beliefer commented on a change in pull request #28060: [SPARK-31291][SQL][TEST]
Avoid load test data if test case not uses them
URL: https://github.com/apache/spark/pull/28060#discussion_r405257472
##########
File path: sql/core/src/test/scala/org/apache/spark/sql/SQLQueryTestSuite.scala
##########
@@ -570,82 +579,94 @@ class SQLQueryTestSuite extends QueryTest with
SharedSparkSession {
}
/** Load built-in test tables into the SparkSession. */
- private def loadTestData(session: SparkSession): Unit = {
+ private def loadTestData(session: SparkSession, testTables: Seq[String]):
Unit = {
import session.implicits._
- (1 to 100).map(i => (i, i.toString)).toDF("key",
"value").createOrReplaceTempView("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")
-
- (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")
-
- session
- .read
- .format("csv")
- .options(Map("delimiter" -> "\t", "header" -> "false"))
- .schema("a int, b float")
- .load(testFile("test-data/postgresql/agg.data"))
- .createOrReplaceTempView("aggtest")
-
- session
- .read
- .format("csv")
- .options(Map("delimiter" -> "\t", "header" -> "false"))
- .schema(
- """
- |unique1 int,
- |unique2 int,
- |two int,
- |four int,
- |ten int,
- |twenty int,
- |hundred int,
- |thousand int,
- |twothousand int,
- |fivethous int,
- |tenthous int,
- |odd int,
- |even int,
- |stringu1 string,
- |stringu2 string,
- |string4 string
- """.stripMargin)
- .load(testFile("test-data/postgresql/onek.data"))
- .createOrReplaceTempView("onek")
-
- session
- .read
- .format("csv")
- .options(Map("delimiter" -> "\t", "header" -> "false"))
- .schema(
- """
- |unique1 int,
- |unique2 int,
- |two int,
- |four int,
- |ten int,
- |twenty int,
- |hundred int,
- |thousand int,
- |twothousand int,
- |fivethous int,
- |tenthous int,
- |odd int,
- |even int,
- |stringu1 string,
- |stringu2 string,
- |string4 string
- """.stripMargin)
- .load(testFile("test-data/postgresql/tenk.data"))
- .createOrReplaceTempView("tenk1")
+ if (testTables.contains("testdata")) {
+ (1 to 100).map(i => (i, i.toString)).toDF("key",
"value").createOrReplaceTempView("testdata")
+ }
+
+ if (testTables.contains("arraydata")) {
+ ((Seq(1, 2, 3), Seq(Seq(1, 2, 3))) :: (Seq(2, 3, 4), Seq(Seq(2, 3, 4)))
:: Nil)
+ .toDF("arraycol", "nestedarraycol")
+ .createOrReplaceTempView("arraydata")
Review comment:
@cloud-fan @maropu
I tried use `createGlobalTempView` but failed.
If we want share the global temp view, we must not use
`sparkSession.newSession()`.
Because every test case use a new session by `sparkSession.newSession()`.
If all the test case use the same `sparkSession`, another issue will occur.
such as:
test case A create view testdata, and test case B will also create view
testdata. However, the schema information of the two testdata is different. If
the same session is shared globally, it will cause conflicts, especially in
parallel execution.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
