I tried using shapeless HLists as data storage for data inside spark.
Unsurprisingly, it failed. The deserialization isn't well-defined because of
all the implicits used by shapeless. How could I make it work?
Sample Code:
/* SimpleApp.scala */
import org.apache.spark.SparkContext
import org.apache.spark.SparkContext._
import org.apache.spark.SparkConf
import shapeless._
import ops.hlist._
object SimpleApp {
def main(args: Array[String]) {
val logFile = "/tmp/README.md" // Should be some file on your system
val conf = new SparkConf().setAppName("Simple Application")
val sc = new SparkContext(conf)
val logData = sc.textFile(logFile, 2).cache()
val numAs = logData
.map(line => line :: HNil)
.filter(_.select[String].contains("a"))
.count()
println("Lines with a: %s".format(numAs))
}
}
Error:
Exception in thread "main" java.lang.NoClassDefFoundError:
shapeless/$colon$colon
at SimpleApp$.main(SimpleApp.scala:15)
at SimpleApp.main(SimpleApp.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:606)
at org.apache.spark.deploy.SparkSubmit$.launch(SparkSubmit.scala:328)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:75)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
