[ https://issues.apache.org/jira/browse/SPARK-20174?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15972211#comment-15972211 ]
Takeshi Yamamuro commented on SPARK-20174: ------------------------------------------ To fix this, it seems to be okay to accept Seq[String] in the first argument of withColumn for multi aliases; {code} scala> val df = Seq((Seq(1, 2, 3))).toDF("a") scala> df.select(posexplode($"a").as("p" :: "c" :: Nil)).show +---+---+ | p| c| +---+---+ | 0| 1| | 1| 2| | 2| 3| +---+---+ scala> df.withColumn("p" :: "c" :: Nil, posexplode($"a")).show <console>:26: error: type mismatch; found : List[String] required: String df.withColumn("p" :: "c" :: Nil, posexplode($"a")).show {code} > Analyzer gives mysterious AnalysisException when posexplode used in withColumn > ------------------------------------------------------------------------------ > > Key: SPARK-20174 > URL: https://issues.apache.org/jira/browse/SPARK-20174 > Project: Spark > Issue Type: Improvement > Components: SQL > Affects Versions: 2.2.0 > Reporter: Jacek Laskowski > Priority: Minor > > Wish I knew how to even describe the issue. It appears that {{posexplode}} > cannot be used in {{withColumn}}, but the error message does not seem to say > it. > [The scaladoc of > posexplode|http://spark.apache.org/docs/latest/api/scala/index.html#org.apache.spark.sql.functions$@posexplode(e:org.apache.spark.sql.Column):org.apache.spark.sql.Column] > is silent about this "limitation", too. > {code} > scala> codes.printSchema > root > |-- id: integer (nullable = false) > |-- rate_plan_code: array (nullable = true) > | |-- element: string (containsNull = true) > scala> codes.withColumn("code", posexplode($"rate_plan_code")).show > org.apache.spark.sql.AnalysisException: The number of aliases supplied in the > AS clause does not match the number of columns output by the UDTF expected 2 > aliases but got code ; > at > org.apache.spark.sql.catalyst.analysis.CheckAnalysis$class.failAnalysis(CheckAnalysis.scala:40) > at > org.apache.spark.sql.catalyst.analysis.Analyzer.failAnalysis(Analyzer.scala:90) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveGenerate$.makeGeneratorOutput(Analyzer.scala:1744) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ExtractGenerator$$anonfun$apply$20$$anonfun$56.apply(Analyzer.scala:1691) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ExtractGenerator$$anonfun$apply$20$$anonfun$56.apply(Analyzer.scala:1679) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) > at > scala.collection.TraversableLike$$anonfun$flatMap$1.apply(TraversableLike.scala:241) > at > scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) > at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) > at scala.collection.TraversableLike$class.flatMap(TraversableLike.scala:241) > at scala.collection.AbstractTraversable.flatMap(Traversable.scala:104) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ExtractGenerator$$anonfun$apply$20.applyOrElse(Analyzer.scala:1679) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ExtractGenerator$$anonfun$apply$20.applyOrElse(Analyzer.scala:1664) > at > org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:62) > at > org.apache.spark.sql.catalyst.plans.logical.LogicalPlan$$anonfun$resolveOperators$1.apply(LogicalPlan.scala:62) > at > org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70) > at > org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:61) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ExtractGenerator$.apply(Analyzer.scala:1664) > at > org.apache.spark.sql.catalyst.analysis.Analyzer$ExtractGenerator$.apply(Analyzer.scala:1629) > 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$1.apply(RuleExecutor.scala:82) > at > scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124) > at scala.collection.immutable.List.foldLeft(List.scala:84) > 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$1.apply(RuleExecutor.scala:74) > at scala.collection.immutable.List.foreach(List.scala:381) > at > org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:74) > at > org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:70) > at > org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:68) > at > org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:51) > at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:67) > at > org.apache.spark.sql.Dataset.org$apache$spark$sql$Dataset$$withPlan(Dataset.scala:2832) > at org.apache.spark.sql.Dataset.select(Dataset.scala:1137) > at org.apache.spark.sql.Dataset.withColumn(Dataset.scala:1882) > ... 48 elided > scala> codes.select(posexplode($"rate_plan_code")).show > +---+------+ > |pos| col| > +---+------+ > | 0| AAA| > | 1| RACK| > | 2|SMOBIX| > | 3|SMOBPX| > +---+------+ > {code} -- This message was sent by Atlassian JIRA (v6.3.15#6346) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org