From 075055eacae02603c18b29895074a80aa1d859db Mon Sep 17 00:00:00 2001 From: Sandro La Bruzzo Date: Tue, 29 Jun 2021 10:33:09 +0200 Subject: [PATCH] added relation dates in bio mapping --- .../eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala | 24 +++++++++++-------- .../dhp/sx/bio/pubmed/BioScholixTest.scala | 9 ++++--- 2 files changed, 18 insertions(+), 15 deletions(-) diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala index 2422a25db..ce4b55684 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala +++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala @@ -77,7 +77,9 @@ object BioDBToOAF { val relation_semantic= (json \ "RelationshipType" \ "Name").extract[String] - createRelation(target_pid, target_pid_type, generate_unresolved_id(source_pid, source_pid_type),collectedFromMap("elsevier"),"relationship", relation_semantic) + val date = (json \ "LinkedPublicationDate").extract[String] + + createRelation(target_pid, target_pid_type, generate_unresolved_id(source_pid, source_pid_type),collectedFromMap("elsevier"),"relationship", relation_semantic, date) } @@ -186,10 +188,10 @@ object BioDBToOAF { OafMapperUtils.structuredProperty(s, SUBJ_CLASS, SUBJ_CLASS, ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES, null) ).asJava) } - + var i_date:Option[UniprotDate] = None if (dates.nonEmpty) { - val i_date = dates.find(d => d.date_info.contains("entry version")) + i_date = dates.find(d => d.date_info.contains("entry version")) if (i_date.isDefined) { i.setDateofacceptance(OafMapperUtils.field(i_date.get.date, DATA_INFO)) d.setDateofacceptance(OafMapperUtils.field(i_date.get.date, DATA_INFO)) @@ -214,12 +216,12 @@ object BioDBToOAF { if (references_pmid != null && references_pmid.nonEmpty) { - val rel = createRelation(references_pmid.head, "pmid", d.getId, collectedFromMap("uniprot"), "relationship", "isRelatedTo") + val rel = createRelation(references_pmid.head, "pmid", d.getId, collectedFromMap("uniprot"), "relationship", "isRelatedTo", if (i_date.isDefined) i_date.get.date else null) rel.getCollectedfrom List(d, rel) } else if (references_doi != null && references_doi.nonEmpty) { - val rel = createRelation(references_doi.head, "doi", d.getId, collectedFromMap("uniprot"), "relationship", "isRelatedTo") + val rel = createRelation(references_doi.head, "doi", d.getId, collectedFromMap("uniprot"), "relationship", "isRelatedTo", if (i_date.isDefined) i_date.get.date else null) List(d, rel) } else @@ -233,7 +235,7 @@ object BioDBToOAF { } - def createRelation(pid: String, pidType: String, sourceId: String, collectedFrom: KeyValue, subRelType:String, relClass:String):Relation = { + def createRelation(pid: String, pidType: String, sourceId: String, collectedFrom: KeyValue, subRelType:String, relClass:String, date:String):Relation = { val rel = new Relation rel.setCollectedfrom(List(collectedFromMap("pdb")).asJava) @@ -246,6 +248,8 @@ object BioDBToOAF { rel.setSource(sourceId) rel.setTarget(s"unresolved::$pid::$pidType") + rel.setValidationDate(date) + rel.getTarget.startsWith("unresolved") rel.setCollectedfrom(List(collectedFrom).asJava) rel @@ -253,8 +257,8 @@ object BioDBToOAF { } - def createSupplementaryRelation(pid: String, pidType: String, sourceId: String, collectedFrom: KeyValue): Relation = { - createRelation(pid,pidType,sourceId,collectedFrom, "supplement","IsSupplementTo") + def createSupplementaryRelation(pid: String, pidType: String, sourceId: String, collectedFrom: KeyValue, date:String): Relation = { + createRelation(pid,pidType,sourceId,collectedFrom, "supplement","IsSupplementTo", date) } @@ -311,7 +315,7 @@ object BioDBToOAF { val pmid = (json \ "pmid").extractOrElse[String](null) if (pmid != null) - List(d, createSupplementaryRelation(pmid, "pmid", d.getId, collectedFromMap("pdb"))) + List(d, createSupplementaryRelation(pmid, "pmid", d.getId, collectedFromMap("pdb"), null)) else List(d) } @@ -383,6 +387,6 @@ object BioDBToOAF { i.setDateofacceptance(OafMapperUtils.field(input.date, DATA_INFO)) d.setDateofacceptance(OafMapperUtils.field(input.date, DATA_INFO)) - List(d, createRelation(input.pmid, "pmid", d.getId, collectedFromMap("ebi"),"relationship", "isRelatedTo")) + List(d, createRelation(input.pmid, "pmid", d.getId, collectedFromMap("ebi"),"relationship", "isRelatedTo", input.date)) } } diff --git a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/sx/bio/pubmed/BioScholixTest.scala b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/sx/bio/pubmed/BioScholixTest.scala index a23c6530f..de13a08d6 100644 --- a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/sx/bio/pubmed/BioScholixTest.scala +++ b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/sx/bio/pubmed/BioScholixTest.scala @@ -4,20 +4,19 @@ import com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper, Ser import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result} import eu.dnetlib.dhp.sx.bio.BioDBToOAF import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved -import eu.dnetlib.dhp.sx.ebi.SparkEBILinksToOaf +import org.json4s.DefaultFormats +import org.json4s.JsonAST.{JField, JObject, JString} +import org.json4s.jackson.JsonMethods.parse import org.junit.jupiter.api.Assertions._ import org.junit.jupiter.api.extension.ExtendWith import org.junit.jupiter.api.{BeforeEach, Test} import org.mockito.junit.jupiter.MockitoExtension -import java.io.{BufferedReader, FileInputStream, InputStream, InputStreamReader} +import java.io.{BufferedReader, InputStream, InputStreamReader} import java.util.zip.GZIPInputStream import scala.collection.JavaConverters._ import scala.io.Source import scala.xml.pull.XMLEventReader -import org.json4s.DefaultFormats -import org.json4s.JsonAST.{JField, JObject, JString} -import org.json4s.jackson.JsonMethods.parse @ExtendWith(Array(classOf[MockitoExtension])) class BioScholixTest extends AbstractVocabularyTest{