lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

Merge pull request 'betaFixPerson' (#505) from betaFixPerson into beta 

Reviewed-on: D-Net/dnet-hadoop#505
This commit is contained in:
Claudio Atzori 2024-11-12 14:09:22 +01:00
parent f31f22801f 250f101779
commit 9f7a606ddd
2 changed files with 19 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/bipaffiliations/PrepareAffiliationRelations.java
View File

@ -104,22 +104,22 @@ public class PrepareAffiliationRelations implements Serializable {
.listKeyValues(OPENAIRE_DATASOURCE_ID, OPENAIRE_DATASOURCE_NAME);
JavaPairRDD<Text, Text> crossrefRelations = prepareAffiliationRelationsNewModel(
spark, crossrefInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + "::crossref");
spark, crossrefInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + ":crossref");
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
spark, pubmedInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + "::pubmed");
spark, pubmedInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + ":pubmed");
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelationsNewModel(
spark, openapcInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + "::openapc");
spark, openapcInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + ":openapc");
JavaPairRDD<Text, Text> dataciteRelations = prepareAffiliationRelationsNewModel(
spark, dataciteInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + "::datacite");
spark, dataciteInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + ":datacite");
JavaPairRDD<Text, Text> webCrawlRelations = prepareAffiliationRelationsNewModel(
spark, webcrawlInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + "::rawaff");
spark, webcrawlInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + ":rawaff");
JavaPairRDD<Text, Text> publisherRelations = prepareAffiliationRelationFromPublisherNewModel(
spark, publisherlInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + "::webcrawl");
spark, publisherlInputPath, collectedfromOpenAIRE, BIP_INFERENCE_PROVENANCE + ":webcrawl");
crossrefRelations
.union(pubmedRelations)

16
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/personentity/ExtractPerson.java
View File

@ -15,6 +15,7 @@ import java.util.stream.Collectors;
import org.apache.commons.cli.ParseException;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
@ -193,8 +194,8 @@ public class ExtractPerson implements Serializable {
private static Relation getProjectRelation(String project, String orcid, String role) {
String source = PERSON_PREFIX + "::" + IdentifierFactory.md5(orcid);
String target = PROJECT_ID_PREFIX + project.substring(0, 14)
+ IdentifierFactory.md5(project.substring(15));
String target = PROJECT_ID_PREFIX + StringUtils.substringBefore(project, "::") + "::"
+ IdentifierFactory.md5(StringUtils.substringAfter(project, "::"));
List<KeyValue> properties = new ArrayList<>();
Relation relation = OafMapperUtils
@ -345,7 +346,16 @@ public class ExtractPerson implements Serializable {
OafMapperUtils
.structuredProperty(
op.getOrcid(), ModelConstants.ORCID, ModelConstants.ORCID_CLASSNAME,
ModelConstants.DNET_PID_TYPES, ModelConstants.DNET_PID_TYPES, null));
ModelConstants.DNET_PID_TYPES, ModelConstants.DNET_PID_TYPES,
OafMapperUtils.dataInfo(false,
null,
false,
false,
OafMapperUtils.qualifier(ModelConstants.SYSIMPORT_CROSSWALK_ENTITYREGISTRY,
ModelConstants.SYSIMPORT_CROSSWALK_ENTITYREGISTRY,
ModelConstants.DNET_PID_TYPES,
ModelConstants.DNET_PID_TYPES),
"0.91")));
person.setDateofcollection(op.getLastModifiedDate());
person.setOriginalId(Arrays.asList(op.getOrcid()));
person.setDataInfo(ORCIDDATAINFO);