dnet-hadoop/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml

    <workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
    <parameters>
        <property>
            <name>PDBPath</name>
            <description>the PDB Database Working Path</description>
        </property>

        <property>
            <name>UNIPROTDBPath</name>
            <description>the UNIPROT Database Working Path</description>
        </property>

        <property>
            <name>EBIDataset</name>
            <description>the EBI Links Dataset  Path</description>
        </property>

        <property>
            <name>ScholixResolvedDBPath</name>
            <description>the Scholix Resolved Dataset  Path</description>
        </property>

        <property>
            <name>CrossrefLinksPath</name>
            <description>the CrossrefLinks Path</description>
        </property>
        <property>
            <name>targetPath</name>
            <description>the Target Working dir path</description>
        </property>
    </parameters>

    <start to="ConvertPDB"/>

    <kill name="Kill">
        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>

    <action name="ConvertPDB">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>Convert PDB to OAF Dataset</name>
            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory=${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.extraListeners=${spark2ExtraListeners}
                --conf spark.sql.shuffle.partitions=2000
                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
            </spark-opts>
            <arg>--master</arg><arg>yarn</arg>
            <arg>--dbPath</arg><arg>${PDBPath}</arg>
            <arg>--database</arg><arg>PDB</arg>
            <arg>--targetPath</arg><arg>${targetPath}/pdb_OAF</arg>
        </spark>
        <ok to="ConvertUNIPROT"/>
        <error to="Kill"/>
    </action>


    <action name="ConvertUNIPROT">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>Convert UNIPROT to OAF Dataset</name>
            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory=${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.extraListeners=${spark2ExtraListeners}
                --conf spark.sql.shuffle.partitions=2000
                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
            </spark-opts>
            <arg>--master</arg><arg>yarn</arg>
            <arg>--dbPath</arg><arg>${UNIPROTDBPath}</arg>
            <arg>--database</arg><arg>UNIPROT</arg>
            <arg>--targetPath</arg><arg>${targetPath}/uniprot_OAF</arg>
        </spark>
        <ok to="ConvertEBILinks"/>
        <error to="Kill"/>
    </action>


    <action name="ConvertEBILinks">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>Convert EBI Links to OAF Dataset</name>
            <class>eu.dnetlib.dhp.sx.graph.ebi.SparkEBILinksToOaf</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory=${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.extraListeners=${spark2ExtraListeners}
                --conf spark.sql.shuffle.partitions=2000
                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
            </spark-opts>
            <arg>--master</arg><arg>yarn</arg>
            <arg>--sourcePath</arg><arg>${EBIDataset}</arg>
            <arg>--targetPath</arg><arg>${targetPath}/ebi_OAF</arg>
        </spark>
        <ok to="ConvertScholixResolved"/>
        <error to="Kill"/>
    </action>


    <action name="ConvertScholixResolved">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>Convert Scholix to OAF Dataset</name>
            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory=${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.extraListeners=${spark2ExtraListeners}
                --conf spark.sql.shuffle.partitions=2000
                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
            </spark-opts>
            <arg>--master</arg><arg>yarn</arg>
            <arg>--dbPath</arg><arg>${ScholixResolvedDBPath}</arg>
            <arg>--database</arg><arg>SCHOLIX</arg>
            <arg>--targetPath</arg><arg>${targetPath}/scholix_resolved_OAF</arg>
        </spark>
        <ok to="ConvertCrossrefLinks"/>
        <error to="Kill"/>
    </action>


    <action name="ConvertCrossrefLinks">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>Convert Crossref Links to OAF Dataset</name>
            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory=${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.extraListeners=${spark2ExtraListeners}
                --conf spark.sql.shuffle.partitions=2000
                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
            </spark-opts>
            <arg>--master</arg><arg>yarn</arg>
            <arg>--dbPath</arg><arg>${CrossrefLinksPath}</arg>
            <arg>--database</arg><arg>CROSSREF_LINKS</arg>
            <arg>--targetPath</arg><arg>${targetPath}/crossref_unresolved_relation_OAF</arg>
        </spark>
        <ok to="End"/>
        <error to="Kill"/>
    </action>




    <end name="End"/>

</workflow-app>