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

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

@@ -1,4 +1,4 @@
-package eu.dnetllib.dhp.sx.bio
+package eu.dnetlib.dhp.sx.bio
 
 import eu.dnetlib.dhp.schema.common.ModelConstants
 import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, OafMapperUtils}

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

@@ -1,8 +1,8 @@
-package eu.dnetllib.dhp.sx.bio
+package eu.dnetlib.dhp.sx.bio
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
 import eu.dnetlib.dhp.schema.oaf.Oaf
-import eu.dnetllib.dhp.sx.bio.BioDBToOAF.ScholixResolved
+import BioDBToOAF.ScholixResolved
 import org.apache.commons.io.IOUtils
 import org.apache.spark.SparkConf
 import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
@@ -13,7 +13,7 @@ object SparkTransformBioDatabaseToOAF {
   def main(args: Array[String]): Unit = {
     val conf: SparkConf = new SparkConf()
     val log: Logger = LoggerFactory.getLogger(getClass)
-    val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/bio_to_oaf_params.json")))
+    val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json")))
     parser.parseArgument(args)
     val database: String = parser.get("database")
     log.info("database: {}", database)

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

@@ -1,10 +1,10 @@
-package eu.dnetllib.dhp.sx.bio.ebi
+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.utils.ISLookupClientFactory
-import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal, PMParser, PubMedToOaf}
 import org.apache.commons.io.IOUtils
 import org.apache.hadoop.conf.Configuration
 import org.apache.hadoop.fs.{FSDataOutputStream, FileSystem, Path}

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

@@ -1,8 +1,9 @@
-package eu.dnetllib.dhp.sx.bio.ebi
+package eu.dnetlib.dhp.sx.bio.ebi
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
-import eu.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem
+import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
-import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
+import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
+import eu.dnetlib.dhp.sx.bio.pubmed.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/java/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala

@@ -1,9 +1,10 @@
-package eu.dnetllib.dhp.sx.bio.ebi
+package eu.dnetlib.dhp.sx.bio.ebi
 
 import eu.dnetlib.dhp.application.ArgumentApplicationParser
 import eu.dnetlib.dhp.schema.oaf.Oaf
-import eu.dnetllib.dhp.sx.bio.BioDBToOAF
+import eu.dnetlib.dhp.sx.bio.BioDBToOAF
-import eu.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem
+import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
+import BioDBToOAF.EBILinkItem
 import org.apache.commons.io.IOUtils
 import org.apache.spark.SparkConf
 import org.apache.spark.sql._

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMArticle.java

@@ -1,5 +1,5 @@
 
-package eu.dnetllib.dhp.sx.bio.pubmed;
+package eu.dnetlib.dhp.sx.bio.pubmed;
 
 import java.io.Serializable;
 import java.util.ArrayList;

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMAuthor.java

@@ -1,5 +1,5 @@
 
-package eu.dnetllib.dhp.sx.bio.pubmed;
+package eu.dnetlib.dhp.sx.bio.pubmed;
 
 import java.io.Serializable;
 

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMGrant.java

@@ -1,5 +1,5 @@
 
-package eu.dnetllib.dhp.sx.bio.pubmed;
+package eu.dnetlib.dhp.sx.bio.pubmed;
 
 public class PMGrant {
 

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMJournal.java

@@ -1,5 +1,5 @@
 
-package eu.dnetllib.dhp.sx.bio.pubmed;
+package eu.dnetlib.dhp.sx.bio.pubmed;
 
 import java.io.Serializable;
 

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

@@ -1,4 +1,4 @@
-package eu.dnetllib.dhp.sx.bio.pubmed
+package eu.dnetlib.dhp.sx.bio.pubmed
 
 import scala.xml.MetaData
 import scala.xml.pull.{EvElemEnd, EvElemStart, EvText, XMLEventReader}

dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMSubject.java

@@ -1,5 +1,5 @@
 
-package eu.dnetllib.dhp.sx.bio.pubmed;
+package eu.dnetlib.dhp.sx.bio.pubmed;
 
 public class PMSubject {
 	private String value;

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

@@ -1,4 +1,4 @@
-package eu.dnetllib.dhp.sx.bio.pubmed
+package eu.dnetlib.dhp.sx.bio.pubmed
 
 import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
 import eu.dnetlib.dhp.schema.common.ModelConstants

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

@@ -0,0 +1,51 @@
+    <workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
+    <parameters>
+        <property>
+            <name>sourcePath</name>
+            <description>the PDB Database Working Path</description>
+        </property>
+        <property>
+            <name>database</name>
+            <description>the PDB Database Working Path</description>
+        </property>
+
+        <property>
+            <name>targetPath</name>
+            <description>the Target Working dir path</description>
+        </property>
+    </parameters>
+
+    <start to="ConvertDB"/>
+
+    <kill name="Kill">
+        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
+    </kill>
+
+    <action name="ConvertDB">
+        <spark xmlns="uri:oozie:spark-action:0.2">
+            <master>yarn</master>
+            <mode>cluster</mode>
+            <name>Convert Bio DB to OAF Dataset</name>
+            <class>eu.dnetlib.dhp.sx.bio.SparkTransformBioDatabaseToOAF</class>
+            <jar>dhp-aggregation-${projectVersion}.jar</jar>
+            <spark-opts>
+                --executor-memory=${sparkExecutorMemory}
+                --executor-cores=${sparkExecutorCores}
+                --driver-memory=${sparkDriverMemory}
+                --conf spark.extraListeners=${spark2ExtraListeners}
+                --conf spark.sql.shuffle.partitions=2000
+                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
+                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
+                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
+            </spark-opts>
+            <arg>--master</arg><arg>yarn</arg>
+            <arg>--dbPath</arg><arg>${sourcePath}</arg>
+            <arg>--database</arg><arg>${database}</arg>
+            <arg>--targetPath</arg><arg>${targetPath}</arg>
+        </spark>
+        <ok to="End"/>
+        <error to="Kill"/>
+    </action>
+    <end name="End"/>
+
+</workflow-app>

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

@@ -1,10 +1,10 @@
-package eu.dnetllib.dhp.sx.bio
+package eu.dnetlib.dhp.sx.bio
 
 import com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper, SerializationFeature}
 import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest
 import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result}
-import eu.dnetllib.dhp.sx.bio.BioDBToOAF.ScholixResolved
+import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
-import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf}
+import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf}
 import org.json4s.DefaultFormats
 import org.json4s.JsonAST.{JField, JObject, JString}
 import org.json4s.jackson.JsonMethods.parse

dhp-workflows/dhp-blacklist/src/main/java/eu/dnetlib/dhp/blacklist/ReadBlacklistFromDB.java

@@ -91,8 +91,8 @@ public class ReadBlacklistFromDB implements Closeable {
 
 			String encoding = rs.getString("relationship");
 			RelationInverse ri = ModelSupport.relationInverseMap.get(encoding);
-			direct.setRelClass(ri.getRelation());
+			direct.setRelClass(ri.getRelClass());
-			inverse.setRelClass(ri.getInverse());
+			inverse.setRelClass(ri.getInverseRelClass());
 			direct.setRelType(ri.getRelType());
 			inverse.setRelType(ri.getRelType());
 			direct.setSubRelType(ri.getSubReltype());

dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml

@@ -1,177 +0,0 @@
-    <workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
-    <parameters>
-        <property>
-            <name>PDBPath</name>
-            <description>the PDB Database Working Path</description>
-        </property>
-
-        <property>
-            <name>UNIPROTDBPath</name>
-            <description>the UNIPROT Database Working Path</description>
-        </property>
-
-        <property>
-            <name>EBIDataset</name>
-            <description>the EBI Links Dataset  Path</description>
-        </property>
-
-        <property>
-            <name>ScholixResolvedDBPath</name>
-            <description>the Scholix Resolved Dataset  Path</description>
-        </property>
-
-        <property>
-            <name>CrossrefLinksPath</name>
-            <description>the CrossrefLinks Path</description>
-        </property>
-        <property>
-            <name>targetPath</name>
-            <description>the Target Working dir path</description>
-        </property>
-    </parameters>
-
-    <start to="ConvertPDB"/>
-
-    <kill name="Kill">
-        <message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
-    </kill>
-
-    <action name="ConvertPDB">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Convert PDB to OAF Dataset</name>
-            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.shuffle.partitions=2000
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-            </spark-opts>
-            <arg>--master</arg><arg>yarn</arg>
-            <arg>--dbPath</arg><arg>${PDBPath}</arg>
-            <arg>--database</arg><arg>PDB</arg>
-            <arg>--targetPath</arg><arg>${targetPath}/pdb_OAF</arg>
-        </spark>
-        <ok to="ConvertUNIPROT"/>
-        <error to="Kill"/>
-    </action>
-
-
-    <action name="ConvertUNIPROT">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Convert UNIPROT to OAF Dataset</name>
-            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.shuffle.partitions=2000
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-            </spark-opts>
-            <arg>--master</arg><arg>yarn</arg>
-            <arg>--dbPath</arg><arg>${UNIPROTDBPath}</arg>
-            <arg>--database</arg><arg>UNIPROT</arg>
-            <arg>--targetPath</arg><arg>${targetPath}/uniprot_OAF</arg>
-        </spark>
-        <ok to="ConvertEBILinks"/>
-        <error to="Kill"/>
-    </action>
-
-
-    <action name="ConvertEBILinks">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Convert EBI Links to OAF Dataset</name>
-            <class>eu.dnetlib.dhp.sx.graph.ebi.SparkEBILinksToOaf</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.shuffle.partitions=2000
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-            </spark-opts>
-            <arg>--master</arg><arg>yarn</arg>
-            <arg>--sourcePath</arg><arg>${EBIDataset}</arg>
-            <arg>--targetPath</arg><arg>${targetPath}/ebi_OAF</arg>
-        </spark>
-        <ok to="ConvertScholixResolved"/>
-        <error to="Kill"/>
-    </action>
-
-
-    <action name="ConvertScholixResolved">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Convert Scholix to OAF Dataset</name>
-            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.shuffle.partitions=2000
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-            </spark-opts>
-            <arg>--master</arg><arg>yarn</arg>
-            <arg>--dbPath</arg><arg>${ScholixResolvedDBPath}</arg>
-            <arg>--database</arg><arg>SCHOLIX</arg>
-            <arg>--targetPath</arg><arg>${targetPath}/scholix_resolved_OAF</arg>
-        </spark>
-        <ok to="ConvertCrossrefLinks"/>
-        <error to="Kill"/>
-    </action>
-
-
-    <action name="ConvertCrossrefLinks">
-        <spark xmlns="uri:oozie:spark-action:0.2">
-            <master>yarn</master>
-            <mode>cluster</mode>
-            <name>Convert Crossref Links to OAF Dataset</name>
-            <class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
-            <jar>dhp-graph-mapper-${projectVersion}.jar</jar>
-            <spark-opts>
-                --executor-memory=${sparkExecutorMemory}
-                --executor-cores=${sparkExecutorCores}
-                --driver-memory=${sparkDriverMemory}
-                --conf spark.extraListeners=${spark2ExtraListeners}
-                --conf spark.sql.shuffle.partitions=2000
-                --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
-                --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
-                --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
-            </spark-opts>
-            <arg>--master</arg><arg>yarn</arg>
-            <arg>--dbPath</arg><arg>${CrossrefLinksPath}</arg>
-            <arg>--database</arg><arg>CROSSREF_LINKS</arg>
-            <arg>--targetPath</arg><arg>${targetPath}/crossref_unresolved_relation_OAF</arg>
-        </spark>
-        <ok to="End"/>
-        <error to="Kill"/>
-    </action>
-
-
-
-
-    <end name="End"/>
-
-</workflow-app>

dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/SolrConfigExploreTest.java

@@ -74,7 +74,6 @@ public class SolrConfigExploreTest extends SolrExploreTest {
 			.config(conf)
 			.getOrCreate();
 
-
 	}
 
 	@AfterAll
@@ -87,7 +86,8 @@ public class SolrConfigExploreTest extends SolrExploreTest {
 
 		String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
 
-        new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null).run(isLookupClient);
+		new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null)
+			.run(isLookupClient);
 		Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
 
 		String[] queryStrings = {
@@ -108,7 +108,8 @@ public class SolrConfigExploreTest extends SolrExploreTest {
 //            System.out.println(rsp.getExplainMap());
 
 			for (SolrDocument doc : rsp.getResults()) {
-                System.out.println(
+				System.out
+					.println(
 						doc.get("score") + "\t" +
 							doc.get("__indexrecordidentifier") + "\t" +
 							doc.get("resultidentifier") + "\t" +
@@ -118,8 +119,7 @@ public class SolrConfigExploreTest extends SolrExploreTest {
 							doc.get("resulttitle") + "\t" +
 							doc.get("relprojectname") + "\t" +
 							doc.get("resultdescription") + "\t" +
-                        doc.get("__all") + "\t"
+							doc.get("__all") + "\t");
-                );
 			}
 		}
 	}

dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/SolrConfigTest.java

@@ -83,7 +83,6 @@ public class SolrConfigTest extends SolrTest {
 			.config(conf)
 			.getOrCreate();
 
-
 	}
 
 	@AfterAll
@@ -96,7 +95,8 @@ public class SolrConfigTest extends SolrTest {
 
 		String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
 
-        new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null).run(isLookupClient);
+		new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null)
+			.run(isLookupClient);
 		Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
 
 		String[] queryStrings = {
@@ -113,7 +113,8 @@ public class SolrConfigTest extends SolrTest {
 			QueryResponse rsp = miniCluster.getSolrClient().query(query);
 
 			for (SolrDocument doc : rsp.getResults()) {
-                System.out.println(
+				System.out
+					.println(
 						doc.get("score") + "\t" +
 							doc.get("__indexrecordidentifier") + "\t" +
 							doc.get("resultidentifier") + "\t" +
@@ -123,8 +124,7 @@ public class SolrConfigTest extends SolrTest {
 							doc.get("resulttitle") + "\t" +
 							doc.get("relprojectname") + "\t" +
 							doc.get("resultdescription") + "\t" +
-                        doc.get("__all") + "\t"
+							doc.get("__all") + "\t");
-                );
 			}
 		}
 	}

pom.xml

@@ -753,7 +753,7 @@
 		<mockito-core.version>3.3.3</mockito-core.version>
 		<mongodb.driver.version>3.4.2</mongodb.driver.version>
 		<vtd.version>[2.12,3.0)</vtd.version>
-		<dhp-schemas.version>[2.8.20]</dhp-schemas.version>
+		<dhp-schemas.version>[2.8.21]</dhp-schemas.version>
 		<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
 		<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
 		<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>