mergin with branch beta

This commit is contained in:
Miriam Baglioni 2022-05-04 10:06:56 +02:00
commit bd1108f98b
18 changed files with 1054 additions and 311 deletions

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()

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"));
}

View File

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

View File

@ -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)
}

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;

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>

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

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);

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)

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)

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);

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')
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

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(false, ds.getDataprovider().getValue());
assertEquals(false, ds.getServiceprovider().getValue());
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) {

View File

@ -5,14 +5,47 @@
"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 +261,20 @@
"type": "string",
"value": "2579-5447"
},
{
"field": "researchentitytypes",
"type": "array",
"value": [
"Research Data"
]
},
{
"field": "providedproducttypes",
"type": "array",
"value": [
]
},
{
"field": "jurisdiction",
"type": "string",
@ -266,7 +294,32 @@
"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 +336,10 @@
"field": "consenttermsofusedate",
"type": "date",
"value": "2022-03-11"
},
{
"field": "lastconsenttermsofusedate",
"type": "date",
"value": "2022-03-11"
}
]

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;

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());
}
}

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>