set up Spark
shell
$ cd /usr/local/Cellar
$ git clone git@github.com:apache/spark.git
$ cd spark
$ sbt/sbt assembly
$ sbt/sbt publish-local
configure SPARK_HOME
shell
$ vi ~/.xxxrc
export SPARK_HOME=/usr/local/Cellar/spark
spark-shell
shell
$ cd $SPARK_HOME
$ ./bin/spark-shell
build
shell
$ git clone git@github.com:databricks/learning-spark.git
$ cd learning-spark
$ sbt/sbt compile
run
shell
$ sbt/sbt run
Multiple main classes detected, select one to run:
shell
$ sbt/sbt 'run-main com.oreilly.learningsparkexamples.scala.BasicAvgFromFile local[4] inputfile'
shell
$ sbt/sbt assembly
$ cp target/scala-2.10/learning-spark-examples-assembly-0.0.1.jar ~/.
$ cd ~
$ CLASSPATH=./learning-spark-examples-assembly-0.0.1.jar
$ java -cp $CLASSPATH com.oreilly.learningsparkexamples.scala.BasicAvgFromFile local[4] inputfile