activePromoteDatasetActionPayload
when true will promote actions with eu.dnetlib.dhp.schema.oaf.Dataset payload
activePromoteResultActionPayload
when true will promote actions with eu.dnetlib.dhp.schema.oaf.Result payload
inputGraphRootPath
root location of input materialized graph
inputActionPayloadRootPath
root location of action payloads to promote
outputGraphRootPath
root location for output materialized graph
mergeAndGetStrategy
strategy for merging graph table objects with action payload instances, MERGE_FROM_AND_GET or SELECT_NEWER_AND_GET
shouldGroupById
indicates whether the promotion operation should group objects in the graph by id or not
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
${jobTracker}
${nameNode}
oozie.action.sharelib.for.spark
${oozieActionShareLibForSpark2}
Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]
${(activePromoteDatasetActionPayload eq "true") and
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputGraphRootPath')),'/'),'dataset')) eq "true") and
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputActionPayloadRootPath')),'/'),'clazz=eu.dnetlib.dhp.schema.oaf.Dataset')) eq "true")}
yarn-cluster
cluster
PromoteDatasetActionPayloadForDatasetTable
eu.dnetlib.dhp.actionmanager.promote.PromoteActionPayloadForGraphTableJob
dhp-actionmanager-${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.shuffle.partitions=2560
--inputGraphTablePath${inputGraphRootPath}/dataset
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Dataset
--inputActionPayloadPath${inputActionPayloadRootPath}/clazz=eu.dnetlib.dhp.schema.oaf.Dataset
--actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Dataset
--outputGraphTablePath${workingDir}/dataset
--mergeAndGetStrategy${mergeAndGetStrategy}
--shouldGroupById${shouldGroupById}
-pb
${inputGraphRootPath}/dataset
${workingDir}/dataset
${(activePromoteResultActionPayload eq "true") and
(fs:exists(concat(concat(concat(concat(wf:conf('nameNode'),'/'),wf:conf('inputActionPayloadRootPath')),'/'),'clazz=eu.dnetlib.dhp.schema.oaf.Result')) eq "true")}
yarn-cluster
cluster
PromoteResultActionPayloadForDatasetTable
eu.dnetlib.dhp.actionmanager.promote.PromoteActionPayloadForGraphTableJob
dhp-actionmanager-${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.shuffle.partitions=2560
--inputGraphTablePath${workingDir}/dataset
--graphTableClassNameeu.dnetlib.dhp.schema.oaf.Dataset
--inputActionPayloadPath${inputActionPayloadRootPath}/clazz=eu.dnetlib.dhp.schema.oaf.Result
--actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Result
--outputGraphTablePath${outputGraphRootPath}/dataset
--mergeAndGetStrategy${mergeAndGetStrategy}
--shouldGroupById${shouldGroupById}
-pb
${workingDir}/dataset
${outputGraphRootPath}/dataset