D-Net
/
dnet-dedup
5
1
Fork 0
Code Issues Pull Requests 1 Releases Wiki Activity

minor changes

This commit is contained in:
miconis 2020-03-20 18:02:52 +01:00
parent 0ba1f6f96a
commit a73bc6cddc
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
dnet-dedup-test/src/main/java/eu/dnetlib/Deduper.java
View File

@ -13,6 +13,7 @@ import org.apache.commons.logging.LogFactory;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.Optional;
import org.apache.spark.graphx.Edge;
import org.apache.spark.rdd.RDD;
import org.apache.spark.util.LongAccumulator;
@ -90,6 +91,7 @@ public class Deduper implements Serializable {
return Utility.getGroupingKeys(config, currentDocument).stream()
.map(it -> new Tuple2<>(it, currentDocument)).collect(Collectors.toList()).iterator();
}).groupByKey();
}
/**