Created
December 12, 2017 17:35
-
-
Save arpadtamasi/c51df064378b1e4f3c417e46c9212aac to your computer and use it in GitHub Desktop.
Spark schema nullability modifier
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
object DataFrameHelpers { | |
import org.apache.spark.sql.types._ | |
implicit class NullableDataFrame(df: DataFrame) { | |
def setNullableStateOfColumns( nullable: Boolean, containsNull: Boolean, cn: String*) : DataFrame = { | |
// get schema | |
val names = cn.toSet | |
val schema = df.schema | |
// modify [[StructField] with name `cn` | |
val newSchema = schemaWithNullableStates(schema, nullable, containsNull, names) | |
// apply new schema | |
df.sqlContext.createDataFrame( df.rdd, newSchema ) | |
} | |
private def schemaWithNullableStates(schema: StructType, nullable: Boolean, containsNull: Boolean, names: Set[String]): StructType = | |
StructType(schema.map { | |
case StructField( name, dataType: ArrayType, _, metadata) if names.exists(_.startsWith(s"$name.")) && dataType.elementType.isInstanceOf[StructType] => | |
val innerColumns = names collect { | |
case n if n.startsWith(s"$name.") => n.drop(name.length + 1) | |
} | |
val newArrayType = ArrayType( | |
schemaWithNullableStates(dataType.elementType.asInstanceOf[StructType], nullable, containsNull, innerColumns), | |
dataType.containsNull | |
) | |
StructField( name, newArrayType, nullable = nullable, metadata) | |
case StructField(name, dataType: StructType, nullability, metadata) if names.exists(_.startsWith(s"$name.")) => | |
val innerColumns = names collect { | |
case n if n.startsWith(s"$name.") => n.drop(name.length + 1) | |
} | |
StructField( name, schemaWithNullableStates(dataType, nullable, containsNull, innerColumns), nullability, metadata) | |
case StructField( name, dataType: ArrayType, _, metadata) if names.contains(name) => | |
StructField( name, dataType.copy(containsNull = containsNull), nullable = nullable, metadata) | |
case StructField( name, dataType, _, metadata) if names.contains(name) => | |
StructField( name, dataType, nullable = nullable, metadata) | |
case y: StructField => y | |
}) | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment