forked from antonis.lempesis/dnet-hadoop
added compression to output dataset
This commit is contained in:
parent
9a2fa9dc2f
commit
005f849674
|
@ -128,6 +128,8 @@ public class SparkGenEnrichedOrcidWorks {
|
||||||
})
|
})
|
||||||
.filter(p -> p != null);
|
.filter(p -> p != null);
|
||||||
|
|
||||||
|
sc.hadoopConfiguration().set("mapreduce.output.fileoutputformat.compress", "true");
|
||||||
|
|
||||||
oafPublicationRDD
|
oafPublicationRDD
|
||||||
.mapToPair(
|
.mapToPair(
|
||||||
p -> new Tuple2<>(p.getClass().toString(),
|
p -> new Tuple2<>(p.getClass().toString(),
|
||||||
|
|
Loading…
Reference in New Issue