test

import spark.implicits._
import org.apache.spark.sql.types._

val logDF = spark.read.textFile("/sparkdata/logcat/test.txt").map(
		_.replace('-', ' ').replace(':', ' ').trim.split("\\s+", 10)).map{
			case Array(mm, dd, hr, mn, sc, pid, tid, priority, tag, message) =>
			(mm, dd, hr, mn, sc, pid, tid, priority, tag, message)
		}.toDF(
		"mm", "dd", "hr", "mn", "sc", "pid", "tid", "priority", "tag", "message")

case class logParse(mm:String, dd:String, hr:String, mn:String, sc:String,
 pid:String, tid:String, priority:String, tag:String, message:String)

val logDS = logDF.as[logParse]

logDS.printSchema()