refactoring create actionset of scholexplorer, moved on package dhp-aggregation

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/scholix/SparkCreateActionset.scala

@@ -1,9 +1,9 @@
-package eu.dnetlib.dhp.sx.provision
+package eu.dnetlib.dhp.actionmanager.scholix
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
 import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result}
-import org.apache.spark.{SparkConf, sql}
-import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
+import org.apache.spark.SparkConf
+import org.apache.spark.sql._
 import org.slf4j.{Logger, LoggerFactory}
 
 import scala.io.Source
@@ -34,16 +34,16 @@ object SparkCreateActionset {
     val workingDirFolder = parser.get("workingDirFolder")
     log.info(s"workingDirFolder  -> $workingDirFolder")
 
-    implicit val oafEncoders:Encoder[Oaf] = Encoders.kryo[Oaf]
-    implicit val resultEncoders:Encoder[Result] = Encoders.kryo[Result]
-    implicit val relationEncoders:Encoder[Relation] = Encoders.kryo[Relation]
+    implicit val oafEncoders: Encoder[Oaf] = Encoders.kryo[Oaf]
+    implicit val resultEncoders: Encoder[Result] = Encoders.kryo[Result]
+    implicit val relationEncoders: Encoder[Relation] = Encoders.kryo[Relation]
 
     import spark.implicits._
 
     val relation = spark.read.load(s"$sourcePath/relation").as[Relation]
 
-    relation.filter(r => (r.getDataInfo== null || r.getDataInfo.getDeletedbyinference == false) && !r.getRelClass.toLowerCase.contains("merge"))
-      .flatMap(r => List(r.getSource,r.getTarget)).distinct().write.mode(SaveMode.Overwrite).save(s"$workingDirFolder/id_relation")
+    relation.filter(r => (r.getDataInfo == null || r.getDataInfo.getDeletedbyinference == false) && !r.getRelClass.toLowerCase.contains("merge"))
+      .flatMap(r => List(r.getSource, r.getTarget)).distinct().write.mode(SaveMode.Overwrite).save(s"$workingDirFolder/id_relation")
 
 
     val idRelation = spark.read.load(s"$workingDirFolder/id_relation").as[String]
@@ -53,12 +53,12 @@ object SparkCreateActionset {
 
     log.info("save relation filtered")
 
-    relation.filter(r => (r.getDataInfo== null || r.getDataInfo.getDeletedbyinference == false) && !r.getRelClass.toLowerCase.contains("merge"))
+    relation.filter(r => (r.getDataInfo == null || r.getDataInfo.getDeletedbyinference == false) && !r.getRelClass.toLowerCase.contains("merge"))
       .write.mode(SaveMode.Overwrite).save(s"$workingDirFolder/actionSetOaf")
 
     log.info("saving entities")
 
-    val entities:Dataset[(String, Result)] = spark.read.load(s"$sourcePath/entities/*").as[Result].map(p => (p.getId, p))(Encoders.tuple(Encoders.STRING, resultEncoders))
+    val entities: Dataset[(String, Result)] = spark.read.load(s"$sourcePath/entities/*").as[Result].map(p => (p.getId, p))(Encoders.tuple(Encoders.STRING, resultEncoders))
 
 
     entities.filter(r => r.isInstanceOf[Result]).map(r => r.asInstanceOf[Result])

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/scholix/SparkSaveActionSet.scala

@@ -1,9 +1,9 @@
-package eu.dnetlib.dhp.sx.provision
+package eu.dnetlib.dhp.actionmanager.scholix
 
 import com.fasterxml.jackson.databind.ObjectMapper
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
 import eu.dnetlib.dhp.schema.action.AtomicAction
-import eu.dnetlib.dhp.schema.oaf.{Oaf, OtherResearchProduct, Publication, Relation, Software, Dataset => OafDataset}
+import eu.dnetlib.dhp.schema.oaf.{Oaf, Dataset => OafDataset,Publication, Software, OtherResearchProduct, Relation}
 import org.apache.hadoop.io.Text
 import org.apache.hadoop.io.compress.GzipCodec
 import org.apache.hadoop.mapred.SequenceFileOutputFormat
@@ -73,13 +73,13 @@ object SparkSaveActionSet {
     val targetPath = parser.get("targetPath")
     log.info(s"targetPath  -> $targetPath")
 
-    implicit val oafEncoders:Encoder[Oaf] = Encoders.kryo[Oaf]
-    implicit val tEncoder:Encoder[(String,String)] = Encoders.tuple(Encoders.STRING,Encoders.STRING)
+    implicit val oafEncoders: 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 =>toActionSet(o))
-      .filter(o => o!= null)
-      .rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text,Text]], classOf[GzipCodec])
+      .map(o => toActionSet(o))
+      .filter(o => o != null)
+      .rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text, Text]], classOf[GzipCodec])
 
   }
 

dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/actionset/oozie_app/workflow.xml

@@ -26,7 +26,7 @@
             <mode>cluster</mode>
             <name>Create Action Set</name>
             <class>eu.dnetlib.dhp.sx.provision.SparkCreateActionset</class>
-            <jar>dhp-graph-provision-${projectVersion}.jar</jar>
+            <jar>dhp-aggregation-${projectVersion}.jar</jar>
             <spark-opts>
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}
@@ -53,7 +53,7 @@
             <mode>cluster</mode>
             <name>Save Action Set</name>
             <class>eu.dnetlib.dhp.sx.provision.SparkSaveActionSet</class>
-            <jar>dhp-graph-provision-${projectVersion}.jar</jar>
+            <jar>dhp-aggregation-${projectVersion}.jar</jar>
             <spark-opts>
                 --executor-memory=${sparkExecutorMemory}
                 --executor-cores=${sparkExecutorCores}