imported from branch stable_ids generation of Actionset datacite

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/datacite/ExportActionSetJobNode.scala

@@ -0,0 +1,40 @@
+package eu.dnetlib.dhp.actionmanager.datacite
+import eu.dnetlib.dhp.application.ArgumentApplicationParser
+import eu.dnetlib.dhp.schema.oaf.Oaf
+import org.apache.hadoop.io.Text
+import org.apache.hadoop.io.compress.GzipCodec
+import org.apache.hadoop.mapred.SequenceFileOutputFormat
+import org.apache.spark.SparkConf
+import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
+import org.slf4j.{Logger, LoggerFactory}
+
+import scala.io.Source
+
+object ExportActionSetJobNode {
+
+  val log: Logger = LoggerFactory.getLogger(ExportActionSetJobNode.getClass)
+
+  def main(args: Array[String]): Unit = {
+    val conf = new SparkConf
+    val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/exportDataset_parameters.json")).mkString)
+    parser.parseArgument(args)
+    val master = parser.get("master")
+    val sourcePath = parser.get("sourcePath")
+    val targetPath = parser.get("targetPath")
+
+    val spark: SparkSession = SparkSession.builder().config(conf)
+      .appName(ExportActionSetJobNode.getClass.getSimpleName)
+      .master(master)
+      .getOrCreate()
+    implicit val resEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
+    implicit val tEncoder:Encoder[(String,String)] = Encoders.tuple(Encoders.STRING,Encoders.STRING)
+
+    spark.read.load(sourcePath).as[Oaf]
+      .map(o =>DataciteToOAFTransformation.toActionSet(o))
+      .filter(o => o!= null)
+      .rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text,Text]], classOf[GzipCodec])
+
+
+  }
+
+}

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/datacite/exportDataset_parameters.json

@@ -0,0 +1,21 @@
+[
+  {
+    "paramName": "s",
+    "paramLongName": "sourcePath",
+    "paramDescription": "the source mdstore path",
+    "paramRequired": true
+  },
+
+  {
+    "paramName": "t",
+    "paramLongName": "targetPath",
+    "paramDescription": "the target mdstore path",
+    "paramRequired": true
+  },
+  {
+    "paramName": "m",
+    "paramLongName": "master",
+    "paramDescription": "the master name",
+    "paramRequired": true
+  }
+]

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/datacite_export/oozie_app/config-default.xml

@@ -0,0 +1,23 @@
+<configuration>
+    <property>
+        <name>jobTracker</name>
+        <value>yarnRM</value>
+    </property>
+    <property>
+        <name>nameNode</name>
+        <value>hdfs://nameservice1</value>
+    </property>
+    <property>
+        <name>oozie.use.system.libpath</name>
+        <value>true</value>
+    </property>
+    <property>
+        <name>oozie.action.sharelib.for.spark</name>
+        <value>spark2</value>
+    </property>
+
+    <property>
+        <name>oozie.launcher.mapreduce.user.classpath.first</name>
+        <value>true</value>
+    </property>
+</configuration>

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/datacite_export/oozie_app/workflow.xml

@@ -0,0 +1,46 @@
+<workflow-app name="Datacite_to_ActionSet_Workflow" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>sourcePath</name>
+            <description>the working path of Datacite stores</description>
+        </property>
+        <property>
+            <name>outputPath</name>
+            <description>the path of Datacite ActionSet</description>
+        </property>
+    </parameters>
+
+    <start to="ExportDataset"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+
+    <action name="ExportDataset">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn-cluster</master>
+            <mode>cluster</mode>
+            <name>ExportDataset</name>
+            <class>eu.dnetlib.dhp.actionmanager.datacite.ExportActionSetJobNode</class>
+            <jar>dhp-aggregation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.sql.shuffle.partitions=3840
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+            </spark-opts>
+            <arg>--sourcePath</arg><arg>${sourcePath}</arg>
+            <arg>--targetPath</arg><arg>${outputPath}</arg>
+            <arg>--master</arg><arg>yarn-cluster</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+
+    <end name="End"/>
+</workflow-app>