Merge branch 'beta' into stats_with_spark_sql

dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/Crossref2Oaf.scala

@@ -25,7 +25,7 @@ case class mappingAffiliation(name: String) {}
 
 case class mappingAuthor(
   given: Option[String],
-  family: String,
+  family: Option[String],
   sequence: Option[String],
   ORCID: Option[String],
   affiliation: Option[mappingAffiliation]
@@ -226,14 +226,14 @@ case object Crossref2Oaf {
 
     //Mapping Author
     val authorList: List[mappingAuthor] =
-      (json \ "author").extractOrElse[List[mappingAuthor]](List())
+      (json \ "author").extract[List[mappingAuthor]].filter(a => a.family.isDefined)
 
     val sorted_list = authorList.sortWith((a: mappingAuthor, b: mappingAuthor) =>
       a.sequence.isDefined && a.sequence.get.equalsIgnoreCase("first")
     )
 
     result.setAuthor(sorted_list.zipWithIndex.map { case (a, index) =>
-      generateAuhtor(a.given.orNull, a.family, a.ORCID.orNull, index)
+      generateAuhtor(a.given.orNull, a.family.get, a.ORCID.orNull, index)
     }.asJava)
 
     // Mapping instance

dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala

@@ -22,6 +22,13 @@ class CrossrefMappingTest {
   val logger: Logger = LoggerFactory.getLogger(Crossref2Oaf.getClass)
   val mapper = new ObjectMapper()
 
+  @Test
+  def testMissingAuthorParser():Unit = {
+    val json: String = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/s41567-022-01757-y.json")).mkString
+    val result = Crossref2Oaf.convert(json)
+    result.filter(o => o.isInstanceOf[Publication]).map(p=> p.asInstanceOf[Publication]).foreach(p =>assertTrue(p.getAuthor.size()>0))
+  }
+
   @Test
   def testFunderRelationshipsMapping(): Unit = {
     val template = Source