merge upstream

This commit is contained in:
Miriam Baglioni 2020-10-27 15:54:16 +01:00
commit cc68855a1e
2 changed files with 11 additions and 2 deletions

View File

@ -94,7 +94,13 @@ public class AuthorMerger {
if (r.getPid() == null) {
r.setPid(new ArrayList<>());
}
r.getPid().add(a._1());
// TERRIBLE HACK but for some reason when we create and Array with Arrays.asList,
// it creates of fixed size, and the add method raise UnsupportedOperationException at
// java.util.AbstractList.add
final List<StructuredProperty> tmp = new ArrayList<>(r.getPid());
tmp.add(a._1());
r.setPid(tmp);
}
}
});

View File

@ -1,13 +1,15 @@
package eu.dnetlib.doiboost
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.{Publication, Relation, Dataset => OafDataset, Organization}
import eu.dnetlib.dhp.oa.merge.AuthorMerger
import eu.dnetlib.dhp.schema.oaf.{Organization, Publication, Relation, Dataset => OafDataset}
import eu.dnetlib.doiboost.mag.ConversionUtil
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.functions.col
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
object SparkGenerateDoiBoost {
@ -49,6 +51,7 @@ object SparkGenerateDoiBoost {
val otherPub = item._2._2
if (otherPub != null) {
crossrefPub.mergeFrom(otherPub)
crossrefPub.setAuthor(AuthorMerger.mergeAuthor(crossrefPub.getAuthor, otherPub.getAuthor))
}
}
crossrefPub