uros-db commented on code in PR #48400:
URL: https://github.com/apache/spark/pull/48400#discussion_r1793746374
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala:
##########
@@ -1576,39 +1576,6 @@ class CollationSuite extends DatasourceV2SQLBase with
AdaptiveSparkPlanHelper {
})
}
- test("rewrite with collationkey should be an excludable rule") {
- val t1 = "T_1"
- val t2 = "T_2"
- val collation = "UTF8_LCASE"
- val collationRewriteJoinRule =
"org.apache.spark.sql.catalyst.analysis.RewriteCollationJoin"
- withTable(t1, t2) {
- withSQLConf(SQLConf.OPTIMIZER_EXCLUDED_RULES.key ->
collationRewriteJoinRule) {
- sql(s"CREATE TABLE $t1 (x STRING COLLATE $collation, i int) USING
PARQUET")
- sql(s"INSERT INTO $t1 VALUES ('aa', 1)")
-
- sql(s"CREATE TABLE $t2 (y STRING COLLATE $collation, j int) USING
PARQUET")
- sql(s"INSERT INTO $t2 VALUES ('AA', 2), ('aa', 2)")
-
- val df = sql(s"SELECT * FROM $t1 JOIN $t2 ON $t1.x = $t2.y")
- checkAnswer(df, Seq(Row("aa", 1, "AA", 2), Row("aa", 1, "aa", 2)))
-
- val queryPlan = df.queryExecution.executedPlan
-
- // confirm that sort merge join is used instead of hash join
- assert(
- collectFirst(queryPlan) {
- case _: HashJoin => ()
- }.isEmpty
- )
- assert(
- collectFirst(queryPlan) {
- case _: SortMergeJoinExec => ()
Review Comment:
in this particular test, the rewrite rule was excluded manually - that's why
SMJ is used
##########
sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala:
##########
@@ -1576,39 +1576,6 @@ class CollationSuite extends DatasourceV2SQLBase with
AdaptiveSparkPlanHelper {
})
}
- test("rewrite with collationkey should be an excludable rule") {
- val t1 = "T_1"
- val t2 = "T_2"
- val collation = "UTF8_LCASE"
- val collationRewriteJoinRule =
"org.apache.spark.sql.catalyst.analysis.RewriteCollationJoin"
- withTable(t1, t2) {
- withSQLConf(SQLConf.OPTIMIZER_EXCLUDED_RULES.key ->
collationRewriteJoinRule) {
- sql(s"CREATE TABLE $t1 (x STRING COLLATE $collation, i int) USING
PARQUET")
- sql(s"INSERT INTO $t1 VALUES ('aa', 1)")
-
- sql(s"CREATE TABLE $t2 (y STRING COLLATE $collation, j int) USING
PARQUET")
- sql(s"INSERT INTO $t2 VALUES ('AA', 2), ('aa', 2)")
-
- val df = sql(s"SELECT * FROM $t1 JOIN $t2 ON $t1.x = $t2.y")
- checkAnswer(df, Seq(Row("aa", 1, "AA", 2), Row("aa", 1, "aa", 2)))
-
- val queryPlan = df.queryExecution.executedPlan
-
- // confirm that sort merge join is used instead of hash join
- assert(
- collectFirst(queryPlan) {
- case _: HashJoin => ()
- }.isEmpty
- )
- assert(
- collectFirst(queryPlan) {
- case _: SortMergeJoinExec => ()
Review Comment:
in this particular test, the rewrite rule was excluded manually - that's why
SMJ was used
--
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]
