This commit is contained in:
Claudio Atzori 2021-10-19 16:09:54 +02:00
commit c8850456e9
22 changed files with 294 additions and 418 deletions

View File

@ -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.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, OafMapperUtils} import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, OafMapperUtils}

View File

@ -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.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.Oaf 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.commons.io.IOUtils
import org.apache.spark.SparkConf import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession} import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
@ -13,7 +13,7 @@ object SparkTransformBioDatabaseToOAF {
def main(args: Array[String]): Unit = { def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf() val conf: SparkConf = new SparkConf()
val log: Logger = LoggerFactory.getLogger(getClass) 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) parser.parseArgument(args)
val database: String = parser.get("database") val database: String = parser.get("database")
log.info("database: {}", database) log.info("database: {}", database)

View File

@ -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.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.oaf.Result 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.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.commons.io.IOUtils
import org.apache.hadoop.conf.Configuration import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FSDataOutputStream, FileSystem, Path} import org.apache.hadoop.fs.{FSDataOutputStream, FileSystem, Path}

View File

@ -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.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.commons.io.IOUtils
import org.apache.http.client.config.RequestConfig import org.apache.http.client.config.RequestConfig
import org.apache.http.client.methods.HttpGet import org.apache.http.client.methods.HttpGet

View File

@ -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.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.Oaf 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.commons.io.IOUtils
import org.apache.spark.SparkConf import org.apache.spark.SparkConf
import org.apache.spark.sql._ import org.apache.spark.sql._

View File

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

View File

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

View File

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

View File

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

View File

@ -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.MetaData
import scala.xml.pull.{EvElemEnd, EvElemStart, EvText, XMLEventReader} import scala.xml.pull.{EvElemEnd, EvElemStart, EvText, XMLEventReader}

View File

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

View File

@ -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.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.common.ModelConstants import eu.dnetlib.dhp.schema.common.ModelConstants

View File

@ -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>

View File

@ -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 com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper, SerializationFeature}
import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest
import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result} 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.DefaultFormats
import org.json4s.JsonAST.{JField, JObject, JString} import org.json4s.JsonAST.{JField, JObject, JString}
import org.json4s.jackson.JsonMethods.parse import org.json4s.jackson.JsonMethods.parse

View File

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

View File

@ -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>

View File

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

View File

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

View File

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