[
https://issues.apache.org/jira/browse/SPARK-21154?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Brian Zhang updated SPARK-21154:
--------------------------------
Description:
When creating View from another existing View in Spark SQL, we will see
ParseException if existing View.
Here is the detail on how to reproduce it:
*Hive* (I'm using 1.1.0):
hive> *CREATE TABLE my_table (id int, name string);*
OK
Time taken: 0.107 seconds
hive> *CREATE VIEW my_view(view_id,view_name) AS SELECT * FROM my_table;*
OK
Time taken: 0.075 seconds
# View Information
View Original Text: SELECT * FROM my_table
View Expanded Text: SELECT `id` AS `view_id`, `name` AS `view_name` FROM
(SELECT `my_table`.`id`, `my_table`.`name` FROM `default`.`my_table`)
`default.my_view`
Time taken: 0.04 seconds, Fetched: 28 row(s)
*Spark* (Same behavior for spark 2.1.0 and 2.1.1):
scala> *sqlContext.sql("CREATE VIEW my_view_spark AS SELECT * FROM my_view");*
java.lang.RuntimeException: Failed to analyze the canonicalized SQL: SELECT
`gen_attr_0` AS `view_id`, `gen_attr_1` AS `view_name` FROM (SELECT
`gen_attr_0`, `gen_attr_1` FROM (SELECT `gen_attr_2` AS `gen_attr_0`,
`gen_attr_3` AS `gen_attr_1` FROM (SELECT `gen_attr_2`, `gen_attr_3` FROM
(SELECT `id` AS `gen_attr_2`, `name` AS `gen_attr_3` FROM `default`.`my_table`)
AS gen_subquery_0) AS default.my_view) AS my_view) AS my_view
at
org.apache.spark.sql.execution.command.CreateViewCommand.prepareTable(views.scala:222)
at
org.apache.spark.sql.execution.command.CreateViewCommand.run(views.scala:176)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:87)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:87)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:185)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:699)
... 74 elided
Caused by: org.apache.spark.sql.catalyst.parser.ParseException:
mismatched input 'FROM' expecting {<EOF>, 'WHERE', 'GROUP', 'ORDER', 'HAVING',
'LIMIT', 'LATERAL', 'WINDOW', 'UNION', 'EXCEPT', 'MINUS', 'INTERSECT', 'SORT',
'CLUSTER', 'DISTRIBUTE'}(line 1, pos 62)
== SQL ==
SELECT `gen_attr_0` AS `view_id`, `gen_attr_1` AS `view_name` FROM (SELECT
`gen_attr_0`, `gen_attr_1` FROM (SELECT `gen_attr_2` AS `gen_attr_0`,
`gen_attr_3` AS `gen_attr_1` FROM (SELECT `gen_attr_2`, `gen_attr_3` FROM
(SELECT `id` AS `gen_attr_2`, `name` AS `gen_attr_3` FROM `default`.`my_table`)
AS gen_subquery_0) AS default.my_view) AS my_view) AS my_view
--------------------------------------------------------------^^^
at
org.apache.spark.sql.catalyst.parser.ParseException.withCommand(ParseDriver.scala:197)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parse(ParseDriver.scala:99)
at
org.apache.spark.sql.execution.SparkSqlParser.parse(SparkSqlParser.scala:45)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parsePlan(ParseDriver.scala:53)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
at
org.apache.spark.sql.execution.command.CreateViewCommand.prepareTable(views.scala:219)
... 90 more
was:
When creating View from another existing View in Spark SQL, we will see
ParseException if existing View.
Here is the detail on how to reproduce it:
*Hive* (I'm using 1.1.0):
hive> *CREATE TABLE my_table (id int, name string);*
OK
Time taken: 0.107 seconds
hive> *CREATE VIEW my_view(view_id,view_name) AS SELECT * FROM my_table;*
OK
Time taken: 0.075 seconds
# View Information
View Original Text: SELECT * FROM my_table
View Expanded Text: SELECT `id` AS `view_id`, `name` AS `view_name` FROM
(SELECT `my_table`.`id`, `my_table`.`name` FROM `default`.`my_table`)
`default.my_view`
Time taken: 0.04 seconds, Fetched: 28 row(s)
*Spark* (Same behavior for spark 2.1.0 and 2.1.1):
scala> sqlContext.sql("CREATE VIEW my_view_spark AS SELECT * FROM my_view");
java.lang.RuntimeException: Failed to analyze the canonicalized SQL: SELECT
`gen_attr_0` AS `view_id`, `gen_attr_1` AS `view_name` FROM (SELECT
`gen_attr_0`, `gen_attr_1` FROM (SELECT `gen_attr_2` AS `gen_attr_0`,
`gen_attr_3` AS `gen_attr_1` FROM (SELECT `gen_attr_2`, `gen_attr_3` FROM
(SELECT `id` AS `gen_attr_2`, `name` AS `gen_attr_3` FROM `default`.`my_table`)
AS gen_subquery_0) AS default.my_view) AS my_view) AS my_view
at
org.apache.spark.sql.execution.command.CreateViewCommand.prepareTable(views.scala:222)
at
org.apache.spark.sql.execution.command.CreateViewCommand.run(views.scala:176)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
at
org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:87)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:87)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:185)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:699)
... 74 elided
Caused by: org.apache.spark.sql.catalyst.parser.ParseException:
mismatched input 'FROM' expecting {<EOF>, 'WHERE', 'GROUP', 'ORDER', 'HAVING',
'LIMIT', 'LATERAL', 'WINDOW', 'UNION', 'EXCEPT', 'MINUS', 'INTERSECT', 'SORT',
'CLUSTER', 'DISTRIBUTE'}(line 1, pos 62)
== SQL ==
SELECT `gen_attr_0` AS `view_id`, `gen_attr_1` AS `view_name` FROM (SELECT
`gen_attr_0`, `gen_attr_1` FROM (SELECT `gen_attr_2` AS `gen_attr_0`,
`gen_attr_3` AS `gen_attr_1` FROM (SELECT `gen_attr_2`, `gen_attr_3` FROM
(SELECT `id` AS `gen_attr_2`, `name` AS `gen_attr_3` FROM `default`.`my_table`)
AS gen_subquery_0) AS default.my_view) AS my_view) AS my_view
--------------------------------------------------------------^^^
at
org.apache.spark.sql.catalyst.parser.ParseException.withCommand(ParseDriver.scala:197)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parse(ParseDriver.scala:99)
at
org.apache.spark.sql.execution.SparkSqlParser.parse(SparkSqlParser.scala:45)
at
org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parsePlan(ParseDriver.scala:53)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
at
org.apache.spark.sql.execution.command.CreateViewCommand.prepareTable(views.scala:219)
... 90 more
> ParseException when Create View from another View in Spark SQL
> ---------------------------------------------------------------
>
> Key: SPARK-21154
> URL: https://issues.apache.org/jira/browse/SPARK-21154
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.1.0, 2.1.1
> Reporter: Brian Zhang
>
> When creating View from another existing View in Spark SQL, we will see
> ParseException if existing View.
> Here is the detail on how to reproduce it:
> *Hive* (I'm using 1.1.0):
> hive> *CREATE TABLE my_table (id int, name string);*
> OK
> Time taken: 0.107 seconds
> hive> *CREATE VIEW my_view(view_id,view_name) AS SELECT * FROM my_table;*
> OK
> Time taken: 0.075 seconds
> # View Information
> View Original Text: SELECT * FROM my_table
> View Expanded Text: SELECT `id` AS `view_id`, `name` AS `view_name` FROM
> (SELECT `my_table`.`id`, `my_table`.`name` FROM `default`.`my_table`)
> `default.my_view`
> Time taken: 0.04 seconds, Fetched: 28 row(s)
> *Spark* (Same behavior for spark 2.1.0 and 2.1.1):
> scala> *sqlContext.sql("CREATE VIEW my_view_spark AS SELECT * FROM my_view");*
> java.lang.RuntimeException: Failed to analyze the canonicalized SQL: SELECT
> `gen_attr_0` AS `view_id`, `gen_attr_1` AS `view_name` FROM (SELECT
> `gen_attr_0`, `gen_attr_1` FROM (SELECT `gen_attr_2` AS `gen_attr_0`,
> `gen_attr_3` AS `gen_attr_1` FROM (SELECT `gen_attr_2`, `gen_attr_3` FROM
> (SELECT `id` AS `gen_attr_2`, `name` AS `gen_attr_3` FROM
> `default`.`my_table`) AS gen_subquery_0) AS default.my_view) AS my_view) AS
> my_view
> at
> org.apache.spark.sql.execution.command.CreateViewCommand.prepareTable(views.scala:222)
> at
> org.apache.spark.sql.execution.command.CreateViewCommand.run(views.scala:176)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:58)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:56)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:74)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:114)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:135)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:132)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:113)
> at
> org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:87)
> at
> org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:87)
> at org.apache.spark.sql.Dataset.<init>(Dataset.scala:185)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:64)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:699)
> ... 74 elided
> Caused by: org.apache.spark.sql.catalyst.parser.ParseException:
> mismatched input 'FROM' expecting {<EOF>, 'WHERE', 'GROUP', 'ORDER',
> 'HAVING', 'LIMIT', 'LATERAL', 'WINDOW', 'UNION', 'EXCEPT', 'MINUS',
> 'INTERSECT', 'SORT', 'CLUSTER', 'DISTRIBUTE'}(line 1, pos 62)
> == SQL ==
> SELECT `gen_attr_0` AS `view_id`, `gen_attr_1` AS `view_name` FROM (SELECT
> `gen_attr_0`, `gen_attr_1` FROM (SELECT `gen_attr_2` AS `gen_attr_0`,
> `gen_attr_3` AS `gen_attr_1` FROM (SELECT `gen_attr_2`, `gen_attr_3` FROM
> (SELECT `id` AS `gen_attr_2`, `name` AS `gen_attr_3` FROM
> `default`.`my_table`) AS gen_subquery_0) AS default.my_view) AS my_view) AS
> my_view
> --------------------------------------------------------------^^^
> at
> org.apache.spark.sql.catalyst.parser.ParseException.withCommand(ParseDriver.scala:197)
> at
> org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parse(ParseDriver.scala:99)
> at
> org.apache.spark.sql.execution.SparkSqlParser.parse(SparkSqlParser.scala:45)
> at
> org.apache.spark.sql.catalyst.parser.AbstractSqlParser.parsePlan(ParseDriver.scala:53)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:592)
> at
> org.apache.spark.sql.execution.command.CreateViewCommand.prepareTable(views.scala:219)
> ... 90 more
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
