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

code formatting

This commit is contained in:
Claudio Atzori 2020-06-25 12:54:21 +02:00
parent 7df2712824
commit 93f627ea51
1 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/PrepareRelationsJob.java
View File

@ -1,15 +1,12 @@
package eu.dnetlib.dhp.oa.provision;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.base.Splitter;
import com.google.common.collect.Iterables;
import com.google.common.collect.Sets;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.provision.model.SortableRelationKey;
import eu.dnetlib.dhp.oa.provision.utils.RelationPartitioner;
import eu.dnetlib.dhp.schema.oaf.Relation;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.HashSet;
import java.util.Optional;
import java.util.Set;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
@ -20,14 +17,19 @@ import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.base.Splitter;
import com.google.common.collect.Iterables;
import com.google.common.collect.Sets;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.provision.model.SortableRelationKey;
import eu.dnetlib.dhp.oa.provision.utils.RelationPartitioner;
import eu.dnetlib.dhp.schema.oaf.Relation;
import scala.Tuple2;
import java.util.HashSet;
import java.util.Optional;
import java.util.Set;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
/**
* Joins the graph nodes by resolving the links of distance = 1 to create an adjacency list of linked objects. The
* operation considers all the entity types (publication, dataset, software, ORP, project, datasource, organization, and