[
https://issues.apache.org/jira/browse/FLINK-5803?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15899274#comment-15899274
]
ASF GitHub Bot commented on FLINK-5803:
---------------------------------------
Github user fhueske commented on a diff in the pull request:
https://github.com/apache/flink/pull/3397#discussion_r104642668
--- Diff:
flink-libraries/flink-table/src/main/scala/org/apache/flink/table/plan/nodes/datastream/DataStreamOverAggregate.scala
---
@@ -0,0 +1,199 @@
+/*
+ * 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.plan.nodes.datastream
+
+import org.apache.calcite.plan.{RelOptCluster, RelTraitSet}
+import org.apache.calcite.rel.`type`.RelDataType
+import org.apache.calcite.rel.core.AggregateCall
+import org.apache.calcite.rel.{RelNode, RelWriter, SingleRel}
+import org.apache.flink.api.java.typeutils.RowTypeInfo
+import org.apache.flink.streaming.api.datastream.DataStream
+import org.apache.flink.table.api.{StreamTableEnvironment, TableException}
+import org.apache.flink.table.calcite.FlinkTypeFactory
+import
org.apache.flink.table.runtime.aggregate.AggregateUtil.{CalcitePair, _}
+import org.apache.flink.table.runtime.aggregate._
+import org.apache.flink.table.plan.nodes.OverAggregate
+import org.apache.flink.types.Row
+import org.apache.calcite.rel.core.Window
+import org.apache.calcite.rel.core.Window.Group
+import java.util.{List => JList}
+
+import org.apache.flink.table.functions.{ProcTimeType, RowTimeType}
+
+import scala.collection.JavaConverters._
+import scala.collection.immutable.IndexedSeq
+
+class DataStreamOverAggregate(
+ logicWindow: Window,
+ cluster: RelOptCluster,
+ traitSet: RelTraitSet,
+ inputNode: RelNode,
+ rowRelDataType: RelDataType,
+ inputType: RelDataType)
+ extends SingleRel(cluster, traitSet, inputNode)
+ with OverAggregate
+ with DataStreamRel {
+
+ override def deriveRowType(): RelDataType = rowRelDataType
+
+ override def copy(traitSet: RelTraitSet, inputs: JList[RelNode]):
RelNode = {
+ new DataStreamOverAggregate(
+ logicWindow,
+ cluster,
+ traitSet,
+ inputs.get(0),
+ getRowType,
+ inputType)
+ }
+
+ override def toString: String = {
+ s"OverAggregate(${aggOpName})"
+ }
+
+ override def explainTerms(pw: RelWriter): RelWriter = {
+ val (
+ overWindow: Group,
+ partition: Array[Int],
+ namedAggregates: IndexedSeq[CalcitePair[AggregateCall, String]]
+ ) = genPartitionKeysAndNamedAggregates
+
+ super.explainTerms(pw)
+ .itemIf("partitionBy", partitionToString(inputType, partition),
partition.nonEmpty)
+ .item("orderBy",orderingToString(inputType,
overWindow.orderKeys.getFieldCollations))
+ .item("range", windowRange(overWindow))
+ .item(
+ "select", aggregationToString(
+ inputType,
+ getRowType,
+ namedAggregates))
+ }
+
+ override def translateToPlan(tableEnv: StreamTableEnvironment):
DataStream[Row] = {
+ if (logicWindow.groups.size > 1) {
+ throw new TableException(
+ "Unsupported use of OVER windows. All aggregates must be computed
on the same window.")
+ }
+
+ val overWindow: org.apache.calcite.rel.core.Window.Group =
logicWindow.groups.get(0)
+
+ val inputDS =
input.asInstanceOf[DataStreamRel].translateToPlan(tableEnv)
+
+ if (overWindow.orderKeys.getFieldCollations.size() != 1) {
+ throw new TableException(
+ "Unsupported use of OVER windows. The window may only be ordered
by a single time column.")
+ }
+
+ val timeType = inputType
+ .getFieldList
+ .get(overWindow.orderKeys.getFieldCollations.get(0).getFieldIndex)
+ .getValue
+
+ timeType match {
+ case _: ProcTimeType =>
+ // both ROWS and RANGE clause with UNBOUNDED PRECEDING and CURRENT
ROW condition.
+ if (overWindow.lowerBound.isUnbounded &&
+ overWindow.upperBound.isCurrentRow) {
+ createUnboundedAndCurrentRowProcessingTimeOverWindow(inputDS)
+ } else {
+ throw new TableException(
+ "OVER window only support ProcessingTime UNBOUNDED PRECEDING
and CURRENT ROW " +
+ "condition.")
+ }
+ case _: RowTimeType =>
+ throw new TableException("OVER Window of the EventTime type is not
currently supported.")
+ case _ =>
+ throw new TableException(s"Unsupported time type {$timeType}")
+ }
+
+ }
+
+ def createUnboundedAndCurrentRowProcessingTimeOverWindow(
+ inputDS: DataStream[Row]): DataStream[Row] = {
+
+ val (_,
+ partition: Array[Int],
+ namedAggregates: IndexedSeq[CalcitePair[AggregateCall, String]]
+ ) = genPartitionKeysAndNamedAggregates
--- End diff --
change `genPartitionKeysAndNamedAggregates()` to only generate named
aggregates and rename.
Functions that do only one thing are easier to understand and partition
keys can be generated in one line: `overWindow.keys.toArray`.
> Add [partitioned] processing time OVER RANGE BETWEEN UNBOUNDED PRECEDING
> aggregation to SQL
> -------------------------------------------------------------------------------------------
>
> Key: FLINK-5803
> URL: https://issues.apache.org/jira/browse/FLINK-5803
> Project: Flink
> Issue Type: Sub-task
> Components: Table API & SQL
> Reporter: sunjincheng
> Assignee: sunjincheng
>
> The goal of this issue is to add support for OVER RANGE aggregations on
> processing time streams to the SQL interface.
> Queries similar to the following should be supported:
> {code}
> SELECT
> a,
> SUM(b) OVER (PARTITION BY c ORDER BY procTime() RANGE BETWEEN UNBOUNDED
> PRECEDING AND CURRENT ROW) AS sumB,
> MIN(b) OVER (PARTITION BY c ORDER BY procTime() RANGE BETWEEN UNBOUNDED
> PRECEDING AND CURRENT ROW) AS minB
> FROM myStream
> {code}
> The following restrictions should initially apply:
> - All OVER clauses in the same SELECT clause must be exactly the same.
> - The ORDER BY clause may only have procTime() as parameter. procTime() is a
> parameterless scalar function that just indicates processing time mode.
> - bounded PRECEDING is not supported (see FLINK-5654)
> - FOLLOWING is not supported.
> The restrictions will be resolved in follow up issues. If we find that some
> of the restrictions are trivial to address, we can add the functionality in
> this issue as well.
> This issue includes:
> - Design of the DataStream operator to compute OVER ROW aggregates
> - Translation from Calcite's RelNode representation (LogicalProject with
> RexOver expression).
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
