bio.ferlab.datalake.spark3.transformation.SHA1Dynamic.scala Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of datalake-spark3_2.12 Show documentation

Library built on top of Apache Spark to speed-up data lakes development..

There is a newer version: 14.8.0

package bio.ferlab.datalake.spark3.transformation

import bio.ferlab.datalake.spark3.transformation.HashTransformation.DynamicHashTransformation
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.functions.{col, concat_ws, lit, sha1, when}
import org.apache.spark.sql.types.StringType

case class SHA1Dynamic(salt: String, override val columns: DataFrame => Seq[String]) extends DynamicHashTransformation {

  override def transform: DataFrame => DataFrame = { df =>
    columns(df).foldLeft(df){ case (d, column) =>
      d.withColumn(column,
        when(col(column).isNull, nullValues)
          .otherwise(
            if(salt.nonEmpty) sha1(concat_ws("_", col(column).cast(StringType), lit(salt)))
            else sha1(col(column).cast(StringType))
          ))
    }
  }
}