huaxingao commented on a change in pull request #34445:
URL: https://github.com/apache/spark/pull/34445#discussion_r741315128
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/datasources/FileSourceAggregatePushDownSuite.scala
##########
@@ -261,6 +261,63 @@ trait FileSourceAggregatePushDownSuite
}
}
+ test("aggregate with partition group by can be pushed down") {
+ withTempPath { dir =>
+ spark.range(10).selectExpr("id", "id % 3 as p")
+ .write.partitionBy("p").format(format).save(dir.getCanonicalPath)
+ withTempView("tmp") {
+
spark.read.format(format).load(dir.getCanonicalPath).createOrReplaceTempView("tmp");
+ Seq("false", "true").foreach { enableVectorizedReader =>
+ withSQLConf(aggPushDownEnabledKey -> "true",
+ vectorizedReaderEnabledKey -> enableVectorizedReader) {
+ val df = sql("SELECT count(*), count(id), p, max(id), p, p,
max(id), min(id), p" +
Review comment:
I added `count(p)`, but didn't add `max(p)` since it won't be pushed down
--
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]
