dnet-hadoop/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml

<workflow-app name="community_to_result_propagation" xmlns="uri:oozie:workflow:0.5">
    <parameters>
        <property>
            <name>sourcePath</name>
            <description>the source path</description>
        </property>
        <property>
            <name>organizationtoresultcommunitymap</name>
            <description>organization community map</description>
        </property>

    </parameters>

    <global>
        <job-tracker>${jobTracker}</job-tracker>
        <name-node>${nameNode}</name-node>
        <configuration>
            <property>
                <name>oozie.action.sharelib.for.spark</name>
                <value>${oozieActionShareLibForSpark2}</value>
            </property>
        </configuration>
    </global>

    <start to="prepare_result_communitylist"/>

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

    <action name="prepare_result_communitylist">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>Prepare-Community-Result-Organization</name>
            <class>eu.dnetlib.dhp.resulttocommunityfromorganization.PrepareResultCommunitySet</class>
            <jar>dhp-enrichment-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-cores=${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}${spark2EventLogDir}
                --conf spark.dynamicAllocation.enabled=true
                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
            </spark-opts>
            <arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
            <arg>--outputPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
            <arg>--organizationtoresultcommunitymap</arg><arg>${organizationtoresultcommunitymap}</arg>
        </spark>
        <ok to="fork-join-exec-propagation"/>
        <error to="Kill"/>
    </action>

    <fork name="fork-join-exec-propagation">
        <path start="join_propagate_publication"/>
        <path start="join_propagate_dataset"/>
        <path start="join_propagate_otherresearchproduct"/>
        <path start="join_propagate_software"/>
    </fork>

    <action name="join_propagate_publication">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>community2resultfromorganization-Publication</name>
            <class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
            <jar>dhp-enrichment-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-cores=${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}${spark2EventLogDir}
                --conf spark.dynamicAllocation.enabled=true
                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
            </spark-opts>
            <arg>--preparedInfoPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
            <arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
            <arg>--outputPath</arg><arg>${workingDir}/communityorganization/publication</arg>
            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>

        </spark>
        <ok to="wait2"/>
        <error to="Kill"/>
    </action>

    <action name="join_propagate_dataset">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>community2resultfromorganization-Dataset</name>
            <class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
            <jar>dhp-enrichment-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-cores=${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}${spark2EventLogDir}
                --conf spark.dynamicAllocation.enabled=true
                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
            </spark-opts>
            <arg>--preparedInfoPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
            <arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
            <arg>--outputPath</arg><arg>${workingDir}/communityorganization/dataset</arg>
            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>

        </spark>
        <ok to="wait2"/>
        <error to="Kill"/>
    </action>

    <action name="join_propagate_otherresearchproduct">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>community2resultfromorganization-ORP</name>
            <class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
            <jar>dhp-enrichment-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-cores=${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}${spark2EventLogDir}
                --conf spark.dynamicAllocation.enabled=true
                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
            </spark-opts>
            <arg>--preparedInfoPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
            <arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
            <arg>--outputPath</arg><arg>${workingDir}/communityorganization/otherresearchproduct</arg>
            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>

        </spark>
        <ok to="wait2"/>
        <error to="Kill"/>
    </action>

    <action name="join_propagate_software">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn</master>
            <mode>cluster</mode>
            <name>community2resultfromorganization-Software</name>
            <class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
            <jar>dhp-enrichment-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-cores=${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}${spark2EventLogDir}
                --conf spark.dynamicAllocation.enabled=true
                --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
            </spark-opts>
            <arg>--preparedInfoPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
            <arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
            <arg>--outputPath</arg><arg>${workingDir}/communityorganization/software</arg>
            <arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
            <arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>

        </spark>
        <ok to="wait2"/>
        <error to="Kill"/>
    </action>

    <join name="wait2" to="reset_workingDir"/>

    <action name="reset_workingDir">
        <fs>
            <delete path="${workingDir}"/>
            <mkdir path="${workingDir}"/>
        </fs>
        <ok to="End"/>
        <error to="Kill"/>
    </action>
    <end name="End"/>

</workflow-app>