diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java index cbfba30c55..18d98be543 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java @@ -75,21 +75,27 @@ public class PrepareAffiliationRelations implements Serializable { spark -> { Constants.removeOutputDir(spark, outputPath); - List collectedFromCrossref = OafMapperUtils.listKeyValues(ModelConstants.CROSSREF_ID, "Crossref"); - JavaPairRDD crossrefRelations = prepareAffiliationRelations(spark, inputPath, collectedFromCrossref); + List collectedFromCrossref = OafMapperUtils + .listKeyValues(ModelConstants.CROSSREF_ID, "Crossref"); + JavaPairRDD crossrefRelations = prepareAffiliationRelations( + spark, inputPath, collectedFromCrossref); - List collectedFromPubmed = OafMapperUtils.listKeyValues(ModelConstants.PUBMED_CENTRAL_ID, "Pubmed"); - JavaPairRDD pubmedRelations = prepareAffiliationRelations(spark, inputPath, collectedFromPubmed); + List collectedFromPubmed = OafMapperUtils + .listKeyValues(ModelConstants.PUBMED_CENTRAL_ID, "Pubmed"); + JavaPairRDD pubmedRelations = prepareAffiliationRelations( + spark, inputPath, collectedFromPubmed); crossrefRelations - .union(pubmedRelations) - .saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class); + .union(pubmedRelations) + .saveAsHadoopFile( + outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class); }); } - private static JavaPairRDD prepareAffiliationRelations(SparkSession spark, String inputPath, - List collectedfrom) { + private static JavaPairRDD prepareAffiliationRelations(SparkSession spark, + String inputPath, + List collectedfrom) { // load and parse affiliation relations from HDFS Dataset df = spark diff --git a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml index c0a6bfc528..e3fdddfd6d 100644 --- a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/actionmanager/bipaffiliations/oozie_app/workflow.xml @@ -87,7 +87,7 @@ yarn cluster - Produces the atomic action with the inferred by BIP! affiliation relations from Crossref + Produces the atomic action with the inferred by BIP! affiliation relations (from Crossref and Pubmed) eu.dnetlib.dhp.actionmanager.bipaffiliations.PrepareAffiliationRelations dhp-aggregation-${projectVersion}.jar