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

testing for RO-Hub

This commit is contained in:
Alessia Bardi 2022-09-02 16:07:36 +02:00
parent cb7c07c54e
commit a11eb38065
4 changed files with 144 additions and 67 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java
View File

@ -926,6 +926,15 @@ class MappersTest {
// assertTrue(StringUtils.isNotBlank(p.getTitle().get(0).getValue())); // assertTrue(StringUtils.isNotBlank(p.getTitle().get(0).getValue()));
} }
@Test
void testROHub2() throws IOException, DocumentException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("rohub-modified.xml")));
final List<Oaf> list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml);
System.out.println("***************");
System.out.println(new ObjectMapper().writeValueAsString(list));
System.out.println("***************");
}
private void assertValidId(final String id) { private void assertValidId(final String id) {
// System.out.println(id); // System.out.println(id);

1
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/terms.txt
View File

@ -1049,6 +1049,7 @@ dnet:pid_types @=@ dnet:pid_types @=@ who @=@ WHO Identifier
dnet:pid_types @=@ dnet:pid_types @=@ drks @=@ DRKS Identifier dnet:pid_types @=@ dnet:pid_types @=@ drks @=@ DRKS Identifier
dnet:pid_types @=@ dnet:pid_types @=@ handle @=@ Handle dnet:pid_types @=@ dnet:pid_types @=@ handle @=@ Handle
dnet:pid_types @=@ dnet:pid_types @=@ data.europa.eu @=@ EU Persistent URL dnet:pid_types @=@ dnet:pid_types @=@ data.europa.eu @=@ EU Persistent URL
dnet:pid_types @=@ dnet:pid_types @=@ w3id @=@ w3id.org
dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/SUBJECT/ACM @=@ An ACM classification term that can be associated to your publications dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/SUBJECT/ACM @=@ An ACM classification term that can be associated to your publications
dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/SUBJECT/ARXIV @=@ An ARXIV classification term that can be associated to your publications dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/SUBJECT/ARXIV @=@ An ARXIV classification term that can be associated to your publications
dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/SUBJECT/DDC @=@ A Dewey Decimal classification term (DDC) that can be associated to your publications dnet:topic_types @=@ dnet:topic_types @=@ ENRICH/MISSING/SUBJECT/DDC @=@ A Dewey Decimal classification term (DDC) that can be associated to your publications

85
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/rohub-modified.xml Normal file
View File

@ -0,0 +1,85 @@
<?xml version="1.0" encoding="UTF-8"?>
<record xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
xmlns:datacite="http://datacite.org/schema/kernel-4"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:dc="http://purl.org/dc/elements/1.1/">
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<identifier>https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</identifier>
<datestamp>2022-09-02T09:55:35Z</datestamp>
<setSpec>rohub_data</setSpec>
<setSpec>ro-crate_data</setSpec>
<dri:objIdentifier>fsh_____4119::afc7592914ae190a50570db90f55f9c2</dri:objIdentifier>
<dri:recordIdentifier>https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</dri:recordIdentifier>
<dri:dateOfCollection>2019-03-27T15:15:22.22Z</dri:dateOfCollection>
<oaf:datasourceprefix>fsh_____4119</oaf:datasourceprefix>
<dr:dateOfTransformation>2019-04-17T16:04:20.586Z</dr:dateOfTransformation>
</header>
<metadata>
<datacite:resource>
<datacite:identifier identifierType="w3id">https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</datacite:identifier>
<datacite:alternateIdentifiers/>
<datacite:relatedIdentifiers>
<datacite:relatedIdentifier relatedIdentifierType="w3id" relationType="HasPart">
https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca/resources/24fae96f-f986-46e1-bfd0-a21ca20ff0ce
</datacite:relatedIdentifier>
<datacite:relatedIdentifier relatedIdentifierType="w3id" relationType="HasPart">
https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca/resources/6d3427a8-352e-49f4-9796-f618c44dc16d
</datacite:relatedIdentifier>
</datacite:relatedIdentifiers>
<datacite:resourceType xs:anyURI="http://purl.org/coar/resource_type/c_1843">RO-crate</datacite:resourceType>
<datacite:rightsList>
<datacite:rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</datacite:rights>
</datacite:rightsList>
<datacite:titles>
<datacite:title>Using biological effects tools to define Good Environmental Status under the European Union Marine Strategy Framework Directive</datacite:title>
</datacite:titles>
<datacite:descriptions>
<datacite:description descriptionType="Abstract">The use of biological effects tools offer enormous potential to meet the challenges outlined by the European Union Marine Strategy Framework Directive (MSFD) whereby Member States are required to develop a robust set of tools for defining 11 qualitative descriptors of Good Environmental Status (GES), such as demonstrating that "Concentrations of contaminants are at levels not giving rise to pollution effects" (GES Descriptor 8). This paper discusses the combined approach of monitoring chemical contaminant levels, along side biological effect measurements relating to the effect of pollutants, for undertaking assessments of GES across European marine regions. We outline the minimum standards that biological effects tools should meet if they are to be used for defining GES in relation to Descriptor 8 and describe the current international initiatives underway to develop assessment criteria for these biological effects techniques. Crown Copyright (C) 2010 Published by Elsevier Ltd. All rights reserved.</datacite:description>
</datacite:descriptions>
<datacite:publisher>Poznań Supercomputing and Networking Center</datacite:publisher>
<contributors xmlns="http://datacite.org/schema/kernel-4">
<contributor>
<contributor contributorType="Researcher">
<contributorName>Generation Service</contributorName>
</contributor>
</contributor>
</contributors>
<creators xmlns="http://datacite.org/schema/kernel-4">
<creator>
<creator>
<creatorName>CNR-ISMAR</creatorName>
</creator>
</creator>
</creators>
<dates xmlns="http://datacite.org/schema/kernel-4">
<date dateType="Created">2018-06-20T11:21:46Z</date>
</dates>
<dc:descriptions>
<dc:description descriptionType="Abstract">The use of biological effects tools offer enormous potential to meet the challenges outlined by the European Union Marine Strategy Framework Directive (MSFD) whereby Member States are required to develop a robust set of tools for defining 11 qualitative descriptors of Good Environmental Status (GES), such as demonstrating that "Concentrations of contaminants are at levels not giving rise to pollution effects" (GES Descriptor 8). This paper discusses the combined approach of monitoring chemical contaminant levels, along side biological effect measurements relating to the effect of pollutants, for undertaking assessments of GES across European marine regions. We outline the minimum standards that biological effects tools should meet if they are to be used for defining GES in relation to Descriptor 8 and describe the current international initiatives underway to develop assessment criteria for these biological effects techniques. Crown Copyright (C) 2010 Published by Elsevier Ltd. All rights reserved.</dc:description>
</dc:descriptions>
<dc:publicationYear>2018</dc:publicationYear>
<rightsList xmlns="http://datacite.org/schema/kernel-4">
<rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</rights>
</rightsList>
<sizes xmlns="http://datacite.org/schema/kernel-4">
<size>3.866 KB</size>
</sizes>
<subjects xmlns="http://datacite.org/schema/kernel-4">
<subject>Ecology</subject>
<subject>EOSC::RO-crate</subject>
</subjects>
</datacite:resource>
<oaf:identifier identifierType="w3id">https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</oaf:identifier>
<dr:CobjCategory type="other research product">other research product</dr:CobjCategory>
<oaf:dateAccepted/>
<oaf:accessrights>OPEN</oaf:accessrights>
<oaf:language/>
<oaf:hostedBy name="ROHub" id="fairsharing_::4119"/>
<oaf:collectedFrom name="ROHub" id="fairsharing_::4119"/>
</metadata>
</record>

116
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/rohub.xml
View File

@ -1,103 +1,85 @@
<?xml version="1.0" encoding="UTF-8"?> <?xml version="1.0" encoding="UTF-8"?>
<record xmlns:datacite="http://datacite.org/schema/kernel-4" <record xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:datacite="http://datacite.org/schema/kernel-4"
xmlns:dr="http://www.driver-repository.eu/namespace/dr" xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:dri="http://www.driver-repository.eu/namespace/dri" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:oaf="http://namespace.openaire.eu/oaf" xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:dc="http://purl.org/dc/elements/1.1/">
<header xmlns="http://www.openarchives.org/OAI/2.0/"> <header xmlns="http://www.openarchives.org/OAI/2.0/">
<dri:objIdentifier>eosca5322f5f::4dd1aaf93ae136b65dc9ee4e6f76eac9</dri:objIdentifier> <identifier>https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</identifier>
<dri:recordIdentifier>53aa90bf-c593-4e6d-923f-d4711ac4b0e1</dri:recordIdentifier> <datestamp>2022-09-02T09:55:35Z</datestamp>
<dri:dateOfCollection>2022-05-25T15:35:48.262Z</dri:dateOfCollection>
<oaf:datasourceprefix>eosca5322f5f</oaf:datasourceprefix>
<identifier>53aa90bf-c593-4e6d-923f-d4711ac4b0e1</identifier>
<datestamp>2022-05-25T15:35:38Z</datestamp>
<setSpec>rohub_data</setSpec> <setSpec>rohub_data</setSpec>
<setSpec>ro-crate_data</setSpec> <setSpec>ro-crate_data</setSpec>
<dr:dateOfTransformation>2022-05-25T15:36:11.094Z</dr:dateOfTransformation> <dri:objIdentifier>fsh_____4119::afc7592914ae190a50570db90f55f9c2</dri:objIdentifier>
<dri:recordIdentifier>https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</dri:recordIdentifier>
<dri:dateOfCollection>2019-03-27T15:15:22.22Z</dri:dateOfCollection>
<oaf:datasourceprefix>fsh_____4119</oaf:datasourceprefix>
<dr:dateOfTransformation>2019-04-17T16:04:20.586Z</dr:dateOfTransformation>
</header> </header>
<metadata> <metadata>
<oaire:resource xmlns="http://namespace.openaire.eu/schema/oaire/"> <datacite:resource>
<datacite:identifier identifierType="landingPage">https://w3id.org/ro-id/53aa90bf-c593-4e6d-923f-d4711ac4b0e1</datacite:identifier> <datacite:identifier identifierType="URL">https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</datacite:identifier>
<datacite:alternateIdentifiers> <datacite:alternateIdentifiers/>
<datacite:alternateIdentifier alternateIdentifierType="URL">http://api.rohub.org/api/ros/53aa90bf-c593-4e6d-923f-d4711ac4b0e1/</datacite:alternateIdentifier>
</datacite:alternateIdentifiers>
<datacite:relatedIdentifiers> <datacite:relatedIdentifiers>
<datacite:relatedIdentifier relatedIdentifierType="" relationType=""> <datacite:relatedIdentifier relatedIdentifierType="" relationType="">
https://github.com/NordicESMhub/RELIANCE/blob/main/content/science/notebooks/air_quality_lockdown.ipynb https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca/resources/24fae96f-f986-46e1-bfd0-a21ca20ff0ce
</datacite:relatedIdentifier> </datacite:relatedIdentifier>
<datacite:relatedIdentifier relatedIdentifierType="URI" relationType="IsPartOf">https://github.com/NordicESMhub/RELIANCE/blob/main/content/science/notebooks/air_quality_lockdown.ipynb</datacite:relatedIdentifier>
<datacite:relatedIdentifier relatedIdentifierType="" relationType=""> <datacite:relatedIdentifier relatedIdentifierType="" relationType="">
https://nordicesmhub.github.io/RELIANCE/science/notebooks/air_quality_lockdown.html https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca/resources/6d3427a8-352e-49f4-9796-f618c44dc16d
</datacite:relatedIdentifier> </datacite:relatedIdentifier>
<datacite:relatedIdentifier relatedIdentifierType="URI" relationType="IsPartOf">https://nordicesmhub.github.io/RELIANCE/science/notebooks/air_quality_lockdown.html</datacite:relatedIdentifier>
</datacite:relatedIdentifiers> </datacite:relatedIdentifiers>
<datacite:resourceType xs:anyURI="http://purl.org/coar/resource_type/c_1843">RO-crate</datacite:resourceType>
<datacite:rightsList>
<datacite:rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</datacite:rights>
</datacite:rightsList>
<datacite:titles>
<datacite:title>Using biological effects tools to define Good Environmental Status under the European Union Marine Strategy Framework Directive</datacite:title>
</datacite:titles>
<datacite:descriptions>
<datacite:description descriptionType="Abstract">The use of biological effects tools offer enormous potential to meet the challenges outlined by the European Union Marine Strategy Framework Directive (MSFD) whereby Member States are required to develop a robust set of tools for defining 11 qualitative descriptors of Good Environmental Status (GES), such as demonstrating that "Concentrations of contaminants are at levels not giving rise to pollution effects" (GES Descriptor 8). This paper discusses the combined approach of monitoring chemical contaminant levels, along side biological effect measurements relating to the effect of pollutants, for undertaking assessments of GES across European marine regions. We outline the minimum standards that biological effects tools should meet if they are to be used for defining GES in relation to Descriptor 8 and describe the current international initiatives underway to develop assessment criteria for these biological effects techniques. Crown Copyright (C) 2010 Published by Elsevier Ltd. All rights reserved.</datacite:description>
</datacite:descriptions>
<datacite:publisher>Poznań Supercomputing and Networking Center</datacite:publisher>
<contributors xmlns="http://datacite.org/schema/kernel-4">
<contributor>
<contributor contributorType="Researcher">
<contributorName>Generation Service</contributorName>
</contributor>
</contributor>
</contributors>
<creators xmlns="http://datacite.org/schema/kernel-4"> <creators xmlns="http://datacite.org/schema/kernel-4">
<creator> <creator>
<creator> <creator>
<creatorName>Anne Fouilloux</creatorName> <creatorName>CNR-ISMAR</creatorName>
</creator> </creator>
</creator> </creator>
</creators> </creators>
<dates xmlns="http://datacite.org/schema/kernel-4"> <dates xmlns="http://datacite.org/schema/kernel-4">
<date dateType="Created">2021-12-19T21:18:33Z</date> <date dateType="Created">2018-06-20T11:21:46Z</date>
</dates> </dates>
<dc:descriptions> <dc:descriptions>
<dc:description descriptionType="Abstract">The COVID-19 pandemic has led to significant reductions in economic activity, especially during lockdowns. Several studies has shown that the concentration of nitrogen dioxyde and particulate matter levels have reduced during lockdown events. Reductions in transportation sector emissions are most likely largely responsible for the NO2 anomalies. In this study, we analyze the impact of lockdown events on the air quality using data from Copernicus Atmosphere Monitoring Service over Europe and at selected locations.</dc:description> <dc:description descriptionType="Abstract">The use of biological effects tools offer enormous potential to meet the challenges outlined by the European Union Marine Strategy Framework Directive (MSFD) whereby Member States are required to develop a robust set of tools for defining 11 qualitative descriptors of Good Environmental Status (GES), such as demonstrating that "Concentrations of contaminants are at levels not giving rise to pollution effects" (GES Descriptor 8). This paper discusses the combined approach of monitoring chemical contaminant levels, along side biological effect measurements relating to the effect of pollutants, for undertaking assessments of GES across European marine regions. We outline the minimum standards that biological effects tools should meet if they are to be used for defining GES in relation to Descriptor 8 and describe the current international initiatives underway to develop assessment criteria for these biological effects techniques. Crown Copyright (C) 2010 Published by Elsevier Ltd. All rights reserved.</dc:description>
</dc:descriptions> </dc:descriptions>
<oaire:fundingReferences> <dc:publicationYear>2018</dc:publicationYear>
<oaire:fundingReference>
<oaire:funderName>European Commission</oaire:funderName>
<oaire:funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000781</oaire:funderIdentifier>
<oaire:awardNumber awardURI="">101017502</oaire:awardNumber>
<oaire:awardTitle>Research Lifecycle Management for Earth Science Communities and Copernicus Users</oaire:awardTitle>
</oaire:fundingReference>
</oaire:fundingReferences>
<oaire:licenseCondition uri="https://opensource.org/licenses/MIT">MIT License</oaire:licenseCondition>
<dc:publisher>University of Oslo</dc:publisher>
<dc:publicationYear>2021</dc:publicationYear>
<oaire:resourceType resourceTypeGeneral="other research product" uri="http://purl.org/coar/resource_type/c_1843">RO-crate</oaire:resourceType>
<rightsList xmlns="http://datacite.org/schema/kernel-4"> <rightsList xmlns="http://datacite.org/schema/kernel-4">
<rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</rights> <rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</rights>
</rightsList> </rightsList>
<sizes xmlns="http://datacite.org/schema/kernel-4"> <sizes xmlns="http://datacite.org/schema/kernel-4">
<size>11.971 MB</size> <size>3.866 KB</size>
</sizes> </sizes>
<subjects xmlns="http://datacite.org/schema/kernel-4"> <subjects xmlns="http://datacite.org/schema/kernel-4">
<subject>Applied sciences</subject> <subject>Ecology</subject>
<subject>Meteorology</subject>
<subject>EOSC::RO-crate</subject> <subject>EOSC::RO-crate</subject>
</subjects> </subjects>
<titles xmlns="http://datacite.org/schema/kernel-4"> </datacite:resource>
<title>Impact of the Covid-19 Lockdown on Air quality over Europe</title> <oaf:identifier identifierType="URL">https://w3id.org/ro-id/0ab171a7-45c5-4194-82d4-850955504bca</oaf:identifier>
</titles> <dr:CobjCategory type="other research product">other research product</dr:CobjCategory>
</oaire:resource>
<oaf:identifier identifierType="URL">https://w3id.org/ro-id/53aa90bf-c593-4e6d-923f-d4711ac4b0e1</oaf:identifier>
<dr:CobjCategory type="other">0048</dr:CobjCategory>
<oaf:dateAccepted/> <oaf:dateAccepted/>
<oaf:accessrights>OPEN</oaf:accessrights> <oaf:accessrights>OPEN</oaf:accessrights>
<oaf:license>https://opensource.org/licenses/MIT</oaf:license> <oaf:language/>
<oaf:language>und</oaf:language> <oaf:hostedBy name="ROHub" id="fairsharing_::4119"/>
<oaf:hostedBy id="eosc________::psnc::psnc.rohub" name="ROHub"/> <oaf:collectedFrom name="ROHub" id="fairsharing_::4119"/>
<oaf:collectedFrom id="eosc________::psnc::psnc.rohub" name="ROHub"/>
</metadata> </metadata>
<about xmlns:oai="http://www.openarchives.org/OAI/2.0/" xmlns:prov="http://www.openarchives.org/OAI/2.0/provenance">
<provenance xmlns="http://www.openarchives.org/OAI/2.0/provenance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/provenance http://www.openarchives.org/OAI/2.0/provenance.xsd">
<originDescription altered="true" harvestDate="2022-05-25T15:35:48.262Z">
<baseURL>https%3A%2F%2Fapi.rohub.org%2Fapi%2Foai2d%2F</baseURL>
<identifier>53aa90bf-c593-4e6d-923f-d4711ac4b0e1</identifier>
<datestamp>2022-05-25T15:35:38Z</datestamp>
<metadataNamespace/>
</originDescription>
</provenance>
<oaf:datainfo>
<oaf:inferred>false</oaf:inferred>
<oaf:deletedbyinference>false</oaf:deletedbyinference>
<oaf:trust>0.9</oaf:trust>
<oaf:inferenceprovenance/>
<oaf:provenanceaction classid="sysimport:crosswalk"
classname="Harvested" schemeid="dnet:provenanceActions" schemename="dnet:provenanceActions"/>
</oaf:datainfo>
</about>
</record> </record>