Last Updated: February 25, 2016
·
1.88K
· fxzo

CsvReactiveIteratee - Scala and Play2

The following case class allow a Play2 controller to process a big CSV File upload reactively without putting the whole file in memory.
The function used to process each line is passed as a parameter.
My code is inspired by the following post : http://stackoverflow.com/questions/11941102/play-2-scala-best-way-to-upload-a-big-csv-file-with-iteratee-in-order-to-proce

package intech.api

import play.api.mvc._
import play.api.libs.iteratee.{Iteratee, Input}
import play.api.libs.concurrent.Promise
import play.api.libs.iteratee.Input.{El, EOF, Empty}
import au.com.bytecode.opencsv.CSVReader
import java.io.StringReader
import scala.collection.JavaConversions._

case class CsvReactiveIteratee(f: Array[String] => Int, state: Symbol = 'Cont, input: Input[Array[Byte]] = Empty, lastChunk: String = "", lineProcessed: Int = 0, isFirst: Boolean = false) extends Iteratee[Array[Byte], Either[Result, Int]] {
  def fold[B](
               done: (Either[Result, Int], Input[Array[Byte]]) => Promise[B],
               cont: (Input[Array[Byte]] => Iteratee[Array[Byte], Either[Result, Int]]) => Promise[B],
               error: (String, Input[Array[Byte]]) => Promise[B]
           ): Promise[B] = state match {
    case 'Done =>
      done(Right(lineProcessed), Input.Empty)

case 'Cont => cont(in => in match {
      case in: El[Array[Byte]] => {
        // Retrieve the part that has not been processed in the previous chunk and copy it in front of the current chunk
        val content = lastChunk + new String(in.e)
    val csvBody =
          if (isFirst)
      // Skip http header if it is the first chunk
            content.drop(content.indexOf("\r\n\r\n") + 4)
          else content
        val csv = new CSVReader(new StringReader(csvBody), ';')
        val lines = csv.readAll
        // Process all lines excepted the last one since it is cut by the chunk
        var nbLine = 0
        for (line <- lines.init)
          nbLine += f(line)

    // Put forward the part that has not been processed
        val last = lines.last.toList.mkString(";")
        copy(input = in, lastChunk = last, lineProcessed = lineProcessed + nbLine, isFirst = false)
      }
      case Empty => copy(input = in, lineProcessed = lineProcessed, isFirst = false)
      case EOF => copy(state = 'Done, input = in, lineProcessed = lineProcessed, isFirst = false)
      case _ => copy(state = 'Error, input = in, lineProcessed = lineProcessed, isFirst = false)
    })

    case _ =>
      error("Unexpected state", input)

  }
}

The following controller uses the class to send a new json structure to elasticsearch for each line :

def upload = Action(BodyParser(rh => new CsvReactiveIteratee(f = processNALine, isFirst = true))) {
  request =>
    Ok("File Processed\n Nb lines processed : " + request.body)
}

def processNALine(line: Array[String]): Int =
  if (line.size == 4) {
    WS.url("http://localhost:9200/affa/na/").post(
      toJson(
        Map(
          "date" -> toJson(line(0)),
          "trig" -> toJson(line(1)),
          "code" -> toJson(line(2)),
          "nbs" -> toJson(line(3).toDouble)
        )
      )
    )
    1
  } else 0