za.co.absa.enceladus.conformance.interpreter.rules.CoalesceRuleInterpreter.scala Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of spark-jobs Show documentation
The newest version!
/*
 * Copyright 2018 ABSA Group Limited
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

package za.co.absa.enceladus.conformance.interpreter.rules

import org.apache.spark.sql.functions._
import org.apache.spark.sql.{Dataset, Row, SparkSession}
import za.co.absa.enceladus.conformance.config.ConformanceConfig
import za.co.absa.enceladus.conformance.interpreter.{ExplosionState, InterpreterContextArgs, RuleValidators}
import za.co.absa.enceladus.dao.EnceladusDAO
import za.co.absa.enceladus.model.conformanceRule.{CoalesceConformanceRule, ConformanceRule}
import za.co.absa.spark.hats.Extensions._
import CoalesceRuleInterpreter._

object CoalesceRuleInterpreter {
  private final val ruleName = "Coalesce rule"
}

case class CoalesceRuleInterpreter(rule: CoalesceConformanceRule) extends RuleInterpreter {

  override def conformanceRule: Option[ConformanceRule] = Some(rule)

  def conform(df: Dataset[Row])
             (implicit spark: SparkSession,
              explosionState: ExplosionState,
              dao: EnceladusDAO,
              progArgs: InterpreterContextArgs): Dataset[Row] = {
    // Validate the rule parameters
    RuleValidators.validateSameParent(progArgs.datasetName, ruleName, rule.inputColumns :+ rule.outputColumn: _*)

    if (rule.outputColumn.contains('.')) {
      conformNestedField(df)
    } else {
      conformRootField(df)
    }
  }

  /** Handles coalesce conformance rule for nested fields. */
  private def conformNestedField(df: Dataset[Row])(implicit spark: SparkSession): Dataset[Row] = {
    df.nestedWithColumnExtended(rule.outputColumn, getField => {
      coalesce(rule.inputColumns.map(getField): _*)
    })
  }

  /** Handles coalesce conformance rule for root (non-nested) fields. */
  private def conformRootField(df: Dataset[Row])(implicit spark: SparkSession): Dataset[Row] = {
    // Applying the rule
    df.withColumn(rule.outputColumn, coalesce(rule.inputColumns.map(col): _*))
  }

}