extended the model to accomodate the new entities and relation to be dumped

This commit is contained in:
Miriam Baglioni 2023-10-25 11:59:16 +02:00
parent 25267c1689
commit 8d83b5173c
6 changed files with 46 additions and 13 deletions

View File

@ -1,6 +1,11 @@
package eu.dnetlib.dhp.eosc.model; package eu.dnetlib.dhp.eosc.model;
/**
* @author miriam.baglioni
* @Date 25/10/23
*/
/** /**
* @author miriam.baglioni * @author miriam.baglioni
* @Date 25/10/23 * @Date 25/10/23

View File

@ -1,6 +1,11 @@
package eu.dnetlib.dhp.eosc.model; package eu.dnetlib.dhp.eosc.model;
/**
* @author miriam.baglioni
* @Date 25/10/23
*/
/** /**
* @author miriam.baglioni * @author miriam.baglioni
* @Date 25/10/23 * @Date 25/10/23

View File

@ -1,6 +1,11 @@
package eu.dnetlib.dhp.eosc.model; package eu.dnetlib.dhp.eosc.model;
/**
* @author miriam.baglioni
* @Date 25/10/23
*/
/** /**
* @author miriam.baglioni * @author miriam.baglioni
* @Date 25/10/23 * @Date 25/10/23

View File

@ -1,6 +1,11 @@
package eu.dnetlib.dhp.eosc.model; package eu.dnetlib.dhp.eosc.model;
/**
* @author miriam.baglioni
* @Date 25/10/23
*/
/** /**
* @author miriam.baglioni * @author miriam.baglioni
* @Date 25/10/23 * @Date 25/10/23

View File

@ -1,6 +1,11 @@
package eu.dnetlib.dhp.eosc.model; package eu.dnetlib.dhp.eosc.model;
/**
* @author miriam.baglioni
* @Date 25/10/23
*/
/** /**
* @author miriam.baglioni * @author miriam.baglioni
* @Date 25/10/23 * @Date 25/10/23

View File

@ -6,9 +6,6 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable; import java.io.Serializable;
import java.util.Optional; import java.util.Optional;
import eu.dnetlib.dhp.eosc.model.Organization;
import eu.dnetlib.dhp.eosc.model.Project;
import eu.dnetlib.dhp.schema.common.ModelConstants;
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.api.java.function.FilterFunction; import org.apache.spark.api.java.function.FilterFunction;
@ -21,8 +18,11 @@ import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.eosc.model.Organization;
import eu.dnetlib.dhp.eosc.model.Project;
import eu.dnetlib.dhp.eosc.model.Provenance; import eu.dnetlib.dhp.eosc.model.Provenance;
import eu.dnetlib.dhp.eosc.model.RelType; import eu.dnetlib.dhp.eosc.model.RelType;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.DataInfo; import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
import scala.Tuple2; import scala.Tuple2;
@ -74,18 +74,26 @@ public class SparkDumpOrganizationProject implements Serializable {
Dataset<Organization> organization = Utils.readPath(spark, outputPath + "organization", Organization.class); Dataset<Organization> organization = Utils.readPath(spark, outputPath + "organization", Organization.class);
Dataset<Project> project = Utils.readPath(spark, outputPath + "project", Project.class); Dataset<Project> project = Utils.readPath(spark, outputPath + "project", Project.class);
Dataset<Relation> relation = Utils.readPath(spark, inputPath + "/relation", Relation.class) Dataset<Relation> relation = Utils
.filter((FilterFunction<Relation>) r-> !r.getDataInfo().getDeletedbyinference() && r.getRelClass().equalsIgnoreCase(ModelConstants.IS_PARTICIPANT)); .readPath(spark, inputPath + "/relation", Relation.class)
.filter(
(FilterFunction<Relation>) r -> !r.getDataInfo().getDeletedbyinference()
&& r.getRelClass().equalsIgnoreCase(ModelConstants.IS_PARTICIPANT));
Dataset<Relation> eoscOrgs = relation.joinWith(organization, relation.col("source").equalTo(organization.col("id"))) Dataset<Relation> eoscOrgs = relation
.map((MapFunction<Tuple2<Relation, Organization>, Relation>) t2 -> t2._1(), Encoders.bean(Relation.class)); .joinWith(organization, relation.col("source").equalTo(organization.col("id")))
.map((MapFunction<Tuple2<Relation, Organization>, Relation>) t2 -> t2._1(), Encoders.bean(Relation.class));
eoscOrgs.joinWith(project, eoscOrgs.col("target").equalTo(project.col("id"))) eoscOrgs
.map((MapFunction<Tuple2<Relation, Project>, eu.dnetlib.dhp.eosc.model.Relation>) t2-> eu.dnetlib.dhp.eosc.model.Relation.newInstance(t2._1().getSource(), t2._1().getTarget()), Encoders.bean(eu.dnetlib.dhp.eosc.model.Relation.class)) .joinWith(project, eoscOrgs.col("target").equalTo(project.col("id")))
.write() .map(
.mode(SaveMode.Overwrite) (MapFunction<Tuple2<Relation, Project>, eu.dnetlib.dhp.eosc.model.Relation>) t2 -> eu.dnetlib.dhp.eosc.model.Relation
.option("compression","gzip") .newInstance(t2._1().getSource(), t2._1().getTarget()),
.json(outputPath + "organizationProject"); Encoders.bean(eu.dnetlib.dhp.eosc.model.Relation.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "organizationProject");
} }