scala> // Step 1
scala> val inputList = List( "data=first data || key1=r1v1 || key2=",
| "data=second data || key1=r2v1 || key2=r2v2",
| "key1=r3v1"
| )
inputList: List[String] = List(data=first data || key1=r1v1 || key2=, data=second data || key1=r2v1 || key2=r2v2, key1=r3v1)
scala> // Step 2
scala> val splitted = inputList.map{ x =>
| x.split("\\|\\|")
| .map(_.trim)
| }
splitted: List[Array[String]] = List(Array(data=first data, key1=r1v1, key2=), Array(data=second data, key1=r2v1, key2=r2v2), Array(key1=r3v1))
scala> // Step 3
scala> val filteredList = splitted.map{ x =>
| val retval = for { element <- x
| val keyNval = element.split("=")
| if keyNval.size >= 2
| } yield {
| val splitted = element.split("=")
| // Create Tuple of Key and Value
| splitted(0) -> splitted(1)
| }
| retval
| }
warning: there were 1 deprecation warning(s); re-run with -deprecation for details
filteredList: List[Array[(String, String)]] = List(Array((data,first data), (key1,r1v1)), Array((data,second data), (key1,r2v1), (key2,r2v2)), Array((key1,r3v1)))
scala> // Step 4
scala> val dnryList = filteredList.map{ x =>
| x.toMap
| }
dnryList: List[scala.collection.immutable.Map[String,String]] = List(Map(data -> first data, key1 -> r1v1), Map(data -> second data, key1 -> r2v1, key2 -> r2v2), Map(key1 -> r3v1))
scala> // Step 5
scala> val filteredDnryList = dnryList.filter{ x =>
| if (x.getOrElse("data", ()) != ())
| true
| else
| false
| }
filteredDnryList: List[scala.collection.immutable.Map[String,String]] = List(Map(data -> first data, key1 -> r1v1), Map(data -> second data, key1 -> r2v1, key2 -> r2v2))
scala> // Step 6
scala> val keyvaluepairs = filteredDnryList.map { x =>
| val data = x.getOrElse("data", "")
| (data, x)
| }
keyvaluepairs: List[(String, scala.collection.immutable.Map[String,String])] = List((first data,Map(data -> first data, key1 -> r1v1)), (second data,Map(data -> second data, key1 -> r2v1, key2 -> r2v2)))
scala> // Step 7
scala> val words = keyvaluepairs.flatMap{ x =>
| //Underscore (_) is used as a Placeholder indicator
| val xsplitted = x._1.split(" ").map(_.trim)
| val wordNmeta = for { element <- xsplitted
| } yield {
| (element, x._2)
| }
| wordNmeta
| }
words: List[(String, scala.collection.immutable.Map[String,String])] = List((first,Map(data -> first data, key1 -> r1v1)), (data,Map(data -> first data, key1 -> r1v1)), (second,Map(data -> second data, key1 -> r2v1, key2 -> r2v2)), (data,Map(data -> second data, key1 -> r2v1, key2 -> r2v2)))
c200 > a15Data Conversion using : Map, for/yield etc...
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment