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 #3715: [FLINK-6232][Table&SQL]Support proctime inner equi...
Date Wed, 21 Jun 2017 13:07:56 GMT
Github user fhueske commented on a diff in the pull request:

    https://github.com/apache/flink/pull/3715#discussion_r122843078
  
    --- Diff: flink-libraries/flink-table/src/main/scala/org/apache/flink/table/plan/nodes/datastream/DataStreamRowStreamJoin.scala
---
    @@ -0,0 +1,186 @@
    +/*
    + * 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._
    +import org.apache.calcite.rel.core.{JoinInfo, JoinRelType}
    +import org.apache.calcite.rel.{BiRel, RelNode, RelWriter}
    +import org.apache.calcite.rex.RexNode
    +import org.apache.flink.api.java.functions.NullByteKeySelector
    +import org.apache.flink.streaming.api.datastream.DataStream
    +import org.apache.flink.table.api.{StreamQueryConfig, StreamTableEnvironment, TableException}
    +import org.apache.flink.table.calcite.FlinkTypeFactory
    +import org.apache.flink.table.plan.nodes.CommonJoin
    +import org.apache.flink.table.plan.schema.RowSchema
    +import org.apache.flink.table.runtime.join.{JoinUtil, ProcTimeInnerJoin}
    +import org.apache.flink.table.runtime.types.{CRow, CRowTypeInfo}
    +
    +/**
    +  * Flink RelNode which matches along with JoinOperator and its related operations.
    +  */
    +class DataStreamRowStreamJoin(
    +    cluster: RelOptCluster,
    +    traitSet: RelTraitSet,
    +    leftNode: RelNode,
    +    rightNode: RelNode,
    +    joinCondition: RexNode,
    +    joinType: JoinRelType,
    +    leftSchema: RowSchema,
    +    rightSchema: RowSchema,
    +    schema: RowSchema,
    +    ruleDescription: String)
    +  extends BiRel(cluster, traitSet, leftNode, rightNode)
    +  with CommonJoin
    +  with DataStreamRel {
    +
    +  override def deriveRowType() = schema.logicalType
    +
    +  override def copy(traitSet: RelTraitSet, inputs: java.util.List[RelNode]): RelNode
= {
    +    new DataStreamRowStreamJoin(
    +      cluster,
    +      traitSet,
    +      inputs.get(0),
    +      inputs.get(1),
    +      joinCondition,
    +      joinType,
    +      leftSchema,
    +      rightSchema,
    +      schema,
    +      ruleDescription)
    +  }
    +
    +  override def toString: String = {
    +
    +    s"${joinTypeToString(joinType)}" +
    +      s"(condition: (${joinConditionToString(schema.logicalType,
    +        joinCondition, getExpressionString)}), " +
    +      s"select: (${joinSelectionToString(schema.logicalType)}))"
    +  }
    +
    +  override def explainTerms(pw: RelWriter): RelWriter = {
    +    super.explainTerms(pw)
    +      .item("condition", joinConditionToString(schema.logicalType,
    +        joinCondition, getExpressionString))
    +      .item("select", joinSelectionToString(schema.logicalType))
    +      .item("joinType", joinTypeToString(joinType))
    +  }
    +
    +  override def translateToPlan(
    +      tableEnv: StreamTableEnvironment,
    +      queryConfig: StreamQueryConfig): DataStream[CRow] = {
    +
    +    val config = tableEnv.getConfig
    +
    +    // get the equality keys and other condition
    +    val joinInfo = JoinInfo.of(leftNode, rightNode, joinCondition)
    +    val leftKeys = joinInfo.leftKeys.toIntArray
    +    val rightKeys = joinInfo.rightKeys.toIntArray
    +    val otherCondition = joinInfo.getRemaining(cluster.getRexBuilder)
    +
    +    // analyze time boundary and time predicate type(proctime/rowtime)
    +    val (timeType, leftStreamWindowSize, rightStreamWindowSize, remainCondition) =
    +      JoinUtil.analyzeTimeBoundary(
    --- End diff --
    
    I think we should move the analysis to the rule. Otherwise, we might end up with a plan
that cannot be translated. It is the rule's responsibility to ensure that the translated plan
can be executed.
    
    The rule can then pass the analyzed time predicate parameters (time type, bounds) to the
`DataStreamRowStreamJoin`


---
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