From 005f849674c93f44e9a3e66b86211dd8f38f8919 Mon Sep 17 00:00:00 2001
From: Enrico Ottonello <enrico.ottonello@isti.cnr.it>
Date: Fri, 13 Nov 2020 12:45:31 +0100
Subject: [PATCH] added compression to output dataset

---
 .../dnetlib/doiboost/orcidnodoi/SparkGenEnrichedOrcidWorks.java | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/SparkGenEnrichedOrcidWorks.java b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/SparkGenEnrichedOrcidWorks.java
index cc65b0b4f..a92d534d8 100644
--- a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/SparkGenEnrichedOrcidWorks.java
+++ b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/SparkGenEnrichedOrcidWorks.java
@@ -128,6 +128,8 @@ public class SparkGenEnrichedOrcidWorks {
 						})
 					.filter(p -> p != null);
 
+				sc.hadoopConfiguration().set("mapreduce.output.fileoutputformat.compress", "true");
+
 				oafPublicationRDD
 					.mapToPair(
 						p -> new Tuple2<>(p.getClass().toString(),