dnet-hadoop/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionset/h2020programme/oozie_app/workflow.xml

<workflow-app name="H2020Programme" xmlns="uri:oozie:workflow:0.5">
    <parameters>
        <property>
            <name>projectFileURL</name>
            <description>the url where to get the projects file</description>
        </property>

        <property>
            <name>programmeFileURL</name>
            <description>the url where to get the programme file</description>
        </property>

        <property>
            <name>outputPath</name>
            <description>path where to store the action set</description>
        </property>
    </parameters>

    <start to="deleteoutputpath"/>
    <kill name="Kill">
        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    <action name="deleteoutputpath">
        <fs>
            <delete path='${outputPath}'/>
            <mkdir path='${outputPath}'/>
        </fs>
        <ok to="get_project_file"/>
        <error to="Kill"/>
    </action>

    <action name="get_project_file">
        <java>
            <main-class>eu.dnetlib.dhp.actionset.h2020programme.GetFile</main-class>
            <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
            <arg>--fileUrl</arg><arg>${projectFileURL}</arg>
            <arg>--hdfsPath</arg><arg>${workingDir}/projects.csv</arg>
        </java>
        <ok to="shell_get_programme_file"/>
        <error to="Kill"/>
    </action>

    <action name="shell_get_programme_file">
        <java>
            <main-class>eu.dnetlib.dhp.actionset.h2020programme.GetFile</main-class>
            <arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
            <arg>--fileUrl</arg><arg>${programmeFileURL}</arg>
            <arg>--hdfsPath</arg><arg>${workingDir}/programme.csv</arg>
        </java>
        <ok to="End"/>
        <error to="Kill"/>
    </action>

<!--    <action name="create_actionset">-->
<!--        <spark xmlns="uri:oozie:spark-action:0.2">-->
<!--            <master>yarn</master>-->
<!--            <mode>cluster</mode>-->
<!--            <name>ProjectProgrammeAS</name>-->
<!--            <class>eu.dnetlib.dhp.actionset.h2020programme</class>-->
<!--            <jar>dhp-aggregation-${projectVersion}.jar</jar>-->
<!--            <spark-opts>-->
<!--                &#45;&#45;executor-cores=${sparkExecutorCores}-->
<!--                &#45;&#45;executor-memory=${sparkExecutorMemory}-->
<!--                &#45;&#45;driver-memory=${sparkDriverMemory}-->
<!--                &#45;&#45;conf spark.extraListeners=${spark2ExtraListeners}-->
<!--                &#45;&#45;conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}-->
<!--                &#45;&#45;conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}-->
<!--                &#45;&#45;conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}-->
<!--                &#45;&#45;conf spark.sql.shuffle.partitions=3840-->
<!--            </spark-opts>-->
<!--            <arg>&#45;&#45;sourcePath</arg><arg>${sourcePath}/relation</arg>-->
<!--            <arg>&#45;&#45;outputPath</arg><arg>${outputPath}/relation</arg>-->
<!--            <arg>&#45;&#45;hdfsPath</arg><arg>${workingDir}/blacklist</arg>-->
<!--            <arg>&#45;&#45;mergesPath</arg><arg>${workingDir}/mergesRelation</arg>-->
<!--        </spark>-->
<!--        <ok to="End"/>-->
<!--        <error to="Kill"/>-->
<!--    </action>-->

    <end name="End"/>
</workflow-app>