Skip to content

Add support for Spark 4 - needs spark-commons released. #123

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

Draft
yruslan wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Add support for Spark 4 - needs spark-commons released. #123

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
4 changes: 2 additions & 2 deletions build.sbt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,10 +21,10 @@ ThisBuild / name := "spark-data-standardization"
ThisBuild / organization := "za.co.absa"

lazy val scala212 = "2.12.20"
lazy val scala213 = "2.13.16"
lazy val scala213 = "2.13.17"

ThisBuild / crossScalaVersions := Seq(scala212, scala213)
ThisBuild / scalaVersion := scala212
ThisBuild / scalaVersion := scala213

ThisBuild / versionScheme := Some("early-semver")

Expand Down
8 changes: 6 additions & 2 deletions project/Dependencies.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,15 +25,19 @@ object Dependencies {

private def sparkFastTestsVersion(scalaVersion: String): String = "1.1.0"

def getSparkVersion(scalaVersion: String): String = "3.5.7"
def getSparkVersion(scalaVersion: String): String = if (scalaVersion.startsWith("2.12"))
"3.5.7"
else
"4.1.2"


def dependencyList(scalaVersion: String): Seq[ModuleID] = {
val sparkVersion = getSparkVersion(scalaVersion)
val sparkVersionUpToMinor = getSparkVersionUpToMinor(sparkVersion)
List(
"org.apache.spark" %% "spark-core" % sparkVersion % Provided,
"org.apache.spark" %% "spark-sql" % sparkVersion % Provided,
"za.co.absa" %% s"spark-commons-spark$sparkVersionUpToMinor" % "0.6.3" % Provided,
"za.co.absa" %% s"spark-commons-spark$sparkVersionUpToMinor" % "0.6.4-SNAPSHOT" % Provided,
"za.co.absa" %% "spark-commons-test" % "0.6.3" % Test,
"com.typesafe" % "config" % "1.4.2",
"com.github.mrpowers" %% "spark-fast-tests" % sparkFastTestsVersion(scalaVersion) % Test,
Expand Down
5 changes: 2 additions & 3 deletions src/main/scala/za/co/absa/standardization/stages/TypeParser.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@ import za.co.absa.spark.commons.implicits.ColumnImplicits.ColumnEnhancements
import za.co.absa.spark.commons.implicits.StructFieldImplicits.StructFieldMetadataEnhancements
import za.co.absa.spark.commons.implicits.StructTypeImplicits.StructTypeEnhancements
import za.co.absa.spark.commons.utils.SchemaUtils
import za.co.absa.spark.hofs.transform
import za.co.absa.standardization.config.StandardizationConfig
import za.co.absa.standardization.implicits.StdColumnImplicits.StdColumnEnhancements
import za.co.absa.standardization.schema.StdSchemaUtils.FieldWithSource
Expand Down Expand Up @@ -214,9 +213,9 @@ object TypeParser {
val finalErrs = when(nullErrCond,
array(typedLit(StandardizationErrorMessage.stdNullErr(inputFullPathName)(stdConfig.errorCodes))))
.otherwise(
typedLit(flatten(transform(column, lambdaErrCols, lambdaVariableName)))
typedLit(flatten(transform(column, lambdaErrCols)))

@yruslan yruslan Sep 14, 2026

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Spark 3+ supports higher level array functions, so spark-hofs is no longer needed, and we can use Spark's functions here. It does not take lambda variable names as an argument

)
val stdCols = transform(column, lambdaStdCols, lambdaVariableName)
val stdCols = transform(column, lambdaStdCols)
logger.info(s"Finished standardization plan for Array $inputFullPathName")
ParseOutput(stdCols as (fieldOutputName, metadata), finalErrs)
}
Expand Down
33 changes: 17 additions & 16 deletions src/test/scala/za/co/absa/standardization/interpreter/stages/TypeParserSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,10 +19,11 @@ package za.co.absa.standardization.interpreter.stages
import org.apache.spark.sql.types._
import org.scalatest.funsuite.AnyFunSuite
import za.co.absa.spark.commons.test.SparkTestBase
import za.co.absa.spark.commons.utils.ColUtils
import za.co.absa.standardization.RecordIdGeneration.IdType.NoId
import za.co.absa.standardization.config.{BasicMetadataColumnsConfig, BasicStandardizationConfig, StandardizationConfig}
import za.co.absa.standardization.config.{BasicMetadataColumnsConfig, BasicStandardizationConfig}
import za.co.absa.standardization.stages.TypeParser
import za.co.absa.standardization.types.{TypeDefaults, CommonTypeDefaults}
import za.co.absa.standardization.types.{CommonTypeDefaults, TypeDefaults}
import za.co.absa.standardization.udf.UDFLibrary

class TypeParserSuite extends AnyFunSuite with SparkTestBase {
Expand All @@ -44,21 +45,21 @@ class TypeParserSuite extends AnyFunSuite with SparkTestBase {
val schema = StructType(Array(structFieldNoMetadata, structFieldWithMetadataNotSourceColumn, structFieldWithMetadataSourceColumn))
//Just Testing field name override
val parseOutputStructFieldNoMetadata = TypeParser.standardize(structFieldNoMetadata, "path", schema, stdConfig)
assertResult(true)(parseOutputStructFieldNoMetadata.stdCol.expr.toString().contains("path.a"))
assertResult(false)(parseOutputStructFieldNoMetadata.stdCol.expr.toString().replaceAll("path.a", "").contains("path"))
assertResult(true)(parseOutputStructFieldNoMetadata.errors.expr.toString().contains("path.a"))
assertResult(false)(parseOutputStructFieldNoMetadata.errors.expr.toString().replaceAll("path.a", "").contains("path"))
assertResult(true)(ColUtils.col2Expr(parseOutputStructFieldNoMetadata.stdCol).toString().contains("path.a"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldNoMetadata.stdCol).toString().replaceAll("path.a", "").contains("path"))
assertResult(true)(ColUtils.col2Expr(parseOutputStructFieldNoMetadata.errors).toString().contains("path.a"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldNoMetadata.errors).toString().replaceAll("path.a", "").contains("path"))
val parseOutputStructFieldWithMetadataNotSourceColumn = TypeParser.standardize(structFieldWithMetadataNotSourceColumn, "path", schema, stdConfig)
assertResult(true)(parseOutputStructFieldWithMetadataNotSourceColumn.stdCol.expr.toString().contains("path.b"))
assertResult(false)(parseOutputStructFieldWithMetadataNotSourceColumn.stdCol.expr.toString().replaceAll("path.b", "").contains("path"))
assertResult(true)(parseOutputStructFieldWithMetadataNotSourceColumn.errors.expr.toString().contains("path.b"))
assertResult(false)(parseOutputStructFieldWithMetadataNotSourceColumn.errors.expr.toString().replaceAll("path.b", "").contains("path"))
assertResult(true)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataNotSourceColumn.stdCol).toString().contains("path.b"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataNotSourceColumn.stdCol).toString().replaceAll("path.b", "").contains("path"))
assertResult(true)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataNotSourceColumn.errors).toString().contains("path.b"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataNotSourceColumn.errors).toString().replaceAll("path.b", "").contains("path"))
val parseOutputStructFieldWithMetadataSourceColumn = TypeParser.standardize(structFieldWithMetadataSourceColumn, "path", schema, stdConfig)
assertResult(false)(parseOutputStructFieldWithMetadataSourceColumn.stdCol.expr.toString().contains("path.c"))
assertResult(true)(parseOutputStructFieldWithMetadataSourceColumn.stdCol.expr.toString().contains("path.override_c"))
assertResult(false)(parseOutputStructFieldWithMetadataSourceColumn.stdCol.expr.toString().replaceAll("path.override_c", "").contains("path"))
assertResult(false)(parseOutputStructFieldWithMetadataSourceColumn.errors.expr.toString().contains("path.c"))
assertResult(true)(parseOutputStructFieldWithMetadataSourceColumn.errors.expr.toString().contains("path.override_c"))
assertResult(false)(parseOutputStructFieldWithMetadataSourceColumn.errors.expr.toString().replaceAll("path.override_c", "").contains("path"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataSourceColumn.stdCol).toString().contains("path.c"))
assertResult(true)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataSourceColumn.stdCol).toString().contains("path.override_c"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataSourceColumn.stdCol).toString().replaceAll("path.override_c", "").contains("path"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataSourceColumn.errors).toString().contains("path.c"))
assertResult(true)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataSourceColumn.errors).toString().contains("path.override_c"))
assertResult(false)(ColUtils.col2Expr(parseOutputStructFieldWithMetadataSourceColumn.errors).toString().replaceAll("path.override_c", "").contains("path"))
}
}
Loading