KvKDataset.scala

import spark.implicits._

val kvKDataset = spark.read.option("header", true).option("sep", ";").option("ignoreLeadingWhiteSpace", true).option("ignoreTrailingWhiteSpace", true).option("quote", """"""").option("nullValue", "").option("mode", "FAILFAST").csv(path)

kvKDataset.select(
        'DOSSIERNR.as("dossierNummer"),
        'VG_NR.as("vgNummer"),
        'HANDELSN30.as("naamShort"),
        'HANDN1_30.as("naamShortP1"),
        'HANDN2_30.as("naamShortP2"),
        'HANDELSN45.as("naamLong"),
        'ADRES_VA.as("adresV"),
        'PCPLAATSVA.as("postcodePlaatsV"),
        'ADRES_CA.as("adresC"),
        'PCPLAATSCA.as("postcodePlaatsC"),
        'WPFT.as("wptf").cast(IntegerType),
        'SBI.as("sbi").cast(IntegerType)
      )
      .as[KvKRecord]