Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: UNIC-705 add HashTransformation traits #232

Merged
merged 1 commit into from
Jul 15, 2024
Merged

feat: UNIC-705 add HashTransformation traits #232

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 7 additions & 2 deletions ...-spark3/src/main/scala/bio/ferlab/datalake/spark3/transformation/HashTransformation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,15 @@
package bio.ferlab.datalake.spark3.transformation

import org.apache.spark.sql.Column
import org.apache.spark.sql.{Column, DataFrame}
import org.apache.spark.sql.functions.lit
import org.apache.spark.sql.types.StringType

trait HashTransformation[A] extends Transformation {self =>
sealed trait HashTransformation[A] extends Transformation {self =>
val columns: A
val nullValues: Column = lit(null).cast(StringType)
}

object HashTransformation {
trait SimpleHashTransformation extends HashTransformation[Seq[String]]
trait DynamicHashTransformation extends HashTransformation[DataFrame => Seq[String]]
}
3 changes: 2 additions & 1 deletion datalake-spark3/src/main/scala/bio/ferlab/datalake/spark3/transformation/PBKDF2.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
package bio.ferlab.datalake.spark3.transformation

import bio.ferlab.datalake.spark3.transformation.HashTransformation.SimpleHashTransformation
import bio.ferlab.datalake.spark3.transformation.PBKDF2.pbkdf2Udf
import com.roundeights.hasher.Implicits._
import org.apache.spark.sql._
Expand All @@ -17,7 +18,7 @@ import scala.language.postfixOps
* @param keyLength length of the resulting hash
* @param columns names of the columns to hash
*/
case class PBKDF2(salt: String, iteration: Int, keyLength: Int, override val columns: String*) extends HashTransformation[Seq[String]] {
case class PBKDF2(salt: String, iteration: Int, keyLength: Int, override val columns: String*) extends SimpleHashTransformation {

override def transform: DataFrame => DataFrame = { df =>

Expand Down
3 changes: 2 additions & 1 deletion datalake-spark3/src/main/scala/bio/ferlab/datalake/spark3/transformation/SHA1.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
package bio.ferlab.datalake.spark3.transformation

import bio.ferlab.datalake.spark3.transformation.HashTransformation.SimpleHashTransformation
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.StringType

case class SHA1(salt: String, override val columns: String*) extends HashTransformation[Seq[String]] {
case class SHA1(salt: String, override val columns: String*) extends SimpleHashTransformation {
override def transform: DataFrame => DataFrame = { df =>
columns.foldLeft(df){ case (d, column) =>
d.withColumn(column,
Expand Down
3 changes: 2 additions & 1 deletion datalake-spark3/src/main/scala/bio/ferlab/datalake/spark3/transformation/SHA1Dynamic.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
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 HashTransformation[DataFrame => Seq[String]] {
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) =>
Expand Down
3 changes: 2 additions & 1 deletion datalake-spark3/src/main/scala/bio/ferlab/datalake/spark3/transformation/SHA256.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,10 +1,11 @@
package bio.ferlab.datalake.spark3.transformation

import bio.ferlab.datalake.spark3.transformation.HashTransformation.SimpleHashTransformation
import org.apache.spark.sql.DataFrame
import org.apache.spark.sql.functions._
import org.apache.spark.sql.types.StringType

case class SHA256(salt: String, override val columns: String*) extends HashTransformation[Seq[String]] {
case class SHA256(salt: String, override val columns: String*) extends SimpleHashTransformation {
override def transform: DataFrame => DataFrame = { df =>
columns.foldLeft(df){ case (d, column) =>
d.withColumn(column,
Expand Down
Loading