some(projection) => + table.output.size == projection.schema.size && + projection.schema.zip(table.output).forall { case (field, outAttr) => + isCompatible(field, outAttr) + } + case None => true + }) + } + + private def rowIdAttrsResolved: Boolean = { + projections.rowIdProjection.schema.forall { field => + originalTable.resolve(Seq(field.name), conf.resolver) match { Review comment: Well, it is a little bit tricky. The actual type is defined by the projection. For example, consider MERGE operations. The incoming plan will have wrong nullability for metadata and row ID columns (they will be always nullable as those columns are null for records to insert). However, we never pass row ID or metadata columns with inserts. We only pass them with updates and deletes where those columns have correct values. In other words, the projection has more precise types. The existing logic validates that whatever the projections produce satisfy the target output attributes. That being said, you are also right that we probably need some validation that we can actually project those columns from query... What do you think, @rdblue? -- 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]
