ganeshchand

/**
  * Author: github.com/ganeshchand
  * Date: 03/04/2021
  * Specifying schema when reading different source format is mandatory or optional depending on which DataFrameReader you are using.
  * spark.read() is a batch DataFrame reader
  * spark.readStream() is a streaming DataFrame reader
  * Let's write a quick test to test which reader enforces us to specify schema on read
  */

// step1: Let's generate test dataset for csv, json, parquet, orc and delta

marmbrus

import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.hadoop.conf.Configuration 

  case class S3File(path: String, isDir: Boolean, size: Long) {
    def children = listFiles(path)
  }

  def listFiles(path: String): Seq[S3File] = {
    val fs = FileSystem.get(new java.net.URI(path), new Configuration())
    fs.listStatus(new Path(path)).map(s => S3File(s.getPath.toString, s.isDir, s.getLen))

lihaoyi

object ScalaJSExample extends js.JSApp{
  def main() = {
    val xs = Seq(1, 2, 3)
    println(xs.toString)
    val ys = Seq(4, 5, 6)
    println(ys.toString)
    val zs = for{
      x <- xs
      y <- ys
    } yield x * y

mariussoutier

package object mail {

  implicit def stringToSeq(single: String): Seq[String] = Seq(single)
  implicit def liftToOption[T](t: T): Option[T] = Some(t)

  sealed abstract class MailType
  case object Plain extends MailType
  case object Rich extends MailType
  case object MultiPart extends MailType

kencoba

abstract class Product

abstract class PizzaBuilder {
  var dough: String
  var sauce: String
  var topping: String

  def withDough(dough: String): PizzaBuilder
  def withSauce(sauce: String): PizzaBuilder
  def withTopping(topping: String): PizzaBuilder