andreas.czerniak
/
BrBETA_dnet-hadoop
forked from D-Net/dnet-hadoop
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

relations for openorgs: not it choose only one master

This commit is contained in:
miconis 2020-11-05 15:48:42 +01:00
parent c4a59d1b9a
commit 1699d41d39
1 changed files with 26 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkPrepareOrgRels.java
View File

@ -1,13 +1,9 @@
package eu.dnetlib.dhp.oa.dedup;
import com.google.common.collect.Lists;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.dedup.model.OrgSimRel;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import java.io.IOException;
import java.util.*;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
@ -17,12 +13,19 @@ import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.common.collect.Lists;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.dedup.model.OrgSimRel;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import scala.Tuple2;
import scala.Tuple3;
import java.io.IOException;
import java.util.*;
public class SparkPrepareOrgRels extends AbstractSparkAction {
private static final Logger log = LoggerFactory.getLogger(SparkCreateDedupRecord.class);
@ -125,12 +128,11 @@ public class SparkPrepareOrgRels extends AbstractSparkAction {
List<String> ids = sortIds(l);
List<Tuple3<String, String, String>> rels = new ArrayList<>();
for (String source : ids) {
if (source.contains("openorgs____") || ids.indexOf(source) == 0)
String source = ids.get(0);
for (String target : ids) {
rels.add(new Tuple3<>(source, target, groupId));
}
}
return rels.iterator();
})
.rdd(),