pispis
/
dnet-hadoop
forked from antonis.lempesis/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

merged from master

This commit is contained in:
Claudio Atzori 2020-01-17 14:25:57 +01:00
parent 63c0db4ff8 749b0660ab
commit 1cd6899480
55 changed files with 3285 additions and 74 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.gitignore vendored
View File

@ -18,4 +18,5 @@
/*/build
/build
spark-warehouse
/dhp-workflows/dhp-graph-mapper/job-override.properties
/*/*/job-override.properties

1
dhp-build/dhp-build-assembly-resources/pom.xml
View File

@ -17,6 +17,7 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>${maven.compiler.plugin.version}</version>
</plugin>
</plugins>
</build>

1
dhp-build/dhp-build-properties-maven-plugin/pom.xml
View File

@ -53,6 +53,7 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>${maven.compiler.plugin.version}</version>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>

10
dhp-common/pom.xml
View File

@ -17,6 +17,10 @@
<groupId>commons-cli</groupId>
<artifactId>commons-cli</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
<artifactId>commons-lang3</artifactId>
@ -29,21 +33,15 @@
<groupId>javax.persistence</groupId>
<artifactId>javax.persistence-api</artifactId>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
</dependency>
<!-- https://mvnrepository.com/artifact/com.rabbitmq/amqp-client -->
<dependency>
<groupId>com.rabbitmq</groupId>
<artifactId>amqp-client</artifactId>
</dependency>
<dependency>
<groupId>commons-io</groupId>
<artifactId>commons-io</artifactId>
</dependency>
</dependencies>
</project>

41
dhp-common/src/main/java/eu/dnetlib/dhp/application/ArgumentApplicationParser.java
View File

@ -2,17 +2,25 @@ package eu.dnetlib.dhp.application;
import com.fasterxml.jackson.databind.ObjectMapper;
import org.apache.commons.cli.*;
import org.apache.commons.codec.binary.Base64;
import org.apache.commons.io.IOUtils;
import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.Serializable;
import java.util.Arrays;
import java.util.HashMap;
import java.util.Map;
import java.io.StringWriter;
import java.util.*;
import java.util.zip.GZIPInputStream;
import java.util.zip.GZIPOutputStream;
import java.util.zip.Inflater;
public class ArgumentApplicationParser implements Serializable {
private final Options options = new Options();
private final Map<String, String> objectMap = new HashMap<>();
private final List<String> compressedValues = new ArrayList<>();
public ArgumentApplicationParser(final String json_configuration) throws Exception {
final ObjectMapper mapper = new ObjectMapper();
final OptionsParameter[] configuration = mapper.readValue(json_configuration, OptionsParameter[].class);
@ -29,6 +37,9 @@ public class ArgumentApplicationParser implements Serializable {
final Option o = new Option(conf.getParamName(), true, conf.getParamDescription());
o.setLongOpt(conf.getParamLongName());
o.setRequired(conf.isParamRequired());
if (conf.isCompressed()) {
compressedValues.add(conf.getParamLongName());
}
return o;
}).forEach(options::addOption);
@ -38,10 +49,32 @@ public class ArgumentApplicationParser implements Serializable {
}
public static String decompressValue(final String abstractCompressed) {
try {
byte[] byteArray = Base64.decodeBase64(abstractCompressed.getBytes());
GZIPInputStream gis = new GZIPInputStream(new ByteArrayInputStream(byteArray));
final StringWriter stringWriter = new StringWriter();
IOUtils.copy(gis, stringWriter);
return stringWriter.toString();
} catch (Throwable e) {
System.out.println("Wrong value to decompress:" + abstractCompressed);
throw new RuntimeException(e);
}
}
public static String compressArgument(final String value) throws Exception{
ByteArrayOutputStream out = new ByteArrayOutputStream();
GZIPOutputStream gzip = new GZIPOutputStream(out);
gzip.write(value.getBytes());
gzip.close();
return java.util.Base64.getEncoder().encodeToString(out.toByteArray());
}
public void parseArgument(final String[] args) throws Exception {
CommandLineParser parser = new BasicParser();
CommandLine cmd = parser.parse(options, args);
Arrays.stream(cmd.getOptions()).forEach(it -> objectMap.put(it.getLongOpt(), it.getValue()));
Arrays.stream(cmd.getOptions()).forEach(it -> objectMap.put(it.getLongOpt(), compressedValues.contains(it.getLongOpt())? decompressValue(it.getValue()): it.getValue()));
}
public String get(final String key) {

9
dhp-common/src/main/java/eu/dnetlib/dhp/application/OptionsParameter.java
View File

@ -7,6 +7,7 @@ public class OptionsParameter {
private String paramLongName;
private String paramDescription;
private boolean paramRequired;
private boolean compressed;
public OptionsParameter() {
}
@ -26,4 +27,12 @@ public class OptionsParameter {
public boolean isParamRequired() {
return paramRequired;
}
public boolean isCompressed() {
return compressed;
}
public void setCompressed(boolean compressed) {
this.compressed = compressed;
}
}

10
dhp-common/src/test/java/eu/dnetlib/dhp/application/ArgumentApplicationParserTest.java
View File

@ -3,6 +3,10 @@ package eu.dnetlib.dhp.application;
import org.apache.commons.io.IOUtils;
import org.junit.Test;
import java.io.ByteArrayOutputStream;
import java.util.Base64;
import java.util.zip.GZIPOutputStream;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertNotNull;
@ -24,6 +28,7 @@ public class ArgumentApplicationParserTest {
"-ro", "value7",
"-rr", "value8",
"-w", "value9",
"-cc", ArgumentApplicationParser.compressArgument(jsonConfiguration)
});
assertNotNull(parser.get("hdfsPath"));
assertNotNull(parser.get("apidescriptor"));
@ -45,7 +50,12 @@ public class ArgumentApplicationParserTest {
assertEquals("value7", parser.get("rabbitOngoingQueue"));
assertEquals("value8", parser.get("rabbitReportQueue"));
assertEquals("value9", parser.get("workflowId"));
assertEquals(jsonConfiguration, parser.get("ccCoco"));
}
}

21
dhp-common/src/test/resources/eu/dnetlib/application/parameters.json
View File

@ -1,12 +1,13 @@
[
{"paramName":"p", "paramLongName":"hdfsPath", "paramDescription": "the path where storing the sequential file", "paramRequired": true},
{"paramName":"a", "paramLongName":"apidescriptor", "paramDescription": "the JSON encoding of the API Descriptor", "paramRequired": true},
{"paramName":"n", "paramLongName":"namenode", "paramDescription": "the Name Node URI", "paramRequired": true},
{"paramName":"u", "paramLongName":"userHDFS", "paramDescription": "the user wich create the hdfs seq file", "paramRequired": true},
{"paramName":"ru", "paramLongName":"rabbitUser", "paramDescription": "the user to connect with RabbitMq for messaging", "paramRequired": true},
{"paramName":"rp", "paramLongName":"rabbitPassWord", "paramDescription": "the password to connect with RabbitMq for messaging", "paramRequired": true},
{"paramName":"rh", "paramLongName":"rabbitHost", "paramDescription": "the host of the RabbitMq server", "paramRequired": true},
{"paramName":"ro", "paramLongName":"rabbitOngoingQueue", "paramDescription": "the name of the ongoing queue", "paramRequired": true},
{"paramName":"rr", "paramLongName":"rabbitReportQueue", "paramDescription": "the name of the report queue", "paramRequired": true},
{"paramName":"w", "paramLongName":"workflowId", "paramDescription": "the identifier of the dnet Workflow", "paramRequired": true}
{"paramName":"p", "paramLongName":"hdfsPath", "paramDescription": "the path where storing the sequential file", "paramRequired": true},
{"paramName":"a", "paramLongName":"apidescriptor", "paramDescription": "the JSON encoding of the API Descriptor", "paramRequired": true},
{"paramName":"n", "paramLongName":"namenode", "paramDescription": "the Name Node URI", "paramRequired": true},
{"paramName":"u", "paramLongName":"userHDFS", "paramDescription": "the user wich create the hdfs seq file", "paramRequired": true},
{"paramName":"ru", "paramLongName":"rabbitUser", "paramDescription": "the user to connect with RabbitMq for messaging", "paramRequired": true},
{"paramName":"rp", "paramLongName":"rabbitPassWord", "paramDescription": "the password to connect with RabbitMq for messaging", "paramRequired": true},
{"paramName":"rh", "paramLongName":"rabbitHost", "paramDescription": "the host of the RabbitMq server", "paramRequired": true},
{"paramName":"ro", "paramLongName":"rabbitOngoingQueue", "paramDescription": "the name of the ongoing queue", "paramRequired": true},
{"paramName":"rr", "paramLongName":"rabbitReportQueue", "paramDescription": "the name of the report queue", "paramRequired": true},
{"paramName":"w", "paramLongName":"workflowId", "paramDescription": "the identifier of the dnet Workflow", "paramRequired": true},
{"paramName":"cc", "paramLongName":"ccCoco", "paramDescription": "the identifier of the dnet Workflow", "compressed":true,"paramRequired": true}
]

19
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Context.java
View File

@ -23,4 +23,23 @@ public class Context implements Serializable {
public void setDataInfo(List<DataInfo> dataInfo) {
this.dataInfo = dataInfo;
}
@Override
public int hashCode() {
return id ==null? 0 : id.hashCode();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
Context other = (Context) obj;
return id.equals(other.getId());
}
}

24
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Dataset.java
View File

@ -19,7 +19,7 @@ public class Dataset extends Result implements Serializable {
private List<GeoLocation> geolocation;
public Field<String> getStoragedate() {
public Field<String> getStoragedate() {
return storagedate;
}
@ -74,4 +74,26 @@ public class Dataset extends Result implements Serializable {
public void setGeolocation(List<GeoLocation> geolocation) {
this.geolocation = geolocation;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
final Dataset d = (Dataset) e;
storagedate = d.getStoragedate() != null && compareTrust(this, e)<0? d.getStoragedate() : storagedate;
device= d.getDevice() != null && compareTrust(this, e)<0? d.getDevice() : device;
size= d.getSize() != null && compareTrust(this, e)<0? d.getSize() : size;
version= d.getVersion() != null && compareTrust(this, e)<0? d.getVersion() : version;
lastmetadataupdate= d.getLastmetadataupdate() != null && compareTrust(this, e)<0? d.getLastmetadataupdate() :lastmetadataupdate;
metadataversionnumber= d.getMetadataversionnumber() != null && compareTrust(this, e)<0? d.getMetadataversionnumber() : metadataversionnumber;
geolocation = mergeLists(geolocation, d.getGeolocation());
mergeOAFDataInfo(d);
}
}

65
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Datasource.java
View File

@ -78,7 +78,7 @@ public class Datasource extends OafEntity implements Serializable {
private Field<String> certificates;
private List< KeyValue> policies;
private List<KeyValue> policies;
private Journal journal;
@ -361,4 +361,67 @@ public class Datasource extends OafEntity implements Serializable {
public void setJournal(Journal journal) {
this.journal = journal;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
Datasource d = (Datasource)e;
datasourcetype = d.getDatasourcetype() != null && compareTrust(this, e)<0? d.getDatasourcetype() : datasourcetype;
openairecompatibility = d.getOpenairecompatibility() != null && compareTrust(this, e)<0? d.getOpenairecompatibility() : openairecompatibility;
officialname = d.getOfficialname() != null && compareTrust(this, e)<0? d.getOfficialname() : officialname;
englishname = d.getEnglishname() != null && compareTrust(this, e)<0? d.getEnglishname() : officialname;
websiteurl = d.getWebsiteurl() != null && compareTrust(this, e)<0? d.getWebsiteurl() : websiteurl;
logourl = d.getLogourl() != null && compareTrust(this, e)<0? d.getLogourl() : getLogourl();
contactemail = d.getContactemail() != null && compareTrust(this, e)<0? d.getContactemail() : contactemail;
namespaceprefix = d.getNamespaceprefix() != null && compareTrust(this, e)<0? d.getNamespaceprefix() : namespaceprefix;
latitude = d.getLatitude() != null && compareTrust(this, e)<0? d.getLatitude() : latitude;
longitude = d.getLongitude() != null && compareTrust(this, e)<0? d.getLongitude() : longitude;
dateofvalidation = d.getDateofvalidation() != null && compareTrust(this, e)<0? d.getDateofvalidation() : dateofvalidation;
description = d.getDescription() != null && compareTrust(this, e)<0? d.getDescription() : description;
subjects = mergeLists(subjects, d.getSubjects());
// opendoar specific fields (od*)
odnumberofitems = d.getOdnumberofitems() != null && compareTrust(this, e)<0? d.getOdnumberofitems() : odnumberofitems;
odnumberofitemsdate = d.getOdnumberofitemsdate() != null && compareTrust(this, e)<0? d.getOdnumberofitemsdate() : odnumberofitemsdate;
odpolicies = d.getOdpolicies() != null && compareTrust(this, e)<0? d.getOdpolicies() : odpolicies;
odlanguages = mergeLists(odlanguages, d.getOdlanguages());
odcontenttypes = mergeLists(odcontenttypes, d.getOdcontenttypes());
accessinfopackage = mergeLists(accessinfopackage, d.getAccessinfopackage());
// re3data fields
releasestartdate = d.getReleasestartdate() != null && compareTrust(this, e)<0? d.getReleasestartdate() : releasestartdate;
releaseenddate = d.getReleaseenddate() != null && compareTrust(this, e)<0? d.getReleaseenddate() : releaseenddate;
missionstatementurl = d.getMissionstatementurl() != null && compareTrust(this, e)<0? d.getMissionstatementurl() : missionstatementurl;
dataprovider = d.getDataprovider() != null && compareTrust(this, e)<0? d.getDataprovider() : dataprovider;
serviceprovider = d.getServiceprovider() != null && compareTrust(this, e)<0? d.getServiceprovider() : serviceprovider;
// {open, restricted or closed}
databaseaccesstype = d.getDatabaseaccesstype() != null && compareTrust(this, e)<0? d.getDatabaseaccesstype() : databaseaccesstype;
// {open, restricted or closed}
datauploadtype = d.getDatauploadtype() != null && compareTrust(this, e)<0? d.getDatauploadtype() : datauploadtype;
// {feeRequired, registration, other}
databaseaccessrestriction = d.getDatabaseaccessrestriction() != null && compareTrust(this, e)<0? d.getDatabaseaccessrestriction() : databaseaccessrestriction;
// {feeRequired, registration, other}
datauploadrestriction = d.getDatauploadrestriction() != null && compareTrust(this, e)<0? d.getDatauploadrestriction() : datauploadrestriction;
versioning = d.getVersioning() != null && compareTrust(this, e)<0? d.getVersioning() : versioning;
citationguidelineurl = d.getCitationguidelineurl() != null && compareTrust(this, e)<0? d.getCitationguidelineurl() : citationguidelineurl;
//{yes, no, unknown}
qualitymanagementkind = d.getQualitymanagementkind() != null && compareTrust(this, e)<0? d.getQualitymanagementkind() : qualitymanagementkind;
pidsystems = d.getPidsystems() != null && compareTrust(this, e)<0? d.getPidsystems() : pidsystems;
certificates = d.getCertificates() != null && compareTrust(this, e)<0? d.getCertificates() : certificates;
policies = mergeLists(policies, d.getPolicies());
journal = d.getJournal() != null && compareTrust(this, e)<0? d.getJournal() : journal;
mergeOAFDataInfo(e);
}
}

17
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Field.java
View File

@ -23,4 +23,21 @@ public class Field<T> implements Serializable {
public void setDataInfo(DataInfo dataInfo) {
this.dataInfo = dataInfo;
}
@Override
public int hashCode() {
return getValue() == null ? 0 : getValue().hashCode();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
Field<T> other = (Field<T>) obj;
return getValue().equals(other.getValue());
}
}

33
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/GeoLocation.java
View File

@ -1,5 +1,7 @@
package eu.dnetlib.dhp.schema.oaf;
import org.apache.commons.lang3.StringUtils;
import java.io.Serializable;
public class GeoLocation implements Serializable {
@ -33,4 +35,35 @@ public class GeoLocation implements Serializable {
public void setPlace(String place) {
this.place = place;
}
public boolean isBlank() {
return StringUtils.isBlank(point) &&
StringUtils.isBlank(box) &&
StringUtils.isBlank(place);
}
public String toComparableString() {
return isBlank()?"":String.format("%s::%s%s", point != null ? point.toLowerCase() : "", box != null ? box.toLowerCase() : "", place != null ? place.toLowerCase() : "");
}
@Override
public int hashCode() {
return toComparableString().hashCode();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
GeoLocation other = (GeoLocation) obj;
return toComparableString()
.equals(other.toComparableString());
}
}

30
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Instance.java
View File

@ -85,4 +85,34 @@ public class Instance implements Serializable {
public void setDateofacceptance(Field<String> dateofacceptance) {
this.dateofacceptance = dateofacceptance;
}
public String toComparableString(){
return String.format("%s::%s::%s::%s",
hostedby != null && hostedby.getKey()!= null ? hostedby.getKey().toLowerCase() : "",
accessright!= null && accessright.getClassid()!= null ? accessright.getClassid() : "",
instancetype!= null && instancetype.getClassid()!= null ? instancetype.getClassid() : "",
url != null ? url:"");
}
@Override
public int hashCode() {
return toComparableString().hashCode();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
Instance other = (Instance) obj;
return toComparableString()
.equals(other.toComparableString());
}
}

29
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/KeyValue.java
View File

@ -1,5 +1,7 @@
package eu.dnetlib.dhp.schema.oaf;
import org.apache.commons.lang3.StringUtils;
import java.io.Serializable;
public class KeyValue implements Serializable {
@ -33,4 +35,31 @@ public class KeyValue implements Serializable {
public void setDataInfo(DataInfo dataInfo) {
this.dataInfo = dataInfo;
}
public String toComparableString() {
return isBlank()?"":String.format("%s::%s", key != null ? key.toLowerCase() : "", value != null ? value.toLowerCase() : "");
}
public boolean isBlank() {
return StringUtils.isBlank(key) && StringUtils.isBlank(value);
}
@Override
public int hashCode() {
return toComparableString().hashCode();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
KeyValue other = (KeyValue) obj;
return toComparableString().equals(other.toComparableString());
}
}

27
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Oaf.java
View File

@ -1,8 +1,5 @@
package eu.dnetlib.dhp.schema.oaf;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import java.io.Serializable;
public abstract class Oaf implements Serializable {
@ -27,13 +24,23 @@ public abstract class Oaf implements Serializable {
this.lastupdatetimestamp = lastupdatetimestamp;
}
@Override
public String toString() {
try {
return new ObjectMapper().writeValueAsString(this);
} catch (JsonProcessingException e) {
throw new RuntimeException(e);
}
public void mergeOAFDataInfo(Oaf e) {
if (e.getDataInfo()!= null && compareTrust(this,e)<0)
dataInfo = e.getDataInfo();
}
protected String extractTrust(Oaf e) {
if (e == null || e.getDataInfo()== null || e.getDataInfo().getTrust()== null)
return "0.0";
return e.getDataInfo().getTrust();
}
protected int compareTrust(Oaf a, Oaf b) {
return extractTrust(a).compareTo(extractTrust(b));
}
}

35
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/OafEntity.java
View File

@ -1,7 +1,8 @@
package eu.dnetlib.dhp.schema.oaf;
import java.io.Serializable;
import java.util.List;
import java.util.*;
import java.util.stream.Collectors;
public abstract class OafEntity extends Oaf implements Serializable {
@ -84,4 +85,36 @@ public abstract class OafEntity extends Oaf implements Serializable {
public void setOaiprovenance(OAIProvenance oaiprovenance) {
this.oaiprovenance = oaiprovenance;
}
public void mergeFrom(OafEntity e) {
if (e == null)
return;
originalId = mergeLists(originalId, e.getOriginalId());
collectedfrom = mergeLists(collectedfrom, e.getCollectedfrom());
pid = mergeLists(pid, e.getPid());
if (e.getDateofcollection() != null && compareTrust(this, e) < 0)
dateofcollection = e.getDateofcollection();
if (e.getDateoftransformation() != null && compareTrust(this, e) < 0)
dateoftransformation = e.getDateoftransformation();
extraInfo = mergeLists(extraInfo, e.getExtraInfo());
if (e.getOaiprovenance() != null && compareTrust(this, e) < 0)
oaiprovenance = e.getOaiprovenance();
}
protected <T> List<T> mergeLists(final List<T>... lists) {
return Arrays.stream(lists).filter(Objects::nonNull).flatMap(List::stream).distinct().collect(Collectors.toList());
}
}

24
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Organization.java
View File

@ -164,4 +164,28 @@ public class Organization extends OafEntity implements Serializable {
public void setCountry(Qualifier country) {
this.country = country;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
final Organization o = (Organization) e;
legalshortname = o.getLegalshortname() != null && compareTrust(this, e)<0? o.getLegalshortname() : legalshortname;
legalname = o.getLegalname() != null && compareTrust(this, e)<0 ? o.getLegalname() : legalname;
alternativeNames = mergeLists(o.getAlternativeNames(), alternativeNames);
websiteurl = o.getWebsiteurl() != null && compareTrust(this, e)<0? o.getWebsiteurl() : websiteurl;
logourl = o.getLogourl() != null && compareTrust(this, e)<0? o.getLogourl() : logourl;
eclegalbody = o.getEclegalbody() != null && compareTrust(this, e)<0? o.getEclegalbody() : eclegalbody;
eclegalperson = o.getEclegalperson() != null && compareTrust(this, e)<0? o.getEclegalperson() : eclegalperson;
ecnonprofit = o.getEcnonprofit() != null && compareTrust(this, e)<0? o.getEcnonprofit() : ecnonprofit;
ecresearchorganization = o.getEcresearchorganization() != null && compareTrust(this, e)<0? o.getEcresearchorganization() : ecresearchorganization;
echighereducation = o.getEchighereducation() != null && compareTrust(this, e)<0? o.getEchighereducation() : echighereducation;
ecinternationalorganizationeurinterests = o.getEcinternationalorganizationeurinterests() != null && compareTrust(this, e)<0? o.getEcinternationalorganizationeurinterests() : ecinternationalorganizationeurinterests;
ecinternationalorganization = o.getEcinternationalorganization() != null && compareTrust(this, e)<0? o.getEcinternationalorganization() : ecinternationalorganization;
ecenterprise = o.getEcenterprise() != null && compareTrust(this, e)<0? o.getEcenterprise() :ecenterprise;
ecsmevalidated = o.getEcsmevalidated() != null && compareTrust(this, e)<0? o.getEcsmevalidated() :ecsmevalidated;
ecnutscode = o.getEcnutscode() != null && compareTrust(this, e)<0? o.getEcnutscode() :ecnutscode;
country = o.getCountry() != null && compareTrust(this, e)<0 ? o.getCountry() :country;
mergeOAFDataInfo(o);
}
}

12
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/OtherResearchProduct.java
View File

@ -34,4 +34,16 @@ public class OtherResearchProduct extends Result implements Serializable {
public void setTool(List<Field<String>> tool) {
this.tool = tool;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
OtherResearchProduct o = (OtherResearchProduct)e;
contactperson = mergeLists(contactperson, o.getContactperson());
contactgroup = mergeLists(contactgroup, o.getContactgroup());
tool = mergeLists(tool, o.getTool());
mergeOAFDataInfo(e);
}
}

35
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Project.java
View File

@ -264,4 +264,39 @@ public class Project extends OafEntity implements Serializable {
public void setFundedamount(Float fundedamount) {
this.fundedamount = fundedamount;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
Project p = (Project)e;
websiteurl= p.getWebsiteurl()!= null && compareTrust(this,e)<0?p.getWebsiteurl():websiteurl;
code= p.getCode()!=null && compareTrust(this,e)<0?p.getCode():code;
acronym= p.getAcronym()!= null && compareTrust(this,e)<0?p.getAcronym():acronym;
title= p.getTitle()!= null && compareTrust(this,e)<0?p.getTitle():title;
startdate= p.getStartdate()!=null && compareTrust(this,e)<0?p.getStartdate():startdate;
enddate= p.getEnddate()!=null && compareTrust(this,e)<0?p.getEnddate():enddate;
callidentifier= p.getCallidentifier()!=null && compareTrust(this,e)<0?p.getCallidentifier():callidentifier;
keywords= p.getKeywords()!=null && compareTrust(this,e)<0?p.getKeywords():keywords;
duration= p.getDuration()!=null && compareTrust(this,e)<0?p.getDuration():duration;
ecsc39= p.getEcsc39()!=null && compareTrust(this,e)<0?p.getEcsc39():ecsc39;
oamandatepublications= p.getOamandatepublications()!=null && compareTrust(this,e)<0?p.getOamandatepublications():oamandatepublications;
ecarticle29_3= p.getEcarticle29_3()!=null && compareTrust(this,e)<0?p.getEcarticle29_3():ecarticle29_3;
subjects= mergeLists(subjects, p.getSubjects());
fundingtree= mergeLists(fundingtree, p.getFundingtree());
contracttype= p.getContracttype()!=null && compareTrust(this,e)<0?p.getContracttype():contracttype;
optional1= p.getOptional1()!=null && compareTrust(this,e)<0?p.getOptional1():optional1;
optional2= p.getOptional2()!=null && compareTrust(this,e)<0?p.getOptional2():optional2;
jsonextrainfo= p.getJsonextrainfo()!=null && compareTrust(this,e)<0?p.getJsonextrainfo():jsonextrainfo;
contactfullname= p.getContactfullname()!=null && compareTrust(this,e)<0?p.getContactfullname():contactfullname;
contactfax= p.getContactfax()!=null && compareTrust(this,e)<0?p.getContactfax():contactfax;
contactphone= p.getContactphone()!=null && compareTrust(this,e)<0?p.getContactphone():contactphone;
contactemail= p.getContactemail()!=null && compareTrust(this,e)<0?p.getContactemail():contactemail;
summary= p.getSummary()!=null && compareTrust(this,e)<0?p.getSummary():summary;
currency= p.getCurrency()!=null && compareTrust(this,e)<0?p.getCurrency():currency;
totalcost= p.getTotalcost()!=null && compareTrust(this,e)<0?p.getTotalcost():totalcost;
fundedamount= p.getFundedamount()!= null && compareTrust(this,e)<0?p.getFundedamount():fundedamount;
mergeOAFDataInfo(e);
}
}

13
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Publication.java
View File

@ -14,4 +14,17 @@ public class Publication extends Result implements Serializable {
public void setJournal(Journal journal) {
this.journal = journal;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
Publication p = (Publication) e;
if (p.getJournal() != null && compareTrust(this, e)<0)
journal = p.getJournal();
mergeOAFDataInfo(e);
}
}

35
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Qualifier.java
View File

@ -1,5 +1,7 @@
package eu.dnetlib.dhp.schema.oaf;
import org.apache.commons.lang3.StringUtils;
import java.io.Serializable;
public class Qualifier implements Serializable {
@ -40,4 +42,37 @@ public class Qualifier implements Serializable {
public void setSchemename(String schemename) {
this.schemename = schemename;
}
public String toComparableString() {
return isBlank()?"": String.format("%s::%s::%s::%s",
classid != null ? classid : "",
classname != null ? classname : "",
schemeid != null ? schemeid : "",
schemename != null ? schemename : "");
}
public boolean isBlank() {
return StringUtils.isBlank(classid) &&
StringUtils.isBlank(classname) &&
StringUtils.isBlank(schemeid) &&
StringUtils.isBlank(schemename);
}
@Override
public int hashCode() {
return toComparableString().hashCode();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
Qualifier other = (Qualifier) obj;
return toComparableString()
.equals(other.toComparableString());
}
}

103
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Result.java
View File

@ -1,7 +1,10 @@
package eu.dnetlib.dhp.schema.oaf;
import org.apache.commons.lang3.StringUtils;
import java.io.Serializable;
import java.util.List;
import java.util.*;
import java.util.stream.Collectors;
public abstract class Result extends OafEntity implements Serializable {
@ -12,35 +15,35 @@ public abstract class Result extends OafEntity implements Serializable {
// common fields
private Qualifier language;
private List<Qualifier> country;
private List<StructuredProperty> subject;
private List<StructuredProperty> title;
private List<StructuredProperty> relevantdate;
private List<Field<String>> description;
private Field<String> dateofacceptance;
private Field<String> publisher;
private Field<String> embargoenddate;
private List<Field<String>> source;
private List<Field<String>> fulltext; // remove candidate
private List<Field<String>> format;
private List<Field<String>> contributor;
private Qualifier resourcetype;
private List<Field<String>> coverage;
private Field<String> refereed; //peer-review status
private List<Context> context;
@ -240,4 +243,76 @@ public abstract class Result extends OafEntity implements Serializable {
this.processingchargecurrency = processingchargecurrency;
return this;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
Result r = (Result) e;
instance = mergeLists(instance, r.getInstance());
if (r.getResulttype() != null && compareTrust(this, r) < 0)
resulttype = r.getResulttype();
if (r.getLanguage() != null && compareTrust(this, r) < 0)
language = r.getLanguage();
country = mergeLists(country, r.getCountry());
subject = mergeLists(subject, r.getSubject());
title = mergeLists(title, r.getTitle());
relevantdate = mergeLists(relevantdate, r.getRelevantdate());
description = longestLists(description, r.getDescription());
if (r.getPublisher() != null && compareTrust(this, r) < 0)
publisher = r.getPublisher();
if (r.getEmbargoenddate() != null && compareTrust(this, r) < 0)
embargoenddate = r.getEmbargoenddate();
source = mergeLists(source, r.getSource());
fulltext = mergeLists(fulltext, r.getFulltext());
format = mergeLists(format, r.getFormat());
contributor = mergeLists(contributor, r.getContributor());
if (r.getResourcetype() != null)
resourcetype = r.getResourcetype();
coverage = mergeLists(coverage, r.getCoverage());
if (r.getRefereed() != null && compareTrust(this, r) < 0)
refereed = r.getRefereed();
context = mergeLists(context, r.getContext());
if (r.getProcessingchargeamount() != null && compareTrust(this, r) < 0)
processingchargeamount = r.getProcessingchargeamount();
if (r.getProcessingchargecurrency() != null && compareTrust(this, r) < 0)
processingchargecurrency = r.getProcessingchargecurrency();
externalReference = mergeLists(externalReference, r.getExternalReference());
}
private List<Field<String>> longestLists(List<Field<String>> a, List<Field<String>> b) {
if (a == null || b == null)
return a == null ? b : a;
if (a.size() == b.size()) {
int msa = a.stream().filter(i -> i.getValue() != null).map(i -> i.getValue().length()).max(Comparator.naturalOrder()).orElse(0);
int msb = b.stream().filter(i -> i.getValue() != null).map(i -> i.getValue().length()).max(Comparator.naturalOrder()).orElse(0);
return msa > msb ? a : b;
}
return a.size() > b.size() ? a : b;
}
}

15
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/Software.java
View File

@ -44,4 +44,19 @@ public class Software extends Result implements Serializable {
public void setProgrammingLanguage(Qualifier programmingLanguage) {
this.programmingLanguage = programmingLanguage;
}
@Override
public void mergeFrom(OafEntity e) {
super.mergeFrom(e);
final Software s = (Software) e;
documentationUrl = mergeLists(documentationUrl, s.getDocumentationUrl());
license = mergeLists(license, s.getLicense());
codeRepositoryUrl = s.getCodeRepositoryUrl()!= null && compareTrust(this, s)<0?s.getCodeRepositoryUrl():codeRepositoryUrl;
programmingLanguage= s.getProgrammingLanguage()!= null && compareTrust(this, s)<0?s.getProgrammingLanguage():programmingLanguage;
mergeOAFDataInfo(e);
}
}

24
dhp-schemas/src/main/java/eu/dnetlib/dhp/schema/oaf/StructuredProperty.java
View File

@ -33,4 +33,28 @@ public class StructuredProperty implements Serializable {
public void setDataInfo(DataInfo dataInfo) {
this.dataInfo = dataInfo;
}
public String toComparableString(){
return value != null ? value.toLowerCase() : "";
}
@Override
public int hashCode() {
return toComparableString().hashCode();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (getClass() != obj.getClass())
return false;
StructuredProperty other = (StructuredProperty) obj;
return toComparableString()
.equals(other.toComparableString());
}
}

89
dhp-schemas/src/test/java/eu/dnetlib/dhp/schema/oaf/MergeTest.java Normal file
View File

@ -0,0 +1,89 @@
package eu.dnetlib.dhp.schema.oaf;
import org.junit.Assert;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.List;
public class MergeTest {
OafEntity oaf;
@Before
public void setUp() {
oaf = new Publication();
}
@Test
public void mergeListsTest() {
//string list merge test
List<String> a = Arrays.asList("a", "b", "c", "e");
List<String> b = Arrays.asList("a", "b", "c", "d");
List<String> c = null;
System.out.println("merge result 1 = " + oaf.mergeLists(a, b));
System.out.println("merge result 2 = " + oaf.mergeLists(a, c));
System.out.println("merge result 3 = " + oaf.mergeLists(c, c));
}
@Test
public void mergePublicationCollectedFromTest() {
Publication a = new Publication();
Publication b = new Publication();
a.setCollectedfrom(Arrays.asList(setKV("a", "open"), setKV("b", "closed")));
b.setCollectedfrom(Arrays.asList(setKV("A", "open"), setKV("b", "Open")));
a.mergeFrom(b);
Assert.assertNotNull(a.getCollectedfrom());
Assert.assertEquals(3, a.getCollectedfrom().size());
}
@Test
public void mergePublicationSubjectTest() {
Publication a = new Publication();
Publication b = new Publication();
a.setSubject(Arrays.asList(setSP("a", "open", "classe"), setSP("b", "open", "classe")));
b.setSubject(Arrays.asList(setSP("A", "open", "classe"), setSP("c", "open", "classe")));
a.mergeFrom(b);
Assert.assertNotNull(a.getSubject());
Assert.assertEquals(3, a.getSubject().size());
}
private KeyValue setKV(final String key, final String value) {
KeyValue k = new KeyValue();
k.setKey(key);
k.setValue(value);
return k;
}
private StructuredProperty setSP(final String value, final String schema, final String classname) {
StructuredProperty s = new StructuredProperty();
s.setValue(value);
Qualifier q = new Qualifier();
q.setClassname(classname);
q.setClassid(classname);
q.setSchemename(schema);
q.setSchemeid(schema);
s.setQualifier(q);
return s;
}
}

2
dhp-workflows/dhp-aggregation/pom.xml
View File

@ -7,6 +7,8 @@
<version>1.0.5-SNAPSHOT</version>
</parent>
<artifactId>dhp-aggregation</artifactId>
<dependencies>
<dependency>

4
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/transformation/TransformationJobTest.java
View File

@ -89,6 +89,8 @@ public class TransformationJobTest {
"-rh", "",
"-ro", "",
"-rr", ""});
}
@Test
@ -96,7 +98,7 @@ public class TransformationJobTest {
final String path = this.getClass().getResource("/eu/dnetlib/dhp/transform/mdstorenative").getFile();
System.out.println("path = " + path);
Path tempDirWithPrefix = Files.createTempDirectory("mdsotre_output");
Path tempDirWithPrefix = Files.createTempDirectory("mdstore_output");
System.out.println(tempDirWithPrefix.toFile().getAbsolutePath());

61
dhp-workflows/dhp-dedup/pom.xml Normal file
View File

@ -0,0 +1,61 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<artifactId>dhp-workflows</artifactId>
<groupId>eu.dnetlib.dhp</groupId>
<version>1.0.5-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>dhp-dedup</artifactId>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-schemas</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>com.arakelian</groupId>
<artifactId>java-jq</artifactId>
</dependency>
<dependency>
<groupId>eu.dnetlib</groupId>
<artifactId>dnet-pace-core</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-graphx_2.11</artifactId>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-databind</artifactId>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-core</artifactId>
</dependency>
</dependencies>
</project>

119
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/DatePicker.java Normal file
View File

@ -0,0 +1,119 @@
package eu.dnetlib.dedup;
import eu.dnetlib.dhp.schema.oaf.Field;
import org.apache.commons.lang.StringUtils;
import java.time.Year;
import java.util.*;
import java.util.stream.Collectors;
import static java.util.Collections.reverseOrder;
import static java.util.Map.Entry.comparingByValue;
import static java.util.stream.Collectors.toMap;
import static org.apache.commons.lang.StringUtils.endsWith;
import static org.apache.commons.lang.StringUtils.substringBefore;
public class DatePicker {
private static final String DATE_PATTERN = "\\d{4}-\\d{2}-\\d{2}";
private static final String DATE_DEFAULT_SUFFIX = "01-01";
private static final int YEAR_LB = 1300;
private static final int YEAR_UB = Year.now().getValue() + 5;
public static Field<String> pick(final Collection<String> dateofacceptance) {
final Map<String, Integer> frequencies = dateofacceptance
.parallelStream()
.filter(StringUtils::isNotBlank)
.collect(
Collectors.toConcurrentMap(
w -> w, w -> 1, Integer::sum));
if (frequencies.isEmpty()) {
return new Field<>();
}
final Field<String> date = new Field<>();
date.setValue(frequencies.keySet().iterator().next());
// let's sort this map by values first, filtering out invalid dates
final Map<String, Integer> sorted = frequencies
.entrySet()
.stream()
.filter(d -> StringUtils.isNotBlank(d.getKey()))
.filter(d -> d.getKey().matches(DATE_PATTERN))
.filter(d -> inRange(d.getKey()))
.sorted(reverseOrder(comparingByValue()))
.collect(
toMap(
Map.Entry::getKey,
Map.Entry::getValue, (e1, e2) -> e2,
LinkedHashMap::new));
// shortcut
if (sorted.size() == 0) {
return date;
}
// voting method (1/3 + 1) wins
if (sorted.size() >= 3) {
final int acceptThreshold = (sorted.size() / 3) + 1;
final List<String> accepted = sorted.entrySet().stream()
.filter(e -> e.getValue() >= acceptThreshold)
.map(e -> e.getKey())
.collect(Collectors.toList());
// cannot find strong majority
if (accepted.isEmpty()) {
final int max = sorted.values().iterator().next();
Optional<String> first = sorted.entrySet().stream()
.filter(e -> e.getValue() == max && !endsWith(e.getKey(), DATE_DEFAULT_SUFFIX))
.map(Map.Entry::getKey)
.findFirst();
if (first.isPresent()) {
date.setValue(first.get());
return date;
}
date.setValue(sorted.keySet().iterator().next());
return date;
}
if (accepted.size() == 1) {
date.setValue(accepted.get(0));
return date;
} else {
final Optional<String> first = accepted.stream()
.filter(d -> !endsWith(d, DATE_DEFAULT_SUFFIX))
.findFirst();
if (first.isPresent()) {
date.setValue(first.get());
return date;
}
return date;
}
//1st non YYYY-01-01 is returned
} else {
if (sorted.size() == 2) {
for (Map.Entry<String, Integer> e : sorted.entrySet()) {
if (!endsWith(e.getKey(), DATE_DEFAULT_SUFFIX)) {
date.setValue(e.getKey());
return date;
}
}
}
// none of the dates seems good enough, return the 1st one
date.setValue(sorted.keySet().iterator().next());
return date;
}
}
private static boolean inRange(final String date) {
final int year = Integer.parseInt(substringBefore(date, "-"));
return year >= YEAR_LB && year <= YEAR_UB;
}
}

279
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/DedupRecordFactory.java Normal file
View File

@ -0,0 +1,279 @@
package eu.dnetlib.dedup;
import com.google.common.collect.Lists;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.pace.config.DedupConfig;
import eu.dnetlib.pace.util.MapDocumentUtil;
import org.apache.commons.lang.NotImplementedException;
import org.apache.commons.lang.StringUtils;
import org.apache.spark.api.java.JavaPairRDD;
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.Encoders;
import org.apache.spark.sql.SparkSession;
import org.codehaus.jackson.map.ObjectMapper;
import scala.Tuple2;
import java.util.Collection;
import java.util.Random;
import static java.util.stream.Collectors.toMap;
public class DedupRecordFactory {
public static JavaRDD<OafEntity> createDedupRecord(final JavaSparkContext sc, final SparkSession spark, final String mergeRelsInputPath, final String entitiesInputPath, final OafEntityType entityType, final DedupConfig dedupConf) {
long ts = System.currentTimeMillis();
//<id, json_entity>
final JavaPairRDD<String, String> inputJsonEntities = sc.textFile(entitiesInputPath)
.mapToPair((PairFunction<String, String, String>) it ->
new Tuple2<String, String>(MapDocumentUtil.getJPathString(dedupConf.getWf().getIdPath(), it), it)
);
//<source, target>: source is the dedup_id, target is the id of the mergedIn
JavaPairRDD<String, String> mergeRels = spark
.read().load(mergeRelsInputPath).as(Encoders.bean(Relation.class))
.where("relClass=='merges'")
.javaRDD()
.mapToPair(
(PairFunction<Relation, String, String>) r ->
new Tuple2<String, String>(r.getTarget(), r.getSource())
);
//<dedup_id, json_entity_merged>
final JavaPairRDD<String, String> joinResult = mergeRels.join(inputJsonEntities).mapToPair((PairFunction<Tuple2<String, Tuple2<String, String>>, String, String>) Tuple2::_2);
JavaPairRDD<String, Iterable<String>> sortedJoinResult = joinResult.groupByKey();
switch (entityType) {
case publication:
return sortedJoinResult.map(p -> DedupRecordFactory.publicationMerger(p, ts));
case dataset:
return sortedJoinResult.map(d -> DedupRecordFactory.datasetMerger(d, ts));
case project:
return sortedJoinResult.map(p -> DedupRecordFactory.projectMerger(p, ts));
case software:
return sortedJoinResult.map(s -> DedupRecordFactory.softwareMerger(s, ts));
case datasource:
return sortedJoinResult.map(d -> DedupRecordFactory.datasourceMerger(d, ts));
case organization:
return sortedJoinResult.map(o -> DedupRecordFactory.organizationMerger(o, ts));
case otherresearchproduct:
return sortedJoinResult.map(o -> DedupRecordFactory.otherresearchproductMerger(o, ts));
default:
return null;
}
}
private static Publication publicationMerger(Tuple2<String, Iterable<String>> e, final long ts) {
Publication p = new Publication(); //the result of the merge, to be returned at the end
p.setId(e._1());
final ObjectMapper mapper = new ObjectMapper();
final Collection<String> dateofacceptance = Lists.newArrayList();
if (e._2() != null)
e._2().forEach(pub -> {
try {
Publication publication = mapper.readValue(pub, Publication.class);
p.mergeFrom(publication);
p.setAuthor(DedupUtility.mergeAuthor(p.getAuthor(), publication.getAuthor()));
//add to the list if they are not null
if (publication.getDateofacceptance() != null)
dateofacceptance.add(publication.getDateofacceptance().getValue());
} catch (Exception exc) {
throw new RuntimeException(exc);
}
});
p.setDateofacceptance(DatePicker.pick(dateofacceptance));
if (p.getDataInfo() == null)
p.setDataInfo(new DataInfo());
p.getDataInfo().setTrust("0.9");
p.setLastupdatetimestamp(ts);
return p;
}
private static Dataset datasetMerger(Tuple2<String, Iterable<String>> e, final long ts) {
Dataset d = new Dataset(); //the result of the merge, to be returned at the end
d.setId(e._1());
final ObjectMapper mapper = new ObjectMapper();
final Collection<String> dateofacceptance = Lists.newArrayList();
if (e._2() != null)
e._2().forEach(dat -> {
try {
Dataset dataset = mapper.readValue(dat, Dataset.class);
d.mergeFrom(dataset);
d.setAuthor(DedupUtility.mergeAuthor(d.getAuthor(), dataset.getAuthor()));
//add to the list if they are not null
if (dataset.getDateofacceptance() != null)
dateofacceptance.add(dataset.getDateofacceptance().getValue());
} catch (Exception exc) {
throw new RuntimeException(exc);
}
});
d.setDateofacceptance(DatePicker.pick(dateofacceptance));
if (d.getDataInfo() == null)
d.setDataInfo(new DataInfo());
d.getDataInfo().setTrust("0.9");
d.setLastupdatetimestamp(ts);
return d;
}
private static Project projectMerger(Tuple2<String, Iterable<String>> e, final long ts) {
Project p = new Project(); //the result of the merge, to be returned at the end
p.setId(e._1());
final ObjectMapper mapper = new ObjectMapper();
if (e._2() != null)
e._2().forEach(proj -> {
try {
Project project = mapper.readValue(proj, Project.class);
p.mergeFrom(project);
} catch (Exception exc) {
throw new RuntimeException(exc);
}
});
if (p.getDataInfo() == null)
p.setDataInfo(new DataInfo());
p.getDataInfo().setTrust("0.9");
p.setLastupdatetimestamp(ts);
return p;
}
private static Software softwareMerger(Tuple2<String, Iterable<String>> e, final long ts) {
Software s = new Software(); //the result of the merge, to be returned at the end
s.setId(e._1());
final ObjectMapper mapper = new ObjectMapper();
final Collection<String> dateofacceptance = Lists.newArrayList();
if (e._2() != null)
e._2().forEach(soft -> {
try {
Software software = mapper.readValue(soft, Software.class);
s.mergeFrom(software);
s.setAuthor(DedupUtility.mergeAuthor(s.getAuthor(), software.getAuthor()));
//add to the list if they are not null
if (software.getDateofacceptance() != null)
dateofacceptance.add(software.getDateofacceptance().getValue());
} catch (Exception exc) {
throw new RuntimeException(exc);
}
});
s.setDateofacceptance(DatePicker.pick(dateofacceptance));
if (s.getDataInfo() == null)
s.setDataInfo(new DataInfo());
s.getDataInfo().setTrust("0.9");
s.setLastupdatetimestamp(ts);
return s;
}
private static Datasource datasourceMerger(Tuple2<String, Iterable<String>> e, final long ts) {
Datasource d = new Datasource(); //the result of the merge, to be returned at the end
d.setId(e._1());
final ObjectMapper mapper = new ObjectMapper();
if (e._2() != null)
e._2().forEach(dat -> {
try {
Datasource datasource = mapper.readValue(dat, Datasource.class);
d.mergeFrom(datasource);
} catch (Exception exc) {
throw new RuntimeException(exc);
}
});
if (d.getDataInfo() == null)
d.setDataInfo(new DataInfo());
d.getDataInfo().setTrust("0.9");
d.setLastupdatetimestamp(ts);
return d;
}
private static Organization organizationMerger(Tuple2<String, Iterable<String>> e, final long ts) {
Organization o = new Organization(); //the result of the merge, to be returned at the end
o.setId(e._1());
final ObjectMapper mapper = new ObjectMapper();
StringBuilder trust = new StringBuilder("0.0");
if (e._2() != null)
e._2().forEach(pub -> {
try {
Organization organization = mapper.readValue(pub, Organization.class);
final String currentTrust = organization.getDataInfo().getTrust();
if (!"1.0".equals(currentTrust)) {
trust.setLength(0);
trust.append(currentTrust);
}
o.mergeFrom(organization);
} catch (Exception exc) {
throw new RuntimeException(exc);
}
});
if (o.getDataInfo() == null)
{
o.setDataInfo(new DataInfo());
}
if (o.getDataInfo() == null)
o.setDataInfo(new DataInfo());
o.getDataInfo().setTrust("0.9");
o.setLastupdatetimestamp(ts);
return o;
}
private static OtherResearchProduct otherresearchproductMerger(Tuple2<String, Iterable<String>> e, final long ts) {
OtherResearchProduct o = new OtherResearchProduct(); //the result of the merge, to be returned at the end
o.setId(e._1());
final ObjectMapper mapper = new ObjectMapper();
final Collection<String> dateofacceptance = Lists.newArrayList();
if (e._2() != null)
e._2().forEach(orp -> {
try {
OtherResearchProduct otherResearchProduct = mapper.readValue(orp, OtherResearchProduct.class);
o.mergeFrom(otherResearchProduct);
o.setAuthor(DedupUtility.mergeAuthor(o.getAuthor(), otherResearchProduct.getAuthor()));
//add to the list if they are not null
if (otherResearchProduct.getDateofacceptance() != null)
dateofacceptance.add(otherResearchProduct.getDateofacceptance().getValue());
} catch (Exception exc) {
throw new RuntimeException(exc);
}
});
if (o.getDataInfo() == null)
o.setDataInfo(new DataInfo());
o.setDateofacceptance(DatePicker.pick(dateofacceptance));
o.getDataInfo().setTrust("0.9");
o.setLastupdatetimestamp(ts);
return o;
}
}

219
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/DedupUtility.java Normal file
View File

@ -0,0 +1,219 @@
package eu.dnetlib.dedup;
import com.google.common.collect.Sets;
import com.wcohen.ss.JaroWinkler;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.pace.clustering.BlacklistAwareClusteringCombiner;
import eu.dnetlib.pace.config.DedupConfig;
import eu.dnetlib.pace.model.MapDocument;
import eu.dnetlib.pace.model.Person;
import org.apache.commons.codec.binary.Hex;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.spark.SparkContext;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.util.LongAccumulator;
import scala.Tuple2;
import java.io.IOException;
import java.io.StringWriter;
import java.nio.charset.StandardCharsets;
import java.security.MessageDigest;
import java.text.Normalizer;
import java.util.*;
import java.util.stream.Collectors;
import java.util.stream.Stream;
public class DedupUtility {
private static final Double THRESHOLD = 0.95;
public static Map<String, LongAccumulator> constructAccumulator(final DedupConfig dedupConf, final SparkContext context) {
Map<String, LongAccumulator> accumulators = new HashMap<>();
String acc1 = String.format("%s::%s", dedupConf.getWf().getEntityType(), "records per hash key = 1");
accumulators.put(acc1, context.longAccumulator(acc1));
String acc2 = String.format("%s::%s", dedupConf.getWf().getEntityType(), "missing " + dedupConf.getWf().getOrderField());
accumulators.put(acc2, context.longAccumulator(acc2));
String acc3 = String.format("%s::%s", dedupConf.getWf().getEntityType(), String.format("Skipped records for count(%s) >= %s", dedupConf.getWf().getOrderField(), dedupConf.getWf().getGroupMaxSize()));
accumulators.put(acc3, context.longAccumulator(acc3));
String acc4 = String.format("%s::%s", dedupConf.getWf().getEntityType(), "skip list");
accumulators.put(acc4, context.longAccumulator(acc4));
String acc5 = String.format("%s::%s", dedupConf.getWf().getEntityType(), "dedupSimilarity (x2)");
accumulators.put(acc5, context.longAccumulator(acc5));
String acc6 = String.format("%s::%s", dedupConf.getWf().getEntityType(), "d < " + dedupConf.getWf().getThreshold());
accumulators.put(acc6, context.longAccumulator(acc6));
return accumulators;
}
public static JavaRDD<String> loadDataFromHDFS(String path, JavaSparkContext context) {
return context.textFile(path);
}
public static void deleteIfExists(String path) throws IOException {
Configuration conf = new Configuration();
FileSystem fileSystem = FileSystem.get(conf);
if (fileSystem.exists(new Path(path))) {
fileSystem.delete(new Path(path), true);
}
}
public static DedupConfig loadConfigFromHDFS(String path) throws IOException {
Configuration conf = new Configuration();
FileSystem fileSystem = FileSystem.get(conf);
FSDataInputStream inputStream = new FSDataInputStream(fileSystem.open(new Path(path)));
return DedupConfig.load(IOUtils.toString(inputStream, StandardCharsets.UTF_8.name()));
}
static <T> String readFromClasspath(final String filename, final Class<T> clazz) {
final StringWriter sw = new StringWriter();
try {
IOUtils.copy(clazz.getResourceAsStream(filename), sw);
return sw.toString();
} catch (final IOException e) {
throw new RuntimeException("cannot load resource from classpath: " + filename);
}
}
static Set<String> getGroupingKeys(DedupConfig conf, MapDocument doc) {
return Sets.newHashSet(BlacklistAwareClusteringCombiner.filterAndCombine(doc, conf));
}
public static String md5(final String s) {
try {
final MessageDigest md = MessageDigest.getInstance("MD5");
md.update(s.getBytes("UTF-8"));
return new String(Hex.encodeHex(md.digest()));
} catch (final Exception e) {
System.err.println("Error creating id");
return null;
}
}
public static List<Author> mergeAuthor(final List<Author> a, final List<Author> b) {
int pa = countAuthorsPids(a);
int pb = countAuthorsPids(b);
List<Author> base, enrich;
int sa = authorsSize(a);
int sb = authorsSize(b);
if (pa == pb) {
base = sa > sb ? a : b;
enrich = sa > sb ? b : a;
} else {
base = pa > pb ? a : b;
enrich = pa > pb ? b : a;
}
enrichPidFromList(base, enrich);
return base;
}
private static void enrichPidFromList(List<Author> base, List<Author> enrich) {
if (base == null || enrich == null)
return;
final Map<String, Author> basePidAuthorMap = base.stream()
.filter(a -> a.getPid() != null && a.getPid().size() > 0)
.flatMap(a -> a.getPid()
.stream()
.map(p -> new Tuple2<>(p.toComparableString(), a))
).collect(Collectors.toMap(Tuple2::_1, Tuple2::_2, (x1, x2) -> x1));
final List<Tuple2<StructuredProperty, Author>> pidToEnrich = enrich
.stream()
.filter(a -> a.getPid() != null && a.getPid().size() > 0)
.flatMap(a -> a.getPid().stream().filter(p -> !basePidAuthorMap.containsKey(p.toComparableString())).map(p -> new Tuple2<>(p, a)))
.collect(Collectors.toList());
pidToEnrich.forEach(a -> {
Optional<Tuple2<Double, Author>> simAuhtor = base.stream().map(ba -> new Tuple2<>(sim(ba, a._2()), ba)).max(Comparator.comparing(Tuple2::_1));
if (simAuhtor.isPresent() && simAuhtor.get()._1() > THRESHOLD) {
Author r = simAuhtor.get()._2();
r.getPid().add(a._1());
}
});
}
public static String createEntityPath(final String basePath, final String entityType) {
return String.format("%s/%s", basePath, entityType);
}
public static String createSimRelPath(final String basePath, final String entityType) {
return String.format("%s/%s_simRel", basePath, entityType);
}
public static String createMergeRelPath(final String basePath, final String entityType) {
return String.format("%s/%s_mergeRel", basePath, entityType);
}
private static Double sim(Author a, Author b) {
final Person pa = parse(a);
final Person pb = parse(b);
if (pa.isAccurate() & pb.isAccurate()) {
return new JaroWinkler().score(
normalize(pa.getSurnameString()),
normalize(pb.getSurnameString()));
} else {
return new JaroWinkler().score(
normalize(pa.getNormalisedFullname()),
normalize(pb.getNormalisedFullname()));
}
}
private static String normalize(final String s) {
return nfd(s).toLowerCase()
// do not compact the regexes in a single expression, would cause StackOverflowError in case of large input strings
.replaceAll("(\\W)+", " ")
.replaceAll("(\\p{InCombiningDiacriticalMarks})+", " ")
.replaceAll("(\\p{Punct})+", " ")
.replaceAll("(\\d)+", " ")
.replaceAll("(\\n)+", " ")
.trim();
}
private static String nfd(final String s) {
return Normalizer.normalize(s, Normalizer.Form.NFD);
}
private static Person parse(Author author) {
if (StringUtils.isNotBlank(author.getSurname())) {
return new Person(author.getSurname() + ", " + author.getName(), false);
} else {
return new Person(author.getFullname(), false);
}
}
private static int countAuthorsPids(List<Author> authors) {
if (authors == null)
return 0;
return (int) authors.stream().filter(DedupUtility::hasPid).count();
}
private static int authorsSize(List<Author> authors) {
if (authors == null)
return 0;
return authors.size();
}
private static boolean hasPid(Author a) {
if (a == null || a.getPid() == null || a.getPid().size() == 0)
return false;
return a.getPid().stream().anyMatch(p -> p != null && StringUtils.isNotBlank(p.getValue()));
}
}

162
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/Deduper.java Normal file
View File

@ -0,0 +1,162 @@
package eu.dnetlib.dedup;
import eu.dnetlib.pace.config.DedupConfig;
import eu.dnetlib.pace.model.Field;
import eu.dnetlib.pace.model.MapDocument;
import eu.dnetlib.pace.util.BlockProcessor;
import eu.dnetlib.pace.util.MapDocumentUtil;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFlatMapFunction;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.util.LongAccumulator;
import scala.Serializable;
import scala.Tuple2;
import java.util.*;
import java.util.stream.Collectors;
public class Deduper implements Serializable {
private static final Log log = LogFactory.getLog(Deduper.class);
/**
* @return the list of relations generated by the deduplication
* @param: the spark context
* @param: list of JSON entities to be deduped
* @param: the dedup configuration
*/
public static JavaPairRDD<String, String> dedup(JavaSparkContext context, JavaRDD<String> entities, DedupConfig config) {
Map<String, LongAccumulator> accumulators = DedupUtility.constructAccumulator(config, context.sc());
//create vertexes of the graph: <ID, MapDocument>
JavaPairRDD<String, MapDocument> mapDocs = mapToVertexes(context, entities, config);
//create blocks for deduplication
JavaPairRDD<String, Iterable<MapDocument>> blocks = createBlocks(context, mapDocs, config);
//create relations by comparing only elements in the same group
return computeRelations(context, blocks, config);
// final RDD<Edge<String>> edgeRdd = relationRDD.map(it -> new Edge<>(it._1().hashCode(), it._2().hashCode(), "equalTo")).rdd();
//
// RDD<Tuple2<Object, MapDocument>> vertexes = mapDocs.mapToPair((PairFunction<Tuple2<String, MapDocument>, Object, MapDocument>) t -> new Tuple2<Object, MapDocument>((long) t._1().hashCode(), t._2())).rdd();
// accumulators.forEach((name, acc) -> log.info(name + " -> " + acc.value()));
//
// return GraphProcessor.findCCs(vertexes, edgeRdd, 20).toJavaRDD();
}
/**
* @return the list of relations generated by the deduplication
* @param: the spark context
* @param: list of blocks
* @param: the dedup configuration
*/
public static JavaPairRDD<String, String> computeRelations(JavaSparkContext context, JavaPairRDD<String, Iterable<MapDocument>> blocks, DedupConfig config) {
Map<String, LongAccumulator> accumulators = DedupUtility.constructAccumulator(config, context.sc());
return blocks.flatMapToPair((PairFlatMapFunction<Tuple2<String, Iterable<MapDocument>>, String, String>) it -> {
final SparkReporter reporter = new SparkReporter(accumulators);
new BlockProcessor(config).process(it._1(), it._2(), reporter);
return reporter.getRelations().iterator();
}).mapToPair(
(PairFunction<Tuple2<String, String>, String, Tuple2<String, String>>) item ->
new Tuple2<String, Tuple2<String, String>>(item._1() + item._2(), item))
.reduceByKey((a, b) -> a)
.mapToPair((PairFunction<Tuple2<String, Tuple2<String, String>>, String, String>) Tuple2::_2);
}
/**
* @return the list of blocks based on clustering of dedup configuration
* @param: the spark context
* @param: list of entities: <id, entity>
* @param: the dedup configuration
*/
public static JavaPairRDD<String, Iterable<MapDocument>> createBlocks(JavaSparkContext context, JavaPairRDD<String, MapDocument> mapDocs, DedupConfig config) {
return mapDocs
//the reduce is just to be sure that we haven't document with same id
.reduceByKey((a, b) -> a)
.map(Tuple2::_2)
//Clustering: from <id, doc> to List<groupkey,doc>
.flatMapToPair((PairFlatMapFunction<MapDocument, String, MapDocument>) a ->
DedupUtility.getGroupingKeys(config, a)
.stream()
.map(it -> new Tuple2<>(it, a))
.collect(Collectors.toList())
.iterator())
.groupByKey();
}
public static JavaPairRDD<String, List<MapDocument>> createsortedBlocks(JavaSparkContext context, JavaPairRDD<String, MapDocument> mapDocs, DedupConfig config) {
final String of = config.getWf().getOrderField();
final int maxQueueSize = config.getWf().getGroupMaxSize();
return mapDocs
//the reduce is just to be sure that we haven't document with same id
.reduceByKey((a, b) -> a)
.map(Tuple2::_2)
//Clustering: from <id, doc> to List<groupkey,doc>
.flatMapToPair((PairFlatMapFunction<MapDocument, String, List<MapDocument>>) a ->
DedupUtility.getGroupingKeys(config, a)
.stream()
.map(it -> {
List<MapDocument> tmp = new ArrayList<>();
tmp.add(a);
return new Tuple2<>(it, tmp);
}
)
.collect(Collectors.toList())
.iterator())
.reduceByKey((Function2<List<MapDocument>, List<MapDocument>, List<MapDocument>>) (v1, v2) -> {
v1.addAll(v2);
v1.sort(Comparator.comparing(a -> a.getFieldMap().get(of).stringValue()));
if (v1.size() > maxQueueSize)
return new ArrayList<>(v1.subList(0, maxQueueSize));
return v1;
});
}
/**
* @return the list of vertexes: <id, mapDocument>
* @param: the spark context
* @param: list of JSON entities
* @param: the dedup configuration
*/
public static JavaPairRDD<String, MapDocument> mapToVertexes(JavaSparkContext context, JavaRDD<String> entities, DedupConfig config) {
return entities.mapToPair((PairFunction<String, String, MapDocument>) s -> {
MapDocument mapDocument = MapDocumentUtil.asMapDocumentWithJPath(config, s);
return new Tuple2<String, MapDocument>(mapDocument.getIdentifier(), mapDocument);
});
}
public static JavaPairRDD<String, String> computeRelations2(JavaSparkContext context, JavaPairRDD<String, List<MapDocument>> blocks, DedupConfig config) {
Map<String, LongAccumulator> accumulators = DedupUtility.constructAccumulator(config, context.sc());
return blocks.flatMapToPair((PairFlatMapFunction<Tuple2<String, List<MapDocument>>, String, String>) it -> {
try {
final SparkReporter reporter = new SparkReporter(accumulators);
new BlockProcessor(config).processSortedBlock(it._1(), it._2(), reporter);
return reporter.getRelations().iterator();
} catch (Exception e) {
throw new RuntimeException(it._2().get(0).getIdentifier(), e);
}
}).mapToPair(
(PairFunction<Tuple2<String, String>, String, Tuple2<String, String>>) item ->
new Tuple2<String, Tuple2<String, String>>(item._1() + item._2(), item))
.reduceByKey((a, b) -> a)
.mapToPair((PairFunction<Tuple2<String, Tuple2<String, String>>, String, String>) Tuple2::_2);
}
}

15
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/OafEntityType.java Normal file
View File

@ -0,0 +1,15 @@
package eu.dnetlib.dedup;
public enum OafEntityType {
datasource,
organization,
project,
dataset,
otherresearchproduct,
software,
publication
}

79
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/SparkCreateConnectedComponent.java Normal file
View File

@ -0,0 +1,79 @@
package eu.dnetlib.dedup;
import com.google.common.collect.Iterables;
import com.google.common.collect.Lists;
import com.google.common.hash.HashFunction;
import com.google.common.hash.Hashing;
import eu.dnetlib.dedup.graph.ConnectedComponent;
import eu.dnetlib.dedup.graph.GraphProcessor;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.pace.config.DedupConfig;
import eu.dnetlib.pace.util.MapDocumentUtil;
import org.apache.commons.io.IOUtils;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.graphx.Edge;
import org.apache.spark.rdd.RDD;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import scala.Tuple2;
import java.util.ArrayList;
import java.util.List;
public class SparkCreateConnectedComponent {
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateConnectedComponent.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/dedup_parameters.json")));
parser.parseArgument(args);
final SparkSession spark = SparkSession
.builder()
.appName(SparkCreateConnectedComponent.class.getSimpleName())
.master(parser.get("master"))
.getOrCreate();
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
final String inputPath = parser.get("sourcePath");
final String entity = parser.get("entity");
final String targetPath = parser.get("targetPath");
// final DedupConfig dedupConf = DedupConfig.load(IOUtils.toString(SparkCreateConnectedComponent.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/conf/org.curr.conf2.json")));
final DedupConfig dedupConf = DedupConfig.load(parser.get("dedupConf"));
final JavaPairRDD<Object, String> vertexes = sc.textFile(inputPath + "/" + entity)
.map(s -> MapDocumentUtil.getJPathString(dedupConf.getWf().getIdPath(), s))
.mapToPair((PairFunction<String, Object, String>)
s -> new Tuple2<Object, String>(getHashcode(s), s)
);
final Dataset<Relation> similarityRelations = spark.read().load(DedupUtility.createSimRelPath(targetPath,entity)).as(Encoders.bean(Relation.class));
final RDD<Edge<String>> edgeRdd = similarityRelations.javaRDD().map(it -> new Edge<>(getHashcode(it.getSource()), getHashcode(it.getTarget()), it.getRelClass())).rdd();
final JavaRDD<ConnectedComponent> cc = GraphProcessor.findCCs(vertexes.rdd(), edgeRdd, dedupConf.getWf().getMaxIterations()).toJavaRDD();
final Dataset<Relation> mergeRelation = spark.createDataset(cc.filter(k->k.getDocIds().size()>1).flatMap((FlatMapFunction<ConnectedComponent, Relation>) c ->
c.getDocIds()
.stream()
.flatMap(id -> {
List<Relation> tmp = new ArrayList<>();
Relation r = new Relation();
r.setSource(c.getCcId());
r.setTarget(id);
r.setRelClass("merges");
tmp.add(r);
r = new Relation();
r.setTarget(c.getCcId());
r.setSource(id);
r.setRelClass("isMergedIn");
tmp.add(r);
return tmp.stream();
}).iterator()).rdd(), Encoders.bean(Relation.class));
mergeRelation.write().mode("overwrite").save(DedupUtility.createMergeRelPath(targetPath,entity));
}
public static long getHashcode(final String id) {
return Hashing.murmur3_128().hashUnencodedChars(id).asLong();
}
}

39
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/SparkCreateDedupRecord.java Normal file
View File

@ -0,0 +1,39 @@
package eu.dnetlib.dedup;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.pace.config.DedupConfig;
import org.apache.commons.io.IOUtils;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.SparkSession;
public class SparkCreateDedupRecord {
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateDedupRecord.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/dedupRecord_parameters.json")));
parser.parseArgument(args);
final SparkSession spark = SparkSession
.builder()
.appName(SparkCreateDedupRecord.class.getSimpleName())
.master(parser.get("master"))
.getOrCreate();
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
final String sourcePath = parser.get("sourcePath");
final String entity = parser.get("entity");
final String dedupPath = parser.get("dedupPath");
// final DedupConfig dedupConf = DedupConfig.load(IOUtils.toString(SparkCreateDedupRecord.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/conf/org.curr.conf2.json")));
final DedupConfig dedupConf = DedupConfig.load(parser.get("dedupConf"));
final JavaRDD<OafEntity> dedupRecord = DedupRecordFactory.createDedupRecord(sc, spark, DedupUtility.createMergeRelPath(dedupPath,entity), DedupUtility.createEntityPath(sourcePath,entity), OafEntityType.valueOf(entity), dedupConf);
dedupRecord.map(r-> {
ObjectMapper mapper = new ObjectMapper();
return mapper.writeValueAsString(r);
}).saveAsTextFile(dedupPath+"/"+entity+"_dedup_record_json");
}
}

73
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/SparkCreateSimRels.java Normal file
View File

@ -0,0 +1,73 @@
package eu.dnetlib.dedup;
import com.google.common.hash.Hashing;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.pace.config.DedupConfig;
import eu.dnetlib.pace.model.MapDocument;
import eu.dnetlib.pace.util.MapDocumentUtil;
import org.apache.commons.io.IOUtils;
import org.apache.spark.api.java.JavaPairRDD;
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.Encoders;
import org.apache.spark.sql.SparkSession;
import scala.Tuple2;
import java.util.List;
/**
* This Spark class creates similarity relations between entities, saving result
*
* param request:
* sourcePath
* entityType
* target Path
*/
public class SparkCreateSimRels {
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkCreateSimRels.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/dedup_parameters.json")));
parser.parseArgument(args);
final SparkSession spark = SparkSession
.builder()
.appName(SparkCreateSimRels.class.getSimpleName())
.master(parser.get("master"))
.getOrCreate();
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
final String inputPath = parser.get("sourcePath");
final String entity = parser.get("entity");
final String targetPath = parser.get("targetPath");
// final DedupConfig dedupConf = DedupConfig.load(IOUtils.toString(SparkCreateSimRels.class.getResourceAsStream("/eu/dnetlib/dhp/dedup/conf/org.curr.conf.json")));
final DedupConfig dedupConf = DedupConfig.load(parser.get("dedupConf"));
final long total = sc.textFile(inputPath + "/" + entity).count();
JavaPairRDD<String, MapDocument> mapDocument = sc.textFile(inputPath + "/" + entity)
.mapToPair(s->{
MapDocument d = MapDocumentUtil.asMapDocumentWithJPath(dedupConf,s);
return new Tuple2<>(d.getIdentifier(), d);});
//create blocks for deduplication
JavaPairRDD<String, List<MapDocument>> blocks = Deduper.createsortedBlocks(sc, mapDocument, dedupConf);
// JavaPairRDD<String, Iterable<MapDocument>> blocks = Deduper.createBlocks(sc, mapDocument, dedupConf);
//create relations by comparing only elements in the same group
final JavaPairRDD<String,String> dedupRels = Deduper.computeRelations2(sc, blocks, dedupConf);
// final JavaPairRDD<String,String> dedupRels = Deduper.computeRelations(sc, blocks, dedupConf);
final JavaRDD<Relation> isSimilarToRDD = dedupRels.map(simRel -> {
final Relation r = new Relation();
r.setSource(simRel._1());
r.setTarget(simRel._2());
r.setRelClass("isSimilarTo");
return r;
});
spark.createDataset(isSimilarToRDD.rdd(), Encoders.bean(Relation.class)).write().mode("overwrite").save( DedupUtility.createSimRelPath(targetPath,entity));
}
}

47
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/SparkReporter.java Normal file
View File

@ -0,0 +1,47 @@
package eu.dnetlib.dedup;
import eu.dnetlib.pace.util.Reporter;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.spark.util.LongAccumulator;
import scala.Serializable;
import scala.Tuple2;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
public class SparkReporter implements Serializable, Reporter {
final List<Tuple2<String, String>> relations = new ArrayList<>();
private static final Log log = LogFactory.getLog(SparkReporter.class);
Map<String, LongAccumulator> accumulators;
public SparkReporter(Map<String, LongAccumulator> accumulators){
this.accumulators = accumulators;
}
public void incrementCounter(String counterGroup, String counterName, long delta, Map<String, LongAccumulator> accumulators) {
final String accumulatorName = String.format("%s::%s", counterGroup, counterName);
if (accumulators.containsKey(accumulatorName)){
accumulators.get(accumulatorName).add(delta);
}
}
@Override
public void incrementCounter(String counterGroup, String counterName, long delta) {
incrementCounter(counterGroup, counterName, delta, accumulators);
}
@Override
public void emit(String type, String from, String to) {
relations.add(new Tuple2<>(from, to));
}
public List<Tuple2<String, String>> getRelations() {
return relations;
}
}

80
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/graph/ConnectedComponent.java Normal file
View File

@ -0,0 +1,80 @@
package eu.dnetlib.dedup.graph;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dedup.DedupUtility;
import eu.dnetlib.pace.util.PaceException;
import org.apache.commons.lang.StringUtils;
import org.codehaus.jackson.annotate.JsonIgnore;
import java.io.IOException;
import java.io.Serializable;
import java.util.Set;
public class ConnectedComponent implements Serializable {
private Set<String> docIds;
private String ccId;
public ConnectedComponent() {
}
public ConnectedComponent(Set<String> docIds) {
this.docIds = docIds;
createID();
}
public String createID() {
if (docIds.size() > 1) {
final String s = getMin();
String prefix = s.split("\\|")[0];
ccId =prefix + "|dedup_______::" + DedupUtility.md5(s);
return ccId;
} else {
return docIds.iterator().next();
}
}
@JsonIgnore
public String getMin(){
final StringBuilder min = new StringBuilder();
docIds.forEach(i -> {
if (StringUtils.isBlank(min.toString())) {
min.append(i);
} else {
if (min.toString().compareTo(i) > 0) {
min.setLength(0);
min.append(i);
}
}
});
return min.toString();
}
@Override
public String toString(){
ObjectMapper mapper = new ObjectMapper();
try {
return mapper.writeValueAsString(this);
} catch (IOException e) {
throw new PaceException("Failed to create Json: ", e);
}
}
public Set<String> getDocIds() {
return docIds;
}
public void setDocIds(Set<String> docIds) {
this.docIds = docIds;
}
public String getCcId() {
return ccId;
}
public void setCcId(String ccId) {
this.ccId = ccId;
}
}

37
dhp-workflows/dhp-dedup/src/main/java/eu/dnetlib/dedup/graph/GraphProcessor.scala Normal file
View File

@ -0,0 +1,37 @@
package eu.dnetlib.dedup.graph
import org.apache.spark.graphx._
import org.apache.spark.rdd.RDD
import scala.collection.JavaConversions;
object GraphProcessor {
def findCCs(vertexes: RDD[(VertexId, String)], edges: RDD[Edge[String]], maxIterations: Int): RDD[ConnectedComponent] = {
val graph: Graph[String, String] = Graph(vertexes, edges).partitionBy(PartitionStrategy.RandomVertexCut) //TODO remember to remove partitionby
val cc = graph.connectedComponents(maxIterations).vertices
val joinResult = vertexes.leftOuterJoin(cc).map {
case (id, (openaireId, cc)) => {
if (cc.isEmpty) {
(id, openaireId)
}
else {
(cc.get, openaireId)
}
}
}
val connectedComponents = joinResult.groupByKey()
.map[ConnectedComponent](cc => asConnectedComponent(cc))
connectedComponents
}
def asConnectedComponent(group: (VertexId, Iterable[String])): ConnectedComponent = {
val docs = group._2.toSet[String]
val connectedComponent = new ConnectedComponent(JavaConversions.setAsJavaSet[String](docs));
connectedComponent
}
}

33
dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/dedupRecord_parameters.json Normal file
View File

@ -0,0 +1,33 @@
[
{
"paramName": "mt",
"paramLongName": "master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the path of the sequential file to read",
"paramRequired": true
},
{
"paramName": "e",
"paramLongName": "entity",
"paramDescription": "the type of entity to be deduped",
"paramRequired": true
},
{
"paramName": "c",
"paramLongName": "dedupConf",
"paramDescription": "dedup configuration to be used",
"compressed": true,
"paramRequired": true
},
{
"paramName": "d",
"paramLongName": "dedupPath",
"paramDescription": "dedup path to load mergeRelation",
"paramRequired": true
}
]

33
dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/dedup_parameters.json Normal file
View File

@ -0,0 +1,33 @@
[
{
"paramName": "mt",
"paramLongName": "master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the path of the sequential file to read",
"paramRequired": true
},
{
"paramName": "e",
"paramLongName": "entity",
"paramDescription": "the type of entity to be deduped",
"paramRequired": true
},
{
"paramName": "c",
"paramLongName": "dedupConf",
"paramDescription": "dedup configuration to be used",
"compressed": true,
"paramRequired": true
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "target path to save dedup result",
"paramRequired": true
}
]

26
dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/oozie_app/config-default.xml Normal file
View File

@ -0,0 +1,26 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>hive_metastore_uris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>hive_db_name</name>
<value>openaire</value>
</property>
</configuration>

126
dhp-workflows/dhp-dedup/src/main/resources/eu/dnetlib/dhp/dedup/oozie_app/workflow.xml Normal file
View File

@ -0,0 +1,126 @@
<workflow-app name="Dedup Entities" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>entity</name>
<description>the entity that should be processed</description>
</property>
<property>
<name>dedupConf</name>
<description>the dedup Configuration</description>
</property>
<property>
<name>targetPath</name>
<description>the target path</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
</property>
</parameters>
<start to="CreateSimRels"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<!-- <action name="DeleteTargetPath">-->
<!-- <fs>-->
<!-- <delete path='${targetPath}/${entity}_simrel'/>-->
<!-- <delete path='${targetPath}/${entity}_mergeRels'/>-->
<!-- </fs>-->
<!-- <ok to="CreateSimRels"/>-->
<!-- <error to="Kill"/>-->
<!-- </action>-->
<action name="CreateSimRels">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Create Similarity Relations</name>
<class>eu.dnetlib.dedup.SparkCreateSimRels</class>
<jar>dhp-dedup-${projectVersion}.jar</jar>
<spark-opts>--executor-memory ${sparkExecutorMemory} --executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory} --conf
spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener" --conf
spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener" --conf
spark.sql.warehouse.dir="/user/hive/warehouse"
</spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--entity</arg><arg>${entity}</arg>
<arg>--dedupConf</arg><arg>${dedupConf}</arg>
</spark>
<ok to="CreateConnectedComponents"/>
<error to="Kill"/>
</action>
<action name="CreateConnectedComponents">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Create Connected Components</name>
<class>eu.dnetlib.dedup.SparkCreateConnectedComponent</class>
<jar>dhp-dedup-${projectVersion}.jar</jar>
<spark-opts>--executor-memory ${sparkExecutorMemory} --executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory} --conf
spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener" --conf
spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener" --conf
spark.sql.warehouse.dir="/user/hive/warehouse"
</spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--entity</arg><arg>${entity}</arg>
<arg>--dedupConf</arg><arg>${dedupConf}</arg>
</spark>
<ok to="CreateDedupRecord"/>
<error to="Kill"/>
</action>
<action name="CreateDedupRecord">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Create Dedup Record</name>
<class>eu.dnetlib.dedup.SparkCreateDedupRecord</class>
<jar>dhp-dedup-${projectVersion}.jar</jar>
<spark-opts>--executor-memory ${sparkExecutorMemory} --executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory} --conf
spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener" --conf
spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener" --conf
spark.sql.warehouse.dir="/user/hive/warehouse"
</spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--dedupPath</arg><arg>${dedupPath}</arg>
<arg>--entity</arg><arg>${entity}</arg>
<arg>--dedupConf</arg><arg>${dedupConf}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

61
dhp-workflows/dhp-dedup/src/test/java/eu/dnetlib/dedup/MergeAuthorTest.java Normal file
View File

@ -0,0 +1,61 @@
package eu.dnetlib.dedup;
import eu.dnetlib.dhp.schema.oaf.Publication;
import org.apache.commons.io.IOUtils;
import org.codehaus.jackson.map.ObjectMapper;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
import java.util.stream.Collectors;
public class MergeAuthorTest {
List<Publication> publicationsToMerge;
final ObjectMapper mapper = new ObjectMapper();
@Before
public void setUp() throws Exception {
final String json = IOUtils.toString(this.getClass().getResourceAsStream("/eu/dnetlib/dedup/json/authors_merge.json"));
publicationsToMerge = Arrays.asList(json.split("\n")).stream().map(s-> {
try {
return mapper.readValue(s, Publication.class);
} catch (IOException e) {
throw new RuntimeException(e);
}
}).collect(Collectors.toList());
}
@Test
public void test() throws Exception {
Publication dedup = new Publication();
publicationsToMerge.forEach(p-> {
dedup.mergeFrom(p);
dedup.setAuthor(DedupUtility.mergeAuthor(dedup.getAuthor(),p.getAuthor()));
});
System.out.println(mapper.writeValueAsString(dedup));
}
}

86
dhp-workflows/dhp-dedup/src/test/java/eu/dnetlib/dedup/SparkCreateDedupTest.java Normal file
View File

@ -0,0 +1,86 @@
package eu.dnetlib.dedup;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.hash.HashFunction;
import com.google.common.hash.Hashing;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Publication;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
import org.junit.Before;
import org.junit.Ignore;
import org.junit.Test;
import java.io.File;
import java.io.IOException;
import java.util.List;
public class SparkCreateDedupTest {
String configuration;
String entity = "organization";
@Before
public void setUp() throws IOException {
configuration = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dedup/conf/org.curr.conf.json"));
}
@Test
@Ignore
public void createSimRelsTest() throws Exception {
SparkCreateSimRels.main(new String[] {
"-mt", "local[*]",
"-s", "/Users/miconis/dumps",
"-e", entity,
"-c", ArgumentApplicationParser.compressArgument(configuration),
"-t", "/tmp/dedup",
});
}
@Test
@Ignore
public void createCCTest() throws Exception {
SparkCreateConnectedComponent.main(new String[] {
"-mt", "local[*]",
"-s", "/Users/miconis/dumps",
"-e", entity,
"-c", ArgumentApplicationParser.compressArgument(configuration),
"-t", "/tmp/dedup",
});
}
@Test
@Ignore
public void dedupRecordTest() throws Exception {
SparkCreateDedupRecord.main(new String[] {
"-mt", "local[*]",
"-s", "/Users/miconis/dumps",
"-e", entity,
"-c", ArgumentApplicationParser.compressArgument(configuration),
"-d", "/tmp/dedup",
});
}
@Test
public void printConfiguration() throws Exception {
System.out.println(ArgumentApplicationParser.compressArgument(configuration));
}
@Test
public void testHashCode() {
final String s1 = "20|grid________::6031f94bef015a37783268ec1e75f17f";
final String s2 = "20|nsf_________::b12be9edf414df8ee66b4c52a2d8da46";
final HashFunction hashFunction = Hashing.murmur3_128();
System.out.println( s1.hashCode());
System.out.println(hashFunction.hashUnencodedChars(s1).asLong());
System.out.println( s2.hashCode());
System.out.println(hashFunction.hashUnencodedChars(s2).asLong());
}
}

31
dhp-workflows/dhp-dedup/src/test/java/eu/dnetlib/dedup/jpath/JsonPathTest.java Normal file
View File

@ -0,0 +1,31 @@
package eu.dnetlib.dedup.jpath;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.jayway.jsonpath.JsonPath;
import org.apache.commons.io.IOUtils;
import org.junit.Test;
import java.util.List;
import java.util.Map;
public class JsonPathTest {
@Test
public void testJPath () throws Exception {
final String json = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dedup/conf/sample.json"));
List<Map<String, Object>> pid = JsonPath.read(json, "$.pid[*]");
// System.out.println(json);
pid.forEach(it -> {
try {
System.out.println(new ObjectMapper().writeValueAsString(it));
} catch (JsonProcessingException e) {
e.printStackTrace();
}
});
}
}

266
dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dedup/conf/org.curr.conf.json Normal file
View File

@ -0,0 +1,266 @@
{
"wf" : {
"threshold" : "0.99",
"dedupRun" : "001",
"entityType" : "organization",
"orderField" : "legalname",
"queueMaxSize" : "2000",
"groupMaxSize" : "50",
"slidingWindowSize" : "200",
"idPath":"$.id",
"rootBuilder" : [ "organization", "projectOrganization_participation_isParticipant", "datasourceOrganization_provision_isProvidedBy" ],
"includeChildren" : "true",
"maxIterations": "20"
},
"pace" : {
"clustering" : [
{ "name" : "sortedngrampairs", "fields" : [ "legalname" ], "params" : { "max" : 2, "ngramLen" : "3"} },
{ "name" : "suffixprefix", "fields" : [ "legalname" ], "params" : { "max" : 1, "len" : "3" } },
{ "name" : "urlclustering", "fields" : [ "websiteurl" ], "params" : { } },
{ "name" : "keywordsclustering", "fields" : [ "legalname" ], "params" : { "max": 2, "windowSize": 4} }
],
"decisionTree" : {
"start": {
"fields": [
{
"field": "gridid",
"comparator": "exactMatch",
"weight": 1,
"countIfUndefined": "false",
"params": {}
}
],
"threshold": 1,
"aggregation": "AVG",
"positive": "MATCH",
"negative": "NO_MATCH",
"undefined": "layer2",
"ignoreUndefined": "false"
},
"layer2": {
"fields": [
{
"field": "websiteurl",
"comparator": "domainExactMatch",
"weight": 1,
"countIfUndefined": "false",
"params": {}
},
{
"field": "country",
"comparator": "exactMatch",
"weight": 1,
"countIfUndefined": "true",
"params": {}
},
{
"field": "legalname",
"comparator": "numbersMatch",
"weight": 1,
"countIfUndefined": "true",
"params": {}
},
{
"field": "legalname",
"comparator": "romansMatch",
"weight": 1,
"countIfUndefined": "true",
"params": {}
}
],
"threshold": 1,
"aggregation": "AND",
"positive": "layer3",
"negative": "NO_MATCH",
"undefined": "layer3",
"ignoreUndefined": "true"
},
"layer3": {
"fields": [
{
"field": "legalname",
"comparator": "cityMatch",
"weight": 1.0,
"countIfUndefined": "true",
"params": {
"windowSize": "4"
}
}
],
"threshold": 0.7,
"aggregation": "W_MEAN",
"positive": "layer4",
"negative": "NO_MATCH",
"undefined": "NO_MATCH",
"ignoreUndefined": "true"
},
"layer4": {
"fields": [
{
"field": "legalname",
"comparator": "keywordMatch",
"weight": 1.0,
"countIfUndefined": "true",
"params": {
"windowSize": "4"
}
}
],
"threshold": 0.9,
"aggregation": "AVG",
"positive": "layer5",
"negative": "NO_MATCH",
"undefined": "layer5",
"ignoreUndefined": "true"
},
"layer5": {
"fields": [
{
"field": "legalname",
"comparator": "jaroWinklerNormalizedName",
"weight": 0.9,
"countIfUndefined": "true",
"params": {
"windowSize": "4"
}
},
{
"field": "legalshortname",
"comparator": "jaroWinklerNormalizedName",
"weight": 0.1,
"countIfUndefined": "false",
"params": {}
}
],
"threshold": 0.9,
"aggregation": "W_MEAN",
"positive": "MATCH",
"negative": "NO_MATCH",
"undefined": "NO_MATCH",
"ignoreUndefined": "true"
}
},
"model" : [
{ "name" : "country", "type" : "String", "path" : "$.country.classid"},
{ "name" : "legalshortname", "type" : "String", "path" : "$.legalshortname.value"},
{ "name" : "legalname", "type" : "String", "path" : "$.legalname.value" },
{ "name" : "websiteurl", "type" : "URL", "path" : "$.websiteurl.value" },
{ "name" : "gridid", "type" : "String", "path" : "$.pid[?(@.qualifier.classid =='grid.ac')].value"},
{ "name" : "originalId", "type" : "String", "path" : "$.id" }
],
"blacklists" : {
"legalname" : []
},
"synonyms": {
"key::1": ["university","università","università studi","universitario","universitaria","université", "universite", "universitaire","universitaires","universidad","universitade","Universität","universitaet","Uniwersytet","университет","universiteit","πανεπιστήμιο","universitesi","universiteti", "universiti"],
"key::2": ["studies","studi","études","estudios","estudos","Studien","studia","исследования","studies","σπουδές"],
"key::3": ["advanced","superiore","supérieur","supérieure","supérieurs","supérieures","avancado","avancados","fortgeschrittene","fortgeschritten","zaawansowany","передовой","gevorderd","gevorderde","προχωρημένος","προχωρημένη","προχωρημένο","προχωρημένες","προχωρημένα","wyzsza"],
"key::4": ["institute","istituto","institut","instituto","instituto","Institut","instytut","институт","instituut","ινστιτούτο"],
"key::5": ["hospital","ospedale","hôpital","hospital","hospital","Krankenhaus","szpital","больница","ziekenhuis","νοσοκομείο"],
"key::6": ["research","ricerca","recherche","investigacion","pesquisa","Forschung","badania","исследования","onderzoek","έρευνα","erevna","erevnas"],
"key::7": ["college","collegio","colegio","faculdade","Hochschule","Szkoła Wyższa","Высшая школа","κολλέγιο"],
"key::8": ["foundation","fondazione","fondation","fundación","fundação","Stiftung","Fundacja","фонд","stichting","ίδρυμα","idryma"],
"key::9": ["center","centro","centre","centro","centro","zentrum","centrum","центр","centrum","κέντρο"],
"key::10": ["national","nazionale","national","nationale","nationaux","nationales","nacional","nacional","national","krajowy","национальный","nationaal","nationale","εθνικό"],
"key::11": ["association","associazione","association","asociación","associação","Verein","verband","stowarzyszenie","ассоциация","associatie"],
"key::12": ["society","societa","société","sociedad","sociedade","gesellschaft","społeczeństwo","общество","maatschappij","κοινωνία"],
"key::13": ["international","internazionale","international","internacional","internacional","international","międzynarodowy","Международный","internationaal","internationale","διεθνής","διεθνή","διεθνές"],
"key::14": ["community","comunita","communauté","comunidad","comunidade","Gemeinschaft","społeczność","сообщество","gemeenschap","κοινότητα"],
"key::15": ["school","scuola","école","escuela","escola","schule","Szkoła","школа","school","σχολείο"],
"key::16": ["education","educazione","éducation","educacion","Educação","Bildung","Edukacja","образование","opleiding","εκπαίδευση"],
"key::17": ["academy","accademia","académie","academia","academia","Akademie","akademie","академия","academie","ακαδημία"],
"key::18": ["public","pubblico","public","publique","publics","publiques","publico","publico","Öffentlichkeit","publiczny","публичный","publiek","publieke","δημόσιος","δημόσια","δημόσιο"],
"key::19": ["museum","museo","musée","mueso","museu","museum","muzeum","музей","museum","μουσείο"],
"key::20": ["group","gruppo","groupe","grupo","grupo","gruppe","grupa","группа","groep","ομάδα","όμιλος"],
"key::21": ["department","dipartimento","département","departamento","departamento","abteilung","departament","отдел","afdeling","τμήμα"],
"key::22": ["council","consiglio","conseil","Consejo","conselho","gesellschaft","rada","совет","raad","συμβούλιο"],
"key::23": ["library","biblioteca","bibliothèque","biblioteca","biblioteca","Bibliothek","biblioteka","библиотека","bibliotheek","βιβλιοθήκη"],
"key::24": ["ministry","ministero","ministère","ministerio","ministério","Ministerium","ministerstwo","министерство","ministerie","υπουργείο"],
"key::25": ["services","servizi","services","servicios","Serviços","Dienstleistungen","usługi","услуги","diensten","υπηρεσίες"],
"key::26": ["central","centrale","central","centrale","centrales","central","central","zentral","centralny","цетральный","centraal","κεντρικός","κεντρική","κεντρικό","κεντρικά"],
"key::27": ["general","generale","général","générale","généraux","générales","general","geral","general","Allgemeines","general","общий","algemeen","algemene","γενικός","γενική","γενικό","γενικά"],
"key::28": ["applied","applicati","appliqué","appliquée","appliqués","appliquées","aplicado","aplicada","angewendet","stosowany","прикладной","toegepast","toegepaste","εφαρμοσμένος","εφαρμοσμένη","εφαρμοσμένο","εφαρμοσμένα"],
"key::29": ["european","europee","europea","européen","européenne","européens","européennes","europeo","europeu","europäisch","europejski","европейский","Europees","Europese","ευρωπαϊκός","ευρωπαϊκή","ευρωπαϊκό","ευρωπαϊκά"],
"key::30": ["agency","agenzia","agence","agencia","agencia","agentur","agencja","агенция","agentschap","πρακτορείο"],
"key::31": ["laboratory","laboratorio","laboratoire","laboratorio","laboratorio","labor","laboratorium","лаборатория","laboratorium","εργαστήριο"],
"key::32": ["industry","industria","industrie","индустрия","industrie","βιομηχανία"],
"key::33": ["industrial","industriale","industriel","industrielle","industriels","industrielles","индустриальный","industrieel","βιομηχανικός","βιομηχανική","βιομηχανικό","βιομηχανικά","βιομηχανικές"],
"key::34": ["consortium","consorzio","consortium","консорциум","consortium","κοινοπραξία"],
"key::35": ["organization","organizzazione","organisation","organización","organização","organizacja","организация","organisatie","οργανισμός"],
"key::36": ["authority","autorità","autorité","авторитет","autoriteit"],
"key::37": ["federation","federazione","fédération","федерация","federatie","ομοσπονδία"],
"key::38": ["observatory","osservatorio","observatoire","обсерватория","observatorium","αστεροσκοπείο"],
"key::39": ["bureau","ufficio","bureau","офис","bureau","γραφείο"],
"key::40": ["company","impresa","compagnie","société","компания","bedrijf","εταιρία"],
"key::41": ["polytechnic","politecnico","polytechnique","политехника","polytechnisch","πολυτεχνείο","universita politecnica","polytechnic university","universidad politecnica","universitat politecnica","politechnika","politechniki","university technology","university science technology"],
"key::42": ["coalition","coalizione","coalition","коалиция","coalitie","συνασπισμός"],
"key::43": ["initiative","iniziativa","initiative","инициатива","initiatief","πρωτοβουλία"],
"key::44": ["academic","accademico","académique","universitaire","акадеческий academisch","ακαδημαϊκός","ακαδημαϊκή","ακαδημαϊκό","ακαδημαϊκές","ακαδημαϊκοί"],
"key::45": ["institution","istituzione","institution","институциональный","instelling","ινστιτούτο"],
"key::46": ["division","divisione","division","отделение","divisie","τμήμα"],
"key::47": ["committee","comitato","comité","комитет","commissie","επιτροπή"],
"key::48": ["promotion","promozione","продвижение","proothisis","forderung"],
"key::49": ["medical","medicine","clinical","medicina","clinici","médico","medicina","clínica","médico","medicina","clínica","medizinisch","Medizin","klinisch","medisch","geneeskunde","klinisch","ιατρικός","ιατρική","ιατρικό","ιατρικά","κλινικός","κλινική","κλινικό","κλινικά","tıbbi","tıp","klinik","orvosi","orvostudomány","klinikai","zdravniški","medicinski","klinični","meditsiini","kliinik","kliiniline"],
"key::50": ["technology","technological","tecnologia","tecnologie","tecnología","tecnológico","tecnologia","tecnológico","Technologie","technologisch","technologie","technologisch","τεχνολογία","τεχνολογικός","τεχνολογική","τεχνολογικό","teknoloji","teknolojik","technológia","technológiai","tehnologija","tehnološki","tehnoloogia","tehnoloogiline","technologii","technical","texniki","teknik"],
"key::51": ["science","scientific","scienza","scientifiche","scienze","ciencia","científico","ciência","científico","Wissenschaft","wissenschaftlich","wetenschap","wetenschappelijk","επιστήμη","επιστημονικός","επιστημονική","επιστημονικό","επιστημονικά","bilim","bilimsel","tudomány","tudományos","znanost","znanstveni","teadus","teaduslik",""],
"key::52": ["engineering","ingegneria","ingeniería","engenharia","Ingenieurwissenschaft","ingenieurswetenschappen","bouwkunde","μηχανικός","μηχανική","μηχανικό","mühendislik","mérnöki","Inženirstvo","inseneeria","inseneri",""],
"key::53": ["management","gestione","gestionale","gestionali","gestión","administración","gestão","administração","Verwaltung","management","διαχείριση","yönetim","menedzsment","vodstvo","upravljanje","management","juhtkond","juhtimine","haldus",""],
"key::54": ["energy","energia","energía","energia","Energie","energie","ενέργεια","enerji","energia","energija","energia",""],
"key::55": ["agricultural","agriculture","agricoltura","agricole","agrícola","agricultura","agrícola","agricultura","landwirtschaftlich","Landwirtschaft","landbouwkundig","landbouw","αγροτικός","αγροτική","αγροτικό","γεωργικός","γεωργική","γεωργικό","γεωργία","tarımsal","tarım","mezőgazdasági","mezőgazdaság","poljedelski","poljedelstvo","põllumajandus","põllumajanduslik",""],
"key::56": ["information","informazione","información","informação","Information","informatie","πληροφορία","bilgi","információ","informacija","informatsioon","informatycznych",""],
"key::57": ["social","sociali","social","social","Sozial","sociaal","maatschappelijk","κοινωνικός","κοινωνική","κοινωνικό","κοινωνικά","sosyal","szociális","družbeni","sotsiaal","sotsiaalne",""],
"key::58": ["environmental","ambiente","medioambiental","ambiente","medioambiente","meioambiente","Umwelt","milieu","milieuwetenschap","milieukunde","περιβαλλοντικός","περιβαλλοντική","περιβαλλοντικό","περιβαλλοντικά","çevre","környezeti","okoliški","keskonna",""],
"key::59": ["business","economia","economiche","economica","negocio","empresa","negócio","Unternehmen","bedrijf","bedrijfskunde","επιχείρηση","iş","üzleti","posel","ettevõte/äri",""],
"key::60": ["pharmaceuticals","pharmacy","farmacia","farmaceutica","farmacéutica","farmacia","farmacêutica","farmácia","Pharmazeutika","Arzneimittelkunde","farmaceutica","geneesmiddelen","apotheek","φαρμακευτικός","φαρμακευτική","φαρμακευτικό","φαρμακευτικά","φαρμακείο","ilaç","eczane","gyógyszerészeti","gyógyszertár","farmacevtika","lekarništvo","farmaatsia","farmatseutiline",""],
"key::61": ["healthcare","health services","salute","atenciónmédica","cuidadodelasalud","cuidadoscomasaúde","Gesundheitswesen","gezondheidszorg","ιατροφαρμακευτικήπερίθαλψη","sağlıkhizmeti","egészségügy","zdravstvo","tervishoid","tervishoiu",""],
"key::62": ["history","storia","historia","história","Geschichte","geschiedenis","geschiedkunde","ιστορία","tarih","történelem","zgodovina","ajalugu",""],
"key::63": ["materials","materiali","materia","materiales","materiais","materialen","υλικά","τεκμήρια","malzemeler","anyagok","materiali","materjalid","vahendid",""],
"key::64": ["economics","economia","economiche","economica","economía","economia","Wirtschaft","economie","οικονομικά","οικονομικέςεπιστήμες","ekonomi","közgazdaságtan","gospodarstvo","ekonomija","majanduslik","majandus",""],
"key::65": ["therapeutics","terapeutica","terapéutica","terapêutica","therapie","θεραπευτική","tedavibilimi","gyógykezelés","terapevtika","terapeutiline","ravi",""],
"key::66": ["oncology","oncologia","oncologico","oncología","oncologia","Onkologie","oncologie","ογκολογία","onkoloji","onkológia","onkologija","onkoloogia",""],
"key::67": ["natural","naturali","naturale","natural","natural","natürlich","natuurlijk","φυσικός","φυσική","φυσικό","φυσικά","doğal","természetes","naraven","loodus",""],
"key::68": ["educational","educazione","pedagogia","educacional","educativo","educacional","pädagogisch","educatief","εκπαιδευτικός","εκπαιδευτική","εκπαιδευτικό","εκπαιδευτικά","eğitimsel","oktatási","izobraževalen","haridus","hariduslik",""],
"key::69": ["biomedical","biomedica","biomédico","biomédico","biomedizinisch","biomedisch","βιοιατρικός","βιοιατρική","βιοιατρικό","βιοιατρικά","biyomedikal","orvosbiológiai","biomedicinski","biomeditsiiniline",""],
"key::70": ["veterinary","veterinaria","veterinarie","veterinaria","veterinária","tierärtzlich","veterinair","veeartsenijlkunde","κτηνιατρικός","κτηνιατρική","κτηνιατρικό","κτηνιατρικά","veteriner","állatorvosi","veterinar","veterinarski","veterinaaria",""],
"key::71": ["chemistry","chimica","química","química","Chemie","chemie","scheikunde","χημεία","kimya","kémia","kemija","keemia",""],
"key::72": ["security","sicurezza","seguridad","segurança","Sicherheit","veiligheid","ασφάλεια","güvenlik","biztonsági","varnost","turvalisus","julgeolek",""],
"key::73": ["biotechnology","biotecnologia","biotecnologie","biotecnología","biotecnologia","Biotechnologie","biotechnologie","βιοτεχνολογία","biyoteknoloji","biotechnológia","biotehnologija","biotehnoloogia",""],
"key::74": ["military","militare","militari","militar","militar","Militär","militair","leger","στρατιωτικός","στρατιωτική","στρατιωτικό","στρατιωτικά","askeri","katonai","vojaški","vojni","militaar","wojskowa",""],
"key::75": ["theological","teologia","teologico","teológico","tecnológica","theologisch","theologisch","θεολογικός","θεολογική","θεολογικό","θεολογικά","teolojik","technológiai","teološki","teoloogia","usuteadus","teoloogiline",""],
"key::76": ["electronics","elettronica","electrónica","eletrônicos","Elektronik","elektronica","ηλεκτρονική","elektronik","elektronika","elektronika","elektroonika",""],
"key::77": ["forestry","forestale","forestali","silvicultura","forestal","floresta","Forstwirtschaft","bosbouw","δασοκομία","δασολογία","ormancılık","erdészet","gozdarstvo","metsandus",""],
"key::78": ["maritime","marittima","marittime","marittimo","marítimo","marítimo","maritiem","ναυτικός","ναυτική","ναυτικό","ναυτικά","ναυτιλιακός","ναυτιλιακή","ναυτιλιακό","ναυτιλιακά","θαλάσσιος","θαλάσσια","θαλάσσιο","denizcilik","tengeri","morski","mere","merendus",""],
"key::79": ["sports","sport","deportes","esportes","Sport","sport","sportwetenschappen","άθληση","γυμναστικήδραστηριότητα","spor","sport","šport","sport","spordi",""],
"key::80": ["surgery","chirurgia","chirurgiche","cirugía","cirurgia","Chirurgie","chirurgie","heelkunde","εγχείρηση","επέμβαση","χειρουργικήεπέμβαση","cerrahi","sebészet","kirurgija","kirurgia",""],
"key::81": ["cultural","culturale","culturali","cultura","cultural","cultural","kulturell","cultureel","πολιτιστικός","πολιτιστική","πολιτιστικό","πολιτισμικός","πολιτισμική","πολιτισμικό","kültürel","kultúrális","kulturni","kultuuri","kultuuriline",""],
"key::82": ["computerscience","informatica","ordenador","computadora","informática","computación","cienciasdelacomputación","ciênciadacomputação","Computer","computer","υπολογιστής","ηλεκτρονικόςυπολογιστής","bilgisayar","számítógép","računalnik","arvuti",""],
"key::83": ["finance","financial","finanza","finanziarie","finanza","financiero","finanças","financeiro","Finanzen","finanziell","financiën","financieel","χρηματοοικονομικά","χρηματοδότηση","finanse","finansal","pénzügy","pénzügyi","finance","finančni","finants","finantsiline",""],
"key::84": ["communication","comunicazione","comuniciación","comunicação","Kommunikation","communication","επικοινωνία","iletişim","kommunikáció","komuniciranje","kommunikatsioon",""],
"key::85": ["justice","giustizia","justicia","justiça","Recht","Justiz","justitie","gerechtigheid","δικαιοσύνη","υπουργείοδικαιοσύνης","δίκαιο","adalet","igazságügy","pravo","õigus",""],
"key::86": ["aerospace","aerospaziale","aerospaziali","aeroespacio","aeroespaço","Luftfahrt","luchtvaart","ruimtevaart","αεροπορικός","αεροπορική","αεροπορικό","αεροναυπηγικός","αεροναυπηγική","αεροναυπηγικό","αεροναυπηγικά","havacılıkveuzay","légtér","zrakoplovstvo","atmosfäär","kosmos",""],
"key::87": ["dermatology","dermatologia","dermatología","dermatologia","Dermatologie","dermatologie","δρματολογία","dermatoloji","bőrgyógyászat","dermatológia","dermatologija","dermatoloogia",""],
"key::88": ["architecture","architettura","arquitectura","arquitetura","Architektur","architectuur","αρχιτεκτονική","mimarlık","építészet","arhitektura","arhitektuur",""],
"key::89": ["mathematics","matematica","matematiche","matemáticas","matemáticas","Mathematik","wiskunde","mathematica","μαθηματικά","matematik","matematika","matematika","matemaatika",""],
"key::90": ["language","lingue","linguistica","linguistiche","lenguaje","idioma","língua","idioma","Sprache","taal","taalkunde","γλώσσα","dil","nyelv","jezik","keel",""],
"key::91": ["neuroscience","neuroscienza","neurociencia","neurociência","Neurowissenschaft","neurowetenschappen","νευροεπιστήμη","nörobilim","idegtudomány","nevroznanost","neuroteadused",""],
"key::92": ["automation","automazione","automatización","automação","Automatisierung","automatisering","αυτοματοποίηση","otomasyon","automatizálás","avtomatizacija","automatiseeritud",""],
"key::93": ["pediatric","pediatria","pediatriche","pediatrico","pediátrico","pediatría","pediátrico","pediatria","pädiatrisch","pediatrische","παιδιατρική","pediatrik","gyermekgyógyászat","pediatrija","pediaatria",""],
"key::94": ["photonics","fotonica","fotoniche","fotónica","fotônica","Photonik","fotonica","φωτονική","fotonik","fotonika","fotonika","fotoonika",""],
"key::95": ["mechanics", "mechanical", "meccanica","meccaniche","mecánica","mecânica","Mechanik","Maschinenbau","mechanica","werktuigkunde","μηχανικής","mekanik","gépészet","mehanika","mehaanika",""],
"key::96": ["psychiatrics","psichiatria","psichiatrica","psichiatriche","psiquiatría","psiquiatria","Psychiatrie","psychiatrie","ψυχιατρική","psikiyatrik","pszihiátria","psihiatrija","psühhaatria",""],
"key::97": ["psychology","fisiologia","psicología","psicologia","Psychologie","psychologie","ψυχολογία","psikoloji","pszihológia","psihologija","psühholoogia",""],
"key::98": ["automotive","industriaautomobilistica","industriadelautomóvil","automotriz","industriaautomotriz","automotivo","Automobilindustrie","autoindustrie","αυτοκίνητος","αυτοκίνητη","αυτοκίνητο","αυτοκινούμενος","αυτοκινούμενη","αυτοκινούμενο","αυτοκινητιστικός","αυτοκινητιστική","αυτοκινητιστικό","otomotiv","autóipari","samogiben","avtomobilskaindustrija","auto-",""],
"key::99": ["neurology","neurologia","neurologiche","neurología","neurologia","Neurologie","neurologie","zenuwleer","νευρολογία","nöroloji","neurológia","ideggyógyászat","nevrologija","neuroloogia",""],
"key::100": ["geology","geologia","geologiche","geología","geologia","Geologie","geologie","aardkunde","γεωλογία","jeoloji","geológia","földtudomány","geologija","geoloogia",""],
"key::101": ["microbiology","microbiologia","micro-biologia","microbiologiche","microbiología","microbiologia","Mikrobiologie","microbiologie","μικροβιολογία","mikrobiyoloji","mikrobiológia","mikrobiologija","mikrobioloogia",""],
"key::102": ["informatics","informatica","informática","informática","informatica",""],
"key::103": ["forschungsgemeinschaft","comunita ricerca","research community","research foundation","research association"],
"key::104": ["commerce","ticaret","ticarət","commercio","trade","handel","comercio"],
"key::105" : ["state", "stato", "etade", "estado", "statale", "etat", "zustand", "estado"],
"key::106" : ["seminary", "seminario", "seminaire", "seminar"],
"key::107" : ["agricultural forestry", "af", "a f"],
"key::108" : ["agricultural mechanical", "am", "a m"],
"key::109" : ["catholic", "catholique", "katholische", "catolica", "cattolica", "catolico"]
}
}
}

280
dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dedup/conf/pub.curr.conf.json Normal file
View File

@ -0,0 +1,280 @@
{
"wf" : {
"threshold" : "0.99",
"dedupRun" : "001",
"entityType" : "result",
"subEntityType" : "resulttype",
"subEntityValue" : "publication",
"orderField" : "title",
"queueMaxSize" : "2000",
"groupMaxSize" : "100",
"maxChildren" : "100",
"idPath": "$.id",
"slidingWindowSize" : "200",
"rootBuilder" : [ "result", "resultProject_outcome_isProducedBy", "resultResult_publicationDataset_isRelatedTo", "resultResult_similarity_isAmongTopNSimilarDocuments", "resultResult_similarity_hasAmongTopNSimilarDocuments", "resultOrganization_affiliation_isAffiliatedWith", "resultResult_part_hasPart", "resultResult_part_isPartOf", "resultResult_supplement_isSupplementTo", "resultResult_supplement_isSupplementedBy", "resultResult_version_isVersionOf" ],
"includeChildren" : "true"
},
"pace" : {
"clustering" : [
{ "name" : "ngrampairs", "fields" : [ "title" ], "params" : { "max" : "1", "ngramLen" : "3"} },
{ "name" : "suffixprefix", "fields" : [ "title" ], "params" : { "max" : "1", "len" : "3" } },
{ "name" : "lowercase", "fields" : [ "doi" ], "params" : { } }
],
"strictConditions" : [
{ "name" : "pidMatch", "fields" : [ "pid" ] }
],
"conditions" : [
{ "name" : "titleVersionMatch", "fields" : [ "title" ] },
{ "name" : "sizeMatch", "fields" : [ "authors" ] }
],
"model" : [
{ "name" : "doi", "algo" : "Null", "type" : "String", "weight" : "0.0", "ignoreMissing" : "true", "path" : "$.pid[?(@.qualifier.classid ==\"doi\")].value" },
{ "name" : "pid", "algo" : "Null", "type" : "JSON", "weight" : "0.0", "ignoreMissing" : "true", "path" : "$.pid", "overrideMatch" : "true" },
{ "name" : "title", "algo" : "LevensteinTitle", "type" : "String", "weight" : "1.0", "ignoreMissing" : "false", "path" : "$.title[?(@.qualifier.classid ==\"main title\")].value", "length" : 250, "size" : 5 },
{ "name" : "authors", "algo" : "Null", "type" : "List", "weight" : "0.0", "ignoreMissing" : "true", "path" : "$.author[*].fullname", "size" : 200 },
{ "name" : "resulttype", "algo" : "Null", "type" : "String", "weight" : "0.0", "ignoreMissing" : "false", "path" : "$.resulttype.classid" }
],
"synonyms": {},
"blacklists" : {
"title" : [
"^Inside Front Cover$",
"(?i)^Poster presentations$",
"^THE ASSOCIATION AND THE GENERAL MEDICAL COUNCIL$",
"^Problems with perinatal pathology\\.?$",
"(?i)^Cases? of Puerperal Convulsions$",
"(?i)^Operative Gyna?ecology$",
"(?i)^Mind the gap\\!?\\:?$",
"^Chronic fatigue syndrome\\.?$",
"^Cartas? ao editor Letters? to the Editor$",
"^Note from the Editor$",
"^Anesthesia Abstract$",
"^Annual report$",
"(?i)^“?THE RADICAL PREVENTION OF VENEREAL DISEASE\\.?”?$",
"(?i)^Graph and Table of Infectious Diseases?$",
"^Presentation$",
"(?i)^Reviews and Information on Publications$",
"(?i)^PUBLIC HEALTH SERVICES?$",
"(?i)^COMBINED TEXT-?BOOK OF OBSTETRICS AND GYN(Æ|ae)COLOGY$",
"(?i)^Adrese autora$",
"(?i)^Systematic Part .*\\. Catalogus Fossilium Austriae, Band 2: Echinoidea neogenica$",
"(?i)^Acknowledgement to Referees$",
"(?i)^Behçet's disease\\.?$",
"(?i)^Isolation and identification of restriction endonuclease.*$",
"(?i)^CEREBROVASCULAR DISEASES?.?$",
"(?i)^Screening for abdominal aortic aneurysms?\\.?$",
"^Event management$",
"(?i)^Breakfast and Crohn's disease.*\\.?$",
"^Cálculo de concentraciones en disoluciones acuosas. Ejercicio interactivo\\..*\\.$",
"(?i)^Genetic and functional analyses of SHANK2 mutations suggest a multiple hit model of Autism spectrum disorders?\\.?$",
"^Gushi hakubutsugaku$",
"^Starobosanski nadpisi u Bosni i Hercegovini \\(.*\\)$",
"^Intestinal spirocha?etosis$",
"^Treatment of Rodent Ulcer$",
"(?i)^\\W*Cloud Computing\\W*$",
"^Compendio mathematico : en que se contienen todas las materias mas principales de las Ciencias que tratan de la cantidad$",
"^Free Communications, Poster Presentations: Session [A-F]$",
"^“The Historical Aspects? of Quackery\\.?”$",
"^A designated centre for people with disabilities operated by St John of God Community Services (Limited|Ltd), Louth$",
"^P(er|re)-Mile Premiums for Auto Insurance\\.?$",
"(?i)^Case Report$",
"^Boletín Informativo$",
"(?i)^Glioblastoma Multiforme$",
"(?i)^Nuevos táxones animales descritos en la península Ibérica y Macaronesia desde 1994 \\(.*\\)$",
"^Zaměstnanecké výhody$",
"(?i)^The Economics of Terrorism and Counter-Terrorism: A Survey \\(Part .*\\)$",
"(?i)^Carotid body tumours?\\.?$",
"(?i)^\\[Españoles en Francia : La condición Emigrante.*\\]$",
"^Avant-propos$",
"(?i)^St\\. Patrick's Cathedral, Dublin, County Dublin - Head(s)? and Capital(s)?$",
"(?i)^St\\. Patrick's Cathedral, Dublin, County Dublin - Bases?$",
"(?i)^PUBLIC HEALTH VERSUS THE STATE$",
"^Viñetas de Cortázar$",
"(?i)^Search for heavy neutrinos and W(\\[|_|\\(|_\\{|-)?R(\\]|\\)|\\})? bosons with right-handed couplings in a left-right symmetric model in pp collisions at.*TeV(\\.)?$",
"(?i)^Measurement of the pseudorapidity and centrality dependence of the transverse energy density in Pb(-?)Pb collisions at.*tev(\\.?)$",
"(?i)^Search for resonances decaying into top-quark pairs using fully hadronic decays in pp collisions with ATLAS at.*TeV$",
"(?i)^Search for neutral minimal supersymmetric standard model Higgs bosons decaying to tau pairs in pp collisions at.*tev$",
"(?i)^Relatório de Estágio (de|em) Angiologia e Cirurgia Vascular$",
"^Aus der AGMB$",
"^Znanstveno-stručni prilozi$",
"(?i)^Zhodnocení finanční situace podniku a návrhy na zlepšení$",
"(?i)^Evaluation of the Financial Situation in the Firm and Proposals to its Improvement$",
"(?i)^Hodnocení finanční situace podniku a návrhy na její zlepšení$",
"^Finanční analýza podniku$",
"^Financial analysis( of business)?$",
"(?i)^Textbook of Gyn(a)?(Æ)?(e)?cology$",
"^Jikken nihon shūshinsho$",
"(?i)^CORONER('|s)(s|') INQUESTS$",
"(?i)^(Μελέτη παραγόντων )?risk management( για ανάπτυξη και εφαρμογή ενός πληροφοριακού συστήματος| και ανάπτυξη συστήματος)?$",
"(?i)^Consultants' contract(s)?$",
"(?i)^Upute autorima$",
"(?i)^Bijdrage tot de Kennis van den Godsdienst der Dajaks van Lan(d|f)ak en Tajan$",
"^Joshi shin kokubun$",
"^Kōtō shōgaku dokuhon nōson'yō$",
"^Jinjō shōgaku shōka$",
"^Shōgaku shūjichō$",
"^Nihon joshi dokuhon$",
"^Joshi shin dokuhon$",
"^Chūtō kanbun dokuhon$",
"^Wabun dokuhon$",
"(?i)^(Analysis of economy selected village or town|Rozbor hospodaření vybrané obce či města)$",
"(?i)^cardiac rehabilitation$",
"(?i)^Analytical summary$",
"^Thesaurus resolutionum Sacrae Congregationis Concilii$",
"(?i)^Sumario analítico(\\s{1})?(Analitic summary)?$",
"^Prikazi i osvrti$",
"^Rodinný dům s provozovnou$",
"^Family house with an establishment$",
"^Shinsei chūtō shin kokugun$",
"^Pulmonary alveolar proteinosis(\\.?)$",
"^Shinshū kanbun$",
"^Viñeta(s?) de Rodríguez$",
"(?i)^RUBRIKA UREDNIKA$",
"^A Matching Model of the Academic Publication Market$",
"^Yōgaku kōyō$",
"^Internetový marketing$",
"^Internet marketing$",
"^Chūtō kokugo dokuhon$",
"^Kokugo dokuhon$",
"^Antibiotic Cover for Dental Extraction(s?)$",
"^Strategie podniku$",
"^Strategy of an Enterprise$",
"(?i)^respiratory disease(s?)(\\.?)$",
"^Award(s?) for Gallantry in Civil Defence$",
"^Podniková kultura$",
"^Corporate Culture$",
"^Severe hyponatraemia in hospital inpatient(s?)(\\.?)$",
"^Pracovní motivace$",
"^Work Motivation$",
"^Kaitei kōtō jogaku dokuhon$",
"^Konsolidovaná účetní závěrka$",
"^Consolidated Financial Statements$",
"(?i)^intracranial tumour(s?)$",
"^Climate Change Mitigation Options and Directed Technical Change: A Decentralized Equilibrium Analysis$",
"^\\[CERVECERIAS MAHOU(\\.|\\:) INTERIOR\\] \\[Material gráfico\\]$",
"^Housing Market Dynamics(\\:|\\.) On the Contribution of Income Shocks and Credit Constraint(s?)$",
"^\\[Funciones auxiliares de la música en Radio París,.*\\]$",
"^Úroveň motivačního procesu jako způsobu vedení lidí$",
"^The level of motivation process as a leadership$",
"^Pay-beds in N(\\.?)H(\\.?)S(\\.?) Hospitals$",
"(?i)^news and events$",
"(?i)^NOVOSTI I DOGAĐAJI$",
"^Sansū no gakushū$",
"^Posouzení informačního systému firmy a návrh změn$",
"^Information System Assessment and Proposal for ICT Modification$",
"^Stresové zatížení pracovníků ve vybrané profesi$",
"^Stress load in a specific job$",
"^Sunday: Poster Sessions, Pt.*$",
"^Monday: Poster Sessions, Pt.*$",
"^Wednesday: Poster Sessions, Pt.*",
"^Tuesday: Poster Sessions, Pt.*$",
"^Analýza reklamy$",
"^Analysis of advertising$",
"^Shōgaku shūshinsho$",
"^Shōgaku sansū$",
"^Shintei joshi kokubun$",
"^Taishō joshi kokubun dokuhon$",
"^Joshi kokubun$",
"^Účetní uzávěrka a účetní závěrka v ČR$",
"(?i)^The \"?Causes\"? of Cancer$",
"^Normas para la publicación de artículos$",
"^Editor('|s)(s|') [Rr]eply$",
"^Editor(’|s)(s|’) letter$",
"^Redaktoriaus žodis$",
"^DISCUSSION ON THE PRECEDING PAPER$",
"^Kōtō shōgaku shūshinsho jidōyō$",
"^Shōgaku nihon rekishi$",
"^(Theory of the flow of action currents in isolated myelinated nerve fibers).*$",
"^Préface$",
"^Occupational [Hh]ealth [Ss]ervices.$",
"^In Memoriam Professor Toshiyuki TAKESHIMA$",
"^Účetní závěrka ve vybraném podniku.*$",
"^Financial statements in selected company$",
"^Abdominal [Aa]ortic [Aa]neurysms.*$",
"^Pseudomyxoma peritonei$",
"^Kazalo autora$",
"(?i)^uvodna riječ$",
"^Motivace jako způsob vedení lidí$",
"^Motivation as a leadership$",
"^Polyfunkční dům$",
"^Multi\\-funkcional building$",
"^Podnikatelský plán$",
"(?i)^Podnikatelský záměr$",
"(?i)^Business Plan$",
"^Oceňování nemovitostí$",
"^Marketingová komunikace$",
"^Marketing communication$",
"^Sumario Analítico$",
"^Riječ uredništva$",
"^Savjetovanja i priredbe$",
"^Índice$",
"^(Starobosanski nadpisi).*$",
"^Vzdělávání pracovníků v organizaci$",
"^Staff training in organization$",
"^(Life Histories of North American Geometridae).*$",
"^Strategická analýza podniku$",
"^Strategic Analysis of an Enterprise$",
"^Sadržaj$",
"^Upute suradnicima$",
"^Rodinný dům$",
"(?i)^Fami(l)?ly house$",
"^Upute autorima$",
"^Strategic Analysis$",
"^Finanční analýza vybraného podniku$",
"^Finanční analýza$",
"^Riječ urednika$",
"(?i)^Content(s?)$",
"(?i)^Inhalt$",
"^Jinjō shōgaku shūshinsho jidōyō$",
"(?i)^Index$",
"^Chūgaku kokubun kyōkasho$",
"^Retrato de una mujer$",
"^Retrato de un hombre$",
"^Kōtō shōgaku dokuhon$",
"^Shotōka kokugo$",
"^Shōgaku dokuhon$",
"^Jinjō shōgaku kokugo dokuhon$",
"^Shinsei kokugo dokuhon$",
"^Teikoku dokuhon$",
"^Instructions to Authors$",
"^KİTAP TAHLİLİ$",
"^PRZEGLĄD PIŚMIENNICTWA$",
"(?i)^Presentación$",
"^İçindekiler$",
"(?i)^Tabl?e of contents$",
"^(CODICE DEL BEATO DE LOS REYES FERNANDO I Y SANCHA).*$",
"^(\\[MADRID\\. BIBL\\. NAC\\. N.*KING FERDINAND I.*FROM SAN ISIDORO DE LEON\\. FACUNDUS SCRIPSIT DATED.*\\]).*",
"^Editorial( Board)?$",
"(?i)^Editorial \\(English\\)$",
"^Editörden$",
"^(Corpus Oral Dialectal \\(COD\\)\\.).*$",
"^(Kiri Karl Morgensternile).*$",
"^(\\[Eksliibris Aleksandr).*\\]$",
"^(\\[Eksliibris Aleksandr).*$",
"^(Eksliibris Aleksandr).*$",
"^(Kiri A\\. de Vignolles).*$",
"^(2 kirja Karl Morgensternile).*$",
"^(Pirita kloostri idaosa arheoloogilised).*$",
"^(Kiri tundmatule).*$",
"^(Kiri Jenaer Allgemeine Literaturzeitung toimetusele).*$",
"^(Eksliibris Nikolai Birukovile).*$",
"^(Eksliibris Nikolai Issakovile).*$",
"^(WHP Cruise Summary Information of section).*$",
"^(Measurement of the top quark\\-pair production cross section with ATLAS in pp collisions at).*$",
"^(Measurement of the spin\\-dependent structure function).*",
"(?i)^.*authors['’′]? reply\\.?$",
"(?i)^.*authors['’′]? response\\.?$"
]
}
}
}

386
dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dedup/conf/pub_dt.curr.conf.json Normal file
View File

@ -0,0 +1,386 @@
{
"wf": {
"threshold": "0.99",
"dedupRun": "001",
"entityType": "result",
"subEntityType": "resulttype",
"subEntityValue": "publication",
"orderField": "title",
"queueMaxSize": "2000",
"groupMaxSize": "100",
"maxChildren": "100",
"slidingWindowSize": "200",
"rootBuilder": [
"result",
"resultProject_outcome_isProducedBy",
"resultResult_publicationDataset_isRelatedTo",
"resultResult_similarity_isAmongTopNSimilarDocuments",
"resultResult_similarity_hasAmongTopNSimilarDocuments",
"resultOrganization_affiliation_isAffiliatedWith",
"resultResult_part_hasPart",
"resultResult_part_isPartOf",
"resultResult_supplement_isSupplementTo",
"resultResult_supplement_isSupplementedBy",
"resultResult_version_isVersionOf"
],
"includeChildren": "true",
"maxIterations": 20,
"idPath": "$.id"
},
"pace": {
"clustering": [
{
"name": "ngrampairs",
"fields": [
"title"
],
"params": {
"max": "1",
"ngramLen": "3"
}
},
{
"name": "suffixprefix",
"fields": [
"title"
],
"params": {
"max": "1",
"len": "3"
}
},
{
"name": "lowercase",
"fields": [
"doi"
],
"params": {}
}
],
"decisionTree": {
"start": {
"fields": [
{
"field": "pid",
"comparator": "jsonListMatch",
"weight": 1.0,
"countIfUndefined": "false",
"params": {
"jpath_value": "$.value",
"jpath_classid": "$.qualifier.classid"
}
}
],
"threshold": 0.5,
"aggregation": "AVG",
"positive": "MATCH",
"negative": "layer2",
"undefined": "layer2",
"ignoreUndefined": "true"
},
"layer2": {
"fields": [
{
"field": "title",
"comparator": "titleVersionMatch",
"weight": 1.0,
"countIfUndefined": "false",
"params": {}
},
{
"field": "authors",
"comparator": "sizeMatch",
"weight": 1.0,
"countIfUndefined": "false",
"params": {}
}
],
"threshold": 1.0,
"aggregation": "AND",
"positive": "layer3",
"negative": "NO_MATCH",
"undefined": "layer3",
"ignoreUndefined": "false"
},
"layer3": {
"fields": [
{
"field": "title",
"comparator": "levensteinTitle",
"weight": 1.0,
"countIfUndefined": "true",
"params": {}
}
],
"threshold": 0.99,
"aggregation": "AVG",
"positive": "MATCH",
"negative": "NO_MATCH",
"undefined": "NO_MATCH",
"ignoreUndefined": "true"
}
},
"model": [
{
"name": "doi",
"type": "String",
"path": "$.pid[?(@.qualifier.classid == 'doi')].value"
},
{
"name": "pid",
"type": "JSON",
"path": "$.pid",
"overrideMatch": "true"
},
{
"name": "title",
"type": "String",
"path": "$.title[?(@.qualifier.classid == 'main title')].value",
"length": 250,
"size": 5
},
{
"name": "authors",
"type": "List",
"path": "$.author[*].fullname",
"size": 200
},
{
"name": "resulttype",
"type": "String",
"path": "$.resulttype.classid"
}
],
"blacklists": {
"title": [
"^Inside Front Cover$",
"(?i)^Poster presentations$",
"^THE ASSOCIATION AND THE GENERAL MEDICAL COUNCIL$",
"^Problems with perinatal pathology\\.?$",
"(?i)^Cases? of Puerperal Convulsions$",
"(?i)^Operative Gyna?ecology$",
"(?i)^Mind the gap\\!?\\:?$",
"^Chronic fatigue syndrome\\.?$",
"^Cartas? ao editor Letters? to the Editor$",
"^Note from the Editor$",
"^Anesthesia Abstract$",
"^Annual report$",
"(?i)^“?THE RADICAL PREVENTION OF VENEREAL DISEASE\\.?”?$",
"(?i)^Graph and Table of Infectious Diseases?$",
"^Presentation$",
"(?i)^Reviews and Information on Publications$",
"(?i)^PUBLIC HEALTH SERVICES?$",
"(?i)^COMBINED TEXT-?BOOK OF OBSTETRICS AND GYN(Æ|ae)COLOGY$",
"(?i)^Adrese autora$",
"(?i)^Systematic Part .*\\. Catalogus Fossilium Austriae, Band 2: Echinoidea neogenica$",
"(?i)^Acknowledgement to Referees$",
"(?i)^Behçet's disease\\.?$",
"(?i)^Isolation and identification of restriction endonuclease.*$",
"(?i)^CEREBROVASCULAR DISEASES?.?$",
"(?i)^Screening for abdominal aortic aneurysms?\\.?$",
"^Event management$",
"(?i)^Breakfast and Crohn's disease.*\\.?$",
"^Cálculo de concentraciones en disoluciones acuosas. Ejercicio interactivo\\..*\\.$",
"(?i)^Genetic and functional analyses of SHANK2 mutations suggest a multiple hit model of Autism spectrum disorders?\\.?$",
"^Gushi hakubutsugaku$",
"^Starobosanski nadpisi u Bosni i Hercegovini \\(.*\\)$",
"^Intestinal spirocha?etosis$",
"^Treatment of Rodent Ulcer$",
"(?i)^\\W*Cloud Computing\\W*$",
"^Compendio mathematico : en que se contienen todas las materias mas principales de las Ciencias que tratan de la cantidad$",
"^Free Communications, Poster Presentations: Session [A-F]$",
"^“The Historical Aspects? of Quackery\\.?”$",
"^A designated centre for people with disabilities operated by St John of God Community Services (Limited|Ltd), Louth$",
"^P(er|re)-Mile Premiums for Auto Insurance\\.?$",
"(?i)^Case Report$",
"^Boletín Informativo$",
"(?i)^Glioblastoma Multiforme$",
"(?i)^Nuevos táxones animales descritos en la península Ibérica y Macaronesia desde 1994 \\(.*\\)$",
"^Zaměstnanecké výhody$",
"(?i)^The Economics of Terrorism and Counter-Terrorism: A Survey \\(Part .*\\)$",
"(?i)^Carotid body tumours?\\.?$",
"(?i)^\\[Españoles en Francia : La condición Emigrante.*\\]$",
"^Avant-propos$",
"(?i)^St\\. Patrick's Cathedral, Dublin, County Dublin - Head(s)? and Capital(s)?$",
"(?i)^St\\. Patrick's Cathedral, Dublin, County Dublin - Bases?$",
"(?i)^PUBLIC HEALTH VERSUS THE STATE$",
"^Viñetas de Cortázar$",
"(?i)^Search for heavy neutrinos and W(\\[|_|\\(|_\\{|-)?R(\\]|\\)|\\})? bosons with right-handed couplings in a left-right symmetric model in pp collisions at.*TeV(\\.)?$",
"(?i)^Measurement of the pseudorapidity and centrality dependence of the transverse energy density in Pb(-?)Pb collisions at.*tev(\\.?)$",
"(?i)^Search for resonances decaying into top-quark pairs using fully hadronic decays in pp collisions with ATLAS at.*TeV$",
"(?i)^Search for neutral minimal supersymmetric standard model Higgs bosons decaying to tau pairs in pp collisions at.*tev$",
"(?i)^Relatório de Estágio (de|em) Angiologia e Cirurgia Vascular$",
"^Aus der AGMB$",
"^Znanstveno-stručni prilozi$",
"(?i)^Zhodnocení finanční situace podniku a návrhy na zlepšení$",
"(?i)^Evaluation of the Financial Situation in the Firm and Proposals to its Improvement$",
"(?i)^Hodnocení finanční situace podniku a návrhy na její zlepšení$",
"^Finanční analýza podniku$",
"^Financial analysis( of business)?$",
"(?i)^Textbook of Gyn(a)?(Æ)?(e)?cology$",
"^Jikken nihon shūshinsho$",
"(?i)^CORONER('|s)(s|') INQUESTS$",
"(?i)^(Μελέτη παραγόντων )?risk management( για ανάπτυξη και εφαρμογή ενός πληροφοριακού συστήματος| και ανάπτυξη συστήματος)?$",
"(?i)^Consultants' contract(s)?$",
"(?i)^Upute autorima$",
"(?i)^Bijdrage tot de Kennis van den Godsdienst der Dajaks van Lan(d|f)ak en Tajan$",
"^Joshi shin kokubun$",
"^Kōtō shōgaku dokuhon nōson'yō$",
"^Jinjō shōgaku shōka$",
"^Shōgaku shūjichō$",
"^Nihon joshi dokuhon$",
"^Joshi shin dokuhon$",
"^Chūtō kanbun dokuhon$",
"^Wabun dokuhon$",
"(?i)^(Analysis of economy selected village or town|Rozbor hospodaření vybrané obce či města)$",
"(?i)^cardiac rehabilitation$",
"(?i)^Analytical summary$",
"^Thesaurus resolutionum Sacrae Congregationis Concilii$",
"(?i)^Sumario analítico(\\s{1})?(Analitic summary)?$",
"^Prikazi i osvrti$",
"^Rodinný dům s provozovnou$",
"^Family house with an establishment$",
"^Shinsei chūtō shin kokugun$",
"^Pulmonary alveolar proteinosis(\\.?)$",
"^Shinshū kanbun$",
"^Viñeta(s?) de Rodríguez$",
"(?i)^RUBRIKA UREDNIKA$",
"^A Matching Model of the Academic Publication Market$",
"^Yōgaku kōyō$",
"^Internetový marketing$",
"^Internet marketing$",
"^Chūtō kokugo dokuhon$",
"^Kokugo dokuhon$",
"^Antibiotic Cover for Dental Extraction(s?)$",
"^Strategie podniku$",
"^Strategy of an Enterprise$",
"(?i)^respiratory disease(s?)(\\.?)$",
"^Award(s?) for Gallantry in Civil Defence$",
"^Podniková kultura$",
"^Corporate Culture$",
"^Severe hyponatraemia in hospital inpatient(s?)(\\.?)$",
"^Pracovní motivace$",
"^Work Motivation$",
"^Kaitei kōtō jogaku dokuhon$",
"^Konsolidovaná účetní závěrka$",
"^Consolidated Financial Statements$",
"(?i)^intracranial tumour(s?)$",
"^Climate Change Mitigation Options and Directed Technical Change: A Decentralized Equilibrium Analysis$",
"^\\[CERVECERIAS MAHOU(\\.|\\:) INTERIOR\\] \\[Material gráfico\\]$",
"^Housing Market Dynamics(\\:|\\.) On the Contribution of Income Shocks and Credit Constraint(s?)$",
"^\\[Funciones auxiliares de la música en Radio París,.*\\]$",
"^Úroveň motivačního procesu jako způsobu vedení lidí$",
"^The level of motivation process as a leadership$",
"^Pay-beds in N(\\.?)H(\\.?)S(\\.?) Hospitals$",
"(?i)^news and events$",
"(?i)^NOVOSTI I DOGAĐAJI$",
"^Sansū no gakushū$",
"^Posouzení informačního systému firmy a návrh změn$",
"^Information System Assessment and Proposal for ICT Modification$",
"^Stresové zatížení pracovníků ve vybrané profesi$",
"^Stress load in a specific job$",
"^Sunday: Poster Sessions, Pt.*$",
"^Monday: Poster Sessions, Pt.*$",
"^Wednesday: Poster Sessions, Pt.*",
"^Tuesday: Poster Sessions, Pt.*$",
"^Analýza reklamy$",
"^Analysis of advertising$",
"^Shōgaku shūshinsho$",
"^Shōgaku sansū$",
"^Shintei joshi kokubun$",
"^Taishō joshi kokubun dokuhon$",
"^Joshi kokubun$",
"^Účetní uzávěrka a účetní závěrka v ČR$",
"(?i)^The \"?Causes\"? of Cancer$",
"^Normas para la publicación de artículos$",
"^Editor('|s)(s|') [Rr]eply$",
"^Editor(’|s)(s|’) letter$",
"^Redaktoriaus žodis$",
"^DISCUSSION ON THE PRECEDING PAPER$",
"^Kōtō shōgaku shūshinsho jidōyō$",
"^Shōgaku nihon rekishi$",
"^(Theory of the flow of action currents in isolated myelinated nerve fibers).*$",
"^Préface$",
"^Occupational [Hh]ealth [Ss]ervices.$",
"^In Memoriam Professor Toshiyuki TAKESHIMA$",
"^Účetní závěrka ve vybraném podniku.*$",
"^Financial statements in selected company$",
"^Abdominal [Aa]ortic [Aa]neurysms.*$",
"^Pseudomyxoma peritonei$",
"^Kazalo autora$",
"(?i)^uvodna riječ$",
"^Motivace jako způsob vedení lidí$",
"^Motivation as a leadership$",
"^Polyfunkční dům$",
"^Multi\\-funkcional building$",
"^Podnikatelský plán$",
"(?i)^Podnikatelský záměr$",
"(?i)^Business Plan$",
"^Oceňování nemovitostí$",
"^Marketingová komunikace$",
"^Marketing communication$",
"^Sumario Analítico$",
"^Riječ uredništva$",
"^Savjetovanja i priredbe$",
"^Índice$",
"^(Starobosanski nadpisi).*$",
"^Vzdělávání pracovníků v organizaci$",
"^Staff training in organization$",
"^(Life Histories of North American Geometridae).*$",
"^Strategická analýza podniku$",
"^Strategic Analysis of an Enterprise$",
"^Sadržaj$",
"^Upute suradnicima$",
"^Rodinný dům$",
"(?i)^Fami(l)?ly house$",
"^Upute autorima$",
"^Strategic Analysis$",
"^Finanční analýza vybraného podniku$",
"^Finanční analýza$",
"^Riječ urednika$",
"(?i)^Content(s?)$",
"(?i)^Inhalt$",
"^Jinjō shōgaku shūshinsho jidōyō$",
"(?i)^Index$",
"^Chūgaku kokubun kyōkasho$",
"^Retrato de una mujer$",
"^Retrato de un hombre$",
"^Kōtō shōgaku dokuhon$",
"^Shotōka kokugo$",
"^Shōgaku dokuhon$",
"^Jinjō shōgaku kokugo dokuhon$",
"^Shinsei kokugo dokuhon$",
"^Teikoku dokuhon$",
"^Instructions to Authors$",
"^KİTAP TAHLİLİ$",
"^PRZEGLĄD PIŚMIENNICTWA$",
"(?i)^Presentación$",
"^İçindekiler$",
"(?i)^Tabl?e of contents$",
"^(CODICE DEL BEATO DE LOS REYES FERNANDO I Y SANCHA).*$",
"^(\\[MADRID\\. BIBL\\. NAC\\. N.*KING FERDINAND I.*FROM SAN ISIDORO DE LEON\\. FACUNDUS SCRIPSIT DATED.*\\]).*",
"^Editorial( Board)?$",
"(?i)^Editorial \\(English\\)$",
"^Editörden$",
"^(Corpus Oral Dialectal \\(COD\\)\\.).*$",
"^(Kiri Karl Morgensternile).*$",
"^(\\[Eksliibris Aleksandr).*\\]$",
"^(\\[Eksliibris Aleksandr).*$",
"^(Eksliibris Aleksandr).*$",
"^(Kiri A\\. de Vignolles).*$",
"^(2 kirja Karl Morgensternile).*$",
"^(Pirita kloostri idaosa arheoloogilised).*$",
"^(Kiri tundmatule).*$",
"^(Kiri Jenaer Allgemeine Literaturzeitung toimetusele).*$",
"^(Eksliibris Nikolai Birukovile).*$",
"^(Eksliibris Nikolai Issakovile).*$",
"^(WHP Cruise Summary Information of section).*$",
"^(Measurement of the top quark\\-pair production cross section with ATLAS in pp collisions at).*$",
"^(Measurement of the spin\\-dependent structure function).*",
"(?i)^.*authors['’′]? reply\\.?$",
"(?i)^.*authors['’′]? response\\.?$"
]
},
"synonyms": {}
}
}

1
dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dedup/conf/sample.json Normal file
View File

File diff suppressed because one or more lines are too long

3
dhp-workflows/dhp-dedup/src/test/resources/eu/dnetlib/dedup/json/authors_merge.json Normal file
View File

File diff suppressed because one or more lines are too long

2
dhp-workflows/docs/oozie-installer.markdown
View File

@ -73,7 +73,7 @@ Workflow definition requirements
This property can be set using maven `-D` switch.
`[oozie_app]` is the default directory name however it can be set to any value as soon as `oozieAppDir` property is provided with directory name as value.
`[oozie_app]` is the default directory name however it can be set to any value as soon as `oozieAppDir` property is provided with directory name as value.
Subworkflows are supported as well and subworkflow directories should be nested within `[oozie_app]` directory.

3
dhp-workflows/pom.xml
View File

@ -17,6 +17,7 @@
<module>dhp-aggregation</module>
<module>dhp-distcp</module>
<module>dhp-graph-mapper</module>
<module>dhp-dedup</module>
</modules>
<pluginRepositories>
@ -310,6 +311,7 @@
</executions>
</plugin>
<plugin>
<!-- this plugin prepares oozie installer package-->
@ -523,6 +525,7 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-failsafe-plugin</artifactId>
<version>${maven.failsave.plugin.version}</version>
<executions>
<execution>
<id>default-integration-test</id>

81
pom.xml
View File

@ -114,6 +114,12 @@
<version>${dhp.spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-graphx_2.11</artifactId>
<version>${dhp.spark.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>org.apache.commons</groupId>
@ -177,6 +183,7 @@
<version>${dhp.jackson.version}</version>
<scope>provided</scope>
</dependency>
<dependency>
<groupId>com.fasterxml.jackson.core</groupId>
<artifactId>jackson-annotations</artifactId>
@ -190,6 +197,12 @@
<scope>provided</scope>
</dependency>
<dependency>
<groupId>eu.dnetlib</groupId>
<artifactId>dnet-pace-core</artifactId>
<version>4.0.0-SNAPSHOT</version>
</dependency>
<dependency>
<groupId>javax.persistence</groupId>
@ -203,6 +216,21 @@
<artifactId>amqp-client</artifactId>
<version>5.6.0</version>
</dependency>
<dependency>
<groupId>com.jayway.jsonpath</groupId>
<artifactId>json-path</artifactId>
<version>2.4.0</version>
</dependency>
<dependency>
<groupId>com.arakelian</groupId>
<artifactId>java-jq</artifactId>
<version>0.10.1</version>
</dependency>
<dependency>
<groupId>edu.cmu</groupId>
<artifactId>secondstring</artifactId>
<version>1.0.0</version>
</dependency>
<dependency>
<groupId>org.apache.oozie</groupId>
@ -230,7 +258,7 @@
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.6.0</version>
<version>${maven.compiler.plugin.version}</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
@ -259,27 +287,6 @@
</executions>
</plugin>
<plugin>
<groupId>eu.dnetlib</groupId>
<artifactId>protoc-jar-maven-plugin</artifactId>
<version>1.1.0</version>
<executions>
<execution>
<phase>generate-sources</phase>
<goals>
<goal>run</goal>
</goals>
<configuration>
<protocVersion>${google.protobuf.version}</protocVersion>
<inputDirectories>
<include>src/main/resources</include>
</inputDirectories>
<outputDirectory>src/gen/java</outputDirectory>
</configuration>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
@ -342,6 +349,31 @@
</execution>
</executions>
</plugin>
<plugin>
<groupId>net.alchim31.maven</groupId>
<artifactId>scala-maven-plugin</artifactId>
<version>4.0.1</version>
<executions>
<execution>
<id>scala-compile-first</id>
<phase>initialize</phase>
<goals>
<goal>add-source</goal>
<goal>compile</goal>
</goals>
</execution>
<execution>
<id>scala-test-compile</id>
<phase>process-test-resources</phase>
<goals>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
<configuration>
<scalaVersion>${scala.version}</scalaVersion>
</configuration>
</plugin>
</plugins>
<extensions>
@ -380,14 +412,15 @@
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
<maven.compiler.plugin.version>3.6.0</maven.compiler.plugin.version>
<maven.failsave.plugin.version>2.22.2</maven.failsave.plugin.version>
<dhp.cdh.version>cdh5.9.2</dhp.cdh.version>
<dhp.hadoop.version>2.6.0-${dhp.cdh.version}</dhp.hadoop.version>
<dhp.oozie.version>4.1.0-${dhp.cdh.version}</dhp.oozie.version>
<dhp.spark.version>2.4.0.cloudera2</dhp.spark.version>
<dhp.jackson.version>2.9.6</dhp.jackson.version>
<dhp.commons.lang.version>3.5</dhp.commons.lang.version>
<scala.version>2.11.8</scala.version>
<scala.version>2.11.12</scala.version>
</properties>
</project>