From f09e0658654a89e91147a1b6dbbbc6e4ab48c8c6 Mon Sep 17 00:00:00 2001
From: Sandro La Bruzzo <sandro.labruzzo@isti.cnr.it>
Date: Wed, 26 Feb 2020 19:26:19 +0100
Subject: [PATCH] incremented number of repartition

---
 .../java/eu/dnetlib/dhp/provision/SparkGenerateScholix.java     | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/provision/SparkGenerateScholix.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/provision/SparkGenerateScholix.java
index 2c7107b70..be24d8a4b 100644
--- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/provision/SparkGenerateScholix.java
+++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/provision/SparkGenerateScholix.java
@@ -37,7 +37,7 @@ public class SparkGenerateScholix {
         final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
 
 
-        final JavaRDD<String> relationToExport = sc.textFile(graphPath + "/relation").filter(ProvisionUtil::isNotDeleted);
+        final JavaRDD<String> relationToExport = sc.textFile(graphPath + "/relation").filter(ProvisionUtil::isNotDeleted).repartition(4000);
         final JavaPairRDD<String,String> scholixSummary = sc.textFile(workingDirPath + "/summary").mapToPair((PairFunction<String, String, String>) i -> new Tuple2<>(DHPUtils.getJPathString(jsonIDPath, i), i));
         scholixSummary.join(
                 relationToExport