viirya commented on code in PR #210:
URL:
https://github.com/apache/arrow-datafusion-comet/pull/210#discussion_r1538646722
##########
dev/diffs/3.4.2.diff:
##########
@@ -1139,6 +1205,94 @@ index 75f440caefc..36b1146bc3a 100644
}.headOption.getOrElse {
fail(s"No FileScan in query\n${df.queryExecution}")
}
+diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateDistributionSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateDistributionSuite.scala
+index b597a244710..b2e8be41065 100644
+---
a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateDistributionSuite.scala
++++
b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateDistributionSuite.scala
+@@ -21,6 +21,7 @@ import java.io.File
+
+ import org.apache.commons.io.FileUtils
+
++import org.apache.spark.sql.IgnoreComet
+ import org.apache.spark.sql.catalyst.streaming.InternalOutputModes.Update
+ import org.apache.spark.sql.execution.streaming.{FlatMapGroupsWithStateExec,
MemoryStream}
+ import org.apache.spark.sql.internal.SQLConf
+@@ -91,7 +92,7 @@ class FlatMapGroupsWithStateDistributionSuite extends
StreamTest
+ }
+
+ test("SPARK-38204: flatMapGroupsWithState should require
StatefulOpClusteredDistribution " +
+- "from children - without initial state") {
++ "from children - without initial state", IgnoreComet("TODO: fix Comet for
this test")) {
+ // function will return -1 on timeout and returns count of the state
otherwise
+ val stateFunc =
+ (key: (String, String), values: Iterator[(String, String, Long)],
+@@ -243,7 +244,8 @@ class FlatMapGroupsWithStateDistributionSuite extends
StreamTest
+ }
+
+ test("SPARK-38204: flatMapGroupsWithState should require
ClusteredDistribution " +
+- "from children if the query starts from checkpoint in 3.2.x - without
initial state") {
++ "from children if the query starts from checkpoint in 3.2.x - without
initial state",
++ IgnoreComet("TODO: fix Comet for this test")) {
+ // function will return -1 on timeout and returns count of the state
otherwise
+ val stateFunc =
+ (key: (String, String), values: Iterator[(String, String, Long)],
+@@ -335,7 +337,8 @@ class FlatMapGroupsWithStateDistributionSuite extends
StreamTest
+ }
+
+ test("SPARK-38204: flatMapGroupsWithState should require
ClusteredDistribution " +
+- "from children if the query starts from checkpoint in prior to 3.2") {
++ "from children if the query starts from checkpoint in prior to 3.2",
++ IgnoreComet("TODO: fix Comet for this test")) {
+ // function will return -1 on timeout and returns count of the state
otherwise
+ val stateFunc =
+ (key: (String, String), values: Iterator[(String, String, Long)],
+diff --git
a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateSuite.scala
b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateSuite.scala
+index 6aa7d0945c7..38523536154 100644
+---
a/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateSuite.scala
++++
b/sql/core/src/test/scala/org/apache/spark/sql/streaming/FlatMapGroupsWithStateSuite.scala
+@@ -25,7 +25,7 @@ import org.scalatest.exceptions.TestFailedException
+
+ import org.apache.spark.SparkException
+ import org.apache.spark.api.java.function.FlatMapGroupsWithStateFunction
+-import org.apache.spark.sql.{DataFrame, Encoder}
++import org.apache.spark.sql.{DataFrame, Encoder, IgnoreCometSuite}
+ import org.apache.spark.sql.catalyst.InternalRow
+ import org.apache.spark.sql.catalyst.expressions.{GenericInternalRow,
UnsafeProjection, UnsafeRow}
+ import org.apache.spark.sql.catalyst.plans.logical.FlatMapGroupsWithState
+@@ -46,8 +46,9 @@ case class RunningCount(count: Long)
+
+ case class Result(key: Long, count: Int)
+
++// TODO: fix Comet to enable this suite
Review Comment:
Hmm, all this suite fail?
--
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]
