Github user marmbrus commented on a diff in the pull request:
https://github.com/apache/spark/pull/7191#discussion_r35706609
--- Diff:
sql/hive/src/test/scala/org/apache/spark/sql/hive/parquetSuites.scala ---
@@ -255,118 +263,118 @@ class ParquetMetastoreSuite extends
ParquetPartitioningTest {
sql(s"SELECT intField, stringField FROM test_insert_parquet"),
(1 to 10).map(i => Row(i, s"str$i")) ++ (1 to 4).map(i => Row(i,
s"str$i"))
)
- sql("DROP TABLE IF EXISTS test_insert_parquet")
+ dropTables("test_insert_parquet")
}
test("scan a parquet table created through a CTAS statement") {
- sql(
- """
- |create table test_parquet_ctas ROW FORMAT
- |SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
- |STORED AS
- | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
- | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
- |AS select * from jt
- """.stripMargin)
+ withTable("test_parquet_ctas") {
+ sql(
+ """
+ |create table test_parquet_ctas ROW FORMAT
+ |SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
+ |STORED AS
+ | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
+ | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
+ |AS select * from jt
+ """.stripMargin)
- checkAnswer(
- sql(s"SELECT a, b FROM test_parquet_ctas WHERE a = 1"),
- Seq(Row(1, "str1"))
- )
+ checkAnswer(
+ sql(s"SELECT a, b FROM test_parquet_ctas WHERE a = 1"),
+ Seq(Row(1, "str1"))
+ )
- table("test_parquet_ctas").queryExecution.optimizedPlan match {
- case LogicalRelation(_: ParquetRelation) => // OK
- case _ => fail(
- "test_parquet_ctas should be converted to " +
- s"${classOf[ParquetRelation].getCanonicalName}")
+ table("test_parquet_ctas").queryExecution.optimizedPlan match {
+ case LogicalRelation(_: ParquetRelation) => // OK
+ case _ => fail(
+ "test_parquet_ctas should be converted to " +
+ s"${classOf[ParquetRelation].getCanonicalName }")
+ }
}
-
- sql("DROP TABLE IF EXISTS test_parquet_ctas")
}
test("MetastoreRelation in InsertIntoTable will be converted") {
- sql(
- """
- |create table test_insert_parquet
- |(
- | intField INT
- |)
- |ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
- |STORED AS
- | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
- | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
- """.stripMargin)
+ withTable("test_insert_parquet") {
+ sql(
+ """
+ |create table test_insert_parquet
+ |(
+ | intField INT
+ |)
+ |ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
+ |STORED AS
+ | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
+ | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
+ """.stripMargin)
+
+ val df = sql("INSERT INTO TABLE test_insert_parquet SELECT a FROM
jt")
+ df.queryExecution.executedPlan match {
+ case ExecutedCommand(InsertIntoHadoopFsRelation(_:
ParquetRelation, _, _)) => // OK
+ case o => fail("test_insert_parquet should be converted to a " +
+ s"${classOf[ParquetRelation].getCanonicalName} and " +
+ s"${classOf[InsertIntoDataSource].getCanonicalName} is expcted
as the SparkPlan. " +
+ s"However, found a ${o.toString} ")
+ }
- val df = sql("INSERT INTO TABLE test_insert_parquet SELECT a FROM jt")
- df.queryExecution.executedPlan match {
- case ExecutedCommand(InsertIntoHadoopFsRelation(_: ParquetRelation,
_, _)) => // OK
- case o => fail("test_insert_parquet should be converted to a " +
- s"${classOf[ParquetRelation].getCanonicalName} and " +
- s"${classOf[InsertIntoDataSource].getCanonicalName} is expcted as
the SparkPlan. " +
- s"However, found a ${o.toString} ")
+ checkAnswer(
+ sql("SELECT intField FROM test_insert_parquet WHERE
test_insert_parquet.intField > 5"),
+ sql("SELECT a FROM jt WHERE jt.a > 5").collect()
+ )
}
-
- checkAnswer(
- sql("SELECT intField FROM test_insert_parquet WHERE
test_insert_parquet.intField > 5"),
- sql("SELECT a FROM jt WHERE jt.a > 5").collect()
- )
-
- sql("DROP TABLE IF EXISTS test_insert_parquet")
}
test("MetastoreRelation in InsertIntoHiveTable will be converted") {
- sql(
- """
- |create table test_insert_parquet
- |(
- | int_array array<int>
- |)
- |ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
- |STORED AS
- | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
- | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
- """.stripMargin)
+ withTable("test_insert_parquet") {
+ sql(
+ """
+ |create table test_insert_parquet
+ |(
+ | int_array array<int>
+ |)
+ |ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
+ |STORED AS
+ | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
+ | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
+ """.stripMargin)
+
+ val df = sql("INSERT INTO TABLE test_insert_parquet SELECT a FROM
jt_array")
+ df.queryExecution.executedPlan match {
+ case ExecutedCommand(InsertIntoHadoopFsRelation(r:
ParquetRelation, _, _)) => // OK
+ case o => fail("test_insert_parquet should be converted to a " +
+ s"${classOf[ParquetRelation].getCanonicalName} and " +
+ s"${classOf[InsertIntoDataSource].getCanonicalName} is expcted
as the SparkPlan." +
+ s"However, found a ${o.toString} ")
+ }
- val df = sql("INSERT INTO TABLE test_insert_parquet SELECT a FROM
jt_array")
- df.queryExecution.executedPlan match {
- case ExecutedCommand(InsertIntoHadoopFsRelation(r: ParquetRelation,
_, _)) => // OK
- case o => fail("test_insert_parquet should be converted to a " +
- s"${classOf[ParquetRelation].getCanonicalName} and " +
- s"${classOf[InsertIntoDataSource].getCanonicalName} is expcted as
the SparkPlan." +
- s"However, found a ${o.toString} ")
+ checkAnswer(
+ sql("SELECT int_array FROM test_insert_parquet"),
+ sql("SELECT a FROM jt_array").collect()
+ )
}
-
- checkAnswer(
- sql("SELECT int_array FROM test_insert_parquet"),
- sql("SELECT a FROM jt_array").collect()
- )
-
- sql("DROP TABLE IF EXISTS test_insert_parquet")
}
test("SPARK-6450 regression test") {
- sql(
- """CREATE TABLE IF NOT EXISTS ms_convert (key INT)
- |ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
- |STORED AS
- | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
- | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
- """.stripMargin)
+ withTable("ms_convert") {
+ sql(
+ """CREATE TABLE IF NOT EXISTS ms_convert (key INT)
+ |ROW FORMAT SERDE
'org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe'
+ |STORED AS
+ | INPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat'
+ | OUTPUTFORMAT
'org.apache.hadoop.hive.ql.io.parquet.MapredParquetOutputFormat'
+ """.stripMargin)
+
+ // This shouldn't throw AnalysisException
+ val analyzed = sql(
+ """SELECT key FROM ms_convert
+ |UNION ALL
+ |SELECT key FROM ms_convert
+ """.stripMargin).queryExecution.analyzed
- // This shouldn't throw AnalysisException
- val analyzed = sql(
- """SELECT key FROM ms_convert
- |UNION ALL
- |SELECT key FROM ms_convert
- """.stripMargin).queryExecution.analyzed
-
- assertResult(2) {
- analyzed.collect {
- case r @ LogicalRelation(_: ParquetRelation) => r
- }.size
+ assertResult(2) {
+ analyzed.collect {
+ case r@LogicalRelation(_: ParquetRelation) => r
--- End diff --
nit: spaces around `@`
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
