You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Jordan Thomas (JIRA)" <ji...@apache.org> on 2015/08/19 16:16:46 UTC
[jira] [Created] (SPARK-10113) Support for unsigned Parquet logical
types
Jordan Thomas created SPARK-10113:
-------------------------------------
Summary: Support for unsigned Parquet logical types
Key: SPARK-10113
URL: https://issues.apache.org/jira/browse/SPARK-10113
Project: Spark
Issue Type: Improvement
Components: SQL
Affects Versions: 1.5.0
Reporter: Jordan Thomas
Add support for unsigned Parquet logical types UINT_16, UINT_32 and UINT_64.
{code}
org.apache.spark.sql.AnalysisException: Illegal Parquet type: INT64 (UINT_64);
at org.apache.spark.sql.parquet.CatalystSchemaConverter.illegalType$1(CatalystSchemaConverter.scala:130)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertPrimitiveField(CatalystSchemaConverter.scala:169)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:115)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:97)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:94)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.Iterator$class.foreach(Iterator.scala:742)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.org$apache$spark$sql$parquet$CatalystSchemaConverter$$convert(CatalystSchemaConverter.scala:94)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$convertGroupField$1.apply(CatalystSchemaConverter.scala:200)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$convertGroupField$1.apply(CatalystSchemaConverter.scala:200)
at scala.Option.fold(Option.scala:158)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertGroupField(CatalystSchemaConverter.scala:200)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:116)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:97)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:94)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.Iterator$class.foreach(Iterator.scala:742)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.org$apache$spark$sql$parquet$CatalystSchemaConverter$$convert(CatalystSchemaConverter.scala:94)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:91)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$readSchemaFromFooter$2.apply(ParquetRelation.scala:734)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$readSchemaFromFooter$2.apply(ParquetRelation.scala:734)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.parquet.ParquetRelation$.readSchemaFromFooter(ParquetRelation.scala:734)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28$$anonfun$apply$8.apply(ParquetRelation.scala:714)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28$$anonfun$apply$8.apply(ParquetRelation.scala:713)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.Iterator$class.foreach(Iterator.scala:742)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28.apply(ParquetRelation.scala:713)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28.apply(ParquetRelation.scala:692)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
15/08/19 07:10:26 WARN TaskSetManager: Lost task 1.0 in stage 0.0 (TID 1, localhost): org.apache.spark.sql.AnalysisException: Illegal Parquet type: INT64 (UINT_64);
at org.apache.spark.sql.parquet.CatalystSchemaConverter.illegalType$1(CatalystSchemaConverter.scala:130)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertPrimitiveField(CatalystSchemaConverter.scala:169)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:115)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:97)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:94)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.Iterator$class.foreach(Iterator.scala:742)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.org$apache$spark$sql$parquet$CatalystSchemaConverter$$convert(CatalystSchemaConverter.scala:94)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$convertGroupField$1.apply(CatalystSchemaConverter.scala:200)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$convertGroupField$1.apply(CatalystSchemaConverter.scala:200)
at scala.Option.fold(Option.scala:158)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertGroupField(CatalystSchemaConverter.scala:200)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convertField(CatalystSchemaConverter.scala:116)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:97)
at org.apache.spark.sql.parquet.CatalystSchemaConverter$$anonfun$2.apply(CatalystSchemaConverter.scala:94)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.Iterator$class.foreach(Iterator.scala:742)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.org$apache$spark$sql$parquet$CatalystSchemaConverter$$convert(CatalystSchemaConverter.scala:94)
at org.apache.spark.sql.parquet.CatalystSchemaConverter.convert(CatalystSchemaConverter.scala:91)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$readSchemaFromFooter$2.apply(ParquetRelation.scala:734)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$readSchemaFromFooter$2.apply(ParquetRelation.scala:734)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.sql.parquet.ParquetRelation$.readSchemaFromFooter(ParquetRelation.scala:734)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28$$anonfun$apply$8.apply(ParquetRelation.scala:714)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28$$anonfun$apply$8.apply(ParquetRelation.scala:713)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:245)
at scala.collection.Iterator$class.foreach(Iterator.scala:742)
at scala.collection.AbstractIterator.foreach(Iterator.scala:1194)
at scala.collection.IterableLike$class.foreach(IterableLike.scala:72)
at scala.collection.AbstractIterable.foreach(Iterable.scala:54)
at scala.collection.TraversableLike$class.map(TraversableLike.scala:245)
at scala.collection.AbstractTraversable.map(Traversable.scala:104)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28.apply(ParquetRelation.scala:713)
at org.apache.spark.sql.parquet.ParquetRelation$$anonfun$28.apply(ParquetRelation.scala:692)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:264)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66)
at org.apache.spark.scheduler.Task.run(Task.scala:88)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
{code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org