From 09fc7e2f7882277534b9ccf97b6a1d9060ded335 Mon Sep 17 00:00:00 2001 From: Alessia Bardi Date: Wed, 10 Feb 2021 11:22:09 +0100 Subject: [PATCH 1/3] serialization of validated flag on relationships --- .../CreateRelatedEntitiesJob_phase2.java | 2 +- .../oa/provision/utils/GraphMappingUtils.java | 3 +- .../oa/provision/utils/TemplateFactory.java | 6 +- .../oa/provision/utils/XmlRecordFactory.java | 3 +- .../dnetlib/dhp/oa/provision/template/rel.st | 3 +- .../oa/provision/XmlRecordFactoryTest.java | 70 +++++++++++ .../eu/dnetlib/dhp/oa/provision/project.json | 109 ++++++++++++++++++ .../eu/dnetlib/dhp/oa/provision/record.xml | 22 ++++ .../dhp/oa/provision/relToProject.json | 31 +++++ .../oa/provision/relToValidatedProject.json | 31 +++++ 10 files changed, 275 insertions(+), 5 deletions(-) create mode 100644 dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/project.json create mode 100644 dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToProject.json create mode 100644 dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToValidatedProject.json diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/CreateRelatedEntitiesJob_phase2.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/CreateRelatedEntitiesJob_phase2.java index f3fbca47d..e2cf58d00 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/CreateRelatedEntitiesJob_phase2.java +++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/CreateRelatedEntitiesJob_phase2.java @@ -8,7 +8,6 @@ import java.util.Objects; import java.util.Optional; import java.util.stream.Collectors; -import eu.dnetlib.dhp.schema.common.ModelConstants; import org.apache.commons.io.IOUtils; import org.apache.commons.lang3.StringUtils; import org.apache.spark.SparkConf; @@ -28,6 +27,7 @@ import eu.dnetlib.dhp.common.HdfsSupport; import eu.dnetlib.dhp.oa.provision.model.JoinedEntity; import eu.dnetlib.dhp.oa.provision.model.ProvisionModelSupport; import eu.dnetlib.dhp.oa.provision.model.RelatedEntityWrapper; +import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelSupport; import eu.dnetlib.dhp.schema.oaf.*; import scala.Tuple2; diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/GraphMappingUtils.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/GraphMappingUtils.java index 74d35bf5e..d2131ef28 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/GraphMappingUtils.java +++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/GraphMappingUtils.java @@ -14,7 +14,8 @@ public class GraphMappingUtils { public static final String SEPARATOR = "_"; - public static Set authorPidTypes = Sets.newHashSet( + public static Set authorPidTypes = Sets + .newHashSet( ModelConstants.ORCID, ModelConstants.ORCID_PENDING, "magidentifier"); public static String removePrefix(final String s) { diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/TemplateFactory.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/TemplateFactory.java index 21b526ab1..173ba326a 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/TemplateFactory.java +++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/TemplateFactory.java @@ -73,7 +73,9 @@ public class TemplateFactory { final Collection fields, final String semanticclass, final String semantischeme, - final DataInfo info) { + final DataInfo info, + final boolean validated, + final String validationDate) { return getTemplate(resources.getRel()) .add("type", type) .add("objIdentifier", escapeXml(removePrefix(objIdentifier))) @@ -86,6 +88,8 @@ public class TemplateFactory { .add( "provenanceaction", info.getProvenanceaction() != null ? info.getProvenanceaction().getClassid() : "") + .add("validated", validated) + .add("validationdate", validationDate) .render(); } diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/XmlRecordFactory.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/XmlRecordFactory.java index 9f16e99d8..b0a21c62b 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/XmlRecordFactory.java +++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/XmlRecordFactory.java @@ -1096,7 +1096,8 @@ public class XmlRecordFactory implements Serializable { final HashSet fields = Sets.newHashSet(mapFields(link, contexts)); return templateFactory .getRel( - targetType, rel.getTarget(), fields, rel.getRelClass(), scheme, rel.getDataInfo()); + targetType, rel.getTarget(), fields, rel.getRelClass(), scheme, rel.getDataInfo(), rel.getValidated(), + rel.getValidationDate()); } private List listChildren( diff --git a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/template/rel.st b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/template/rel.st index af19ba497..e77a86e1d 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/template/rel.st +++ b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/template/rel.st @@ -1,4 +1,5 @@ - $objIdentifier$ +$if(validated)$$else$$endif$ +$objIdentifier$ $metadata:{ it | $it$ }$ \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java index 8ae8a55c3..c391a95c9 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java +++ b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java @@ -5,22 +5,29 @@ import static org.junit.jupiter.api.Assertions.*; import java.io.IOException; import java.io.StringReader; +import java.util.List; import org.apache.commons.io.IOUtils; import org.dom4j.Document; import org.dom4j.DocumentException; import org.dom4j.io.SAXReader; +import org.junit.Assert; import org.junit.jupiter.api.Assertions; import org.junit.jupiter.api.Disabled; import org.junit.jupiter.api.Test; +import com.clearspring.analytics.util.Lists; import com.fasterxml.jackson.databind.DeserializationFeature; import com.fasterxml.jackson.databind.ObjectMapper; import eu.dnetlib.dhp.oa.provision.model.JoinedEntity; +import eu.dnetlib.dhp.oa.provision.model.RelatedEntity; +import eu.dnetlib.dhp.oa.provision.model.RelatedEntityWrapper; import eu.dnetlib.dhp.oa.provision.utils.ContextMapper; import eu.dnetlib.dhp.oa.provision.utils.XmlRecordFactory; +import eu.dnetlib.dhp.schema.oaf.Project; import eu.dnetlib.dhp.schema.oaf.Publication; +import eu.dnetlib.dhp.schema.oaf.Relation; public class XmlRecordFactoryTest { @@ -58,4 +65,67 @@ public class XmlRecordFactoryTest { // TODO add assertions based of values extracted from the XML record } + + @Test + public void testXMLRecordFactoryWithValidatedProject() throws IOException, DocumentException { + + ContextMapper contextMapper = new ContextMapper(); + + XmlRecordFactory xmlRecordFactory = new XmlRecordFactory(contextMapper, false, XmlConverterJob.schemaLocation, + otherDsTypeId); + + Publication p = OBJECT_MAPPER + .readValue(IOUtils.toString(getClass().getResourceAsStream("publication.json")), Publication.class); + Project pj = OBJECT_MAPPER + .readValue(IOUtils.toString(getClass().getResourceAsStream("project.json")), Project.class); + Relation rel = OBJECT_MAPPER + .readValue( + (IOUtils.toString(getClass().getResourceAsStream("relToValidatedProject.json"))), Relation.class); + RelatedEntity relatedProject = CreateRelatedEntitiesJob_phase1.asRelatedEntity(pj, Project.class); + List links = Lists.newArrayList(); + RelatedEntityWrapper rew = new RelatedEntityWrapper(rel, relatedProject); + links.add(rew); + JoinedEntity je = new JoinedEntity<>(p); + je.setLinks(links); + + String xml = xmlRecordFactory.build(je); + + assertNotNull(xml); + + Document doc = new SAXReader().read(new StringReader(xml)); + assertNotNull(doc); + System.out.println(doc.asXML()); + Assertions.assertEquals("2021-01-01", doc.valueOf("//validated/@date")); + } + + @Test + public void testXMLRecordFactoryWithNonValidatedProject() throws IOException, DocumentException { + + ContextMapper contextMapper = new ContextMapper(); + + XmlRecordFactory xmlRecordFactory = new XmlRecordFactory(contextMapper, false, XmlConverterJob.schemaLocation, + otherDsTypeId); + + Publication p = OBJECT_MAPPER + .readValue(IOUtils.toString(getClass().getResourceAsStream("publication.json")), Publication.class); + Project pj = OBJECT_MAPPER + .readValue(IOUtils.toString(getClass().getResourceAsStream("project.json")), Project.class); + Relation rel = OBJECT_MAPPER + .readValue((IOUtils.toString(getClass().getResourceAsStream("relToProject.json"))), Relation.class); + RelatedEntity relatedProject = CreateRelatedEntitiesJob_phase1.asRelatedEntity(pj, Project.class); + List links = Lists.newArrayList(); + RelatedEntityWrapper rew = new RelatedEntityWrapper(rel, relatedProject); + links.add(rew); + JoinedEntity je = new JoinedEntity<>(p); + je.setLinks(links); + + String xml = xmlRecordFactory.build(je); + + assertNotNull(xml); + + Document doc = new SAXReader().read(new StringReader(xml)); + assertNotNull(doc); + System.out.println(doc.asXML()); + assertEquals("", doc.valueOf("//rel/validated")); + } } diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/project.json b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/project.json new file mode 100644 index 000000000..b61e55d1a --- /dev/null +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/project.json @@ -0,0 +1,109 @@ +{ + "id": "40|corda__h2020::79a0e16c122c9a18eb60e4a5e64b620d", + "originalId": [], + "pid": [], + "dateofcollection": "2020-01-01", + "dateoftransformation": "2020-01-01", + "extraInfo": [], + "oaiprovenance": null, + "websiteurl": { + "value": "https://web.site", + "datainfo": null + }, + "code": { + "value": "79a0e", + "datainfo": null + }, + "acronym": { + "value": "79a0e_acronym", + "datainfo": null + }, + "title": { + "value": "79a0e_title", + "datainfo": null + }, + "startdate": { + "value": "2019-02-01", + "datainfo": null + }, + "enddate": { + "value": "2021-01-09", + "datainfo": null + }, + "callidentifier": { + "value": "79a0e_callID", + "datainfo": null + }, + "keywords": { + "value": "", + "datainfo": null + }, + "duration": { + "value": "", + "datainfo": null + }, + "ecsc39": { + "value": "true", + "datainfo": null + }, + "oamandatepublications": { + "value": "true", + "datainfo": null + }, + "ecarticle29_3": { + "value": "false", + "datainfo": null + }, + "optional1": { + "value": "", + "datainfo": null + }, + "optional2": { + "value": "", + "datainfo": null + }, + "jsonextrainfo":{ + "value": "", + "datainfo": null + }, + "contactfullname":{ + "value": "", + "datainfo": null + }, + "contactfax": { + "value": "", + "datainfo": null + }, + "contactphone": { + "value": "", + "datainfo": null + }, + "contactemail": { + "value": "", + "datainfo": null + }, + "summary": { + "value": "79a0e_description", + "datainfo": null + }, + "currency": { + "value": "EUR", + "datainfo": null + }, + "totalcost": 120000, + "fundedamount": 18000, + "h2020topiccode": "", + "h2020topicdescription": "", + "h2020classification": [], + "subjects": [ + { + "value": "", + "qualifier": null, + "datainfo": null + } + ], + "fundingtree": [] + +} + + diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/record.xml b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/record.xml index a0ca0aa6f..2d6049416 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/record.xml +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/record.xml @@ -294,6 +294,28 @@ >rcuk________::23feba2a5ca7f6b6016bf3a45180da50 University of Delhi + + true + corda_______::30c6b5ab90f30666de1d112fb93d8c77 + 227878 + + + ec__________::EC::FP7 + ec__________::EC::FP7::SP2 + ec__________::EC::FP7::SP2::ERC + + Complex structure and dynamics of collective motion + COLLMOT + + + + irb_hr______::2330a1d0dac71ffbe15fbcbc807288d4 + 108-1083570-3635 + + + + Pentadecapeptide BPC 157 - further investigations + diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToProject.json b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToProject.json new file mode 100644 index 000000000..b4d975255 --- /dev/null +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToProject.json @@ -0,0 +1,31 @@ +{ +"collectedfrom": [ +{ +"key": "10|opendoar____::eccbc87e4b5ce2fe28308fd9f2a7baf3", +"value": "AMS Acta", +"dataInfo": null +} +], +"dataInfo": { +"invisible": false, +"inferred": false, +"deletedbyinference": false, +"trust": "0.9", +"inferenceprovenance": "", +"provenanceaction": { +"classid": "sysimport:crosswalk:repository", +"classname": "sysimport:crosswalk:repository", +"schemeid": "dnet:provenanceActions", +"schemename": "dnet:provenanceActions" +} +}, +"lastupdatetimestamp": 1606898557407, +"relType": "resultProject", +"subRelType": "outcome", +"relClass": "isProducedBy", +"source": "50|CSC_________::0000ec4dd9df012feaafa77e71a0fb4c", +"target": "40|corda__h2020::79a0e16c122c9a18eb60e4a5e64b620d", +"validated": false, +"validationDate": null, +"properties": [] +} \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToValidatedProject.json b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToValidatedProject.json new file mode 100644 index 000000000..0346d7264 --- /dev/null +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/relToValidatedProject.json @@ -0,0 +1,31 @@ +{ +"collectedfrom": [ +{ +"key": "10|opendoar____::eccbc87e4b5ce2fe28308fd9f2a7baf3", +"value": "AMS Acta", +"dataInfo": null +} +], +"dataInfo": { +"invisible": false, +"inferred": false, +"deletedbyinference": false, +"trust": "0.9", +"inferenceprovenance": "", +"provenanceaction": { +"classid": "sysimport:crosswalk:repository", +"classname": "sysimport:crosswalk:repository", +"schemeid": "dnet:provenanceActions", +"schemename": "dnet:provenanceActions" +} +}, +"lastupdatetimestamp": 1606898557407, +"relType": "resultProject", +"subRelType": "outcome", +"relClass": "isProducedBy", +"source": "50|CSC_________::0000ec4dd9df012feaafa77e71a0fb4c", +"target": "40|corda__h2020::79a0e16c122c9a18eb60e4a5e64b620d", +"validated": true, +"validationDate": "2021-01-01", +"properties": [] +} \ No newline at end of file From c4d1feca7451b8e50f0abe8287fb056c32516f17 Mon Sep 17 00:00:00 2001 From: Alessia Bardi Date: Wed, 10 Feb 2021 11:22:54 +0100 Subject: [PATCH 2/3] mapper test with validated link to project --- .../src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java | 1 + .../resources/eu/dnetlib/dhp/oa/graph/raw/oaf_claim_crossref.xml | 1 + 2 files changed, 2 insertions(+) diff --git a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java index 853106cd8..ab956a378 100644 --- a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java +++ b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java @@ -334,6 +334,7 @@ public class MappersTest { assertValidId(p.getCollectedfrom().get(0).getKey()); System.out.println(p.getTitle().get(0).getValue()); assertTrue(StringUtils.isNotBlank(p.getTitle().get(0).getValue())); + } @Test diff --git a/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/oaf_claim_crossref.xml b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/oaf_claim_crossref.xml index 8f69a5e2d..93349f3c9 100644 --- a/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/oaf_claim_crossref.xml +++ b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/oaf_claim_crossref.xml @@ -46,6 +46,7 @@ 10.1080/23744235.2020.1774644 Infectious Diseases + corda__h2020::814530 From 986dd969d3e32975f7d49cbbdda2eb6f2adcee8a Mon Sep 17 00:00:00 2001 From: Alessia Bardi Date: Wed, 10 Feb 2021 12:03:54 +0100 Subject: [PATCH 3/3] use the proper import for Lists --- .../eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java index c391a95c9..27860ca32 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java +++ b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java @@ -11,14 +11,12 @@ import org.apache.commons.io.IOUtils; import org.dom4j.Document; import org.dom4j.DocumentException; import org.dom4j.io.SAXReader; -import org.junit.Assert; import org.junit.jupiter.api.Assertions; -import org.junit.jupiter.api.Disabled; import org.junit.jupiter.api.Test; -import com.clearspring.analytics.util.Lists; import com.fasterxml.jackson.databind.DeserializationFeature; import com.fasterxml.jackson.databind.ObjectMapper; +import com.google.common.collect.Lists; import eu.dnetlib.dhp.oa.provision.model.JoinedEntity; import eu.dnetlib.dhp.oa.provision.model.RelatedEntity;