diff --git a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/project/oozie_app/workflow.xml b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/project/oozie_app/workflow.xml
index 992c2ded1..cd4d79ab7 100644
--- a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/project/oozie_app/workflow.xml
+++ b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/project/oozie_app/workflow.xml
@@ -24,6 +24,7 @@
+
@@ -31,51 +32,100 @@
- eu.dnetlib.dhp.actionmanager.project.GetFile
+ eu.dnetlib.dhp.actionmanager.project.csvutils.ReadCSV
--hdfsNameNode${nameNode}
--fileURL${projectFileURL}
- --hdfsPath${workingDir}/projects.csv
+ --hdfsPath${workingDir}/projects
+ --classForNameeu.dnetlib.dhp.actionmanager.project.csvutils.CSVProject
-
+
-
+
- eu.dnetlib.dhp.actionmanager.project.GetFile
+ eu.dnetlib.dhp.actionmanager.project.csvutils.ReadCSV
--hdfsNameNode${nameNode}
--fileURL${programmeFileURL}
- --hdfsPath${workingDir}/programme.csv
+ --hdfsPath${workingDir}/programme
+ --classForNameeu.dnetlib.dhp.actionmanager.project.csvutils.CSVProgramme
+
+
+
+
+
+
+ yarn
+ cluster
+ PrepareProgramme
+ eu.dnetlib.dhp.actionmanager.project.PrepareProgramme
+ dhp-aggregation-${projectVersion}.jar
+
+ --executor-cores=${sparkExecutorCores}
+ --executor-memory=${sparkExecutorMemory}
+ --driver-memory=${sparkDriverMemory}
+ --conf spark.extraListeners=${spark2ExtraListeners}
+ --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+ --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+ --conf spark.sql.shuffle.partitions=3840
+
+ --programmePath${workingDir}/programme
+ --outputPath${workingDir}/preparedProgramme
+
+
+
+
+
+
+
+ yarn
+ cluster
+ PrepareProgramme
+ eu.dnetlib.dhp.actionmanager.project.PrepareProjects
+ dhp-aggregation-${projectVersion}.jar
+
+ --executor-cores=${sparkExecutorCores}
+ --executor-memory=${sparkExecutorMemory}
+ --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
+
+ --projectPath${workingDir}/projects
+ --outputPath${workingDir}/preparedProjects
+
+
+
+
+
+
+
+ yarn
+ cluster
+ ProjectProgrammeAS
+ eu.dnetlib.dhp.actionmanager.project.SparkAtomicActionJob
+ dhp-aggregation-${projectVersion}.jar
+
+ --executor-cores=${sparkExecutorCores}
+ --executor-memory=${sparkExecutorMemory}
+ --driver-memory=${sparkDriverMemory}
+ --conf spark.extraListeners=${spark2ExtraListeners}
+ --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+ --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+ --conf spark.sql.shuffle.partitions=3840
+
+ --projectPath${workingDir}/preparedProjects
+ --programmePath${workingDir}/preparedProgramme
+ --outputPath/tmp/h2020programme
+
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
\ No newline at end of file