flink-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From fhueske <...@git.apache.org>
Subject [GitHub] flink pull request #3714: [FLINK-6075] - Support Limit/Top(Sort) for Stream ...
Date Wed, 19 Apr 2017 15:02:23 GMT
Github user fhueske commented on a diff in the pull request:

    https://github.com/apache/flink/pull/3714#discussion_r112225554
  
    --- Diff: flink-libraries/flink-table/src/main/scala/org/apache/flink/table/runtime/aggregate/ProcTimeBoundedSortProcessFunction.scala
---
    @@ -0,0 +1,114 @@
    +/*
    + * 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.runtime.aggregate
    +
    +import org.apache.flink.api.common.state.{ ListState, ListStateDescriptor }
    +import org.apache.flink.api.java.typeutils.RowTypeInfo
    +import org.apache.flink.configuration.Configuration
    +import org.apache.flink.runtime.state.{ FunctionInitializationContext, FunctionSnapshotContext
}
    +import org.apache.flink.streaming.api.functions.ProcessFunction
    +import org.apache.flink.table.functions.{ Accumulator, AggregateFunction }
    +import org.apache.flink.types.Row
    +import org.apache.flink.util.{ Collector, Preconditions }
    +import org.apache.flink.api.common.state.ValueState
    +import org.apache.flink.api.common.state.ValueStateDescriptor
    +import scala.util.control.Breaks._
    +import org.apache.flink.api.java.tuple.{ Tuple2 => JTuple2 }
    +import org.apache.flink.api.common.state.MapState
    +import org.apache.flink.api.common.state.MapStateDescriptor
    +import org.apache.flink.api.common.typeinfo.TypeInformation
    +import org.apache.flink.api.java.typeutils.ListTypeInfo
    +import java.util.LinkedList
    +import java.util.Comparator
    +
    +
    +/**
    + * Process Function used for the aggregate in bounded proctime sort without offset/fetch
    + * [[org.apache.flink.streaming.api.datastream.DataStream]]
    + *
    + * @param fieldCount Is used to indicate fields in the current element to forward
    + * @param inputType It is used to mark the type of the incoming data
    + * @param rowComparator the [[java.util.Comparator]] is used for this sort aggregation
    + */
    +class ProcTimeBoundedSortProcessFunction(
    +  private val fieldCount: Int,
    +  private val inputType: TypeInformation[Row],
    +  private val rowComparator:Comparator[Row])
    +    extends ProcessFunction[Row, Row] {
    +
    +  Preconditions.checkNotNull(rowComparator)
    +
    +  private var stateEventsBuffer: ListState[Row] = _
    +
    +  override def open(config: Configuration) {
    +    val sortDescriptor = new ListStateDescriptor[Row]("sortState", inputType)
    +    stateEventsBuffer = getRuntimeContext.getListState(sortDescriptor)
    +  }
    +
    +  override def processElement(
    +    input: Row,
    +    ctx: ProcessFunction[Row, Row]#Context,
    +    out: Collector[Row]): Unit = {
    +
    +    val currentTime = ctx.timerService.currentProcessingTime
    +    //buffer the event incoming event
    +  
    +    //we accumulate the events as they arrive within the given proctime
    +    stateEventsBuffer.add(input)
    +    
    +    //deduplication of multiple registered timers is done automatically
    +    ctx.timerService.registerProcessingTimeTimer(currentTime + 1)  
    +    
    +  }
    +  
    +  override def onTimer(
    +    timestamp: Long,
    +    ctx: ProcessFunction[Row, Row]#OnTimerContext,
    +    out: Collector[Row]): Unit = {
    +    
    +    var i = 0
    +    val sortList = new LinkedList[Row]
    --- End diff --
    
    Reuse an `ArrayList` which creates fewer objects.


---
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.
---

Mime
View raw message