D-Net

<?xml version="1.0"?>

<!-- Note that documentation placed in comments in this file uses the

"markdown" syntax (along with its way of dividing text into sections). -->

<workflow-app xmlns="uri:oozie:workflow:0.3" name="test-referenceextraction_project_main_sampletest">

	<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{document_text, 

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

				eu/dnetlib/iis/referenceextraction/project/data/document_text_only_nulls.json}</arg>

			<arg>-C{project, 

				eu.dnetlib.iis.importer.schemas.Project,

				eu/dnetlib/iis/referenceextraction/project/data/empty.json}</arg>

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

			<arg>-Odocument_text=${workingDir}/producer/document_text</arg>

			<arg>-Oproject=${workingDir}/producer/project</arg>

		</java>

		<ok to="referenceextraction_project" />

		<error to="fail" />

	</action>

    <action name="referenceextraction_project">

        <sub-workflow>

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

                </property>

                <property>

                    <name>input_document_text</name>

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

                </property>

                <property>

                    <name>input_project</name>

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

                </property>

                <property>

                    <name>output_document_to_project</name>

                    <value>${workingDir}/referenceextraction_project/document_to_project</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>

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

			<arg>-C{document_to_project,

				eu.dnetlib.iis.referenceextraction.project.schemas.DocumentToProject,

				eu/dnetlib/iis/referenceextraction/project/data/empty.json}</arg>

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

			<arg>-Idocument_to_project=${workingDir}/referenceextraction_project/document_to_project</arg>

		</java>

		<ok to="end" />

		<error to="fail" />

	</action>

    <kill name="fail">

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

        			[${wf:errorMessage(wf:lastErrorNode())}]

        		</message>

    </kill>

    <end name="end"/>

</workflow-app>