Skip to content

[SPARK-50245][SQL][TESTS] Extended CollationSuite and added tests where SortMergeJoin is forced #48774

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
vladanvasi-db wants to merge 4 commits into from
Closed

[SPARK-50245][SQL][TESTS] Extended CollationSuite and added tests where SortMergeJoin is forced #48774

Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
81b08fc
Extended CollationSuite and added tests where SortMergeJoin is forced
vladanvasi-db Nov 6, 2024
265efcd
Refactored test suite to reduce code
vladanvasi-db Nov 7, 2024
9851790
Simplified assertions for SortMerge and HashJoin
vladanvasi-db Nov 8, 2024
ba3e702
Moved collation key check into common helper function
vladanvasi-db Nov 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Simplified assertions for SortMerge and HashJoin
  • Loading branch information
@vladanvasi-db
vladanvasi-db committed Nov 8, 2024
commit 9851790db3e24a9ef44e99dfebb1b1955ffa6a2c
45 changes: 13 additions & 32 deletions sql/core/src/test/scala/org/apache/spark/sql/CollationSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,29 +51,10 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {

private def checkRightTypeOfJoinUsed(queryPlan: SparkPlan): Unit = {
assert(
// If sort merge join is forced, we should not see HashJoin in the plan.
isSortMergeForced ||
// If sort merge join is not forced, we should see HashJoin in the plan
// and not SortMergeJoin.
collectFirst(queryPlan) {
case _: HashJoin => ()
}.nonEmpty &&
collectFirst(queryPlan) {
case _: SortMergeJoinExec => ()
}.isEmpty
)

assert(
// If sort merge join is not forced, we should not see SortMergeJoin in the plan.
!isSortMergeForced ||
// If sort merge join is forced, we should see SortMergeJoin in the plan
// and not HashJoin.
collectFirst(queryPlan) {
case _: HashJoin => ()
}.isEmpty &&
collectFirst(queryPlan) {
case _: SortMergeJoinExec => ()
}.nonEmpty
collectFirst(queryPlan) {
case _: SortMergeJoinExec => assert(isSortMergeForced)
case _: HashJoin => assert(!isSortMergeForced)
}.nonEmpty
)
}

Expand Down Expand Up @@ -1413,7 +1394,7 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {
for (codeGen <- Seq("NO_CODEGEN", "CODEGEN_ONLY")) {
val collationSetup = if (collation.isEmpty) "" else " COLLATE " + collation
val supportsBinaryEquality = collation.isEmpty || collation == "UNICODE" ||
CollationFactory.fetchCollation(collation).isUtf8BinaryType
CollationFactory.fetchCollation(collation).supportsBinaryEquality

test(s"Group by on map containing$collationSetup strings ($codeGen)") {
val tableName = "t"
Expand Down Expand Up @@ -1618,15 +1599,15 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {

if (isSortMergeForced) {
// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(queryPlan.toString().contains("collationkey"))
} else {
assert(!queryPlan.toString().contains("collationkey"))
}
}
else {
// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(collectFirst(queryPlan) {
case b: HashJoin => b.leftKeys.head
}.head.isInstanceOf[CollationKey])
Expand Down Expand Up @@ -1681,15 +1662,15 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {

if (isSortMergeForced) {
// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(queryPlan.toString().contains("collationkey"))
} else {
assert(!queryPlan.toString().contains("collationkey"))
}
}
else {
// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(collectFirst(queryPlan) {
case b: BroadcastHashJoinExec => b.leftKeys.head
}.head.asInstanceOf[ArrayTransform].function.asInstanceOf[LambdaFunction].
Expand Down Expand Up @@ -1749,15 +1730,15 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {

if (isSortMergeForced) {
// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(queryPlan.toString().contains("collationkey"))
} else {
assert(!queryPlan.toString().contains("collationkey"))
}
}
else {
// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(collectFirst(queryPlan) {
case b: BroadcastHashJoinExec => b.leftKeys.head
}.head.asInstanceOf[ArrayTransform].function.
Expand Down Expand Up @@ -1813,7 +1794,7 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {
checkRightTypeOfJoinUsed(queryPlan)

// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(queryPlan.toString().contains("collationkey"))
} else {
assert(!queryPlan.toString().contains("collationkey"))
Expand Down Expand Up @@ -1870,7 +1851,7 @@ class CollationSuite extends DatasourceV2SQLBase with AdaptiveSparkPlanHelper {
checkRightTypeOfJoinUsed(queryPlan)

// Only if collation doesn't support binary equality, collation key should be injected.
if (!CollationFactory.fetchCollation(t.collation).isUtf8BinaryType) {
if (!CollationFactory.fetchCollation(t.collation).supportsBinaryEquality) {
assert(queryPlan.toString().contains("collationkey"))
} else {
assert(!queryPlan.toString().contains("collationkey"))
Expand Down