Skip to content
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

[SPARK-33770][SQL][TESTS] Fix the ALTER TABLE .. DROP PARTITION tests that delete files out of partition path #30752

Closed
wants to merge 5 commits into from
Closed

[SPARK-33770][SQL][TESTS] Fix the ALTER TABLE .. DROP PARTITION tests that delete files out of partition path #30752

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5439710
Remove LOCATION from the test "universal type conversions of partitio…
MaxGekk Dec 13, 2020
4da34f2
Fix the test "create/drop partitions in managed tables with location"
MaxGekk Dec 13, 2020
8916218
Change paths in "add/drop partition with location - managed table"
MaxGekk Dec 13, 2020
4a9abab
Fix StatisticsSuite
MaxGekk Dec 13, 2020
e9a6133
Update sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/cata…
MaxGekk Dec 14, 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
11 changes: 9 additions & 2 deletions sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/catalog/ExternalCatalogSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -408,8 +408,8 @@ abstract class ExternalCatalogSuite extends SparkFunSuite with BeforeAndAfterEac
partitionColumnNames = Seq("partCol1", "partCol2"))
catalog.createTable(table, ignoreIfExists = false)

val newLocationPart1 = newUriForDatabase()
val newLocationPart2 = newUriForDatabase()
val newLocationPart1 = newUriForPartition(Seq("p1=1", "p2=2"))
val newLocationPart2 = newUriForPartition(Seq("p1=3", "p2=4"))

val partition1 =
CatalogTablePartition(Map("partCol1" -> "1", "partCol2" -> "2"),
Expand Down Expand Up @@ -991,6 +991,13 @@ abstract class CatalogTestUtils {

def newUriForDatabase(): URI = new URI(Utils.createTempDir().toURI.toString.stripSuffix("/"))

def newUriForPartition(parts: Seq[String]): URI = {
val path = parts.foldLeft(Utils.createTempDir()) {
case (parent, part) => new java.io.File(parent, part)
}
new URI(path.toURI.toString.stripSuffix("/"))
}

def newDb(name: String): CatalogDatabase = {
CatalogDatabase(name, name + " description", newUriForDatabase(), Map.empty)
}
Expand Down
2 changes: 1 addition & 1 deletion ...c/test/scala/org/apache/spark/sql/execution/command/AlterTableAddPartitionSuiteBase.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -154,7 +154,7 @@ trait AlterTableAddPartitionSuiteBase extends QueryTest with SQLTestUtils {
| part8 = '2020-11-23',
| part9 = '2020-11-23 22:13:10.123456'
|""".stripMargin
sql(s"ALTER TABLE $t ADD PARTITION ($partSpec) LOCATION 'loc1'")
Copy link
Member Author

Choose a reason for hiding this comment

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

location doesn't matter in the test.

sql(s"ALTER TABLE $t ADD PARTITION ($partSpec)")
val expected = Map(
"part0" -> "-1",
"part1" -> "0",
Expand Down
12 changes: 8 additions & 4 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/StatisticsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -983,12 +983,16 @@ class StatisticsSuite extends StatisticsCollectionTestBase with TestHiveSingleto
assert(fetched1.get.colStats.size == 2)

withTempPaths(numPaths = 2) { case Seq(dir1, dir2) =>
val file1 = new File(dir1 + "/data")
val partDir1 = new File(new File(dir1, "ds=2008-04-09"), "hr=11")
val file1 = new File(partDir1, "data")
file1.getParentFile.mkdirs()
Utils.tryWithResource(new PrintWriter(file1)) { writer =>
writer.write("1,a")
}

val file2 = new File(dir2 + "/data")
val partDir2 = new File(new File(dir2, "ds=2008-04-09"), "hr=12")
val file2 = new File(partDir2, "data")
file2.getParentFile.mkdirs()
Utils.tryWithResource(new PrintWriter(file2)) { writer =>
writer.write("1,a")
}
Expand All @@ -997,8 +1001,8 @@ class StatisticsSuite extends StatisticsCollectionTestBase with TestHiveSingleto
sql(
s"""
|ALTER TABLE $table ADD
|PARTITION (ds='2008-04-09', hr='11') LOCATION '${dir1.toURI.toString}'
|PARTITION (ds='2008-04-09', hr='12') LOCATION '${dir2.toURI.toString}'
|PARTITION (ds='2008-04-09', hr='11') LOCATION '${partDir1.toURI.toString}'
|PARTITION (ds='2008-04-09', hr='12') LOCATION '${partDir1.toURI.toString}'
Copy link
Member

Choose a reason for hiding this comment

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

Sorry for commenting here.

This bug is introduced here and backported to 2.4.8/3.0.2/3.1.0 and SPARK-38786 fixed this at master branch for Apache Spark 3.4 recently.

""".stripMargin)
if (autoUpdate) {
val fetched2 = checkTableStats(table, hasSizeInBytes = true, expectedRowCounts = None)
Expand Down
4 changes: 2 additions & 2 deletions sql/hive/src/test/scala/org/apache/spark/sql/hive/execution/HiveDDLSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -601,8 +601,8 @@ class HiveDDLSuite
val tab = "tab_with_partitions"
withTempDir { tmpDir =>
val basePath = new File(tmpDir.getCanonicalPath)
val part1Path = new File(basePath + "/part1")
val part2Path = new File(basePath + "/part2")
val part1Path = new File(new File(basePath, "part10"), "part11")
val part2Path = new File(new File(basePath, "part20"), "part21")
val dirSet = part1Path :: part2Path :: Nil

// Before data insertion, all the directory are empty
Expand Down