Merge branch 'beta' of https://code-repo.d4science.org/D-Net/dnet-hadoop into beta

dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java

@@ -13,6 +13,8 @@ import java.util.stream.Collectors;
 import java.util.stream.Stream;
 
 import org.apache.commons.lang3.StringUtils;
+import org.apache.spark.api.java.function.MapFunction;
+import org.apache.spark.sql.Encoders;
 
 import com.github.sisyphsu.dateparser.DateParserUtils;
 import com.google.common.collect.Lists;
@@ -23,8 +25,6 @@ import eu.dnetlib.dhp.schema.common.ModelConstants;
 import eu.dnetlib.dhp.schema.common.ModelSupport;
 import eu.dnetlib.dhp.schema.oaf.*;
 import me.xuender.unidecode.Unidecode;
-import org.apache.spark.api.java.function.MapFunction;
-import org.apache.spark.sql.Encoders;
 
 public class GraphCleaningFunctions extends CleaningFunctions {
 

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

@@ -27,7 +27,8 @@ object SparkCreateBaselineDataFrame {
   def requestBaseLineUpdatePage(maxFile: String): List[(String, String)] = {
     val data = requestPage("https://ftp.ncbi.nlm.nih.gov/pubmed/updatefiles/")
 
-    val result = data.linesWithSeparators.map(l =>l.stripLineEnd)
+    val result = data.linesWithSeparators
+      .map(l => l.stripLineEnd)
       .filter(l => l.startsWith("<a href="))
       .map { l =>
         val end = l.lastIndexOf("\">")

dhp-workflows/dhp-aggregation/src/test/scala/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala

@@ -63,7 +63,9 @@ class BioScholixTest extends AbstractVocabularyTest {
     val records: String = Source
       .fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/pubmed_dump"))
       .mkString
-    val r: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).toList
+    val r: List[Oaf] = records.linesWithSeparators
+      .map(l => l.stripLineEnd)
+      .toList
       .map(s => mapper.readValue(s, classOf[PMArticle]))
       .map(a => PubMedToOaf.convert(a, vocabularies))
     assertEquals(10, r.size)
@@ -173,9 +175,10 @@ class BioScholixTest extends AbstractVocabularyTest {
     val records: String = Source
       .fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/pdb_dump"))
       .mkString
-    records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
+    records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
 
-    val result: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).toList.flatMap(o => BioDBToOAF.pdbTOOaf(o))
+    val result: List[Oaf] =
+      records.linesWithSeparators.map(l => l.stripLineEnd).toList.flatMap(o => BioDBToOAF.pdbTOOaf(o))
 
     assertTrue(result.nonEmpty)
     result.foreach(r => assertNotNull(r))
@@ -194,9 +197,10 @@ class BioScholixTest extends AbstractVocabularyTest {
     val records: String = Source
       .fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/uniprot_dump"))
       .mkString
-    records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
+    records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
 
-    val result: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).toList.flatMap(o => BioDBToOAF.uniprotToOAF(o))
+    val result: List[Oaf] =
+      records.linesWithSeparators.map(l => l.stripLineEnd).toList.flatMap(o => BioDBToOAF.uniprotToOAF(o))
 
     assertTrue(result.nonEmpty)
     result.foreach(r => assertNotNull(r))
@@ -239,9 +243,10 @@ class BioScholixTest extends AbstractVocabularyTest {
     val records: String = Source
       .fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/crossref_links"))
       .mkString
-    records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
+    records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
 
-    val result: List[Oaf] = records.linesWithSeparators.map(l =>l.stripLineEnd).map(s => BioDBToOAF.crossrefLinksToOaf(s)).toList
+    val result: List[Oaf] =
+      records.linesWithSeparators.map(l => l.stripLineEnd).map(s => BioDBToOAF.crossrefLinksToOaf(s)).toList
 
     assertNotNull(result)
     assertTrue(result.nonEmpty)
@@ -276,14 +281,17 @@ class BioScholixTest extends AbstractVocabularyTest {
         getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/scholix_resolved")
       )
       .mkString
-    records.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
+    records.linesWithSeparators.map(l => l.stripLineEnd).foreach(s => assertTrue(s.nonEmpty))
 
     implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
 
-    val l: List[ScholixResolved] = records.linesWithSeparators.map(l =>l.stripLineEnd).map { input =>
+    val l: List[ScholixResolved] = records.linesWithSeparators
+      .map(l => l.stripLineEnd)
+      .map { input =>
         lazy val json = parse(input)
         json.extract[ScholixResolved]
-    }.toList
+      }
+      .toList
 
     val result: List[Oaf] = l.map(s => BioDBToOAF.scholixResolvedToOAF(s))
 

dhp-workflows/dhp-broker-events/src/main/java/eu/dnetlib/dhp/broker/oa/util/SubscriptionUtils.java

@@ -37,12 +37,24 @@ public class SubscriptionUtils {
 	}
 
 	public static boolean verifyDateRange(final long date, final String min, final String max) {
+
+		long from = 0;
+		long to = Long.MAX_VALUE;
+
 		try {
-			return date >= DateUtils.parseDate(min, "yyyy-MM-dd").getTime()
+			from = min != null ? DateUtils.parseDate(min, "yyyy-MM-dd").getTime() : 0;
-				&& date < DateUtils.parseDate(max, "yyyy-MM-dd").getTime() + ONE_DAY;
 		} catch (final ParseException e) {
-			return false;
+			from = 0;
 		}
+
+		try {
+			to = max != null ? DateUtils.parseDate(max, "yyyy-MM-dd").getTime() + ONE_DAY : Long.MAX_VALUE;
+		} catch (final ParseException e) {
+			to = Long.MAX_VALUE;
+		}
+
+		return date >= from && date < to;
+
 	}
 
 	public static boolean verifyExact(final String s1, final String s2) {

dhp-workflows/dhp-broker-events/src/test/java/eu/dnetlib/dhp/broker/oa/util/SubscriptionUtilsTest.java

@@ -41,6 +41,18 @@ public class SubscriptionUtilsTest {
 
 		assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", "2011-01-01"));
 		assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", "2021-01-01"));
+
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", "NULL"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "2010-01-01", null));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "NULL", "2011-01-01"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, null, "2011-01-01"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, "NULL", "NULL"));
+		assertTrue(SubscriptionUtils.verifyDateRange(date, null, null));
+
+		assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", null));
+		assertFalse(SubscriptionUtils.verifyDateRange(date, "2020-01-01", "NULL"));
+		assertFalse(SubscriptionUtils.verifyDateRange(date, null, "2005-01-01"));
+		assertFalse(SubscriptionUtils.verifyDateRange(date, "NULL", "2005-01-01"));
 	}
 
 	@Test

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

@@ -309,6 +309,8 @@ case object Crossref2Oaf {
       result
   }
 
+
+
   def generateAuhtor(given: String, family: String, orcid: String, index: Int): Author = {
     val a = new Author
     a.setName(given)
@@ -370,10 +372,57 @@ case object Crossref2Oaf {
       case dataset: Dataset         => convertDataset(dataset)
     }
 
+
+    val doisReference:List[String] = for {
+      JObject(reference_json) <- json \ "reference"
+      JField("DOI", JString(doi_json)) <- reference_json
+    } yield doi_json
+
+
+
+    if (doisReference!= null && doisReference.nonEmpty) {
+      val citation_relations:List[Relation] = generateCitationRelations(doisReference, result)
+      resultList = resultList ::: citation_relations
+    }
     resultList = resultList ::: List(result)
     resultList
   }
 
+
+
+  private def createCiteRelation(source:Result, targetPid:String, targetPidType:String) :List[Relation] = {
+
+
+    val targetId = IdentifierFactory.idFromPid("50",targetPidType, targetPid, true)
+
+    val from = new Relation
+    from.setSource(source.getId)
+    from.setTarget(targetId)
+    from.setRelType(ModelConstants.RESULT_RESULT)
+    from.setRelClass(ModelConstants.CITES)
+    from.setSubRelType(ModelConstants.CITATION)
+    from.setCollectedfrom(source.getCollectedfrom)
+    from.setDataInfo(source.getDataInfo)
+    from.setLastupdatetimestamp(source.getLastupdatetimestamp)
+
+
+    val to = new Relation
+    to.setTarget(source.getId)
+    to.setSource(targetId)
+    to.setRelType(ModelConstants.RESULT_RESULT)
+    to.setRelClass(ModelConstants.IS_CITED_BY)
+    to.setSubRelType(ModelConstants.CITATION)
+    to.setCollectedfrom(source.getCollectedfrom)
+    to.setDataInfo(source.getDataInfo)
+    to.setLastupdatetimestamp(source.getLastupdatetimestamp)
+
+    List(from,to)
+  }
+
+  def generateCitationRelations(dois:List[String], result:Result):List[Relation] = {
+    dois.flatMap(d => createCiteRelation(result, d, "doi"))
+  }
+
   def mappingFunderToRelations(
     funders: List[mappingFunder],
     sourceId: String,

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

@@ -1,9 +1,14 @@
 package eu.dnetlib.dhp.doiboost.crossref
 
+import eu.dnetlib.dhp.schema.common.ModelConstants
 import eu.dnetlib.dhp.schema.oaf._
 import eu.dnetlib.dhp.utils.DHPUtils
 import eu.dnetlib.doiboost.crossref.Crossref2Oaf
 import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
+import org.json4s
+import org.json4s.JsonAST.{JField, JObject, JString}
+import org.json4s.{DefaultFormats, JValue}
+import org.json4s.jackson.JsonMethods
 import org.junit.jupiter.api.Assertions._
 import org.junit.jupiter.api.Test
 import org.slf4j.{Logger, LoggerFactory}
@@ -31,13 +36,13 @@ class CrossrefMappingTest {
       .fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/funder_doi"))
       .mkString
 
-    for (line <- funder_doi.linesWithSeparators.map(l =>l.stripLineEnd)) {
+    for (line <- funder_doi.linesWithSeparators.map(l => l.stripLineEnd)) {
       val json = template.replace("%s", line)
       val resultList: List[Oaf] = Crossref2Oaf.convert(json)
       assertTrue(resultList.nonEmpty)
       checkRelation(resultList)
     }
-    for (line <- funder_name.linesWithSeparators.map(l =>l.stripLineEnd)) {
+    for (line <- funder_name.linesWithSeparators.map(l => l.stripLineEnd)) {
       val json = template.replace("%s", line)
       val resultList: List[Oaf] = Crossref2Oaf.convert(json)
       assertTrue(resultList.nonEmpty)
@@ -109,6 +114,44 @@ class CrossrefMappingTest {
 
   }
 
+
+  private def parseJson(input:String):JValue = {
+    implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
+    lazy val json: json4s.JValue = JsonMethods.parse(input)
+
+    json
+  }
+
+  @Test
+  def testCitationRelations():Unit =  {
+    val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_embargo.json")).mkString
+
+
+    assertNotNull(json)
+    assertFalse(json.isEmpty)
+
+    val result:List[Oaf] = Crossref2Oaf.convert(json)
+
+    assertTrue(result.nonEmpty)
+
+
+    val j = parseJson(json)
+
+    val doisReference: List[String] = for {
+      JObject(reference_json) <- j \ "reference"
+      JField("DOI", JString(doi_json)) <- reference_json
+    } yield doi_json
+
+
+
+    val relationList:List[Relation] = result.filter(s => s.isInstanceOf[Relation]).map(r=> r.asInstanceOf[Relation]).filter(r => r.getSubRelType.equalsIgnoreCase(ModelConstants.CITATION))
+
+    assertNotNull(relationList)
+    assertFalse(relationList.isEmpty)
+
+    assertEquals(doisReference.size*2, relationList.size)
+  }
+
   @Test
   def testEmptyTitle(): Unit = {
     val json = Source

dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/orcid/MappingORCIDToOAFTest.scala

@@ -25,7 +25,9 @@ class MappingORCIDToOAFTest {
       .mkString
     assertNotNull(json)
     assertFalse(json.isEmpty)
-    json.linesWithSeparators.map(l =>l.stripLineEnd).foreach(s => {
+    json.linesWithSeparators
+      .map(l => l.stripLineEnd)
+      .foreach(s => {
         assertNotNull(ORCIDToOAF.extractValueFromInputString(s))
       })
   }

dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/uw/UnpayWallMappingTest.scala

@@ -22,7 +22,7 @@ class UnpayWallMappingTest {
       .mkString
 
     var i: Int = 0
-    for (line <- Ilist.linesWithSeparators.map(l =>l.stripLineEnd)) {
+    for (line <- Ilist.linesWithSeparators.map(l => l.stripLineEnd)) {
       val p = UnpayWallToOAF.convertToOAF(line)
 
       if (p != null) {
@@ -43,7 +43,7 @@ class UnpayWallMappingTest {
       i = i + 1
     }
 
-    val l = Ilist.linesWithSeparators.map(l =>l.stripLineEnd).next()
+    val l = Ilist.linesWithSeparators.map(l => l.stripLineEnd).next()
 
     val item = UnpayWallToOAF.convertToOAF(l)
 

dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/clean/CleanCountryTest.java

@@ -5,7 +5,6 @@ import java.io.IOException;
 import java.nio.file.Files;
 import java.nio.file.Path;
 
-import eu.dnetlib.dhp.schema.oaf.Dataset;
 import org.apache.commons.io.FileUtils;
 import org.apache.spark.SparkConf;
 import org.apache.spark.api.java.JavaRDD;
@@ -27,6 +26,7 @@ import org.slf4j.LoggerFactory;
 import com.fasterxml.jackson.databind.ObjectMapper;
 
 import eu.dnetlib.dhp.oa.graph.clean.country.CleanCountrySparkJob;
+import eu.dnetlib.dhp.schema.oaf.Dataset;
 import eu.dnetlib.dhp.schema.oaf.Publication;
 
 public class CleanCountryTest {
@@ -185,7 +185,6 @@ public class CleanCountryTest {
 
 		Assertions.assertEquals(0, tmp.first().getCountry().size());
 
-
 	}
 
 }

dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/oa/graph/resolution/ResolveEntitiesTest.scala

@@ -53,7 +53,8 @@ class ResolveEntitiesTest extends Serializable {
   def generateUpdates(spark: SparkSession): Unit = {
     val template = Source.fromInputStream(this.getClass.getResourceAsStream("updates")).mkString
 
-    val pids: List[String] = template.linesWithSeparators.map(l =>l.stripLineEnd)
+    val pids: List[String] = template.linesWithSeparators
+      .map(l => l.stripLineEnd)
       .map { id =>
         val r = new Result
         r.setId(id.toLowerCase.trim)
@@ -127,7 +128,7 @@ class ResolveEntitiesTest extends Serializable {
     entities.foreach { e =>
       val template = Source.fromInputStream(this.getClass.getResourceAsStream(s"$e")).mkString
       spark
-        .createDataset(spark.sparkContext.parallelize(template.linesWithSeparators.map(l =>l.stripLineEnd).toList))
+        .createDataset(spark.sparkContext.parallelize(template.linesWithSeparators.map(l => l.stripLineEnd).toList))
         .as[String]
         .write
         .option("compression", "gzip")
@@ -264,7 +265,8 @@ class ResolveEntitiesTest extends Serializable {
       Source
         .fromInputStream(this.getClass.getResourceAsStream(s"publication"))
         .mkString
-        .linesWithSeparators.map(l =>l.stripLineEnd)
+        .linesWithSeparators
+        .map(l => l.stripLineEnd)
         .next(),
       classOf[Publication]
     )

dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/sx/graph/scholix/ScholixGraphTest.scala

@@ -47,7 +47,7 @@ class ScholixGraphTest extends AbstractVocabularyTest {
     val inputRelations = Source
       .fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/oaf_to_summary"))
       .mkString
-    val items = inputRelations.linesWithSeparators.map(l =>l.stripLineEnd).toList
+    val items = inputRelations.linesWithSeparators.map(l => l.stripLineEnd).toList
     assertNotNull(items)
     items.foreach(i => assertTrue(i.nonEmpty))
     val result =
@@ -69,7 +69,8 @@ class ScholixGraphTest extends AbstractVocabularyTest {
         getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/merge_result_scholix")
       )
       .mkString
-    val result: List[(Relation, ScholixSummary)] = inputRelations.linesWithSeparators.map(l =>l.stripLineEnd)
+    val result: List[(Relation, ScholixSummary)] = inputRelations.linesWithSeparators
+      .map(l => l.stripLineEnd)
       .sliding(2)
       .map(s => (s.head, s(1)))
       .map(p => (mapper.readValue(p._1, classOf[Relation]), mapper.readValue(p._2, classOf[ScholixSummary])))