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

Merge branch 'beta' into 7096-fileGZip-collector-plugin

This commit is contained in:
Claudio Atzori 2022-06-16 09:22:16 +02:00
parent 623f7be26d 88d531dc91
commit 06b5533d4c
64 changed files with 2685 additions and 667 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtils.java
View File

@ -3,6 +3,8 @@ package eu.dnetlib.dhp.schema.oaf.utils;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import java.sql.Array;
import java.sql.SQLException;
import java.util.*;
import java.util.concurrent.ConcurrentHashMap;
import java.util.function.Function;
@ -118,6 +120,17 @@ public class OafMapperUtils {
.collect(Collectors.toList());
}
public static <T> List<T> listValues(Array values) throws SQLException {
if (Objects.isNull(values)) {
return null;
}
return Arrays
.stream((T[]) values.getArray())
.filter(Objects::nonNull)
.distinct()
.collect(Collectors.toList());
}
public static List<Field<String>> listFields(final DataInfo info, final List<String> values) {
return values
.stream()

185
dhp-common/src/test/java/eu/dnetlib/dhp/schema/oaf/utils/OafMapperUtilsTest.java
View File

@ -44,105 +44,104 @@ class OafMapperUtilsTest {
@Test
void testDateValidation() {
assertTrue(GraphCleaningFunctions.doCleanDate("2016-05-07T12:41:19.202Z ").isPresent());
assertTrue(GraphCleaningFunctions.doCleanDate("2020-09-10 11:08:52 ").isPresent());
assertTrue(GraphCleaningFunctions.doCleanDate(" 2016-04-05").isPresent());
assertNotNull(GraphCleaningFunctions.cleanDate("2016-05-07T12:41:19.202Z "));
assertNotNull(GraphCleaningFunctions.cleanDate("2020-09-10 11:08:52 "));
assertNotNull(GraphCleaningFunctions.cleanDate(" 2016-04-05"));
assertEquals("2016-04-05", GraphCleaningFunctions.doCleanDate("2016 Apr 05").get());
assertEquals("2016-04-05", GraphCleaningFunctions.cleanDate("2016 Apr 05"));
assertEquals("2009-05-08", GraphCleaningFunctions.doCleanDate("May 8, 2009 5:57:51 PM").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("oct 7, 1970").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("oct 7, '70").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("oct. 7, 1970").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("oct. 7, 70").get());
assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("Mon Jan 2 15:04:05 2006").get());
assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("Mon Jan 2 15:04:05 MST 2006").get());
assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("Mon Jan 02 15:04:05 -0700 2006").get());
assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("Monday, 02-Jan-06 15:04:05 MST").get());
assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("Mon, 02 Jan 2006 15:04:05 MST").get());
assertEquals("2017-07-11", GraphCleaningFunctions.doCleanDate("Tue, 11 Jul 2017 16:28:13 +0200 (CEST)").get());
assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("Mon, 02 Jan 2006 15:04:05 -0700").get());
assertEquals("2018-01-04", GraphCleaningFunctions.doCleanDate("Thu, 4 Jan 2018 17:53:36 +0000").get());
assertEquals("2015-08-10", GraphCleaningFunctions.doCleanDate("Mon Aug 10 15:44:11 UTC+0100 2015").get());
assertEquals("2009-05-08", GraphCleaningFunctions.cleanDate("May 8, 2009 5:57:51 PM"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("oct 7, 1970"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("oct 7, '70"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("oct. 7, 1970"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("oct. 7, 70"));
assertEquals("2006-01-02", GraphCleaningFunctions.cleanDate("Mon Jan 2 15:04:05 2006"));
assertEquals("2006-01-02", GraphCleaningFunctions.cleanDate("Mon Jan 2 15:04:05 MST 2006"));
assertEquals("2006-01-02", GraphCleaningFunctions.cleanDate("Mon Jan 02 15:04:05 -0700 2006"));
assertEquals("2006-01-02", GraphCleaningFunctions.cleanDate("Monday, 02-Jan-06 15:04:05 MST"));
assertEquals("2006-01-02", GraphCleaningFunctions.cleanDate("Mon, 02 Jan 2006 15:04:05 MST"));
assertEquals("2017-07-11", GraphCleaningFunctions.cleanDate("Tue, 11 Jul 2017 16:28:13 +0200 (CEST)"));
assertEquals("2006-01-02", GraphCleaningFunctions.cleanDate("Mon, 02 Jan 2006 15:04:05 -0700"));
assertEquals("2018-01-04", GraphCleaningFunctions.cleanDate("Thu, 4 Jan 2018 17:53:36 +0000"));
assertEquals("2015-08-10", GraphCleaningFunctions.cleanDate("Mon Aug 10 15:44:11 UTC+0100 2015"));
assertEquals(
"2015-07-03",
GraphCleaningFunctions.doCleanDate("Fri Jul 03 2015 18:04:07 GMT+0100 (GMT Daylight Time)").get());
assertEquals("2012-09-17", GraphCleaningFunctions.doCleanDate("September 17, 2012 10:09am").get());
assertEquals("2012-09-17", GraphCleaningFunctions.doCleanDate("September 17, 2012 at 10:09am PST-08").get());
assertEquals("2012-09-17", GraphCleaningFunctions.doCleanDate("September 17, 2012, 10:10:09").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("October 7, 1970").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("October 7th, 1970").get());
assertEquals("2006-02-12", GraphCleaningFunctions.doCleanDate("12 Feb 2006, 19:17").get());
assertEquals("2006-02-12", GraphCleaningFunctions.doCleanDate("12 Feb 2006 19:17").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("7 oct 70").get());
assertEquals("1970-10-07", GraphCleaningFunctions.doCleanDate("7 oct 1970").get());
assertEquals("2013-02-03", GraphCleaningFunctions.doCleanDate("03 February 2013").get());
assertEquals("2013-07-01", GraphCleaningFunctions.doCleanDate("1 July 2013").get());
assertEquals("2013-02-03", GraphCleaningFunctions.doCleanDate("2013-Feb-03").get());
assertEquals("2014-03-31", GraphCleaningFunctions.doCleanDate("3/31/2014").get());
assertEquals("2014-03-31", GraphCleaningFunctions.doCleanDate("03/31/2014").get());
assertEquals("1971-08-21", GraphCleaningFunctions.doCleanDate("08/21/71").get());
assertEquals("1971-01-08", GraphCleaningFunctions.doCleanDate("8/1/71").get());
assertEquals("2014-08-04", GraphCleaningFunctions.doCleanDate("4/8/2014 22:05").get());
assertEquals("2014-08-04", GraphCleaningFunctions.doCleanDate("04/08/2014 22:05").get());
assertEquals("2014-08-04", GraphCleaningFunctions.doCleanDate("4/8/14 22:05").get());
assertEquals("2014-02-04", GraphCleaningFunctions.doCleanDate("04/2/2014 03:00:51").get());
assertEquals("1965-08-08", GraphCleaningFunctions.doCleanDate("8/8/1965 12:00:00 AM").get());
assertEquals("1965-08-08", GraphCleaningFunctions.doCleanDate("8/8/1965 01:00:01 PM").get());
assertEquals("1965-08-08", GraphCleaningFunctions.doCleanDate("8/8/1965 01:00 PM").get());
assertEquals("1965-08-08", GraphCleaningFunctions.doCleanDate("8/8/1965 1:00 PM").get());
assertEquals("1965-08-08", GraphCleaningFunctions.doCleanDate("8/8/1965 12:00 AM").get());
assertEquals("2014-02-04", GraphCleaningFunctions.doCleanDate("4/02/2014 03:00:51").get());
assertEquals("2012-03-19", GraphCleaningFunctions.doCleanDate("03/19/2012 10:11:59").get());
assertEquals("2012-03-19", GraphCleaningFunctions.doCleanDate("03/19/2012 10:11:59.3186369").get());
assertEquals("2014-03-31", GraphCleaningFunctions.doCleanDate("2014/3/31").get());
assertEquals("2014-03-31", GraphCleaningFunctions.doCleanDate("2014/03/31").get());
assertEquals("2014-04-08", GraphCleaningFunctions.doCleanDate("2014/4/8 22:05").get());
assertEquals("2014-04-08", GraphCleaningFunctions.doCleanDate("2014/04/08 22:05").get());
assertEquals("2014-04-02", GraphCleaningFunctions.doCleanDate("2014/04/2 03:00:51").get());
assertEquals("2014-04-02", GraphCleaningFunctions.doCleanDate("2014/4/02 03:00:51").get());
assertEquals("2012-03-19", GraphCleaningFunctions.doCleanDate("2012/03/19 10:11:59").get());
assertEquals("2012-03-19", GraphCleaningFunctions.doCleanDate("2012/03/19 10:11:59.3186369").get());
assertEquals("2014-04-08", GraphCleaningFunctions.doCleanDate("2014年04月08日").get());
assertEquals("2006-01-02", GraphCleaningFunctions.doCleanDate("2006-01-02T15:04:05+0000").get());
assertEquals("2009-08-13", GraphCleaningFunctions.doCleanDate("2009-08-12T22:15:09-07:00").get());
assertEquals("2009-08-12", GraphCleaningFunctions.doCleanDate("2009-08-12T22:15:09").get());
assertEquals("2009-08-13", GraphCleaningFunctions.doCleanDate("2009-08-12T22:15:09Z").get());
assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 17:24:37.3186369").get());
assertEquals("2012-08-03", GraphCleaningFunctions.doCleanDate("2012-08-03 18:31:59.257000000").get());
assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 17:24:37.123").get());
assertEquals("2013-04-01", GraphCleaningFunctions.doCleanDate("2013-04-01 22:43").get());
assertEquals("2013-04-01", GraphCleaningFunctions.doCleanDate("2013-04-01 22:43:22").get());
assertEquals("2014-12-16", GraphCleaningFunctions.doCleanDate("2014-12-16 06:20:00 UTC").get());
assertEquals("2014-12-16", GraphCleaningFunctions.doCleanDate("2014-12-16 06:20:00 GMT").get());
assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 05:24:37 PM").get());
assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 13:13:43 +0800").get());
assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 13:13:43 +0800 +08").get());
assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26 13:13:44 +09:00").get());
assertEquals("2012-08-03", GraphCleaningFunctions.doCleanDate("2012-08-03 18:31:59.257000000 +0000 UTC").get());
assertEquals("2015-09-30", GraphCleaningFunctions.doCleanDate("2015-09-30 18:48:56.35272715 +0000 UTC").get());
assertEquals("2015-02-18", GraphCleaningFunctions.doCleanDate("2015-02-18 00:12:00 +0000 GMT").get());
assertEquals("2015-02-18", GraphCleaningFunctions.doCleanDate("2015-02-18 00:12:00 +0000 UTC").get());
GraphCleaningFunctions.cleanDate("Fri Jul 03 2015 18:04:07 GMT+0100 (GMT Daylight Time)"));
assertEquals("2012-09-17", GraphCleaningFunctions.cleanDate("September 17, 2012 10:09am"));
assertEquals("2012-09-17", GraphCleaningFunctions.cleanDate("September 17, 2012 at 10:09am PST-08"));
assertEquals("2012-09-17", GraphCleaningFunctions.cleanDate("September 17, 2012, 10:10:09"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("October 7, 1970"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("October 7th, 1970"));
assertEquals("2006-02-12", GraphCleaningFunctions.cleanDate("12 Feb 2006, 19:17"));
assertEquals("2006-02-12", GraphCleaningFunctions.cleanDate("12 Feb 2006 19:17"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("7 oct 70"));
assertEquals("1970-10-07", GraphCleaningFunctions.cleanDate("7 oct 1970"));
assertEquals("2013-02-03", GraphCleaningFunctions.cleanDate("03 February 2013"));
assertEquals("2013-07-01", GraphCleaningFunctions.cleanDate("1 July 2013"));
assertEquals("2013-02-03", GraphCleaningFunctions.cleanDate("2013-Feb-03"));
assertEquals("2014-03-31", GraphCleaningFunctions.cleanDate("3/31/2014"));
assertEquals("2014-03-31", GraphCleaningFunctions.cleanDate("03/31/2014"));
assertEquals("1971-08-21", GraphCleaningFunctions.cleanDate("08/21/71"));
assertEquals("1971-01-08", GraphCleaningFunctions.cleanDate("8/1/71"));
assertEquals("2014-08-04", GraphCleaningFunctions.cleanDate("4/8/2014 22:05"));
assertEquals("2014-08-04", GraphCleaningFunctions.cleanDate("04/08/2014 22:05"));
assertEquals("2014-08-04", GraphCleaningFunctions.cleanDate("4/8/14 22:05"));
assertEquals("2014-02-04", GraphCleaningFunctions.cleanDate("04/2/2014 03:00:51"));
assertEquals("1965-08-08", GraphCleaningFunctions.cleanDate("8/8/1965 12:00:00 AM"));
assertEquals("1965-08-08", GraphCleaningFunctions.cleanDate("8/8/1965 01:00:01 PM"));
assertEquals("1965-08-08", GraphCleaningFunctions.cleanDate("8/8/1965 01:00 PM"));
assertEquals("1965-08-08", GraphCleaningFunctions.cleanDate("8/8/1965 1:00 PM"));
assertEquals("1965-08-08", GraphCleaningFunctions.cleanDate("8/8/1965 12:00 AM"));
assertEquals("2014-02-04", GraphCleaningFunctions.cleanDate("4/02/2014 03:00:51"));
assertEquals("2012-03-19", GraphCleaningFunctions.cleanDate("03/19/2012 10:11:59"));
assertEquals("2012-03-19", GraphCleaningFunctions.cleanDate("03/19/2012 10:11:59.3186369"));
assertEquals("2014-03-31", GraphCleaningFunctions.cleanDate("2014/3/31"));
assertEquals("2014-03-31", GraphCleaningFunctions.cleanDate("2014/03/31"));
assertEquals("2014-04-08", GraphCleaningFunctions.cleanDate("2014/4/8 22:05"));
assertEquals("2014-04-08", GraphCleaningFunctions.cleanDate("2014/04/08 22:05"));
assertEquals("2014-04-02", GraphCleaningFunctions.cleanDate("2014/04/2 03:00:51"));
assertEquals("2014-04-02", GraphCleaningFunctions.cleanDate("2014/4/02 03:00:51"));
assertEquals("2012-03-19", GraphCleaningFunctions.cleanDate("2012/03/19 10:11:59"));
assertEquals("2012-03-19", GraphCleaningFunctions.cleanDate("2012/03/19 10:11:59.3186369"));
assertEquals("2014-04-08", GraphCleaningFunctions.cleanDate("2014年04月08日"));
assertEquals("2006-01-02", GraphCleaningFunctions.cleanDate("2006-01-02T15:04:05+0000"));
assertEquals("2009-08-13", GraphCleaningFunctions.cleanDate("2009-08-12T22:15:09-07:00"));
assertEquals("2009-08-12", GraphCleaningFunctions.cleanDate("2009-08-12T22:15:09"));
assertEquals("2014-04-26", GraphCleaningFunctions.cleanDate("2014-04-26 17:24:37.3186369"));
assertEquals("2012-08-03", GraphCleaningFunctions.cleanDate("2012-08-03 18:31:59.257000000"));
assertEquals("2014-04-26", GraphCleaningFunctions.cleanDate("2014-04-26 17:24:37.123"));
assertEquals("2013-04-01", GraphCleaningFunctions.cleanDate("2013-04-01 22:43"));
assertEquals("2013-04-01", GraphCleaningFunctions.cleanDate("2013-04-01 22:43:22"));
assertEquals("2014-12-16", GraphCleaningFunctions.cleanDate("2014-12-16 06:20:00 UTC"));
assertEquals("2014-12-16", GraphCleaningFunctions.cleanDate("2014-12-16 06:20:00 GMT"));
assertEquals("2014-04-26", GraphCleaningFunctions.cleanDate("2014-04-26 05:24:37 PM"));
assertEquals("2014-04-26", GraphCleaningFunctions.cleanDate("2014-04-26 13:13:43 +0800"));
assertEquals("2014-04-26", GraphCleaningFunctions.cleanDate("2014-04-26 13:13:43 +0800 +08"));
assertEquals("2014-04-26", GraphCleaningFunctions.cleanDate("2014-04-26 13:13:44 +09:00"));
assertEquals("2012-08-03", GraphCleaningFunctions.cleanDate("2012-08-03 18:31:59.257000000 +0000 UTC"));
assertEquals("2015-09-30", GraphCleaningFunctions.cleanDate("2015-09-30 18:48:56.35272715 +0000 UTC"));
assertEquals("2015-02-18", GraphCleaningFunctions.cleanDate("2015-02-18 00:12:00 +0000 GMT"));
assertEquals("2015-02-18", GraphCleaningFunctions.cleanDate("2015-02-18 00:12:00 +0000 UTC"));
assertEquals(
"2015-02-08", GraphCleaningFunctions.doCleanDate("2015-02-08 03:02:00 +0300 MSK m=+0.000000001").get());
"2015-02-08", GraphCleaningFunctions.cleanDate("2015-02-08 03:02:00 +0300 MSK m=+0.000000001"));
assertEquals(
"2015-02-08", GraphCleaningFunctions.doCleanDate("2015-02-08 03:02:00.001 +0300 MSK m=+0.000000001").get());
assertEquals("2017-07-19", GraphCleaningFunctions.doCleanDate("2017-07-19 03:21:51+00:00").get());
assertEquals("2014-04-26", GraphCleaningFunctions.doCleanDate("2014-04-26").get());
assertEquals("2014-04-01", GraphCleaningFunctions.doCleanDate("2014-04").get());
assertEquals("2014-01-01", GraphCleaningFunctions.doCleanDate("2014").get());
assertEquals("2014-05-11", GraphCleaningFunctions.doCleanDate("2014-05-11 08:20:13,787").get());
assertEquals("2014-03-31", GraphCleaningFunctions.doCleanDate("3.31.2014").get());
assertEquals("2014-03-31", GraphCleaningFunctions.doCleanDate("03.31.2014").get());
assertEquals("1971-08-21", GraphCleaningFunctions.doCleanDate("08.21.71").get());
assertEquals("2014-03-01", GraphCleaningFunctions.doCleanDate("2014.03").get());
assertEquals("2014-03-30", GraphCleaningFunctions.doCleanDate("2014.03.30").get());
assertEquals("2014-06-01", GraphCleaningFunctions.doCleanDate("20140601").get());
assertEquals("2014-07-22", GraphCleaningFunctions.doCleanDate("20140722105203").get());
assertEquals("2012-03-19", GraphCleaningFunctions.doCleanDate("1332151919").get());
assertEquals("2013-11-12", GraphCleaningFunctions.doCleanDate("1384216367189").get());
assertEquals("2013-11-12", GraphCleaningFunctions.doCleanDate("1384216367111222").get());
assertEquals("2013-11-12", GraphCleaningFunctions.doCleanDate("1384216367111222333").get());
"2015-02-08", GraphCleaningFunctions.cleanDate("2015-02-08 03:02:00.001 +0300 MSK m=+0.000000001"));
assertEquals("2017-07-19", GraphCleaningFunctions.cleanDate("2017-07-19 03:21:51+00:00"));
assertEquals("2014-04-26", GraphCleaningFunctions.cleanDate("2014-04-26"));
assertEquals("2014-04-01", GraphCleaningFunctions.cleanDate("2014-04"));
assertEquals("2014-01-01", GraphCleaningFunctions.cleanDate("2014"));
assertEquals("2014-05-11", GraphCleaningFunctions.cleanDate("2014-05-11 08:20:13,787"));
assertEquals("2014-03-31", GraphCleaningFunctions.cleanDate("3.31.2014"));
assertEquals("2014-03-31", GraphCleaningFunctions.cleanDate("03.31.2014"));
assertEquals("1971-08-21", GraphCleaningFunctions.cleanDate("08.21.71"));
assertEquals("2014-03-01", GraphCleaningFunctions.cleanDate("2014.03"));
assertEquals("2014-03-30", GraphCleaningFunctions.cleanDate("2014.03.30"));
assertEquals("2014-06-01", GraphCleaningFunctions.cleanDate("20140601"));
assertEquals("2014-07-22", GraphCleaningFunctions.cleanDate("20140722105203"));
assertEquals("2012-03-19", GraphCleaningFunctions.cleanDate("1332151919"));
assertEquals("2013-11-12", GraphCleaningFunctions.cleanDate("1384216367189"));
assertEquals("2013-11-12", GraphCleaningFunctions.cleanDate("1384216367111222"));
assertEquals("2013-11-12", GraphCleaningFunctions.cleanDate("1384216367111222333"));
}

31
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/ror/GenerateRorActionSetJob.java
View File

@ -3,7 +3,6 @@ package eu.dnetlib.dhp.actionmanager.ror;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static eu.dnetlib.dhp.schema.common.ModelConstants.ENTITYREGISTRY_PROVENANCE_ACTION;
import static eu.dnetlib.dhp.schema.common.ModelConstants.ORG_ORG_RELTYPE;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.dataInfo;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.field;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.listKeyValues;
@ -39,7 +38,6 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.ror.model.ExternalIdType;
import eu.dnetlib.dhp.actionmanager.ror.model.Relationship;
import eu.dnetlib.dhp.actionmanager.ror.model.RorOrganization;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
@ -51,7 +49,6 @@ import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.utils.DHPUtils;
import scala.Tuple2;
@ -168,38 +165,10 @@ public class GenerateRorActionSetJob {
final List<AtomicAction<? extends Oaf>> res = new ArrayList<>();
res.add(new AtomicAction<>(Organization.class, o));
for (final Relationship rorRel : r.getRelationships()) {
if (rorRel.getType().equalsIgnoreCase("parent")) {
final String orgId1 = calculateOpenaireId(r.getId());
final String orgId2 = calculateOpenaireId(rorRel.getId());
res
.add(
new AtomicAction<>(Relation.class,
calculateHierarchyRel(orgId1, orgId2, ModelConstants.IS_PARENT_OF)));
res
.add(
new AtomicAction<>(Relation.class,
calculateHierarchyRel(orgId2, orgId1, ModelConstants.IS_CHILD_OF)));
}
}
return res;
}
private static Relation calculateHierarchyRel(final String source, final String target, final String relClass) {
final Relation rel = new Relation();
rel.setSource(source);
rel.setTarget(target);
rel.setRelType(ORG_ORG_RELTYPE);
rel.setSubRelType(ModelConstants.RELATIONSHIP);
rel.setRelClass(relClass);
rel.setCollectedfrom(ROR_COLLECTED_FROM);
rel.setDataInfo(ROR_DATA_INFO);
rel.setLastupdatetimestamp(System.currentTimeMillis());
return rel;
}
private static String calculateOpenaireId(final String rorId) {
return String.format("20|%s::%s", ROR_NS_PREFIX, DHPUtils.md5(rorId));
}

19
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/usagestats/SparkAtomicActionUsageJob.java
View File

@ -10,6 +10,8 @@ import java.util.List;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
@ -24,11 +26,13 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Measure;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import scala.Tuple2;
/**
* created the Atomic Action for each type of results
@ -73,7 +77,7 @@ public class SparkAtomicActionUsageJob implements Serializable {
spark -> {
removeOutputDir(spark, outputPath);
prepareResults(dbname, spark, workingPath);
prepareActionSet(spark, workingPath, outputPath);
writeActionSet(spark, workingPath, outputPath);
});
}
@ -89,7 +93,7 @@ public class SparkAtomicActionUsageJob implements Serializable {
.json(workingPath);
}
public static void prepareActionSet(SparkSession spark, String inputPath, String outputPath) {
public static void writeActionSet(SparkSession spark, String inputPath, String outputPath) {
readPath(spark, inputPath, UsageStatsModel.class)
.groupByKey((MapFunction<UsageStatsModel, String>) us -> us.getResult_id(), Encoders.STRING())
.mapGroups((MapGroupsFunction<String, UsageStatsModel, Result>) (k, it) -> {
@ -105,10 +109,13 @@ public class SparkAtomicActionUsageJob implements Serializable {
res.setMeasures(getMeasure(first.getDownloads(), first.getViews()));
return res;
}, Encoders.bean(Result.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
.toJavaRDD()
.map(p -> new AtomicAction(p.getClass(), p))
.mapToPair(
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
}
private static List<Measure> getMeasure(Long downloads, Long views) {

15
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/datacite/hostedBy_map.json
View File

@ -15,7 +15,7 @@
"official_name": "Aperta TÜBİTAK Open Archive"
},
"BL.CAM": {
"openaire_id": "re3data_____::r3d100010620",
"openaire_id": "opendoar____::109",
"datacite_name": "Apollo",
"official_name": "Apollo"
},
@ -196,7 +196,7 @@
},
"CSIC.DIGITAL": {
"openaire_id": "re3data_____::r3d100011076",
"datacite_name": "DIGITAL.CSIC",
"datacite_name": "Digital CSIC",
"official_name": "DIGITAL.CSIC"
},
"BL.DRI": {
@ -644,6 +644,11 @@
"datacite_name": "PANGAEA",
"official_name": "PANGAEA"
},
"TIB.PANGAEA": {
"openaire_id": "re3data_____::r3d100010134",
"datacite_name": "PANGAEA",
"official_name": "PANGAEA"
},
"NASAPDS.NASAPDS": {
"openaire_id": "re3data_____::r3d100010121",
"datacite_name": "PDS",
@ -896,7 +901,7 @@
},
"FIGSHARE.UCT": {
"openaire_id": "re3data_____::r3d100012633",
"datacite_name": "ZivaHub",
"datacite_name": "University of Cape Town (UCT)",
"official_name": "ZivaHub"
},
"BL.UCLAN": {
@ -1030,9 +1035,9 @@
"official_name": "ZBW Journal Data Archive"
},
"CERN.ZENODO": {
"openaire_id": "re3data_____::r3d100010468",
"openaire_id": "opendoar____::2659",
"datacite_name": "Zenodo",
"official_name": "Zenodo"
"official_name": "ZENODO"
},
"ZBW.ZEW": {
"openaire_id": "re3data_____::r3d100010399",

18
dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTransformation.scala
View File

@ -47,13 +47,18 @@ object DataciteToOAFTransformation {
}
/** This method should skip record if json contains invalid text
* defined in gile datacite_filter
* defined in file datacite_filter
*
* @param json
* @param record : unparsed datacite record
* @param json : parsed record
* @return True if the record should be skipped
*/
def skip_record(json: String): Boolean = {
datacite_filter.exists(f => json.contains(f))
def skip_record(record: String, json: org.json4s.JValue): Boolean = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
datacite_filter.exists(f => record.contains(f)) || (json \\ "publisher")
.extractOrElse[String]("")
.equalsIgnoreCase("FAIRsharing")
}
@deprecated("this method will be removed", "dhp")
@ -304,12 +309,13 @@ object DataciteToOAFTransformation {
vocabularies: VocabularyGroup,
exportLinks: Boolean
): List[Oaf] = {
if (skip_record(input))
return List()
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json = parse(input)
if (skip_record(input, json))
return List()
val resourceType = (json \ "attributes" \ "types" \ "resourceType").extractOrElse[String](null)
val resourceTypeGeneral =
(json \ "attributes" \ "types" \ "resourceTypeGeneral").extractOrElse[String](null)

11
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/usagestats/SparkAtomicActionCountJobTest.java
View File

@ -13,9 +13,6 @@ import org.apache.hadoop.io.Text;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.Assertions;
@ -26,7 +23,6 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.bipfinder.SparkAtomicActionScoreJob;
import eu.dnetlib.dhp.schema.action.AtomicAction;
import eu.dnetlib.dhp.schema.oaf.Result;
@ -75,13 +71,14 @@ public class SparkAtomicActionCountJobTest {
.getResource("/eu/dnetlib/dhp/actionmanager/usagestats/usagestatsdb")
.getPath();
SparkAtomicActionUsageJob.prepareActionSet(spark, usageScoresPath, workingDir.toString() + "/actionSet");
SparkAtomicActionUsageJob.writeActionSet(spark, usageScoresPath, workingDir.toString() + "/actionSet");
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
.textFile(workingDir.toString() + "/actionSet")
.map(usm -> OBJECT_MAPPER.readValue(usm, Result.class));
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.map(usm -> OBJECT_MAPPER.readValue(usm._2.getBytes(), AtomicAction.class))
.map(aa -> (Result) aa.getPayload());
Assertions.assertEquals(9, tmp.count());

1
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/datacite/record_fairsharing.json Normal file
View File

File diff suppressed because one or more lines are too long

15
dhp-workflows/dhp-aggregation/src/test/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTest.scala
View File

@ -107,4 +107,19 @@ class DataciteToOAFTest extends AbstractVocabularyTest {
}
@Test
def testFilter(): Unit = {
val record = Source
.fromInputStream(
getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/record_fairsharing.json")
)
.mkString
val mapper = new ObjectMapper().enable(SerializationFeature.INDENT_OUTPUT)
val res: List[Oaf] = DataciteToOAFTransformation.generateOAF(record, 0L, 0L, vocabularies, true)
assertTrue(res.isEmpty)
}
}

2
dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/SparkGenerateDoiBoost.scala
View File

@ -284,4 +284,4 @@ object SparkGenerateDoiBoost {
.save(s"$workingDirPath/doiBoostOrganization")
}
}
}

19
dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/Crossref2Oaf.scala
View File

@ -2,7 +2,7 @@ package eu.dnetlib.doiboost.crossref
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf._
import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, OafMapperUtils}
import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, IdentifierFactory, OafMapperUtils}
import eu.dnetlib.dhp.utils.DHPUtils
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
@ -280,10 +280,10 @@ case object Crossref2Oaf {
instance.setDateofacceptance(asField(createdDate.getValue))
}
val s: List[String] = List("https://doi.org/" + doi)
// val links: List[String] = ((for {JString(url) <- json \ "link" \ "URL"} yield url) ::: List(s)).filter(p => p != null && p.toLowerCase().contains(doi.toLowerCase())).distinct
// if (links.nonEmpty) {
// instance.setUrl(links.asJava)
// }
// val links: List[String] = ((for {JString(url) <- json \ "link" \ "URL"} yield url) ::: List(s)).filter(p => p != null && p.toLowerCase().contains(doi.toLowerCase())).distinct
// if (links.nonEmpty) {
// instance.setUrl(links.asJava)
// }
if (s.nonEmpty) {
instance.setUrl(s.asJava)
}
@ -576,14 +576,19 @@ case object Crossref2Oaf {
def extractDate(dt: String, datePart: List[List[Int]]): String = {
if (StringUtils.isNotBlank(dt))
return dt
return GraphCleaningFunctions.cleanDate(dt)
if (datePart != null && datePart.size == 1) {
val res = datePart.head
if (res.size == 3) {
val dp = f"${res.head}-${res(1)}%02d-${res(2)}%02d"
if (dp.length == 10) {
return dp
return GraphCleaningFunctions.cleanDate(dp)
}
} else if (res.size == 2) {
val dp = f"${res.head}-${res(1)}%02d-01"
return GraphCleaningFunctions.cleanDate(dp)
} else if (res.size == 1) {
return GraphCleaningFunctions.cleanDate(s"${res.head}-01-01")
}
}
null

330
dhp-workflows/dhp-doiboost/src/test/resources/eu/dnetlib/doiboost/crossref/issue_date.json Normal file
View File

@ -0,0 +1,330 @@
{
"indexed":{
"date-parts":[
[
2022,
4,
14
]
],
"date-time":"2022-04-14T11:27:30Z",
"timestamp":1649935650109
},
"reference-count":22,
"publisher":"SAGE Publications",
"issue":"2",
"license":[
{
"start":{
"date-parts":[
[
1980,
4,
1
]
],
"date-time":"1980-04-01T00:00:00Z",
"timestamp":323395200000
},
"content-version":"tdm",
"delay-in-days":0,
"URL":"http:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"
}
],
"content-domain":{
"domain":[
],
"crossmark-restriction":false
},
"short-container-title":[
"Perception"
],
"published-print":{
"date-parts":[
[
1980,
4
]
]
},
"abstract":"<jats:p> To answer the question \u2018What is suppressed during binocular rivalry?\u2019 a series of three experiments was performed. In the first experiment observers viewed binocular rivalry between orthogonally oriented patterns. When the dominant and suppressed patterns were interchanged between the eyes observers continued seeing with the dominant eye, indicating that an eye, not a pattern, is suppressed during rivalry. In a second experiment it was found that a suppressed eye was able to contribute to stereopsis. A third experiment demonstrated that the predominance of an eye could be influenced by prior adaptation of the other eye, indicating that binocular mechanisms participate in the rivalry process. <\/jats:p>",
"DOI":"10.1068\/p090223",
"type":"journal-article",
"created":{
"date-parts":[
[
2007,
1,
23
]
],
"date-time":"2007-01-23T15:21:36Z",
"timestamp":1169565696000
},
"page":"223-231",
"source":"Crossref",
"is-referenced-by-count":123,
"title":[
"What is Suppressed during Binocular Rivalry?"
],
"prefix":"10.1177",
"volume":"9",
"author":[
{
"given":"Randolph",
"family":"Blake",
"sequence":"first",
"affiliation":[
{
"name":"Cresap Neuroscience Laboratory, Northwestern University, Evanston, Illinois 60201, USA"
}
]
},
{
"given":"David H",
"family":"Westendorf",
"sequence":"additional",
"affiliation":[
{
"name":"Department of Psychology, University of Arkansas, Fayetteville, Arkansas 72701, USA"
}
]
},
{
"given":"Randall",
"family":"Overton",
"sequence":"additional",
"affiliation":[
{
"name":"Department of Psychology, Illinois State University, Normal, Illinois 61761, USA"
}
]
}
],
"member":"179",
"published-online":{
"date-parts":[
[
2016,
6,
25
]
]
},
"reference":[
{
"key":"bibr1-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1136\/bjo.37.1.37"
},
{
"key":"bibr2-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1037\/0096-1523.5.2.315"
},
{
"key":"bibr3-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1016\/0042-6989(74)90065-0"
},
{
"key":"bibr4-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1068\/p080143"
},
{
"key":"bibr5-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1016\/0042-6989(70)90036-2"
},
{
"key":"bibr6-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1113\/jphysiol.1969.sp008862"
},
{
"key":"bibr7-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1113\/jphysiol.1972.sp010006"
},
{
"key":"bibr8-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1146\/annurev.ps.23.020172.002213"
},
{
"key":"bibr9-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1126\/science.166.3902.245"
},
{
"key":"bibr10-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1037\/h0075805"
},
{
"key":"bibr11-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1113\/jphysiol.1968.sp008552"
},
{
"key":"bibr12-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1113\/jphysiol.1965.sp007784"
},
{
"key":"bibr13-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1037\/h0032455"
},
{
"key":"bibr14-p090223",
"volume-title":"Treatise on Physiological Optics",
"volume":"3",
"author":"von Helmholtz H",
"year":"1866",
"edition":"3"
},
{
"key":"bibr15-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1068\/p040125"
},
{
"key":"bibr16-p090223",
"volume-title":"On Binocular Rivalry",
"author":"Levelt W J M",
"year":"1965"
},
{
"key":"bibr17-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1001\/archopht.1935.00840020011001"
},
{
"key":"bibr18-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.3758\/BF03205796"
},
{
"key":"bibr19-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.3758\/BF03210180"
},
{
"key":"bibr20-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1037\/0033-2909.85.2.376"
},
{
"key":"bibr21-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.1016\/0042-6989(79)90169-X"
},
{
"key":"bibr22-p090223",
"doi-asserted-by":"publisher",
"DOI":"10.3758\/BF03210465"
}
],
"container-title":[
"Perception"
],
"original-title":[
],
"language":"en",
"link":[
{
"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1068\/p090223",
"content-type":"application\/pdf",
"content-version":"vor",
"intended-application":"text-mining"
},
{
"URL":"http:\/\/journals.sagepub.com\/doi\/pdf\/10.1068\/p090223",
"content-type":"unspecified",
"content-version":"vor",
"intended-application":"similarity-checking"
}
],
"deposited":{
"date-parts":[
[
2021,
12,
3
]
],
"date-time":"2021-12-03T11:49:48Z",
"timestamp":1638532188000
},
"score":1,
"resource":{
"primary":{
"URL":"http:\/\/journals.sagepub.com\/doi\/10.1068\/p090223"
}
},
"subtitle":[
],
"short-title":[
],
"issued":{
"date-parts":[
[
1980,
4
]
]
},
"references-count":22,
"journal-issue":{
"issue":"2",
"published-print":{
"date-parts":[
[
1980,
4
]
]
}
},
"alternative-id":[
"10.1068\/p090223"
],
"URL":"http:\/\/dx.doi.org\/10.1068\/p090223",
"relation":{
},
"ISSN":[
"0301-0066",
"1468-4233"
],
"issn-type":[
{
"value":"0301-0066",
"type":"print"
},
{
"value":"1468-4233",
"type":"electronic"
}
],
"subject":[
"Artificial Intelligence",
"Sensory Systems",
"Experimental and Cognitive Psychology",
"Ophthalmology"
],
"published":{
"date-parts":[
[
1980,
4
]
]
}
}

16
dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala
View File

@ -73,6 +73,20 @@ class CrossrefMappingTest {
}
@Test
def crossrefIssueDateTest(): Unit = {
val json =
Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/issue_date.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty)
val resultList: List[Oaf] = Crossref2Oaf.convert(json)
assertTrue(resultList.nonEmpty)
val items = resultList.filter(p => p.isInstanceOf[Result])
println(mapper.writeValueAsString(items.head))
}
@Test
def testOrcidID(): Unit = {
val json = Source
@ -82,7 +96,7 @@ class CrossrefMappingTest {
.mkString
assertNotNull(json)
assertFalse(json.isEmpty);
assertFalse(json.isEmpty)
val resultList: List[Oaf] = Crossref2Oaf.convert(json)

251
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkEoscTag.java Normal file
View File

@ -0,0 +1,251 @@
package eu.dnetlib.dhp.bulktag;
import static eu.dnetlib.dhp.PropagationConstant.readPath;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.*;
import java.util.function.Function;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
public class SparkEoscTag {
private static final Logger log = LoggerFactory.getLogger(SparkEoscTag.class);
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static final Qualifier EOSC_QUALIFIER = OafMapperUtils
.qualifier(
"EOSC",
"European Open Science Cloud",
ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES);
public static final DataInfo EOSC_DATAINFO = OafMapperUtils
.dataInfo(
false, "propagation", true, false,
OafMapperUtils
.qualifier(
"propagation:subject", "Inferred by OpenAIRE",
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
"0.9");
public final static StructuredProperty EOSC_NOTEBOOK = OafMapperUtils
.structuredProperty(
"EOSC::Jupyter Notebook", EOSC_QUALIFIER, EOSC_DATAINFO);
public final static StructuredProperty EOSC_GALAXY = OafMapperUtils
.structuredProperty(
"EOSC::Galaxy Workflow", EOSC_QUALIFIER, EOSC_DATAINFO);
public final static StructuredProperty EOSC_TWITTER = OafMapperUtils
.structuredProperty(
"EOSC::Twitter Data", EOSC_QUALIFIER, EOSC_DATAINFO);
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
SparkEoscTag.class
.getResourceAsStream(
"/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String workingPath = parser.get("workingPath");
log.info("workingPath: {}", workingPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
execEoscTag(spark, inputPath, workingPath);
});
}
private static void execEoscTag(SparkSession spark, String inputPath, String workingPath) {
readPath(spark, inputPath + "/software", Software.class)
.map((MapFunction<Software, Software>) s -> {
List<StructuredProperty> sbject;
if (!Optional.ofNullable(s.getSubject()).isPresent())
s.setSubject(new ArrayList<>());
sbject = s.getSubject();
if (containsCriteriaNotebook(s)) {
sbject.add(EOSC_NOTEBOOK);
if (sbject.stream().anyMatch(sb -> sb.getValue().equals("EOSC Jupyter Notebook"))) {
sbject = sbject.stream().map(sb -> {
if (sb.getValue().equals("EOSC Jupyter Notebook")) {
return null;
}
return sb;
}).filter(Objects::nonNull).collect(Collectors.toList());
s.setSubject(sbject);
}
}
if (containsCriteriaGalaxy(s)) {
sbject.add(EOSC_GALAXY);
}
return s;
}, Encoders.bean(Software.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingPath + "/software");
readPath(spark, workingPath + "/software", Software.class)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + "/software");
readPath(spark, inputPath + "/otherresearchproduct", OtherResearchProduct.class)
.map((MapFunction<OtherResearchProduct, OtherResearchProduct>) orp -> {
List<StructuredProperty> sbject;
if (!Optional.ofNullable(orp.getSubject()).isPresent())
orp.setSubject(new ArrayList<>());
sbject = orp.getSubject();
if (containsCriteriaGalaxy(orp)) {
sbject.add(EOSC_GALAXY);
}
if (containscriteriaTwitter(orp)) {
sbject.add(EOSC_TWITTER);
}
return orp;
}, Encoders.bean(OtherResearchProduct.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingPath + "/otherresearchproduct");
readPath(spark, workingPath + "/otherresearchproduct", OtherResearchProduct.class)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + "/otherresearchproduct");
readPath(spark, inputPath + "/dataset", Dataset.class)
.map((MapFunction<Dataset, Dataset>) d -> {
List<StructuredProperty> sbject;
if (!Optional.ofNullable(d.getSubject()).isPresent())
d.setSubject(new ArrayList<>());
sbject = d.getSubject();
if (containscriteriaTwitter(d)) {
sbject.add(EOSC_TWITTER);
}
return d;
}, Encoders.bean(Dataset.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingPath + "/dataset");
readPath(spark, workingPath + "/dataset", Dataset.class)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + "/dataset");
}
private static boolean containscriteriaTwitter(Result r) {
Set<String> words = getWordsSP(r.getTitle());
words.addAll(getWordsF(r.getDescription()));
if (words.contains("twitter") &&
(words.contains("data") || words.contains("dataset")))
return true;
if (r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("twitter")) &&
r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("data")))
return true;
return false;
}
private static boolean containsCriteriaGalaxy(Result r) {
Set<String> words = getWordsSP(r.getTitle());
words.addAll(getWordsF(r.getDescription()));
if (words.contains("galaxy") &&
words.contains("workflow"))
return true;
if (r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("galaxy")) &&
r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("workflow")))
return true;
return false;
}
private static boolean containsCriteriaNotebook(Software s) {
if (s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("jupyter")))
return true;
if (s
.getSubject()
.stream()
.anyMatch(
sbj -> sbj.getValue().toLowerCase().contains("python") &&
sbj.getValue().toLowerCase().contains("notebook")))
return true;
if (s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("python")) &&
s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("notebook")))
return true;
return false;
}
private static Set<String> getSubjects(List<StructuredProperty> s) {
Set<String> subjects = new HashSet<>();
s.stream().forEach(sbj -> subjects.addAll(Arrays.asList(sbj.getValue().toLowerCase().split(" "))));
s.stream().forEach(sbj -> subjects.add(sbj.getValue().toLowerCase()));
return subjects;
}
private static Set<String> getWordsSP(List<StructuredProperty> elem) {
Set<String> words = new HashSet<>();
Optional
.ofNullable(elem)
.ifPresent(
e -> e
.forEach(
t -> words
.addAll(
Arrays.asList(t.getValue().toLowerCase().replaceAll("[^a-zA-Z ]", "").split(" ")))));
return words;
}
private static Set<String> getWordsF(List<Field<String>> elem) {
Set<String> words = new HashSet<>();
Optional
.ofNullable(elem)
.ifPresent(
e -> e
.forEach(
t -> words
.addAll(
Arrays.asList(t.getValue().toLowerCase().replaceAll("[^a-zA-Z ]", "").split(" ")))));
// elem
// .forEach(
// t -> words.addAll(Arrays.asList(t.getValue().toLowerCase().replaceAll("[^a-zA-Z ]", "").split(" "))));
return words;
}
}

19
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java
View File

@ -102,21 +102,28 @@ public class SparkCountryPropagationJob {
private static <R extends Result> MapFunction<Tuple2<R, ResultCountrySet>, R> getCountryMergeFn() {
return t -> {
Optional.ofNullable(t._2()).ifPresent(r -> {
t._1().getCountry().addAll(merge(t._1().getCountry(), r.getCountrySet()));
if (Optional.ofNullable(t._1().getCountry()).isPresent())
t._1().getCountry().addAll(merge(t._1().getCountry(), r.getCountrySet()));
else
t._1().setCountry(merge(null, t._2().getCountrySet()));
});
return t._1();
};
}
private static List<Country> merge(List<Country> c1, List<CountrySbs> c2) {
HashSet<String> countries = c1
.stream()
.map(Qualifier::getClassid)
.collect(Collectors.toCollection(HashSet::new));
HashSet<String> countries = new HashSet<>();
if (Optional.ofNullable(c1).isPresent()) {
countries = c1
.stream()
.map(Qualifier::getClassid)
.collect(Collectors.toCollection(HashSet::new));
}
HashSet<String> finalCountries = countries;
return c2
.stream()
.filter(c -> !countries.contains(c.getClassid()))
.filter(c -> !finalCountries.contains(c.getClassid()))
.map(c -> getCountry(c.getClassid(), c.getClassname()))
.collect(Collectors.toList());
}

21
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json Normal file
View File

@ -0,0 +1,21 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "wp",
"paramLongName": "workingPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
}
]

26
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml
View File

@ -204,7 +204,31 @@
<error to="Kill"/>
</action>
<join name="wait" to="End"/>
<join name="wait" to="eosc_tag"/>
<action name="eosc_tag">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>EOSC_tagging</name>
<class>eu.dnetlib.dhp.bulktag.SparkEoscTag</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--num-executors=${sparkExecutorNumber}
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${outputPath}</arg>
<arg>--workingPath</arg><arg>${workingDir}/eoscTag</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>

538
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/bulktag/EOSCTagJobTest.java Normal file
View File

@ -0,0 +1,538 @@
package eu.dnetlib.dhp.bulktag;
import static eu.dnetlib.dhp.bulktag.community.TaggingConstants.ZENODO_COMMUNITY_INDICATOR;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.List;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.oaf.*;
public class EOSCTagJobTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static SparkSession spark;
private static Path workingDir;
private static final Logger log = LoggerFactory.getLogger(EOSCTagJobTest.class);
@BeforeAll
public static void beforeAll() throws IOException {
workingDir = Files.createTempDirectory(EOSCTagJobTest.class.getSimpleName());
log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf();
conf.setAppName(EOSCTagJobTest.class.getSimpleName());
conf.setMaster("local[*]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.toString());
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
spark = SparkSession
.builder()
.appName(EOSCTagJobTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
spark.stop();
}
@Test
void jupyterUpdatesTest() throws Exception {
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/software").getPath())
.map(
(MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class),
Encoders.bean(Software.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/software");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/dataset").getPath())
.map(
(MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class),
Encoders.bean(Dataset.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/dataset");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/otherresearchproduct").getPath())
.map(
(MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER
.readValue(value, OtherResearchProduct.class),
Encoders.bean(OtherResearchProduct.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/otherresearchproduct");
SparkEoscTag
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input",
"-workingPath", workingDir.toString() + "/working"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Software> tmp = sc
.textFile(workingDir.toString() + "/input/software")
.map(item -> OBJECT_MAPPER.readValue(item, Software.class));
Assertions.assertEquals(10, tmp.count());
Assertions
.assertEquals(
4,
tmp
.filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook")))
.count());
Assertions
.assertEquals(
1, tmp
.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions
.assertEquals(
5, tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions
.assertEquals(
9, tmp
.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions
.assertEquals(
5, tmp
.filter(sw -> sw.getId().equals("50|od______1582::5aec1186054301b66c0c5dc35972a589"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::5aec1186054301b66c0c5dc35972a589"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions
.assertEquals(
9, tmp
.filter(sw -> sw.getId().equals("50|od______1582::639909adfad9d708308f2aedb733e4a0"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::639909adfad9d708308f2aedb733e4a0"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
List<StructuredProperty> subjects = tmp
.filter(sw -> sw.getId().equals("50|od______1582::6e7a9b21a2feef45673890432af34244"))
.collect()
.get(0)
.getSubject();
Assertions.assertEquals(8, subjects.size());
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("jupyter")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("Modeling and Simulation")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("structure granulaire")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("algorithme")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("simulation numérique")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("flux de gaz")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("flux de liquide")));
Assertions
.assertEquals(
10, sc
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class))
.count());
Assertions
.assertEquals(
0, sc
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class))
.filter(
ds -> ds.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook")))
.count());
Assertions
.assertEquals(
10, sc
.textFile(workingDir.toString() + "/input/otherresearchproduct")
.map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class))
.count());
Assertions
.assertEquals(
0, sc
.textFile(workingDir.toString() + "/input/otherresearchproduct")
.map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class))
.filter(
ds -> ds.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook")))
.count());
// spark.stop();
}
@Test
void galaxyUpdatesTest() throws Exception {
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/software").getPath())
.map(
(MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class),
Encoders.bean(Software.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/software");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/dataset").getPath())
.map(
(MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class),
Encoders.bean(Dataset.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/dataset");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/otherresearchproduct").getPath())
.map(
(MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER
.readValue(value, OtherResearchProduct.class),
Encoders.bean(OtherResearchProduct.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/otherresearchproduct");
SparkEoscTag
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input",
"-workingPath", workingDir.toString() + "/working"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Software> tmp = sc
.textFile(workingDir.toString() + "/input/software")
.map(item -> OBJECT_MAPPER.readValue(item, Software.class));
Assertions.assertEquals(11, tmp.count());
Assertions
.assertEquals(
1,
tmp
.filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow")))
.count());
Assertions
.assertEquals(
2, tmp
.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions
.assertEquals(
5, tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertEquals(
8, tmp
.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
JavaRDD<OtherResearchProduct> orp = sc
.textFile(workingDir.toString() + "/input/otherresearchproduct")
.map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class));
Assertions.assertEquals(10, orp.count());
Assertions
.assertEquals(
1,
orp
.filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow")))
.count());
Assertions
.assertEquals(
3, orp
.filter(sw -> sw.getId().equals("50|od______2017::0750a4d0782265873d669520f5e33c07"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
orp
.filter(sw -> sw.getId().equals("50|od______2017::0750a4d0782265873d669520f5e33c07"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions
.assertEquals(
2, orp
.filter(sw -> sw.getId().equals("50|od______2017::1bd97baef19dbd2db3203b112bb83bc5"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
orp
.filter(sw -> sw.getId().equals("50|od______2017::1bd97baef19dbd2db3203b112bb83bc5"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions
.assertEquals(
2, orp
.filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
orp
.filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
}
@Test
void twitterUpdatesTest() throws Exception {
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/twitter/software").getPath())
.map(
(MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class),
Encoders.bean(Software.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/software");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/twitter/dataset").getPath())
.map(
(MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class),
Encoders.bean(Dataset.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/dataset");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/twitter/otherresearchproduct").getPath())
.map(
(MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER
.readValue(value, OtherResearchProduct.class),
Encoders.bean(OtherResearchProduct.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/otherresearchproduct");
SparkEoscTag
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input",
"-workingPath", workingDir.toString() + "/working"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Software> tmp = sc
.textFile(workingDir.toString() + "/input/software")
.map(item -> OBJECT_MAPPER.readValue(item, Software.class));
Assertions.assertEquals(10, tmp.count());
Assertions
.assertEquals(
0,
tmp
.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Twitter Data")))
.count());
JavaRDD<OtherResearchProduct> orp = sc
.textFile(workingDir.toString() + "/input/otherresearchproduct")
.map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class));
Assertions.assertEquals(10, orp.count());
Assertions
.assertEquals(
3,
orp
.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Twitter Data")))
.count());
JavaRDD<Dataset> dats = sc
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
Assertions.assertEquals(11, dats.count());
Assertions
.assertEquals(
3,
dats
.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Twitter Data")))
.count());
}
}

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/galaxy/dataset/dataset_10.json Normal file
View File

File diff suppressed because one or more lines are too long

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/galaxy/otherresearchproduct/otherresearchproduct_10.json Normal file
View File

File diff suppressed because one or more lines are too long

11
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/galaxy/software/software_10.json Normal file
View File

File diff suppressed because one or more lines are too long

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/jupyter/dataset/dataset_10.json Normal file
View File

File diff suppressed because one or more lines are too long

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/jupyter/otherresearchproduct/otherresearchproduct_10.json Normal file
View File

File diff suppressed because one or more lines are too long

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/jupyter/software/software_10.json Normal file
View File

File diff suppressed because one or more lines are too long

11
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/twitter/dataset/dataset_10.json Normal file
View File

File diff suppressed because one or more lines are too long

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/twitter/otherresearchproduct/otherresearchproduct_10.json Normal file
View File

File diff suppressed because one or more lines are too long

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/twitter/software/software_10.json Normal file
View File

File diff suppressed because one or more lines are too long

31
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphTableSparkJob.java
View File

@ -5,6 +5,7 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.*;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
@ -136,7 +137,7 @@ public class MergeGraphTableSparkJob {
/**
* Datasources involved in the merge operation doesn't obey to the infra precedence policy, but relies on a custom
* behaviour that, given two datasources from beta and prod returns the one from prod with the highest
* compatibility among the two.
* compatibility among the two. Furthermore, the procedure merges the collectedfrom, originalId, and pid lists.
*
* @param p datasource from PROD
* @param b datasource from BETA
@ -160,9 +161,37 @@ public class MergeGraphTableSparkJob {
List<Qualifier> list = Arrays.asList(dp.getOpenairecompatibility(), db.getOpenairecompatibility());
dp.setOpenairecompatibility(Collections.min(list, new DatasourceCompatibilityComparator()));
dp
.setCollectedfrom(
Stream
.concat(
Optional
.ofNullable(dp.getCollectedfrom())
.map(Collection::stream)
.orElse(Stream.empty()),
Optional
.ofNullable(db.getCollectedfrom())
.map(Collection::stream)
.orElse(Stream.empty()))
.distinct() // relies on KeyValue.equals
.collect(Collectors.toList()));
dp.setOriginalId(mergeLists(dp.getOriginalId(), db.getOriginalId()));
dp.setPid(mergeLists(dp.getPid(), db.getPid()));
return (P) dp;
}
private static final <T> List<T> mergeLists(final List<T>... lists) {
return Arrays
.stream(lists)
.filter(Objects::nonNull)
.flatMap(List::stream)
.filter(Objects::nonNull)
.distinct()
.collect(Collectors.toList());
}
private static <P extends Oaf, B extends Oaf> P mergeWithPriorityToPROD(Optional<P> p, Optional<B> b) {
if (b.isPresent() & !p.isPresent()) {
return (P) b.get();

99
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/MigrateDbEntitiesApplication.java
View File

@ -27,15 +27,7 @@ import static eu.dnetlib.dhp.schema.common.ModelConstants.RESULT_PROJECT;
import static eu.dnetlib.dhp.schema.common.ModelConstants.RESULT_RESULT;
import static eu.dnetlib.dhp.schema.common.ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.USER_CLAIM;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.asString;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.dataInfo;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.field;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.journal;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.listFields;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.listKeyValues;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.qualifier;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils.*;
import java.io.Closeable;
import java.io.IOException;
@ -143,8 +135,8 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
smdbe.execute("queryClaims.sql", smdbe::processClaims);
break;
case openaire:
log.info("Processing datasources...");
smdbe.execute("queryDatasources.sql", smdbe::processDatasource, verifyNamespacePrefix);
log.info("Processing services...");
smdbe.execute("queryServices.sql", smdbe::processService, verifyNamespacePrefix);
log.info("Processing projects...");
if (dbSchema.equalsIgnoreCase("beta")) {
@ -156,10 +148,10 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
log.info("Processing Organizations...");
smdbe.execute("queryOrganizations.sql", smdbe::processOrganization, verifyNamespacePrefix);
log.info("Processing relationsNoRemoval ds <-> orgs ...");
log.info("Processing relations services <-> orgs ...");
smdbe
.execute(
"queryDatasourceOrganization.sql", smdbe::processDatasourceOrganization,
"queryServiceOrganization.sql", smdbe::processServiceOrganization,
verifyNamespacePrefix);
log.info("Processing projects <-> orgs ...");
@ -235,32 +227,30 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
dbClient.processResults(sql, consumer);
}
public List<Oaf> processDatasource(final ResultSet rs) {
public List<Oaf> processService(final ResultSet rs) {
try {
final DataInfo info = prepareDataInfo(rs);
final Datasource ds = new Datasource();
ds.setId(createOpenaireId(10, rs.getString("datasourceid"), true));
ds.setId(createOpenaireId(10, rs.getString("id"), true));
ds
.setOriginalId(
Arrays
.asList((String[]) rs.getArray("identities").getArray())
.asList((String[]) rs.getArray("originalid").getArray())
.stream()
.filter(StringUtils::isNotBlank)
.collect(Collectors.toList()));
ds
.setCollectedfrom(
listKeyValues(
createOpenaireId(10, rs.getString("collectedfromid"), true),
rs.getString("collectedfromname")));
ds.setPid(new ArrayList<>());
ds.setCollectedfrom(prepareCollectedfrom(rs.getArray("collectedfrom")));
ds.setPid(prepareListOfStructProps(rs.getArray("pid"), info));
ds.setDateofcollection(asString(rs.getDate("dateofcollection")));
ds.setDateoftransformation(null); // Value not returned by the SQL query
ds.setExtraInfo(new ArrayList<>()); // Values not present in the DB
ds.setOaiprovenance(null); // Values not present in the DB
ds.setDatasourcetype(prepareQualifierSplitting(rs.getString("datasourcetype")));
ds.setDatasourcetypeui(prepareQualifierSplitting(rs.getString("datasourcetypeui")));
ds.setEosctype(prepareQualifierSplitting(rs.getString("eosctype")));
ds.setEoscdatasourcetype(prepareQualifierSplitting(rs.getString("eoscdatasourcetype")));
ds.setOpenairecompatibility(prepareQualifierSplitting(rs.getString("openairecompatibility")));
ds.setOfficialname(field(rs.getString("officialname"), info));
ds.setEnglishname(field(rs.getString("englishname"), info));
@ -277,20 +267,19 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
ds.setOdnumberofitemsdate(field(asString(rs.getDate("odnumberofitemsdate")), info));
ds.setOdpolicies(field(rs.getString("odpolicies"), info));
ds.setOdlanguages(prepareListFields(rs.getArray("odlanguages"), info));
ds.setOdcontenttypes(prepareListFields(rs.getArray("odcontenttypes"), info));
ds.setLanguages(listValues(rs.getArray("languages")));
ds.setAccessinfopackage(prepareListFields(rs.getArray("accessinfopackage"), info));
ds.setReleasestartdate(field(asString(rs.getDate("releasestartdate")), info));
ds.setReleaseenddate(field(asString(rs.getDate("releaseenddate")), info));
ds.setMissionstatementurl(field(rs.getString("missionstatementurl"), info));
ds.setDataprovider(field(rs.getBoolean("dataprovider"), info));
ds.setServiceprovider(field(rs.getBoolean("serviceprovider"), info));
ds.setDatabaseaccesstype(field(rs.getString("databaseaccesstype"), info));
ds.setDatauploadtype(field(rs.getString("datauploadtype"), info));
ds.setDatabaseaccessrestriction(field(rs.getString("databaseaccessrestriction"), info));
ds.setDatauploadrestriction(field(rs.getString("datauploadrestriction"), info));
ds.setVersioning(field(rs.getBoolean("versioning"), info));
ds.setVersioncontrol(rs.getBoolean("versioncontrol"));
ds.setCitationguidelineurl(field(rs.getString("citationguidelineurl"), info));
ds.setQualitymanagementkind(field(rs.getString("qualitymanagementkind"), info));
ds.setPidsystems(field(rs.getString("pidsystems"), info));
ds.setCertificates(field(rs.getString("certificates"), info));
ds.setPolicies(new ArrayList<>()); // The sql query returns an empty array
@ -299,13 +288,18 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
journal(
rs.getString("officialname"), rs.getString("issnPrinted"), rs.getString("issnOnline"),
rs.getString("issnLinking"), info)); // Journal
ds.setDataInfo(info);
ds.setLastupdatetimestamp(lastUpdateTimestamp);
ds.setResearchentitytypes(listValues(rs.getArray("researchentitytypes")));
ds.setJurisdiction(prepareQualifierSplitting(rs.getString("jurisdiction")));
ds.setThematic(rs.getBoolean("thematic"));
ds.setKnowledgegraph(rs.getBoolean("knowledgegraph"));
ds.setContentpolicies(prepareListOfQualifiers(rs.getArray("contentpolicies")));
ds.setSubmissionpolicyurl(rs.getString("submissionpolicyurl"));
ds.setPreservationpolicyurl(rs.getString("preservationpolicyurl"));
ds.setResearchproductaccesspolicies(listValues(rs.getArray("researchproductaccesspolicies")));
ds
.setResearchproductmetadataaccesspolicies(
listValues(rs.getArray("researchproductmetadataaccesspolicies")));
ds.setConsenttermsofuse(rs.getBoolean("consenttermsofuse"));
ds.setFulltextdownload(rs.getBoolean("fulltextdownload"));
ds
@ -313,8 +307,18 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
Optional
.ofNullable(
rs.getDate("consenttermsofusedate"))
.map(c -> c.toString())
.map(java.sql.Date::toString)
.orElse(null));
ds
.setLastconsenttermsofusedate(
Optional
.ofNullable(
rs.getDate("lastconsenttermsofusedate"))
.map(java.sql.Date::toString)
.orElse(null));
ds.setDataInfo(info);
ds.setLastupdatetimestamp(lastUpdateTimestamp);
return Arrays.asList(ds);
} catch (final Exception e) {
@ -425,11 +429,11 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
}
}
public List<Oaf> processDatasourceOrganization(final ResultSet rs) {
public List<Oaf> processServiceOrganization(final ResultSet rs) {
try {
final DataInfo info = prepareDataInfo(rs);
final String orgId = createOpenaireId(20, rs.getString("organization"), true);
final String dsId = createOpenaireId(10, rs.getString("datasource"), true);
final String dsId = createOpenaireId(10, rs.getString("service"), true);
final List<KeyValue> collectedFrom = listKeyValues(
createOpenaireId(10, rs.getString("collectedfromid"), true), rs.getString("collectedfromname"));
@ -603,6 +607,32 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
String.format("%.3f", trust));
}
private List<KeyValue> prepareCollectedfrom(Array values) throws SQLException {
if (Objects.isNull(values)) {
return null;
}
return Arrays
.stream((String[]) values.getArray())
.filter(Objects::nonNull)
.distinct()
.map(s -> keyValueSplitting(s, "@@@"))
.collect(Collectors.toList());
}
public static KeyValue keyValueSplitting(final String s, String separator) {
if (StringUtils.isBlank(s)) {
return null;
}
final String[] arr = s.split(separator);
if (arr.length != 2) {
return null;
}
KeyValue kv = new KeyValue();
kv.setKey(createOpenaireId(10, arr[0], true));
kv.setValue(arr[1]);
return kv;
}
private Qualifier prepareQualifierSplitting(final String s) {
if (StringUtils.isBlank(s)) {
return null;
@ -711,10 +741,7 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
final Relation r = new Relation();
r.setRelType(ORG_ORG_RELTYPE);
r.setSubRelType(ModelConstants.RELATIONSHIP);
r
.setRelClass(
rs.getString("type").equalsIgnoreCase("parent") ? ModelConstants.IS_PARENT_OF
: ModelConstants.IS_CHILD_OF);
r.setRelClass(rs.getString("type"));
r.setSource(orgId1);
r.setTarget(orgId2);
r.setCollectedfrom(collectedFrom);

10
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/group/oozie_app/workflow.xml
View File

@ -283,7 +283,15 @@
<error to="Kill"/>
</action>
<join name="wait_dispatch" to="copy_relation"/>
<join name="wait_dispatch" to="delete_target_relation"/>
<action name="delete_target_relation">
<fs>
<delete path="${nameNode}/${graphOutputPath}/relation"/>
</fs>
<ok to="copy_relation"/>
<error to="Kill"/>
</action>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">

65
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_db/oozie_app/workflow.xml
View File

@ -30,6 +30,11 @@
<value></value>
<description>a blacklist of nsprefixes (comma separeted)</description>
</property>
<property>
<name>reuseContent</name>
<value>false</value>
<description>reuse content in the aggregator database</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
@ -85,12 +90,20 @@
</configuration>
</global>
<start to="ImportDB"/>
<start to="reuse_db"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<decision name="reuse_db">
<switch>
<case to="ImportDB">${wf:conf('reuseContent') eq false}</case>
<case to="GenerateEntities">${wf:conf('reuseContent') eq true}</case>
<default to="ImportDB"/>
</switch>
</decision>
<action name="ImportDB">
<java>
<prepare>
@ -102,6 +115,7 @@
<arg>--postgresUser</arg><arg>${postgresUser}</arg>
<arg>--postgresPassword</arg><arg>${postgresPassword}</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--action</arg><arg>openaire</arg>
<arg>--dbschema</arg><arg>${dbSchema}</arg>
<arg>--nsPrefixBlacklist</arg><arg>${nsPrefixBlacklist}</arg>
</java>
@ -124,6 +138,55 @@
<arg>--action</arg><arg>claims</arg>
<arg>--nsPrefixBlacklist</arg><arg>${nsPrefixBlacklist}</arg>
</java>
<ok to="GenerateEntities"/>
<error to="Kill"/>
</action>
<action name="GenerateEntities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>GenerateEntities</name>
<class>eu.dnetlib.dhp.oa.graph.raw.GenerateEntitiesApplication</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePaths</arg><arg>${contentPath}/db_records,${contentPath}/db_claims</arg>
<arg>--targetPath</arg><arg>${workingDir}/entities</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--shouldHashId</arg><arg>true</arg>
</spark>
<ok to="GenerateGraph"/>
<error to="Kill"/>
</action>
<action name="GenerateGraph">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>GenerateGraph</name>
<class>eu.dnetlib.dhp.oa.graph.raw.DispatchEntitiesApplication</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/entities</arg>
<arg>--graphRawPath</arg><arg>${workingDir}/graph_aggregator</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryOrganizations.sql
View File

@ -27,7 +27,7 @@ SELECT
'sysimport:crosswalk:entityregistry@@@dnet:provenance_actions' AS provenanceaction,
array_remove(array_agg(DISTINCT i.pid || '###' || i.issuertype || '@@@' || i.issuertype), NULL) AS pid
FROM dsm_organizations o
LEFT OUTER JOIN dsm_datasources d ON (d.id = o.collectedfrom)
LEFT OUTER JOIN dsm_services d ON (d.id = o.collectedfrom)
LEFT OUTER JOIN dsm_organizationpids p ON (p.organization = o.id)
LEFT OUTER JOIN dsm_identities i ON (i.pid = p.pid)
GROUP BY

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryParentChildRelsOpenOrgs.sql
View File

@ -10,4 +10,4 @@ SELECT
'OpenOrgs Database' AS collectedfromname,
'sysimport:crosswalk:entityregistry@@@dnet:provenance_actions' AS provenanceaction
FROM relationships
WHERE reltype = 'Child' OR reltype = 'Parent'
WHERE reltype = 'IsChildOf' OR reltype = 'IsParentOf'

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryProjectOrganization.sql
View File

@ -16,4 +16,4 @@ SELECT
FROM project_organization po
LEFT OUTER JOIN projects p ON (p.id = po.project)
LEFT OUTER JOIN dsm_datasources dc ON (dc.id = p.collectedfrom);
LEFT OUTER JOIN dsm_services dc ON (dc.id = p.collectedfrom);

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryProjects.sql
View File

@ -42,7 +42,7 @@ SELECT
LEFT OUTER JOIN projectpids pp ON (pp.project = p.id)
LEFT OUTER JOIN dsm_identities i ON (i.pid = pp.pid)
LEFT OUTER JOIN dsm_datasources dc ON (dc.id = p.collectedfrom)
LEFT OUTER JOIN dsm_services dc ON (dc.id = p.collectedfrom)
LEFT OUTER JOIN project_fundingpath pf ON (pf.project = p.id)
LEFT OUTER JOIN fundingpaths fp ON (fp.id = pf.funding)

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryProjects_production.sql
View File

@ -40,7 +40,7 @@ SELECT
LEFT OUTER JOIN projectpids pp ON (pp.project = p.id)
LEFT OUTER JOIN dsm_identities i ON (i.pid = pp.pid)
LEFT OUTER JOIN dsm_datasources dc ON (dc.id = p.collectedfrom)
LEFT OUTER JOIN dsm_services dc ON (dc.id = p.collectedfrom)
LEFT OUTER JOIN project_fundingpath pf ON (pf.project = p.id)
LEFT OUTER JOIN fundingpaths fp ON (fp.id = pf.funding)

8
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryDatasourceOrganization.sql → dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryServiceOrganization.sql
View File

@ -1,5 +1,5 @@
SELECT
dor.datasource AS datasource,
dor.service AS service,
dor.organization AS organization,
NULL AS startdate,
NULL AS enddate,
@ -11,6 +11,6 @@ SELECT
dc.officialname AS collectedfromname,
'providedBy@@@dnet:datasources_organizations_typologies' AS semantics,
d.provenanceaction || '@@@dnet:provenanceActions' AS provenanceaction
FROM dsm_datasource_organization dor
LEFT OUTER JOIN dsm_datasources d ON (dor.datasource = d.id)
LEFT OUTER JOIN dsm_datasources dc ON (dc.id = d.collectedfrom);
FROM dsm_service_organization dor
LEFT OUTER JOIN dsm_services d ON (dor.service = d.id)
LEFT OUTER JOIN dsm_services dc ON (dc.id = d.collectedfrom);

109
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryDatasources.sql → dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/sql/queryServices.sql
View File

@ -1,6 +1,7 @@
SELECT
d.id AS datasourceid,
d.id || array_agg(distinct di.pid) AS identities,
d.id AS id,
array_remove(d.id || array_agg(distinct CASE WHEN dp.pid like 'piwik%' THEN di.pid ELSE NULL END) || array_agg(distinct dds.duplicate), NULL) AS originalid,
array_remove(array_agg(distinct CASE WHEN di.pid NOT LIKE 'piwik%' THEN di.pid||'###'||di.issuertype||'@@@'||'dnet:pid_types' ELSE NULL END), NULL) as pid,
d.officialname AS officialname,
d.englishname AS englishname,
d.contactemail AS contactemail,
@ -9,8 +10,8 @@ SELECT
THEN
'openaire-cris_1.1@@@dnet:datasourceCompatibilityLevel'
WHEN (array_agg(DISTINCT COALESCE (a.compatibility_override, a.compatibility):: TEXT) @> ARRAY ['openaire4.0'])
THEN
'openaire4.0@@@dnet:datasourceCompatibilityLevel'
THEN
'openaire4.0@@@dnet:datasourceCompatibilityLevel'
WHEN (array_agg(DISTINCT COALESCE (a.compatibility_override, a.compatibility):: TEXT) @> ARRAY ['driver', 'openaire2.0'])
THEN
'driver-openaire2.0@@@dnet:datasourceCompatibilityLevel'
@ -40,25 +41,29 @@ SELECT
END AS openairecompatibility,
d.websiteurl AS websiteurl,
d.logourl AS logourl,
array_agg(DISTINCT CASE WHEN a.protocol = 'oai' and last_aggregation_date is not null THEN a.baseurl ELSE NULL END) AS accessinfopackage,
array_remove(array_agg(DISTINCT CASE WHEN a.protocol = 'oai' and last_aggregation_date is not null THEN a.baseurl ELSE NULL END), NULL) AS accessinfopackage,
d.latitude AS latitude,
d.longitude AS longitude,
d.namespaceprefix AS namespaceprefix,
NULL AS odnumberofitems,
NULL AS odnumberofitemsdate,
(SELECT array_agg(s|| '###keywords@@@dnet:subject_classification_typologies')
(SELECT array_agg(s|| '###keyword@@@dnet:subject_classification_typologies')
FROM UNNEST(
ARRAY(
SELECT trim(s)
FROM unnest(string_to_array(d.subjects, '@@')) AS s)) AS s) AS subjects,
FROM unnest(string_to_array(d.subjects, '@@')) AS s)) AS s) AS subjects,
d.description AS description,
NULL AS odpolicies,
ARRAY(SELECT trim(s)
FROM unnest(string_to_array(d.languages, ',')) AS s) AS odlanguages,
ARRAY(SELECT trim(s)
FROM unnest(string_to_array(d.od_contenttypes, '-')) AS s) AS odcontenttypes,
array_remove(ARRAY(SELECT trim(s)
FROM unnest(string_to_array(regexp_replace(d.languages, '{|}|"', '', 'g'), ',')) AS s), '{}') AS odlanguages,
array_remove(ARRAY(SELECT trim(s)
FROM unnest(string_to_array(regexp_replace(d.languages, '{|}|"', '', 'g'), ',')) AS s), '{}') AS languages,
-- Term provided only by OpenDOAR:
-- probably updating the TR it could be replaced by research_entity_types[]
-- But a study on the vocabulary terms is needed
-- REMOVED: ARRAY(SELECT trim(s) FROM unnest(string_to_array(d.od_contenttypes, '-')) AS s) AS odcontenttypes,
false AS inferred,
false AS deletedbyinference,
0.9 AS trust,
@ -69,39 +74,59 @@ SELECT
d.releasestartdate AS releasestartdate,
d.releaseenddate AS releaseenddate,
d.missionstatementurl AS missionstatementurl,
d.dataprovider AS dataprovider,
d.serviceprovider AS serviceprovider,
-- the following 2 fields (provided by re3data) have been replaced by research_entity_types[]
-- VALUE 'Research Data' : d.dataprovider AS dataprovider,
-- VALUE 'Services' : d.serviceprovider AS serviceprovider,
d.databaseaccesstype AS databaseaccesstype,
d.datauploadtype AS datauploadtype,
d.databaseaccessrestriction AS databaseaccessrestriction,
d.datauploadrestriction AS datauploadrestriction,
d.versioning AS versioning,
-- REPLACED BY version_control : d.versioning AS versioning,
d.version_control AS versioning,
d.version_control AS versioncontrol,
d.citationguidelineurl AS citationguidelineurl,
d.qualitymanagementkind AS qualitymanagementkind,
d.pidsystems AS pidsystems,
array_to_string(array_agg(distinct dps.scheme), ' ') AS pidsystems,
d.certificates AS certificates,
ARRAY[]::text[] AS policies,
dc.id AS collectedfromid,
dc.officialname AS collectedfromname,
d.typology||'@@@dnet:datasource_typologies' AS datasourcetype,
d.typology||'@@@dnet:datasource_typologies_ui' AS datasourcetypeui,
'sysimport:crosswalk:entityregistry@@@dnet:provenance_actions' AS provenanceaction,
array_remove(
array(
select distinct cf
from unnest(
dc.id||'@@@'||dc.officialname || array_agg(distinct dds_cf.id||'@@@'||dds_cf.officialname)
) as cf),
NULL) AS collectedfrom,
d._typology_to_remove_||'@@@dnet:datasource_typologies' AS datasourcetype,
d._typology_to_remove_||'@@@dnet:datasource_typologies_ui' AS datasourcetypeui,
d.eosc_type||'@@@dnet:eosc_types' AS eosctype,
d.eosc_datasource_type||'@@@dnet:eosc_datasource_types' AS eoscdatasourcetype,
d.issn AS issnPrinted,
d.eissn AS issnOnline,
d.lissn AS issnLinking,
d.research_entity_types AS researchentitytypes,
d.consenttermsofuse AS consenttermsofuse,
d.fulltextdownload AS fulltextdownload,
d.consenttermsofusedate AS consenttermsofusedate,
de.jurisdiction||'@@@eosc:jurisdictions' AS jurisdiction,
de.thematic AS thematic,
de.knowledge_graph AS knowledgegraph,
array(select unnest(de.content_policies)||'@@@eosc:contentpolicies') AS contentpolicies
d.lastconsenttermsofusedate AS lastconsenttermsofusedate,
d.jurisdiction||'@@@eosc:jurisdictions' AS jurisdiction,
d.thematic AS thematic,
array(select unnest(d.content_policies)||'@@@eosc:contentpolicies') AS contentpolicies,
nullif(trim(d.submission_policy_url), '') AS submissionpolicyurl,
nullif(trim(d.preservation_policy_url), '') AS preservationpolicyurl,
array_remove(d.research_product_access_policies, '') AS researchproductaccesspolicies,
array_remove(d.research_product_metadata_access_policies, '') AS researchproductmetadataaccesspolicies
FROM dsm_datasources d
LEFT OUTER JOIN dsm_datasources_eosc de on (d.id = de.id)
LEFT OUTER JOIN dsm_datasources dc on (d.collectedfrom = dc.id)
LEFT OUTER JOIN dsm_api a ON (d.id = a.datasource)
LEFT OUTER JOIN dsm_datasourcepids di ON (d.id = di.datasource)
FROM dsm_services d
LEFT OUTER JOIN dsm_services dc on (d.collectedfrom = dc.id)
LEFT OUTER JOIN dsm_api a ON (d.id = a.service)
LEFT OUTER JOIN dsm_servicepids dp ON (d.id = dp.service)
LEFT OUTER JOIN dsm_identities di ON (dp.pid = di.pid)
LEFT OUTER JOIN dsm_dedup_services dds ON (d.id = dds.id)
LEFT OUTER JOIN dsm_services dds_dup ON (dds.duplicate = dds_dup.id)
LEFT OUTER JOIN dsm_services dds_cf ON (dds_dup.collectedfrom = dds_cf.id)
LEFT OUTER JOIN dsm_pid_systems dps ON (d.id = dps.service)
WHERE
d.dedup_main_service = true
GROUP BY
d.id,
@ -119,23 +144,27 @@ GROUP BY
d.releasestartdate,
d.releaseenddate,
d.missionstatementurl,
d.dataprovider,
d.serviceprovider,
-- TODO REMOVED ???: d.dataprovider,
-- TODO REMOVED ???: d.serviceprovider,
d.databaseaccesstype,
d.datauploadtype,
d.databaseaccessrestriction,
d.datauploadrestriction,
d.versioning,
-- REPLACED BY version_control : d.versioning,
d.version_control,
d.citationguidelineurl,
d.qualitymanagementkind,
d.pidsystems,
-- REMOVED: d.qualitymanagementkind,
d.certificates,
dc.id,
dc.officialname,
d.issn,
d.eissn,
d.lissn,
de.jurisdiction,
de.thematic,
de.knowledge_graph,
de.content_policies
d.jurisdiction,
d.thematic,
-- REMOVED ???: de.knowledge_graph,
d.content_policies,
d.submission_policy_url,
d.preservation_policy_url,
d.research_product_access_policies,
d.research_product_metadata_access_policies

11
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkConvertRDDtoDataset.scala
View File

@ -7,6 +7,7 @@ import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
object SparkConvertRDDtoDataset {
@ -94,8 +95,8 @@ object SparkConvertRDDtoDataset {
log.info("Converting Relation")
val relationSemanticFilter = List(
"cites",
"iscitedby",
// "cites",
// "iscitedby",
"merges",
"ismergedin",
"HasAmongTopNSimilarDocuments",
@ -107,6 +108,12 @@ object SparkConvertRDDtoDataset {
.map(s => mapper.readValue(s, classOf[Relation]))
.filter(r => r.getDataInfo != null && r.getDataInfo.getDeletedbyinference == false)
.filter(r => r.getSource.startsWith("50") && r.getTarget.startsWith("50"))
//filter OpenCitations relations
.filter(r =>
r.getCollectedfrom != null && r.getCollectedfrom.size() > 0 && !r.getCollectedfrom.asScala.exists(k =>
"opencitations".equalsIgnoreCase(k.getValue)
)
)
.filter(r => !relationSemanticFilter.exists(k => k.equalsIgnoreCase(r.getRelClass)))
spark.createDataset(rddRelation).as[Relation].write.mode(SaveMode.Overwrite).save(s"$relPath")

136
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/pangaea/PangaeaUtils.scala
View File

@ -1,136 +0,0 @@
package eu.dnetlib.dhp.sx.graph.pangaea
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.{Encoder, Encoders}
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import java.util.regex.Pattern
import scala.language.postfixOps
import scala.xml.{Elem, Node, XML}
case class PangaeaDataModel(
identifier: String,
title: List[String],
objectType: List[String],
creator: List[String],
publisher: List[String],
dataCenter: List[String],
subject: List[String],
language: String,
rights: String,
parent: String,
relation: List[String],
linkage: List[(String, String)]
) {}
object PangaeaUtils {
def toDataset(input: String): PangaeaDataModel = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = parse(input)
val xml = (json \ "xml").extract[String]
parseXml(xml)
}
def findDOIInRelation(input: List[String]): List[String] = {
val pattern = Pattern.compile("\\b(10[.][0-9]{4,}(?:[.][0-9]+)*\\/(?:(?![\"&\\'<>])\\S)+)\\b")
input
.map(i => {
val matcher = pattern.matcher(i)
if (matcher.find())
matcher.group(0)
else
null
})
.filter(i => i != null)
}
def attributeOpt(attribute: String, node: Node): Option[String] =
node.attribute(attribute) flatMap (_.headOption) map (_.text)
def extractLinkage(node: Elem): List[(String, String)] = {
(node \ "linkage")
.map(n => (attributeOpt("type", n), n.text))
.filter(t => t._1.isDefined)
.map(t => (t._1.get, t._2))(collection.breakOut)
}
def parseXml(input: String): PangaeaDataModel = {
val xml = XML.loadString(input)
val identifier = (xml \ "identifier").text
val title: List[String] = (xml \ "title").map(n => n.text)(collection.breakOut)
val pType: List[String] = (xml \ "type").map(n => n.text)(collection.breakOut)
val creators: List[String] = (xml \ "creator").map(n => n.text)(collection.breakOut)
val publisher: List[String] = (xml \ "publisher").map(n => n.text)(collection.breakOut)
val dataCenter: List[String] = (xml \ "dataCenter").map(n => n.text)(collection.breakOut)
val subject: List[String] = (xml \ "subject").map(n => n.text)(collection.breakOut)
val language = (xml \ "language").text
val rights = (xml \ "rights").text
val parentIdentifier = (xml \ "parentIdentifier").text
val relation: List[String] = (xml \ "relation").map(n => n.text)(collection.breakOut)
val relationFiltered = findDOIInRelation(relation)
val linkage: List[(String, String)] = extractLinkage(xml)
PangaeaDataModel(
identifier,
title,
pType,
creators,
publisher,
dataCenter,
subject,
language,
rights,
parentIdentifier,
relationFiltered,
linkage
)
}
def getDatasetAggregator(): Aggregator[(String, PangaeaDataModel), PangaeaDataModel, PangaeaDataModel] =
new Aggregator[(String, PangaeaDataModel), PangaeaDataModel, PangaeaDataModel] {
override def zero: PangaeaDataModel = null
override def reduce(b: PangaeaDataModel, a: (String, PangaeaDataModel)): PangaeaDataModel = {
if (b == null)
a._2
else {
if (a == null)
b
else {
if (b.title != null && b.title.nonEmpty)
b
else
a._2
}
}
}
override def merge(b1: PangaeaDataModel, b2: PangaeaDataModel): PangaeaDataModel = {
if (b1 == null)
b2
else {
if (b2 == null)
b1
else {
if (b1.title != null && b1.title.nonEmpty)
b1
else
b2
}
}
}
override def finish(reduction: PangaeaDataModel): PangaeaDataModel = reduction
override def bufferEncoder: Encoder[PangaeaDataModel] = Encoders.kryo[PangaeaDataModel]
override def outputEncoder: Encoder[PangaeaDataModel] = Encoders.kryo[PangaeaDataModel]
}
}

58
dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/pangaea/SparkGeneratePanagaeaDataset.scala
View File

@ -1,58 +0,0 @@
package eu.dnetlib.dhp.sx.graph.pangaea
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.{SparkConf, SparkContext}
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
import scala.io.Source
object SparkGeneratePanagaeaDataset {
def main(args: Array[String]): Unit = {
val logger: Logger = LoggerFactory.getLogger(getClass)
val conf: SparkConf = new SparkConf()
val parser = new ArgumentApplicationParser(
Source
.fromInputStream(
getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/pangaea/pangaea_to_dataset.json")
)
.mkString
)
parser.parseArgument(args)
val spark: SparkSession =
SparkSession
.builder()
.config(conf)
.appName(SparkGeneratePanagaeaDataset.getClass.getSimpleName)
.master(parser.get("master"))
.getOrCreate()
parser.getObjectMap.asScala.foreach(s => logger.info(s"${s._1} -> ${s._2}"))
logger.info("Converting sequential file into Dataset")
val sc: SparkContext = spark.sparkContext
val workingPath: String = parser.get("workingPath")
implicit val pangaeaEncoders: Encoder[PangaeaDataModel] = Encoders.kryo[PangaeaDataModel]
val inputRDD: RDD[PangaeaDataModel] =
sc.textFile(s"$workingPath/update").map(s => PangaeaUtils.toDataset(s))
spark
.createDataset(inputRDD)
.as[PangaeaDataModel]
.map(s => (s.identifier, s))(Encoders.tuple(Encoders.STRING, pangaeaEncoders))
.groupByKey(_._1)(Encoders.STRING)
.agg(PangaeaUtils.getDatasetAggregator().toColumn)
.map(s => s._2)
.write
.mode(SaveMode.Overwrite)
.save(s"$workingPath/dataset")
}
}

19
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphTableSparkJobTest.java
View File

@ -2,6 +2,7 @@
package eu.dnetlib.dhp.oa.graph.merge;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertNotNull;
import java.io.IOException;
import java.util.Optional;
@ -25,7 +26,23 @@ class MergeGraphTableSparkJobTest {
}
@Test
void testMergeDatasources() throws IOException {
void testMerge() throws IOException {
Datasource d = MergeGraphTableSparkJob
.mergeDatasource(
d("datasource_cris.json"),
d("datasource_openaire2.0.json"));
assertEquals("10|274269ac6f3b::2a2e2793b500f3f7b47ef24b1a9277b7", d.getId());
assertNotNull(d.getOriginalId());
assertEquals(2, d.getOriginalId().size());
assertNotNull(d.getCollectedfrom());
assertEquals(2, d.getCollectedfrom().size());
assertNotNull(d.getPid());
assertEquals(1, d.getPid().size());
}
@Test
void testMergeCompatibility() throws IOException {
assertEquals(
"openaire-cris_1.1",
MergeGraphTableSparkJob

14
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java
View File

@ -835,6 +835,20 @@ class MappersTest {
assertEquals("EUR", p.getProcessingchargecurrency().getValue());
}
@Test
void testROHub() throws IOException, DocumentException {
final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("rohub.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("***************");
// final Dataset p = (Dataset) list.get(0);
// assertValidId(p.getId());
// assertValidId(p.getCollectedfrom().get(0).getKey());
// System.out.println(p.getTitle().get(0).getValue());
// assertTrue(StringUtils.isNotBlank(p.getTitle().get(0).getValue()));
}
private void assertValidId(final String id) {
// System.out.println(id);

146
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MigrateDbEntitiesApplicationTest.java
View File

@ -12,8 +12,11 @@ import java.sql.Array;
import java.sql.Date;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.util.HashSet;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
@ -28,12 +31,7 @@ import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
@ExtendWith(MockitoExtension.class)
@ -63,22 +61,32 @@ public class MigrateDbEntitiesApplicationTest {
}
@Test
public void testProcessDatasource() throws Exception {
final List<TypedField> fields = prepareMocks("datasources_resultset_entry.json");
public void testProcessService() throws Exception {
final List<TypedField> fields = prepareMocks("services_resultset_entry.json");
final List<Oaf> list = app.processDatasource(rs);
final List<Oaf> list = app.processService(rs);
assertEquals(1, list.size());
verifyMocks(fields);
final Datasource ds = (Datasource) list.get(0);
assertValidId(ds.getId());
assertValidId(ds.getCollectedfrom().get(0).getKey());
ds
.getCollectedfrom()
.stream()
.map(KeyValue::getKey)
.forEach(dsId -> assertValidId(dsId));
assertEquals(1, ds.getPid().size());
assertEquals("r3d100010218", ds.getPid().get(0).getValue());
assertEquals("re3data", ds.getPid().get(0).getQualifier().getClassid());
assertEquals("dnet:pid_types", ds.getPid().get(0).getQualifier().getSchemeid());
assertEquals(getValueAsString("officialname", fields), ds.getOfficialname().getValue());
assertEquals(getValueAsString("englishname", fields), ds.getEnglishname().getValue());
assertEquals(getValueAsString("contactemail", fields), ds.getContactemail().getValue());
assertEquals(getValueAsString("websiteurl", fields), ds.getWebsiteurl().getValue());
assertEquals(getValueAsString("logourl", fields), ds.getLogourl());
assertEquals(getValueAsString("contactemail", fields), ds.getContactemail().getValue());
assertEquals(getValueAsString("namespaceprefix", fields), ds.getNamespaceprefix().getValue());
assertEquals(getValueAsString("collectedfromname", fields), ds.getCollectedfrom().get(0).getValue());
assertEquals(getValueAsString("officialname", fields), ds.getJournal().getName());
assertEquals(getValueAsString("issnPrinted", fields), ds.getJournal().getIssnPrinted());
assertEquals(getValueAsString("issnOnline", fields), ds.getJournal().getIssnOnline());
@ -90,19 +98,98 @@ public class MigrateDbEntitiesApplicationTest {
assertEquals("pubsrepository::journal", ds.getDatasourcetypeui().getClassid());
assertEquals("dnet:datasource_typologies_ui", ds.getDatasourcetypeui().getSchemeid());
assertEquals("Data Source", ds.getEosctype().getClassid());
assertEquals("Data Source", ds.getEosctype().getClassname());
assertEquals("dnet:eosc_types", ds.getEosctype().getSchemeid());
assertEquals("dnet:eosc_types", ds.getEosctype().getSchemename());
assertEquals("Journal archive", ds.getEoscdatasourcetype().getClassid());
assertEquals("Journal archive", ds.getEoscdatasourcetype().getClassname());
assertEquals("dnet:eosc_datasource_types", ds.getEoscdatasourcetype().getSchemeid());
assertEquals("dnet:eosc_datasource_types", ds.getEoscdatasourcetype().getSchemename());
assertEquals("openaire4.0", ds.getOpenairecompatibility().getClassid());
assertEquals("openaire4.0", ds.getOpenairecompatibility().getClassname());
assertEquals("dnet:datasourceCompatibilityLevel", ds.getOpenairecompatibility().getSchemeid());
assertEquals("dnet:datasourceCompatibilityLevel", ds.getOpenairecompatibility().getSchemename());
assertEquals(getValueAsDouble("latitude", fields).toString(), ds.getLatitude().getValue());
assertEquals(getValueAsDouble("longitude", fields).toString(), ds.getLongitude().getValue());
assertEquals(getValueAsString("dateofvalidation", fields), ds.getDateofvalidation());
assertEquals(getValueAsString("description", fields), ds.getDescription().getValue());
// TODO assertEquals(getValueAsString("subjects", fields), ds.getSubjects());
assertEquals("0.0", ds.getOdnumberofitems().getValue());
assertEquals(getValueAsString("odnumberofitemsdate", fields), ds.getOdnumberofitemsdate());
assertEquals(getValueAsString("odpolicies", fields), ds.getOdpolicies());
assertEquals(
getValueAsList("odlanguages", fields),
ds.getOdlanguages().stream().map(Field::getValue).collect(Collectors.toList()));
assertEquals(getValueAsList("languages", fields), ds.getLanguages());
assertEquals(
getValueAsList("accessinfopackage", fields),
ds.getAccessinfopackage().stream().map(Field::getValue).collect(Collectors.toList()));
assertEquals(getValueAsString("releasestartdate", fields), ds.getReleasestartdate());
assertEquals(getValueAsString("releaseenddate", fields), ds.getReleasestartdate());
assertEquals(getValueAsString("missionstatementurl", fields), ds.getMissionstatementurl());
assertEquals(null, ds.getDataprovider());
assertEquals(null, ds.getServiceprovider());
assertEquals(getValueAsString("databaseaccesstype", fields), ds.getDatabaseaccesstype());
assertEquals(getValueAsString("datauploadtype", fields), ds.getDatauploadtype());
assertEquals(getValueAsString("databaseaccessrestriction", fields), ds.getDatabaseaccessrestriction());
assertEquals(getValueAsString("datauploadrestriction", fields), ds.getDatauploadrestriction());
assertEquals(false, ds.getVersioning().getValue());
assertEquals(false, ds.getVersioncontrol());
assertEquals(getValueAsString("citationguidelineurl", fields), ds.getCitationguidelineurl());
assertEquals(getValueAsString("pidsystems", fields), ds.getPidsystems());
assertEquals(getValueAsString("certificates", fields), ds.getCertificates());
assertEquals(getValueAsList("researchentitytypes", fields), ds.getResearchentitytypes());
assertEquals("National", ds.getJurisdiction().getClassid());
assertEquals("eosc:jurisdictions", ds.getJurisdiction().getSchemeid());
assertTrue(ds.getThematic());
assertTrue(ds.getKnowledgegraph());
assertEquals(1, ds.getContentpolicies().size());
assertEquals("Journal article", ds.getContentpolicies().get(0).getClassid());
assertEquals("eosc:contentpolicies", ds.getContentpolicies().get(0).getSchemeid());
HashSet<String> cpSchemeId = ds
.getContentpolicies()
.stream()
.map(Qualifier::getSchemeid)
.collect(Collectors.toCollection(HashSet::new));
assertTrue(cpSchemeId.size() == 1);
assertTrue(cpSchemeId.contains("eosc:contentpolicies"));
HashSet<String> cpSchemeName = ds
.getContentpolicies()
.stream()
.map(Qualifier::getSchemename)
.collect(Collectors.toCollection(HashSet::new));
assertTrue(cpSchemeName.size() == 1);
assertTrue(cpSchemeName.contains("eosc:contentpolicies"));
assertEquals(2, ds.getContentpolicies().size());
assertEquals("Taxonomic classification", ds.getContentpolicies().get(0).getClassid());
assertEquals("Resource collection", ds.getContentpolicies().get(1).getClassid());
assertEquals(getValueAsString("submissionpolicyurl", fields), ds.getSubmissionpolicyurl());
assertEquals(getValueAsString("preservationpolicyurl", fields), ds.getPreservationpolicyurl());
assertEquals(
getValueAsList("researchproductaccesspolicies", fields),
ds.getResearchproductaccesspolicies());
assertEquals(
getValueAsList("researchproductmetadataaccesspolicies", fields),
ds.getResearchproductmetadataaccesspolicies());
assertEquals(true, ds.getConsenttermsofuse());
assertEquals(true, ds.getFulltextdownload());
assertEquals("2022-03-11", ds.getConsenttermsofusedate());
assertEquals("2022-03-11", ds.getLastconsenttermsofusedate());
}
@Test
@ -154,7 +241,7 @@ public class MigrateDbEntitiesApplicationTest {
public void testProcessDatasourceOrganization() throws Exception {
final List<TypedField> fields = prepareMocks("datasourceorganization_resultset_entry.json");
final List<Oaf> list = app.processDatasourceOrganization(rs);
final List<Oaf> list = app.processServiceOrganization(rs);
assertEquals(2, list.size());
verifyMocks(fields);
@ -356,18 +443,31 @@ public class MigrateDbEntitiesApplicationTest {
}
private Float getValueAsFloat(final String name, final List<TypedField> fields) {
return new Float(getValueAs(name, fields).toString());
final Object value = getValueAs(name, fields);
return value != null ? new Float(value.toString()) : null;
}
private Double getValueAsDouble(final String name, final List<TypedField> fields) {
final Object value = getValueAs(name, fields);
return value != null ? new Double(value.toString()) : null;
}
private Integer getValueAsInt(final String name, final List<TypedField> fields) {
final Object value = getValueAs(name, fields);
return value != null ? new Integer(value.toString()) : null;
}
private <T> T getValueAs(final String name, final List<TypedField> fields) {
return fields
final Optional<T> field = fields
.stream()
.filter(f -> f.getField().equals(name))
.map(TypedField::getValue)
.filter(Objects::nonNull)
.map(o -> (T) o)
.findFirst()
.get();
.map(TypedField::getValue)
.map(o -> (T) o);
if (!field.isPresent()) {
return null;
}
return field.get();
}
private List<String> getValueAsList(final String name, final List<TypedField> fields) {

29
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/sx/pangaea/PangaeaTransformTest.scala
View File

@ -1,29 +0,0 @@
package eu.dnetlib.dhp.sx.pangaea
import eu.dnetlib.dhp.sx.graph.pangaea.PangaeaUtils
import org.junit.jupiter.api.Test
import java.util.TimeZone
import java.text.SimpleDateFormat
import java.util.Date
import scala.io.Source
class PangaeaTransformTest {
@Test
def test_dateStamp() :Unit ={
val d = new Date()
val s:String = s"${new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ss.SSS")format d}Z"
println(s)
val xml = Source.fromInputStream(getClass.getResourceAsStream("input.xml")).mkString
println(PangaeaUtils.parseXml(xml))
}
}

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

@ -497,6 +497,7 @@ dnet:publication_resource @=@ 0044 @=@ Graduate diploma
dnet:publication_resource @=@ 0044 @=@ Undergraduate diploma
dnet:publication_resource @=@ 0000 @=@ UNKNOWN
dnet:publication_resource @=@ 0042 @=@ EGI Virtual Appliance
dnet:publication_resource @=@ 0048 @=@ RO-crate
dnet:languages @=@ abk @=@ ab
dnet:languages @=@ aar @=@ aa
dnet:languages @=@ afr @=@ af

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

@ -164,6 +164,7 @@ dnet:publication_resource @=@ dnet:publication_resource @=@ 0030 @=@ Sound
dnet:publication_resource @=@ dnet:publication_resource @=@ 0044 @=@ Thesis
dnet:publication_resource @=@ dnet:publication_resource @=@ 0000 @=@ Unknown
dnet:publication_resource @=@ dnet:publication_resource @=@ 0042 @=@ Virtual Appliance
dnet:publication_resource @=@ dnet:publication_resource @=@ 0048 @=@ Research Object
ec:funding_typologies @=@ ec:funding_typologies @=@ ec:frameworkprogram @=@ frameworkprogram
ec:funding_typologies @=@ ec:funding_typologies @=@ ec:program @=@ program
ec:funding_typologies @=@ ec:funding_typologies @=@ ec:specificprogram @=@ specificprogram

2
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/datasource.json
View File

File diff suppressed because one or more lines are too long

6
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/merge/datasource_cris.json
View File

@ -1 +1,5 @@
{ "id": "10|274269ac6f3b::2a2e2793b500f3f7b47ef24b1a9277b7", "openairecompatibility": { "classid": "openaire-cris_1.1" }}
{ "id": "10|274269ac6f3b::2a2e2793b500f3f7b47ef24b1a9277b7", "openairecompatibility": { "classid": "openaire-cris_1.1" },
"originalId": ["eurocrisdris::1234"],
"collectedfrom": [{"key": "eurocrisdris::2b29d08e383ff4cd8a2b6b226ce37e38", "value": "Directory of Research Information System (DRIS)"}],
"pid": [{"value": "10.1010.xyx", "qualifier": {"classid": "doi"}}]
}

5
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/merge/datasource_openaire2.0.json
View File

@ -1 +1,4 @@
{ "id": "10|274269ac6f3b::2a2e2793b500f3f7b47ef24b1a9277b7", "openairecompatibility": { "classid": "openaire2.0" }}
{ "id": "10|274269ac6f3b::2a2e2793b500f3f7b47ef24b1a9277b7", "openairecompatibility": { "classid": "openaire2.0" },
"originalId": ["opendoar____::1234"],
"collectedfrom": [{"key": "openaire____::47ce9e9f4fad46e732cff06419ecaabb", "value": "OpenDOAR"}]
}

2
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/datasourceorganization_resultset_entry.json
View File

@ -1,6 +1,6 @@
[
{
"field": "datasource",
"field": "service",
"type": "string",
"value": "openaire____::revistasunicauca"
},

103
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/rohub.xml Normal file
View File

@ -0,0 +1,103 @@
<?xml version="1.0" encoding="UTF-8"?>
<record xmlns:datacite="http://datacite.org/schema/kernel-4"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<header xmlns="http://www.openarchives.org/OAI/2.0/">
<dri:objIdentifier>eosca5322f5f::4dd1aaf93ae136b65dc9ee4e6f76eac9</dri:objIdentifier>
<dri:recordIdentifier>53aa90bf-c593-4e6d-923f-d4711ac4b0e1</dri:recordIdentifier>
<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>ro-crate_data</setSpec>
<dr:dateOfTransformation>2022-05-25T15:36:11.094Z</dr:dateOfTransformation>
</header>
<metadata>
<oaire:resource xmlns="http://namespace.openaire.eu/schema/oaire/">
<datacite:identifier identifierType="landingPage">https://w3id.org/ro-id/53aa90bf-c593-4e6d-923f-d4711ac4b0e1</datacite:identifier>
<datacite:alternateIdentifiers>
<datacite:alternateIdentifier alternateIdentifierType="URL">http://api.rohub.org/api/ros/53aa90bf-c593-4e6d-923f-d4711ac4b0e1/</datacite:alternateIdentifier>
</datacite:alternateIdentifiers>
<datacite:relatedIdentifiers>
<datacite:relatedIdentifier relatedIdentifierType="" relationType="">
https://github.com/NordicESMhub/RELIANCE/blob/main/content/science/notebooks/air_quality_lockdown.ipynb
</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="">
https://nordicesmhub.github.io/RELIANCE/science/notebooks/air_quality_lockdown.html
</datacite:relatedIdentifier>
<datacite:relatedIdentifier relatedIdentifierType="URI" relationType="IsPartOf">https://nordicesmhub.github.io/RELIANCE/science/notebooks/air_quality_lockdown.html</datacite:relatedIdentifier>
</datacite:relatedIdentifiers>
<creators xmlns="http://datacite.org/schema/kernel-4">
<creator>
<creator>
<creatorName>Anne Fouilloux</creatorName>
</creator>
</creator>
</creators>
<dates xmlns="http://datacite.org/schema/kernel-4">
<date dateType="Created">2021-12-19T21:18:33Z</date>
</dates>
<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:descriptions>
<oaire:fundingReferences>
<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">
<rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</rights>
</rightsList>
<sizes xmlns="http://datacite.org/schema/kernel-4">
<size>11.971 MB</size>
</sizes>
<subjects xmlns="http://datacite.org/schema/kernel-4">
<subject>Applied sciences</subject>
<subject>Meteorology</subject>
<subject>EOSC::RO-crate</subject>
</subjects>
<titles xmlns="http://datacite.org/schema/kernel-4">
<title>Impact of the Covid-19 Lockdown on Air quality over Europe</title>
</titles>
</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:accessrights>OPEN</oaf:accessrights>
<oaf:license>https://opensource.org/licenses/MIT</oaf:license>
<oaf:language>und</oaf:language>
<oaf:hostedBy id="eosc________::psnc::psnc.rohub" name="ROHub"/>
<oaf:collectedFrom id="eosc________::psnc::psnc.rohub" name="ROHub"/>
</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>

238
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/datasources_resultset_entry.json → dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/services_resultset_entry.json
View File

@ -1,18 +1,51 @@
[
{
"field": "datasourceid",
"field": "id",
"type": "string",
"value": "274269ac6f3b::2579-5449"
},
{
"field": "identities",
"field": "originalid",
"type": "array",
"value": [
"274269ac6f3b::2579-5449",
"fairsharing_::1562",
"piwik:13",
null
null,
"re3data_____::r3d100010213"
]
},
{
"field": "pid",
"type": "array",
"value": [
"r3d100010218###re3data@@@dnet:pid_types"
]
},
{
"field": "datasourcetype",
"type": "string",
"value": "pubsrepository::journal@@@dnet:datasource_typologies"
},
{
"field": "datasourcetypeui",
"type": "string",
"value": "pubsrepository::journal@@@dnet:datasource_typologies_ui"
},
{
"field": "eosctype",
"type": "string",
"value": "Data Source@@@dnet:eosc_types"
},
{
"field": "eoscdatasourcetype",
"type": "string",
"value": "Journal archive@@@dnet:eosc_datasource_types"
},
{
"field": "openairecompatibility",
"type": "string",
"value": "openaire4.0@@@dnet:datasourceCompatibilityLevel"
},
{
"field": "officialname",
"type": "string",
@ -23,16 +56,6 @@
"type": "string",
"value": "Jurnal Ilmiah Pendidikan Scholastic"
},
{
"field": "contactemail",
"type": "string",
"value": "test@test.it"
},
{
"field": "openairecompatibility",
"type": "string",
"value": "hostedBy@@@dnet:datasourceCompatibilityLevel"
},
{
"field": "websiteurl",
"type": "string",
@ -44,11 +67,14 @@
"value": null
},
{
"field": "accessinfopackage",
"type": "array",
"value": [
null
]
"field": "contactemail",
"type": "string",
"value": "test@test.it"
},
{
"field": "namespaceprefix",
"type": "string",
"value": "ojs_25795449"
},
{
"field": "latitude",
@ -61,9 +87,19 @@
"value": 0
},
{
"field": "namespaceprefix",
"field": "dateofvalidation",
"type": "date",
"value": null
},
{
"field": "description",
"type": "string",
"value": "ojs_25795449"
"value": "veterinary medicine"
},
{
"field": "subjects",
"type": "array",
"value": []
},
{
"field": "odnumberofitems",
@ -75,16 +111,6 @@
"type": "date",
"value": null
},
{
"field": "subjects",
"type": "array",
"value": null
},
{
"field": "description",
"type": "string",
"value": null
},
{
"field": "odpolicies",
"type": "string",
@ -93,44 +119,33 @@
{
"field": "odlanguages",
"type": "array",
"value": []
},
{
"field": "odcontenttypes",
"type": "array",
"value": [
"Journal articles"
"English",
"German",
"French",
"Danish",
"Norwegian",
"Swedish"
]
},
{
"field": "inferred",
"type": "boolean",
"value": false
"field": "languages",
"type": "array",
"value": [
"English",
"German",
"French",
"Danish",
"Norwegian",
"Swedish"
]
},
{
"field": "deletedbyinference",
"type": "boolean",
"value": false
},
{
"field": "trust",
"type": "double",
"value": 0.9
},
{
"field": "inferenceprovenance",
"type": "string",
"value": null
},
{
"field": "dateofcollection",
"type": "date",
"value": "2020-01-21"
},
{
"field": "dateofvalidation",
"type": "date",
"value": null
"field": "accessinfopackage",
"type": "array",
"value": [
"http://www.revista.vocesdelaeducacion.com.mx/index.php/index/oai"
]
},
{
"field": "releasestartdate",
@ -147,16 +162,6 @@
"type": "string",
"value": null
},
{
"field": "dataprovider",
"type": "boolean",
"value": null
},
{
"field": "serviceprovider",
"type": "boolean",
"value": null
},
{
"field": "databaseaccesstype",
"type": "string",
@ -183,12 +188,12 @@
"value": null
},
{
"field": "citationguidelineurl",
"type": "string",
"field": "versioncontrol",
"type": "boolean",
"value": null
},
{
"field": "qualitymanagementkind",
"field": "citationguidelineurl",
"type": "string",
"value": null
},
@ -208,29 +213,38 @@
"value": []
},
{
"field": "collectedfromid",
"type": "string",
"value": "openaire____::SnVybmFsIEZha3VsdGFzIFNhc3RyYSBVbml2ZXJzaXRhcyBFa2FzYWt0aQ=="
"field": "inferred",
"type": "boolean",
"value": false
},
{
"field": "collectedfromname",
"type": "string",
"value": "Jurnal Fakultas Sastra Universitas Ekasakti"
"field": "deletedbyinference",
"type": "boolean",
"value": false
},
{
"field": "datasourcetype",
"type": "string",
"value": "pubsrepository::journal@@@dnet:datasource_typologies"
"field": "trust",
"type": "double",
"value": 0.9
},
{
"field": "datasourcetypeui",
"field": "inferenceprovenance",
"type": "string",
"value": "pubsrepository::journal@@@dnet:datasource_typologies_ui"
"value": null
},
{
"field": "provenanceaction",
"type": "not_used",
"value": "sysimport:crosswalk:entityregistry@@@dnet:provenance_actions"
"field": "dateofcollection",
"type": "date",
"value": "2020-01-21"
},
{
"field": "collectedfrom",
"type": "array",
"value": [
"openaire____::fairsharing@@@FAIRsharing.org",
"openaire____::opendoar@@@OpenDOAR",
"openaire____::re3data@@@Registry of Research Data Repository"
]
},
{
"field": "issnPrinted",
@ -247,6 +261,13 @@
"type": "string",
"value": "2579-5447"
},
{
"field": "researchentitytypes",
"type": "array",
"value": [
"Research Data"
]
},
{
"field": "jurisdiction",
"type": "string",
@ -257,16 +278,36 @@
"type": "boolean",
"value": true
},
{
"field": "knowledgegraph",
"type": "boolean",
"value": true
},
{
"field": "contentpolicies",
"type": "array",
"value": [
"Journal article@@@eosc:contentpolicies"
"Taxonomic classification@@@eosc:contentpolicies",
"Resource collection@@@eosc:contentpolicies"
]
},
{
"field": "submissionpolicyurl",
"type": "string",
"value": null
},
{
"field": "preservationpolicyurl",
"type": "string",
"value": "Permanent Archiving https://datadryad.org/stash/faq"
},
{
"field": "researchproductaccesspolicies",
"type": "array",
"value": [
"https://100percentit.com/legal/"
]
},
{
"field": "researchproductmetadataaccesspolicies",
"type": "array",
"value": [
"https://wenmr.science.uu.nl/conditions"
]
},
{
@ -283,5 +324,10 @@
"field": "consenttermsofusedate",
"type": "date",
"value": "2022-03-11"
},
{
"field": "lastconsenttermsofusedate",
"type": "date",
"value": "2022-03-11"
}
]

BIN
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/sample/datasource/datasource_10.json.gz
View File

Binary file not shown.

89
dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/XmlRecordFactory.java
View File

@ -535,6 +535,12 @@ public class XmlRecordFactory implements Serializable {
if (ds.getDatasourcetypeui() != null) {
metadata.add(XmlSerializationUtils.mapQualifier("datasourcetypeui", ds.getDatasourcetypeui()));
}
if (ds.getEosctype() != null) {
metadata.add(XmlSerializationUtils.mapQualifier("eosctype", ds.getEosctype()));
}
if (ds.getEoscdatasourcetype() != null) {
metadata.add(XmlSerializationUtils.mapQualifier("eoscdatasourcetype", ds.getEoscdatasourcetype()));
}
if (ds.getOpenairecompatibility() != null) {
metadata
.add(
@ -583,6 +589,16 @@ public class XmlRecordFactory implements Serializable {
metadata
.add(XmlSerializationUtils.asXmlElement("description", ds.getDescription().getValue()));
}
if (ds.getSubjects() != null) {
metadata
.addAll(
ds
.getSubjects()
.stream()
.filter(Objects::nonNull)
.map(sp -> XmlSerializationUtils.mapStructuredProperty("subjects", sp))
.collect(Collectors.toList()));
}
if (ds.getOdnumberofitems() != null) {
metadata
.add(
@ -609,6 +625,16 @@ public class XmlRecordFactory implements Serializable {
.map(c -> XmlSerializationUtils.asXmlElement("odlanguages", c.getValue()))
.collect(Collectors.toList()));
}
if (ds.getLanguages() != null) {
metadata
.addAll(
ds
.getLanguages()
.stream()
.filter(Objects::nonNull)
.map(c -> XmlSerializationUtils.asXmlElement("languages", c))
.collect(Collectors.toList()));
}
if (ds.getOdcontenttypes() != null) {
metadata
.addAll(
@ -689,18 +715,18 @@ public class XmlRecordFactory implements Serializable {
XmlSerializationUtils
.asXmlElement("versioning", ds.getVersioning().getValue().toString()));
}
if (ds.getVersioncontrol() != null) {
metadata
.add(
XmlSerializationUtils
.asXmlElement("versioncontrol", ds.getVersioncontrol().toString()));
}
if (ds.getCitationguidelineurl() != null) {
metadata
.add(
XmlSerializationUtils
.asXmlElement("citationguidelineurl", ds.getCitationguidelineurl().getValue()));
}
if (ds.getQualitymanagementkind() != null) {
metadata
.add(
XmlSerializationUtils
.asXmlElement("qualitymanagementkind", ds.getQualitymanagementkind().getValue()));
}
if (ds.getPidsystems() != null) {
metadata
.add(XmlSerializationUtils.asXmlElement("pidsystems", ds.getPidsystems().getValue()));
@ -722,17 +748,24 @@ public class XmlRecordFactory implements Serializable {
if (ds.getJournal() != null) {
metadata.add(XmlSerializationUtils.mapJournal(ds.getJournal()));
}
if (ds.getSubjects() != null) {
if (ds.getResearchentitytypes() != null) {
metadata
.addAll(
ds
.getSubjects()
.getResearchentitytypes()
.stream()
.filter(Objects::nonNull)
.map(sp -> XmlSerializationUtils.mapStructuredProperty("subjects", sp))
.map(c -> XmlSerializationUtils.asXmlElement("researchentitytypes", c))
.collect(Collectors.toList()));
}
if (ds.getProvidedproducttypes() != null) {
metadata
.addAll(
ds
.getProvidedproducttypes()
.stream()
.map(c -> XmlSerializationUtils.asXmlElement("providedproducttypes", c))
.collect(Collectors.toList()));
}
if (ds.getJurisdiction() != null) {
metadata.add(XmlSerializationUtils.mapQualifier("jurisdiction", ds.getJurisdiction()));
}
@ -741,11 +774,6 @@ public class XmlRecordFactory implements Serializable {
metadata.add(XmlSerializationUtils.asXmlElement("thematic", ds.getThematic().toString()));
}
if (ds.getKnowledgegraph() != null) {
metadata
.add(XmlSerializationUtils.asXmlElement("knowledgegraph", ds.getKnowledgegraph().toString()));
}
if (ds.getContentpolicies() != null) {
metadata
.addAll(
@ -756,7 +784,34 @@ public class XmlRecordFactory implements Serializable {
.map(q -> XmlSerializationUtils.mapQualifier("contentpolicy", q))
.collect(Collectors.toList()));
}
if (ds.getSubmissionpolicyurl() != null) {
metadata
.add(XmlSerializationUtils.asXmlElement("submissionpolicyurl", ds.getSubmissionpolicyurl()));
}
if (ds.getPreservationpolicyurl() != null) {
metadata
.add(
XmlSerializationUtils.asXmlElement("preservationpolicyurl", ds.getPreservationpolicyurl()));
}
if (ds.getResearchproductaccesspolicies() != null) {
metadata
.addAll(
ds
.getResearchproductaccesspolicies()
.stream()
.map(c -> XmlSerializationUtils.asXmlElement("researchproductaccesspolicies", c))
.collect(Collectors.toList()));
}
if (ds.getResearchproductmetadataaccesspolicies() != null) {
metadata
.addAll(
ds
.getResearchproductmetadataaccesspolicies()
.stream()
.map(
c -> XmlSerializationUtils.asXmlElement("researchproductmetadataaccesspolicies", c))
.collect(Collectors.toList()));
}
break;
case organization:
final Organization o = (Organization) entity;

3
dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/sx/provision/scholix_index.json
View File

@ -41,7 +41,8 @@
}
},
"publicationDate": {
"type": "keyword"
"type": "date",
"format": "yyyy-MM-dd"
},
"relationship": {
"properties": {

11
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlRecordFactoryTest.java
View File

@ -11,6 +11,7 @@ import java.util.List;
import org.apache.commons.io.IOUtils;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.junit.jupiter.api.Test;
@ -142,7 +143,7 @@ public class XmlRecordFactoryTest {
}
@Test
public void testDatasource() throws IOException, DocumentException {
public void testService() throws IOException, DocumentException {
final ContextMapper contextMapper = new ContextMapper();
final XmlRecordFactory xmlRecordFactory = new XmlRecordFactory(contextMapper, false,
@ -167,6 +168,14 @@ public class XmlRecordFactoryTest {
assertEquals("true", doc.valueOf("//thematic"));
assertEquals("Journal article", doc.valueOf("//contentpolicy/@classname"));
assertEquals("Journal archive", doc.valueOf("//datasourcetypeui/@classname"));
assertEquals("Data Source", doc.valueOf("//eosctype/@classname"));
final List pids = doc.selectNodes("//pid");
assertEquals(1, pids.size());
assertEquals("re3data", ((Element) pids.get(0)).attribute("classid").getValue());
assertEquals(
"Registry of research data repositories", ((Element) pids.get(0)).attribute("classname").getValue());
assertEquals("dnet:pid_types", ((Element) pids.get(0)).attribute("schemeid").getValue());
assertEquals("dnet:pid_types", ((Element) pids.get(0)).attribute("schemename").getValue());
}
}

389
dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/datasource.json
View File

File diff suppressed because one or more lines are too long

32
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql
View File

@ -80,4 +80,34 @@ where reltype='resultResult'
and r2.datainfo.deletedbyinference=false and r2.datainfo.invisible = FALSE
and r1.resulttype.classname != 'other'
and r2.resulttype.classname != 'other'
and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE;
and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE;
create table ${stats_db_name}.result_citations_oc stored as parquet as
select substr(target, 4) as id, count(distinct substr(source, 4)) as citations
from ${openaire_db_name}.relation rel
join ${openaire_db_name}.result r1 on rel.source=r1.id
join ${openaire_db_name}.result r2 on r2.id=rel.target
where relClass='Cites' and rel.datainfo.provenanceaction.classid = 'sysimport:crosswalk:opencitations'
and reltype='resultResult'
and r1.resulttype.classname!=r2.resulttype.classname
and r1.datainfo.deletedbyinference=false and r1.datainfo.invisible = FALSE
and r2.datainfo.deletedbyinference=false and r2.datainfo.invisible = FALSE
and r1.resulttype.classname != 'other'
and r2.resulttype.classname != 'other'
and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE
group by substr(target, 4);
create table ${stats_db_name}.result_references_oc stored as parquet as
select substr(source, 4) as id, count(distinct substr(target, 4)) as references
from ${openaire_db_name}.relation rel
join ${openaire_db_name}.result r1 on rel.source=r1.id
join ${openaire_db_name}.result r2 on r2.id=rel.target
where relClass='Cites' and rel.datainfo.provenanceaction.classid = 'sysimport:crosswalk:opencitations'
and reltype='resultResult'
and r1.resulttype.classname!=r2.resulttype.classname
and r1.datainfo.deletedbyinference=false and r1.datainfo.invisible = FALSE
and r2.datainfo.deletedbyinference=false and r2.datainfo.invisible = FALSE
and r1.resulttype.classname != 'other'
and r2.resulttype.classname != 'other'
and rel.datainfo.deletedbyinference=false and rel.datainfo.invisible = FALSE
group by substr(source, 4);

48
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql
View File

@ -82,31 +82,31 @@ on r.id= tmp.id;
compute stats indi_funded_result_with_fundref;
create table indi_result_org_country_collab stored as parquet as
with tmp as
(select o.id as id, o.country , ro.id as result,r.type from organization o
join result_organization ro on o.id=ro.organization
join result r on r.id=ro.id where o.country <> 'UNKNOWN')
select o1.id org1,o2.country country2, o1.type, count(distinct o1.result) as collaborations
from tmp as o1
join tmp as o2 on o1.result=o2.result
where o1.id<>o2.id and o1.country<>o2.country
group by o1.id, o1.type,o2.country;
-- create table indi_result_org_country_collab stored as parquet as
-- with tmp as
-- (select o.id as id, o.country , ro.id as result,r.type from organization o
-- join result_organization ro on o.id=ro.organization
-- join result r on r.id=ro.id where o.country <> 'UNKNOWN')
-- select o1.id org1,o2.country country2, o1.type, count(distinct o1.result) as collaborations
-- from tmp as o1
-- join tmp as o2 on o1.result=o2.result
-- where o1.id<>o2.id and o1.country<>o2.country
-- group by o1.id, o1.type,o2.country;
--
-- compute stats indi_result_org_country_collab;
compute stats indi_result_org_country_collab;
create table indi_result_org_collab stored as parquet as
with tmp as
(select o.id, ro.id as result,r.type from organization o
join result_organization ro on o.id=ro.organization
join result r on r.id=ro.id)
select o1.id org1,o2.id org2, o1.type, count(distinct o1.result) as collaborations
from tmp as o1
join tmp as o2 on o1.result=o2.result
where o1.id<>o2.id
group by o1.id, o2.id, o1.type;
compute stats indi_result_org_collab;
-- create table indi_result_org_collab stored as parquet as
-- with tmp as
-- (select o.id, ro.id as result,r.type from organization o
-- join result_organization ro on o.id=ro.organization
-- join result r on r.id=ro.id)
-- select o1.id org1,o2.id org2, o1.type, count(distinct o1.result) as collaborations
-- from tmp as o1
-- join tmp as o2 on o1.result=o2.result
-- where o1.id<>o2.id
-- group by o1.id, o2.id, o1.type;
--
-- compute stats indi_result_org_collab;
create table indi_funder_country_collab stored as parquet as
with tmp as (select funder, project, country from organization_projects op

50
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql
View File

@ -18,28 +18,45 @@ create table TARGET.result stored as parquet as
select * from SOURCE.result r where exists (select 1 from SOURCE.result_concepts rc where rc.id=r.id)
union all
select * from SOURCE.result r where exists (select 1 from SOURCE.result_organization ro where ro.id=r.id and ro.organization in (
'openorgs____::759d59f05d77188faee99b7493b46805',
'openorgs____::b84450f9864182c67b8611b5593f4250',
'openorgs____::d41cf6bd4ab1b1362a44397e0b95c975',
'openorgs____::eadc8da90a546e98c03f896661a2e4d4',
'openorgs____::d2a09b9d5eabb10c95f9470e172d05d2',
'openorgs____::d169c7407dd417152596908d48c11460',
'openorgs____::1ec924b1759bb16d0a02f2dad8689b21',
'openorgs____::2fb1e47b4612688d9de9169d579939a7',
'openorgs____::759d59f05d77188faee99b7493b46805',
'openorgs____::cad284878801b9465fa51a95b1d779db',
'openorgs____::eadc8da90a546e98c03f896661a2e4d4',
'openorgs____::c0286313e36479eff8676dba9b724b40'
-- ,'openorgs____::c80a8243a5e5c620d7931c88d93bf17a' -- Paris Diderot
) )) foo;
'openorgs____::b84450f9864182c67b8611b5593f4250', --"Athena Research and Innovation Center In Information Communication & Knowledge Technologies', --ARC"
'openorgs____::d41cf6bd4ab1b1362a44397e0b95c975', --National Research Council
'openorgs____::d2a09b9d5eabb10c95f9470e172d05d2', --??? Not exists ??
'openorgs____::d169c7407dd417152596908d48c11460', --Masaryk University
'openorgs____::1ec924b1759bb16d0a02f2dad8689b21', --University of Belgrade
'openorgs____::2fb1e47b4612688d9de9169d579939a7', --University of Helsinki
'openorgs____::759d59f05d77188faee99b7493b46805', --University of Minho
'openorgs____::cad284878801b9465fa51a95b1d779db', --Universidad Politécnica de Madrid
'openorgs____::eadc8da90a546e98c03f896661a2e4d4', --University of Göttingen
'openorgs____::c0286313e36479eff8676dba9b724b40', --National and Kapodistrian University of Athens
-- 'openorgs____::c80a8243a5e5c620d7931c88d93bf17a', --Université Paris Diderot
'openorgs____::c08634f0a6b0081c3dc6e6c93a4314f3', --Bielefeld University
'openorgs____::6fc85e4a8f7ecaf4b0c738d010e967ea', --University of Southern Denmark
'openorgs____::3d6122f87f9a97a99d8f6e3d73313720', --Humboldt-Universität zu Berlin
'openorgs____::16720ada63d0fa8ca41601feae7d1aa5', --TU Darmstadt
'openorgs____::ccc0a066b56d2cfaf90c2ae369df16f5', --KU Leuven
'openorgs____::4c6f119632adf789746f0a057ed73e90', --University of the Western Cape
'openorgs____::ec3665affa01aeafa28b7852c4176dbd', --Rudjer Boskovic Institute
'openorgs____::5f31346d444a7f06a28c880fb170b0f6', --Ghent University
'openorgs____::2dbe47117fd5409f9c61620813456632', --University of Luxembourg
'openorgs____::6445d7758d3a40c4d997953b6632a368' --National Institute of Informatics (NII)
) )) foo;
compute stats TARGET.result;
create table TARGET.result_citations stored as parquet as select * from SOURCE.result_citations orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_citations;
create table TARGET.result_references_oc stored as parquet as select * from SOURCE.result_references_oc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_references_oc;
create table TARGET.result_citations_oc stored as parquet as select * from SOURCE.result_citations_oc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_citations_oc;
create table TARGET.result_classifications stored as parquet as select * from SOURCE.result_classifications orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_classifications;
create table TARGET.result_apc stored as parquet as select * from SOURCE.result_apc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_apc;
create table TARGET.result_concepts stored as parquet as select * from SOURCE.result_concepts orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_concepts;
@ -90,11 +107,6 @@ compute stats TARGET.result_sources;
create table TARGET.result_topics stored as parquet as select * from SOURCE.result_topics orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_topics;
create table TARGET.result_apc stored as parquet as select * from SOURCE.result_apc orig where exists (select 1 from TARGET.result r where r.id=orig.id);
compute stats TARGET.result_apc;
create view TARGET.foo1 as select * from SOURCE.result_result rr where rr.source in (select id from TARGET.result);
create view TARGET.foo2 as select * from SOURCE.result_result rr where rr.target in (select id from TARGET.result);
create table TARGET.result_result STORED AS PARQUET as select distinct * from (select * from TARGET.foo1 union all select * from TARGET.foo2) foufou;

1
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql
View File

@ -127,6 +127,7 @@ CREATE TABLE ${stats_db_name}.result_organization STORED AS PARQUET AS
SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS organization
FROM ${openaire_db_name}.relation r
WHERE r.reltype = 'resultOrganization'
and r.target like '50|%'
and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false;
CREATE TABLE ${stats_db_name}.result_projects STORED AS PARQUET AS

2
dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql
View File

@ -93,7 +93,7 @@ where d.datainfo.deletedbyinference=false and d.datainfo.invisible=false;
CREATE TABLE ${stats_db_name}.datasource_organizations STORED AS PARQUET AS
SELECT substr(r.target, 4) AS id, substr(r.source, 4) AS organization
FROM ${openaire_db_name}.relation r
WHERE r.reltype = 'datasourceOrganization' and r.datainfo.deletedbyinference = false and r.datainfo.invisible=false;
WHERE r.reltype = 'datasourceOrganization' and r.datainfo.deletedbyinference = false and r.target like '20|%' and r.datainfo.invisible=false;
-- datasource sources:
-- where the datasource info have been collected from.

2
pom.xml
View File

@ -801,7 +801,7 @@
<mockito-core.version>3.3.3</mockito-core.version>
<mongodb.driver.version>3.4.2</mongodb.driver.version>
<vtd.version>[2.12,3.0)</vtd.version>
<dhp-schemas.version>[2.10.32]</dhp-schemas.version>
<dhp-schemas.version>[2.12.0]</dhp-schemas.version>
<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>