D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 10 Projects 2 Releases 2 Wiki Activity

Merge branch 'master' of https://code-repo.d4science.org/D-Net/dnet-hadoop into orcid-no-doi

This commit is contained in:
Enrico Ottonello 2020-11-16 11:57:19 +01:00
parent 005f849674 6ab1ce53c9
commit c796adae24
29 changed files with 616 additions and 157 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
dhp-build/dhp-code-style/pom.xml
View File

@ -15,12 +15,12 @@
<snapshotRepository>
<id>dnet45-snapshots</id>
<name>DNet45 Snapshots</name>
<url>http://maven.research-infrastructures.eu/nexus/content/repositories/dnet45-snapshots</url>
<url>https://maven.d4science.org/nexus/content/repositories/dnet45-snapshots</url>
<layout>default</layout>
</snapshotRepository>
<repository>
<id>dnet45-releases</id>
<url>http://maven.research-infrastructures.eu/nexus/content/repositories/dnet45-releases</url>
<url>https://maven.d4science.org/nexus/content/repositories/dnet45-releases</url>
</repository>
</distributionManagement>

44
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/common/OafMapperUtils.java → dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/OafMapperUtils.java
View File

@ -1,5 +1,5 @@
package eu.dnetlib.dhp.oa.graph.raw.common;
package eu.dnetlib.dhp.schema.oaf;
import java.util.ArrayList;
import java.util.Arrays;
@ -13,19 +13,43 @@ import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.ExtraInfo;
import eu.dnetlib.dhp.schema.oaf.Field;
import eu.dnetlib.dhp.schema.oaf.Journal;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.OAIProvenance;
import eu.dnetlib.dhp.schema.oaf.OriginDescription;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.utils.DHPUtils;
public class OafMapperUtils {
public static Oaf merge(final Oaf o1, final Oaf o2) {
if (ModelSupport.isSubClass(o1, OafEntity.class)) {
if (ModelSupport.isSubClass(o1, Result.class)) {
return mergeResults((Result) o1, (Result) o2);
} else if (ModelSupport.isSubClass(o1, Datasource.class)) {
((Datasource) o1).mergeFrom((Datasource) o2);
} else if (ModelSupport.isSubClass(o1, Organization.class)) {
((Organization) o1).mergeFrom((Organization) o2);
} else if (ModelSupport.isSubClass(o1, Project.class)) {
((Project) o1).mergeFrom((Project) o2);
} else {
throw new RuntimeException("invalid OafEntity subtype:" + o1.getClass().getCanonicalName());
}
} else if (ModelSupport.isSubClass(o1, Relation.class)) {
((Relation) o1).mergeFrom((Relation) o2);
} else {
throw new RuntimeException("invalid Oaf type:" + o1.getClass().getCanonicalName());
}
return o1;
}
public static Result mergeResults(Result r1, Result r2) {
if (new ResultTypeComparator().compare(r1, r2) < 0) {
r1.mergeFrom(r2);
return r1;
} else {
r2.mergeFrom(r1);
return r2;
}
}
public static KeyValue keyValue(final String k, final String v) {
final KeyValue kv = new KeyValue();
kv.setKey(k);

49
dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/ResultTypeComparator.java Normal file
View File

@ -0,0 +1,49 @@
package eu.dnetlib.dhp.schema.oaf;
import java.util.Comparator;
import eu.dnetlib.dhp.schema.common.ModelConstants;
public class ResultTypeComparator implements Comparator<Result> {
@Override
public int compare(Result left, Result right) {
if (left == null && right == null)
return 0;
if (left == null)
return 1;
if (right == null)
return -1;
String lClass = left.getResulttype().getClassid();
String rClass = right.getResulttype().getClassid();
if (lClass.equals(rClass))
return 0;
if (lClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.DATASET_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.SOFTWARE_RESULTTYPE_CLASSID))
return 1;
if (lClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
return -1;
if (rClass.equals(ModelConstants.ORP_RESULTTYPE_CLASSID))
return 1;
// Else (but unlikely), lexicographical ordering will do.
return lClass.compareTo(rClass);
}
}

7
dhp-common/src/main/java/eu/dnetlib/dhp/utils/DHPUtils.java
View File

@ -5,6 +5,7 @@ import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.nio.charset.StandardCharsets;
import java.security.MessageDigest;
import java.util.List;
import java.util.zip.GZIPInputStream;
import java.util.zip.GZIPOutputStream;
@ -15,9 +16,15 @@ import org.apache.commons.codec.binary.Hex;
import com.jayway.jsonpath.JsonPath;
import net.minidev.json.JSONArray;
import scala.collection.JavaConverters;
import scala.collection.Seq;
public class DHPUtils {
public static Seq<String> toSeq(List<String> list) {
return JavaConverters.asScalaIteratorConverter(list.iterator()).asScala().toSeq();
}
public static String md5(final String s) {
try {
final MessageDigest md = MessageDigest.getInstance("MD5");

22
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleanGraphSparkJob.java
View File

@ -3,14 +3,12 @@ package eu.dnetlib.dhp.oa.graph.clean;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.BufferedInputStream;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
@ -23,11 +21,9 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.graph.raw.AbstractMdRecordToOafMapper;
import eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils;
import eu.dnetlib.dhp.oa.graph.raw.common.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
@ -75,12 +71,12 @@ public class CleanGraphSparkJob {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
fixGraphTable(spark, vocs, inputPath, entityClazz, outputPath);
HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
cleanGraphTable(spark, vocs, inputPath, entityClazz, outputPath);
});
}
private static <T extends Oaf> void fixGraphTable(
private static <T extends Oaf> void cleanGraphTable(
SparkSession spark,
VocabularyGroup vocs,
String inputPath,
@ -106,13 +102,15 @@ public class CleanGraphSparkJob {
return spark
.read()
.textFile(inputEntityPath)
.filter((FilterFunction<String>) s -> isEntityType(s, clazz))
.map((MapFunction<String, String>) s -> StringUtils.substringAfter(s, "|"), Encoders.STRING())
.map(
(MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, clazz),
Encoders.bean(clazz));
}
private static void removeOutputDir(SparkSession spark, String path) {
HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
private static <T extends Oaf> boolean isEntityType(final String s, final Class<T> clazz) {
return StringUtils.substringBefore(s, "|").equals(clazz.getName());
}
}

3
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleaningFunctions.java
View File

@ -11,7 +11,6 @@ import org.apache.commons.lang3.StringUtils;
import com.clearspring.analytics.util.Lists;
import eu.dnetlib.dhp.oa.graph.raw.AbstractMdRecordToOafMapper;
import eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
@ -115,7 +114,7 @@ public class CleaningFunctions {
.stream()
.filter(Objects::nonNull)
.filter(sp -> StringUtils.isNotBlank(StringUtils.trim(sp.getValue())))
.filter(sp -> NONE.equalsIgnoreCase(sp.getValue()))
.filter(sp -> !NONE.equalsIgnoreCase(sp.getValue().trim()))
.filter(sp -> Objects.nonNull(sp.getQualifier()))
.filter(sp -> StringUtils.isNotBlank(sp.getQualifier().getClassid()))
.map(sp -> {

206
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/GroupEntitiesAndRelationsSparkJob.java Normal file
View File

@ -0,0 +1,206 @@
package eu.dnetlib.dhp.oa.graph.clean;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static eu.dnetlib.dhp.utils.DHPUtils.toSeq;
import java.io.IOException;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.expressions.Aggregator;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.jayway.jsonpath.Configuration;
import com.jayway.jsonpath.DocumentContext;
import com.jayway.jsonpath.JsonPath;
import com.jayway.jsonpath.Option;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import scala.Tuple2;
/**
* Groups the graph content by entity identifier to ensure ID uniqueness
*/
public class GroupEntitiesAndRelationsSparkJob {
private static final Logger log = LoggerFactory.getLogger(GroupEntitiesAndRelationsSparkJob.class);
private final static String ID_JPATH = "$.id";
private final static String SOURCE_JPATH = "$.source";
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
GroupEntitiesAndRelationsSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/group_graph_entities_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String graphInputPath = parser.get("graphInputPath");
log.info("graphInputPath: {}", graphInputPath);
String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
SparkConf conf = new SparkConf();
conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
conf.registerKryoClasses(ModelSupport.getOafModelClasses());
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
groupEntitiesAndRelations(spark, graphInputPath, outputPath);
});
}
private static void groupEntitiesAndRelations(
SparkSession spark,
String inputPath,
String outputPath) {
TypedColumn<Oaf, Oaf> aggregator = new GroupingAggregator().toColumn();
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
spark
.read()
.textFile(toSeq(listPaths(inputPath, sc)))
.map((MapFunction<String, Oaf>) s -> parseOaf(s), Encoders.kryo(Oaf.class))
.filter((FilterFunction<Oaf>) oaf -> StringUtils.isNotBlank(ModelSupport.idFn().apply(oaf)))
.groupByKey((MapFunction<Oaf, String>) oaf -> ModelSupport.idFn().apply(oaf), Encoders.STRING())
.agg(aggregator)
.map(
(MapFunction<Tuple2<String, Oaf>, String>) t -> t._2().getClass().getName() +
"|" + OBJECT_MAPPER.writeValueAsString(t._2()),
Encoders.STRING())
.write()
.option("compression", "gzip")
.mode(SaveMode.Overwrite)
.text(outputPath);
}
public static class GroupingAggregator extends Aggregator<Oaf, Oaf, Oaf> {
@Override
public Oaf zero() {
return null;
}
@Override
public Oaf reduce(Oaf b, Oaf a) {
return mergeAndGet(b, a);
}
private Oaf mergeAndGet(Oaf b, Oaf a) {
if (Objects.nonNull(a) && Objects.nonNull(b)) {
return OafMapperUtils.merge(b, a);
}
return Objects.isNull(a) ? b : a;
}
@Override
public Oaf merge(Oaf b, Oaf a) {
return mergeAndGet(b, a);
}
@Override
public Oaf finish(Oaf j) {
return j;
}
@Override
public Encoder<Oaf> bufferEncoder() {
return Encoders.kryo(Oaf.class);
}
@Override
public Encoder<Oaf> outputEncoder() {
return Encoders.kryo(Oaf.class);
}
}
private static Oaf parseOaf(String s) {
DocumentContext dc = JsonPath
.parse(s, Configuration.defaultConfiguration().addOptions(Option.SUPPRESS_EXCEPTIONS));
final String id = dc.read(ID_JPATH);
if (StringUtils.isNotBlank(id)) {
String prefix = StringUtils.substringBefore(id, "|");
switch (prefix) {
case "10":
return parse(s, Datasource.class);
case "20":
return parse(s, Organization.class);
case "40":
return parse(s, Project.class);
case "50":
String resultType = dc.read("$.resulttype.classid");
switch (resultType) {
case "publication":
return parse(s, Publication.class);
case "dataset":
return parse(s, eu.dnetlib.dhp.schema.oaf.Dataset.class);
case "software":
return parse(s, Software.class);
case "other":
return parse(s, OtherResearchProduct.class);
default:
throw new IllegalArgumentException(String.format("invalid resultType: '%s'", resultType));
}
default:
throw new IllegalArgumentException(String.format("invalid id prefix: '%s'", prefix));
}
} else {
String source = dc.read(SOURCE_JPATH);
if (StringUtils.isNotBlank(source)) {
return parse(s, Relation.class);
} else {
throw new IllegalArgumentException(String.format("invalid oaf: '%s'", s));
}
}
}
private static <T extends Oaf> Oaf parse(String s, Class<T> clazz) {
try {
return OBJECT_MAPPER.readValue(s, clazz);
} catch (IOException e) {
throw new RuntimeException(e);
}
}
private static List<String> listPaths(String inputPath, JavaSparkContext sc) {
return HdfsSupport
.listFiles(inputPath, sc.hadoopConfiguration())
.stream()
.collect(Collectors.toList());
}
}

4
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphSparkJob.java → dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphTableSparkJob.java
View File

@ -33,9 +33,9 @@ import scala.Tuple2;
* are picked preferring those from the BETA aggregator rather then from PROD. The identity of a relationship is defined
* by eu.dnetlib.dhp.schema.common.ModelSupport#idFn()
*/
public class MergeGraphSparkJob {
public class MergeGraphTableSparkJob {
private static final Logger log = LoggerFactory.getLogger(CleanGraphSparkJob.class);
private static final Logger log = LoggerFactory.getLogger(MergeGraphTableSparkJob.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/AbstractMdRecordToOafMapper.java
View File

@ -1,8 +1,8 @@
package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.*;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.*;
import java.util.*;

41
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/GenerateEntitiesApplication.java
View File

@ -29,16 +29,7 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.graph.raw.common.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.OafEntity;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import scala.Tuple2;
@ -78,7 +69,7 @@ public class GenerateEntitiesApplication {
final SparkConf conf = new SparkConf();
runWithSparkSession(conf, isSparkSessionManaged, spark -> {
removeOutputDir(spark, targetPath);
HdfsSupport.remove(targetPath, spark.sparkContext().hadoopConfiguration());
generateEntities(spark, vocs, sourcePaths, targetPath);
});
}
@ -92,7 +83,7 @@ public class GenerateEntitiesApplication {
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
final List<String> existingSourcePaths = Arrays
.stream(sourcePaths.split(","))
.filter(p -> exists(sc, p))
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
.collect(Collectors.toList());
log.info("Generate entities from files:");
@ -113,7 +104,7 @@ public class GenerateEntitiesApplication {
inputRdd
.mapToPair(oaf -> new Tuple2<>(ModelSupport.idFn().apply(oaf), oaf))
.reduceByKey((o1, o2) -> merge(o1, o2))
.reduceByKey((o1, o2) -> OafMapperUtils.merge(o1, o2))
.map(Tuple2::_2)
.map(
oaf -> oaf.getClass().getSimpleName().toLowerCase()
@ -122,17 +113,6 @@ public class GenerateEntitiesApplication {
.saveAsTextFile(targetPath, GzipCodec.class);
}
private static Oaf merge(final Oaf o1, final Oaf o2) {
if (ModelSupport.isSubClass(o1, OafEntity.class)) {
((OafEntity) o1).mergeFrom((OafEntity) o2);
} else if (ModelSupport.isSubClass(o1, Relation.class)) {
((Relation) o1).mergeFrom((Relation) o2);
} else {
throw new RuntimeException("invalid Oaf type:" + o1.getClass().getCanonicalName());
}
return o1;
}
private static List<Oaf> convertToListOaf(
final String id,
final String s,
@ -181,17 +161,4 @@ public class GenerateEntitiesApplication {
}
}
private static boolean exists(final JavaSparkContext context, final String pathToFile) {
try {
final FileSystem hdfs = FileSystem.get(context.hadoopConfiguration());
final Path path = new Path(pathToFile);
return hdfs.exists(path);
} catch (final IOException e) {
throw new RuntimeException(e);
}
}
private static void removeOutputDir(final SparkSession spark, final String path) {
HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
}
}

17
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/MigrateDbEntitiesApplication.java
View File

@ -1,15 +1,6 @@
package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.asString;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.dataInfo;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.field;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.journal;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.listFields;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.listKeyValues;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.qualifier;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DATASET_DEFAULT_RESULTTYPE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DATASOURCE_ORGANIZATION;
import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_PROVENANCE_ACTIONS;
@ -32,6 +23,7 @@ import static eu.dnetlib.dhp.schema.common.ModelConstants.RESULT_PROJECT;
import static eu.dnetlib.dhp.schema.common.ModelConstants.RESULT_RESULT;
import static eu.dnetlib.dhp.schema.common.ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE;
import static eu.dnetlib.dhp.schema.common.ModelConstants.USER_CLAIM;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.*;
import java.io.Closeable;
import java.io.IOException;
@ -527,9 +519,12 @@ public class MigrateDbEntitiesApplication extends AbstractMigrationApplication i
final Boolean deletedbyinference = rs.getBoolean("deletedbyinference");
final String inferenceprovenance = rs.getString("inferenceprovenance");
final Boolean inferred = rs.getBoolean("inferred");
final String trust = rs.getString("trust");
final double trust = rs.getDouble("trust");
return dataInfo(
deletedbyinference, inferenceprovenance, inferred, false, ENTITYREGISTRY_PROVENANCE_ACTION, trust);
deletedbyinference, inferenceprovenance, inferred, false, ENTITYREGISTRY_PROVENANCE_ACTION,
String.format("%.3f", trust));
}
private Qualifier prepareQualifierSplitting(final String s) {

6
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OafToOafMapper.java
View File

@ -1,10 +1,10 @@
package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.field;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.field;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.structuredProperty;
import java.util.ArrayList;
import java.util.List;

6
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OdfToOafMapper.java
View File

@ -1,10 +1,10 @@
package eu.dnetlib.dhp.oa.graph.raw;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.field;
import static eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils.structuredProperty;
import static eu.dnetlib.dhp.schema.common.ModelConstants.*;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.createOpenaireId;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.field;
import static eu.dnetlib.dhp.schema.oaf.OafMapperUtils.structuredProperty;
import java.util.ArrayList;
import java.util.Arrays;

1
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/common/Vocabulary.java
View File

@ -10,6 +10,7 @@ import org.apache.commons.lang3.StringUtils;
import com.google.common.collect.Maps;
import eu.dnetlib.dhp.schema.oaf.OafMapperUtils;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
public class Vocabulary implements Serializable {

1
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/common/VocabularyGroup.java
View File

@ -7,6 +7,7 @@ import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.schema.oaf.OafMapperUtils;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;

42
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/clean/oozie_app/workflow.xml
View File

@ -50,12 +50,36 @@
</property>
</parameters>
<start to="fork_clean_graph"/>
<start to="group_entities"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="group_entities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>group graph entities and relations</name>
<class>eu.dnetlib.dhp.oa.graph.clean.GroupEntitiesAndRelationsSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--graphInputPath</arg><arg>${graphInputPath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/grouped_entities</arg>
</spark>
<ok to="fork_clean_graph"/>
<error to="Kill"/>
</action>
<fork name="fork_clean_graph">
<path start="clean_publication"/>
<path start="clean_dataset"/>
@ -84,7 +108,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/publication</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/publication</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
@ -110,7 +134,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/dataset</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/dataset</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
@ -136,7 +160,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/otherresearchproduct</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/otherresearchproduct</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
@ -162,7 +186,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/software</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/software</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
@ -188,7 +212,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/datasource</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/datasource</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Datasource</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
@ -214,7 +238,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/organization</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/organization</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Organization</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
@ -240,7 +264,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/project</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/project</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
@ -266,7 +290,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--inputPath</arg><arg>${graphInputPath}/relation</arg>
<arg>--inputPath</arg><arg>${workingDir}/grouped_entities</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/relation</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>

20
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/group_graph_entities_parameters.json Normal file
View File

@ -0,0 +1,20 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "gin",
"paramLongName": "graphInputPath",
"paramDescription": "the graph root path",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramDescription": "the output merged graph root path",
"paramRequired": true
}
]

52
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/merge/oozie_app/workflow.xml
View File

@ -2,11 +2,11 @@
<parameters>
<property>
<name>betaInputGgraphPath</name>
<name>betaInputGraphPath</name>
<description>the beta graph root path</description>
</property>
<property>
<name>prodInputGgraphPath</name>
<name>prodInputGraphPath</name>
<description>the production graph root path</description>
</property>
<property>
@ -76,7 +76,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge publications</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -88,8 +88,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/publication</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/publication</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/publication</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/publication</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/publication</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--priority</arg><arg>${priority}</arg>
@ -103,7 +103,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge datasets</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -115,8 +115,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/dataset</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/dataset</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/dataset</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/dataset</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/dataset</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--priority</arg><arg>${priority}</arg>
@ -130,7 +130,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge otherresearchproducts</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -142,8 +142,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/otherresearchproduct</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/otherresearchproduct</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/otherresearchproduct</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/otherresearchproduct</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--priority</arg><arg>${priority}</arg>
@ -157,7 +157,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge softwares</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -169,8 +169,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/software</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/software</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/software</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/software</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/software</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--priority</arg><arg>${priority}</arg>
@ -184,7 +184,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge datasources</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -196,8 +196,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/datasource</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/datasource</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/datasource</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/datasource</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/datasource</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Datasource</arg>
<arg>--priority</arg><arg>${priority}</arg>
@ -211,7 +211,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge organizations</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -223,8 +223,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/organization</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/organization</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/organization</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/organization</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/organization</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Organization</arg>
<arg>--priority</arg><arg>${priority}</arg>
@ -238,7 +238,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge projects</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -250,8 +250,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/project</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/project</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/project</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/project</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/project</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
<arg>--priority</arg><arg>${priority}</arg>
@ -265,7 +265,7 @@
<master>yarn</master>
<mode>cluster</mode>
<name>Merge relations</name>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphSparkJob</class>
<class>eu.dnetlib.dhp.oa.graph.merge.MergeGraphTableSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
@ -277,8 +277,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=7680
</spark-opts>
<arg>--betaInputPath</arg><arg>${betaInputGgraphPath}/relation</arg>
<arg>--prodInputPath</arg><arg>${prodInputGgraphPath}/relation</arg>
<arg>--betaInputPath</arg><arg>${betaInputGraphPath}/relation</arg>
<arg>--prodInputPath</arg><arg>${prodInputGraphPath}/relation</arg>
<arg>--outputPath</arg><arg>${graphOutputPath}/relation</arg>
<arg>--graphTableClassName</arg><arg>eu.dnetlib.dhp.schema.oaf.Relation</arg>
<arg>--priority</arg><arg>${priority}</arg>

14
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphSparkJobTest.java → dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/merge/MergeGraphTableSparkJobTest.java
View File

@ -15,7 +15,7 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.oaf.Datasource;
public class MergeGraphSparkJobTest {
public class MergeGraphTableSparkJobTest {
private ObjectMapper mapper;
@ -28,7 +28,7 @@ public class MergeGraphSparkJobTest {
public void testMergeDatasources() throws IOException {
assertEquals(
"openaire-cris_1.1",
MergeGraphSparkJob
MergeGraphTableSparkJob
.mergeDatasource(
d("datasource_cris.json"),
d("datasource_UNKNOWN.json"))
@ -36,7 +36,7 @@ public class MergeGraphSparkJobTest {
.getClassid());
assertEquals(
"openaire-cris_1.1",
MergeGraphSparkJob
MergeGraphTableSparkJob
.mergeDatasource(
d("datasource_UNKNOWN.json"),
d("datasource_cris.json"))
@ -44,7 +44,7 @@ public class MergeGraphSparkJobTest {
.getClassid());
assertEquals(
"driver-openaire2.0",
MergeGraphSparkJob
MergeGraphTableSparkJob
.mergeDatasource(
d("datasource_native.json"),
d("datasource_driver-openaire2.0.json"))
@ -52,7 +52,7 @@ public class MergeGraphSparkJobTest {
.getClassid());
assertEquals(
"driver-openaire2.0",
MergeGraphSparkJob
MergeGraphTableSparkJob
.mergeDatasource(
d("datasource_driver-openaire2.0.json"),
d("datasource_native.json"))
@ -60,7 +60,7 @@ public class MergeGraphSparkJobTest {
.getClassid());
assertEquals(
"openaire4.0",
MergeGraphSparkJob
MergeGraphTableSparkJob
.mergeDatasource(
d("datasource_notCompatible.json"),
d("datasource_openaire4.0.json"))
@ -68,7 +68,7 @@ public class MergeGraphSparkJobTest {
.getClassid());
assertEquals(
"notCompatible",
MergeGraphSparkJob
MergeGraphTableSparkJob
.mergeDatasource(
d("datasource_notCompatible.json"),
d("datasource_UNKNOWN.json"))

99
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/GenerateEntitiesApplicationTest.java Normal file
View File

@ -0,0 +1,99 @@
package eu.dnetlib.dhp.oa.graph.raw;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertTrue;
import static org.mockito.Mockito.lenient;
import java.io.IOException;
import java.util.List;
import org.apache.commons.io.IOUtils;
import org.junit.jupiter.api.BeforeEach;
import org.junit.jupiter.api.Test;
import org.junit.jupiter.api.extension.ExtendWith;
import org.mockito.Mock;
import org.mockito.junit.jupiter.MockitoExtension;
import eu.dnetlib.dhp.oa.graph.clean.CleaningFunctionTest;
import eu.dnetlib.dhp.oa.graph.raw.common.VocabularyGroup;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
@ExtendWith(MockitoExtension.class)
public class GenerateEntitiesApplicationTest {
@Mock
private ISLookUpService isLookUpService;
@Mock
private VocabularyGroup vocs;
@BeforeEach
public void setUp() throws IOException, ISLookUpException {
lenient().when(isLookUpService.quickSearchProfile(VocabularyGroup.VOCABULARIES_XQUERY)).thenReturn(vocs());
lenient()
.when(isLookUpService.quickSearchProfile(VocabularyGroup.VOCABULARY_SYNONYMS_XQUERY))
.thenReturn(synonyms());
vocs = VocabularyGroup.loadVocsFromIS(isLookUpService);
}
@Test
public void testMergeResult() throws IOException {
Result publication = getResult("oaf_record.xml", Publication.class);
Result dataset = getResult("odf_dataset.xml", Dataset.class);
Result software = getResult("odf_software.xml", Software.class);
Result orp = getResult("oaf_orp.xml", OtherResearchProduct.class);
verifyMerge(publication, dataset, Publication.class, ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
verifyMerge(dataset, publication, Publication.class, ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
verifyMerge(publication, software, Publication.class, ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
verifyMerge(software, publication, Publication.class, ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
verifyMerge(publication, orp, Publication.class, ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
verifyMerge(orp, publication, Publication.class, ModelConstants.PUBLICATION_RESULTTYPE_CLASSID);
verifyMerge(dataset, software, Dataset.class, ModelConstants.DATASET_RESULTTYPE_CLASSID);
verifyMerge(software, dataset, Dataset.class, ModelConstants.DATASET_RESULTTYPE_CLASSID);
verifyMerge(dataset, orp, Dataset.class, ModelConstants.DATASET_RESULTTYPE_CLASSID);
verifyMerge(orp, dataset, Dataset.class, ModelConstants.DATASET_RESULTTYPE_CLASSID);
verifyMerge(software, orp, Software.class, ModelConstants.SOFTWARE_RESULTTYPE_CLASSID);
verifyMerge(orp, software, Software.class, ModelConstants.SOFTWARE_RESULTTYPE_CLASSID);
}
protected <T extends Result> void verifyMerge(Result publication, Result dataset, Class<T> clazz,
String resultType) {
final Result merge = OafMapperUtils.mergeResults(publication, dataset);
assertTrue(clazz.isAssignableFrom(merge.getClass()));
assertEquals(resultType, merge.getResulttype().getClassid());
}
protected <T extends Result> Result getResult(String xmlFileName, Class<T> clazz) throws IOException {
final String xml = IOUtils.toString(getClass().getResourceAsStream(xmlFileName));
return new OdfToOafMapper(vocs, false)
.processMdRecord(xml)
.stream()
.filter(s -> clazz.isAssignableFrom(s.getClass()))
.map(s -> (Result) s)
.findFirst()
.get();
}
private List<String> vocs() throws IOException {
return IOUtils
.readLines(CleaningFunctionTest.class.getResourceAsStream("/eu/dnetlib/dhp/oa/graph/clean/terms.txt"));
}
private List<String> synonyms() throws IOException {
return IOUtils
.readLines(CleaningFunctionTest.class.getResourceAsStream("/eu/dnetlib/dhp/oa/graph/clean/synonyms.txt"));
}
}

8
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MigrateDbEntitiesApplicationTest.java
View File

@ -27,14 +27,8 @@ import org.mockito.junit.jupiter.MockitoExtension;
import com.fasterxml.jackson.core.type.TypeReference;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.oa.graph.raw.common.OafMapperUtils;
import eu.dnetlib.dhp.oa.graph.raw.common.VocabularyGroup;
import eu.dnetlib.dhp.schema.oaf.Datasource;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.Organization;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.*;
@ExtendWith(MockitoExtension.class)
public class MigrateDbEntitiesApplicationTest {

4
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/datasourceorganization_resultset_entry.json
View File

@ -31,8 +31,8 @@
},
{
"field": "trust",
"type": "string",
"value": "0.9"
"type": "double",
"value": 0.9
},
{
"field": "inferenceprovenance",

4
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/datasources_resultset_entry.json
View File

@ -114,8 +114,8 @@
},
{
"field": "trust",
"type": "string",
"value": "0.9"
"type": "double",
"value": 0.9
},
{
"field": "inferenceprovenance",

84
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/oaf_orp.xml Normal file
View File

@ -0,0 +1,84 @@
<?xml version="1.0" encoding="UTF-8"?>
<record xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:prov="http://www.openarchives.org/OAI/2.0/provenance" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<header xmlns="http://namespace.openaire.eu/">
<dri:objIdentifier>pensoft_____::00ea4a1cd53806a97d62ea6bf268f2a2</dri:objIdentifier>
<dri:recordIdentifier>10.3897/oneeco.2.e13718</dri:recordIdentifier>
<dri:dateOfCollection/>
<dri:mdFormat/>
<dri:mdFormatInterpretation/>
<dri:repositoryId/>
<dr:objectIdentifier/>
<dr:dateOfCollection>2020-03-23T00:20:51.392Z</dr:dateOfCollection>
<dr:dateOfTransformation>2020-03-23T00:26:59.078Z</dr:dateOfTransformation>
<oaf:datasourceprefix>pensoft_____</oaf:datasourceprefix>
</header>
<metadata xmlns="http://namespace.openaire.eu/">
<dc:title>Ecosystem Service capacity is higher in areas of multiple designation types</dc:title>
<dc:creator>Nikolaidou,Charitini</dc:creator>
<dc:creator nameIdentifier="0000-0001-6651-1178" nameIdentifierScheme="ORCID">Votsi,Nefta</dc:creator>
<dc:creator>Sgardelis,Steanos</dc:creator>
<dc:creator>Halley,John</dc:creator>
<dc:creator>Pantis,John</dc:creator>
<dc:creator>Tsiafouli,Maria</dc:creator>
<dc:date>2017</dc:date>
<dc:description>The implementation of the Ecosystem Service (ES) concept into practice might be a challenging task as it has to take into account previous “traditional” policies and approaches that have evaluated nature and biodiversity differently. Among them the Habitat (92/43/EC) and Bird Directives (79/409/EC), the Water Framework Directive (2000/60/EC), and the Noise Directive (2002/49/EC) have led to the evaluation/designation of areas in Europe with different criteria. In this study our goal was to understand how the ES capacity of an area is related to its designation and if areas with multiple designations have higher capacity in providing ES. We selected four catchments in Greece with a great variety of characteristics covering over 25% of the national territory. Inside the catchments we assessed the ES capacity (following the methodology of Burkhard et al. 2009) of areas designated as Natura 2000 sites, Quiet areas and Wetlands or Water bodies and found those areas that have multiple designations. Data were analyzed by GLM to reveal differences regarding the ES capacity among the different types of areas. We also investigated by PCA synergies and trade-offs among different kinds of ES and tested for correlations among landscape properties, such as elevation, aspect and slope and the ES potential. Our results show that areas with different types or multiple designations have a different capacity in providing ES. Areas of one designation type (Protected or Quiet Areas) had in general intermediate scores in most ES but scores were higher compared to areas with no designation, which displayed stronger capacity in provisioning services. Among Protected Areas and Quiet Areas the latter scored better in general. Areas that combined both designation types (Protected and Quiet Areas) showed the highest capacity in 13 out of 29 ES, that were mostly linked with natural and forest ecosystems. We found significant synergies among most regulating, supporting and cultural ES which in turn display trade-offs with provisioning services. The different ES are spatially related and display strong correlation with landscape properties, such as elevation and slope. We suggest that the designation status of an area can be used as an alternative tool for environmental policy, indicating the capacity for ES provision. Multiple designations of areas can be used as proxies for locating ES “hotspots”. This integration of “traditional” evaluation and designation and the “newer” ES concept forms a time- and cost-effective way to be adopted by stakeholders and policy-makers in order to start complying with new standards and demands for nature conservation and environmental management.</dc:description>
<dc:format>text/html</dc:format>
<dc:identifier>https://doi.org/10.3897/oneeco.2.e13718</dc:identifier>
<dc:identifier>https://oneecosystem.pensoft.net/article/13718/</dc:identifier>
<dc:language>eng</dc:language>
<dc:publisher>Pensoft Publishers</dc:publisher>
<dc:relation>info:eu-repo/semantics/altIdentifier/eissn/2367-8194</dc:relation>
<dc:relation>info:eu-repo/grantAgreement/EC/FP7/226852</dc:relation>
<dc:source>One Ecosystem 2: e13718</dc:source>
<dc:source>One Ecosystem 2: e13718</dc:source>
<dc:source>One Ecosystem 2: e13718</dc:source>
<dc:subject>Ecosystem Services hotspots</dc:subject>
<dc:subject>Natura 2000</dc:subject>
<dc:subject>Quiet Protected Areas</dc:subject>
<dc:subject>Biodiversity</dc:subject>
<dc:subject>Agriculture</dc:subject>
<dc:subject>Elevation</dc:subject>
<dc:subject>Slope</dc:subject>
<dc:subject>Ecosystem Service trade-offs and synergies</dc:subject>
<dc:subject> cultural services</dc:subject>
<dc:subject>provisioning services</dc:subject>
<dc:subject>regulating services</dc:subject>
<dc:subject>supporting services</dc:subject>
<dc:type>Research Article</dc:type>
<!--<dr:CobjCategory type="publication">0001</dr:CobjCategory>-->
<dr:CobjCategory>0020</dr:CobjCategory>
<oaf:dateAccepted>2017-01-01</oaf:dateAccepted>
<oaf:projectid>corda_______::226852</oaf:projectid>
<oaf:accessrights>OPEN</oaf:accessrights>
<oaf:hostedBy id="openaire____::issn226852" name="One Ecosystem"/>
<oaf:collectedFrom
id="openaire____::45e3c7b69bcee6cc5fa945c9e183deb9" name="Pensoft"/>
<oaf:identifier identifierType="doi">10.3897/oneeco.2.e13718</oaf:identifier>
<oaf:fulltext>https://oneecosystem.pensoft.net/article/13718/</oaf:fulltext>
<oaf:journal eissn="2367-8194" issn="">One Ecosystem</oaf:journal>
<oaf:refereed>0001</oaf:refereed>
</metadata>
<about xmlns:oai="http://www.openarchives.org/OAI/2.0/">
<provenance xmlns="http://www.openarchives.org/OAI/2.0/provenance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/provenance http://www.openarchives.org/OAI/2.0/provenance.xsd">
<originDescription altered="true" harvestDate="2020-03-23T00:20:51.392Z">
<baseURL>http%3A%2F%2Fzookeys.pensoft.net%2Foai.php</baseURL>
<identifier>10.3897/oneeco.2.e13718</identifier>
<datestamp>2017-09-08</datestamp>
<metadataNamespace>http://www.openarchives.org/OAI/2.0/oai_dc/</metadataNamespace>
</originDescription>
</provenance>
<oaf:datainfo>
<oaf:inferred>false</oaf:inferred>
<oaf:deletedbyinference>false</oaf:deletedbyinference>
<oaf:trust>0.9</oaf:trust>
<oaf:inferenceprovenance/>
<oaf:provenanceaction classid="sysimport:crosswalk:repository"
classname="sysimport:crosswalk:repository"
schemeid="dnet:provenanceActions" schemename="dnet:provenanceActions"/>
</oaf:datainfo>
</about>
</record>

4
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/organizations_resultset_entry.json
View File

@ -96,8 +96,8 @@
},
{
"field": "trust",
"type": "string",
"value": "0.9"
"type": "double",
"value": 0.9
},
{
"field": "inferenceprovenance",

4
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/projectorganization_resultset_entry.json
View File

@ -41,8 +41,8 @@
},
{
"field": "trust",
"type": "string",
"value": "0.9"
"type": "double",
"value": 0.9
},
{
"field": "inferenceprovenance",

4
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/projects_resultset_entry.json
View File

@ -86,8 +86,8 @@
},
{
"field": "trust",
"type": "string",
"value": "0.9"
"type": "double",
"value": 0.9
},
{
"field": "inferenceprovenance",

15
dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/XmlConverterJob.java
View File

@ -2,12 +2,11 @@
package eu.dnetlib.dhp.oa.provision;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import static eu.dnetlib.dhp.utils.DHPUtils.toSeq;
import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
@ -28,13 +27,11 @@ import com.google.common.collect.Maps;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.provision.model.*;
import eu.dnetlib.dhp.oa.provision.model.JoinedEntity;
import eu.dnetlib.dhp.oa.provision.model.ProvisionModelSupport;
import eu.dnetlib.dhp.oa.provision.utils.ContextMapper;
import eu.dnetlib.dhp.oa.provision.utils.XmlRecordFactory;
import eu.dnetlib.dhp.schema.oaf.*;
import scala.Tuple2;
import scala.collection.JavaConverters;
import scala.collection.Seq;
/**
* XmlConverterJob converts the JoinedEntities as XML records
@ -43,8 +40,6 @@ public class XmlConverterJob {
private static final Logger log = LoggerFactory.getLogger(XmlConverterJob.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static final String schemaLocation = "https://www.openaire.eu/schema/1.0/oaf-1.0.xsd";
public static void main(String[] args) throws Exception {
@ -129,10 +124,6 @@ public class XmlConverterJob {
HdfsSupport.remove(path, spark.sparkContext().hadoopConfiguration());
}
private static Seq<String> toSeq(List<String> list) {
return JavaConverters.asScalaIteratorConverter(list.iterator()).asScala().toSeq();
}
private static Map<String, LongAccumulator> prepareAccumulators(SparkContext sc) {
Map<String, LongAccumulator> accumulators = Maps.newHashMap();
accumulators

6
pom.xml
View File

@ -50,7 +50,7 @@
<repository>
<id>dnet45-releases</id>
<name>D-Net 45 releases</name>
<url>http://maven.research-infrastructures.eu/nexus/content/repositories/dnet45-releases</url>
<url>https://maven.d4science.org/nexus/content/repositories/dnet45-releases</url>
<layout>default</layout>
<snapshots>
<enabled>false</enabled>
@ -651,12 +651,12 @@
<snapshotRepository>
<id>dnet45-snapshots</id>
<name>DNet45 Snapshots</name>
<url>http://maven.research-infrastructures.eu/nexus/content/repositories/dnet45-snapshots</url>
<url>https://maven.d4science.org/nexus/content/repositories/dnet45-snapshots</url>
<layout>default</layout>
</snapshotRepository>
<repository>
<id>dnet45-releases</id>
<url>http://maven.research-infrastructures.eu/nexus/content/repositories/dnet45-releases</url>
<url>https://maven.d4science.org/nexus/content/repositories/dnet45-releases</url>
</repository>
</distributionManagement>
<reporting>