From 55595d723599a3d0b30fbec81742829ad801e9b0 Mon Sep 17 00:00:00 2001
From: Claudio Atzori <claudio.atzori@isti.cnr.it>
Date: Tue, 26 May 2020 10:28:35 +0200
Subject: [PATCH] HACK: patch NULL values with defaults found in
 result.datainfo.deletedbyinference and result.context

---
 .../eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java   | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java
index 1c65e8ade..4800def0a 100644
--- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java
+++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java
@@ -4,6 +4,7 @@ package eu.dnetlib.dhp.bulktag;
 import static eu.dnetlib.dhp.PropagationConstant.removeOutputDir;
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
 
+import java.util.ArrayList;
 import java.util.Optional;
 
 import org.apache.commons.io.IOUtils;
@@ -100,6 +101,7 @@ public class SparkBulkTagJob {
 
 		ResultTagger resultTagger = new ResultTagger();
 		readPath(spark, inputPath, resultClazz)
+			.map(patchResult(), Encoders.bean(resultClazz))
 			.map(
 				(MapFunction<R, R>) value -> resultTagger
 					.enrichContextCriteria(
@@ -119,4 +121,17 @@ public class SparkBulkTagJob {
 			.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
 	}
 
+	// TODO remove this hack as soon as the values fixed by this method will be provided as NON null
+	private static <R extends Result> MapFunction<R, R> patchResult() {
+		return (MapFunction<R, R>) r -> {
+			if (r.getDataInfo().getDeletedbyinference() == null) {
+				r.getDataInfo().setDeletedbyinference(false);
+			}
+			if (r.getContext() == null) {
+				r.setContext(new ArrayList<>());
+			}
+			return r;
+		};
+	}
+
 }