import com.datastax.spark.connector.cql.CassandraConnector
import org.apache.spark.{SparkContext, SparkConf}
import org.apache.spark.sql.{Row, SQLContext}

/** Spark SQL: Txt, Parquet, JSON Support with the Spark Cassandra Connector */
object SampleJson extends App {
  import com.datastax.spark.connector._
  import GitHubEvents._

  val conf = new SparkConf(true)
   /** .set("spark.cassandra.connection.host", "127.0.0.1") */
   /** .setMaster("local[*]") */
    .setAppName("app2")

  val sc = new SparkContext(conf)
  val sqlContext = new org.apache.spark.sql.SQLContext(sc)
  val json = sc.parallelize(Seq("""{"user":"helena","commits":98, "month":12, "year":2014}""","""{"user":"pkolaczk", "commits":42, "month":12, "year":2014}"""))

  sqlContext.jsonRDD(json).map(MonthlyCommits(_)).saveToCassandra("githubstats","monthly_commits")

  sc.cassandraTable[MonthlyCommits]("githubstats","monthly_commits").collect foreach println

  sc.stop()
}

object GitHubEvents {

  sealed trait Stat extends Serializable
  trait User extends Stat
  trait Repo extends Stat
  trait Commits extends Stat
  case class MonthlyCommits(user: String, commits: Int, month: Int, year: Int) extends Commits
  object MonthlyCommits {
    def apply(r: Row): MonthlyCommits = MonthlyCommits(
      r.getString(0), r.getInt(1), r.getInt(2), r.getInt(3))
  }
}