zhenlineo commented on code in PR #40581: URL: https://github.com/apache/spark/pull/40581#discussion_r1158884111
########## connector/connect/client/jvm/src/test/scala/org/apache/spark/sql/UserDefinedFunctionE2ETestSuite.scala: ########## @@ -0,0 +1,131 @@ +/* + * 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 + +import java.lang.{Long => JLong} +import java.util.{Iterator => JIterator} +import java.util.Arrays + +import scala.collection.JavaConverters._ + +import org.apache.spark.api.java.function._ +import org.apache.spark.sql.catalyst.encoders.AgnosticEncoders.{PrimitiveIntEncoder, PrimitiveLongEncoder} +import org.apache.spark.sql.connect.client.util.RemoteSparkSession +import org.apache.spark.sql.functions.{col, udf} + +/** + * All tests in this class requires client UDF artifacts synced with the server. TODO: It means + * these tests only works with SBT for now. + */ +class UserDefinedFunctionE2ETestSuite extends RemoteSparkSession { + test("Dataset typed filter") { + val rows = spark.range(10).filter(n => n % 2 == 0).collectAsList() + assert(rows == Arrays.asList[Long](0, 2, 4, 6, 8)) + } + + test("Dataset typed filter - java") { + val rows = spark + .range(10) + .filter(new FilterFunction[JLong] { + override def call(value: JLong): Boolean = value % 2 == 0 + }) + .collectAsList() + assert(rows == Arrays.asList[Long](0, 2, 4, 6, 8)) + } + + test("Dataset typed map") { + val rows = spark.range(10).map(n => n / 2)(PrimitiveLongEncoder).collectAsList() + assert(rows == Arrays.asList[Long](0, 0, 1, 1, 2, 2, 3, 3, 4, 4)) + } + + test("filter with condition") { + // This should go via `def filter(condition: Column)` rather than + // `def filter(func: T => Boolean)` + def func(i: Long): Boolean = i < 5 + val under5 = udf(func _) + val longs = spark.range(10).filter(under5(col("id") * 2)).collectAsList() + assert(longs == Arrays.asList[Long](0, 1, 2)) + } + + test("filter with col(*)") { Review Comment: Note this test will run the udf as typed filter 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: [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]
