D-Net

define avro_load_input_a

org.apache.pig.piggybank.storage.avro.AvroStorage(

'input_schema_class', '$schema');

define avro_load_input_b

org.apache.pig.piggybank.storage.avro.AvroStorage(

'input_schema_class', '$schema');

define avro_load_input_c

org.apache.pig.piggybank.storage.avro.AvroStorage(

'input_schema_class', '$schema');

define avro_load_input_d

org.apache.pig.piggybank.storage.avro.AvroStorage(

'input_schema_class', '$schema');

define avro_store_output

org.apache.pig.piggybank.storage.avro.AvroStorage(

'index', '0',

'output_schema_class', '$schema');

input_a = load '$input_a' using avro_load_input_a;

input_b = load '$input_b' using avro_load_input_b;

input_c = load '$input_c' using avro_load_input_c;

input_d = load '$input_d' using avro_load_input_d;

output_final = union input_a, input_b, input_c, input_d; 

store output_final into '$output' using avro_store_output;

<workflow-app xmlns="uri:oozie:workflow:0.4" name="transformers_common_union4">

	<parameters>

		<property>

			<name>input_a</name>

		</property>

		<property>

			<name>input_b</name>

		</property>

		<property>

			<name>input_c</name>

		</property>

		<property>

			<name>input_d</name>

		</property>

		<property>

			<name>output</name>

		</property>

		<property>

			<name>schema</name>

		</property>

	</parameters>

    <start to="transformer"/>

    <action name="transformer">

        <pig>

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

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

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

			<prepare>

				<delete path="${nameNode}${output}" />

			</prepare>

            <configuration>

                <property>

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

                    <value>${queueName}</value>

                </property>

            </configuration>

            <!-- Path to PIG script the workflow executes. -->

            <script>lib/scripts/union.pig</script>

            <param>input_a=${input_a}</param>

            <param>input_b=${input_b}</param>

            <param>input_c=${input_c}</param>

            <param>input_d=${input_d}</param>

            <param>output=${output}</param>

            <param>schema=${schema}</param>

        </pig>

        <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>