resolved conflicts

This commit is contained in:
Claudio Atzori 2019-10-25 09:45:12 +02:00
commit 4b331790e7
8 changed files with 77 additions and 82 deletions

View File

@ -15,7 +15,6 @@ public class Author implements Serializable {
// json containing a Citation or Statistics
private String value;
public String getName() {
return name;
}

View File

@ -17,9 +17,6 @@ public abstract class OafEntity extends Oaf implements Serializable {
private String dateoftransformation;
//TODO remove this field
private List<OafEntity> children;
private List<ExtraInfo> extraInfo;
private OAIProvenance oaiprovenance;
@ -79,15 +76,6 @@ public abstract class OafEntity extends Oaf implements Serializable {
return this;
}
public List<OafEntity> getChildren() {
return children;
}
public OafEntity setChildren(List<OafEntity> children) {
this.children = children;
return this;
}
public List<ExtraInfo> getExtraInfo() {
return extraInfo;
}

View File

@ -16,7 +16,7 @@ public class OriginDescription implements Serializable {
private String metadataNamespace;
private OriginDescription originDescription;
//private OriginDescription originDescription;
public String getHarvestDate() {
return harvestDate;
@ -72,12 +72,12 @@ public class OriginDescription implements Serializable {
return this;
}
public OriginDescription getOriginDescription() {
return originDescription;
}
public OriginDescription setOriginDescription(OriginDescription originDescription) {
this.originDescription = originDescription;
return this;
}
// public OriginDescription getOriginDescription() {
// return originDescription;
// }
//
// public OriginDescription setOriginDescription(OriginDescription originDescription) {
// this.originDescription = originDescription;
// return this;
// }
}

View File

@ -9,7 +9,7 @@ public class Qualifier implements Serializable {
private String schemeid;
private String schemename;
private DataInfo dataInfo;
// private DataInfo dataInfo;
public String getClassid() {
return classid;
@ -47,12 +47,12 @@ public class Qualifier implements Serializable {
return this;
}
public DataInfo getDataInfo() {
return dataInfo;
}
public Qualifier setDataInfo(DataInfo dataInfo) {
this.dataInfo = dataInfo;
return this;
}
// public DataInfo getDataInfo() {
// return dataInfo;
// }
//
// public Qualifier setDataInfo(DataInfo dataInfo) {
// this.dataInfo = dataInfo;
// return this;
// }
}

View File

@ -64,6 +64,7 @@ public class ProtoConverter implements Serializable {
final DatasourceProtos.Datasource.Metadata m = oaf.getEntity().getDatasource().getMetadata();
final Organization org = setOaf(new Organization(), oaf);
return setEntity(org, oaf);
//TODO set org fields
}
@ -71,11 +72,10 @@ public class ProtoConverter implements Serializable {
final DatasourceProtos.Datasource.Metadata m = oaf.getEntity().getDatasource().getMetadata();
final Datasource datasource = setOaf(new Datasource(), oaf);
return setEntity(datasource, oaf)
.setAccessinfopackage(m.getAccessinfopackageCount() > 0 ?
m.getAccessinfopackageList()
.setAccessinfopackage(m.getAccessinfopackageList()
.stream()
.map(ProtoUtils::mapStringField)
.collect(Collectors.toList()) : null)
.collect(Collectors.toList()))
.setCertificates(mapStringField(m.getCertificates()))
.setCitationguidelineurl(mapStringField(m.getCitationguidelineurl()))
.setContactemail(mapStringField(m.getContactemail()))
@ -94,36 +94,32 @@ public class ProtoConverter implements Serializable {
.setLogourl(mapStringField(m.getLogourl()))
.setMissionstatementurl(mapStringField(m.getMissionstatementurl()))
.setNamespaceprefix(mapStringField(m.getNamespaceprefix()))
.setOdcontenttypes(m.getOdcontenttypesCount() > 0 ?
m.getOdcontenttypesList()
.setOdcontenttypes(m.getOdcontenttypesList()
.stream()
.map(ProtoUtils::mapStringField)
.collect(Collectors.toList()) : null)
.setOdlanguages(m.getOdlanguagesCount() > 0 ?
m.getOdlanguagesList()
.collect(Collectors.toList()))
.setOdlanguages(m.getOdlanguagesList()
.stream()
.map(ProtoUtils::mapStringField)
.collect(Collectors.toList()) : null)
.collect(Collectors.toList()))
.setOdnumberofitems(mapStringField(m.getOdnumberofitems()))
.setOdnumberofitemsdate(mapStringField(m.getOdnumberofitemsdate()))
.setOdpolicies(mapStringField(m.getOdpolicies()))
.setOfficialname(mapStringField(m.getOfficialname()))
.setOpenairecompatibility(mapQualifier(m.getOpenairecompatibility()))
.setPidsystems(mapStringField(m.getPidsystems()))
.setPolicies(m.getPoliciesCount() > 0 ?
m.getPoliciesList()
.setPolicies(m.getPoliciesList()
.stream()
.map(ProtoUtils::mapKV)
.collect(Collectors.toList()) : null)
.collect(Collectors.toList()))
.setQualitymanagementkind(mapStringField(m.getQualitymanagementkind()))
.setReleaseenddate(mapStringField(m.getReleaseenddate()))
.setServiceprovider(mapBoolField(m.getServiceprovider()))
.setReleasestartdate(mapStringField(m.getReleasestartdate()))
.setSubjects(m.getSubjectsCount() > 0 ?
m.getSubjectsList()
.setSubjects(m.getSubjectsList()
.stream()
.map(ProtoUtils::mapStructuredProperty)
.collect(Collectors.toList()) : null)
.collect(Collectors.toList()))
.setVersioning(mapBoolField(m.getVersioning()))
.setWebsiteurl(mapStringField(m.getWebsiteurl()))
.setJournal(mapJournal(m.getJournal()));
@ -151,16 +147,14 @@ public class ProtoConverter implements Serializable {
.setFundedamount(m.getFundedamount())
.setTotalcost(m.getTotalcost())
.setKeywords(mapStringField(m.getKeywords()))
.setSubjects(m.getSubjectsCount() > 0 ?
m.getSubjectsList().stream()
.setSubjects(m.getSubjectsList().stream()
.map(sp -> mapStructuredProperty(sp))
.collect(Collectors.toList()) : null)
.collect(Collectors.toList()))
.setTitle(mapStringField(m.getTitle()))
.setWebsiteurl(mapStringField(m.getWebsiteurl()))
.setFundingtree(m.getFundingtreeCount() > 0 ?
m.getFundingtreeList().stream()
.setFundingtree(m.getFundingtreeList().stream()
.map(f -> mapStringField(f))
.collect(Collectors.toList()) : null)
.collect(Collectors.toList()))
.setJsonextrainfo(mapStringField(m.getJsonextrainfo()))
.setSummary(mapStringField(m.getSummary()))
.setOptional1(mapStringField(m.getOptional1()))

View File

@ -63,8 +63,8 @@ public class ProtoUtils {
.setClassid(q.getClassid())
.setClassname(q.getClassname())
.setSchemeid(q.getSchemeid())
.setSchemename(q.getSchemename())
.setDataInfo(q.hasDataInfo() ? mapDataInfo(q.getDataInfo()) : null);
.setSchemename(q.getSchemename());
//.setDataInfo(q.hasDataInfo() ? mapDataInfo(q.getDataInfo()) : null);
}
public static StructuredProperty mapStructuredProperty(FieldTypeProtos.StructuredProperty sp) {
@ -95,8 +95,8 @@ public class ProtoUtils {
.setIdentifier(originDescription.getIdentifier())
.setDatestamp(originDescription.getDatestamp())
.setMetadataNamespace(originDescription.getMetadataNamespace());
if (originDescription.hasOriginDescription())
originDescriptionResult.setOriginDescription(mapOriginalDescription(originDescription.getOriginDescription()));
// if (originDescription.hasOriginDescription())
// originDescriptionResult.setOriginDescription(mapOriginalDescription(originDescription.getOriginDescription()));
return originDescriptionResult;
}

View File

@ -1,15 +1,21 @@
package eu.dnetlib.dhp.graph;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.Publication;
import org.apache.hadoop.io.Text;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoder;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import scala.Tuple2;
import javax.xml.crypto.Data;
public class SparkGraphImporterJob {
@ -30,20 +36,24 @@ public class SparkGraphImporterJob {
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
final JavaRDD<Tuple2<String, String>> inputRDD = sc.sequenceFile("file:///home/sandro/part-m-00000", Text.class, Text.class).map(item -> new Tuple2<>(item._1.toString(), item._2.toString()));
final String path = "file:///home/sandro/part-m-00000";
final JavaRDD<Tuple2<String, String>> inputRDD = sc.sequenceFile(path, Text.class, Text.class)
.map(item -> new Tuple2<>(item._1.toString(), item._2.toString()));
Tuple2<String, String> item = inputRDD
final JavaRDD<Datasource> datasources = inputRDD
.filter(s -> s._1().split("@")[2].equalsIgnoreCase("body"))
.first();
System.out.println(item._1());
System.out.println(item._2());
.map(Tuple2::_2)
.map(ProtoConverter::convert)
.filter(s-> s instanceof Datasource)
.map(s->(Datasource)s);
final Encoder<Datasource> encoder = Encoders.bean(Datasource.class);
final Dataset<Datasource> mdstore = spark.createDataset(datasources.rdd(), encoder);
// .map(Tuple2::_2)
// .map(ProtoConverter::convert)
// .mapToPair((PairFunction<Oaf, String,Integer>) s-> new Tuple2<String, Integer>(s.getClass().getName(),1))
// .reduceByKey(Integer::sum).collect().forEach(System.out::println);
System.out.println(mdstore.count());
//
//
// .filter(s -> s instanceof Publication)

View File

@ -1,5 +1,6 @@
package eu.dnetlib.dhp.graph;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import org.apache.commons.io.IOUtils;
@ -23,6 +24,9 @@ public class ProtoConverterTest {
System.out.println(ds.getId());
ObjectMapper mapper = new ObjectMapper();
System.out.println(mapper.writeValueAsString(result));
}