From b0fed1725edc8c000619906751ad46a105c9449b Mon Sep 17 00:00:00 2001
From: Claudio Atzori <claudio.atzori@isti.cnr.it>
Date: Thu, 19 Oct 2023 12:13:45 +0200
Subject: [PATCH] avoid NPEs

---
 .../oaf/utils/GraphCleaningFunctions.java     | 10 ++++++
 .../dnetlib/dhp/bulktag/SparkBulkTagJob.java  |  7 ++--
 .../PrepareResultCountrySet.java              | 32 ++++++++++++++-----
 3 files changed, 39 insertions(+), 10 deletions(-)

diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java b/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java
index 324e3dd58..b4402a2fb 100644
--- a/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java
+++ b/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java
@@ -286,6 +286,12 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 
 	public static <T extends Oaf> T cleanup(T value, VocabularyGroup vocs) {
 
+		if (Objects.isNull(value.getDataInfo())) {
+			final DataInfo d = new DataInfo();
+			d.setDeletedbyinference(false);
+			value.setDataInfo(d);
+		}
+
 		if (value instanceof OafEntity) {
 
 			OafEntity e = (OafEntity) value;
@@ -305,6 +311,10 @@ public class GraphCleaningFunctions extends CleaningFunctions {
 			} else if (value instanceof Result) {
 				Result r = (Result) value;
 
+				if (Objects.isNull(r.getContext())) {
+					r.setContext(new ArrayList<>());
+				}
+
 				if (Objects.nonNull(r.getFulltext())
 					&& (ModelConstants.SOFTWARE_RESULTTYPE_CLASSID.equals(r.getResulttype().getClassid()) ||
 						ModelConstants.DATASET_RESULTTYPE_CLASSID.equals(r.getResulttype().getClassid()))) {
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 3186ed5c0..fc3882b73 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
@@ -25,6 +25,7 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
 import eu.dnetlib.dhp.bulktag.community.*;
 import eu.dnetlib.dhp.schema.oaf.Datasource;
 import eu.dnetlib.dhp.schema.oaf.Result;
+import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
 
 public class SparkBulkTagJob {
 
@@ -170,10 +171,12 @@ public class SparkBulkTagJob {
 	// 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 r -> {
-			if (r.getDataInfo().getDeletedbyinference() == null) {
+			if (Objects.isNull(r.getDataInfo())) {
+				r.setDataInfo(OafMapperUtils.dataInfo(false, "", false, false, OafMapperUtils.unknown("", ""), ""));
+			} else if (r.getDataInfo().getDeletedbyinference() == null) {
 				r.getDataInfo().setDeletedbyinference(false);
 			}
-			if (r.getContext() == null) {
+			if (Objects.isNull(r.getContext())) {
 				r.setContext(new ArrayList<>());
 			}
 			return r;
diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java
index 28b6f616d..184d24751 100644
--- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java
+++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java
@@ -5,10 +5,7 @@ import static eu.dnetlib.dhp.PropagationConstant.*;
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
 import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
 
-import java.util.ArrayList;
-import java.util.Arrays;
-import java.util.HashSet;
-import java.util.Set;
+import java.util.*;
 import java.util.stream.Collectors;
 
 import org.apache.commons.io.IOUtils;
@@ -88,14 +85,33 @@ public class PrepareResultCountrySet {
 		// selects all the results non deleted by inference and non invisible
 		Dataset<R> result = readPath(spark, inputPath, resultClazz)
 			.filter(
-				(FilterFunction<R>) r -> !r.getDataInfo().getDeletedbyinference() &&
-					!r.getDataInfo().getInvisible());
+				(FilterFunction<R>) r -> Optional
+					.ofNullable(r.getDataInfo())
+					.map(dataInfo -> !dataInfo.getDeletedbyinference() && !dataInfo.getInvisible())
+					.orElse(true));
 
 		// of the results collects the distinct keys for collected from (at the level of the result) and hosted by
 		// and produces pairs resultId, key for each distinct key associated to the result
 		result.flatMap((FlatMapFunction<R, EntityEntityRel>) r -> {
-			Set<String> cfhb = r.getCollectedfrom().stream().map(cf -> cf.getKey()).collect(Collectors.toSet());
-			cfhb.addAll(r.getInstance().stream().map(i -> i.getHostedby().getKey()).collect(Collectors.toSet()));
+			Set<String> cfhb = Optional
+				.ofNullable(r.getCollectedfrom())
+				.map(cf -> cf.stream().map(KeyValue::getKey).collect(Collectors.toSet()))
+				.orElse(new HashSet<>());
+			cfhb
+				.addAll(
+					Optional
+						.ofNullable(r.getInstance())
+						.map(
+							i -> i
+								.stream()
+								.map(
+									ii -> Optional
+										.ofNullable(ii.getHostedby())
+										.map(KeyValue::getKey)
+										.orElse(null))
+								.filter(Objects::nonNull)
+								.collect(Collectors.toSet()))
+						.orElse(new HashSet<>()));
 			return cfhb
 				.stream()
 				.map(value -> EntityEntityRel.newInstance(r.getId(), value))