D-Net
/
dnet-hadoop
13
4
Fork 10
Code Issues 14 Pull Requests 8 Projects 2 Releases 1 Wiki Activity

avoid NPEs

This commit is contained in:
Claudio Atzori 2023-10-19 12:13:45 +02:00
parent 3b1c8b9fbd
commit b0fed1725e
3 changed files with 39 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java
View File

@ -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()))) {

7
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java
View File

@ -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;

32
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java
View File

@ -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))