Text processing/1: Difference between revisions

Added Scala
(use incorrect template parameters)
(Added Scala)
Line 1,189:
puts ""
puts "Maximum run(s) of #{max_invalid_count} consecutive false readings ends at #{invalid_run_end}"</lang>
 
=={{header|Scala}}==
=={{works with|Scala|2.8}}==
<lang scala>object DataMunging {
val pattern = """^(\d+-\d+-\d+)""" + """\s+(\d+\.\d+)\s+(-?\d+)""" * 24 + "$" r;
 
def spans[A](list: List[A]) = list.tail.foldLeft(List((list.head, 1))) {
case ((a, n) :: tail, b) if a == b => (a, n + 1) :: tail
case (l, b) => (b, 1) :: l
}
type Flag = ((Boolean, Int), String)
type Flags = List[Flag]
type LineIterator = Iterator[Option[(Double, Int, Flags)]]
def linesIterator(file: java.io.File) = Source.fromFile(file).getLines().map(
pattern findFirstMatchIn _ map (
_.subgroups match {
case List(date, rawData @ _*) =>
val dataset = (rawData map (_ toDouble) iterator) grouped 2 toList;
val valid = dataset filter (_.last > 0) map (_.head)
val validSize = valid length;
val validSum = valid sum;
val flags = spans(dataset map (_.last > 0)) map ((_, date))
println("Line: %11s Reject: %2d Accept: %2d Line_tot: %10.3f Line_avg: %10.3f" format
(date, 24 - validSize, validSize, validSum, validSum / validSize))
(validSum, validSize, flags)
}
)
)
def totalizeLines(fileIterator: LineIterator) =
fileIterator.foldLeft(0.0, 0, List[Flag]()) {
case ((totalSum, totalSize, ((flag, size), date) :: tail), Some((validSum, validSize, flags))) =>
val ((firstFlag, firstSize), _) = flags.last
if (firstFlag == flag) {
(totalSum + validSum, totalSize + validSize, flags.init ::: ((flag, size + firstSize), date) :: tail)
} else {
(totalSum + validSum, totalSize + validSize, flags ::: ((flag, size), date) :: tail)
}
case ((_, _, Nil), Some(partials)) => partials
case (totals, None) => totals
}
def main(args: Array[String]) {
val filenames = args map (new java.io.File(_)) filter (file => file.isFile && file.canRead)
val lines = filenames.iterator flatMap linesIterator
val (totalSum, totalSize, flags) = totalizeLines(lines)
val ((_, run), startDate) = flags.filter(!_._1._1).max
val report = """|
|File(s) = %s
|Total = %10.3f
|Readings = %6d
|Average = %10.3f
|
|Maximum run(s) of %d consecutive false readings ends at line starting %s""".stripMargin
println(report format (filenames mkString " ", totalSum, totalSize, totalSum / totalSize, run, startDate))
}
}</lang>
 
Last few lines of the sample output:
 
<pre>
Line: 2004-12-29 Reject: 1 Accept: 23 Line_tot: 56.300 Line_avg: 2.448
Line: 2004-12-30 Reject: 1 Accept: 23 Line_tot: 65.300 Line_avg: 2.839
Line: 2004-12-31 Reject: 1 Accept: 23 Line_tot: 47.300 Line_avg: 2.057
 
File(s) = readings.txt
Total = 1358393.400
Readings = 129403
Average = 10.497
</pre>
 
=={{header|Tcl}}==
Anonymous user