leesf commented on a change in pull request #2761: URL: https://github.com/apache/hudi/pull/2761#discussion_r614780712
########## File path: hudi-spark-datasource/hudi-spark3-extensions_2.12/src/main/scala/org/apache/spark/sql/hudi/execution/MergeIntoHudiTable.scala ########## @@ -0,0 +1,332 @@ +/* + * 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.hudi.execution + +import org.apache.hudi.DataSourceWriteOptions.{DEFAULT_PAYLOAD_OPT_VAL, PAYLOAD_CLASS_OPT_KEY, RECORDKEY_FIELD_OPT_KEY} +import org.apache.hudi.common.model.{OverwriteNonDefaultsWithLatestAvroPayload, WriteOperationType} +import org.apache.hudi.execution.HudiSQLUtils +import org.apache.spark.internal.Logging +import org.apache.spark.sql._ +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.encoders.{ExpressionEncoder, RowEncoder} +import org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate +import org.apache.spark.sql.catalyst.merge._ +import org.apache.spark.sql.catalyst.expressions.{And, Attribute, BasePredicate, Expression, Literal, PredicateHelper, UnsafeProjection} +import org.apache.spark.sql.functions.{col, lit, when} +import org.apache.spark.sql.catalyst.merge.{HudiMergeClause, HudiMergeInsertClause} +import org.apache.spark.sql.catalyst.plans.logical.{LocalRelation, LogicalPlan, Project} +import org.apache.spark.sql.execution.command.RunnableCommand +import org.apache.spark.sql.internal.StaticSQLConf +import org.apache.spark.sql.types.{StringType, StructType} + +import scala.collection.mutable.ArrayBuffer + +/** + * merge command, execute merge operation for hudi + */ +case class MergeIntoHudiTable( + target: LogicalPlan, + source: LogicalPlan, + joinCondition: Expression, + matchedClauses: Seq[HudiMergeClause], + noMatchedClause: Seq[HudiMergeInsertClause], + finalSchema: StructType, + trimmedSchema: StructType) extends RunnableCommand with Logging with PredicateHelper { + + var tableMeta: Map[String, String] = null + + lazy val isRecordKeyJoin = { + val recordKeyFields = tableMeta.get(RECORDKEY_FIELD_OPT_KEY).get.split(",").map(_.trim).filter(!_.isEmpty) + val intersect = joinCondition.references.intersect(target.outputSet).toSeq + if (recordKeyFields.size == 1 && intersect.size ==1 && intersect(0).name.equalsIgnoreCase(recordKeyFields(0))) { + true + } else { + false + } + } + + override def run(sparkSession: SparkSession): Seq[Row] = { + tableMeta = HudiSQLUtils.getHoodiePropsFromRelation(target, sparkSession) + val enableHive = "hive" == sparkSession.sessionState.conf.getConf(StaticSQLConf.CATALOG_IMPLEMENTATION) Review comment: here please the logic put into a method called `hiveCatalogImplementaion`to be reused -- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org
