inputGraph the input graph name (or path) outputGraph the output graph name (or path) isLookUpUrl the address of the lookUp service inputGraphFormat HIVE the input graph data format outputGraphFormat HIVE the output graph data format hiveMetastoreUris hive server metastore URIs sparkDriverMemory memory for driver process sparkExecutorMemory memory for individual executor sparkExecutorCores number of cores used by single executor oozieActionShareLibForSpark2 oozie action sharelib for spark 2.* spark2ExtraListeners com.cloudera.spark.lineage.NavigatorAppListener spark 2.* extra listeners classname spark2SqlQueryExecutionListeners com.cloudera.spark.lineage.NavigatorQueryListener spark 2.* sql query execution listeners classname spark2YarnHistoryServerAddress spark 2.* yarn history server address spark2EventLogDir spark 2.* event log dir location sparkSqlWarehouseDir spark 2.* db directory 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())}] ${wf:conf('outputGraphFormat') eq 'JSON'} ${wf:conf('outputGraphFormat') eq 'HIVE'} yarn cluster reset_DB eu.dnetlib.dhp.common.ResetHiveDbApplication dhp-graph-mapper-${projectVersion}.jar --executor-memory ${sparkExecutorMemory} --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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --dbName${outputGraph} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean publications eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.Publication --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean datasets eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.Dataset --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean otherresearchproducts eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean softwares eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.Software --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean datasources eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.Datasource --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean organizations eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.Organization --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean projects eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.Project --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris} yarn cluster Clean relations eu.dnetlib.dhp.oa.graph.clean.CleanGraphSparkJob dhp-graph-mapper-${projectVersion}.jar --executor-cores=${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}${spark2EventLogDir} --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} --conf spark.sql.shuffle.partitions=7680 --inputGraph${inputGraph} --outputGraph${outputGraph} --inputGraphFormat${inputGraphFormat} --outputGraphFormat${outputGraphFormat} --graphTableClassNameeu.dnetlib.dhp.schema.oaf.Relation --isLookUpUrl${isLookUpUrl} --hiveMetastoreUris${hiveMetastoreUris}