Mailing-List: contact issues-help@flink.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@flink.apache.org
Date: Tue, 2 May 2017 23:40:04 +0000 (UTC)
From: "ASF GitHub Bot (JIRA)" <jira@apache.org>
To: issues@flink.apache.org
Message-ID: <JIRA.13045970.1487930314000.109849.1493768404544@Atlassian.JIRA>
In-Reply-To: <JIRA.13045970.1487930314000@Atlassian.JIRA>
References: <JIRA.13045970.1487930314000@Atlassian.JIRA> <JIRA.13045970.1487930314361@jira-lw-us.apache.org>
Subject: [jira] [Commented] (FLINK-5906) Add support to register UDAGG in
 Table and SQL API
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
archived-at: Tue, 02 May 2017 23:40:09 -0000


    [ https://issues.apache.org/jira/browse/FLINK-5906?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15994026#comment-15994026 ] 

ASF GitHub Bot commented on FLINK-5906:
---------------------------------------

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

    https://github.com/apache/flink/pull/3809#discussion_r114449859
  
    --- Diff: flink-libraries/flink-table/src/test/scala/org/apache/flink/table/api/scala/stream/table/DStreamUDAGGITCase.scala ---
    @@ -0,0 +1,309 @@
    +/*
    + * 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.table.api.scala.stream.table
    +
    +import java.math.BigDecimal
    +
    +import org.apache.flink.api.java.typeutils.RowTypeInfo
    +import org.apache.flink.api.scala._
    +import org.apache.flink.streaming.api.functions.AssignerWithPunctuatedWatermarks
    +import org.apache.flink.streaming.api.scala.StreamExecutionEnvironment
    +import org.apache.flink.streaming.api.TimeCharacteristic
    +import org.apache.flink.table.utils.TableTestBase
    +import org.apache.flink.streaming.api.datastream.{DataStream => JDataStream}
    +import org.apache.flink.streaming.api.environment.{StreamExecutionEnvironment => JavaExecutionEnv}
    +import org.apache.flink.streaming.api.scala.{DataStream, StreamExecutionEnvironment => ScalaExecutionEnv}
    +import org.apache.flink.streaming.api.watermark.Watermark
    +import org.apache.flink.table.api.java.utils.UserDefinedAggFunctions.{WeightedAvg, WeightedAvgWithMerge, WeightedAvgWithRetract}
    +import org.apache.flink.table.api.scala._
    +import org.apache.flink.table.api.scala.stream.table.DStreamUDAGGITCase.TimestampAndWatermarkWithOffset
    +import org.apache.flink.table.api.scala.stream.utils.StreamITCase
    +import org.apache.flink.table.api.{SlidingWindow, TableEnvironment, Types}
    +import org.apache.flink.streaming.util.StreamingMultipleProgramsTestBase
    +import org.apache.flink.table.functions.aggfunctions.CountAggFunction
    +import org.apache.flink.types.Row
    +import org.junit.Assert._
    +import org.junit.Test
    +import org.mockito.Mockito.{mock, when}
    +
    +import scala.collection.mutable
    +
    +/**
    +  * We only test some aggregations until better testing of constructed DataStream
    +  * programs is possible.
    +  */
    +class DStreamUDAGGITCase
    +  extends StreamingMultipleProgramsTestBase {
    +
    +  val data = List(
    +    //('long, 'int, 'double, 'float, 'bigdec, 'string)
    +    (1000L, 1, 1d, 1f, new BigDecimal("1"), "Hello"),
    +    (2000L, 2, 2d, 2f, new BigDecimal("2"), "Hello"),
    +    (3000L, 3, 3d, 3f, new BigDecimal("3"), "Hello"),
    +    (5000L, 5, 5d, 5f, new BigDecimal("5"), "Hi"),
    +    (6000L, 6, 6d, 6f, new BigDecimal("6"), "Hi"),
    +    (7000L, 7, 7d, 7f, new BigDecimal("7"), "Hi"),
    +    (8000L, 8, 8d, 8f, new BigDecimal("8"), "Hello"),
    +    (9000L, 9, 9d, 9f, new BigDecimal("9"), "Hello"),
    +    (4000L, 4, 4d, 4f, new BigDecimal("4"), "Hello"),
    +    (10000L, 10, 10d, 10f, new BigDecimal("10"), "Hi"),
    +    (11000L, 11, 11d, 11f, new BigDecimal("11"), "Hi"),
    +    (12000L, 12, 12d, 12f, new BigDecimal("12"), "Hi"),
    +    (16000L, 16, 16d, 16f, new BigDecimal("16"), "Hello"))
    +
    +  @Test
    +  def testUdaggSlidingWindowGroupedAggregate(): Unit = {
    +    val env = StreamExecutionEnvironment.getExecutionEnvironment
    +    env.setParallelism(1)
    +    val tEnv = TableEnvironment.getTableEnvironment(env)
    +    StreamITCase.testResults = mutable.MutableList()
    +
    +    val stream = env.fromCollection(data).map(t => (t._1, t._2, t._3, t._4, t._6))
    +    val table = stream.toTable(tEnv, 'long, 'int, 'double, 'float, 'string)
    +
    +    val countFun = new CountAggFunction
    +
    +    val weightAvgFun = new WeightedAvg
    +
    +    val windowedTable = table
    +      .window(Slide over 4.rows every 2.rows as 'w)
    +      .groupBy('w, 'string)
    +      .select(
    +        'string,
    +        countFun('float),
    +        'double.sum,
    +        weightAvgFun('long, 'int),
    +        weightAvgFun('int, 'int))
    +
    +    val results = windowedTable.toDataStream[Row]
    +    results.addSink(new StreamITCase.StringSink)
    +    env.execute()
    +
    +    val expected = Seq(
    +      "Hello,2,3.0,1666,1", "Hi,2,11.0,5545,5", "Hello,4,14.0,5571,5",
    +      "Hello,4,24.0,7083,7", "Hi,4,28.0,7500,7", "Hi,4,40.0,10350,10")
    +    assertEquals(expected, StreamITCase.testResults)
    +  }
    +
    +  @Test
    +  def testUdaggSessionWindowGroupedAggregate(): Unit = {
    +    val env = StreamExecutionEnvironment.getExecutionEnvironment
    +    env.setStreamTimeCharacteristic(TimeCharacteristic.EventTime)
    +    env.setParallelism(1)
    +    val tEnv = TableEnvironment.getTableEnvironment(env)
    +    StreamITCase.testResults = mutable.MutableList()
    +
    +    val countFun = new CountAggFunction
    +
    +    val weightAvgWithMergeFun = new WeightedAvgWithMerge
    +
    +    val stream = env
    +      .fromCollection(data)
    +      .assignTimestampsAndWatermarks(new TimestampAndWatermarkWithOffset(10000))
    --- End diff --
    
    use `.assignAscendingTimestamps(_._1)` instead?


> Add support to register UDAGG in Table and SQL API
> --------------------------------------------------
>
>                 Key: FLINK-5906
>                 URL: https://issues.apache.org/jira/browse/FLINK-5906
>             Project: Flink
>          Issue Type: Sub-task
>          Components: Table API & SQL
>            Reporter: Fabian Hueske
>            Assignee: Shaoxuan Wang
>


--
This message was sent by Atlassian JIRA
(v6.3.15#6346)