D-Net

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

    <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_person,

				eu.dnetlib.iis.importer.schemas.Person,

				eu/dnetlib/iis/transformers/documentssimilarity_with_fulltext/sampledataproducer/data/input_person.json}</arg>

            <arg>-C{input_metadata,

				eu.dnetlib.iis.transformers.metadatamerger.schemas.ExtractedDocumentMetadataMergedWithOriginal,

				eu/dnetlib/iis/transformers/documentssimilarity_with_fulltext/sampledataproducer/data/input_metadata.json}</arg>

            <arg>-C{input_document_text,

				eu.dnetlib.iis.metadataextraction.schemas.DocumentText,

				eu/dnetlib/iis/transformers/documentssimilarity_with_fulltext/sampledataproducer/data/input_document_text.json}</arg>

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

				directory has to be specified as well -->

            <arg>-SworkingDir=${workingDir}/producer/working_dir</arg>

            <arg>-Oinput_person=${workingDir}/producer/input_person</arg>

            <arg>-Oinput_metadata=${workingDir}/producer/input_metadata</arg>

            <arg>-Oinput_document_text=${workingDir}/producer/input_document_text</arg>

        </java>

        <ok to="transformer_documentssimilarity_with_fulltext"/>

        <error to="fail"/>

    </action>

    <action name="transformer_documentssimilarity_with_fulltext">

        <sub-workflow>

            <app-path>${wf:appPath()}/transformer_documentssimilarity_with_fulltext</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}/transformer_documentssimilarity_with_fulltext/working_dir</value>

                </property>

                <!-- Input ports. -->

                <property>

                    <name>input_person</name>

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

                </property>

                <property>

                    <name>input_metadata</name>

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

                </property>

                <property>

                    <name>input_document_text</name>

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

                </property>

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

                <property>

                    <name>output_document_metadata</name>

                    <value>${workingDir}/transformer_documentssimilarity_with_fulltext/output_document_metadata</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_document_metadata,

				eu.dnetlib.iis.documentssimilarity_with_fulltext.schemas.DocumentMetadata,

				eu/dnetlib/iis/transformers/documentssimilarity_with_fulltext/sampledataproducer/data/output_document_metadata.json}</arg>

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

				directory has to be specified as well -->

			<arg>-SworkingDir=${workingDir}/consumer/working_dir</arg>

			<arg>-Ioutput_document_metadata=${workingDir}/transformer_documentssimilarity_with_fulltext/output_document_metadata</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>