-scala: map-reduce

CharactersCount.scala

object CharactersCount extends App {

  val src = fromFile(new File("/Users/akrasnyanskiy/IdeaProjects/spark-sql-example/src/main/resources/words.txt"))
  var mapped = src.map((_, 1))

  val combiner: (((Char, Int), (Char, Int)) => ((Char, Int))) = {
    case ((a, b), (c, d)) => ('_', b + d)
  }

  val wordsAmount = (mapped reduce combiner)._2

  println(wordsAmount)
  
}

Words Count on plain Scala

object WordsCount extends App {

  import java.io.File
  import scala.io.Source.fromFile

  type CombinerType = (((String, Int), (String, Int)) => ((String, Int)))

  val src = fromFile(new File("/Users/akrasnyanskiy/IdeaProjects/spark-sql-example/src/main/resources/words.txt"))
  var mapped = src getLines() flatMap { _.split(" ") } map { (_,1) }

  val combiner: CombinerType = {
    case ((a, b), (c, d)) => ("_", b + d)
  }

  val wordsAmount = mapped.reduce(combiner)._2
  println(wordsAmount)

}

import com.google.common.io.Files;

import java.io.File;
import java.io.IOException;
import java.nio.charset.Charset;
import java.util.List;

public class WordCounterImpl implements WordCounter {

    @Override
    public int count(File file) throws IOException {
        List<String> lines = Files.readLines(file, Charset.defaultCharset());
        int wordsAmount = 0;

        for (String line : lines) {
            String[] tokens = line.split(" ");
            wordsAmount += tokens.length;
        }

        return wordsAmount;
    }

}