parquet_file_path ./src/test/resources/part-00589-733117df-3822-4fce-bded-17289cc5959a-c000.snappy.parquet the full path of the parquet file openaire_guidelines 4.0 the version of the OpenAIRE Guidelines to validate the records against outputPath . the path of the output-directory where the result-json-files will be stored sparkDriverMemory 4096M memory for driver process sparkExecutorMemory 2048m memory for individual executor sparkExecutorCores 4 number of cores used by single executor spark2ExtraListeners com.cloudera.spark.lineage.NavigatorAppListener spark 2.* extra listeners classname spark2SqlQueryExecutionListeners com.cloudera.spark.lineage.NavigatorQueryListener spark 2.* sql query execution listeners classname spark2EventLogDir spark2/logs spark 2.* event log dir location ${jobTracker} ${nameNode} mapreduce.job.queuename ${queueName} oozie.launcher.mapred.job.queue.name ${oozieLauncherQueueName} oozie.action.sharelib.for.spark ${oozieActionShareLibForSpark2} Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] yarn cluster Validate multiple records against OpenAIRE Guidelines eu.dnetlib.dhp.continuous_validator.ContinuousValidator dhp-continuous-validation-${projectVersion}.jar --executor-memory=${sparkExecutorMemory} --conf spark.executor.memoryOverhead=${sparkExecutorMemoryOverhead} --executor-cores=${sparkExecutorCores} --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.sql.shuffle.partitions=3840 --parquet_file_path${parquet_file_path} --openaire_guidelines${openaire_guidelines} --outputPath${outputPath}