[
https://issues.apache.org/jira/browse/SPARK-4709?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Felix Cheung updated SPARK-4709:
--------------------------------
Summary: Spark SQL support error reading Parquet with timestamp type field
(was: Spark SQL support for Parquet with timestamp type field)
> Spark SQL support error reading Parquet with timestamp type field
> -----------------------------------------------------------------
>
> Key: SPARK-4709
> URL: https://issues.apache.org/jira/browse/SPARK-4709
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.1.0
> Reporter: Felix Cheung
> Priority: Critical
>
> Have a data set on Parquet format (created by Hive) with a field of the
> timestamp type. Reading this causes an exception:
> val sqlContext = new org.apache.spark.sql.SQLContext(sc)
> val p = sqlContext.parquetFile("hdfs:///data/parquetdata")
> java.lang.RuntimeException: Potential loss of precision: cannot convert INT96
> at scala.sys.package$.error(package.scala:27)
> at
> org.apache.spark.sql.parquet.ParquetTypesConverter$.toPrimitiveDataType(ParquetTypes.scala:61)
> at
> org.apache.spark.sql.parquet.ParquetTypesConverter$.toDataType(ParquetTypes.scala:113)
> at
> org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$convertToAttributes$1.apply(ParquetTypes.scala:314)
> at
> org.apache.spark.sql.parquet.ParquetTypesConverter$$anonfun$convertToAttributes$1.apply(ParquetTypes.scala:311)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at
> scala.collection.TraversableLike$$anonfun$map$1.apply(TraversableLike.scala:244)
> at scala.collection.Iterator$class.foreach(Iterator.scala:727)
> at scala.collection.AbstractIterator.foreach(Iterator.scala:1157)
> 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:244)
> at scala.collection.AbstractTraversable.map(Traversable.scala:105)
> at
> org.apache.spark.sql.parquet.ParquetTypesConverter$.convertToAttributes(ParquetTypes.scala:310)
> at
> org.apache.spark.sql.parquet.ParquetTypesConverter$.readSchemaFromFile(ParquetTypes.scala:441)
> at
> org.apache.spark.sql.parquet.ParquetRelation.<init>(ParquetRelation.scala:66)
> at org.apache.spark.sql.SQLContext.parquetFile(SQLContext.scala:141)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:17)
> at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:22)
> at $iwC$$iwC$$iwC$$iwC.<init>(<console>:24)
> at $iwC$$iwC$$iwC.<init>(<console>:26)
> at $iwC$$iwC.<init>(<console>:28)
> at $iwC.<init>(<console>:30)
> at <init>(<console>:32)
> at .<init>(<console>:36)
> at .<clinit>(<console>)
> at .<init>(<console>:7)
> at .<clinit>(<console>)
> at $print(<console>)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at
> org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:846)
> at
> org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1119)
> at
> org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:672)
> at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:703)
> at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:667)
> at
> org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:819)
> at
> org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:864)
> at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:776)
> at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:619)
> at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:627)
> at org.apache.spark.repl.SparkILoop.loop(SparkILoop.scala:632)
> at
> org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply$mcZ$sp(SparkILoop.scala:959)
> at
> org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:907)
> at
> org.apache.spark.repl.SparkILoop$$anonfun$process$1.apply(SparkILoop.scala:907)
> at
> scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135)
> at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:907)
> at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1002)
> at org.apache.spark.repl.Main$.main(Main.scala:31)
> at org.apache.spark.repl.Main.main(Main.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:331)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:75)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
