graphBasePath
the raw graph base path
isLookUpUrl
the address of the lookUp service
actionSetId
id of the actionSet
workingPath
path for the working directory
dedupGraphPath
path for the output graph
cutConnectedComponent
max number of elements in a connected component
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}
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
Copy Merge Relations
eu.dnetlib.dhp.oa.dedup.SparkCopyRels
dhp-dedup-openaire-${projectVersion}.jar
--executor-memory=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphBasePath${graphBasePath}
--workingPath${workingPath}
--actionSetId${actionSetId}
--entityTypeorganization
--destinationsimrel
--numPartitions8000
yarn
cluster
Create Similarity Relations
eu.dnetlib.dhp.oa.dedup.SparkCreateSimRels
dhp-dedup-openaire-${projectVersion}.jar
--executor-memory=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphBasePath${graphBasePath}
--isLookUpUrl${isLookUpUrl}
--actionSetId${actionSetId}
--workingPath${workingPath}
--numPartitions8000
yarn
cluster
Create Merge Relations
eu.dnetlib.dhp.oa.dedup.SparkCreateMergeRels
dhp-dedup-openaire-${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=3840
--graphBasePath${graphBasePath}
--workingPath${workingPath}
--isLookUpUrl${isLookUpUrl}
--actionSetId${actionSetId}
--cutConnectedComponent${cutConnectedComponent}
yarn
cluster
Create Merge Relations
eu.dnetlib.dhp.oa.dedup.SparkRemoveDiffRels
dhp-dedup-openaire-${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=3840
--graphBasePath${graphBasePath}
--isLookUpUrl${isLookUpUrl}
--actionSetId${actionSetId}
--workingPath${workingPath}
--numPartitions8000
yarn
cluster
Prepare Organization Relations
eu.dnetlib.dhp.oa.dedup.SparkPrepareOrgRels
dhp-dedup-openaire-${projectVersion}.jar
--executor-memory=${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}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
--graphBasePath${graphBasePath}
--workingPath${workingPath}
--isLookUpUrl${isLookUpUrl}
--actionSetId${actionSetId}
--dbUrl${dbUrl}
--dbTable${dbTable}
--dbUser${dbUser}
--dbPwd${dbPwd}
--numConnections20
yarn
cluster
Prepare New Organizations
eu.dnetlib.dhp.oa.dedup.SparkPrepareNewOrgs
dhp-dedup-openaire-${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=3840
--graphBasePath${graphBasePath}
--workingPath${workingPath}
--isLookUpUrl${isLookUpUrl}
--actionSetId${actionSetId}
--apiUrl${apiUrl}
--dbUrl${dbUrl}
--dbTable${dbTable}
--dbUser${dbUser}
--dbPwd${dbPwd}
--numConnections20