[
https://issues.apache.org/jira/browse/SPARK-18137?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15648291#comment-15648291
]
Herman van Hovell commented on SPARK-18137:
-------------------------------------------
[~srowen] How did you set the Assignee? I spend a while on this, but could not
figure out how to do it.
> RewriteDistinctAggregates UnresolvedException when a UDAF has a foldable
> TypeCheck
> ----------------------------------------------------------------------------------
>
> Key: SPARK-18137
> URL: https://issues.apache.org/jira/browse/SPARK-18137
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 2.1.0
> Reporter: Song Jun
> Assignee: Song Jun
> Fix For: 2.0.3, 2.1.0
>
>
> when run a sql with distinct(on spark github master branch), it throw
> UnresolvedException.
> For example:
> run a test case on spark(branch master) with sql:
> {noformat}
> SELECT percentile_approx(key, 0.99999), count(distinct key),sum(distinct key)
> FROM src LIMIT 1
> {noformat}
> and it throw exception:
> {noformat}
> org.apache.spark.sql.catalyst.analysis.UnresolvedException: Invalid call to
> dataType on unresolved object, tree: 'percentile_approx(CAST(src.`key` AS
> DOUBLE), CAST(0.99999BD AS DOUBLE), 10000)
> at
> org.apache.spark.sql.catalyst.analysis.UnresolvedAttribute.dataType(unresolved.scala:92)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$.org$apache$spark$sql$catalyst$optimizer$RewriteDistinctAggregates$$nullify(RewriteDistinctAggregates.scala:261)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$.org$apache$spark$sql$catalyst$optimizer$RewriteDistinctAggregates$$evalWithinGroup$1(RewriteDistinctAggregates.scala:136)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$$anonfun$16.apply(RewriteDistinctAggregates.scala:187)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$$anonfun$16.apply(RewriteDistinctAggregates.scala:180)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:234)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:234)
> at scala.collection.immutable.List.map(List.scala:285)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$.rewrite(RewriteDistinctAggregates.scala:180)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$$anonfun$apply$1.applyOrElse(RewriteDistinctAggregates.scala:105)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$$anonfun$apply$1.applyOrElse(RewriteDistinctAggregates.scala:104)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:301)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:301)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:69)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:300)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$5.apply(TreeNode.scala:321)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:179)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformChildren(TreeNode.scala:319)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:298)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$.apply(RewriteDistinctAggregates.scala:104)
> at
> org.apache.spark.sql.catalyst.optimizer.RewriteDistinctAggregates$.apply(RewriteDistinctAggregates.scala:102)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:85)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:82)
> at
> scala.collection.IndexedSeqOptimized$class.foldl(IndexedSeqOptimized.scala:57)
> at
> scala.collection.IndexedSeqOptimized$class.foldLeft(IndexedSeqOptimized.scala:66)
> at scala.collection.mutable.WrappedArray.foldLeft(WrappedArray.scala:35)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:82)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:74)
> at scala.collection.immutable.List.foreach(List.scala:381)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74)
> at
> org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:74)
> at
> org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:74)
> at
> org.apache.spark.sql.execution.QueryExecution.sparkPlan$lzycompute(QueryExecution.scala:78)
> at
> org.apache.spark.sql.execution.QueryExecution.sparkPlan(QueryExecution.scala:76)
> at
> org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:83)
> at
> org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:83)
> at org.apache.spark.sql.Dataset.withTypedCallback(Dataset.scala:2572)
> at org.apache.spark.sql.Dataset.head(Dataset.scala:1934)
> at org.apache.spark.sql.Dataset.take(Dataset.scala:2149)
> at
> com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation0(OutputAggregator.scala:76)
> at
> com.databricks.backend.daemon.driver.OutputAggregator$.withOutputAggregation(OutputAggregator.scala:42)
> at
> com.databricks.backend.daemon.driver.SQLDriverLocal.executeSql(SQLDriverLocal.scala:100)
> at
> com.databricks.backend.daemon.driver.SQLDriverLocal.repl(SQLDriverLocal.scala:128)
> at
> com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$1.apply(DriverLocal.scala:202)
> at
> com.databricks.backend.daemon.driver.DriverLocal$$anonfun$execute$1.apply(DriverLocal.scala:191)
> at
> com.databricks.logging.UsageLogging$$anonfun$withAttributionContext$1.apply(UsageLogging.scala:145)
> at scala.util.DynamicVariable.withValue(DynamicVariable.scala:58)
> at
> com.databricks.logging.UsageLogging$class.withAttributionContext(UsageLogging.scala:140)
> at
> com.databricks.backend.daemon.driver.DriverLocal.withAttributionContext(DriverLocal.scala:34)
> at
> com.databricks.logging.UsageLogging$class.withAttributionTags(UsageLogging.scala:178)
> at
> com.databricks.backend.daemon.driver.DriverLocal.withAttributionTags(DriverLocal.scala:34)
> at
> com.databricks.backend.daemon.driver.DriverLocal.execute(DriverLocal.scala:191)
> at
> com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:584)
> at
> com.databricks.backend.daemon.driver.DriverWrapper$$anonfun$tryExecutingCommand$2.apply(DriverWrapper.scala:584)
> at scala.util.Try$.apply(Try.scala:192)
> at
> com.databricks.backend.daemon.driver.DriverWrapper.tryExecutingCommand(DriverWrapper.scala:579)
> at
> com.databricks.backend.daemon.driver.DriverWrapper.executeCommand(DriverWrapper.scala:491)
> at
> com.databricks.backend.daemon.driver.DriverWrapper.runInnerLoop(DriverWrapper.scala:394)
> at
> com.databricks.backend.daemon.driver.DriverWrapper.runInner(DriverWrapper.scala:351)
> at
> com.databricks.backend.daemon.driver.DriverWrapper.run(DriverWrapper.scala:217)
> at java.lang.Thread.run(Thread.java:745)
> {noformat}
--
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
