From 42846d3b911d3759046f4965dfa42d6d288bbc21 Mon Sep 17 00:00:00 2001
From: "miriam.baglioni" <miriam.baglioni@isti.cnr.it>
Date: Wed, 3 Apr 2024 09:25:00 +0200
Subject: [PATCH] [OpenCitation] add compression option when writing the
 sequence file

---
 .../actionmanager/opencitations/CreateActionSetSparkJob.java    | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateActionSetSparkJob.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateActionSetSparkJob.java
index 950b2eb57..39592f0bc 100644
--- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateActionSetSparkJob.java
+++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateActionSetSparkJob.java
@@ -88,7 +88,7 @@ public class CreateActionSetSparkJob implements Serializable {
 	private static void extractContent(SparkSession spark, String inputPath, String outputPath) {
 
 		getTextTextJavaPairRDD(spark, inputPath)
-			.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);// , GzipCodec.class);
+			.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
 	}
 
 	private static JavaPairRDD<Text, Text> getTextTextJavaPairRDD(SparkSession spark, String inputPath) {