[
https://issues.apache.org/jira/browse/SPARK-8072?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14598890#comment-14598890
]
Animesh Baranawal edited comment on SPARK-8072 at 6/24/15 5:34 AM:
-------------------------------------------------------------------
[~rxin]
If we want the rule to apply only on some save/ouput action, would not it be
much intuitive to check the rule before calling write function instead of
adding the rule in checkanalysis.scala
was (Author: animeshbaranawal):
[~rxin]
If we want the rule to apply only on some save/ouput action, would not it be
much intuitive to add the rule in the DataFrameWriter.scala instead of in
CheckAnalysis.scala
> Better AnalysisException for writing DataFrame with identically named columns
> -----------------------------------------------------------------------------
>
> Key: SPARK-8072
> URL: https://issues.apache.org/jira/browse/SPARK-8072
> Project: Spark
> Issue Type: Sub-task
> Components: SQL
> Reporter: Reynold Xin
> Priority: Blocker
>
> We should check if there are duplicate columns, and if yes, throw an explicit
> error message saying there are duplicate columns. See current error message
> below.
> {code}
> In [3]: df.withColumn('age', df.age)
> Out[3]: DataFrame[age: bigint, name: string, age: bigint]
> In [4]: df.withColumn('age', df.age).write.parquet('test-parquet.out')
> ---------------------------------------------------------------------------
> Py4JJavaError Traceback (most recent call last)
> <ipython-input-4-eecb85256898> in <module>()
> ----> 1 df.withColumn('age', df.age).write.parquet('test-parquet.out')
> /scratch/rxin/spark/python/pyspark/sql/readwriter.py in parquet(self, path,
> mode)
> 350 >>> df.write.parquet(os.path.join(tempfile.mkdtemp(), 'data'))
> 351 """
> --> 352 self._jwrite.mode(mode).parquet(path)
> 353
> 354 @since(1.4)
> /Users/rxin/anaconda/lib/python2.7/site-packages/py4j-0.8.1-py2.7.egg/py4j/java_gateway.pyc
> in __call__(self, *args)
> 535 answer = self.gateway_client.send_command(command)
> 536 return_value = get_return_value(answer, self.gateway_client,
> --> 537 self.target_id, self.name)
> 538
> 539 for temp_arg in temp_args:
> /Users/rxin/anaconda/lib/python2.7/site-packages/py4j-0.8.1-py2.7.egg/py4j/protocol.pyc
> in get_return_value(answer, gateway_client, target_id, name)
> 298 raise Py4JJavaError(
> 299 'An error occurred while calling {0}{1}{2}.\n'.
> --> 300 format(target_id, '.', name), value)
> 301 else:
> 302 raise Py4JError(
> Py4JJavaError: An error occurred while calling o35.parquet.
> : org.apache.spark.sql.AnalysisException: Reference 'age' is ambiguous, could
> be: age#0L, age#3L.;
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolve(LogicalPlan.scala:279)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveChildren(LogicalPlan.scala:116)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4$$anonfun$16.apply(Analyzer.scala:350)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4$$anonfun$16.apply(Analyzer.scala:350)
> at
> org.apache.spark.sql.catalyst.analysis.package$.withPosition(package.scala:48)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4.applyOrElse(Analyzer.scala:350)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8$$anonfun$applyOrElse$4.applyOrElse(Analyzer.scala:341)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:285)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.org$apache$spark$sql$catalyst$plans$QueryPlan$$transformExpressionUp$1(QueryPlan.scala:108)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2$$anonfun$apply$2.apply(QueryPlan.scala:123)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan$$anonfun$2.apply(QueryPlan.scala:122)
> at scala.collection.Iterator$$anon$11.next(Iterator.scala:328)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> at
> scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:103)
> at
> scala.collection.mutable.ArrayBuffer.$plus$plus$eq(ArrayBuffer.scala:47)
> at scala.collection.TraversableOnce$class.to(TraversableOnce.scala:273)
> at scala.collection.AbstractIterator.to(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toBuffer(TraversableOnce.scala:265)
> at scala.collection.AbstractIterator.toBuffer(Iterator.scala:1157)
> at
> scala.collection.TraversableOnce$class.toArray(TraversableOnce.scala:252)
> at scala.collection.AbstractIterator.toArray(Iterator.scala:1157)
> at
> org.apache.spark.sql.catalyst.plans.QueryPlan.transformExpressionsUp(QueryPlan.scala:127)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8.applyOrElse(Analyzer.scala:341)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$$anonfun$apply$8.applyOrElse(Analyzer.scala:243)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$transformUp$1.apply(TreeNode.scala:286)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:51)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformUp(TreeNode.scala:285)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:243)
> at
> org.apache.spark.sql.catalyst.analysis.Analyzer$ResolveReferences$.apply(Analyzer.scala:242)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:61)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:59)
> at
> scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:111)
> at scala.collection.immutable.List.foldLeft(List.scala:84)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:59)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:51)
> at scala.collection.immutable.List.foreach(List.scala:318)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:51)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.analyzed$lzycompute(SQLContext.scala:903)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.analyzed(SQLContext.scala:903)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.assertAnalyzed(SQLContext.scala:901)
> at org.apache.spark.sql.DataFrame.<init>(DataFrame.scala:131)
> at org.apache.spark.sql.DataFrame$.apply(DataFrame.scala:51)
> at
> org.apache.spark.sql.sources.InsertIntoHadoopFsRelation.run(commands.scala:98)
> at
> org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult$lzycompute(commands.scala:57)
> at
> org.apache.spark.sql.execution.ExecutedCommand.sideEffectResult(commands.scala:57)
> at
> org.apache.spark.sql.execution.ExecutedCommand.doExecute(commands.scala:68)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
> at
> org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:88)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:148)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:87)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd$lzycompute(SQLContext.scala:920)
> at
> org.apache.spark.sql.SQLContext$QueryExecution.toRdd(SQLContext.scala:920)
> at org.apache.spark.sql.sources.ResolvedDataSource$.apply(ddl.scala:338)
> at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:144)
> at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:135)
> at
> org.apache.spark.sql.DataFrameWriter.parquet(DataFrameWriter.scala:281)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:231)
> at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:379)
> at py4j.Gateway.invoke(Gateway.java:259)
> at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:133)
> at py4j.commands.CallCommand.execute(CallCommand.java:79)
> at py4j.GatewayConnection.run(GatewayConnection.java:207)
> at java.lang.Thread.run(Thread.java:744)
> {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
