Generate case class from spark DataFrame/Dataset schema.

Schema2CaseClass.scala

/**
  * Generate Case class from DataFrame.schema
  *
  *  val df:DataFrame = ...
  *
  *  val s2cc = new Schema2CaseClass
  *  import s2cc.implicit._
  *
  *  println(s2cc.schemaToCaseClass(df.schema, "MyClass"))
  *
  */

import org.apache.spark.sql.types._

class Schema2CaseClass {
  type TypeConverter = (DataType) => String

  def schemaToCaseClass(schema:StructType, className:String)(implicit tc:TypeConverter):String = {
    def genField(s:StructField):String = {
      val f = tc(s.dataType)
      s match {
        case x if(x.nullable) => s"  ${s.name}:Option[$f]"
        case _ => s"  ${s.name}:$f"
      }
    }

    val fieldsStr = schema.map(genField).mkString(",\n  ")
    s"""
       |case class $className (
       |  $fieldsStr
       |)
  """.stripMargin
  }

  object implicits {
    implicit val defaultTypeConverter:TypeConverter = (t:DataType) => { t match {
      case _:ByteType => "Byte"
      case _:ShortType => "Short"
      case _:IntegerType => "Int"
      case _:LongType => "Long"
      case _:FloatType => "Float"
      case _:DoubleType => "Double"
      case _:DecimalType => "java.math.BigDecimal"
      case _:StringType => "String"
      case _:BinaryType => "Array[Byte]"
      case _:BooleanType => "Boolean"
      case _:TimestampType => "java.sql.Timestamp"
      case _:DateType => "java.sql.Date"
      case _:ArrayType => "scala.collection.Seq"
      case _:MapType => "scala.collection.Map"
      case _:StructType => "org.apache.spark.sql.Row"
      case _ => "String"
    }}
  }
}

/*we can use below code directly it will return string instead of writing into file we can get string in a variable */

import org.apache.spark.sql.types._

class SchemaToCaseClassWriter {
type TypeConverter = DataType => String

def write(schema: StructType, className: String): String = {
run(schema, className)
}

private def run(schema: StructType, className: String): String = {
def genField(field: StructField): String = {
val converter = defaultTypeConverter(field.name)
val dataType = converter(field.dataType)
field match {
case x if x.nullable => s" ${field.name}: Option[$dataType]"
case _ => s" ${field.name}: $dataType"
}
}

val fieldsStr = schema.map(genField).mkString(",\n  ")
val schemaClass =
  s"""case class $className (
     |  $fieldsStr
     |)
     |
     |""".stripMargin
schemaClass

}

private def defaultTypeConverter(colName: String): TypeConverter = {
val converter: TypeConverter = {
case _: ByteType => "Byte"
case _: ShortType => "Short"
case _: IntegerType => "Int"
case _: LongType => "Long"
case _: FloatType => "Float"
case _: DoubleType => "Double"
case _: DecimalType => "java.math.BigDecimal"
case _: StringType => "String"
case _: BinaryType => "Array[Byte]"
case _: BooleanType => "Boolean"
case _: TimestampType => "java.sql.Timestamp"
case _: DateType => "java.sql.Date"
case t: ArrayType =>
val e = t match {
case ArrayType(elementType, _) => elementType
}
s"Seq[${defaultTypeConverter(colName)(e)}]"
case _: MapType => "scala.collection.Map"
case t: StructType =>
run(t, colName.capitalize)
colName.capitalize
case _ => "String"
}
converter
}
}

val writer = new SchemaToCaseClassWriter()
val schema = // Your StructType schema
val className = "MyClass"
val caseClassString = writer.write(schema, className)
println(caseClassString) // Output the generated case class string