dnet-hadoop/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/step2/oozie_app/workflow.xml

<workflow-app name="Create Raw Graph Step 2: Map XML to OAF Entities" xmlns="uri:oozie:workflow:0.5">
    <parameters>
        <property>
            <name>workingPath</name>
            <description>the working path</description>
        </property>
        <property>
            <name>sparkDriverMemory</name>
            <description>memory for driver process</description>
        </property>
        <property>
            <name>sparkExecutorMemory</name>
            <description>memory for individual executor</description>
        </property>
    </parameters>

    <start to="ExtractDLIPublication"/>

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

    <action name="ExtractDLIPublication">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <master>yarn-cluster</master>
            <mode>cluster</mode>
            <name>Extract DLI Entities (Publication)</name>
            <class>eu.dnetlib.dhp.sx.graph.SparkSplitOafTODLIEntities</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory ${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.sql.shuffle.partitions=5000
                ${sparkExtraOPT}
            </spark-opts>
            <arg>-mt</arg> <arg>yarn-cluster</arg>
            <arg>--workingPath</arg><arg>${workingPath}</arg>
            <arg>-e</arg><arg>publication</arg>
        </spark>
        <ok to="ExtractDLIDataset"/>
        <error to="Kill"/>
    </action>

    <action name="ExtractDLIDataset">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <master>yarn-cluster</master>
            <mode>cluster</mode>
            <name>Extract DLI Entities (Dataset)</name>
            <class>eu.dnetlib.dhp.sx.graph.SparkSplitOafTODLIEntities</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory ${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.sql.shuffle.partitions=5000
                ${sparkExtraOPT}
            </spark-opts>
            <arg>-mt</arg> <arg>yarn-cluster</arg>
            <arg>--workingPath</arg><arg>${workingPath}</arg>
            <arg>-e</arg><arg>dataset</arg>
        </spark>
        <ok to="ExtractDLIUnknown"/>
        <error to="Kill"/>
    </action>

    <action name="ExtractDLIUnknown">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <master>yarn-cluster</master>
            <mode>cluster</mode>
            <name>Extract DLI Entities (Unknown)</name>
            <class>eu.dnetlib.dhp.sx.graph.SparkSplitOafTODLIEntities</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory ${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.sql.shuffle.partitions=5000
                ${sparkExtraOPT}
            </spark-opts>
            <arg>-mt</arg> <arg>yarn-cluster</arg>
            <arg>--workingPath</arg><arg>${workingPath}</arg>
            <arg>-e</arg><arg>unknown</arg>
        </spark>
        <ok to="ExtractDLIRelation"/>
        <error to="Kill"/>
    </action>

    <action name="ExtractDLIRelation">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <master>yarn-cluster</master>
            <mode>cluster</mode>
            <name>Extract DLI Entities (Relation)</name>
            <class>eu.dnetlib.dhp.sx.graph.SparkSplitOafTODLIEntities</class>
            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory ${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.sql.shuffle.partitions=5000
                ${sparkExtraOPT}
            </spark-opts>
            <arg>-mt</arg> <arg>yarn-cluster</arg>
            <arg>--workingPath</arg><arg>${workingPath}</arg>
            <arg>-e</arg><arg>relation</arg>
        </spark>
        <ok to="End"/>
        <error to="Kill"/>
    </action>

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