[
https://issues.apache.org/jira/browse/SPARK-10741?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ian updated SPARK-10741:
------------------------
Description:
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$1.apply(CheckAnalysis.scala:49)
{code}
Failed Query with OrderBy
{code}
@Test
def testParquetOrderBy() {
val ddl =
"""CREATE TABLE IF NOT EXISTS test ( c1 string, c2 int ) STORED AS
PARQUET"""
val failedOrderBy =
""" SELECT c1, avg ( c2 ) c_avg
| FROM test
| GROUP BY c1
| ORDER BY avg ( c2 )""".stripMargin
TestHive.sql(ddl)
TestHive.sql(failedOrderBy).collect
}
org.apache.spark.sql.AnalysisException: resolved attribute(s) c2#33 missing
from c1#34,c2#35 in operator !Aggregate [c1#34], [avg(cast(c2#33 as bigint)) AS
aggOrder#31,c1#34,avg(cast(c2#35 as bigint)) AS c_avg#28];
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:37)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:44)
{code}
was:
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$1.apply(CheckAnalysis.scala:49)
{code}
Failed Query with OrderBy
{code}
val ddl =
"""CREATE TABLE IF NOT EXISTS test ( c1 string, c2 int ) STORED AS
PARQUET"""
val filedOrderBy =
""" SELECT c1, avg ( c2 ) c_avg
| FROM test
| GROUP BY c1
| ORDER BY avg ( c2 )""".stripMargin
TestHive.sql(ddl)
TestHive.sql(filedOrderBy).collect
org.apache.spark.sql.AnalysisException: resolved attribute(s) c2#33 missing
from c1#34,c2#35 in operator !Aggregate [c1#34], [avg(cast(c2#33 as bigint)) AS
aggOrder#31,c1#34,avg(cast(c2#35 as bigint)) AS c_avg#28];
at
org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:37)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:44)
{code}
> 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
>
> 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$1.apply(CheckAnalysis.scala:49)
> {code}
> Failed Query with OrderBy
> {code}
> @Test
> def testParquetOrderBy() {
> val ddl =
> """CREATE TABLE IF NOT EXISTS test ( c1 string, c2 int ) STORED AS
> PARQUET"""
> val failedOrderBy =
> """ SELECT c1, avg ( c2 ) c_avg
> | FROM test
> | GROUP BY c1
> | ORDER BY avg ( c2 )""".stripMargin
> TestHive.sql(ddl)
> TestHive.sql(failedOrderBy).collect
> }
> org.apache.spark.sql.AnalysisException: resolved attribute(s) c2#33 missing
> from c1#34,c2#35 in operator !Aggregate [c1#34], [avg(cast(c2#33 as bigint))
> AS aggOrder#31,c1#34,avg(cast(c2#35 as bigint)) AS c_avg#28];
> at
> org.apache.spark.sql.catalyst.analysis.CheckAnalysis$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
