Hi, I am getting the error "*java.lang.SecurityException: sealing violation: can't seal package org.apache.derby.impl.services.locks: already loaded"* after running the following code in SCALA.
I do not have any other instances of sparkContext running from my system. I will be grateful for if anyone could kindly help me out. Environment: SCALA: 1.6 OS: MAC OS X ------------ import org.apache.spark.SparkContext import org.apache.spark.SparkConf import org.apache.spark.sql.Row import org.apache.spark.sql.hive.HiveContext import org.apache.spark.sql.types._ import org.apache.spark.sql.SQLContext // Import SuccinctRDD import edu.berkeley.cs.succinct._ object test1 { def main(args: Array[String]) { //the below line returns nothing println(SparkContext.jarOfClass(this.getClass).toString()) val logFile = "/tmp/README.md" // Should be some file on your system val conf = new SparkConf().setAppName("IdeaProjects").setMaster("local[*]") val sc = new SparkContext(conf) val logData = sc.textFile(logFile, 2).cache() val numAs = logData.filter(line => line.contains("a")).count() val numBs = logData.filter(line => line.contains("b")).count() println("Lines with a: %s, Lines with b: %s".format(numAs, numBs)) // Create a Spark RDD as a collection of articles; ctx is the SparkContext val articlesRDD = sc.textFile("/tmp/README.md").map(_.getBytes) // Compress the Spark RDD into a Succinct Spark RDD, and persist it in memory // Note that this is a time consuming step (usually at 8GB/hour/core) since data needs to be compressed. // We are actively working on making this step faster. val succinctRDD = articlesRDD.succinct.persist() // SuccinctRDD supports a set of powerful primitives directly on compressed RDD // Let us start by counting the number of occurrences of "Berkeley" across all Wikipedia articles val count = succinctRDD.count("the") // Now suppose we want to find all offsets in the collection at which ìBerkeleyî occurs; and // create an RDD containing all resulting offsets val offsetsRDD = succinctRDD.search("and") // Let us look at the first ten results in the above RDD val offsets = offsetsRDD.take(10) // Finally, let us extract 20 bytes before and after one of the occurrences of ìBerkeleyî val offset = offsets(0) val data = succinctRDD.extract(offset - 20, 40) println(data) println(">>>") // Create a schema val citySchema = StructType(Seq( StructField("Name", StringType, false), StructField("Length", IntegerType, true), StructField("Area", DoubleType, false), StructField("Airport", BooleanType, true))) // Create an RDD of Rows with some data val cityRDD = sc.parallelize(Seq( Row("San Francisco", 12, 44.52, true), Row("Palo Alto", 12, 22.33, false), Row("Munich", 8, 3.14, true))) val hiveContext = new HiveContext(sc) //val sqlContext = new org.apache.spark.sql.SQLContext(sc) } } ------------- Regards, Gourav Sengupta