chaoqin-li1123 commented on code in PR #43788:
URL: https://github.com/apache/spark/pull/43788#discussion_r1393180207
##########
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/v2/state/StateDataSourceReadSuite.scala:
##########
@@ -494,6 +497,48 @@ abstract class StateDataSourceReadSuite extends
StateDataSourceTestBase with Ass
}
}
+ test("Session window aggregation") {
+ withTempDir { checkpointDir =>
+ val input = MemoryStream[(String, Long)]
+ val sessionWindow = session_window($"eventTime", "10 seconds")
+
+ val events = input.toDF()
+ .select($"_1".as("value"), $"_2".as("timestamp"))
+ .withColumn("eventTime", $"timestamp".cast("timestamp"))
+ .withWatermark("eventTime", "30 seconds")
+ .selectExpr("explode(split(value, ' ')) AS sessionId", "eventTime")
+
+ val streamingDf = events
+ .groupBy(sessionWindow as Symbol("session"), $"sessionId")
+ .agg(count("*").as("numEvents"))
+ .selectExpr("sessionId", "CAST(session.start AS LONG)",
"CAST(session.end AS LONG)",
+ "CAST(session.end AS LONG) - CAST(session.start AS LONG) AS
durationMs",
+ "numEvents")
+
+ testStream(streamingDf, OutputMode.Complete())(
+ StartStream(checkpointLocation = checkpointDir.toString),
+ AddData(input,
+ ("hello world spark streaming", 40L),
+ ("world hello structured streaming", 41L)
+ ),
+ CheckNewAnswer(
+ ("hello", 40, 51, 11, 2),
+ ("world", 40, 51, 11, 2),
+ ("streaming", 40, 51, 11, 2),
+ ("spark", 40, 50, 10, 1),
+ ("structured", 41, 51, 10, 1)
+ ),
+ StopStream
+ )
+
+
+ val df = spark.read.format("statestore").load(checkpointDir.toString)
+ .selectExpr("key.sessionId as sessionId", "value.count as count")
Review Comment:
Changed the query to validate all the field.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
