dnet-hadoop/dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/orcid_updates_download/oozie_app/workflow.xml

<workflow-app name="Orcid Updates Download" xmlns="uri:oozie:workflow:0.5">
    <parameters>
        <property>
            <name>workingPath</name>
            <description>the working dir base path</description>
        </property>
        <property>
            <name>token</name>
            <description>access token</description>
        </property>
        <property>
            <name>shell_cmd</name>
            <value>wget -O /tmp/last_modified.csv.tar http://74804fb637bd8e2fba5b-e0a029c2f87486cddec3b416996a6057.r3.cf1.rackcdn.com/last_modified.csv.tar ; hdfs dfs -copyFromLocal /tmp/last_modified.csv.tar /data/orcid_activities_2020/last_modified.csv.tar ; rm -f /tmp/last_modified.csv.tar
            </value>
            <description>the shell command that downloads the lambda file from orcid containing last orcid update informations</description>
        </property>
        <property>
            <name>sparkExecutorNumber</name>
            <value>20</value>
        </property>
        <property>
            <name>sparkDriverMemory</name>
            <value>7G</value>
            <description>memory for driver process</description>
        </property>
        <property>
            <name>sparkExecutorMemory</name>
            <value>2G</value>
            <description>memory for individual executor</description>
        </property>
        <property>
            <name>sparkExecutorCores</name>
            <value>1</value>
            <description>number of cores used by single executor</description>
        </property>
        <property>
            <name>spark2MaxExecutors</name>
            <value>20</value>
        </property>
        <property>
            <name>oozieActionShareLibForSpark2</name>
            <description>oozie action sharelib for spark 2.*</description>
        </property>
        <property>
            <name>spark2ExtraListeners</name>
            <value>com.cloudera.spark.lineage.NavigatorAppListener</value>
            <description>spark 2.* extra listeners classname</description>
        </property>
        <property>
            <name>spark2SqlQueryExecutionListeners</name>
            <value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
            <description>spark 2.* sql query execution listeners classname</description>
        </property>
        <property>
            <name>spark2YarnHistoryServerAddress</name>
            <description>spark 2.* yarn history server address</description>
        </property>
        <property>
            <name>spark2EventLogDir</name>
            <description>spark 2.* event log dir location</description>
        </property>
    </parameters>

    <global>
        <configuration>
            <property>
                <name>oozie.action.sharelib.for.spark</name>
                <value>${oozieActionShareLibForSpark2}</value>
            </property>
        </configuration>
    </global>

    <start to="DownloadOrcidAuthors"/>
    
    
    <kill name="Kill">
        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
    </kill>
    
    <action name="ResetWorkingPath">
        <fs>
            <delete path='${workingPath}/downloads'/>
            <delete path='${workingPath}/last_modified.csv.tar'/>
            <mkdir path='${workingPath}/downloads'/>
        </fs>
        <ok to="DownloadLambdaFile"/>
        <error to="Kill"/>
    </action>

    <action name="DownloadLambdaFile">
        <shell xmlns="uri:oozie:shell-action:0.1">
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <exec>bash</exec>
            <argument>-c</argument>
            <argument>${shell_cmd}</argument>
            <capture-output/>
        </shell>
        <ok to="DownloadUpdatedXMLAuthors"/>
        <error to="Kill"/>
    </action>

	<action name="DownloadUpdatedXMLAuthors">
        <java>
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <main-class>eu.dnetlib.doiboost.orcid.OrcidDownloader</main-class>
            <arg>-w</arg><arg>${workingPath}/</arg>
            <arg>-n</arg><arg>${nameNode}</arg>
            <arg>-f</arg><arg>last_modified.csv.tar</arg>
            <arg>-o</arg><arg>downloads/</arg>
            <arg>-t</arg><arg>${token}</arg>
        </java>
        <ok to="End"/>
        <error to="Kill"/>
    </action>

    <action name="GenLastModifiedSeq">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn-cluster</master>
            <mode>cluster</mode>
            <name>GenLastModifiedSeq</name>
            <class>eu.dnetlib.doiboost.orcid.SparkGenLastModifiedSeq</class>
            <jar>dhp-doiboost-${projectVersion}.jar</jar>
            <spark-opts>
                --executor-memory=${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.extraListeners=${spark2ExtraListeners}
                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
            </spark-opts>
            <arg>-w</arg><arg>${workingPath}/</arg>
            <arg>-n</arg><arg>${nameNode}</arg>
            <arg>-f</arg><arg>last_modified.csv.tar</arg>
            <arg>-o</arg><arg>last_modified.seq</arg>
            <arg>-t</arg><arg>-</arg>
        </spark>
        <ok to="End"/>
        <error to="Kill"/>
    </action>

    <action name="DownloadOrcidAuthors">
        <spark xmlns="uri:oozie:spark-action:0.2">
            <master>yarn-cluster</master>
            <mode>cluster</mode>
            <name>DownloadOrcidAuthors</name>
            <class>eu.dnetlib.doiboost.orcid.SparkDownloadOrcidAuthors</class>
            <jar>dhp-doiboost-${projectVersion}.jar</jar>
            <spark-opts>
                --num-executors=${sparkExecutorNumber}
                --executor-memory=${sparkExecutorMemory}
                --executor-cores=${sparkExecutorCores}
                --driver-memory=${sparkDriverMemory}
                --conf spark.extraListeners=${spark2ExtraListeners}
                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
            </spark-opts>
            <arg>-w</arg><arg>${workingPath}/</arg>
            <arg>-n</arg><arg>${nameNode}</arg>
            <arg>-f</arg><arg>last_modified.seq</arg>
            <arg>-o</arg><arg>downloads/updated_authors</arg>
            <arg>-t</arg><arg>${token}</arg>
        </spark>
        <ok to="End"/>
        <error to="Kill"/>
    </action>
    
   <end name="End"/>
</workflow-app>