D-Net

<workflow-app xmlns="uri:oozie:workflow:0.2" name="test-origins_collapser_default">

    <start to="producer"/>

    <action name="producer">

        <java>

            <job-tracker>${jobTracker}</job-tracker>

            <name-node>${nameNode}</name-node>

			<!-- The data generated by this node is deleted in this section -->

			<prepare>

				<delete path="${nameNode}${workingDir}/producer" />

				<mkdir path="${nameNode}${workingDir}/producer" />

			</prepare>

            <configuration>

                <property>

                    <name>mapred.job.queue.name</name>

                    <value>${queueName}</value>

                </property>

            </configuration>

            <!-- This is simple wrapper for the Java code -->

			<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class>

			<!-- The business Java code that gets to be executed -->

			<arg>eu.dnetlib.iis.core.java.jsonworkflownodes.Producer</arg>

			<!-- Specification of the output ports -->

			<arg>-C{input,

				eu.dnetlib.iis.collapsers.schemas.DocumentMetadataEnvelope,

				eu/dnetlib/iis/collapsers/origins_collapser/default/data/metadata.json}</arg>

			<!-- All input and output ports have to be bound to paths in HDFS -->

            <arg>-Oinput=${workingDir}/producer/input</arg>

        </java>

        <ok to="origins_collapser"/>

        <error to="fail"/>

    </action>

    <action name="origins_collapser">

        <sub-workflow>

            <app-path>${wf:appPath()}/origins_collapser</app-path>

            <configuration>

                <property>

                    <name>jobTracker</name>

                    <value>${jobTracker}</value>

                </property>

                <property>

                    <name>nameNode</name>

                    <value>${nameNode}</value>

                </property>

                <property>

                    <name>queueName</name>

                    <value>${queueName}</value>

                </property>

                <!-- Working directory of the subworkflow -->                

                <property>

                    <name>workingDir</name>

                    <value>${workingDir}/origins_collapser/working_dir</value>

                </property>

                <property>

                    <name>blocking_field</name>

                    <value>data.id</value>

                </property>

                <property>

                    <name>origins</name>

                    <value>orig,cermine</value>

                </property>

                <property>

                    <name>schema_input</name>

                    <value>eu.dnetlib.iis.collapsers.schemas.DocumentMetadataEnvelope</value>

                </property>

                <property>

                    <name>schema_output</name>

                    <value>eu.dnetlib.iis.importer.schemas.DocumentMetadata</value>

                </property>

                <property>

                    <name>record_collapser</name>

                    <value>eu.dnetlib.iis.collapsers.origins.OriginConfidenceCollapser</value>

                </property>

                <!-- Input ports. -->

                <property>

                    <name>input</name>

                    <value>${workingDir}/producer/input</value>

                </property>

                <!-- Output port bound to given path -->

                <property>

                    <name>output</name>

                    <value>${workingDir}/origins_collapser/output</value>

                </property>

            </configuration>

        </sub-workflow>

        <ok to="consumer"/>

        <error to="fail"/>

    </action>

    <action name="consumer">

		<java>

			<job-tracker>${jobTracker}</job-tracker>

			<name-node>${nameNode}</name-node>

			<configuration>

				<property>

					<name>mapred.job.queue.name</name>

					<value>${queueName}</value>

				</property>

			</configuration>

			<!-- This is simple wrapper for the Java code -->

			<main-class>eu.dnetlib.iis.core.java.ProcessWrapper</main-class>

			<!-- The business Java code that gets to be executed -->

			<arg>eu.dnetlib.iis.core.java.jsonworkflownodes.TestingConsumer</arg>

			<!-- Specification of the input ports -->

			<arg>-C{output,

				eu.dnetlib.iis.importer.schemas.DocumentMetadata,

				eu/dnetlib/iis/collapsers/origins_collapser/default/data/output.json}</arg>

    		<!-- All input and output ports have to be bound to paths in HDFS -->

			<arg>-Ioutput=${workingDir}/origins_collapser/output</arg>

		</java>

		<ok to="end" />

		<error to="fail" />

	</action>

    <kill name="fail">

		<message>Unfortunately, the workflow failed -- error message:

			[${wf:errorMessage(wf:lastErrorNode())}]</message>

    </kill>

    <end name="end"/>

</workflow-app>