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 2020/07/08 15:12:33 UTC
[GitHub] [spark] gaborgsomogyi commented on a change in pull request #28975: [SPARK-32148][SS] Fix stream-stream join issue on missing to copy reused unsafe row
gaborgsomogyi commented on a change in pull request #28975:
URL: https://github.com/apache/spark/pull/28975#discussion_r451617910
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingJoinSuite.scala
##########
@@ -996,4 +997,47 @@ class StreamingOuterJoinSuite extends StreamTest with StateStoreMetricsTest with
)
}
}
+
+ test("SPARK-32148 stream-stream join regression on Spark 3.0.0") {
+ val input1 = MemoryStream[(Timestamp, String, String)]
+ val df1 = input1.toDF
+ .selectExpr("_1 as eventTime", "_2 as id", "_3 as comment")
Review comment:
Any specific reason why not use `select`? I don't see any expression here.
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingJoinSuite.scala
##########
@@ -996,4 +997,47 @@ class StreamingOuterJoinSuite extends StreamTest with StateStoreMetricsTest with
)
}
}
+
+ test("SPARK-32148 stream-stream join regression on Spark 3.0.0") {
+ val input1 = MemoryStream[(Timestamp, String, String)]
+ val df1 = input1.toDF
+ .selectExpr("_1 as eventTime", "_2 as id", "_3 as comment")
+ .withWatermark(s"eventTime", "2 minutes")
+
+ val input2 = MemoryStream[(Timestamp, String, String)]
+ val df2 = input2.toDF
+ .selectExpr("_1 as eventTime", "_2 as id", "_3 as name")
Review comment:
Same here.
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingJoinSuite.scala
##########
@@ -996,4 +997,47 @@ class StreamingOuterJoinSuite extends StreamTest with StateStoreMetricsTest with
)
}
}
+
+ test("SPARK-32148 stream-stream join regression on Spark 3.0.0") {
+ val input1 = MemoryStream[(Timestamp, String, String)]
+ val df1 = input1.toDF
+ .selectExpr("_1 as eventTime", "_2 as id", "_3 as comment")
+ .withWatermark(s"eventTime", "2 minutes")
+
+ val input2 = MemoryStream[(Timestamp, String, String)]
+ val df2 = input2.toDF
+ .selectExpr("_1 as eventTime", "_2 as id", "_3 as name")
+ .withWatermark(s"eventTime", "4 minutes")
+
+ val joined = df1.as("left")
+ .join(df2.as("right"),
+ expr(s"""
Review comment:
Why string interpolation needed?
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/streaming/StreamingJoinSuite.scala
##########
@@ -996,4 +997,47 @@ class StreamingOuterJoinSuite extends StreamTest with StateStoreMetricsTest with
)
}
}
+
+ test("SPARK-32148 stream-stream join regression on Spark 3.0.0") {
+ val input1 = MemoryStream[(Timestamp, String, String)]
+ val df1 = input1.toDF
+ .selectExpr("_1 as eventTime", "_2 as id", "_3 as comment")
+ .withWatermark(s"eventTime", "2 minutes")
+
+ val input2 = MemoryStream[(Timestamp, String, String)]
+ val df2 = input2.toDF
+ .selectExpr("_1 as eventTime", "_2 as id", "_3 as name")
+ .withWatermark(s"eventTime", "4 minutes")
+
+ val joined = df1.as("left")
+ .join(df2.as("right"),
+ expr(s"""
+ |left.id = right.id AND left.eventTime BETWEEN
Review comment:
Nit: indent
----------------------------------------------------------------
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.
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