Skip to content

[SPARK-31291][SQL][TEST] SQLQueryTestSuite: Sharing test data and test tables among multiple test cases #28060

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
beliefer wants to merge 3 commits into from
Closed

[SPARK-31291][SQL][TEST] SQLQueryTestSuite: Sharing test data and test tables among multiple test cases #28060

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
45bba4c
Optimize code
beliefer Apr 8, 2020
40bde64
Fix limit without order.
beliefer Apr 9, 2020
af42f50
Adjust method name
beliefer Apr 9, 2020
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
2 changes: 1 addition & 1 deletion sql/core/src/test/resources/sql-tests/results/limit.sql.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -88,7 +88,7 @@ SELECT * FROM testdata LIMIT key > 3
struct<>
-- !query output
org.apache.spark.sql.AnalysisException
The limit expression must evaluate to a constant value, but got (testdata.`key` > 3);
The limit expression must evaluate to a constant value, but got (spark_catalog.default.testdata.`key` > 3);


-- !query
Expand Down
12 changes: 0 additions & 12 deletions sql/core/src/test/resources/sql-tests/results/show-tables.sql.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,31 +63,19 @@ SHOW TABLES
-- !query schema
struct<database:string,tableName:string,isTemporary:boolean>
-- !query output
aggtest
arraydata
mapdata
onek
show_t1
show_t2
show_t3
tenk1
testdata


-- !query
SHOW TABLES IN showdb
-- !query schema
struct<database:string,tableName:string,isTemporary:boolean>
-- !query output
aggtest
arraydata
mapdata
onek
show_t1
show_t2
show_t3
tenk1
testdata


-- !query
Expand Down
24 changes: 0 additions & 24 deletions sql/core/src/test/resources/sql-tests/results/show-views.sql.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,12 +63,6 @@ SHOW VIEWS
-- !query schema
struct<namespace:string,viewName:string,isTemporary:boolean>
-- !query output
aggtest
arraydata
mapdata
onek
tenk1
testdata
view_1
view_2
view_4
Expand All @@ -79,12 +73,6 @@ SHOW VIEWS FROM showdb
-- !query schema
struct<namespace:string,viewName:string,isTemporary:boolean>
-- !query output
aggtest
arraydata
mapdata
onek
tenk1
testdata
view_1
view_2
view_4
Expand All @@ -95,12 +83,6 @@ SHOW VIEWS IN showdb
-- !query schema
struct<namespace:string,viewName:string,isTemporary:boolean>
-- !query output
aggtest
arraydata
mapdata
onek
tenk1
testdata
view_1
view_2
view_4
Expand All @@ -111,12 +93,6 @@ SHOW VIEWS IN global_temp
-- !query schema
struct<namespace:string,viewName:string,isTemporary:boolean>
-- !query output
aggtest
arraydata
mapdata
onek
tenk1
testdata
view_3
view_4

Expand Down
40 changes: 32 additions & 8 deletions sql/core/src/test/scala/org/apache/spark/sql/SQLQueryTestSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,7 +363,6 @@ class SQLQueryTestSuite extends QueryTest with SharedSparkSession {
// Create a local SparkSession to have stronger isolation between different test cases.
// This does not isolate catalog changes.
val localSparkSession = spark.newSession()
loadTestData(localSparkSession)

testCase match {
case udfTestCase: UDFTest =>
Expand Down Expand Up @@ -572,30 +571,40 @@ class SQLQueryTestSuite extends QueryTest with SharedSparkSession {
}

/** Load built-in test tables into the SparkSession. */
private def loadTestData(session: SparkSession): Unit = {
private def createTestTables(session: SparkSession): Unit = {
import session.implicits._

(1 to 100).map(i => (i, i.toString)).toDF("key", "value").createOrReplaceTempView("testdata")
(1 to 100).map(i => (i, i.toString)).toDF("key", "value")
.repartition(1)
.write
.format("parquet")
.saveAsTable("testdata")

((Seq(1, 2, 3), Seq(Seq(1, 2, 3))) :: (Seq(2, 3, 4), Seq(Seq(2, 3, 4))) :: Nil)
.toDF("arraycol", "nestedarraycol")
.createOrReplaceTempView("arraydata")
.write
.format("parquet")
.saveAsTable("arraydata")

(Tuple1(Map(1 -> "a1", 2 -> "b1", 3 -> "c1", 4 -> "d1", 5 -> "e1")) ::
Tuple1(Map(1 -> "a2", 2 -> "b2", 3 -> "c2", 4 -> "d2")) ::
Tuple1(Map(1 -> "a3", 2 -> "b3", 3 -> "c3")) ::
Tuple1(Map(1 -> "a4", 2 -> "b4")) ::
Tuple1(Map(1 -> "a5")) :: Nil)
.toDF("mapcol")
.createOrReplaceTempView("mapdata")
.write
.format("parquet")
.saveAsTable("mapdata")

session
.read
.format("csv")
.options(Map("delimiter" -> "\t", "header" -> "false"))
.schema("a int, b float")
.load(testFile("test-data/postgresql/agg.data"))
Copy link
Copy Markdown
Member

@dongjoon-hyun dongjoon-hyun Apr 11, 2020

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This seems to be the root cause of failure.

 java.lang.IllegalArgumentException: java.net.URISyntaxException: Relative path in absolute URI: jar:file:/home/jenkins/workspace/spark-branch-3.0-test-maven-hadoop-2.7-hive-2.3/sql/core/target/spark-sql_2.12-3.0.1-SNAPSHOT-tests.jar!/test-data/postgresql/agg.data

.createOrReplaceTempView("aggtest")
.write
.format("parquet")
.saveAsTable("aggtest")

session
.read
Expand All @@ -621,7 +630,9 @@ class SQLQueryTestSuite extends QueryTest with SharedSparkSession {
|string4 string
""".stripMargin)
.load(testFile("test-data/postgresql/onek.data"))
.createOrReplaceTempView("onek")
.write
.format("parquet")
.saveAsTable("onek")

session
.read
Expand All @@ -647,14 +658,26 @@ class SQLQueryTestSuite extends QueryTest with SharedSparkSession {
|string4 string
""".stripMargin)
.load(testFile("test-data/postgresql/tenk.data"))
.createOrReplaceTempView("tenk1")
.write
.format("parquet")
.saveAsTable("tenk1")
}

private def removeTestTables(session: SparkSession): Unit = {
session.sql("DROP TABLE IF EXISTS testdata")
session.sql("DROP TABLE IF EXISTS arraydata")
session.sql("DROP TABLE IF EXISTS mapdata")
session.sql("DROP TABLE IF EXISTS aggtest")
session.sql("DROP TABLE IF EXISTS onek")
session.sql("DROP TABLE IF EXISTS tenk1")
}

private val originalTimeZone = TimeZone.getDefault
private val originalLocale = Locale.getDefault

override def beforeAll(): Unit = {
super.beforeAll()
createTestTables(spark)
// Timezone is fixed to America/Los_Angeles for those timezone sensitive tests (timestamp_*)
TimeZone.setDefault(TimeZone.getTimeZone("America/Los_Angeles"))
// Add Locale setting
Expand All @@ -668,6 +691,7 @@ class SQLQueryTestSuite extends QueryTest with SharedSparkSession {
try {
TimeZone.setDefault(originalTimeZone)
Locale.setDefault(originalLocale)
removeTestTables(spark)

// For debugging dump some statistics about how much time was spent in various optimizer rules
logWarning(RuleExecutor.dumpTimeSpent())
Expand Down