sabeel
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

renamed wrong package, implemented last aggregation workflow for scholexplorer

This commit is contained in:
Sandro La Bruzzo 2021-10-15 15:00:15 +02:00
parent 51a03c0a50
commit 7b15b88d4c
17 changed files with 75 additions and 199 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/BioDBToOAF.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala
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.oaf.utils.{GraphCleaningFunctions, OafMapperUtils}

6
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala
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.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)

4
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala
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.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}

7
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala
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.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem
import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
import eu.dnetlib.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

7
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala
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.schema.oaf.Oaf
import eu.dnetllib.dhp.sx.bio.BioDBToOAF
import eu.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem
import eu.dnetlib.dhp.sx.bio.BioDBToOAF
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._

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMArticle.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMArticle.java
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.util.ArrayList;

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMAuthor.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMAuthor.java
View File

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

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMGrant.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMGrant.java
View File

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

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMJournal.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMJournal.java
View File

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

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMParser.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMParser.scala
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.pull.{EvElemEnd, EvElemStart, EvText, XMLEventReader}

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMSubject.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMSubject.java
View File

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

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PubMedToOaf.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala
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.schema.common.ModelConstants

0
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/config-default.xml → dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/config-default.xml
View File

51
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/workflow.xml Normal file
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>

0
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/bio_to_oaf_params.json → dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json
View File

6
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetllib/dhp/sx/bio/BioScholixTest.scala → dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala
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 eu.dnetlib.dhp.aggregation.AbstractVocabularyTest
import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result}
import eu.dnetllib.dhp.sx.bio.BioDBToOAF.ScholixResolved
import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf}
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
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

177
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml
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>