[
https://issues.apache.org/jira/browse/SPARK-7626?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Michael Armbrust updated SPARK-7626:
------------------------------------
Description:
We recently added a new column page_context to a hive table named "clicks",
partitioned by data_date. This leads to NPE being thrown on DataFrame created
on older partitions without this column populated. For example:
{code}
val hc = new HiveContext(sc)
val clk = hc.sql("select * from clicks where data_date=20150302")
clk.show()
{code}
throws the following error msg:
{code}
java.lang.RuntimeException: cannot find field page_context from
[0:log_format_number, .....]
at
org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.getStandardStructFieldRef(ObjectInspectorUtils.java:415)
at
org.apache.hadoop.hive.serde2.lazy.objectinspector.LazySimpleStructObjectInspector.getStructFieldRef(LazySimpleStructObjectInspector.java:173)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$12.apply(TableReader.scala:278)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$12.apply(TableReader.scala:277)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at
org.apache.spark.sql.hive.HadoopTableReader$.fillObject(TableReader.scala:277)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$4$$anonfun$9.apply(TableReader.scala:194)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$4$$anonfun$9.apply(TableReader.scala:188)
at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:634)
at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:634)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.rdd.UnionRDD.compute(UnionRDD.scala:87)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
{code}
was:
We recently added a new column page_context to a hive table named "clicks",
partitioned by data_date. This leads to NPE being thrown on DataFrame created
on older partitions without this column populated. For example:
val hc = new HiveContext(sc)
val clk = hc.sql("select * from clicks where data_date=20150302")
clk.show()
throws the following error msg:
java.lang.RuntimeException: cannot find field page_context from
[0:log_format_number, .....]
at
org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.getStandardStructFieldRef(ObjectInspectorUtils.java:415)
at
org.apache.hadoop.hive.serde2.lazy.objectinspector.LazySimpleStructObjectInspector.getStructFieldRef(LazySimpleStructObjectInspector.java:173)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$12.apply(TableReader.scala:278)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$12.apply(TableReader.scala:277)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
at scala.collection.AbstractTraversable.map(Traversable.scala:105)
at
org.apache.spark.sql.hive.HadoopTableReader$.fillObject(TableReader.scala:277)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$4$$anonfun$9.apply(TableReader.scala:194)
at
org.apache.spark.sql.hive.HadoopTableReader$$anonfun$4$$anonfun$9.apply(TableReader.scala:188)
at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:634)
at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:634)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.rdd.UnionRDD.compute(UnionRDD.scala:87)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
at org.apache.spark.scheduler.Task.run(Task.scala:64)
> Actions on DataFrame created from HIVE table with newly added column throw
> NPE
> -------------------------------------------------------------------------------
>
> Key: SPARK-7626
> URL: https://issues.apache.org/jira/browse/SPARK-7626
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.3.1
> Reporter: Zhiyang Guo
>
> We recently added a new column page_context to a hive table named "clicks",
> partitioned by data_date. This leads to NPE being thrown on DataFrame
> created on older partitions without this column populated. For example:
> {code}
> val hc = new HiveContext(sc)
> val clk = hc.sql("select * from clicks where data_date=20150302")
> clk.show()
> {code}
> throws the following error msg:
> {code}
> java.lang.RuntimeException: cannot find field page_context from
> [0:log_format_number, .....]
> at
> org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.getStandardStructFieldRef(ObjectInspectorUtils.java:415)
> at
> org.apache.hadoop.hive.serde2.lazy.objectinspector.LazySimpleStructObjectInspector.getStructFieldRef(LazySimpleStructObjectInspector.java:173)
> at
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$12.apply(TableReader.scala:278)
> at
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$12.apply(TableReader.scala:277)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
> at
> scala.collection.TraversableLike$class.map(TraversableLike.scala:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at
> org.apache.spark.sql.hive.HadoopTableReader$.fillObject(TableReader.scala:277)
> at
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$4$$anonfun$9.apply(TableReader.scala:194)
> at
> org.apache.spark.sql.hive.HadoopTableReader$$anonfun$4$$anonfun$9.apply(TableReader.scala:188)
> at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:634)
> at org.apache.spark.rdd.RDD$$anonfun$14.apply(RDD.scala:634)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
> at org.apache.spark.rdd.UnionRDD.compute(UnionRDD.scala:87)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
> at
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
> at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:61)
> at org.apache.spark.scheduler.Task.run(Task.scala:64)
> {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
