Mailing-List: contact issues-help@flink.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@flink.apache.org
From: fhueske <git@git.apache.org>
To: issues@flink.incubator.apache.org
Reply-To: issues@flink.incubator.apache.org
References: <git-pr-1856-flink@git.apache.org>
In-Reply-To: <git-pr-1856-flink@git.apache.org>
Subject: [GitHub] flink pull request #1856: FLINK-3650 Add maxBy/minBy to Scala DataSet API
Content-Type: text/plain
Message-Id: <20160615130707.7ADE7DFC4F@git1-us-west.apache.org>
Date: Wed, 15 Jun 2016 13:07:07 +0000 (UTC)
archived-at: Wed, 15 Jun 2016 13:07:13 -0000

Github user fhueske commented on a diff in the pull request:

    https://github.com/apache/flink/pull/1856#discussion_r67157175
  
    --- Diff: flink-scala/src/test/scala/org/apache/flink/api/operator/SelectByFunctionTest.scala ---
    @@ -0,0 +1,250 @@
    +/*
    + * 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.flink.api.operator
    +
    +import org.apache.flink.api.common.ExecutionConfig
    +import org.apache.flink.api.common.typeinfo.BasicTypeInfo
    +import org.apache.flink.api.common.typeutils.TypeSerializer
    +import org.apache.flink.api.scala.{SelectByMaxFunction, SelectByMinFunction}
    +import org.apache.flink.api.scala.typeutils.CaseClassTypeInfo
    +import org.junit.{Assert, Test}
    +
    +/**
    +  *
    +  */
    +class SelectByFunctionTest {
    +
    +  val tupleTypeInfo = new CaseClassTypeInfo[scala.Tuple5[Int, Long, String, Long, Int]](
    +    classOf[scala.Tuple5[Int, Long, String, Long, Int]],
    +    Array(),
    +    Array(BasicTypeInfo.INT_TYPE_INFO, BasicTypeInfo.LONG_TYPE_INFO,
    +      BasicTypeInfo.STRING_TYPE_INFO,
    +      BasicTypeInfo.LONG_TYPE_INFO, BasicTypeInfo.INT_TYPE_INFO),
    +    Array("_1", "_2","_3","_4","_5")) {
    +    override def createSerializer(config: ExecutionConfig):
    +    TypeSerializer[(Int, Long, String, Long, Int)] = ???
    +  }
    +
    +  private val bigger : Tuple5[Int, Long, String, Long, Int]  =
    +    new scala.Tuple5[Int, Long, String, Long, Int](10, 100L, "HelloWorld", 200L, 20)
    +  private val smaller : Tuple5[Int, Long, String, Long, Int]  =
    +    new scala.Tuple5[Int, Long, String, Long, Int](5, 50L, "Hello", 50L, 15)
    +
    +  //Special case where only the last value determines if bigger or smaller
    +  private val specialCaseBigger : Tuple5[Int, Long, String, Long, Int]  =
    +    new scala.Tuple5[Int, Long, String, Long, Int](10, 100L, "HelloWorld", 200L, 17)
    +  private val specialCaseSmaller : Tuple5[Int, Long, String, Long, Int]  =
    +    new scala.Tuple5[Int, Long, String, Long, Int](5, 50L, "Hello", 50L, 17)
    +
    +  /**
    +    * This test validates whether the order of tuples has
    +    *
    +    * any impact on the outcome and if the bigger tuple is returned.
    +    */
    +  @Test
    +  def testMaxByComparison(): Unit = {
    +    val a1 = Array(0)
    +    val maxByTuple : SelectByMaxFunction[scala.Tuple5[Int, Long, String, Long, Int]] =
    +      new SelectByMaxFunction
    +        [scala.Tuple5[Int, Long, String, Long, Int]](tupleTypeInfo, a1)
    +      try {
    +        Assert.assertSame("SelectByMax must return bigger tuple",
    +          bigger, maxByTuple.reduce(smaller, bigger))
    +        Assert.assertSame("SelectByMax must return bigger tuple",
    +          bigger, maxByTuple.reduce(bigger, smaller))
    +      }catch {
    +        case e : Exception =>
    +          Assert.fail("No exception should be thrown while comapring both tuples")
    +      }
    +  }
    +
    +  // ----------------------- MAXIMUM FUNCTION TEST BELOW --------------------------
    +
    +  /**
    +    * This test cases checks when two tuples only differ in one value, but this value is not
    +    * in the fields list. In that case it should be seen as equal
    +    * and then the first given tuple (value1) should be returned by reduce().
    +    */
    +  @Test
    +  def testMaxByComparisonSpecialCase1() : Unit = {
    +    val a1 = Array(0, 3)
    +    val maxByTuple : SelectByMaxFunction[scala.Tuple5[Int, Long, String, Long, Int]] =
    +    new SelectByMaxFunction[scala.Tuple5[Int, Long, String, Long, Int]](tupleTypeInfo, a1)
    +
    +    try {
    +      Assert.assertSame("SelectByMax must return the first given tuple",
    +        specialCaseBigger, maxByTuple.reduce(specialCaseBigger, bigger))
    +      Assert.assertSame("SelectByMax must return the first given tuple",
    +        bigger, maxByTuple.reduce(bigger, specialCaseBigger))
    +    }catch {
    +      case e : Exception => Assert.fail("No exception should be thrown " +
    +        "while comapring both tuples")
    +    }
    +  }
    +
    +  /**
    +    * This test cases checks when two tuples only differ in one value.
    +    */
    +  @Test
    +  def testMaxByComparisonSpecialCase2() : Unit = {
    +    val a1 = Array(0, 2 ,1 ,4 ,3)
    --- End diff --
    
    ` ,` -> `, `


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---