[scala-refactor] Module dhp-aggregation:

Moved all scala source into src/main/scala and src/test/scala

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

@@ -1,69 +0,0 @@
-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
-import org.apache.spark.sql._
-import org.slf4j.{Logger, LoggerFactory}
-
-import scala.io.Source
-
-object SparkCreateActionset {
-
-  def main(args: Array[String]): Unit = {
-    val log: Logger = LoggerFactory.getLogger(getClass)
-    val conf: SparkConf = new SparkConf()
-    val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/actionset/generate_actionset.json")).mkString)
-    parser.parseArgument(args)
-
-
-    val spark: SparkSession =
-      SparkSession
-        .builder()
-        .config(conf)
-        .appName(getClass.getSimpleName)
-        .master(parser.get("master")).getOrCreate()
-
-
-    val sourcePath = parser.get("sourcePath")
-    log.info(s"sourcePath  -> $sourcePath")
-
-    val targetPath = parser.get("targetPath")
-    log.info(s"targetPath  -> $targetPath")
-
-    val workingDirFolder = parser.get("workingDirFolder")
-    log.info(s"workingDirFolder  -> $workingDirFolder")
-
-    implicit val oafEncoders: Encoder[Oaf] = Encoders.kryo[Oaf]
-    implicit val resultEncoders: Encoder[Result] = Encoders.kryo[Result]
-    implicit val relationEncoders: Encoder[Relation] = Encoders.kryo[Relation]
-
-    import spark.implicits._
-
-    val relation = spark.read.load(s"$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"$workingDirFolder/id_relation")
-
-
-    val idRelation = spark.read.load(s"$workingDirFolder/id_relation").as[String]
-
-    log.info("extract source and target Identifier involved in relations")
-
-
-    log.info("save relation filtered")
-
-    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))
-
-    entities
-      .joinWith(idRelation, entities("_1").equalTo(idRelation("value")))
-      .map(p => p._1._2)
-      .write.mode(SaveMode.Append).save(s"$workingDirFolder/actionSetOaf")
-  }
-
-}

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

@@ -1,86 +0,0 @@
-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, 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
-import org.apache.spark.SparkConf
-import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
-import org.slf4j.{Logger, LoggerFactory}
-
-import scala.io.Source
-
-object SparkSaveActionSet {
-
-
-  def toActionSet(item: Oaf): (String, String) = {
-    val mapper = new ObjectMapper()
-
-    item match {
-      case dataset: OafDataset =>
-        val a: AtomicAction[OafDataset] = new AtomicAction[OafDataset]
-        a.setClazz(classOf[OafDataset])
-        a.setPayload(dataset)
-        (dataset.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case publication: Publication =>
-        val a: AtomicAction[Publication] = new AtomicAction[Publication]
-        a.setClazz(classOf[Publication])
-        a.setPayload(publication)
-        (publication.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case software: Software =>
-        val a: AtomicAction[Software] = new AtomicAction[Software]
-        a.setClazz(classOf[Software])
-        a.setPayload(software)
-        (software.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case orp: OtherResearchProduct =>
-        val a: AtomicAction[OtherResearchProduct] = new AtomicAction[OtherResearchProduct]
-        a.setClazz(classOf[OtherResearchProduct])
-        a.setPayload(orp)
-        (orp.getClass.getCanonicalName, mapper.writeValueAsString(a))
-
-      case relation: Relation =>
-        val a: AtomicAction[Relation] = new AtomicAction[Relation]
-        a.setClazz(classOf[Relation])
-        a.setPayload(relation)
-        (relation.getClass.getCanonicalName, mapper.writeValueAsString(a))
-      case _ =>
-        null
-    }
-
-  }
-
-  def main(args: Array[String]): Unit = {
-    val log: Logger = LoggerFactory.getLogger(getClass)
-    val conf: SparkConf = new SparkConf()
-    val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/actionset/save_actionset.json")).mkString)
-    parser.parseArgument(args)
-
-
-    val spark: SparkSession =
-      SparkSession
-        .builder()
-        .config(conf)
-        .appName(getClass.getSimpleName)
-        .master(parser.get("master")).getOrCreate()
-
-
-    val sourcePath = parser.get("sourcePath")
-    log.info(s"sourcePath  -> $sourcePath")
-
-    val targetPath = parser.get("targetPath")
-    log.info(s"targetPath  -> $targetPath")
-
-    implicit val oafEncoders: Encoder[Oaf] = Encoders.kryo[Oaf]
-    implicit val tEncoder: Encoder[(String, String)] = Encoders.tuple(Encoders.STRING, Encoders.STRING)
-
-    spark.read.load(sourcePath).as[Oaf]
-      .map(o => toActionSet(o))
-      .filter(o => o != null)
-      .rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text, Text]], classOf[GzipCodec])
-
-  }
-
-}

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteModelConstants.scala

@@ -1,8 +1,8 @@
 package eu.dnetlib.dhp.datacite
 
 import eu.dnetlib.dhp.schema.common.ModelConstants
-import eu.dnetlib.dhp.schema.oaf.{DataInfo, KeyValue}
 import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils
+import eu.dnetlib.dhp.schema.oaf.{DataInfo, KeyValue}
 
 import java.io.InputStream
 import java.time.format.DateTimeFormatter

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTransformation.scala

@@ -6,7 +6,7 @@ import eu.dnetlib.dhp.datacite.DataciteModelConstants._
 import eu.dnetlib.dhp.schema.action.AtomicAction
 import eu.dnetlib.dhp.schema.common.ModelConstants
 import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, OafMapperUtils}
-import eu.dnetlib.dhp.schema.oaf.{AccessRight, Author, DataInfo, Instance, KeyValue, Oaf, OtherResearchProduct, Publication, Qualifier, Relation, Result, Software, StructuredProperty, Dataset => OafDataset}
+import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
 import eu.dnetlib.dhp.utils.DHPUtils
 import org.apache.commons.lang3.StringUtils
 import org.json4s.DefaultFormats
@@ -29,6 +29,7 @@ object DataciteToOAFTransformation {
   /**
    * This method should skip record if json contains invalid text
    * defined in gile datacite_filter
+   *
    * @param json
    * @return True if the record should be skipped
    */

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala

@@ -7,6 +7,7 @@ import org.json4s.DefaultFormats
 import org.json4s.JsonAST.{JField, JObject, JString}
 import org.json4s.jackson.JsonMethods.{compact, parse, render}
 import collection.JavaConverters._
+
 object BioDBToOAF {
 
   case class EBILinkItem(id: Long, links: String) {}

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala

@@ -1,9 +1,9 @@
 package eu.dnetlib.dhp.sx.bio
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
-import eu.dnetlib.dhp.schema.oaf.Oaf
-import BioDBToOAF.ScholixResolved
 import eu.dnetlib.dhp.collection.CollectionUtils
+import eu.dnetlib.dhp.schema.oaf.Oaf
+import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
 import org.apache.commons.io.IOUtils
 import org.apache.spark.SparkConf
 import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala

@@ -3,7 +3,7 @@ package eu.dnetlib.dhp.sx.bio.ebi
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
 import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
 import eu.dnetlib.dhp.schema.oaf.Result
-import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal, PMParser, PubMedToOaf}
+import eu.dnetlib.dhp.sx.bio.pubmed._
 import eu.dnetlib.dhp.utils.ISLookupClientFactory
 import org.apache.commons.io.IOUtils
 import org.apache.hadoop.conf.Configuration

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala

@@ -1,9 +1,8 @@
 package eu.dnetlib.dhp.sx.bio.ebi
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
-import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
 import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
-import eu.dnetlib.dhp.sx.bio.pubmed.PMJournal
+import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
 import org.apache.commons.io.IOUtils
 import org.apache.http.client.config.RequestConfig
 import org.apache.http.client.methods.HttpGet

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala

@@ -1,11 +1,10 @@
 package eu.dnetlib.dhp.sx.bio.ebi
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
+import eu.dnetlib.dhp.collection.CollectionUtils
 import eu.dnetlib.dhp.schema.oaf.Oaf
 import eu.dnetlib.dhp.sx.bio.BioDBToOAF
 import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
-import BioDBToOAF.EBILinkItem
-import eu.dnetlib.dhp.collection.CollectionUtils
 import org.apache.commons.io.IOUtils
 import org.apache.spark.SparkConf
 import org.apache.spark.sql._

dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala

@@ -4,7 +4,7 @@ import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
 import eu.dnetlib.dhp.schema.common.ModelConstants
 import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, IdentifierFactory, OafMapperUtils, PidType}
 import eu.dnetlib.dhp.schema.oaf._
-import scala.collection.JavaConverters._
+import collection.JavaConverters._
 
 import java.util.regex.Pattern
 
@@ -22,10 +22,10 @@ object PubMedToOaf {
   val collectedFrom: KeyValue = OafMapperUtils.keyValue(ModelConstants.EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central")
 
 
-
   /**
    * Cleaning the DOI Applying regex in order to
    * remove doi starting with URL
+   *
    * @param doi input DOI
    * @return cleaned DOI
    */
@@ -93,7 +93,6 @@ object PubMedToOaf {
    * @param vocabularyName the input vocabulary name
    * @param vocabularies   all the vocabularies
    * @param term           the term to find
-   *
    * @return the cleaned term value
    */
   def getVocabularyTerm(vocabularyName: String, vocabularies: VocabularyGroup, term: String): Qualifier = {
@@ -106,7 +105,6 @@ object PubMedToOaf {
   /**
    * Map the Pubmed Article into the OAF instance
    *
-   *
    * @param article      the pubmed articles
    * @param vocabularies the vocabularies
    * @return The OAF instance if the mapping did not fail
@@ -185,7 +183,6 @@ object PubMedToOaf {
     //--------------------------------------------------------------------------------------
 
 
-
     // RESULT MAPPING
     //--------------------------------------------------------------------------------------
     result.setDateofacceptance(OafMapperUtils.field(GraphCleaningFunctions.cleanDate(article.getDate), dataInfo))

dhp-workflows/dhp-aggregation/src/test/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTest.scala

@@ -8,6 +8,7 @@ import org.apache.commons.io.FileUtils
 import org.apache.spark.SparkConf
 import org.apache.spark.sql.functions.{col, count}
 import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
+import org.junit.jupiter.api.Assertions._
 import org.junit.jupiter.api.extension.ExtendWith
 import org.junit.jupiter.api.{AfterEach, BeforeEach, Test}
 import org.mockito.junit.jupiter.MockitoExtension
@@ -17,7 +18,6 @@ import java.nio.file.{Files, Path}
 import java.text.SimpleDateFormat
 import java.util.Locale
 import scala.io.Source
-import org.junit.jupiter.api.Assertions._
 
 @ExtendWith(Array(classOf[MockitoExtension]))
 class DataciteToOAFTest extends  AbstractVocabularyTest{