Skip to content

[GLUTEN-12856][TEST] Use withTable for table cleanup in Hive SQL query suites #13405

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

Open
shivadarshan-devadiga wants to merge 2 commits into
base: main
Choose a base branch
from
+328 −370
Open

[GLUTEN-12856][TEST] Use withTable for table cleanup in Hive SQL query suites #13405

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3864815
[GLUTEN-12856][TEST] Use withTable for table cleanup
shivadarshan-devadiga Oct 21, 2026
6613015
Merge branch 'apache:main' into fix-hive-sql-suite-table-cleanup
shivadarshan-devadiga Oct 21, 2026
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
54 changes: 24 additions & 30 deletions .../spark34/src/test/scala/org/apache/spark/sql/hive/execution/GlutenHiveSQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@ package org.apache.spark.sql.hive.execution

import org.apache.spark.SparkConf
import org.apache.spark.sql.Row
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.hive.{HiveExternalCatalog, HiveTableScanExecTransformer}
import org.apache.spark.sql.hive.client.HiveClient

Expand All @@ -33,20 +32,17 @@ class GlutenHiveSQLQuerySuite extends GlutenHiveSQLQuerySuiteBase {
}

testGluten("hive orc scan") {
withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") {
sql("DROP TABLE IF EXISTS test_orc")
sql(
"CREATE TABLE test_orc (name STRING, favorite_color STRING)" +
" USING hive OPTIONS(fileFormat 'orc')")
sql("INSERT INTO test_orc VALUES('test_1', 'red')")
val df = spark.sql("select * from test_orc")
checkAnswer(df, Seq(Row("test_1", "red")))
checkOperatorMatch[HiveTableScanExecTransformer](df)
withTable("test_orc") {
withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") {
sql(
"CREATE TABLE test_orc (name STRING, favorite_color STRING)" +
" USING hive OPTIONS(fileFormat 'orc')")
sql("INSERT INTO test_orc VALUES('test_1', 'red')")
val df = spark.sql("select * from test_orc")
checkAnswer(df, Seq(Row("test_1", "red")))
checkOperatorMatch[HiveTableScanExecTransformer](df)
}
}
spark.sessionState.catalog.dropTable(
TableIdentifier("test_orc"),
ignoreIfNotExists = true,
purge = false)
}

testGluten("orc.force.positional.evolution maps Hive ORC columns by position") {
Expand Down Expand Up @@ -173,22 +169,20 @@ class GlutenHiveSQLQuerySuite extends GlutenHiveSQLQuerySuiteBase {
}

testGluten("avoid unnecessary filter binding for subfield during scan") {
withSQLConf(
"spark.sql.hive.convertMetastoreParquet" -> "false") {
sql("DROP TABLE IF EXISTS test_subfield")
sql(
"CREATE TABLE test_subfield (name STRING, favorite_color STRING," +
" label STRUCT<label_1:STRING, label_2:STRING>) USING hive OPTIONS(fileFormat 'parquet')")
sql(
"INSERT INTO test_subfield VALUES('test_1', 'red', named_struct('label_1', 'label-a'," +
"'label_2', 'label-b'))")
val df = spark.sql("select * from test_subfield where name='test_1'")
checkAnswer(df, Seq(Row("test_1", "red", Row("label-a", "label-b"))))
checkOperatorMatch[HiveTableScanExecTransformer](df)
withTable("test_subfield") {
withSQLConf(
"spark.sql.hive.convertMetastoreParquet" -> "false") {
sql(
"CREATE TABLE test_subfield (name STRING, favorite_color STRING," +
" label STRUCT<label_1:STRING, label_2:STRING>)" +
" USING hive OPTIONS(fileFormat 'parquet')")
sql(
"INSERT INTO test_subfield VALUES('test_1', 'red', named_struct('label_1', 'label-a'," +
"'label_2', 'label-b'))")
val df = spark.sql("select * from test_subfield where name='test_1'")
checkAnswer(df, Seq(Row("test_1", "red", Row("label-a", "label-b"))))
checkOperatorMatch[HiveTableScanExecTransformer](df)
}
}
spark.sessionState.catalog.dropTable(
TableIdentifier("test_subfield"),
ignoreIfNotExists = true,
purge = false)
}
}
155 changes: 73 additions & 82 deletions .../spark35/src/test/scala/org/apache/spark/sql/hive/execution/GlutenHiveSQLQuerySuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,6 @@ import org.apache.gluten.execution.FileSourceScanExecTransformer

import org.apache.spark.SparkConf
import org.apache.spark.sql.Row
import org.apache.spark.sql.catalyst.TableIdentifier
import org.apache.spark.sql.execution.SparkPlan
import org.apache.spark.sql.hive.{HiveExternalCatalog, HiveTableScanExecTransformer}
import org.apache.spark.sql.hive.client.HiveClient
Expand All @@ -39,84 +38,78 @@ class GlutenHiveSQLQuerySuite extends GlutenHiveSQLQuerySuiteBase {
}

testGluten("hive orc scan") {
withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") {
sql("DROP TABLE IF EXISTS test_orc")
sql(
"CREATE TABLE test_orc (name STRING, favorite_color STRING)" +
" USING hive OPTIONS(fileFormat 'orc')")
sql("INSERT INTO test_orc VALUES('test_1', 'red')")
val df = spark.sql("select * from test_orc")
checkAnswer(df, Seq(Row("test_1", "red")))
checkOperatorMatch[HiveTableScanExecTransformer](df)
withTable("test_orc") {
withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") {
sql(
"CREATE TABLE test_orc (name STRING, favorite_color STRING)" +
" USING hive OPTIONS(fileFormat 'orc')")
sql("INSERT INTO test_orc VALUES('test_1', 'red')")
val df = spark.sql("select * from test_orc")
checkAnswer(df, Seq(Row("test_1", "red")))
checkOperatorMatch[HiveTableScanExecTransformer](df)
}
}
spark.sessionState.catalog.dropTable(
TableIdentifier("test_orc"),
ignoreIfNotExists = true,
purge = false)
}

// copy from GLUTEN-4796, which only added to spark33
testGluten("Add orc char type validation") {
withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") {
sql("DROP TABLE IF EXISTS test_orc")
sql(
"CREATE TABLE test_orc (name char(10), id int)" +
" USING hive OPTIONS(fileFormat 'orc')")
sql("INSERT INTO test_orc VALUES('test', 1)")
}
withTable("test_orc") {
withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") {
sql(
"CREATE TABLE test_orc (name char(10), id int)" +
" USING hive OPTIONS(fileFormat 'orc')")
sql("INSERT INTO test_orc VALUES('test', 1)")
}

def testExecPlan(
convertMetastoreOrc: String,
charTypeFallbackEnabled: String,
shouldFindTransformer: Boolean,
transformerClass: Class[_ <: SparkPlan]
): Unit = {
def testExecPlan(
convertMetastoreOrc: String,
charTypeFallbackEnabled: String,
shouldFindTransformer: Boolean,
transformerClass: Class[_ <: SparkPlan]
): Unit = {

withSQLConf(
"spark.sql.hive.convertMetastoreOrc" -> convertMetastoreOrc,
GlutenConfig.VELOX_FORCE_ORC_CHAR_TYPE_SCAN_FALLBACK.key -> charTypeFallbackEnabled
) {
val queries = Seq("select id from test_orc", "select name, id from test_orc")
withSQLConf(
"spark.sql.hive.convertMetastoreOrc" -> convertMetastoreOrc,
GlutenConfig.VELOX_FORCE_ORC_CHAR_TYPE_SCAN_FALLBACK.key -> charTypeFallbackEnabled
) {
val queries = Seq("select id from test_orc", "select name, id from test_orc")

queries.foreach {
query =>
val executedPlan = getExecutedPlan(spark.sql(query))
val planCondition = executedPlan.exists(_.find(transformerClass.isInstance).isDefined)
queries.foreach {
query =>
val executedPlan = getExecutedPlan(spark.sql(query))
val planCondition = executedPlan.exists(_.find(transformerClass.isInstance).isDefined)

if (shouldFindTransformer) {
assert(planCondition)
} else {
assert(!planCondition)
}
if (shouldFindTransformer) {
assert(planCondition)
} else {
assert(!planCondition)
}
}
}
}
}

testExecPlan(
"false",
"true",
shouldFindTransformer = false,
classOf[HiveTableScanExecTransformer])
testExecPlan(
"false",
"false",
shouldFindTransformer = true,
classOf[HiveTableScanExecTransformer])
testExecPlan(
"false",
"true",
shouldFindTransformer = false,
classOf[HiveTableScanExecTransformer])
testExecPlan(
"false",
"false",
shouldFindTransformer = true,
classOf[HiveTableScanExecTransformer])

testExecPlan(
"true",
"true",
shouldFindTransformer = false,
classOf[FileSourceScanExecTransformer])
testExecPlan(
"true",
"false",
shouldFindTransformer = true,
classOf[FileSourceScanExecTransformer])
spark.sessionState.catalog.dropTable(
TableIdentifier("test_orc"),
ignoreIfNotExists = true,
purge = false)
testExecPlan(
"true",
"true",
shouldFindTransformer = false,
classOf[FileSourceScanExecTransformer])
testExecPlan(
"true",
"false",
shouldFindTransformer = true,
classOf[FileSourceScanExecTransformer])
}
}

ignoreGluten("orc.force.positional.evolution maps Hive ORC columns by position") {
Expand Down Expand Up @@ -285,22 +278,20 @@ class GlutenHiveSQLQuerySuite extends GlutenHiveSQLQuerySuiteBase {
}

testGluten("avoid unnecessary filter binding for subfield during scan") {
withSQLConf(
"spark.sql.hive.convertMetastoreParquet" -> "false") {
sql("DROP TABLE IF EXISTS test_subfield")
sql(
"CREATE TABLE test_subfield (name STRING, favorite_color STRING," +
" label STRUCT<label_1:STRING, label_2:STRING>) USING hive OPTIONS(fileFormat 'parquet')")
sql(
"INSERT INTO test_subfield VALUES('test_1', 'red', named_struct('label_1', 'label-a'," +
"'label_2', 'label-b'))")
val df = spark.sql("select * from test_subfield where name='test_1'")
checkAnswer(df, Seq(Row("test_1", "red", Row("label-a", "label-b"))))
checkOperatorMatch[HiveTableScanExecTransformer](df)
withTable("test_subfield") {
withSQLConf(
"spark.sql.hive.convertMetastoreParquet" -> "false") {
sql(
"CREATE TABLE test_subfield (name STRING, favorite_color STRING," +
" label STRUCT<label_1:STRING, label_2:STRING>)" +
" USING hive OPTIONS(fileFormat 'parquet')")
sql(
"INSERT INTO test_subfield VALUES('test_1', 'red', named_struct('label_1', 'label-a'," +
"'label_2', 'label-b'))")
val df = spark.sql("select * from test_subfield where name='test_1'")
checkAnswer(df, Seq(Row("test_1", "red", Row("label-a", "label-b"))))
checkOperatorMatch[HiveTableScanExecTransformer](df)
}
}
spark.sessionState.catalog.dropTable(
TableIdentifier("test_subfield"),
ignoreIfNotExists = true,
purge = false)
}
}
Loading
Loading