pengzhiwei2018 commented on a change in pull request #2645: URL: https://github.com/apache/hudi/pull/2645#discussion_r607469389
########## File path: hudi-spark-datasource/hudi-spark/src/test/scala/org/apache/spark/sql/hudi/MergeIntoTest.scala ########## @@ -0,0 +1,183 @@ +/* + * 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 + +import org.apache.spark.sql.Row + +class MergeIntoTest extends HoodieBaseSqlTest { + + test("Test MergeInto") { + withTempDir { tmp => + val tableName = generateTableName + // Create table + spark.sql( + s""" + |create table $tableName ( + | id int, + | name string, + | price double, + | ts long + |) using hudi + | location '${tmp.getCanonicalPath}' + | options ( + | primaryKey ='id', + | versionColumn = 'ts' + | ) + """.stripMargin) + + // First merge (insert a new record) + spark.sql( + s""" + | merge into $tableName + | using ( + | select 1 as id, 'a1' as name, 10 as price, 1000 as ts + | ) s0 + | on s0.id = $tableName.id + | when matched then update set + | id = s0.id, name = s0.name, price = s0.price, ts = s0.ts + | when not matched then insert * + """.stripMargin) + val queryResult1 = spark.sql(s"select id, name, price, ts from $tableName").collect() + assertResult(Array(Row(1, "a1", 10.0, 1000)))(queryResult1) + + // second merge (update the record) + spark.sql( + s""" + | merge into $tableName + | using ( + | select 1 as id, 'a1' as name, 10 as price, 1001 as ts + | ) s0 + | on s0.id = $tableName.id + | when matched then update set + | id = s0.id, name = s0.name, price = s0.price + $tableName.price, ts = s0.ts + | when not matched then insert * + """.stripMargin) + val queryResult2 = spark.sql(s"select id, name, price, ts from $tableName").collect() + assertResult(Array(Row(1, "a1", 20.0, 1001)))(queryResult2) + + // the third time merge (update & insert the record) + spark.sql( + s""" + | merge into $tableName + | using ( + | select * from ( + | select 1 as id, 'a1' as name, 10 as price, 1002 as ts + | union all + | select 2 as id, 'a2' as name, 12 as price, 1001 as ts + | ) + | ) s0 + | on s0.id = $tableName.id + | when matched then update set + | id = s0.id, name = s0.name, price = s0.price + $tableName.price, ts = s0.ts + | when not matched and id % 2 = 0 then insert * + """.stripMargin) + val queryResult3 = spark.sql(s"select id, name, price, ts from $tableName").collect() + assertResult(Array(Row(1, "a1", 30.0, 1002), Row(2, "a2", 12.0, 1001)))(queryResult3) + + // the fourth merge (delete the record) + spark.sql( + s""" + | merge into $tableName + | using ( + | select 1 as id, 'a1' as name, 12 as price, 1003 as ts + | ) s0 + | on s0.id = $tableName.id + | when matched and id != 1 then update set + | id = s0.id, name = s0.name, price = s0.price, ts = s0.ts + | when matched and id = 1 then delete Review comment: The match-delete condition can support other columns too. The condition `when matched and ts = 1002` can work well. I will add a test case for this. -- 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
