lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

[provision] lowercase relation filter

This commit is contained in:
Claudio Atzori 2021-07-29 13:56:37 +02:00
parent 5d08ad86ae
commit c53d106e80
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/PrepareRelationsJob.java
View File

@ -10,6 +10,7 @@ import java.util.Set;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
@ -81,6 +82,7 @@ public class PrepareRelationsJob {
Set<String> relationFilter = Optional
.ofNullable(parser.get("relationFilter"))
.map(String::toLowerCase)
.map(s -> Sets.newHashSet(Splitter.on(",").split(s)))
.orElse(new HashSet<>());
log.info("relationFilter: {}", relationFilter);
@ -130,7 +132,7 @@ public class PrepareRelationsJob {
JavaRDD<Relation> rels = readPathRelationRDD(spark, inputRelationsPath)
.filter(rel -> rel.getDataInfo().getDeletedbyinference() == false)
.filter(rel -> relationFilter.contains(rel.getRelClass()) == false);
.filter(rel -> relationFilter.contains(StringUtils.lowerCase(rel.getRelClass())) == false);
JavaRDD<Relation> pruned = pruneRels(
pruneRels(