[
https://issues.apache.org/jira/browse/FLINK-8577?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16696315#comment-16696315
]
ASF GitHub Bot commented on FLINK-8577:
---------------------------------------
hequn8128 commented on a change in pull request #6787: [FLINK-8577][table]
Implement proctime DataStream to Table upsert conversion
URL: https://github.com/apache/flink/pull/6787#discussion_r235835509
##########
File path:
flink-libraries/flink-table/src/main/scala/org/apache/flink/table/plan/nodes/datastream/DataStreamLastRow.scala
##########
@@ -0,0 +1,122 @@
+/*
+ * 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 java.util
+
+import org.apache.calcite.plan.{RelOptCluster, RelTraitSet}
+import org.apache.calcite.rel.{RelNode, RelWriter, SingleRel}
+import org.apache.flink.api.java.functions.NullByteKeySelector
+import org.apache.flink.api.java.typeutils.RowTypeInfo
+import org.apache.flink.streaming.api.datastream.DataStream
+import org.apache.flink.table.api.{StreamQueryConfig, StreamTableEnvironment}
+import org.apache.flink.table.plan.rules.datastream.DataStreamRetractionRules
+import org.apache.flink.table.plan.schema.RowSchema
+import org.apache.flink.table.runtime.{CRowKeySelector, LastRowProcessFunction}
+import org.apache.flink.table.runtime.types.{CRow, CRowTypeInfo}
+
+import scala.collection.JavaConversions._
+
+/**
+ * Flink RelNode for ingesting upsert stream from source.
+ */
+class DataStreamLastRow(
+ cluster: RelOptCluster,
+ traitSet: RelTraitSet,
+ input: RelNode,
+ inputSchema: RowSchema,
+ schema: RowSchema,
+ val keyNames: Seq[String])
+ extends SingleRel(cluster, traitSet, input)
+ with DataStreamRel{
+
+ lazy val keyIndexes = getRowType.getFieldNames.zipWithIndex
+ .filter(e => keyNames.contains(e._1))
+ .map(_._2).toArray
+
+ override def copy(traitSet: RelTraitSet, inputs: util.List[RelNode]):
RelNode = {
+ new DataStreamLastRow(
+ cluster,
+ traitSet,
+ inputs.get(0),
+ inputSchema,
+ schema,
+ keyNames)
+ }
+
+ override def explainTerms(pw: RelWriter): RelWriter ={
+ super.explainTerms(pw)
+ .itemIf("keys", keyNames.mkString(", "), keyNames.size != 0)
+ .item("select", input.getRowType.getFieldNames.toArray.mkString(", "))
+ }
+
+ override def toString: String = {
+ s"LastRow(${
+ if (keyNames.size != 0) {
+ s"keys:(${keyNames.mkString(", ")}), "
+ } else {
+ ""
+ }
+ }select:(${input.getRowType.getFieldNames.toArray.mkString(", ")}))"
+ }
+
+ override def producesUpdates: Boolean = true
+
+ override def translateToPlan(
+ tableEnv: StreamTableEnvironment,
+ queryConfig: StreamQueryConfig): DataStream[CRow] = {
+
+ val inputDS =
+ getInput.asInstanceOf[DataStreamRel].translateToPlan(tableEnv,
queryConfig)
+ val outRowType = CRowTypeInfo(schema.typeInfo)
+
+ val needRetraction = DataStreamRetractionRules.isAccRetract(this)
+ val result: DataStream[CRow] = if (needRetraction) {
+ val processFunction = new LastRowProcessFunction(
+ new RowTypeInfo(schema.fieldTypeInfos.toArray,
schema.fieldNames.toArray),
Review comment:
`LastRowProcessFunction` requires a type of RowTypeInfo while
`schema.typeInfo` returns a type of TypeInformation[Row]
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
> Implement proctime DataStream to Table upsert conversion.
> ---------------------------------------------------------
>
> Key: FLINK-8577
> URL: https://issues.apache.org/jira/browse/FLINK-8577
> Project: Flink
> Issue Type: Sub-task
> Components: Table API & SQL
> Reporter: Hequn Cheng
> Assignee: Hequn Cheng
> Priority: Major
> Labels: pull-request-available
>
> Api will looks like:
> {code:java}
> DataStream[(String, Long, Int)] input = ???
> // upsert with keyTable
> table = tEnv.upsertFromStream(input, 'a, 'b, 'c.key)
> // upsert without key -> single row tableTable
> table = tEnv.upsertFromStream(input, 'a, 'b, 'c){code}
> A simple design
> [doc|https://docs.google.com/document/d/1yMEi9xkm3pNYNmmZykbLzqtKjFVezaWe0y7Xqd0c1zE/edit?usp=sharing]
> about this subtask.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
