forked from D-Net/dnet-hadoop
Compare commits
1 Commits
beta
...
serializeL
| Author | SHA1 | Date |
|---|---|---|
 Alessia Bardi
|
300df8b278 | 3 years ago |
@ -1,2 +1,2 @@
|
||||
# dnet-hadoop
|
||||
Dnet-hadoop is the project that defined all the OOZIE workflows for the OpenAIRE Graph construction, processing, provisioning.
|
||||
Dnet-hadoop is a tool for
|
||||
@ -1,21 +0,0 @@
|
||||
style = defaultWithAlign
|
||||
|
||||
align.openParenCallSite = false
|
||||
align.openParenDefnSite = false
|
||||
align.tokens = [{code = "->"}, {code = "<-"}, {code = "=>", owner = "Case"}]
|
||||
continuationIndent.callSite = 2
|
||||
continuationIndent.defnSite = 2
|
||||
danglingParentheses = true
|
||||
indentOperator = spray
|
||||
maxColumn = 120
|
||||
newlines.alwaysBeforeTopLevelStatements = true
|
||||
project.excludeFilters = [".*\\.sbt"]
|
||||
rewrite.rules = [AvoidInfix]
|
||||
rewrite.rules = [ExpandImportSelectors]
|
||||
rewrite.rules = [RedundantBraces]
|
||||
rewrite.rules = [RedundantParens]
|
||||
rewrite.rules = [SortImports]
|
||||
rewrite.rules = [SortModifiers]
|
||||
rewrite.rules = [PreferCurlyFors]
|
||||
spaces.inImportCurlyBraces = false
|
||||
unindentTopLevelOperators = true
|
||||
@ -1,21 +0,0 @@
|
||||
<?xml version="1.0" encoding="ISO-8859-1"?>
|
||||
<project xmlns="http://maven.apache.org/DECORATION/1.8.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xsi:schemaLocation="http://maven.apache.org/DECORATION/1.8.0 https://maven.apache.org/xsd/decoration-1.8.0.xsd"
|
||||
name="DHP-Aggregation">
|
||||
<skin>
|
||||
<groupId>org.apache.maven.skins</groupId>
|
||||
<artifactId>maven-fluido-skin</artifactId>
|
||||
<version>1.8</version>
|
||||
</skin>
|
||||
<poweredBy>
|
||||
<logo name="OpenAIRE Research Graph" href="https://graph.openaire.eu/"
|
||||
img="https://graph.openaire.eu/assets/common-assets/logo-large-graph.png"/>
|
||||
</poweredBy>
|
||||
<body>
|
||||
<links>
|
||||
<item name="Code" href="https://code-repo.d4science.org/" />
|
||||
</links>
|
||||
<menu ref="modules" />
|
||||
<menu ref="reports"/>
|
||||
</body>
|
||||
</project>
|
||||
@ -1,22 +0,0 @@
|
||||
<?xml version="1.0" encoding="ISO-8859-1"?>
|
||||
<project xmlns="http://maven.apache.org/DECORATION/1.8.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xsi:schemaLocation="http://maven.apache.org/DECORATION/1.8.0 https://maven.apache.org/xsd/decoration-1.8.0.xsd"
|
||||
name="DHP-Aggregation">
|
||||
<skin>
|
||||
<groupId>org.apache.maven.skins</groupId>
|
||||
<artifactId>maven-fluido-skin</artifactId>
|
||||
<version>1.8</version>
|
||||
</skin>
|
||||
<poweredBy>
|
||||
<logo name="OpenAIRE Research Graph" href="https://graph.openaire.eu/"
|
||||
img="https://graph.openaire.eu/assets/common-assets/logo-large-graph.png"/>
|
||||
</poweredBy>
|
||||
<body>
|
||||
<links>
|
||||
<item name="Code" href="https://code-repo.d4science.org/" />
|
||||
</links>
|
||||
|
||||
<menu ref="modules" />
|
||||
<menu ref="reports"/>
|
||||
</body>
|
||||
</project>
|
||||
@ -0,0 +1,14 @@
|
||||
|
||||
package eu.dnetlib.dhp.application;
|
||||
|
||||
import java.io.*;
|
||||
import java.util.Map;
|
||||
import java.util.Properties;
|
||||
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
|
||||
import com.google.common.collect.Maps;
|
||||
|
||||
public class ApplicationUtils {
|
||||
|
||||
}
|
||||
@ -0,0 +1,412 @@
|
||||
|
||||
package eu.dnetlib.dhp.common;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.*;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.dump.oaf.*;
|
||||
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityInstance;
|
||||
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
|
||||
import eu.dnetlib.dhp.schema.oaf.DataInfo;
|
||||
import eu.dnetlib.dhp.schema.oaf.Field;
|
||||
import eu.dnetlib.dhp.schema.oaf.Journal;
|
||||
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||
|
||||
public class GraphResultMapper implements Serializable {
|
||||
|
||||
public static <E extends eu.dnetlib.dhp.schema.oaf.OafEntity> Result map(
|
||||
E in) {
|
||||
|
||||
CommunityResult out = new CommunityResult();
|
||||
|
||||
eu.dnetlib.dhp.schema.oaf.Result input = (eu.dnetlib.dhp.schema.oaf.Result) in;
|
||||
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> ort = Optional.ofNullable(input.getResulttype());
|
||||
if (ort.isPresent()) {
|
||||
switch (ort.get().getClassid()) {
|
||||
case "publication":
|
||||
Optional<Journal> journal = Optional
|
||||
.ofNullable(((eu.dnetlib.dhp.schema.oaf.Publication) input).getJournal());
|
||||
if (journal.isPresent()) {
|
||||
Journal j = journal.get();
|
||||
Container c = new Container();
|
||||
c.setConferencedate(j.getConferencedate());
|
||||
c.setConferenceplace(j.getConferenceplace());
|
||||
c.setEdition(j.getEdition());
|
||||
c.setEp(j.getEp());
|
||||
c.setIss(j.getIss());
|
||||
c.setIssnLinking(j.getIssnLinking());
|
||||
c.setIssnOnline(j.getIssnOnline());
|
||||
c.setIssnPrinted(j.getIssnPrinted());
|
||||
c.setName(j.getName());
|
||||
c.setSp(j.getSp());
|
||||
c.setVol(j.getVol());
|
||||
out.setContainer(c);
|
||||
out.setType(ModelConstants.PUBLICATION_DEFAULT_RESULTTYPE.getClassname());
|
||||
}
|
||||
break;
|
||||
case "dataset":
|
||||
eu.dnetlib.dhp.schema.oaf.Dataset id = (eu.dnetlib.dhp.schema.oaf.Dataset) input;
|
||||
Optional.ofNullable(id.getSize()).ifPresent(v -> out.setSize(v.getValue()));
|
||||
Optional.ofNullable(id.getVersion()).ifPresent(v -> out.setVersion(v.getValue()));
|
||||
|
||||
out
|
||||
.setGeolocation(
|
||||
Optional
|
||||
.ofNullable(id.getGeolocation())
|
||||
.map(
|
||||
igl -> igl
|
||||
.stream()
|
||||
.filter(Objects::nonNull)
|
||||
.map(gli -> {
|
||||
GeoLocation gl = new GeoLocation();
|
||||
gl.setBox(gli.getBox());
|
||||
gl.setPlace(gli.getPlace());
|
||||
gl.setPoint(gli.getPoint());
|
||||
return gl;
|
||||
})
|
||||
.collect(Collectors.toList()))
|
||||
.orElse(null));
|
||||
|
||||
out.setType(ModelConstants.DATASET_DEFAULT_RESULTTYPE.getClassname());
|
||||
break;
|
||||
case "software":
|
||||
|
||||
eu.dnetlib.dhp.schema.oaf.Software is = (eu.dnetlib.dhp.schema.oaf.Software) input;
|
||||
Optional
|
||||
.ofNullable(is.getCodeRepositoryUrl())
|
||||
.ifPresent(value -> out.setCodeRepositoryUrl(value.getValue()));
|
||||
Optional
|
||||
.ofNullable(is.getDocumentationUrl())
|
||||
.ifPresent(
|
||||
value -> out
|
||||
.setDocumentationUrl(
|
||||
value
|
||||
.stream()
|
||||
.map(v -> v.getValue())
|
||||
.collect(Collectors.toList())));
|
||||
|
||||
Optional
|
||||
.ofNullable(is.getProgrammingLanguage())
|
||||
.ifPresent(value -> out.setProgrammingLanguage(value.getClassid()));
|
||||
|
||||
out.setType(ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE.getClassname());
|
||||
break;
|
||||
case "other":
|
||||
|
||||
eu.dnetlib.dhp.schema.oaf.OtherResearchProduct ir = (eu.dnetlib.dhp.schema.oaf.OtherResearchProduct) input;
|
||||
out
|
||||
.setContactgroup(
|
||||
Optional
|
||||
.ofNullable(ir.getContactgroup())
|
||||
.map(value -> value.stream().map(cg -> cg.getValue()).collect(Collectors.toList()))
|
||||
.orElse(null));
|
||||
|
||||
out
|
||||
.setContactperson(
|
||||
Optional
|
||||
.ofNullable(ir.getContactperson())
|
||||
.map(value -> value.stream().map(cp -> cp.getValue()).collect(Collectors.toList()))
|
||||
.orElse(null));
|
||||
out
|
||||
.setTool(
|
||||
Optional
|
||||
.ofNullable(ir.getTool())
|
||||
.map(value -> value.stream().map(t -> t.getValue()).collect(Collectors.toList()))
|
||||
.orElse(null));
|
||||
|
||||
out.setType(ModelConstants.ORP_DEFAULT_RESULTTYPE.getClassname());
|
||||
|
||||
break;
|
||||
}
|
||||
|
||||
Optional
|
||||
.ofNullable(input.getAuthor())
|
||||
.ifPresent(ats -> out.setAuthor(ats.stream().map(at -> getAuthor(at)).collect(Collectors.toList())));
|
||||
|
||||
// I do not map Access Right UNKNOWN or OTHER
|
||||
|
||||
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> oar = Optional.ofNullable(input.getBestaccessright());
|
||||
if (oar.isPresent()) {
|
||||
if (Constants.accessRightsCoarMap.containsKey(oar.get().getClassid())) {
|
||||
String code = Constants.accessRightsCoarMap.get(oar.get().getClassid());
|
||||
out
|
||||
.setBestaccessright(
|
||||
AccessRight
|
||||
.newInstance(
|
||||
code,
|
||||
Constants.coarCodeLabelMap.get(code),
|
||||
Constants.COAR_ACCESS_RIGHT_SCHEMA));
|
||||
}
|
||||
}
|
||||
|
||||
final List<String> contributorList = new ArrayList<>();
|
||||
Optional
|
||||
.ofNullable(input.getContributor())
|
||||
.ifPresent(value -> value.stream().forEach(c -> contributorList.add(c.getValue())));
|
||||
out.setContributor(contributorList);
|
||||
|
||||
Optional
|
||||
.ofNullable(input.getCountry())
|
||||
.ifPresent(
|
||||
value -> out
|
||||
.setCountry(
|
||||
value
|
||||
.stream()
|
||||
.map(
|
||||
c -> {
|
||||
if (c.getClassid().equals((ModelConstants.UNKNOWN))) {
|
||||
return null;
|
||||
}
|
||||
Country country = new Country();
|
||||
country.setCode(c.getClassid());
|
||||
country.setLabel(c.getClassname());
|
||||
Optional
|
||||
.ofNullable(c.getDataInfo())
|
||||
.ifPresent(
|
||||
provenance -> country
|
||||
.setProvenance(
|
||||
Provenance
|
||||
.newInstance(
|
||||
provenance
|
||||
.getProvenanceaction()
|
||||
.getClassname(),
|
||||
c.getDataInfo().getTrust())));
|
||||
return country;
|
||||
})
|
||||
.filter(Objects::nonNull)
|
||||
.collect(Collectors.toList())));
|
||||
|
||||
final List<String> coverageList = new ArrayList<>();
|
||||
Optional
|
||||
.ofNullable(input.getCoverage())
|
||||
.ifPresent(value -> value.stream().forEach(c -> coverageList.add(c.getValue())));
|
||||
out.setCoverage(coverageList);
|
||||
|
||||
out.setDateofcollection(input.getDateofcollection());
|
||||
|
||||
final List<String> descriptionList = new ArrayList<>();
|
||||
Optional
|
||||
.ofNullable(input.getDescription())
|
||||
.ifPresent(value -> value.forEach(d -> descriptionList.add(d.getValue())));
|
||||
out.setDescription(descriptionList);
|
||||
Optional<Field<String>> oStr = Optional.ofNullable(input.getEmbargoenddate());
|
||||
if (oStr.isPresent()) {
|
||||
out.setEmbargoenddate(oStr.get().getValue());
|
||||
}
|
||||
|
||||
final List<String> formatList = new ArrayList<>();
|
||||
Optional
|
||||
.ofNullable(input.getFormat())
|
||||
.ifPresent(value -> value.stream().forEach(f -> formatList.add(f.getValue())));
|
||||
out.setFormat(formatList);
|
||||
out.setId(input.getId());
|
||||
out.setOriginalId(input.getOriginalId());
|
||||
|
||||
Optional<List<eu.dnetlib.dhp.schema.oaf.Instance>> oInst = Optional
|
||||
.ofNullable(input.getInstance());
|
||||
|
||||
if (oInst.isPresent()) {
|
||||
out
|
||||
.setInstance(
|
||||
oInst.get().stream().map(i -> getInstance(i)).collect(Collectors.toList()));
|
||||
|
||||
}
|
||||
|
||||
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> oL = Optional.ofNullable(input.getLanguage());
|
||||
if (oL.isPresent()) {
|
||||
eu.dnetlib.dhp.schema.oaf.Qualifier language = oL.get();
|
||||
out.setLanguage(Qualifier.newInstance(language.getClassid(), language.getClassname()));
|
||||
}
|
||||
Optional<Long> oLong = Optional.ofNullable(input.getLastupdatetimestamp());
|
||||
if (oLong.isPresent()) {
|
||||
out.setLastupdatetimestamp(oLong.get());
|
||||
}
|
||||
Optional<List<StructuredProperty>> otitle = Optional.ofNullable(input.getTitle());
|
||||
if (otitle.isPresent()) {
|
||||
List<StructuredProperty> iTitle = otitle
|
||||
.get()
|
||||
.stream()
|
||||
.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("main title"))
|
||||
.collect(Collectors.toList());
|
||||
if (iTitle.size() > 0) {
|
||||
out.setMaintitle(iTitle.get(0).getValue());
|
||||
}
|
||||
|
||||
iTitle = otitle
|
||||
.get()
|
||||
.stream()
|
||||
.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("subtitle"))
|
||||
.collect(Collectors.toList());
|
||||
if (iTitle.size() > 0) {
|
||||
out.setSubtitle(iTitle.get(0).getValue());
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
List<ControlledField> pids = new ArrayList<>();
|
||||
Optional
|
||||
.ofNullable(input.getPid())
|
||||
.ifPresent(
|
||||
value -> value
|
||||
.stream()
|
||||
.forEach(
|
||||
p -> pids
|
||||
.add(
|
||||
ControlledField
|
||||
.newInstance(p.getQualifier().getClassid(), p.getValue()))));
|
||||
out.setPid(pids);
|
||||
oStr = Optional.ofNullable(input.getDateofacceptance());
|
||||
if (oStr.isPresent()) {
|
||||
out.setPublicationdate(oStr.get().getValue());
|
||||
}
|
||||
oStr = Optional.ofNullable(input.getPublisher());
|
||||
if (oStr.isPresent()) {
|
||||
out.setPublisher(oStr.get().getValue());
|
||||
}
|
||||
|
||||
List<String> sourceList = new ArrayList<>();
|
||||
Optional
|
||||
.ofNullable(input.getSource())
|
||||
.ifPresent(value -> value.stream().forEach(s -> sourceList.add(s.getValue())));
|
||||
// out.setSource(input.getSource().stream().map(s -> s.getValue()).collect(Collectors.toList()));
|
||||
List<Subject> subjectList = new ArrayList<>();
|
||||
Optional
|
||||
.ofNullable(input.getSubject())
|
||||
.ifPresent(
|
||||
value -> value
|
||||
.forEach(s -> subjectList.add(getSubject(s))));
|
||||
|
||||
out.setSubjects(subjectList);
|
||||
|
||||
out.setType(input.getResulttype().getClassid());
|
||||
}
|
||||
|
||||
out
|
||||
.setCollectedfrom(
|
||||
input
|
||||
.getCollectedfrom()
|
||||
.stream()
|
||||
.map(cf -> KeyValue.newInstance(cf.getKey(), cf.getValue()))
|
||||
.collect(Collectors.toList()));
|
||||
|
||||
return out;
|
||||
|
||||
}
|
||||
|
||||
private static CommunityInstance getInstance(eu.dnetlib.dhp.schema.oaf.Instance i) {
|
||||
CommunityInstance instance = new CommunityInstance();
|
||||
|
||||
setCommonValue(i, instance);
|
||||
|
||||
instance
|
||||
.setCollectedfrom(
|
||||
KeyValue
|
||||
.newInstance(i.getCollectedfrom().getKey(), i.getCollectedfrom().getValue()));
|
||||
|
||||
instance
|
||||
.setHostedby(
|
||||
KeyValue.newInstance(i.getHostedby().getKey(), i.getHostedby().getValue()));
|
||||
|
||||
return instance;
|
||||
|
||||
}
|
||||
|
||||
private static <I extends Instance> void setCommonValue(eu.dnetlib.dhp.schema.oaf.Instance i, I instance) {
|
||||
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> opAr = Optional
|
||||
.ofNullable(i.getAccessright());
|
||||
if (opAr.isPresent()) {
|
||||
if (Constants.accessRightsCoarMap.containsKey(opAr.get().getClassid())) {
|
||||
String code = Constants.accessRightsCoarMap.get(opAr.get().getClassid());
|
||||
instance
|
||||
.setAccessright(
|
||||
AccessRight
|
||||
.newInstance(
|
||||
code,
|
||||
Constants.coarCodeLabelMap.get(code),
|
||||
Constants.COAR_ACCESS_RIGHT_SCHEMA));
|
||||
}
|
||||
}
|
||||
|
||||
Optional
|
||||
.ofNullable(i.getLicense())
|
||||
.ifPresent(value -> instance.setLicense(value.getValue()));
|
||||
Optional
|
||||
.ofNullable(i.getDateofacceptance())
|
||||
.ifPresent(value -> instance.setPublicationdate(value.getValue()));
|
||||
Optional
|
||||
.ofNullable(i.getRefereed())
|
||||
.ifPresent(value -> instance.setRefereed(value.getClassname()));
|
||||
Optional
|
||||
.ofNullable(i.getInstancetype())
|
||||
.ifPresent(value -> instance.setType(value.getClassname()));
|
||||
Optional.ofNullable(i.getUrl()).ifPresent(value -> instance.setUrl(value));
|
||||
|
||||
}
|
||||
|
||||
private static Subject getSubject(StructuredProperty s) {
|
||||
Subject subject = new Subject();
|
||||
subject.setSubject(ControlledField.newInstance(s.getQualifier().getClassid(), s.getValue()));
|
||||
Optional<DataInfo> di = Optional.ofNullable(s.getDataInfo());
|
||||
if (di.isPresent()) {
|
||||
Provenance p = new Provenance();
|
||||
p.setProvenance(di.get().getProvenanceaction().getClassname());
|
||||
p.setTrust(di.get().getTrust());
|
||||
subject.setProvenance(p);
|
||||
}
|
||||
|
||||
return subject;
|
||||
}
|
||||
|
||||
private static Author getAuthor(eu.dnetlib.dhp.schema.oaf.Author oa) {
|
||||
Author a = new Author();
|
||||
a.setFullname(oa.getFullname());
|
||||
a.setName(oa.getName());
|
||||
a.setSurname(oa.getSurname());
|
||||
a.setRank(oa.getRank());
|
||||
|
||||
Optional<List<StructuredProperty>> oPids = Optional
|
||||
.ofNullable(oa.getPid());
|
||||
if (oPids.isPresent()) {
|
||||
Pid pid = getOrcid(oPids.get());
|
||||
if (pid != null) {
|
||||
a.setPid(pid);
|
||||
}
|
||||
}
|
||||
|
||||
return a;
|
||||
}
|
||||
|
||||
private static Pid getOrcid(List<StructuredProperty> p) {
|
||||
for (StructuredProperty pid : p) {
|
||||
if (pid.getQualifier().getClassid().equals(ModelConstants.ORCID)) {
|
||||
Optional<DataInfo> di = Optional.ofNullable(pid.getDataInfo());
|
||||
if (di.isPresent()) {
|
||||
return Pid
|
||||
.newInstance(
|
||||
ControlledField
|
||||
.newInstance(
|
||||
pid.getQualifier().getClassid(),
|
||||
pid.getValue()),
|
||||
Provenance
|
||||
.newInstance(
|
||||
di.get().getProvenanceaction().getClassname(),
|
||||
di.get().getTrust()));
|
||||
} else {
|
||||
return Pid
|
||||
.newInstance(
|
||||
ControlledField
|
||||
.newInstance(
|
||||
pid.getQualifier().getClassid(),
|
||||
pid.getValue())
|
||||
|
||||
);
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,56 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.common.collection;
|
||||
|
||||
import java.io.*;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import com.opencsv.bean.CsvToBeanBuilder;
|
||||
|
||||
public class GetCSV {
|
||||
|
||||
public static final char DEFAULT_DELIMITER = ',';
|
||||
|
||||
private GetCSV() {
|
||||
}
|
||||
|
||||
public static void getCsv(FileSystem fileSystem, BufferedReader reader, String hdfsPath,
|
||||
String modelClass) throws IOException, ClassNotFoundException {
|
||||
getCsv(fileSystem, reader, hdfsPath, modelClass, DEFAULT_DELIMITER);
|
||||
}
|
||||
|
||||
public static void getCsv(FileSystem fileSystem, Reader reader, String hdfsPath,
|
||||
String modelClass, char delimiter) throws IOException, ClassNotFoundException {
|
||||
|
||||
Path hdfsWritePath = new Path(hdfsPath);
|
||||
FSDataOutputStream fsDataOutputStream = null;
|
||||
if (fileSystem.exists(hdfsWritePath)) {
|
||||
fileSystem.delete(hdfsWritePath, false);
|
||||
}
|
||||
fsDataOutputStream = fileSystem.create(hdfsWritePath);
|
||||
|
||||
try (BufferedWriter writer = new BufferedWriter(
|
||||
new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8))) {
|
||||
|
||||
final ObjectMapper mapper = new ObjectMapper();
|
||||
|
||||
@SuppressWarnings("unchecked")
|
||||
final List lines = new CsvToBeanBuilder(reader)
|
||||
.withType(Class.forName(modelClass))
|
||||
.withSeparator(delimiter)
|
||||
.build()
|
||||
.parse();
|
||||
|
||||
for (Object line : lines) {
|
||||
writer.write(mapper.writeValueAsString(line));
|
||||
writer.newLine();
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,73 +0,0 @@
|
||||
package eu.dnetlib.dhp.application
|
||||
|
||||
import scala.io.Source
|
||||
|
||||
/** This is the main Interface SparkApplication
|
||||
* where all the Spark Scala class should inherit
|
||||
*/
|
||||
trait SparkScalaApplication {
|
||||
|
||||
/** This is the path in the classpath of the json
|
||||
* describes all the argument needed to run
|
||||
*/
|
||||
val propertyPath: String
|
||||
|
||||
/** Utility to parse the arguments using the
|
||||
* property json in the classpath identified from
|
||||
* the variable propertyPath
|
||||
*
|
||||
* @param args the list of arguments
|
||||
*/
|
||||
def parseArguments(args: Array[String]): ArgumentApplicationParser = {
|
||||
val parser = new ArgumentApplicationParser(
|
||||
Source.fromInputStream(getClass.getResourceAsStream(propertyPath)).mkString
|
||||
)
|
||||
parser.parseArgument(args)
|
||||
parser
|
||||
}
|
||||
|
||||
/** Here all the spark applications runs this method
|
||||
* where the whole logic of the spark node is defined
|
||||
*/
|
||||
def run(): Unit
|
||||
}
|
||||
|
||||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql.SparkSession
|
||||
import org.slf4j.Logger
|
||||
|
||||
abstract class AbstractScalaApplication(
|
||||
val propertyPath: String,
|
||||
val args: Array[String],
|
||||
log: Logger
|
||||
) extends SparkScalaApplication {
|
||||
|
||||
var parser: ArgumentApplicationParser = null
|
||||
|
||||
var spark: SparkSession = null
|
||||
|
||||
def initialize(): SparkScalaApplication = {
|
||||
parser = parseArguments(args)
|
||||
spark = createSparkSession()
|
||||
this
|
||||
}
|
||||
|
||||
/** Utility for creating a spark session starting from parser
|
||||
*
|
||||
* @return a spark Session
|
||||
*/
|
||||
private def createSparkSession(): SparkSession = {
|
||||
require(parser != null)
|
||||
|
||||
val conf: SparkConf = new SparkConf()
|
||||
val master = parser.get("master")
|
||||
log.info(s"Creating Spark session: Master: $master")
|
||||
SparkSession
|
||||
.builder()
|
||||
.config(conf)
|
||||
.appName(getClass.getSimpleName)
|
||||
.master(master)
|
||||
.getOrCreate()
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,442 +0,0 @@
|
||||
package eu.dnetlib.dhp.sx.graph.scholix
|
||||
|
||||
import eu.dnetlib.dhp.schema.oaf.{Publication, Relation, Result, StructuredProperty}
|
||||
import eu.dnetlib.dhp.schema.sx.scholix._
|
||||
import eu.dnetlib.dhp.schema.sx.summary.{CollectedFromType, SchemeValue, ScholixSummary, Typology}
|
||||
import eu.dnetlib.dhp.utils.DHPUtils
|
||||
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 scala.collection.JavaConverters._
|
||||
import scala.io.Source
|
||||
|
||||
object ScholixUtils extends Serializable {
|
||||
|
||||
val DNET_IDENTIFIER_SCHEMA: String = "DNET Identifier"
|
||||
|
||||
val DATE_RELATION_KEY: String = "RelationDate"
|
||||
|
||||
case class RelationVocabulary(original: String, inverse: String) {}
|
||||
|
||||
case class RelatedEntities(id: String, relatedDataset: Long, relatedPublication: Long) {}
|
||||
|
||||
val relations: Map[String, RelationVocabulary] = {
|
||||
val input = Source
|
||||
.fromInputStream(
|
||||
getClass.getResourceAsStream("/eu/dnetlib/scholexplorer/relation/relations.json")
|
||||
)
|
||||
.mkString
|
||||
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
|
||||
|
||||
lazy val json: json4s.JValue = parse(input)
|
||||
|
||||
json.extract[Map[String, RelationVocabulary]]
|
||||
}
|
||||
|
||||
def extractRelationDate(relation: Relation): String = {
|
||||
|
||||
if (relation.getProperties == null || !relation.getProperties.isEmpty)
|
||||
null
|
||||
else {
|
||||
val date = relation.getProperties.asScala
|
||||
.find(p => DATE_RELATION_KEY.equalsIgnoreCase(p.getKey))
|
||||
.map(p => p.getValue)
|
||||
if (date.isDefined)
|
||||
date.get
|
||||
else
|
||||
null
|
||||
}
|
||||
}
|
||||
|
||||
def extractRelationDate(summary: ScholixSummary): String = {
|
||||
|
||||
if (summary.getDate == null || summary.getDate.isEmpty)
|
||||
null
|
||||
else {
|
||||
summary.getDate.get(0)
|
||||
}
|
||||
}
|
||||
|
||||
def inverseRelationShip(rel: ScholixRelationship): ScholixRelationship = {
|
||||
new ScholixRelationship(rel.getInverse, rel.getSchema, rel.getName)
|
||||
|
||||
}
|
||||
|
||||
def generateScholixResourceFromResult(r: Result): ScholixResource = {
|
||||
generateScholixResourceFromSummary(ScholixUtils.resultToSummary(r))
|
||||
}
|
||||
|
||||
val statsAggregator: Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] =
|
||||
new Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] with Serializable {
|
||||
override def zero: RelatedEntities = null
|
||||
|
||||
override def reduce(b: RelatedEntities, a: (String, String, Long)): RelatedEntities = {
|
||||
val relatedDataset = if ("dataset".equalsIgnoreCase(a._2)) a._3 else 0
|
||||
val relatedPublication = if ("publication".equalsIgnoreCase(a._2)) a._3 else 0
|
||||
|
||||
if (b == null)
|
||||
RelatedEntities(a._1, relatedDataset, relatedPublication)
|
||||
else
|
||||
RelatedEntities(
|
||||
a._1,
|
||||
b.relatedDataset + relatedDataset,
|
||||
b.relatedPublication + relatedPublication
|
||||
)
|
||||
}
|
||||
|
||||
override def merge(b1: RelatedEntities, b2: RelatedEntities): RelatedEntities = {
|
||||
if (b1 != null && b2 != null)
|
||||
RelatedEntities(
|
||||
b1.id,
|
||||
b1.relatedDataset + b2.relatedDataset,
|
||||
b1.relatedPublication + b2.relatedPublication
|
||||
)
|
||||
else if (b1 != null)
|
||||
b1
|
||||
else
|
||||
b2
|
||||
}
|
||||
|
||||
override def finish(reduction: RelatedEntities): RelatedEntities = reduction
|
||||
|
||||
override def bufferEncoder: Encoder[RelatedEntities] = Encoders.bean(classOf[RelatedEntities])
|
||||
|
||||
override def outputEncoder: Encoder[RelatedEntities] = Encoders.bean(classOf[RelatedEntities])
|
||||
}
|
||||
|
||||
val scholixAggregator: Aggregator[(String, Scholix), Scholix, Scholix] =
|
||||
new Aggregator[(String, Scholix), Scholix, Scholix] with Serializable {
|
||||
override def zero: Scholix = null
|
||||
|
||||
def scholix_complete(s: Scholix): Boolean = {
|
||||
if (s == null || s.getIdentifier == null) {
|
||||
false
|
||||
} else if (s.getSource == null || s.getTarget == null) {
|
||||
false
|
||||
} else if (s.getLinkprovider == null || s.getLinkprovider.isEmpty)
|
||||
false
|
||||
else
|
||||
true
|
||||
}
|
||||
|
||||
override def reduce(b: Scholix, a: (String, Scholix)): Scholix = {
|
||||
if (scholix_complete(b)) b else a._2
|
||||
}
|
||||
|
||||
override def merge(b1: Scholix, b2: Scholix): Scholix = {
|
||||
if (scholix_complete(b1)) b1 else b2
|
||||
}
|
||||
|
||||
override def finish(reduction: Scholix): Scholix = reduction
|
||||
|
||||
override def bufferEncoder: Encoder[Scholix] = Encoders.kryo[Scholix]
|
||||
|
||||
override def outputEncoder: Encoder[Scholix] = Encoders.kryo[Scholix]
|
||||
}
|
||||
|
||||
def createInverseScholixRelation(scholix: Scholix): Scholix = {
|
||||
val s = new Scholix
|
||||
s.setPublicationDate(scholix.getPublicationDate)
|
||||
s.setPublisher(scholix.getPublisher)
|
||||
s.setLinkprovider(scholix.getLinkprovider)
|
||||
s.setRelationship(inverseRelationShip(scholix.getRelationship))
|
||||
s.setSource(scholix.getTarget)
|
||||
s.setTarget(scholix.getSource)
|
||||
s.setIdentifier(
|
||||
DHPUtils.md5(
|
||||
s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
|
||||
)
|
||||
)
|
||||
s
|
||||
|
||||
}
|
||||
|
||||
def extractCollectedFrom(summary: ScholixResource): List[ScholixEntityId] = {
|
||||
if (summary.getCollectedFrom != null && !summary.getCollectedFrom.isEmpty) {
|
||||
val l: List[ScholixEntityId] = summary.getCollectedFrom.asScala.map { d =>
|
||||
new ScholixEntityId(d.getProvider.getName, d.getProvider.getIdentifiers)
|
||||
}(collection.breakOut)
|
||||
l
|
||||
} else List()
|
||||
}
|
||||
|
||||
def extractCollectedFrom(summary: ScholixSummary): List[ScholixEntityId] = {
|
||||
if (summary.getDatasources != null && !summary.getDatasources.isEmpty) {
|
||||
val l: List[ScholixEntityId] = summary.getDatasources.asScala.map { d =>
|
||||
new ScholixEntityId(
|
||||
d.getDatasourceName,
|
||||
List(new ScholixIdentifier(d.getDatasourceId, "DNET Identifier", null)).asJava
|
||||
)
|
||||
}(collection.breakOut)
|
||||
l
|
||||
} else List()
|
||||
}
|
||||
|
||||
def extractCollectedFrom(relation: Relation): List[ScholixEntityId] = {
|
||||
if (relation.getCollectedfrom != null && !relation.getCollectedfrom.isEmpty) {
|
||||
|
||||
val l: List[ScholixEntityId] = relation.getCollectedfrom.asScala.map { c =>
|
||||
new ScholixEntityId(
|
||||
c.getValue,
|
||||
List(new ScholixIdentifier(c.getKey, DNET_IDENTIFIER_SCHEMA, null)).asJava
|
||||
)
|
||||
}.toList
|
||||
l
|
||||
} else List()
|
||||
}
|
||||
|
||||
def generateCompleteScholix(scholix: Scholix, target: ScholixSummary): Scholix = {
|
||||
val s = new Scholix
|
||||
s.setPublicationDate(scholix.getPublicationDate)
|
||||
s.setPublisher(scholix.getPublisher)
|
||||
s.setLinkprovider(scholix.getLinkprovider)
|
||||
s.setRelationship(scholix.getRelationship)
|
||||
s.setSource(scholix.getSource)
|
||||
s.setTarget(generateScholixResourceFromSummary(target))
|
||||
s.setIdentifier(
|
||||
DHPUtils.md5(
|
||||
s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
|
||||
)
|
||||
)
|
||||
s
|
||||
}
|
||||
|
||||
def generateCompleteScholix(scholix: Scholix, target: ScholixResource): Scholix = {
|
||||
val s = new Scholix
|
||||
s.setPublicationDate(scholix.getPublicationDate)
|
||||
s.setPublisher(scholix.getPublisher)
|
||||
s.setLinkprovider(scholix.getLinkprovider)
|
||||
s.setRelationship(scholix.getRelationship)
|
||||
s.setSource(scholix.getSource)
|
||||
s.setTarget(target)
|
||||
s.setIdentifier(
|
||||
DHPUtils.md5(
|
||||
s"${s.getSource.getIdentifier}::${s.getRelationship.getName}::${s.getTarget.getIdentifier}"
|
||||
)
|
||||
)
|
||||
s
|
||||
}
|
||||
|
||||
def generateScholixResourceFromSummary(summaryObject: ScholixSummary): ScholixResource = {
|
||||
val r = new ScholixResource
|
||||
r.setIdentifier(summaryObject.getLocalIdentifier)
|
||||
r.setDnetIdentifier(summaryObject.getId)
|
||||
|
||||
r.setObjectType(summaryObject.getTypology.toString)
|
||||
r.setObjectSubType(summaryObject.getSubType)
|
||||
|
||||
if (summaryObject.getTitle != null && !summaryObject.getTitle.isEmpty)
|
||||
r.setTitle(summaryObject.getTitle.get(0))
|
||||
|
||||
if (summaryObject.getAuthor != null && !summaryObject.getAuthor.isEmpty) {
|
||||
val l: List[ScholixEntityId] =
|
||||
summaryObject.getAuthor.asScala.map(a => new ScholixEntityId(a, null)).toList
|
||||
if (l.nonEmpty)
|
||||
r.setCreator(l.asJava)
|
||||
}
|
||||
|
||||
if (summaryObject.getDate != null && !summaryObject.getDate.isEmpty)
|
||||
r.setPublicationDate(summaryObject.getDate.get(0))
|
||||
if (summaryObject.getPublisher != null && !summaryObject.getPublisher.isEmpty) {
|
||||
val plist: List[ScholixEntityId] =
|
||||
summaryObject.getPublisher.asScala.map(p => new ScholixEntityId(p, null)).toList
|
||||
|
||||
if (plist.nonEmpty)
|
||||
r.setPublisher(plist.asJava)
|
||||
}
|
||||
|
||||
if (summaryObject.getDatasources != null && !summaryObject.getDatasources.isEmpty) {
|
||||
|
||||
val l: List[ScholixCollectedFrom] = summaryObject.getDatasources.asScala
|
||||
.map(c =>
|
||||
new ScholixCollectedFrom(
|
||||
new ScholixEntityId(
|
||||
c.getDatasourceName,
|
||||
List(new ScholixIdentifier(c.getDatasourceId, DNET_IDENTIFIER_SCHEMA, null)).asJava
|
||||
),
|
||||
"collected",
|
||||
"complete"
|
||||
)
|
||||
)
|
||||
.toList
|
||||
|
||||
if (l.nonEmpty)
|
||||
r.setCollectedFrom(l.asJava)
|
||||
|
||||
}
|
||||
r
|
||||
}
|
||||
|
||||
def scholixFromSource(relation: Relation, source: ScholixResource): Scholix = {
|
||||
if (relation == null || source == null)
|
||||
return null
|
||||
val s = new Scholix
|
||||
var l: List[ScholixEntityId] = extractCollectedFrom(relation)
|
||||
if (l.isEmpty)
|
||||
l = extractCollectedFrom(source)
|
||||
if (l.isEmpty)
|
||||
return null
|
||||
s.setLinkprovider(l.asJava)
|
||||
var d = extractRelationDate(relation)
|
||||
if (d == null)
|
||||
d = source.getPublicationDate
|
||||
|
||||
s.setPublicationDate(d)
|
||||
|
||||
if (source.getPublisher != null && !source.getPublisher.isEmpty) {
|
||||
s.setPublisher(source.getPublisher)
|
||||
}
|
||||
|
||||
val semanticRelation = relations.getOrElse(relation.getRelClass.toLowerCase, null)
|
||||
if (semanticRelation == null)
|
||||
return null
|
||||
s.setRelationship(
|
||||
new ScholixRelationship(semanticRelation.original, "datacite", semanticRelation.inverse)
|
||||
)
|
||||
s.setSource(source)
|
||||
|
||||
s
|
||||
}
|
||||
|
||||
def scholixFromSource(relation: Relation, source: ScholixSummary): Scholix = {
|
||||
|
||||
if (relation == null || source == null)
|
||||
return null
|
||||
|
||||
val s = new Scholix
|
||||
|
||||
var l: List[ScholixEntityId] = extractCollectedFrom(relation)
|
||||
if (l.isEmpty)
|
||||
l = extractCollectedFrom(source)
|
||||
if (l.isEmpty)
|
||||
return null
|
||||
|
||||
s.setLinkprovider(l.asJava)
|
||||
|
||||
var d = extractRelationDate(relation)
|
||||
if (d == null)
|
||||
d = extractRelationDate(source)
|
||||
|
||||
s.setPublicationDate(d)
|
||||
|
||||
if (source.getPublisher != null && !source.getPublisher.isEmpty) {
|
||||
val l: List[ScholixEntityId] = source.getPublisher.asScala
|
||||
.map { p =>
|
||||
new ScholixEntityId(p, null)
|
||||
}(collection.breakOut)
|
||||
|
||||
if (l.nonEmpty)
|
||||
s.setPublisher(l.asJava)
|
||||
}
|
||||
|
||||
val semanticRelation = relations.getOrElse(relation.getRelClass.toLowerCase, null)
|
||||
if (semanticRelation == null)
|
||||
return null
|
||||
s.setRelationship(
|
||||
new ScholixRelationship(semanticRelation.original, "datacite", semanticRelation.inverse)
|
||||
)
|
||||
s.setSource(generateScholixResourceFromSummary(source))
|
||||
|
||||
s
|
||||
}
|
||||
|
||||
def findURLForPID(
|
||||
pidValue: List[StructuredProperty],
|
||||
urls: List[String]
|
||||
): List[(StructuredProperty, String)] = {
|
||||
pidValue.map { p =>
|
||||
val pv = p.getValue
|
||||
|
||||
val r = urls.find(u => u.toLowerCase.contains(pv.toLowerCase))
|
||||
(p, r.orNull)
|
||||
}
|
||||
}
|
||||
|
||||
def extractTypedIdentifierFromInstance(r: Result): List[ScholixIdentifier] = {
|
||||
if (r.getInstance() == null || r.getInstance().isEmpty)
|
||||
return List()
|
||||
r.getInstance()
|
||||
.asScala
|
||||
.filter(i => i.getUrl != null && !i.getUrl.isEmpty)
|
||||
.filter(i => i.getPid != null && i.getUrl != null)
|
||||
.flatMap(i => findURLForPID(i.getPid.asScala.toList, i.getUrl.asScala.toList))
|
||||
.map(i => new ScholixIdentifier(i._1.getValue, i._1.getQualifier.getClassid, i._2))
|
||||
.distinct
|
||||
.toList
|
||||
}
|
||||
|
||||
def resultToSummary(r: Result): ScholixSummary = {
|
||||
val s = new ScholixSummary
|
||||
s.setId(r.getId)
|
||||
if (r.getPid == null || r.getPid.isEmpty)
|
||||
return null
|
||||
|
||||
val persistentIdentifiers: List[ScholixIdentifier] = extractTypedIdentifierFromInstance(r)
|
||||
if (persistentIdentifiers.isEmpty)
|
||||
return null
|
||||
s.setLocalIdentifier(persistentIdentifiers.asJava)
|
||||
if (r.isInstanceOf[Publication])
|
||||
s.setTypology(Typology.publication)
|
||||
else
|
||||
s.setTypology(Typology.dataset)
|
||||
|
||||
s.setSubType(r.getInstance().get(0).getInstancetype.getClassname)
|
||||
|
||||
if (r.getTitle != null && r.getTitle.asScala.nonEmpty) {
|
||||
val titles: List[String] = r.getTitle.asScala.map(t => t.getValue).toList
|
||||
if (titles.nonEmpty)
|
||||
s.setTitle(titles.asJava)
|
||||
else
|
||||
return null
|
||||
}
|
||||
|
||||
if (r.getAuthor != null && !r.getAuthor.isEmpty) {
|
||||
val authors: List[String] = r.getAuthor.asScala.map(a => a.getFullname).toList
|
||||
if (authors.nonEmpty)
|
||||
s.setAuthor(authors.asJava)
|
||||
}
|
||||
if (r.getInstance() != null) {
|
||||
val dt: List[String] = r
|
||||
.getInstance()
|
||||
.asScala
|
||||
.filter(i => i.getDateofacceptance != null)
|
||||
.map(i => i.getDateofacceptance.getValue)
|
||||
.toList
|
||||
if (dt.nonEmpty)
|
||||
s.setDate(dt.distinct.asJava)
|
||||
}
|
||||
if (r.getDescription != null && !r.getDescription.isEmpty) {
|
||||
val d = r.getDescription.asScala.find(f => f != null && f.getValue != null)
|
||||
if (d.isDefined)
|
||||
s.setDescription(d.get.getValue)
|
||||
}
|
||||
|
||||
if (r.getSubject != null && !r.getSubject.isEmpty) {
|
||||
val subjects: List[SchemeValue] = r.getSubject.asScala
|
||||
.map(s => new SchemeValue(s.getQualifier.getClassname, s.getValue))
|
||||
.toList
|
||||
if (subjects.nonEmpty)
|
||||
s.setSubject(subjects.asJava)
|
||||
}
|
||||
|
||||
if (r.getPublisher != null)
|
||||
s.setPublisher(List(r.getPublisher.getValue).asJava)
|
||||
|
||||
if (r.getCollectedfrom != null && !r.getCollectedfrom.isEmpty) {
|
||||
val cf: List[CollectedFromType] = r.getCollectedfrom.asScala
|
||||
.map(c => new CollectedFromType(c.getValue, c.getKey, "complete"))
|
||||
.toList
|
||||
if (cf.nonEmpty)
|
||||
s.setDatasources(cf.distinct.asJava)
|
||||
}
|
||||
|
||||
s.setRelatedDatasets(0)
|
||||
s.setRelatedPublications(0)
|
||||
s.setRelatedUnknown(0)
|
||||
|
||||
s
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,92 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager;
|
||||
|
||||
import java.util.Optional;
|
||||
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
|
||||
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.StructuredProperty;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
||||
|
||||
public class Constants {
|
||||
|
||||
public static final String DOI = "doi";
|
||||
public static final String DOI_CLASSNAME = "Digital Object Identifier";
|
||||
|
||||
public static final String DEFAULT_DELIMITER = ",";
|
||||
|
||||
public static final String UPDATE_DATA_INFO_TYPE = "update";
|
||||
public static final String UPDATE_SUBJECT_FOS_CLASS_ID = "subject:fos";
|
||||
public static final String UPDATE_CLASS_NAME = "Inferred by OpenAIRE";
|
||||
public static final String UPDATE_MEASURE_BIP_CLASS_ID = "measure:bip";
|
||||
public static final String UPDATE_SUBJECT_SDG_CLASS_ID = "subject:sdg";
|
||||
|
||||
public static final String FOS_CLASS_ID = "FOS";
|
||||
public static final String FOS_CLASS_NAME = "Fields of Science and Technology classification";
|
||||
|
||||
public static final String SDG_CLASS_ID = "SDG";
|
||||
public static final String SDG_CLASS_NAME = "Sustainable Development Goals";
|
||||
|
||||
public static final String NULL = "NULL";
|
||||
|
||||
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
private Constants() {
|
||||
}
|
||||
|
||||
public static Boolean isSparkSessionManaged(ArgumentApplicationParser parser) {
|
||||
return Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
}
|
||||
|
||||
public static <R> Dataset<R> readPath(
|
||||
SparkSession spark, String inputPath, Class<R> clazz) {
|
||||
return spark
|
||||
.read()
|
||||
.textFile(inputPath)
|
||||
.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
|
||||
}
|
||||
|
||||
public static StructuredProperty getSubject(String sbj, String classid, String classname,
|
||||
String diqualifierclassid) {
|
||||
if (sbj.equals(NULL))
|
||||
return null;
|
||||
StructuredProperty sp = new StructuredProperty();
|
||||
sp.setValue(sbj);
|
||||
sp
|
||||
.setQualifier(
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
classid,
|
||||
classname,
|
||||
ModelConstants.DNET_SUBJECT_TYPOLOGIES,
|
||||
ModelConstants.DNET_SUBJECT_TYPOLOGIES));
|
||||
sp
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false,
|
||||
UPDATE_DATA_INFO_TYPE,
|
||||
true,
|
||||
false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
diqualifierclassid,
|
||||
UPDATE_CLASS_NAME,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
""));
|
||||
|
||||
return sp;
|
||||
|
||||
}
|
||||
}
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.bipmodel;
|
||||
package eu.dnetlib.dhp.actionmanager.bipfinder;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.ArrayList;
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.bipmodel;
|
||||
package eu.dnetlib.dhp.actionmanager.bipfinder;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.List;
|
||||
@ -0,0 +1,84 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.bipfinder;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
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.JavaSparkContext;
|
||||
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.common.HdfsSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
|
||||
/**
|
||||
* Just collects all the atomic actions produced for the different results and saves them in
|
||||
* outputpath for the ActionSet
|
||||
*/
|
||||
public class CollectAndSave implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CollectAndSave.class);
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static <I extends Result> void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
CollectAndSave.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/bipfinder/input_actionset_parameter.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("inputPath");
|
||||
log.info("inputPath {}: ", inputPath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}: ", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
removeOutputDir(spark, outputPath);
|
||||
collectAndSave(spark, inputPath, outputPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static void collectAndSave(SparkSession spark, String inputPath, String outputPath) {
|
||||
JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
sc
|
||||
.sequenceFile(inputPath + "/publication", Text.class, Text.class)
|
||||
.union(sc.sequenceFile(inputPath + "/dataset", Text.class, Text.class))
|
||||
.union(sc.sequenceFile(inputPath + "/otherresearchproduct", Text.class, Text.class))
|
||||
.union(sc.sequenceFile(inputPath + "/software", Text.class, Text.class))
|
||||
.saveAsHadoopFile(outputPath, Text.class, Text.class, SequenceFileOutputFormat.class);
|
||||
}
|
||||
|
||||
private static void removeOutputDir(SparkSession spark, String path) {
|
||||
HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.bipmodel;
|
||||
package eu.dnetlib.dhp.actionmanager.bipfinder;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
@ -0,0 +1,28 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.bipfinder;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
/**
|
||||
* Subset of the information of the generic results that are needed to create the atomic action
|
||||
*/
|
||||
public class PreparedResult implements Serializable {
|
||||
private String id; // openaire id
|
||||
private String value; // doi
|
||||
|
||||
public String getId() {
|
||||
return id;
|
||||
}
|
||||
|
||||
public void setId(String id) {
|
||||
this.id = id;
|
||||
}
|
||||
|
||||
public String getValue() {
|
||||
return value;
|
||||
}
|
||||
|
||||
public void setValue(String value) {
|
||||
this.value = value;
|
||||
}
|
||||
}
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.bipmodel;
|
||||
package eu.dnetlib.dhp.actionmanager.bipfinder;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.List;
|
||||
@ -1,91 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
|
||||
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.DEFAULT_DELIMITER;
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.isSparkSessionManaged;
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.Optional;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.*;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
|
||||
public class GetFOSSparkJob implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(GetFOSSparkJob.class);
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
GetFOSSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/get_input_parameters.json"));
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
// the path where the original fos csv file is stored
|
||||
final String sourcePath = parser.get("sourcePath");
|
||||
log.info("sourcePath {}", sourcePath);
|
||||
|
||||
// the path where to put the file as json
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}", outputPath);
|
||||
|
||||
final String delimiter = Optional
|
||||
.ofNullable(parser.get("delimiter"))
|
||||
.orElse(DEFAULT_DELIMITER);
|
||||
|
||||
SparkConf sconf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
sconf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
getFOS(
|
||||
spark,
|
||||
sourcePath,
|
||||
outputPath,
|
||||
delimiter);
|
||||
});
|
||||
}
|
||||
|
||||
private static void getFOS(SparkSession spark, String sourcePath, String outputPath, String delimiter) {
|
||||
Dataset<Row> fosData = spark
|
||||
.read()
|
||||
.format("csv")
|
||||
.option("sep", delimiter)
|
||||
.option("inferSchema", "true")
|
||||
.option("header", "true")
|
||||
.option("quotes", "\"")
|
||||
.load(sourcePath);
|
||||
|
||||
fosData.map((MapFunction<Row, FOSDataModel>) r -> {
|
||||
FOSDataModel fosDataModel = new FOSDataModel();
|
||||
fosDataModel.setDoi(r.getString(0).toLowerCase());
|
||||
fosDataModel.setLevel1(r.getString(1));
|
||||
fosDataModel.setLevel2(r.getString(2));
|
||||
fosDataModel.setLevel3(r.getString(3));
|
||||
return fosDataModel;
|
||||
}, Encoders.bean(FOSDataModel.class))
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.json(outputPath);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,91 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
|
||||
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.DEFAULT_DELIMITER;
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.isSparkSessionManaged;
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.Optional;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.FilterFunction;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.*;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.SDGDataModel;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
|
||||
public class GetSDGSparkJob implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(GetSDGSparkJob.class);
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
GetSDGSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/get_input_parameters.json"));
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
// the path where the original fos csv file is stored
|
||||
final String sourcePath = parser.get("sourcePath");
|
||||
log.info("sourcePath {}", sourcePath);
|
||||
|
||||
// the path where to put the file as json
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}", outputPath);
|
||||
|
||||
final String delimiter = Optional
|
||||
.ofNullable(parser.get("delimiter"))
|
||||
.orElse(DEFAULT_DELIMITER);
|
||||
|
||||
SparkConf sconf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
sconf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
getSDG(
|
||||
spark,
|
||||
sourcePath,
|
||||
outputPath,
|
||||
delimiter);
|
||||
});
|
||||
}
|
||||
|
||||
private static void getSDG(SparkSession spark, String sourcePath, String outputPath, String delimiter) {
|
||||
Dataset<Row> sdgData = spark
|
||||
.read()
|
||||
.format("csv")
|
||||
.option("sep", delimiter)
|
||||
.option("inferSchema", "true")
|
||||
.option("header", "true")
|
||||
.option("quotes", "\"")
|
||||
.load(sourcePath);
|
||||
|
||||
sdgData.map((MapFunction<Row, SDGDataModel>) r -> {
|
||||
SDGDataModel sdgDataModel = new SDGDataModel();
|
||||
sdgDataModel.setDoi(r.getString(0).toLowerCase());
|
||||
sdgDataModel.setSbj(r.getString(1));
|
||||
|
||||
return sdgDataModel;
|
||||
}, Encoders.bean(SDGDataModel.class))
|
||||
.filter((FilterFunction<SDGDataModel>) sdg -> sdg.getSbj() != null)
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.json(outputPath);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,178 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
|
||||
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.*;
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.UPDATE_CLASS_NAME;
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
import java.util.Optional;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
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.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.actionmanager.bipmodel.BipDeserialize;
|
||||
import eu.dnetlib.dhp.actionmanager.bipmodel.BipScore;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Instance;
|
||||
import eu.dnetlib.dhp.schema.oaf.KeyValue;
|
||||
import eu.dnetlib.dhp.schema.oaf.Measure;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||
|
||||
public class PrepareBipFinder implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(PrepareBipFinder.class);
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
PrepareBipFinder.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_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 sourcePath = parser.get("sourcePath");
|
||||
log.info("sourcePath {}: ", sourcePath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}: ", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
|
||||
prepareResults(spark, sourcePath, outputPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static void prepareResults(SparkSession spark, String inputPath, String outputPath) {
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<BipDeserialize> bipDeserializeJavaRDD = sc
|
||||
.textFile(inputPath)
|
||||
.map(item -> OBJECT_MAPPER.readValue(item, BipDeserialize.class));
|
||||
|
||||
spark
|
||||
.createDataset(bipDeserializeJavaRDD.flatMap(entry -> entry.keySet().stream().map(key -> {
|
||||
BipScore bs = new BipScore();
|
||||
bs.setId(key);
|
||||
bs.setScoreList(entry.get(key));
|
||||
|
||||
return bs;
|
||||
}).collect(Collectors.toList()).iterator()).rdd(), Encoders.bean(BipScore.class))
|
||||
.map((MapFunction<BipScore, Result>) v -> {
|
||||
Result r = new Result();
|
||||
final String cleanedPid = CleaningFunctions.normalizePidValue(DOI, v.getId());
|
||||
|
||||
r.setId(DHPUtils.generateUnresolvedIdentifier(v.getId(), DOI));
|
||||
Instance inst = new Instance();
|
||||
inst.setMeasures(getMeasure(v));
|
||||
|
||||
inst
|
||||
.setPid(
|
||||
Arrays
|
||||
.asList(
|
||||
OafMapperUtils
|
||||
.structuredProperty(
|
||||
cleanedPid,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
DOI, DOI_CLASSNAME,
|
||||
ModelConstants.DNET_PID_TYPES,
|
||||
ModelConstants.DNET_PID_TYPES),
|
||||
null)));
|
||||
r.setInstance(Arrays.asList(inst));
|
||||
r
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, true,
|
||||
false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
ModelConstants.PROVENANCE_ENRICH,
|
||||
null,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
null));
|
||||
return r;
|
||||
}, Encoders.bean(Result.class))
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath + "/bip");
|
||||
}
|
||||
|
||||
private static List<Measure> getMeasure(BipScore value) {
|
||||
return value
|
||||
.getScoreList()
|
||||
.stream()
|
||||
.map(score -> {
|
||||
Measure m = new Measure();
|
||||
m.setId(score.getId());
|
||||
m
|
||||
.setUnit(
|
||||
score
|
||||
.getUnit()
|
||||
.stream()
|
||||
.map(unit -> {
|
||||
KeyValue kv = new KeyValue();
|
||||
kv.setValue(unit.getValue());
|
||||
kv.setKey(unit.getKey());
|
||||
kv
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false,
|
||||
UPDATE_DATA_INFO_TYPE,
|
||||
true,
|
||||
false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
UPDATE_MEASURE_BIP_CLASS_ID,
|
||||
UPDATE_CLASS_NAME,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
""));
|
||||
return kv;
|
||||
})
|
||||
.collect(Collectors.toList()));
|
||||
return m;
|
||||
})
|
||||
.collect(Collectors.toList());
|
||||
}
|
||||
}
|
||||
@ -1,99 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
|
||||
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.*;
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.*;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.api.java.function.MapGroupsFunction;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
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 eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||
|
||||
public class PrepareFOSSparkJob implements Serializable {
|
||||
private static final Logger log = LoggerFactory.getLogger(PrepareFOSSparkJob.class);
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
PrepareFOSSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
String sourcePath = parser.get("sourcePath");
|
||||
log.info("sourcePath: {}", sourcePath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
distributeFOSdois(
|
||||
spark,
|
||||
sourcePath,
|
||||
|
||||
outputPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
|
||||
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
|
||||
|
||||
fosDataset
|
||||
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
|
||||
.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
|
||||
Result r = new Result();
|
||||
FOSDataModel first = it.next();
|
||||
r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
|
||||
HashSet<String> level1 = new HashSet<>();
|
||||
HashSet<String> level2 = new HashSet<>();
|
||||
HashSet<String> level3 = new HashSet<>();
|
||||
addLevels(level1, level2, level3, first);
|
||||
it.forEachRemaining(v -> addLevels(level1, level2, level3, v));
|
||||
List<StructuredProperty> sbjs = new ArrayList<>();
|
||||
level1.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
|
||||
level2.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
|
||||
level3.forEach(l -> sbjs.add(getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
|
||||
r.setSubject(sbjs);
|
||||
return r;
|
||||
}, Encoders.bean(Result.class))
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath + "/fos");
|
||||
}
|
||||
|
||||
private static void addLevels(HashSet<String> level1, HashSet<String> level2, HashSet<String> level3,
|
||||
FOSDataModel first) {
|
||||
level1.add(first.getLevel1());
|
||||
level2.add(first.getLevel2());
|
||||
level3.add(first.getLevel3());
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,89 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
|
||||
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.*;
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.api.java.function.MapGroupsFunction;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
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 eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.SDGDataModel;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||
|
||||
public class PrepareSDGSparkJob implements Serializable {
|
||||
private static final Logger log = LoggerFactory.getLogger(PrepareSDGSparkJob.class);
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
PrepareSDGSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
String sourcePath = parser.get("sourcePath");
|
||||
log.info("sourcePath: {}", sourcePath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
doPrepare(
|
||||
spark,
|
||||
sourcePath,
|
||||
|
||||
outputPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static void doPrepare(SparkSession spark, String sourcePath, String outputPath) {
|
||||
Dataset<SDGDataModel> sdgDataset = readPath(spark, sourcePath, SDGDataModel.class);
|
||||
|
||||
sdgDataset
|
||||
.groupByKey((MapFunction<SDGDataModel, String>) r -> r.getDoi().toLowerCase(), Encoders.STRING())
|
||||
.mapGroups((MapGroupsFunction<String, SDGDataModel, Result>) (k, it) -> {
|
||||
Result r = new Result();
|
||||
r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
|
||||
SDGDataModel first = it.next();
|
||||
List<StructuredProperty> sbjs = new ArrayList<>();
|
||||
sbjs.add(getSubject(first.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID));
|
||||
it
|
||||
.forEachRemaining(
|
||||
s -> sbjs
|
||||
.add(getSubject(s.getSbj(), SDG_CLASS_ID, SDG_CLASS_NAME, UPDATE_SUBJECT_SDG_CLASS_ID)));
|
||||
r.setSubject(sbjs);
|
||||
return r;
|
||||
}, Encoders.bean(Result.class))
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath + "/sdg");
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,79 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
|
||||
|
||||
import static eu.dnetlib.dhp.actionmanager.Constants.*;
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.api.java.function.MapGroupsFunction;
|
||||
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 eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
|
||||
public class SparkSaveUnresolved implements Serializable {
|
||||
private static final Logger log = LoggerFactory.getLogger(SparkSaveUnresolved.class);
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
PrepareFOSSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/produce_unresolved_parameters.json"));
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
String sourcePath = parser.get("sourcePath");
|
||||
log.info("sourcePath: {}", sourcePath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
saveUnresolved(
|
||||
spark,
|
||||
sourcePath,
|
||||
|
||||
outputPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static void saveUnresolved(SparkSession spark, String sourcePath, String outputPath) {
|
||||
|
||||
spark
|
||||
.read()
|
||||
.textFile(sourcePath + "/*")
|
||||
.map(
|
||||
(MapFunction<String, Result>) l -> OBJECT_MAPPER.readValue(l, Result.class),
|
||||
Encoders.bean(Result.class))
|
||||
.groupByKey((MapFunction<Result, String>) Result::getId, Encoders.STRING())
|
||||
.mapGroups((MapGroupsFunction<String, Result, Result>) (k, it) -> {
|
||||
Result ret = it.next();
|
||||
it.forEachRemaining(r -> ret.mergeFrom(r));
|
||||
return ret;
|
||||
}, Encoders.bean(Result.class))
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath);
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,71 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import com.opencsv.bean.CsvBindByPosition;
|
||||
|
||||
public class FOSDataModel implements Serializable {
|
||||
@CsvBindByPosition(position = 0)
|
||||
// @CsvBindByName(column = "doi")
|
||||
private String doi;
|
||||
|
||||
@CsvBindByPosition(position = 1)
|
||||
// @CsvBindByName(column = "level1")
|
||||
private String level1;
|
||||
|
||||
@CsvBindByPosition(position = 2)
|
||||
// @CsvBindByName(column = "level2")
|
||||
private String level2;
|
||||
|
||||
@CsvBindByPosition(position = 3)
|
||||
// @CsvBindByName(column = "level3")
|
||||
private String level3;
|
||||
|
||||
public FOSDataModel() {
|
||||
|
||||
}
|
||||
|
||||
public FOSDataModel(String doi, String level1, String level2, String level3) {
|
||||
this.doi = doi;
|
||||
this.level1 = level1;
|
||||
this.level2 = level2;
|
||||
this.level3 = level3;
|
||||
}
|
||||
|
||||
public static FOSDataModel newInstance(String d, String level1, String level2, String level3) {
|
||||
return new FOSDataModel(d, level1, level2, level3);
|
||||
}
|
||||
|
||||
public String getDoi() {
|
||||
return doi;
|
||||
}
|
||||
|
||||
public void setDoi(String doi) {
|
||||
this.doi = doi;
|
||||
}
|
||||
|
||||
public String getLevel1() {
|
||||
return level1;
|
||||
}
|
||||
|
||||
public void setLevel1(String level1) {
|
||||
this.level1 = level1;
|
||||
}
|
||||
|
||||
public String getLevel2() {
|
||||
return level2;
|
||||
}
|
||||
|
||||
public void setLevel2(String level2) {
|
||||
this.level2 = level2;
|
||||
}
|
||||
|
||||
public String getLevel3() {
|
||||
return level3;
|
||||
}
|
||||
|
||||
public void setLevel3(String level3) {
|
||||
this.level3 = level3;
|
||||
}
|
||||
}
|
||||
@ -1,47 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import com.opencsv.bean.CsvBindByPosition;
|
||||
|
||||
public class SDGDataModel implements Serializable {
|
||||
|
||||
@CsvBindByPosition(position = 0)
|
||||
// @CsvBindByName(column = "doi")
|
||||
private String doi;
|
||||
|
||||
@CsvBindByPosition(position = 1)
|
||||
// @CsvBindByName(column = "sdg")
|
||||
private String sbj;
|
||||
|
||||
public SDGDataModel() {
|
||||
|
||||
}
|
||||
|
||||
public SDGDataModel(String doi, String sbj) {
|
||||
this.doi = doi;
|
||||
this.sbj = sbj;
|
||||
|
||||
}
|
||||
|
||||
public static SDGDataModel newInstance(String d, String sbj) {
|
||||
return new SDGDataModel(d, sbj);
|
||||
}
|
||||
|
||||
public String getDoi() {
|
||||
return doi;
|
||||
}
|
||||
|
||||
public void setDoi(String doi) {
|
||||
this.doi = doi;
|
||||
}
|
||||
|
||||
public String getSbj() {
|
||||
return sbj;
|
||||
}
|
||||
|
||||
public void setSbj(String sbj) {
|
||||
this.sbj = sbj;
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,89 @@
|
||||
package eu.dnetlib.dhp.actionmanager.datacite
|
||||
|
||||
import org.apache.commons.io.IOUtils
|
||||
import org.apache.http.client.config.RequestConfig
|
||||
import org.apache.http.client.methods.{HttpGet, HttpPost, HttpRequestBase, HttpUriRequest}
|
||||
import org.apache.http.entity.StringEntity
|
||||
import org.apache.http.impl.client.{HttpClientBuilder, HttpClients}
|
||||
|
||||
import java.io.IOException
|
||||
|
||||
abstract class AbstractRestClient extends Iterator[String]{
|
||||
|
||||
var buffer: List[String] = List()
|
||||
var current_index:Int = 0
|
||||
|
||||
var scroll_value: Option[String] = None
|
||||
|
||||
var complete:Boolean = false
|
||||
|
||||
|
||||
def extractInfo(input: String): Unit
|
||||
|
||||
protected def getBufferData(): Unit
|
||||
|
||||
|
||||
def doHTTPGETRequest(url:String): String = {
|
||||
val httpGet = new HttpGet(url)
|
||||
doHTTPRequest(httpGet)
|
||||
|
||||
}
|
||||
|
||||
def doHTTPPOSTRequest(url:String, json:String): String = {
|
||||
val httpPost = new HttpPost(url)
|
||||
if (json != null) {
|
||||
val entity = new StringEntity(json)
|
||||
httpPost.setEntity(entity)
|
||||
httpPost.setHeader("Accept", "application/json")
|
||||
httpPost.setHeader("Content-type", "application/json")
|
||||
}
|
||||
doHTTPRequest(httpPost)
|
||||
}
|
||||
|
||||
def hasNext: Boolean = {
|
||||
buffer.nonEmpty && current_index < buffer.size
|
||||
}
|
||||
|
||||
|
||||
override def next(): String = {
|
||||
val next_item:String = buffer(current_index)
|
||||
current_index = current_index + 1
|
||||
if (current_index == buffer.size)
|
||||
getBufferData()
|
||||
next_item
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
private def doHTTPRequest[A <: HttpUriRequest](r: A) :String ={
|
||||
val timeout = 60; // seconds
|
||||
val config = RequestConfig.custom()
|
||||
.setConnectTimeout(timeout * 1000)
|
||||
.setConnectionRequestTimeout(timeout * 1000)
|
||||
.setSocketTimeout(timeout * 1000).build()
|
||||
val client =HttpClientBuilder.create().setDefaultRequestConfig(config).build()
|
||||
var tries = 4
|
||||
try {
|
||||
while (tries > 0) {
|
||||
println(s"requesting ${r.getURI}")
|
||||
val response = client.execute(r)
|
||||
println(s"get response with status${response.getStatusLine.getStatusCode}")
|
||||
if (response.getStatusLine.getStatusCode > 400) {
|
||||
tries -= 1
|
||||
}
|
||||
else
|
||||
return IOUtils.toString(response.getEntity.getContent)
|
||||
}
|
||||
""
|
||||
} catch {
|
||||
case e: Throwable =>
|
||||
throw new RuntimeException("Error on executing request ", e)
|
||||
} finally try client.close()
|
||||
catch {
|
||||
case e: IOException =>
|
||||
throw new RuntimeException("Unable to close client ", e)
|
||||
}
|
||||
}
|
||||
getBufferData()
|
||||
}
|
||||
@ -0,0 +1,607 @@
|
||||
package eu.dnetlib.dhp.actionmanager.datacite
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, OafMapperUtils}
|
||||
import eu.dnetlib.dhp.schema.oaf.{AccessRight, Author, DataInfo, Instance, KeyValue, Oaf, OtherResearchProduct, Publication, Qualifier, Relation, Result, Software, StructuredProperty, Dataset => OafDataset}
|
||||
import eu.dnetlib.dhp.utils.DHPUtils
|
||||
import org.apache.commons.lang3.StringUtils
|
||||
import org.json4s.DefaultFormats
|
||||
import org.json4s.JsonAST.{JField, JObject, JString}
|
||||
import org.json4s.jackson.JsonMethods.parse
|
||||
|
||||
import java.nio.charset.CodingErrorAction
|
||||
import java.text.SimpleDateFormat
|
||||
import java.time.LocalDate
|
||||
import java.time.chrono.ThaiBuddhistDate
|
||||
import java.time.format.DateTimeFormatter
|
||||
import java.util.regex.Pattern
|
||||
import java.util.{Date, Locale}
|
||||
import scala.collection.JavaConverters._
|
||||
import scala.io.{Codec, Source}
|
||||
import scala.language.postfixOps
|
||||
|
||||
case class DataciteType(doi: String, timestamp: Long, isActive: Boolean, json: String) {}
|
||||
|
||||
case class RelatedIdentifierType(relationType: String, relatedIdentifier: String, relatedIdentifierType: String) {}
|
||||
|
||||
case class NameIdentifiersType(nameIdentifierScheme: Option[String], schemeUri: Option[String], nameIdentifier: Option[String]) {}
|
||||
|
||||
case class CreatorType(nameType: Option[String], nameIdentifiers: Option[List[NameIdentifiersType]], name: Option[String], familyName: Option[String], givenName: Option[String], affiliation: Option[List[String]]) {}
|
||||
|
||||
case class TitleType(title: Option[String], titleType: Option[String], lang: Option[String]) {}
|
||||
|
||||
case class SubjectType(subject: Option[String], subjectScheme: Option[String]) {}
|
||||
|
||||
case class DescriptionType(descriptionType: Option[String], description: Option[String]) {}
|
||||
|
||||
case class FundingReferenceType(funderIdentifierType: Option[String], awardTitle: Option[String], awardUri: Option[String], funderName: Option[String], funderIdentifier: Option[String], awardNumber: Option[String]) {}
|
||||
|
||||
case class DateType(date: Option[String], dateType: Option[String]) {}
|
||||
|
||||
case class HostedByMapType(openaire_id: String, datacite_name: String, official_name: String, similarity: Option[Float]) {}
|
||||
|
||||
object DataciteToOAFTransformation {
|
||||
|
||||
val REL_TYPE_VALUE:String = "resultResult"
|
||||
val DATE_RELATION_KEY = "RelationDate"
|
||||
|
||||
val subRelTypeMapping: Map[String,(String,String)] = Map(
|
||||
"References" ->("IsReferencedBy","relationship"),
|
||||
"IsSupplementTo" ->("IsSupplementedBy","supplement"),
|
||||
"IsPartOf" ->("HasPart","part"),
|
||||
"HasPart" ->("IsPartOf","part"),
|
||||
"IsVersionOf" ->("HasVersion","version"),
|
||||
"HasVersion" ->("IsVersionOf","version"),
|
||||
"IsIdenticalTo" ->("IsIdenticalTo","relationship"),
|
||||
"IsPreviousVersionOf" ->("IsNewVersionOf","version"),
|
||||
"IsContinuedBy" ->("Continues","relationship"),
|
||||
"Continues" ->("IsContinuedBy","relationship"),
|
||||
"IsNewVersionOf" ->("IsPreviousVersionOf","version"),
|
||||
"IsSupplementedBy" ->("IsSupplementTo","supplement"),
|
||||
"IsDocumentedBy" ->("Documents","relationship"),
|
||||
"IsSourceOf" ->("IsDerivedFrom","relationship"),
|
||||
"Cites" ->("IsCitedBy","citation"),
|
||||
"IsCitedBy" ->("Cites","citation"),
|
||||
"IsDerivedFrom" ->("IsSourceOf","relationship"),
|
||||
"IsVariantFormOf" ->("IsDerivedFrom","version"),
|
||||
"IsReferencedBy" ->("References","relationship"),
|
||||
"IsObsoletedBy" ->("IsNewVersionOf","version"),
|
||||
"Reviews" ->("IsReviewedBy","review"),
|
||||
"Documents" ->("IsDocumentedBy","relationship"),
|
||||
"IsCompiledBy" ->("Compiles","relationship"),
|
||||
"Compiles" ->("IsCompiledBy","relationship"),
|
||||
"IsReviewedBy" ->("Reviews","review")
|
||||
)
|
||||
|
||||
implicit val codec: Codec = Codec("UTF-8")
|
||||
codec.onMalformedInput(CodingErrorAction.REPLACE)
|
||||
codec.onUnmappableCharacter(CodingErrorAction.REPLACE)
|
||||
|
||||
val DOI_CLASS = "doi"
|
||||
val SUBJ_CLASS = "keywords"
|
||||
|
||||
|
||||
val j_filter: List[String] = {
|
||||
val s = Source.fromInputStream(getClass.getResourceAsStream("datacite_filter")).mkString
|
||||
s.lines.toList
|
||||
}
|
||||
|
||||
val mapper = new ObjectMapper()
|
||||
val unknown_repository: HostedByMapType = HostedByMapType(ModelConstants.UNKNOWN_REPOSITORY_ORIGINALID, ModelConstants.UNKNOWN_REPOSITORY.getValue, ModelConstants.UNKNOWN_REPOSITORY.getValue, Some(1.0F))
|
||||
|
||||
val dataInfo: DataInfo = generateDataInfo("0.9")
|
||||
val DATACITE_COLLECTED_FROM: KeyValue = OafMapperUtils.keyValue(ModelConstants.DATACITE_ID, "Datacite")
|
||||
|
||||
val hostedByMap: Map[String, HostedByMapType] = {
|
||||
val s = Source.fromInputStream(getClass.getResourceAsStream("hostedBy_map.json")).mkString
|
||||
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
|
||||
lazy val json: org.json4s.JValue = parse(s)
|
||||
json.extract[Map[String, HostedByMapType]]
|
||||
}
|
||||
|
||||
val df_en: DateTimeFormatter = DateTimeFormatter.ofPattern("[MM-dd-yyyy][MM/dd/yyyy][dd-MM-yy][dd-MMM-yyyy][dd/MMM/yyyy][dd-MMM-yy][dd/MMM/yy][dd-MM-yy][dd/MM/yy][dd-MM-yyyy][dd/MM/yyyy][yyyy-MM-dd][yyyy/MM/dd]", Locale.ENGLISH)
|
||||
val df_it: DateTimeFormatter = DateTimeFormatter.ofPattern("[dd-MM-yyyy][dd/MM/yyyy]", Locale.ITALIAN)
|
||||
|
||||
val funder_regex: List[(Pattern, String)] = List(
|
||||
(Pattern.compile("(info:eu-repo/grantagreement/ec/h2020/)(\\d\\d\\d\\d\\d\\d)(.*)", Pattern.MULTILINE | Pattern.CASE_INSENSITIVE), "40|corda__h2020::"),
|
||||
(Pattern.compile("(info:eu-repo/grantagreement/ec/fp7/)(\\d\\d\\d\\d\\d\\d)(.*)", Pattern.MULTILINE | Pattern.CASE_INSENSITIVE), "40|corda_______::")
|
||||
|
||||
)
|
||||
|
||||
val Date_regex: List[Pattern] = List(
|
||||
//Y-M-D
|
||||
Pattern.compile("(18|19|20)\\d\\d([- /.])(0[1-9]|1[012])\\2(0[1-9]|[12][0-9]|3[01])", Pattern.MULTILINE),
|
||||
//M-D-Y
|
||||
Pattern.compile("((0[1-9]|1[012])|([1-9]))([- /.])(0[1-9]|[12][0-9]|3[01])([- /.])(18|19|20)?\\d\\d", Pattern.MULTILINE),
|
||||
//D-M-Y
|
||||
Pattern.compile("(?:(?:31(/|-|\\.)(?:0?[13578]|1[02]|(?:Jan|Mar|May|Jul|Aug|Oct|Dec)))\\1|(?:(?:29|30)(/|-|\\.)(?:0?[1,3-9]|1[0-2]|(?:Jan|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec))\\2))(?:(?:1[6-9]|[2-9]\\d)?\\d{2})|(?:29(/|-|\\.)(?:0?2|(?:Feb))\\3(?:(?:(?:1[6-9]|[2-9]\\d)?(?:0[48]|[2468][048]|[13579][26])|(?:(?:16|[2468][048]|[3579][26])00))))|(?:0?[1-9]|1\\d|2[0-8])(/|-|\\.)(?:(?:0?[1-9]|(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep))|(?:1[0-2]|(?:Oct|Nov|Dec)))\\4(?:(?:1[6-9]|[2-9]\\d)?\\d{2})", Pattern.MULTILINE),
|
||||
//Y
|
||||
Pattern.compile("(19|20)\\d\\d", Pattern.MULTILINE)
|
||||
)
|
||||
|
||||
|
||||
def filter_json(json: String): Boolean = {
|
||||
j_filter.exists(f => json.contains(f))
|
||||
}
|
||||
|
||||
def toActionSet(item: Oaf): (String, String) = {
|
||||
val mapper = new ObjectMapper()
|
||||
|
||||
item match {
|
||||
case dataset: OafDataset =>
|
||||
val a: AtomicAction[OafDataset] = new AtomicAction[OafDataset]
|
||||
a.setClazz(classOf[OafDataset])
|
||||
a.setPayload(dataset)
|
||||
(dataset.getClass.getCanonicalName, mapper.writeValueAsString(a))
|
||||
case publication: Publication =>
|
||||
val a: AtomicAction[Publication] = new AtomicAction[Publication]
|
||||
a.setClazz(classOf[Publication])
|
||||
a.setPayload(publication)
|
||||
(publication.getClass.getCanonicalName, mapper.writeValueAsString(a))
|
||||
case software: Software =>
|
||||
val a: AtomicAction[Software] = new AtomicAction[Software]
|
||||
a.setClazz(classOf[Software])
|
||||
a.setPayload(software)
|
||||
(software.getClass.getCanonicalName, mapper.writeValueAsString(a))
|
||||
case orp: OtherResearchProduct =>
|
||||
val a: AtomicAction[OtherResearchProduct] = new AtomicAction[OtherResearchProduct]
|
||||
a.setClazz(classOf[OtherResearchProduct])
|
||||
a.setPayload(orp)
|
||||
(orp.getClass.getCanonicalName, mapper.writeValueAsString(a))
|
||||
|
||||
case relation: Relation =>
|
||||
val a: AtomicAction[Relation] = new AtomicAction[Relation]
|
||||
a.setClazz(classOf[Relation])
|
||||
a.setPayload(relation)
|
||||
(relation.getClass.getCanonicalName, mapper.writeValueAsString(a))
|
||||
case _ =>
|
||||
null
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
|
||||
def embargo_end(embargo_end_date: String): Boolean = {
|
||||
val dt = LocalDate.parse(embargo_end_date, DateTimeFormatter.ofPattern("[yyyy-MM-dd]"))
|
||||
val td = LocalDate.now()
|
||||
td.isAfter(dt)
|
||||
}
|
||||
|
||||
|
||||
def extract_date(input: String): Option[String] = {
|
||||
val d = Date_regex.map(pattern => {
|
||||
val matcher = pattern.matcher(input)
|
||||
if (matcher.find())
|
||||
matcher.group(0)
|
||||
else
|
||||
null
|
||||
}
|
||||
).find(s => s != null)
|
||||
|
||||
if (d.isDefined) {
|
||||
val a_date = if (d.get.length == 4) s"01-01-${d.get}" else d.get
|
||||
try {
|
||||
return Some(LocalDate.parse(a_date, df_en).toString)
|
||||
} catch {
|
||||
case _: Throwable => try {
|
||||
return Some(LocalDate.parse(a_date, df_it).toString)
|
||||
} catch {
|
||||
case _: Throwable =>
|
||||
return None
|
||||
}
|
||||
}
|
||||
}
|
||||
d
|
||||
}
|
||||
|
||||
def fix_thai_date(input:String, format:String) :String = {
|
||||
try {
|
||||
val a_date = LocalDate.parse(input,DateTimeFormatter.ofPattern(format))
|
||||
val d = ThaiBuddhistDate.of(a_date.getYear, a_date.getMonth.getValue, a_date.getDayOfMonth)
|
||||
LocalDate.from(d).toString
|
||||
} catch {
|
||||
case _: Throwable => ""
|
||||
}
|
||||
}
|
||||
def getTypeQualifier(resourceType: String, resourceTypeGeneral: String, schemaOrg: String, vocabularies: VocabularyGroup): (Qualifier, Qualifier) = {
|
||||
if (resourceType != null && resourceType.nonEmpty) {
|
||||
val typeQualifier = vocabularies.getSynonymAsQualifier(ModelConstants.DNET_PUBLICATION_RESOURCE, resourceType)
|
||||
if (typeQualifier != null)
|
||||
return (typeQualifier, vocabularies.getSynonymAsQualifier(ModelConstants.DNET_RESULT_TYPOLOGIES, typeQualifier.getClassid))
|
||||
}
|
||||
if (schemaOrg != null && schemaOrg.nonEmpty) {
|
||||
val typeQualifier = vocabularies.getSynonymAsQualifier(ModelConstants.DNET_PUBLICATION_RESOURCE, schemaOrg)
|
||||
if (typeQualifier != null)
|
||||
return (typeQualifier, vocabularies.getSynonymAsQualifier(ModelConstants.DNET_RESULT_TYPOLOGIES, typeQualifier.getClassid))
|
||||
|
||||
}
|
||||
if (resourceTypeGeneral != null && resourceTypeGeneral.nonEmpty) {
|
||||
val typeQualifier = vocabularies.getSynonymAsQualifier(ModelConstants.DNET_PUBLICATION_RESOURCE, resourceTypeGeneral)
|
||||
if (typeQualifier != null)
|
||||
return (typeQualifier, vocabularies.getSynonymAsQualifier(ModelConstants.DNET_RESULT_TYPOLOGIES, typeQualifier.getClassid))
|
||||
|
||||
}
|
||||
null
|
||||
}
|
||||
|
||||
|
||||
def getResult(resourceType: String, resourceTypeGeneral: String, schemaOrg: String, vocabularies: VocabularyGroup): Result = {
|
||||
val typeQualifiers: (Qualifier, Qualifier) = getTypeQualifier(resourceType, resourceTypeGeneral, schemaOrg, vocabularies)
|
||||
if (typeQualifiers == null)
|
||||
return null
|
||||
val i = new Instance
|
||||
i.setInstancetype(typeQualifiers._1)
|
||||
typeQualifiers._2.getClassname match {
|
||||
case "dataset" =>
|
||||
val r = new OafDataset
|
||||
r.setInstance(List(i).asJava)
|
||||
return r
|
||||
case "publication" =>
|
||||
val r = new Publication
|
||||
r.setInstance(List(i).asJava)
|
||||
return r
|
||||
case "software" =>
|
||||
val r = new Software
|
||||
r.setInstance(List(i).asJava)
|
||||
return r
|
||||
case "other" =>
|
||||
val r = new OtherResearchProduct
|
||||
r.setInstance(List(i).asJava)
|
||||
return r
|
||||
}
|
||||
null
|
||||
}
|
||||
|
||||
|
||||
def available_date(input: String): Boolean = {
|
||||
|
||||
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
|
||||
lazy val json: org.json4s.JValue = parse(input)
|
||||
val l: List[String] = for {
|
||||
JObject(dates) <- json \\ "dates"
|
||||
JField("dateType", JString(dateTypes)) <- dates
|
||||
} yield dateTypes
|
||||
|
||||
l.exists(p => p.equalsIgnoreCase("available"))
|
||||
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* As describe in ticket #6377
|
||||
* when the result come from figshare we need to remove subject
|
||||
* and set Access rights OPEN.
|
||||
*
|
||||
* @param r
|
||||
*/
|
||||
def fix_figshare(r: Result): Unit = {
|
||||
|
||||
if (r.getInstance() != null) {
|
||||
val hosted_by_figshare = r.getInstance().asScala.exists(i => i.getHostedby != null && "figshare".equalsIgnoreCase(i.getHostedby.getValue))
|
||||
if (hosted_by_figshare) {
|
||||
r.getInstance().asScala.foreach(i => i.setAccessright(ModelConstants.OPEN_ACCESS_RIGHT()))
|
||||
val l: List[StructuredProperty] = List()
|
||||
r.setSubject(l.asJava)
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
|
||||
|
||||
def createDNetTargetIdentifier(pid: String, pidType: String, idPrefix: String): String = {
|
||||
val f_part = s"$idPrefix|${pidType.toLowerCase}".padTo(15, '_')
|
||||
s"$f_part::${IdentifierFactory.md5(pid.toLowerCase)}"
|
||||
}
|
||||
|
||||
def generateOAFDate(dt: String, q: Qualifier): StructuredProperty = {
|
||||
OafMapperUtils.structuredProperty(dt, q, null)
|
||||
}
|
||||
|
||||
def generateRelation(sourceId: String, targetId: String, relClass: String, cf: KeyValue, di: DataInfo): Relation = {
|
||||
|
||||
val r = new Relation
|
||||
r.setSource(sourceId)
|
||||
r.setTarget(targetId)
|
||||
r.setRelType(ModelConstants.RESULT_PROJECT)
|
||||
r.setRelClass(relClass)
|
||||
r.setSubRelType(ModelConstants.OUTCOME)
|
||||
r.setCollectedfrom(List(cf).asJava)
|
||||
r.setDataInfo(di)
|
||||
r
|
||||
|
||||
|
||||
}
|
||||
|
||||
def get_projectRelation(awardUri: String, sourceId: String): List[Relation] = {
|
||||
val match_pattern = funder_regex.find(s => s._1.matcher(awardUri).find())
|
||||
|
||||
if (match_pattern.isDefined) {
|
||||
val m = match_pattern.get._1
|
||||
val p = match_pattern.get._2
|
||||
val grantId = m.matcher(awardUri).replaceAll("$2")
|
||||
val targetId = s"$p${DHPUtils.md5(grantId)}"
|
||||
List(
|
||||
generateRelation(sourceId, targetId, "isProducedBy", DATACITE_COLLECTED_FROM, dataInfo),
|
||||
generateRelation(targetId, sourceId, "produces", DATACITE_COLLECTED_FROM, dataInfo)
|
||||
)
|
||||
}
|
||||
else
|
||||
List()
|
||||
|
||||
}
|
||||
|
||||
|
||||
def generateOAF(input: String, ts: Long, dateOfCollection: Long, vocabularies: VocabularyGroup, exportLinks: Boolean): List[Oaf] = {
|
||||
if (filter_json(input))
|
||||
return List()
|
||||
|
||||
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
|
||||
lazy val json = parse(input)
|
||||
|
||||
val resourceType = (json \ "attributes" \ "types" \ "resourceType").extractOrElse[String](null)
|
||||
val resourceTypeGeneral = (json \ "attributes" \ "types" \ "resourceTypeGeneral").extractOrElse[String](null)
|
||||
val schemaOrg = (json \ "attributes" \ "types" \ "schemaOrg").extractOrElse[String](null)
|
||||
|
||||
val doi = (json \ "attributes" \ "doi").extract[String]
|
||||
if (doi.isEmpty)
|
||||
return List()
|
||||
|
||||
//Mapping type based on vocabularies dnet:publication_resource and dnet:result_typologies
|
||||
val result = getResult(resourceType, resourceTypeGeneral, schemaOrg, vocabularies)
|
||||
if (result == null)
|
||||
return List()
|
||||
|
||||
|
||||
val doi_q = OafMapperUtils.qualifier("doi", "doi", ModelConstants.DNET_PID_TYPES, ModelConstants.DNET_PID_TYPES)
|
||||
val pid = OafMapperUtils.structuredProperty(doi, doi_q, dataInfo)
|
||||
result.setPid(List(pid).asJava)
|
||||
result.setId(OafMapperUtils.createOpenaireId(50, s"datacite____::$doi", true))
|
||||
result.setOriginalId(List(doi).asJava)
|
||||
|
||||
val d = new Date(dateOfCollection * 1000)
|
||||
val ISO8601FORMAT = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ssZ", Locale.US)
|
||||
|
||||
|
||||
result.setDateofcollection(ISO8601FORMAT.format(d))
|
||||
result.setDateoftransformation(ISO8601FORMAT.format(d))
|
||||
result.setDataInfo(dataInfo)
|
||||
|
||||
val creators = (json \\ "creators").extractOrElse[List[CreatorType]](List())
|
||||
|
||||
|
||||
val authors = creators.zipWithIndex.map { case (c, idx) =>
|
||||
val a = new Author
|
||||
a.setFullname(c.name.orNull)
|
||||
a.setName(c.givenName.orNull)
|
||||
a.setSurname(c.familyName.orNull)
|
||||
if (c.nameIdentifiers != null && c.nameIdentifiers.isDefined && c.nameIdentifiers.get != null) {
|
||||
a.setPid(c.nameIdentifiers.get.map(ni => {
|
||||
val q = if (ni.nameIdentifierScheme.isDefined) vocabularies.getTermAsQualifier(ModelConstants.DNET_PID_TYPES, ni.nameIdentifierScheme.get.toLowerCase()) else null
|
||||
if (ni.nameIdentifier != null && ni.nameIdentifier.isDefined) {
|
||||
OafMapperUtils.structuredProperty(ni.nameIdentifier.get, q, dataInfo)
|
||||
}
|
||||
else
|
||||
null
|
||||
|
||||
}
|
||||
)
|
||||
.asJava)
|
||||
}
|
||||
if (c.affiliation.isDefined)
|
||||
a.setAffiliation(c.affiliation.get.filter(af => af.nonEmpty).map(af => OafMapperUtils.field(af, dataInfo)).asJava)
|
||||
a.setRank(idx + 1)
|
||||
a
|
||||
}
|
||||
|
||||
|
||||
val titles: List[TitleType] = (json \\ "titles").extractOrElse[List[TitleType]](List())
|
||||
|
||||
result.setTitle(titles.filter(t => t.title.nonEmpty).map(t => {
|
||||
if (t.titleType.isEmpty) {
|
||||
OafMapperUtils.structuredProperty(t.title.get, ModelConstants.MAIN_TITLE_QUALIFIER, null)
|
||||
} else {
|
||||
OafMapperUtils.structuredProperty(t.title.get, t.titleType.get, t.titleType.get, ModelConstants.DNET_DATACITE_TITLE, ModelConstants.DNET_DATACITE_TITLE, null)
|
||||
}
|
||||
}).asJava)
|
||||
|
||||
if (authors == null || authors.isEmpty || !authors.exists(a => a != null))
|
||||
return List()
|
||||
result.setAuthor(authors.asJava)
|
||||
|
||||
val dates = (json \\ "dates").extract[List[DateType]]
|
||||
val publication_year = (json \\ "publicationYear").extractOrElse[String](null)
|
||||
|
||||
val i_date = dates
|
||||
.filter(d => d.date.isDefined && d.dateType.isDefined)
|
||||
.find(d => d.dateType.get.equalsIgnoreCase("issued"))
|
||||
.map(d => extract_date(d.date.get))
|
||||
val a_date: Option[String] = dates
|
||||
.filter(d => d.date.isDefined && d.dateType.isDefined && d.dateType.get.equalsIgnoreCase("available"))
|
||||
.map(d => extract_date(d.date.get))
|
||||
.find(d => d != null && d.isDefined)
|
||||
.map(d => d.get)
|
||||
|
||||
if (a_date.isDefined) {
|
||||
if(doi.startsWith("10.14457"))
|
||||
result.setEmbargoenddate(OafMapperUtils.field(fix_thai_date(a_date.get,"[yyyy-MM-dd]"), null))
|
||||
else
|
||||
result.setEmbargoenddate(OafMapperUtils.field(a_date.get, null))
|
||||
}
|
||||
if (i_date.isDefined && i_date.get.isDefined) {
|
||||
if(doi.startsWith("10.14457")) {
|
||||
result.setDateofacceptance(OafMapperUtils.field(fix_thai_date(i_date.get.get,"[yyyy-MM-dd]"), null))
|
||||
result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(fix_thai_date(i_date.get.get,"[yyyy-MM-dd]"), null))
|
||||
}
|
||||
else {
|
||||
result.setDateofacceptance(OafMapperUtils.field(i_date.get.get, null))
|
||||
result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(i_date.get.get, null))
|
||||
}
|
||||
}
|
||||
else if (publication_year != null) {
|
||||
if(doi.startsWith("10.14457")) {
|
||||
result.setDateofacceptance(OafMapperUtils.field(fix_thai_date(s"01-01-$publication_year","[dd-MM-yyyy]"), null))
|
||||
result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(fix_thai_date(s"01-01-$publication_year","[dd-MM-yyyy]"), null))
|
||||
|
||||
} else {
|
||||
result.setDateofacceptance(OafMapperUtils.field(s"01-01-$publication_year", null))
|
||||
result.getInstance().get(0).setDateofacceptance(OafMapperUtils.field(s"01-01-$publication_year", null))
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
result.setRelevantdate(dates.filter(d => d.date.isDefined && d.dateType.isDefined)
|
||||
.map(d => (extract_date(d.date.get), d.dateType.get))
|
||||
.filter(d => d._1.isDefined)
|
||||
.map(d => (d._1.get, vocabularies.getTermAsQualifier(ModelConstants.DNET_DATACITE_DATE, d._2.toLowerCase())))
|
||||
.filter(d => d._2 != null)
|
||||
.map(d => generateOAFDate(d._1, d._2)).asJava)
|
||||
|
||||
val subjects = (json \\ "subjects").extract[List[SubjectType]]
|
||||
|
||||
result.setSubject(subjects.filter(s => s.subject.nonEmpty)
|
||||
.map(s =>
|
||||
OafMapperUtils.structuredProperty(s.subject.get, SUBJ_CLASS, SUBJ_CLASS, ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES, null)
|
||||
).asJava)
|
||||
|
||||
|
||||
result.setCollectedfrom(List(DATACITE_COLLECTED_FROM).asJava)
|
||||
|
||||
val descriptions = (json \\ "descriptions").extract[List[DescriptionType]]
|
||||
|
||||
result.setDescription(
|
||||
descriptions
|
||||
.filter(d => d.description.isDefined).
|
||||
map(d =>
|
||||
OafMapperUtils.field(d.description.get, null)
|
||||
).filter(s => s != null).asJava)
|
||||
|
||||
|
||||
val publisher = (json \\ "publisher").extractOrElse[String](null)
|
||||
if (publisher != null)
|
||||
result.setPublisher(OafMapperUtils.field(publisher, null))
|
||||
|
||||
|
||||
val language: String = (json \\ "language").extractOrElse[String](null)
|
||||
|
||||
if (language != null)
|
||||
result.setLanguage(vocabularies.getSynonymAsQualifier(ModelConstants.DNET_LANGUAGES, language))
|
||||
|
||||
|
||||
val instance = result.getInstance().get(0)
|
||||
|
||||
val client = (json \ "relationships" \ "client" \\ "id").extractOpt[String]
|
||||
|
||||
val accessRights: List[String] = for {
|
||||
JObject(rightsList) <- json \\ "rightsList"
|
||||
JField("rightsUri", JString(rightsUri)) <- rightsList
|
||||
} yield rightsUri
|
||||
|
||||
val aRights: Option[AccessRight] = accessRights.map(r => {
|
||||
vocabularies.getSynonymAsQualifier(ModelConstants.DNET_ACCESS_MODES, r)
|
||||
}).find(q => q != null).map(q => {
|
||||
val a = new AccessRight
|
||||
a.setClassid(q.getClassid)
|
||||
a.setClassname(q.getClassname)
|
||||
a.setSchemeid(q.getSchemeid)
|
||||
a.setSchemename(q.getSchemename)
|
||||
a
|
||||
})
|
||||
|
||||
|
||||
val access_rights_qualifier = if (aRights.isDefined) aRights.get else OafMapperUtils.accessRight(ModelConstants.UNKNOWN, ModelConstants.NOT_AVAILABLE, ModelConstants.DNET_ACCESS_MODES, ModelConstants.DNET_ACCESS_MODES)
|
||||
|
||||
if (client.isDefined) {
|
||||
val hb = hostedByMap.getOrElse(client.get.toUpperCase(), unknown_repository)
|
||||
instance.setHostedby(OafMapperUtils.keyValue(generateDSId(hb.openaire_id), hb.official_name))
|
||||
instance.setCollectedfrom(DATACITE_COLLECTED_FROM)
|
||||
instance.setUrl(List(s"https://dx.doi.org/$doi").asJava)
|
||||
instance.setAccessright(access_rights_qualifier)
|
||||
instance.setPid(result.getPid)
|
||||
val license = accessRights
|
||||
.find(r => r.startsWith("http") && r.matches(".*(/licenses|/publicdomain|unlicense\\.org/|/legal-and-data-protection-notices|/download/license|/open-government-licence).*"))
|
||||
if (license.isDefined)
|
||||
instance.setLicense(OafMapperUtils.field(license.get, null))
|
||||
}
|
||||
|
||||
val awardUris: List[String] = for {
|
||||
JObject(fundingReferences) <- json \\ "fundingReferences"
|
||||
JField("awardUri", JString(awardUri)) <- fundingReferences
|
||||
} yield awardUri
|
||||
|
||||
result.setId(IdentifierFactory.createIdentifier(result))
|
||||
var relations: List[Relation] = awardUris.flatMap(a => get_projectRelation(a, result.getId)).filter(r => r != null)
|
||||
|
||||
fix_figshare(result)
|
||||
|
||||
if (result.getId == null)
|
||||
return List()
|
||||
|
||||
if (exportLinks) {
|
||||
val rels: List[RelatedIdentifierType] = for {
|
||||
JObject(relIdentifier) <- json \\ "relatedIdentifiers"
|
||||
JField("relationType", JString(relationType)) <- relIdentifier
|
||||
JField("relatedIdentifierType", JString(relatedIdentifierType)) <- relIdentifier
|
||||
JField("relatedIdentifier", JString(relatedIdentifier)) <- relIdentifier
|
||||
} yield RelatedIdentifierType(relationType, relatedIdentifier, relatedIdentifierType)
|
||||
|
||||
relations = relations ::: generateRelations(rels,result.getId, if (i_date.isDefined && i_date.get.isDefined) i_date.get.get else null)
|
||||
}
|
||||
if (relations != null && relations.nonEmpty) {
|
||||
List(result) ::: relations
|
||||
}
|
||||
else
|
||||
List(result)
|
||||
}
|
||||
|
||||
private def generateRelations(rels: List[RelatedIdentifierType], id:String, date:String):List[Relation] = {
|
||||
rels
|
||||
.filter(r =>
|
||||
subRelTypeMapping.contains(r.relationType) && (
|
||||
r.relatedIdentifierType.equalsIgnoreCase("doi") ||
|
||||
r.relatedIdentifierType.equalsIgnoreCase("pmid") ||
|
||||
r.relatedIdentifierType.equalsIgnoreCase("arxiv"))
|
||||
)
|
||||
.map(r => {
|
||||
val rel = new Relation
|
||||
rel.setCollectedfrom(List(DATACITE_COLLECTED_FROM).asJava)
|
||||
rel.setDataInfo(dataInfo)
|
||||
|
||||
val subRelType = subRelTypeMapping(r.relationType)._2
|
||||
rel.setRelType(REL_TYPE_VALUE)
|
||||
rel.setSubRelType(subRelType)
|
||||
rel.setRelClass(r.relationType)
|
||||
|
||||
val dateProps:KeyValue = OafMapperUtils.keyValue(DATE_RELATION_KEY, date)
|
||||
|
||||
rel.setProperties(List(dateProps).asJava)
|
||||
|
||||
rel.setSource(id)
|
||||
rel.setTarget(s"unresolved::${r.relatedIdentifier}::${r.relatedIdentifierType}")
|
||||
rel.setCollectedfrom(List(DATACITE_COLLECTED_FROM).asJava)
|
||||
rel.getCollectedfrom.asScala.map(c => c.getValue)(collection.breakOut)
|
||||
rel
|
||||
})(collection breakOut)
|
||||
}
|
||||
|
||||
def generateDataInfo(trust: String): DataInfo = {
|
||||
val di = new DataInfo
|
||||
di.setDeletedbyinference(false)
|
||||
di.setInferred(false)
|
||||
di.setInvisible(false)
|
||||
di.setTrust(trust)
|
||||
di.setProvenanceaction(ModelConstants.PROVENANCE_ACTION_SET_QUALIFIER)
|
||||
di
|
||||
}
|
||||
|
||||
def generateDSId(input: String): String = {
|
||||
val b = StringUtils.substringBefore(input, "::")
|
||||
val a = StringUtils.substringAfter(input, "::")
|
||||
s"10|$b::${DHPUtils.md5(a)}"
|
||||
}
|
||||
|
||||
|
||||
}
|
||||
@ -0,0 +1,41 @@
|
||||
package eu.dnetlib.dhp.actionmanager.datacite
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf
|
||||
import org.apache.hadoop.io.Text
|
||||
import org.apache.hadoop.io.compress.GzipCodec
|
||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat
|
||||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
|
||||
import scala.io.Source
|
||||
|
||||
object ExportActionSetJobNode {
|
||||
|
||||
val log: Logger = LoggerFactory.getLogger(ExportActionSetJobNode.getClass)
|
||||
|
||||
def main(args: Array[String]): Unit = {
|
||||
val conf = new SparkConf
|
||||
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/exportDataset_parameters.json")).mkString)
|
||||
parser.parseArgument(args)
|
||||
val master = parser.get("master")
|
||||
val sourcePath = parser.get("sourcePath")
|
||||
val targetPath = parser.get("targetPath")
|
||||
|
||||
val spark: SparkSession = SparkSession.builder().config(conf)
|
||||
.appName(ExportActionSetJobNode.getClass.getSimpleName)
|
||||
.master(master)
|
||||
.getOrCreate()
|
||||
implicit val resEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
|
||||
implicit val tEncoder:Encoder[(String,String)] = Encoders.tuple(Encoders.STRING,Encoders.STRING)
|
||||
|
||||
spark.read.load(sourcePath).as[Oaf]
|
||||
.map(o =>DataciteToOAFTransformation.toActionSet(o))
|
||||
.filter(o => o!= null)
|
||||
.rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text,Text]], classOf[GzipCodec])
|
||||
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
@ -0,0 +1,46 @@
|
||||
package eu.dnetlib.dhp.actionmanager.datacite
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
|
||||
import eu.dnetlib.dhp.schema.mdstore.MetadataRecord
|
||||
import eu.dnetlib.dhp.schema.oaf.{Oaf, Result}
|
||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory
|
||||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
|
||||
import scala.io.Source
|
||||
|
||||
object FilterCrossrefEntitiesSpark {
|
||||
|
||||
val log: Logger = LoggerFactory.getLogger(getClass.getClass)
|
||||
|
||||
def main(args: Array[String]): Unit = {
|
||||
val conf = new SparkConf
|
||||
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/filter_crossref_param.json")).mkString)
|
||||
parser.parseArgument(args)
|
||||
val master = parser.get("master")
|
||||
val sourcePath = parser.get("sourcePath")
|
||||
log.info("sourcePath: {}", sourcePath)
|
||||
val targetPath = parser.get("targetPath")
|
||||
log.info("targetPath: {}", targetPath)
|
||||
|
||||
|
||||
|
||||
val spark: SparkSession = SparkSession.builder().config(conf)
|
||||
.appName(getClass.getSimpleName)
|
||||
.master(master)
|
||||
.getOrCreate()
|
||||
|
||||
|
||||
|
||||
implicit val oafEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
|
||||
implicit val resEncoder: Encoder[Result] = Encoders.kryo[Result]
|
||||
|
||||
val d:Dataset[Oaf]= spark.read.load(sourcePath).as[Oaf]
|
||||
|
||||
d.filter(r => r.isInstanceOf[Result]).map(r => r.asInstanceOf[Result]).write.mode(SaveMode.Overwrite).save(targetPath)
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
@ -0,0 +1,48 @@
|
||||
package eu.dnetlib.dhp.actionmanager.datacite
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
|
||||
import eu.dnetlib.dhp.schema.mdstore.MetadataRecord
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf
|
||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory
|
||||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
|
||||
import scala.io.Source
|
||||
|
||||
object GenerateDataciteDatasetSpark {
|
||||
|
||||
val log: Logger = LoggerFactory.getLogger(GenerateDataciteDatasetSpark.getClass)
|
||||
|
||||
def main(args: Array[String]): Unit = {
|
||||
val conf = new SparkConf
|
||||
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/generate_dataset_params.json")).mkString)
|
||||
parser.parseArgument(args)
|
||||
val master = parser.get("master")
|
||||
val sourcePath = parser.get("sourcePath")
|
||||
val targetPath = parser.get("targetPath")
|
||||
val exportLinks = "true".equalsIgnoreCase(parser.get("exportLinks"))
|
||||
val isLookupUrl: String = parser.get("isLookupUrl")
|
||||
log.info("isLookupUrl: {}", isLookupUrl)
|
||||
|
||||
val isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl)
|
||||
val vocabularies = VocabularyGroup.loadVocsFromIS(isLookupService)
|
||||
val spark: SparkSession = SparkSession.builder().config(conf)
|
||||
.appName(GenerateDataciteDatasetSpark.getClass.getSimpleName)
|
||||
.master(master)
|
||||
.getOrCreate()
|
||||
|
||||
implicit val mrEncoder: Encoder[MetadataRecord] = Encoders.kryo[MetadataRecord]
|
||||
|
||||
implicit val resEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
|
||||
|
||||
import spark.implicits._
|
||||
|
||||
spark.read.load(sourcePath).as[DataciteType]
|
||||
.filter(d => d.isActive)
|
||||
.flatMap(d => DataciteToOAFTransformation.generateOAF(d.json, d.timestamp, d.timestamp, vocabularies, exportLinks))
|
||||
.filter(d => d != null)
|
||||
.write.mode(SaveMode.Overwrite).save(targetPath)
|
||||
}
|
||||
}
|
||||
@ -1,181 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.Serializable;
|
||||
import java.util.*;
|
||||
|
||||
import org.apache.commons.cli.ParseException;
|
||||
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.FilterFunction;
|
||||
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
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.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.*;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class CreateActionSetSparkJob implements Serializable {
|
||||
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
|
||||
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
|
||||
private static final String ID_PREFIX = "50|doi_________::";
|
||||
private static final String TRUST = "0.91";
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static void main(final String[] args) throws IOException, ParseException {
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
CreateActionSetSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/as_parameters.json"))));
|
||||
|
||||
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("inputPath");
|
||||
log.info("inputPath {}", inputPath.toString());
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}", outputPath);
|
||||
|
||||
final boolean shouldDuplicateRels = Optional
|
||||
.ofNullable(parser.get("shouldDuplicateRels"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.FALSE);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
extractContent(spark, inputPath, outputPath, shouldDuplicateRels);
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
private static void extractContent(SparkSession spark, String inputPath, String outputPath,
|
||||
boolean shouldDuplicateRels) {
|
||||
spark
|
||||
.sqlContext()
|
||||
.createDataset(spark.sparkContext().textFile(inputPath + "/*", 6000), Encoders.STRING())
|
||||
.flatMap(
|
||||
(FlatMapFunction<String, Relation>) value -> createRelation(value, shouldDuplicateRels).iterator(),
|
||||
Encoders.bean(Relation.class))
|
||||
.filter((FilterFunction<Relation>) value -> value != null)
|
||||
.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<Relation> createRelation(String value, boolean duplicate) {
|
||||
String[] line = value.split(",");
|
||||
if (!line[1].startsWith("10.")) {
|
||||
return new ArrayList<>();
|
||||
}
|
||||
List<Relation> relationList = new ArrayList<>();
|
||||
|
||||
String citing = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[1]));
|
||||
final String cited = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[2]));
|
||||
|
||||
relationList
|
||||
.addAll(
|
||||
getRelations(
|
||||
citing,
|
||||
cited));
|
||||
|
||||
if (duplicate && line[1].endsWith(".refs")) {
|
||||
citing = ID_PREFIX + IdentifierFactory
|
||||
.md5(CleaningFunctions.normalizePidValue("doi", line[1].substring(0, line[1].indexOf(".refs"))));
|
||||
relationList.addAll(getRelations(citing, cited));
|
||||
}
|
||||
|
||||
return relationList;
|
||||
}
|
||||
|
||||
private static Collection<Relation> getRelations(String citing, String cited) {
|
||||
|
||||
return Arrays
|
||||
.asList(
|
||||
getRelation(citing, cited, ModelConstants.CITES),
|
||||
getRelation(cited, citing, ModelConstants.IS_CITED_BY));
|
||||
}
|
||||
|
||||
public static Relation getRelation(
|
||||
String source,
|
||||
String target,
|
||||
String relclass) {
|
||||
Relation r = new Relation();
|
||||
r.setCollectedfrom(getCollectedFrom());
|
||||
r.setSource(source);
|
||||
r.setTarget(target);
|
||||
r.setRelClass(relclass);
|
||||
r.setRelType(ModelConstants.RESULT_RESULT);
|
||||
r.setSubRelType(ModelConstants.CITATION);
|
||||
r
|
||||
.setDataInfo(
|
||||
getDataInfo());
|
||||
return r;
|
||||
}
|
||||
|
||||
public static List<KeyValue> getCollectedFrom() {
|
||||
KeyValue kv = new KeyValue();
|
||||
kv.setKey(ModelConstants.OPENOCITATIONS_ID);
|
||||
kv.setValue(ModelConstants.OPENOCITATIONS_NAME);
|
||||
|
||||
return Arrays.asList(kv);
|
||||
}
|
||||
|
||||
public static DataInfo getDataInfo() {
|
||||
DataInfo di = new DataInfo();
|
||||
di.setInferred(false);
|
||||
di.setDeletedbyinference(false);
|
||||
di.setTrust(TRUST);
|
||||
|
||||
di
|
||||
.setProvenanceaction(
|
||||
getQualifier(OPENCITATIONS_CLASSID, OPENCITATIONS_CLASSNAME, ModelConstants.DNET_PROVENANCE_ACTIONS));
|
||||
return di;
|
||||
}
|
||||
|
||||
public static Qualifier getQualifier(String class_id, String class_name,
|
||||
String qualifierSchema) {
|
||||
Qualifier pa = new Qualifier();
|
||||
pa.setClassid(class_id);
|
||||
pa.setClassname(class_name);
|
||||
pa.setSchemeid(qualifierSchema);
|
||||
pa.setSchemename(qualifierSchema);
|
||||
return pa;
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,93 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||
|
||||
import java.io.*;
|
||||
import java.io.Serializable;
|
||||
import java.util.Objects;
|
||||
import java.util.zip.GZIPOutputStream;
|
||||
import java.util.zip.ZipEntry;
|
||||
import java.util.zip.ZipInputStream;
|
||||
|
||||
import org.apache.commons.cli.ParseException;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FSDataInputStream;
|
||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
|
||||
public class GetOpenCitationsRefs implements Serializable {
|
||||
private static final Logger log = LoggerFactory.getLogger(GetOpenCitationsRefs.class);
|
||||
|
||||
public static void main(final String[] args) throws IOException, ParseException {
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
GetOpenCitationsRefs.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/input_parameters.json"))));
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
final String[] inputFile = parser.get("inputFile").split(";");
|
||||
log.info("inputFile {}", inputFile.toString());
|
||||
|
||||
final String workingPath = parser.get("workingPath");
|
||||
log.info("workingPath {}", workingPath);
|
||||
|
||||
final String hdfsNameNode = parser.get("hdfsNameNode");
|
||||
log.info("hdfsNameNode {}", hdfsNameNode);
|
||||
|
||||
Configuration conf = new Configuration();
|
||||
conf.set("fs.defaultFS", hdfsNameNode);
|
||||
|
||||
FileSystem fileSystem = FileSystem.get(conf);
|
||||
|
||||
GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
|
||||
|
||||
for (String file : inputFile) {
|
||||
ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
private void doExtract(String inputFile, String workingPath, FileSystem fileSystem)
|
||||
throws IOException {
|
||||
|
||||
final Path path = new Path(inputFile);
|
||||
|
||||
FSDataInputStream oc_zip = fileSystem.open(path);
|
||||
|
||||
int count = 1;
|
||||
try (ZipInputStream zis = new ZipInputStream(oc_zip)) {
|
||||
ZipEntry entry = null;
|
||||
while ((entry = zis.getNextEntry()) != null) {
|
||||
|
||||
if (!entry.isDirectory()) {
|
||||
String fileName = entry.getName();
|
||||
fileName = fileName.substring(0, fileName.indexOf("T")) + "_" + count;
|
||||
count++;
|
||||
try (
|
||||
FSDataOutputStream out = fileSystem
|
||||
.create(new Path(workingPath + "/COCI/" + fileName + ".gz"));
|
||||
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
|
||||
|
||||
IOUtils.copy(zis, gzipOs);
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
@ -0,0 +1,40 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.project.utils;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.Set;
|
||||
|
||||
import org.apache.commons.csv.CSVFormat;
|
||||
import org.apache.commons.csv.CSVRecord;
|
||||
import org.apache.commons.lang.reflect.FieldUtils;
|
||||
|
||||
/**
|
||||
* Reads a generic csv and maps it into classes that mirror its schema
|
||||
*/
|
||||
public class CSVParser {
|
||||
|
||||
public <R> List<R> parse(String csvFile, String classForName)
|
||||
throws ClassNotFoundException, IOException, IllegalAccessException, InstantiationException {
|
||||
final CSVFormat format = CSVFormat.EXCEL
|
||||
.withHeader()
|
||||
.withDelimiter(';')
|
||||
.withQuote('"')
|
||||
.withTrim();
|
||||
List<R> ret = new ArrayList<>();
|
||||
final org.apache.commons.csv.CSVParser parser = org.apache.commons.csv.CSVParser.parse(csvFile, format);
|
||||
final Set<String> headers = parser.getHeaderMap().keySet();
|
||||
Class<?> clazz = Class.forName(classForName);
|
||||
for (CSVRecord csvRecord : parser.getRecords()) {
|
||||
final Object cc = clazz.newInstance();
|
||||
for (String header : headers) {
|
||||
FieldUtils.writeField(cc, header, csvRecord.get(header), true);
|
||||
|
||||
}
|
||||
ret.add((R) cc);
|
||||
}
|
||||
|
||||
return ret;
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,200 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.project.utils;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
/**
|
||||
* the mmodel for the projects csv file
|
||||
*/
|
||||
public class CSVProject implements Serializable {
|
||||
private String rcn;
|
||||
private String id;
|
||||
private String acronym;
|
||||
private String status;
|
||||
private String programme;
|
||||
private String topics;
|
||||
private String frameworkProgramme;
|
||||
private String title;
|
||||
private String startDate;
|
||||
private String endDate;
|
||||
private String projectUrl;
|
||||
private String objective;
|
||||
private String totalCost;
|
||||
private String ecMaxContribution;
|
||||
private String call;
|
||||
private String fundingScheme;
|
||||
private String coordinator;
|
||||
private String coordinatorCountry;
|
||||
private String participants;
|
||||
private String participantCountries;
|
||||
private String subjects;
|
||||
|
||||
public String getRcn() {
|
||||
return rcn;
|
||||
}
|
||||
|
||||
public void setRcn(String rcn) {
|
||||
this.rcn = rcn;
|
||||
}
|
||||
|
||||
public String getId() {
|
||||
return id;
|
||||
}
|
||||
|
||||
public void setId(String id) {
|
||||
this.id = id;
|
||||
}
|
||||
|
||||
public String getAcronym() {
|
||||
return acronym;
|
||||
}
|
||||
|
||||
public void setAcronym(String acronym) {
|
||||
this.acronym = acronym;
|
||||
}
|
||||
|
||||
public String getStatus() {
|
||||
return status;
|
||||
}
|
||||
|
||||
public void setStatus(String status) {
|
||||
this.status = status;
|
||||
}
|
||||
|
||||
public String getProgramme() {
|
||||
return programme;
|
||||
}
|
||||
|
||||
public void setProgramme(String programme) {
|
||||
this.programme = programme;
|
||||
}
|
||||
|
||||
public String getTopics() {
|
||||
return topics;
|
||||
}
|
||||
|
||||
public void setTopics(String topics) {
|
||||
this.topics = topics;
|
||||
}
|
||||
|
||||
public String getFrameworkProgramme() {
|
||||
return frameworkProgramme;
|
||||
}
|
||||
|
||||
public void setFrameworkProgramme(String frameworkProgramme) {
|
||||
this.frameworkProgramme = frameworkProgramme;
|
||||
}
|
||||
|
||||
public String getTitle() {
|
||||
return title;
|
||||
}
|
||||
|
||||
public void setTitle(String title) {
|
||||
this.title = title;
|
||||
}
|
||||
|
||||
public String getStartDate() {
|
||||
return startDate;
|
||||
}
|
||||
|
||||
public void setStartDate(String startDate) {
|
||||
this.startDate = startDate;
|
||||
}
|
||||
|
||||
public String getEndDate() {
|
||||
return endDate;
|
||||
}
|
||||
|
||||
public void setEndDate(String endDate) {
|
||||
this.endDate = endDate;
|
||||
}
|
||||
|
||||
public String getProjectUrl() {
|
||||
return projectUrl;
|
||||
}
|
||||
|
||||
public void setProjectUrl(String projectUrl) {
|
||||
this.projectUrl = projectUrl;
|
||||
}
|
||||
|
||||
public String getObjective() {
|
||||
return objective;
|
||||
}
|
||||
|
||||
public void setObjective(String objective) {
|
||||
this.objective = objective;
|
||||
}
|
||||
|
||||
public String getTotalCost() {
|
||||
return totalCost;
|
||||
}
|
||||
|
||||
public void setTotalCost(String totalCost) {
|
||||
this.totalCost = totalCost;
|
||||
}
|
||||
|
||||
public String getEcMaxContribution() {
|
||||
return ecMaxContribution;
|
||||
}
|
||||
|
||||
public void setEcMaxContribution(String ecMaxContribution) {
|
||||
this.ecMaxContribution = ecMaxContribution;
|
||||
}
|
||||
|
||||
public String getCall() {
|
||||
return call;
|
||||
}
|
||||
|
||||
public void setCall(String call) {
|
||||
this.call = call;
|
||||
}
|
||||
|
||||
public String getFundingScheme() {
|
||||
return fundingScheme;
|
||||
}
|
||||
|
||||
public void setFundingScheme(String fundingScheme) {
|
||||
this.fundingScheme = fundingScheme;
|
||||
}
|
||||
|
||||
public String getCoordinator() {
|
||||
return coordinator;
|
||||
}
|
||||
|
||||
public void setCoordinator(String coordinator) {
|
||||
this.coordinator = coordinator;
|
||||
}
|
||||
|
||||
public String getCoordinatorCountry() {
|
||||
return coordinatorCountry;
|
||||
}
|
||||
|
||||
public void setCoordinatorCountry(String coordinatorCountry) {
|
||||
this.coordinatorCountry = coordinatorCountry;
|
||||
}
|
||||
|
||||
public String getParticipants() {
|
||||
return participants;
|
||||
}
|
||||
|
||||
public void setParticipants(String participants) {
|
||||
this.participants = participants;
|
||||
}
|
||||
|
||||
public String getParticipantCountries() {
|
||||
return participantCountries;
|
||||
}
|
||||
|
||||
public void setParticipantCountries(String participantCountries) {
|
||||
this.participantCountries = participantCountries;
|
||||
}
|
||||
|
||||
public String getSubjects() {
|
||||
return subjects;
|
||||
}
|
||||
|
||||
public void setSubjects(String subjects) {
|
||||
this.subjects = subjects;
|
||||
}
|
||||
|
||||
}
|
||||
@ -1,5 +1,5 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.project.utils.model;
|
||||
package eu.dnetlib.dhp.actionmanager.project.utils;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
@ -1,46 +0,0 @@
|
||||
|
||||
package eu.dnetlib.dhp.actionmanager.project.utils.model;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import com.opencsv.bean.CsvBindByName;
|
||||
|
||||
/**
|
||||
* the mmodel for the projects csv file
|
||||
*/
|
||||
public class CSVProject implements Serializable {
|
||||
|
||||
@CsvBindByName(column = "id")
|
||||
private String id;
|
||||
|
||||
@CsvBindByName(column = "programme")
|
||||
private String programme;
|
||||
|
||||
@CsvBindByName(column = "topics")
|
||||
private String topics;
|
||||
|
||||
public String getId() {
|
||||
return id;
|
||||
}
|
||||
|
||||
public void setId(String id) {
|
||||
this.id = id;
|
||||
}
|
||||
|
||||
public String getProgramme() {
|
||||
return programme;
|
||||
}
|
||||
|
||||
public void setProgramme(String programme) {
|
||||
this.programme = programme;
|
||||
}
|
||||
|
||||
public String getTopics() {
|
||||
return topics;
|
||||
}
|
||||
|
||||
public void setTopics(String topics) {
|
||||
this.topics = topics;
|
||||
}
|
||||
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue