Mailing-List: contact issues-help@flink.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@flink.apache.org
From: fhueske <git@git.apache.org>
To: issues@flink.incubator.apache.org
Reply-To: issues@flink.incubator.apache.org
References: <git-pr-4471-flink@git.apache.org>
In-Reply-To: <git-pr-4471-flink@git.apache.org>
Subject: [GitHub] flink pull request #4471: [FLINK-6094] [table] Implement stream-stream proct...
Content-Type: text/plain
Message-Id: <20170810143403.3C055F5559@git1-us-west.apache.org>
Date: Thu, 10 Aug 2017 14:34:03 +0000 (UTC)
archived-at: Thu, 10 Aug 2017 14:34:10 -0000

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

    https://github.com/apache/flink/pull/4471#discussion_r132277678
  
    --- Diff: flink-libraries/flink-table/src/main/scala/org/apache/flink/table/plan/util/UpdatingPlanChecker.scala ---
    @@ -90,40 +96,86 @@ object UpdatingPlanChecker {
                   // resolve names of input fields
                   .map(io => (inNames.get(io._1), io._2))
     
    -            // filter by input keys
    -            val outKeys = inOutNames.filter(io => keys.get.contains(io._1)).map(_._2)
    -            // check if all keys have been preserved
    -            if (outKeys.nonEmpty && outKeys.length == keys.get.length) {
    +            // filter by input keyAncestors
    +            val outKeyAncesters = inOutNames
    +              .filter(io => keyAncestors.get.map(e => e._1).contains(io._1))
    +              .map(io => (io._2, keyAncestors.get.find(ka => ka._1 == io._1).get._2))
    +
    +            // check if all keyAncestors have been preserved
    +            if (outKeyAncesters.nonEmpty &&
    +              outKeyAncesters.map(ka => ka._2).distinct.length ==
    +                keyAncestors.get.map(ka => ka._2).distinct.length) {
                   // all key have been preserved (but possibly renamed)
    -              keys = Some(outKeys.toArray)
    +              Some(outKeyAncesters.toList)
                 } else {
                   // some (or all) keys have been removed. Keys are no longer unique and removed
    -              keys = None
    +              None
                 }
    +          } else {
    +            None
               }
    +
             case _: DataStreamOverAggregate =>
    -          super.visit(node, ordinal, parent)
    -        // keys are always forwarded by Over aggregate
    +          // keyAncestors are always forwarded by Over aggregate
    +          visit(node.getInput(0))
             case a: DataStreamGroupAggregate =>
    -          // get grouping keys
    +          // get grouping keyAncestors
               val groupKeys = a.getRowType.getFieldNames.asScala.take(a.getGroupings.length)
    -          keys = Some(groupKeys.toArray)
    +          Some(groupKeys.map(e => (e, e)).toList)
             case w: DataStreamGroupWindowAggregate =>
    -          // get grouping keys
    +          // get grouping keyAncestors
               val groupKeys =
                 w.getRowType.getFieldNames.asScala.take(w.getGroupings.length).toArray
               // get window start and end time
               val windowStartEnd = w.getWindowProperties.map(_.name)
               // we have only a unique key if at least one window property is selected
               if (windowStartEnd.nonEmpty) {
    -            keys = Some(groupKeys ++ windowStartEnd)
    +            Some((groupKeys ++ windowStartEnd).map(e => (e, e)).toList)
    +          } else {
    +            None
    +          }
    +
    +        case j: DataStreamJoin =>
    +          val leftKeyAncestors = visit(j.getLeft)
    +          val rightKeyAncestors = visit(j.getRight)
    +          if (!leftKeyAncestors.isDefined || !rightKeyAncestors.isDefined) {
    +            None
    +          } else {
    +            // both left and right contain keys
    +            val leftJoinKeys =
    --- End diff --
    
    Is easier to compute with:
    
    ```
    val leftFieldNames = j.getLeft.getRowType.getFieldNames
    val leftJoinKeys: Seq[String] = j.getJoinInfo.leftKeys.asScala.map(leftFieldNames.get(_))
    ```


---
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.
---