Compare commits
2 Commits
c40bf5ebfe
...
be4954b5ff
Author | SHA1 | Date |
---|---|---|
Miriam Baglioni | be4954b5ff | |
Miriam Baglioni | 0a2c28c620 |
|
@ -11,9 +11,9 @@ import com.fasterxml.jackson.annotation.JsonProperty;
|
|||
* @Date 01/09/23
|
||||
*/
|
||||
public class Relations implements Serializable {
|
||||
@JsonProperty("relation_type")
|
||||
|
||||
private String relation_type;
|
||||
@JsonProperty("product_list")
|
||||
|
||||
private List<String> products;
|
||||
|
||||
public static Relations newInstance(String relClass, List<String> target) {
|
||||
|
|
|
@ -16,15 +16,15 @@ public class ResearchProduct extends Entity implements Serializable {
|
|||
private List<Identifier> identifiers;
|
||||
private Map<String, List<String>> titles;
|
||||
private Map<String, List<String>> abstracts;
|
||||
@JsonProperty("product_type")
|
||||
|
||||
private String product_type;
|
||||
private List<ResultTopic> topics;
|
||||
private List<Contribution> contributions;
|
||||
private List<Manifestation> manifestations;
|
||||
@JsonProperty("relevant_organizations")
|
||||
|
||||
private List<String> relevant_organizations;
|
||||
private List<String> funding;
|
||||
@JsonProperty("related_products")
|
||||
|
||||
private List<Relations> related_products;
|
||||
|
||||
public ResearchProduct() {
|
||||
|
|
|
@ -143,7 +143,7 @@ public class DumpResearchProduct implements Serializable {
|
|||
(MapFunction<Tuple2<ResearchProduct, ProductsRelation>, ResearchProduct>) t2 -> {
|
||||
if (t2._2() == null)
|
||||
return t2._1();
|
||||
t2._1().setRelated_products(t2._2().getRelated_products());
|
||||
t2._1().setRelated_products(t2._2().getProducts());
|
||||
return t2._1();
|
||||
|
||||
}, Encoders.bean(ResearchProduct.class))
|
||||
|
|
|
@ -8,12 +8,9 @@ import java.util.*;
|
|||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaPairRDD;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.function.FilterFunction;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.api.java.function.MapGroupsFunction;
|
||||
import org.apache.spark.api.java.function.PairFunction;
|
||||
import org.apache.spark.sql.*;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
import org.apache.spark.sql.types.DataTypes;
|
||||
|
@ -21,18 +18,13 @@ import org.apache.spark.sql.types.StructType;
|
|||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.oa.graph.dump.skgif.beans.ExtendingOrganization;
|
||||
import eu.dnetlib.dhp.oa.graph.dump.skgif.beans.GrantRelation;
|
||||
import eu.dnetlib.dhp.oa.graph.dump.skgif.beans.ProductsRelation;
|
||||
import eu.dnetlib.dhp.oa.graph.dump.skgif.beans.RelationPerProduct;
|
||||
import eu.dnetlib.dhp.schema.oaf.*;
|
||||
import eu.dnetlib.dhp.schema.oaf.Organization;
|
||||
import eu.dnetlib.dhp.skgif.model.*;
|
||||
import scala.Tuple2;
|
||||
import scala.Tuple5;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
|
@ -183,7 +175,7 @@ public class SelectRelation implements Serializable {
|
|||
}
|
||||
|
||||
private static void addResulRelations(ProductsRelation pr, Iterator<Row> v) {
|
||||
pr.setRelated_products(new ArrayList<>());
|
||||
pr.setProducts(new ArrayList<>());
|
||||
Map<String, ArrayList<String>> hashMap = new HashMap<>();
|
||||
while (v.hasNext()) {
|
||||
Row next = v.next();
|
||||
|
@ -196,7 +188,7 @@ public class SelectRelation implements Serializable {
|
|||
hashMap
|
||||
.keySet()
|
||||
.stream()
|
||||
.forEach(key -> pr.getRelated_products().add(Relations.newInstance(key, hashMap.get(key))));
|
||||
.forEach(key -> pr.getProducts().add(Relations.newInstance(key, hashMap.get(key))));
|
||||
}
|
||||
|
||||
private static String convertToSkgIFSem(String sem) {
|
||||
|
|
|
@ -12,7 +12,7 @@ import eu.dnetlib.dhp.skgif.model.Relations;
|
|||
*/
|
||||
public class ProductsRelation implements Serializable {
|
||||
private String resultId;
|
||||
private java.util.List<Relations> related_products;
|
||||
private java.util.List<Relations> products;
|
||||
|
||||
public String getResultId() {
|
||||
return resultId;
|
||||
|
@ -22,11 +22,11 @@ public class ProductsRelation implements Serializable {
|
|||
this.resultId = resultId;
|
||||
}
|
||||
|
||||
public List<Relations> getRelated_products() {
|
||||
return related_products;
|
||||
public List<Relations> getProducts() {
|
||||
return products;
|
||||
}
|
||||
|
||||
public void setRelated_products(List<Relations> related_products) {
|
||||
this.related_products = related_products;
|
||||
public void setProducts(List<Relations> products) {
|
||||
this.products = products;
|
||||
}
|
||||
}
|
||||
|
|
|
@ -272,9 +272,9 @@
|
|||
<jar>dump-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-cores=4
|
||||
--executor-memory=5G
|
||||
--executor-memory=6G
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.executor.memoryOverhead=5G
|
||||
--conf spark.executor.memoryOverhead=6G
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
|
|
2
pom.xml
2
pom.xml
|
@ -103,7 +103,7 @@
|
|||
<junit-jupiter.version>5.6.1</junit-jupiter.version>
|
||||
<dhp.commons.lang.version>3.5</dhp.commons.lang.version>
|
||||
<dhp.guava.version>11.0.2</dhp.guava.version>
|
||||
<dhp-schemas.version>[6.1.1]</dhp-schemas.version>
|
||||
<dhp-schemas.version>[6.1.3]</dhp-schemas.version>
|
||||
</properties>
|
||||
|
||||
</project>
|
Loading…
Reference in New Issue