[
https://issues.apache.org/jira/browse/SPARK-10741?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14906801#comment-14906801
]
Ian commented on SPARK-10741:
-----------------------------
Two of my tests failed.
The query returns nothing.
{code}
test("test insert overwrite parquet ") {
val ddl= List(
"DROP TABLE IF EXISTS tmp",
"DROP TABLE IF EXISTS test",
"CREATE TABLE IF NOT EXISTS tmp ( c1 string, c2 int )",
"""INSERT INTO TABLE tmp select "test1" as c1, (count(*)+1) *10 as c2
from tmp""",
"""INSERT INTO TABLE tmp select "test1" as c1, (count(*)+1) *10 as c2
from tmp""",
"""INSERT INTO TABLE tmp select "test2" as c1, (count(*)+1) *10 as c2
from tmp""",
"""INSERT INTO TABLE tmp select "test2" as c1, (count(*)+1) *10 as c2
from tmp""",
"CREATE TABLE IF NOT EXISTS test ( c1 string, c2 int ) STORED AS PARQUET",
"INSERT OVERWRITE TABLE test SELECT * FROM tmp"
)
ddl.foreach{ x =>
TestHive.sql(x).collect()
}
val tmp = TestHive.sql("select c1, c2 from tmp").collect()
val test = TestHive.sql("select c1, c2 from test").collect()
assert(tmp === test)
}
Array([test1,10], [test1,20], [test2,30], [test2,40]) did not equal Array()
ScalaTestFailureLocation:
org.apache.spark.sql.hive.ParquetRelationTestSuite$$anonfun$1 at
(ParquetRelationTestSuite.scala:29)
org.scalatest.exceptions.TestFailedException: Array([test1,10], [test1,20],
[test2,30], [test2,40]) did not equal Array()
{code}
{code}
test("test insert into parquet ") {
val ddl= List(
"DROP TABLE IF EXISTS tmp",
"DROP TABLE IF EXISTS test",
"CREATE TABLE IF NOT EXISTS tmp ( c1 string, c2 int )",
"CREATE TABLE IF NOT EXISTS test ( c1 string, c2 int ) STORED AS PARQUET",
"""INSERT INTO TABLE test select "test1" as c1, (count(*)+1) *10 as c2
from test""",
"""INSERT INTO TABLE test select "test1" as c1, (count(*)+1) *10 as c2
from test""",
"""INSERT INTO TABLE test select "test2" as c1, (count(*)+1) *10 as c2
from test""",
"""INSERT INTO TABLE test select "test2" as c1, (count(*)+1) *10 as c2
from test"""
)
ddl.foreach{ x =>
TestHive.sql(x).collect()
}
val test = TestHive.sql("select c1, c2 from test").collect()
assert(test.length == 4)
}
Array() had length 0 instead of expected length 4
ScalaTestFailureLocation:
org.apache.spark.sql.hive.ParquetRelationTestSuite$$anonfun$2 at
(ParquetRelationTestSuite.scala:48)
org.scalatest.exceptions.TestFailedException: Array() had length 0 instead of
expected length 4
{code}
> Hive Query Having/OrderBy against Parquet table is not working
> ---------------------------------------------------------------
>
> Key: SPARK-10741
> URL: https://issues.apache.org/jira/browse/SPARK-10741
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.5.0
> Reporter: Ian
> Assignee: Wenchen Fan
>
> Failed Query with Having Clause
> {code}
> def testParquetHaving() {
> val ddl =
> """CREATE TABLE IF NOT EXISTS test ( c1 string, c2 int ) STORED AS
> PARQUET"""
> val failedHaving =
> """ SELECT c1, avg ( c2 ) as c_avg
> | FROM test
> | GROUP BY c1
> | HAVING ( avg ( c2 ) > 5) ORDER BY c1""".stripMargin
> TestHive.sql(ddl)
> TestHive.sql(failedHaving).collect
> }
> org.apache.spark.sql.AnalysisException: resolved attribute(s) c2#16 missing
> from c1#17,c2#18 in operator !Aggregate [c1#17], [cast((avg(cast(c2#16 as
> bigint)) > cast(5 as double)) as boolean) AS
> havingCondition#12,c1#17,avg(cast(c2#18 as bigint)) AS c_avg#9];
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:37)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:44)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:154)
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$$anonfun$checkAnalysis$1.apply(CheckAnalysis.scala:49)
> {code}
> Failed Query with OrderBy
> {code}
> def testParquetOrderBy() {
> val ddl =
> """CREATE TABLE IF NOT EXISTS test ( c1 string, c2 int ) STORED AS
> PARQUET"""
> val failedOrderBy =
> """ SELECT c1, avg ( c2 ) c_avg
> | FROM test
> | GROUP BY c1
> | ORDER BY avg ( c2 )""".stripMargin
> TestHive.sql(ddl)
> TestHive.sql(failedOrderBy).collect
> }
> org.apache.spark.sql.AnalysisException: resolved attribute(s) c2#33 missing
> from c1#34,c2#35 in operator !Aggregate [c1#34], [avg(cast(c2#33 as bigint))
> AS aggOrder#31,c1#34,avg(cast(c2#35 as bigint)) AS c_avg#28];
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:37)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:44)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
