You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2022/02/17 02:50:37 UTC
[GitHub] [spark] HeartSaVioR commented on a change in pull request #35526: [SPARK-38214][SS]No need to filter windows when windowDuration is multiple of slideDuration
HeartSaVioR commented on a change in pull request #35526:
URL: https://github.com/apache/spark/pull/35526#discussion_r808624489
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/DataFrameTimeWindowingSuite.scala
##########
@@ -490,4 +490,42 @@ class DataFrameTimeWindowingSuite extends QueryTest with SharedSparkSession {
assert(attributeReference.dataType == tuple._2)
}
}
+
+ test("No need to filter windows when windowDuration is multiple of slideDuration") {
+ val df1 = Seq(
+ ("2022-02-15 19:39:34", 1, "a"),
+ ("2022-02-15 19:39:56", 2, "a"),
+ ("2022-02-15 19:39:27", 4, "b")).toDF("time", "value", "id")
+ .select(window($"time", "9 seconds", "3 seconds", "0 second"), $"value")
+ .orderBy($"window.start".asc, $"value".desc).select("value")
+ val df2 = Seq(
+ (LocalDateTime.parse("2022-02-15T19:39:34"), 1, "a"),
+ (LocalDateTime.parse("2022-02-15T19:39:56"), 2, "a"),
+ (LocalDateTime.parse("2022-02-15T19:39:27"), 4, "b")).toDF("time", "value", "id")
+ .select(window($"time", "9 seconds", "3 seconds", "0 second"), $"value")
+ .orderBy($"window.start".asc, $"value".desc).select("value")
+
+ val df3 = Seq(
+ ("2022-02-15 19:39:34", 1, "a"),
+ ("2022-02-15 19:39:56", 2, "a"),
+ ("2022-02-15 19:39:27", 4, "b")).toDF("time", "value", "id")
+ .select(window($"time", "9 seconds", "3 seconds", "-2 second"), $"value")
+ .orderBy($"window.start".asc, $"value".desc).select("value")
+ val df4 = Seq(
+ (LocalDateTime.parse("2022-02-15T19:39:34"), 1, "a"),
+ (LocalDateTime.parse("2022-02-15T19:39:56"), 2, "a"),
+ (LocalDateTime.parse("2022-02-15T19:39:27"), 4, "b")).toDF("time", "value", "id")
+ .select(window($"time", "9 seconds", "3 seconds", "2 second"), $"value")
+ .orderBy($"window.start".asc, $"value".desc).select("value")
+
+ Seq(df1, df2, df3, df4).foreach { df =>
+ val filter = df.queryExecution.optimizedPlan.find(_.isInstanceOf[Filter])
+ assert(filter.isDefined)
+ val exist = filter.get.constraints.filter(e =>
+ e.toString.contains(">=") || e.toString.contains("<"))
+ assert(exist.isEmpty, "No need to filter windows " +
+ "when windowDuration is multiple of slideDuration")
+ }
+ }
+
Review comment:
nit: unnecessary empty line
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org