michele.artini
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge pull request 'scala_refactor' (#169) from scala_refactor into beta 

Reviewed-on: D-Net/dnet-hadoop#169
This commit is contained in:
Sandro La Bruzzo 2021-12-06 15:33:44 +01:00
parent 9132727793 d9836f0cf3
commit 5d51b3dd4a
69 changed files with 457 additions and 805 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

0
dhp-common/src/main/java/eu/dnetlib/dhp/application/SparkScalaApplication.scala → dhp-common/src/main/scala/eu/dnetlib/dhp/application/SparkScalaApplication.scala
View File

69
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/scholix/SparkCreateActionset.scala
View File

@ -1,69 +0,0 @@
package eu.dnetlib.dhp.actionmanager.scholix
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result}
import org.apache.spark.SparkConf
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
import scala.io.Source
object SparkCreateActionset {
def main(args: Array[String]): Unit = {
val log: Logger = LoggerFactory.getLogger(getClass)
val conf: SparkConf = new SparkConf()
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/actionset/generate_actionset.json")).mkString)
parser.parseArgument(args)
val spark: SparkSession =
SparkSession
.builder()
.config(conf)
.appName(getClass.getSimpleName)
.master(parser.get("master")).getOrCreate()
val sourcePath = parser.get("sourcePath")
log.info(s"sourcePath -> $sourcePath")
val targetPath = parser.get("targetPath")
log.info(s"targetPath -> $targetPath")
val workingDirFolder = parser.get("workingDirFolder")
log.info(s"workingDirFolder -> $workingDirFolder")
implicit val oafEncoders: Encoder[Oaf] = Encoders.kryo[Oaf]
implicit val resultEncoders: Encoder[Result] = Encoders.kryo[Result]
implicit val relationEncoders: Encoder[Relation] = Encoders.kryo[Relation]
import spark.implicits._
val relation = spark.read.load(s"$sourcePath/relation").as[Relation]
relation.filter(r => (r.getDataInfo == null || r.getDataInfo.getDeletedbyinference == false) && !r.getRelClass.toLowerCase.contains("merge"))
.flatMap(r => List(r.getSource, r.getTarget)).distinct().write.mode(SaveMode.Overwrite).save(s"$workingDirFolder/id_relation")
val idRelation = spark.read.load(s"$workingDirFolder/id_relation").as[String]
log.info("extract source and target Identifier involved in relations")
log.info("save relation filtered")
relation.filter(r => (r.getDataInfo == null || r.getDataInfo.getDeletedbyinference == false) && !r.getRelClass.toLowerCase.contains("merge"))
.write.mode(SaveMode.Overwrite).save(s"$workingDirFolder/actionSetOaf")
log.info("saving entities")
val entities: Dataset[(String, Result)] = spark.read.load(s"$sourcePath/entities/*").as[Result].map(p => (p.getId, p))(Encoders.tuple(Encoders.STRING, resultEncoders))
entities
.joinWith(idRelation, entities("_1").equalTo(idRelation("value")))
.map(p => p._1._2)
.write.mode(SaveMode.Append).save(s"$workingDirFolder/actionSetOaf")
}
}

86
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/scholix/SparkSaveActionSet.scala
View File

@ -1,86 +0,0 @@
package eu.dnetlib.dhp.actionmanager.scholix
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.action.AtomicAction
import eu.dnetlib.dhp.schema.oaf.{Oaf, Dataset => OafDataset,Publication, Software, OtherResearchProduct, Relation}
import org.apache.hadoop.io.Text
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.hadoop.mapred.SequenceFileOutputFormat
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.io.Source
object SparkSaveActionSet {
def toActionSet(item: Oaf): (String, String) = {
val mapper = new ObjectMapper()
item match {
case dataset: OafDataset =>
val a: AtomicAction[OafDataset] = new AtomicAction[OafDataset]
a.setClazz(classOf[OafDataset])
a.setPayload(dataset)
(dataset.getClass.getCanonicalName, mapper.writeValueAsString(a))
case publication: Publication =>
val a: AtomicAction[Publication] = new AtomicAction[Publication]
a.setClazz(classOf[Publication])
a.setPayload(publication)
(publication.getClass.getCanonicalName, mapper.writeValueAsString(a))
case software: Software =>
val a: AtomicAction[Software] = new AtomicAction[Software]
a.setClazz(classOf[Software])
a.setPayload(software)
(software.getClass.getCanonicalName, mapper.writeValueAsString(a))
case orp: OtherResearchProduct =>
val a: AtomicAction[OtherResearchProduct] = new AtomicAction[OtherResearchProduct]
a.setClazz(classOf[OtherResearchProduct])
a.setPayload(orp)
(orp.getClass.getCanonicalName, mapper.writeValueAsString(a))
case relation: Relation =>
val a: AtomicAction[Relation] = new AtomicAction[Relation]
a.setClazz(classOf[Relation])
a.setPayload(relation)
(relation.getClass.getCanonicalName, mapper.writeValueAsString(a))
case _ =>
null
}
}
def main(args: Array[String]): Unit = {
val log: Logger = LoggerFactory.getLogger(getClass)
val conf: SparkConf = new SparkConf()
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/actionset/save_actionset.json")).mkString)
parser.parseArgument(args)
val spark: SparkSession =
SparkSession
.builder()
.config(conf)
.appName(getClass.getSimpleName)
.master(parser.get("master")).getOrCreate()
val sourcePath = parser.get("sourcePath")
log.info(s"sourcePath -> $sourcePath")
val targetPath = parser.get("targetPath")
log.info(s"targetPath -> $targetPath")
implicit val oafEncoders: Encoder[Oaf] = Encoders.kryo[Oaf]
implicit val tEncoder: Encoder[(String, String)] = Encoders.tuple(Encoders.STRING, Encoders.STRING)
spark.read.load(sourcePath).as[Oaf]
.map(o => toActionSet(o))
.filter(o => o != null)
.rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text, Text]], classOf[GzipCodec])
}
}

0
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/collection/CollectionUtils.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/collection/CollectionUtils.scala
View File

0
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/datacite/AbstractRestClient.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/AbstractRestClient.scala
View File

0
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/datacite/DataciteAPIImporter.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteAPIImporter.scala
View File

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/datacite/DataciteModelConstants.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteModelConstants.scala
View File

@ -1,8 +1,8 @@
package eu.dnetlib.dhp.datacite
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.{DataInfo, KeyValue}
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils
import eu.dnetlib.dhp.schema.oaf.{DataInfo, KeyValue}
import java.io.InputStream
import java.time.format.DateTimeFormatter

3
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/datacite/DataciteToOAFTransformation.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTransformation.scala
View File

@ -6,7 +6,7 @@ import eu.dnetlib.dhp.datacite.DataciteModelConstants._
import eu.dnetlib.dhp.schema.action.AtomicAction
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, OafMapperUtils}
import eu.dnetlib.dhp.schema.oaf.{AccessRight, Author, DataInfo, Instance, KeyValue, Oaf, OtherResearchProduct, Publication, Qualifier, Relation, Result, Software, StructuredProperty, Dataset => OafDataset}
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset, _}
import eu.dnetlib.dhp.utils.DHPUtils
import org.apache.commons.lang3.StringUtils
import org.json4s.DefaultFormats
@ -29,6 +29,7 @@ object DataciteToOAFTransformation {
/**
* This method should skip record if json contains invalid text
* defined in gile datacite_filter
*
* @param json
* @return True if the record should be skipped
*/

0
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/datacite/GenerateDataciteDatasetSpark.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/GenerateDataciteDatasetSpark.scala
View File

0
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/datacite/ImportDatacite.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/ImportDatacite.scala
View File

0
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/datacite/SparkDownloadUpdateDatacite.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/datacite/SparkDownloadUpdateDatacite.scala
View File

1
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala
View File

@ -7,6 +7,7 @@ import org.json4s.DefaultFormats
import org.json4s.JsonAST.{JField, JObject, JString}
import org.json4s.jackson.JsonMethods.{compact, parse, render}
import collection.JavaConverters._
object BioDBToOAF {
case class EBILinkItem(id: Long, links: String) {}

4
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala
View File

@ -1,9 +1,9 @@
package eu.dnetlib.dhp.sx.bio
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.Oaf
import BioDBToOAF.ScholixResolved
import eu.dnetlib.dhp.collection.CollectionUtils
import eu.dnetlib.dhp.schema.oaf.Oaf
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala
View File

@ -3,7 +3,7 @@ package eu.dnetlib.dhp.sx.bio.ebi
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.oaf.Result
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal, PMParser, PubMedToOaf}
import eu.dnetlib.dhp.sx.bio.pubmed._
import eu.dnetlib.dhp.utils.ISLookupClientFactory
import org.apache.commons.io.IOUtils
import org.apache.hadoop.conf.Configuration

3
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala
View File

@ -1,9 +1,8 @@
package eu.dnetlib.dhp.sx.bio.ebi
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
import eu.dnetlib.dhp.sx.bio.pubmed.PMJournal
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
import org.apache.commons.io.IOUtils
import org.apache.http.client.config.RequestConfig
import org.apache.http.client.methods.HttpGet

3
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala
View File

@ -1,11 +1,10 @@
package eu.dnetlib.dhp.sx.bio.ebi
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.collection.CollectionUtils
import eu.dnetlib.dhp.schema.oaf.Oaf
import eu.dnetlib.dhp.sx.bio.BioDBToOAF
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
import BioDBToOAF.EBILinkItem
import eu.dnetlib.dhp.collection.CollectionUtils
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql._

0
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMParser.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/pubmed/PMParser.scala
View File

7
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala → dhp-workflows/dhp-aggregation/src/main/scala/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala
View File

@ -4,7 +4,7 @@ import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, IdentifierFactory, OafMapperUtils, PidType}
import eu.dnetlib.dhp.schema.oaf._
import scala.collection.JavaConverters._
import collection.JavaConverters._
import java.util.regex.Pattern
@ -22,10 +22,10 @@ object PubMedToOaf {
val collectedFrom: KeyValue = OafMapperUtils.keyValue(ModelConstants.EUROPE_PUBMED_CENTRAL_ID, "Europe PubMed Central")
/**
* Cleaning the DOI Applying regex in order to
* remove doi starting with URL
*
* @param doi input DOI
* @return cleaned DOI
*/
@ -93,7 +93,6 @@ object PubMedToOaf {
* @param vocabularyName the input vocabulary name
* @param vocabularies all the vocabularies
* @param term the term to find
*
* @return the cleaned term value
*/
def getVocabularyTerm(vocabularyName: String, vocabularies: VocabularyGroup, term: String): Qualifier = {
@ -106,7 +105,6 @@ object PubMedToOaf {
/**
* Map the Pubmed Article into the OAF instance
*
*
* @param article the pubmed articles
* @param vocabularies the vocabularies
* @return The OAF instance if the mapping did not fail
@ -185,7 +183,6 @@ object PubMedToOaf {
//--------------------------------------------------------------------------------------
// RESULT MAPPING
//--------------------------------------------------------------------------------------
result.setDateofacceptance(OafMapperUtils.field(GraphCleaningFunctions.cleanDate(article.getDate), dataInfo))

28
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/opencitations/CreateOpenCitationsASTest.java
View File

@ -89,13 +89,13 @@ public class CreateOpenCitationsASTest {
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet"
workingDir.toString() + "/actionSet1"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.sequenceFile(workingDir.toString() + "/actionSet1", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
@ -121,13 +121,13 @@ public class CreateOpenCitationsASTest {
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet"
workingDir.toString() + "/actionSet2"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.sequenceFile(workingDir.toString() + "/actionSet2", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
@ -153,13 +153,13 @@ public class CreateOpenCitationsASTest {
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet"
workingDir.toString() + "/actionSet3"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.sequenceFile(workingDir.toString() + "/actionSet3", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
@ -186,13 +186,13 @@ public class CreateOpenCitationsASTest {
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet"
workingDir.toString() + "/actionSet4"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.sequenceFile(workingDir.toString() + "/actionSet4", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
@ -226,13 +226,13 @@ public class CreateOpenCitationsASTest {
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet"
workingDir.toString() + "/actionSet5"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.sequenceFile(workingDir.toString() + "/actionSet5", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
@ -261,13 +261,13 @@ public class CreateOpenCitationsASTest {
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet"
workingDir.toString() + "/actionSet6"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.sequenceFile(workingDir.toString() + "/actionSet6", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));
@ -306,13 +306,13 @@ public class CreateOpenCitationsASTest {
"-inputPath",
inputPath,
"-outputPath",
workingDir.toString() + "/actionSet"
workingDir.toString() + "/actionSet7"
});
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<Relation> tmp = sc
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
.sequenceFile(workingDir.toString() + "/actionSet7", Text.class, Text.class)
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
.map(aa -> ((Relation) aa.getPayload()));

2
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/datacite/DataciteToOAFTest.scala → dhp-workflows/dhp-aggregation/src/test/scala/eu/dnetlib/dhp/datacite/DataciteToOAFTest.scala
View File

@ -8,6 +8,7 @@ import org.apache.commons.io.FileUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.functions.{col, count}
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.extension.ExtendWith
import org.junit.jupiter.api.{AfterEach, BeforeEach, Test}
import org.mockito.junit.jupiter.MockitoExtension
@ -17,7 +18,6 @@ import java.nio.file.{Files, Path}
import java.text.SimpleDateFormat
import java.util.Locale
import scala.io.Source
import org.junit.jupiter.api.Assertions._
@ExtendWith(Array(classOf[MockitoExtension]))
class DataciteToOAFTest extends AbstractVocabularyTest{

0
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala → dhp-workflows/dhp-aggregation/src/test/scala/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala
View File

14
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/DoiBoostMappingUtil.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/DoiBoostMappingUtil.scala
View File

@ -1,21 +1,19 @@
package eu.dnetlib.doiboost
import java.time.LocalDate
import java.time.format.DateTimeFormatter
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.action.AtomicAction
import eu.dnetlib.dhp.schema.oaf.{AccessRight, DataInfo, Dataset, Field, Instance, KeyValue, Oaf, OpenAccessRoute, Organization, Publication, Qualifier, Relation, Result, StructuredProperty}
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf._
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils
import eu.dnetlib.dhp.utils.DHPUtils
import org.apache.commons.lang3.StringUtils
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils
import eu.dnetlib.doiboost.DoiBoostMappingUtil.{getClosedAccessQualifier, getEmbargoedAccessQualifier, getUnknownQualifier}
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import org.slf4j.{Logger, LoggerFactory}
import java.time.LocalDate
import java.time.format.DateTimeFormatter
import scala.collection.JavaConverters._

15
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/SparkGenerateDOIBoostActionSet.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/SparkGenerateDOIBoostActionSet.scala
View File

@ -8,11 +8,12 @@ import org.apache.hadoop.io.Text
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.hadoop.mapred.SequenceFileOutputFormat
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
object SparkGenerateDOIBoostActionSet {
val logger: Logger = LoggerFactory.getLogger(getClass)
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf()
@ -55,7 +56,6 @@ object SparkGenerateDOIBoostActionSet {
.map(d => DoiBoostMappingUtil.toActionSet(d))(Encoders.tuple(Encoders.STRING, Encoders.STRING))
val asCRelation = spark.read.load(crossRefRelation).as[Relation]
.filter(r => r != null && r.getSource != null && r.getTarget != null)
.map(d => DoiBoostMappingUtil.toActionSet(d))(Encoders.tuple(Encoders.STRING, Encoders.STRING))
@ -65,23 +65,12 @@ object SparkGenerateDOIBoostActionSet {
.map(d => DoiBoostMappingUtil.toActionSet(d))(Encoders.tuple(Encoders.STRING, Encoders.STRING))
val d: Dataset[(String, String)] = asDataset.union(asPublication).union(asOrganization).union(asCRelation).union(asRelAffiliation)
d.rdd.repartition(6000).map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$sequenceFilePath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text, Text]], classOf[GzipCodec])
}
}

18
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/SparkGenerateDoiBoost.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/SparkGenerateDoiBoost.scala
View File

@ -9,14 +9,12 @@ import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.functions.col
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
import org.apache.spark.sql._
import org.json4s.DefaultFormats
import org.json4s.JsonAST.{JField, JObject, JString,JArray}
import org.json4s.JsonAST.{JField, JObject, JString}
import org.json4s.jackson.JsonMethods.parse
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
object SparkGenerateDoiBoost {
@ -38,7 +36,6 @@ object SparkGenerateDoiBoost {
}
def main(args: Array[String]): Unit = {
val logger: Logger = LoggerFactory.getLogger(getClass)
@ -118,8 +115,7 @@ object SparkGenerateDoiBoost {
val crossrefPublication: Dataset[(String, Publication)] = spark.read.load(s"$workingDirPath/crossrefPublication").as[Publication].map(p => (p.getId, p))
val uwPublication: Dataset[(String, Publication)] = spark.read.load(s"$workingDirPath/uwPublication").as[Publication].map(p => (p.getId, p))
def applyMerge(item:((String, Publication), (String, Publication))) : Publication =
{
def applyMerge(item: ((String, Publication), (String, Publication))): Publication = {
val crossrefPub = item._1._2
if (item._2 != null) {
val otherPub = item._2._2
@ -130,6 +126,7 @@ object SparkGenerateDoiBoost {
}
crossrefPub
}
crossrefPublication.joinWith(uwPublication, crossrefPublication("_1").equalTo(uwPublication("_1")), "left").map(applyMerge).write.mode(SaveMode.Overwrite).save(s"$workingDirPath/firstJoin")
logger.info("Phase 3) Join Result with ORCID")
val fj: Dataset[(String, Publication)] = spark.read.load(s"$workingDirPath/firstJoin").as[Publication].map(p => (p.getId, p))
@ -169,7 +166,6 @@ object SparkGenerateDoiBoost {
.select(col("_1.PaperId"), col("_2.AffiliationId"), col("_2.GridId"), col("_2.OfficialPage"), col("_2.DisplayName")).as[DoiBoostAffiliation]
val magPubs: Dataset[(String, Publication)] = spark.read.load(s"$workingDirPath/doiBoostPublicationFiltered").as[Publication]
.map(p => (ConversionUtil.extractMagIdentifier(p.getOriginalId.asScala), p))(tupleForJoinEncoder).filter(s => s._1 != null)
@ -198,8 +194,6 @@ object SparkGenerateDoiBoost {
})(mapEncoderRel).write.mode(SaveMode.Overwrite).save(s"$workingDirPath/doiBoostPublicationAffiliation_unresolved")
val unresolvedRels: Dataset[(String, Relation)] = spark.read.load(s"$workingDirPath/doiBoostPublicationAffiliation_unresolved").as[Relation].map(r => {
if (r.getSource.startsWith("unresolved"))

9
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/Crossref2Oaf.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/Crossref2Oaf.scala
View File

@ -4,20 +4,19 @@ import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf._
import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, OafMapperUtils}
import eu.dnetlib.dhp.utils.DHPUtils
import eu.dnetlib.doiboost.DoiBoostMappingUtil.{decideAccessRight, _}
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import org.apache.commons.lang.StringUtils
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.JsonAST.{JValue, _}
import org.json4s.JsonAST._
import org.json4s.jackson.JsonMethods._
import org.slf4j.{Logger, LoggerFactory}
import java.util
import scala.collection.JavaConverters._
import scala.collection.mutable
import scala.util.matching.Regex
import java.util
import eu.dnetlib.doiboost.DoiBoostMappingUtil
case class CrossrefDT(doi: String, json:String, timestamp: Long) {}

3
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/CrossrefDataset.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/CrossrefDataset.scala
View File

@ -6,7 +6,7 @@ import org.apache.commons.io.IOUtils
import org.apache.hadoop.io.{IntWritable, Text}
import org.apache.spark.SparkConf
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql.{Dataset, Encoder, SaveMode, SparkSession}
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
@ -30,7 +30,6 @@ object CrossrefDataset {
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf()
val parser = new ArgumentApplicationParser(IOUtils.toString(CrossrefDataset.getClass.getResourceAsStream("/eu/dnetlib/dhp/doiboost/crossref_to_dataset_params.json")))
parser.parseArgument(args)

10
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/GenerateCrossrefDataset.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/GenerateCrossrefDataset.scala
View File

@ -2,17 +2,12 @@ package eu.dnetlib.doiboost.crossref
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.crossref.CrossrefDataset.to_item
import eu.dnetlib.doiboost.crossref.UnpackCrtossrefEntries.getClass
import org.apache.hadoop.io.{IntWritable, Text}
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.{SparkConf, SparkContext}
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.JsonAST.JArray
import org.json4s.jackson.JsonMethods.{compact, parse, render}
import org.json4s.jackson.JsonMethods.parse
import org.slf4j.{Logger, LoggerFactory}
import scala.io.Source
@ -24,7 +19,6 @@ object GenerateCrossrefDataset {
implicit val mrEncoder: Encoder[CrossrefDT] = Encoders.kryo[CrossrefDT]
def crossrefElement(meta: String): CrossrefDT = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = parse(meta)

4
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/SparkMapDumpIntoOAF.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/SparkMapDumpIntoOAF.scala
View File

@ -4,10 +4,8 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf
import eu.dnetlib.dhp.schema.oaf.{Oaf, Publication, Relation, Dataset => OafDataset}
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}

5
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/crossref/UnpackCrtossrefEntries.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/UnpackCrtossrefEntries.scala
View File

@ -2,8 +2,8 @@ package eu.dnetlib.doiboost.crossref
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.spark.sql.SparkSession
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.JsonAST.JArray
@ -17,8 +17,6 @@ object UnpackCrtossrefEntries {
val log: Logger = LoggerFactory.getLogger(UnpackCrtossrefEntries.getClass)
def extractDump(input: String): List[String] = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = parse(input)
@ -30,7 +28,6 @@ object UnpackCrtossrefEntries {
}
def main(args: Array[String]): Unit = {
val conf = new SparkConf
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/doiboost/crossref_dump_reader/generate_dataset_params.json")).mkString)

2
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/mag/MagDataModel.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/mag/MagDataModel.scala
View File

@ -5,10 +5,10 @@ import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, StructuredProperty}
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import scala.collection.JavaConverters._
import scala.collection.mutable

3
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/mag/SparkImportMagIntoDataset.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/mag/SparkImportMagIntoDataset.scala
View File

@ -3,8 +3,8 @@ package eu.dnetlib.doiboost.mag
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.apache.spark.sql.types._
import org.apache.spark.sql.{SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
object SparkImportMagIntoDataset {
@ -75,7 +75,6 @@ object SparkImportMagIntoDataset {
.master(parser.get("master")).getOrCreate()
stream.foreach { case (k, v) =>
val s: StructType = getSchema(k)
val df = spark.read

8
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/mag/SparkProcessMAG.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/mag/SparkProcessMAG.scala
View File

@ -5,13 +5,10 @@ import eu.dnetlib.dhp.schema.oaf.Publication
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.functions._
import org.apache.spark.sql.functions.{col, collect_list, struct}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
object SparkProcessMAG {
def getDistinctResults(d: Dataset[MagPapers]): Dataset[MagPapers] = {
@ -20,7 +17,7 @@ object SparkProcessMAG {
.reduceGroups((p1: MagPapers, p2: MagPapers) => ConversionUtil.choiceLatestMagArtitcle(p1, p2))
.map(_._2)(Encoders.product[MagPapers])
.map(mp => {
new MagPapers(mp.PaperId, mp.Rank, DoiBoostMappingUtil.normalizeDoi(mp.Doi),
MagPapers(mp.PaperId, mp.Rank, DoiBoostMappingUtil.normalizeDoi(mp.Doi),
mp.DocType, mp.PaperTitle, mp.OriginalTitle,
mp.BookTitle, mp.Year, mp.Date, mp.Publisher: String,
mp.JournalId, mp.ConferenceSeriesId, mp.ConferenceInstanceId,
@ -153,6 +150,5 @@ object SparkProcessMAG {
.write.mode(SaveMode.Overwrite).save(s"$targetPath/magPublication")
}
}

7
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/ORCIDToOAF.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/orcid/ORCIDToOAF.scala
View File

@ -4,17 +4,16 @@ import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory
import eu.dnetlib.dhp.schema.oaf.{Author, DataInfo, Publication}
import eu.dnetlib.dhp.schema.orcid.{AuthorData, OrcidDOI}
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil.{createSP, generateDataInfo}
import org.apache.commons.lang.StringUtils
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.JsonAST._
import org.json4s.jackson.JsonMethods._
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
case class ORCIDItem(doi:String, authors:List[OrcidAuthor]){}

0
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkConvertORCIDToOAF.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/orcid/SparkConvertORCIDToOAF.scala
View File

7
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkPreprocessORCID.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/orcid/SparkPreprocessORCID.scala
View File

@ -1,15 +1,12 @@
package eu.dnetlib.doiboost.orcid
import com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper}
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.oa.merge.AuthorMerger
import eu.dnetlib.dhp.schema.oaf.Publication
import eu.dnetlib.dhp.schema.orcid.OrcidDOI
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.functions._
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql.functions.{col, collect_list}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
object SparkPreprocessORCID {

4
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/uw/SparkMapUnpayWallToOAF.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/uw/SparkMapUnpayWallToOAF.scala
View File

@ -1,16 +1,14 @@
package eu.dnetlib.doiboost.uw
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.Publication
import eu.dnetlib.doiboost.crossref.SparkMapDumpIntoOAF
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
object SparkMapUnpayWallToOAF {
def main(args: Array[String]): Unit = {

3
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/uw/UnpayWallToOAF.scala → dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/uw/UnpayWallToOAF.scala
View File

@ -4,14 +4,13 @@ import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory
import eu.dnetlib.dhp.schema.oaf.{AccessRight, Instance, OpenAccessRoute, Publication}
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
import eu.dnetlib.doiboost.uw.UnpayWallToOAF.get_unpaywall_color

70
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/dhp/doiboost/DoiBoostHostedByMapTest.scala
View File

@ -1,70 +0,0 @@
package eu.dnetlib.dhp.doiboost
import eu.dnetlib.dhp.schema.oaf.{Publication, Dataset => OafDataset}
import eu.dnetlib.doiboost.{DoiBoostMappingUtil, HostedByItemType}
import eu.dnetlib.doiboost.SparkGenerateDoiBoost.getClass
import eu.dnetlib.doiboost.mag.ConversionUtil
import eu.dnetlib.doiboost.orcid.ORCIDElement
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
import org.junit.jupiter.api.Test
import scala.io.Source
class DoiBoostHostedByMapTest {
// @Test
// def testMerge():Unit = {
// val conf: SparkConf = new SparkConf()
// val spark: SparkSession =
// SparkSession
// .builder()
// .config(conf)
// .appName(getClass.getSimpleName)
// .master("local[*]").getOrCreate()
//
//
//
// implicit val mapEncoderPub: Encoder[Publication] = Encoders.kryo[Publication]
// implicit val mapEncoderDataset: Encoder[OafDataset] = Encoders.kryo[OafDataset]
// implicit val tupleForJoinEncoder: Encoder[(String, Publication)] = Encoders.tuple(Encoders.STRING, mapEncoderPub)
//
//
// import spark.implicits._
// val dataset:RDD[String]= spark.sparkContext.textFile("/home/sandro/Downloads/hbMap.gz")
//
//
// val hbMap:Dataset[(String, HostedByItemType)] =spark.createDataset(dataset.map(DoiBoostMappingUtil.toHostedByItem))
//
//
// hbMap.show()
//
//
//
//
//
//
//
//
//
//
// }
@Test
def idDSGeneration():Unit = {
val s ="doajarticles::0066-782X"
println(DoiBoostMappingUtil.generateDSId(s))
}
}

20
dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/DoiBoostHostedByMapTest.scala Normal file
View File

@ -0,0 +1,20 @@
package eu.dnetlib.dhp.doiboost
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import org.junit.jupiter.api.Test
class DoiBoostHostedByMapTest {
@Test
def idDSGeneration():Unit = {
val s ="doajarticles::0066-782X"
println(DoiBoostMappingUtil.generateDSId(s))
}
}

0
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/dhp/doiboost/NormalizeDoiTest.scala → dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/NormalizeDoiTest.scala
View File

86
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/crossref/CrossrefMappingTest.scala → dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala
View File

@ -1,7 +1,8 @@
package eu.dnetlib.doiboost.crossref
package eu.dnetlib.dhp.doiboost.crossref
import eu.dnetlib.dhp.schema.oaf._
import eu.dnetlib.dhp.utils.DHPUtils
import eu.dnetlib.doiboost.crossref.Crossref2Oaf
import org.codehaus.jackson.map.{ObjectMapper, SerializationConfig}
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.Test
@ -21,9 +22,9 @@ class CrossrefMappingTest {
@Test
def testFunderRelationshipsMapping(): Unit = {
val template = Source.fromInputStream(getClass.getResourceAsStream("article_funder_template.json")).mkString
val funder_doi = Source.fromInputStream(getClass.getResourceAsStream("funder_doi")).mkString
val funder_name = Source.fromInputStream(getClass.getResourceAsStream("funder_doi")).mkString
val template = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/article_funder_template.json")).mkString
val funder_doi = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/funder_doi")).mkString
val funder_name = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/funder_doi")).mkString
for (line <- funder_doi.lines) {
@ -72,7 +73,7 @@ class CrossrefMappingTest {
@Test
def testOrcidID() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("orcid_data.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/orcid_data.json")).mkString
assertNotNull(json)
@ -93,7 +94,7 @@ class CrossrefMappingTest {
@Test
def testEmptyTitle() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("empty_title.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/empty_title.json")).mkString
assertNotNull(json)
@ -115,7 +116,7 @@ class CrossrefMappingTest {
@Test
def testPeerReviewed(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("prwTest.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/prwTest.json")).mkString
mapper.getSerializationConfig.enable(SerializationConfig.Feature.INDENT_OUTPUT)
assertNotNull(json)
@ -156,7 +157,7 @@ class CrossrefMappingTest {
@Test
def testJournalRelation(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("awardTest.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/awardTest.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty)
@ -177,7 +178,7 @@ class CrossrefMappingTest {
@Test
def testConvertBookFromCrossRef2Oaf(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("book.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/book.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty);
@ -233,7 +234,7 @@ class CrossrefMappingTest {
@Test
def testConvertPreprintFromCrossRef2Oaf(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("preprint.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/preprint.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty);
@ -291,7 +292,7 @@ class CrossrefMappingTest {
@Test
def testConvertDatasetFromCrossRef2Oaf(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("dataset.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/dataset.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty);
@ -332,7 +333,7 @@ class CrossrefMappingTest {
@Test
def testConvertArticleFromCrossRef2Oaf(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("article.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/article.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty);
@ -400,7 +401,7 @@ class CrossrefMappingTest {
@Test
def testSetDateOfAcceptanceCrossRef2Oaf(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("dump_file.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/dump_file.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty);
@ -415,55 +416,12 @@ class CrossrefMappingTest {
assert(items.size == 1)
val result: Result = items.head.asInstanceOf[Publication]
assertNotNull(result)
logger.info(mapper.writeValueAsString(result));
// assertNotNull(result.getDataInfo, "Datainfo test not null Failed");
// assertNotNull(
// result.getDataInfo.getProvenanceaction,
// "DataInfo/Provenance test not null Failed");
// assertFalse(
// result.getDataInfo.getProvenanceaction.getClassid.isEmpty,
// "DataInfo/Provenance/classId test not null Failed");
// assertFalse(
// result.getDataInfo.getProvenanceaction.getClassname.isEmpty,
// "DataInfo/Provenance/className test not null Failed");
// assertFalse(
// result.getDataInfo.getProvenanceaction.getSchemeid.isEmpty,
// "DataInfo/Provenance/SchemeId test not null Failed");
// assertFalse(
// result.getDataInfo.getProvenanceaction.getSchemename.isEmpty,
// "DataInfo/Provenance/SchemeName test not null Failed");
//
// assertNotNull(result.getCollectedfrom, "CollectedFrom test not null Failed");
// assertFalse(result.getCollectedfrom.isEmpty);
//
// val collectedFromList = result.getCollectedfrom.asScala
// assert(collectedFromList.exists(c => c.getKey.equalsIgnoreCase("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")), "Wrong collected from assertion")
//
// assert(collectedFromList.exists(c => c.getValue.equalsIgnoreCase("crossref")), "Wrong collected from assertion")
//
//
// val relevantDates = result.getRelevantdate.asScala
//
// assert(relevantDates.exists(d => d.getQualifier.getClassid.equalsIgnoreCase("created")), "Missing relevant date of type created")
//
// val rels = resultList.filter(p => p.isInstanceOf[Relation]).asInstanceOf[List[Relation]]
// assertFalse(rels.isEmpty)
// rels.foreach(relation => {
// assertNotNull(relation)
// assertFalse(relation.getSource.isEmpty)
// assertFalse(relation.getTarget.isEmpty)
// assertFalse(relation.getRelClass.isEmpty)
// assertFalse(relation.getRelType.isEmpty)
// assertFalse(relation.getSubRelType.isEmpty)
//
// })
}
@Test
def testNormalizeDOI(): Unit = {
val template = Source.fromInputStream(getClass.getResourceAsStream("article_funder_template.json")).mkString
val template = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/article_funder_template.json")).mkString
val line :String = "\"funder\": [{\"name\": \"Wellcome Trust Masters Fellowship\",\"award\": [\"090633\"]}],"
val json = template.replace("%s", line)
val resultList: List[Oaf] = Crossref2Oaf.convert(json)
@ -479,7 +437,7 @@ class CrossrefMappingTest {
@Test
def testNormalizeDOI2(): Unit = {
val template = Source.fromInputStream(getClass.getResourceAsStream("article.json")).mkString
val template = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/article.json")).mkString
val resultList: List[Oaf] = Crossref2Oaf.convert(template)
assertTrue(resultList.nonEmpty)
@ -494,7 +452,7 @@ class CrossrefMappingTest {
@Test
def testLicenseVorClosed() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("publication_license_vor.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_vor.json")).mkString
assertNotNull(json)
@ -521,7 +479,7 @@ class CrossrefMappingTest {
@Test
def testLicenseOpen() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("publication_license_open.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_open.json")).mkString
assertNotNull(json)
@ -544,7 +502,7 @@ class CrossrefMappingTest {
@Test
def testLicenseEmbargoOpen() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("publication_license_embargo_open.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_embargo_open.json")).mkString
assertNotNull(json)
@ -567,7 +525,7 @@ class CrossrefMappingTest {
@Test
def testLicenseEmbargo() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("publication_license_embargo.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_embargo.json")).mkString
assertNotNull(json)
@ -591,7 +549,7 @@ class CrossrefMappingTest {
@Test
def testLicenseEmbargoDateTime() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("publication_license_embargo_datetime.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/publication_license_embargo_datetime.json")).mkString
assertNotNull(json)
@ -614,7 +572,7 @@ class CrossrefMappingTest {
@Test
def testMultipleURLs() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("multiple_urls.json")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/multiple_urls.json")).mkString
assertNotNull(json)

11
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/mag/MAGMappingTest.scala → dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/mag/MAGMappingTest.scala
View File

@ -1,11 +1,12 @@
package eu.dnetlib.doiboost.mag
package eu.dnetlib.dhp.doiboost.mag
import eu.dnetlib.doiboost.mag.{ConversionUtil, MagPapers, SparkProcessMAG}
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, SparkSession}
import org.codehaus.jackson.map.ObjectMapper
import org.json4s.DefaultFormats
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.Test
import org.json4s.DefaultFormats
import org.slf4j.{Logger, LoggerFactory}
import java.sql.Timestamp
@ -47,7 +48,7 @@ class MAGMappingTest {
@Test
def buildInvertedIndexTest(): Unit = {
val json_input = Source.fromInputStream(getClass.getResourceAsStream("invertedIndex.json")).mkString
val json_input = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/mag/invertedIndex.json")).mkString
val description = ConversionUtil.convertInvertedIndexString(json_input)
assertNotNull(description)
assertTrue(description.nonEmpty)
@ -71,7 +72,7 @@ class MAGMappingTest {
.appName(getClass.getSimpleName)
.config(conf)
.getOrCreate()
val path = getClass.getResource("magPapers.json").getPath
val path = getClass.getResource("/eu/dnetlib/doiboost/mag/magPapers.json").getPath
import org.apache.spark.sql.Encoders
val schema = Encoders.product[MagPapers].schema
@ -101,7 +102,7 @@ class MAGMappingTest {
.appName(getClass.getSimpleName)
.config(conf)
.getOrCreate()
val path = getClass.getResource("duplicatedMagPapers.json").getPath
val path = getClass.getResource("/eu/dnetlib/doiboost/mag/duplicatedMagPapers.json").getPath
import org.apache.spark.sql.Encoders
val schema = Encoders.product[MagPapers].schema

8
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/MappingORCIDToOAFTest.scala → dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/orcid/MappingORCIDToOAFTest.scala
View File

@ -1,7 +1,8 @@
package eu.dnetlib.doiboost.orcid
package eu.dnetlib.dhp.doiboost.orcid
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.oaf.Publication
import eu.dnetlib.doiboost.orcid._
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.junit.jupiter.api.Assertions._
@ -10,9 +11,8 @@ import org.junit.jupiter.api.io.TempDir
import org.slf4j.{Logger, LoggerFactory}
import java.nio.file.Path
import scala.io.Source
import scala.collection.JavaConversions._
import scala.io.Source
class MappingORCIDToOAFTest {
val logger: Logger = LoggerFactory.getLogger(ORCIDToOAF.getClass)
@ -20,7 +20,7 @@ class MappingORCIDToOAFTest {
@Test
def testExtractData():Unit ={
val json = Source.fromInputStream(getClass.getResourceAsStream("dataOutput")).mkString
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/orcid/dataOutput")).mkString
assertNotNull(json)
assertFalse(json.isEmpty)
json.lines.foreach(s => {

10
dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/uw/UnpayWallMappingTest.scala → dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/uw/UnpayWallMappingTest.scala
View File

@ -1,13 +1,13 @@
package eu.dnetlib.doiboost.uw
package eu.dnetlib.dhp.doiboost.uw
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.oaf.OpenAccessRoute
import eu.dnetlib.doiboost.uw.UnpayWallToOAF
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.Test
import org.slf4j.{Logger, LoggerFactory}
import scala.io.Source
import org.junit.jupiter.api.Assertions._
import org.slf4j.{Logger, LoggerFactory}
class UnpayWallMappingTest {
@ -18,7 +18,7 @@ class UnpayWallMappingTest {
@Test
def testMappingToOAF():Unit ={
val Ilist = Source.fromInputStream(getClass.getResourceAsStream("input.json")).mkString
val Ilist = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/uw/input.json")).mkString
var i:Int = 0
for (line <-Ilist.lines) {

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/hostedbymap/Aggregators.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/Aggregators.scala
View File

@ -1,8 +1,8 @@
package eu.dnetlib.dhp.oa.graph.hostedbymap
import eu.dnetlib.dhp.oa.graph.hostedbymap.model.EntityInfo
import org.apache.spark.sql.{Dataset, Encoder, Encoders, TypedColumn}
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.{Dataset, Encoder, Encoders, TypedColumn}
case class HostedByItemType(id: String, officialname: String, issn: String, eissn: String, lissn: String, openAccess: Boolean) {}

5
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkApplyHostedByMapToDatasource.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkApplyHostedByMapToDatasource.scala
View File

@ -2,13 +2,12 @@ package eu.dnetlib.dhp.oa.graph.hostedbymap
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.oa.graph.hostedbymap.SparkApplyHostedByMapToResult.{applyHBtoPubs, getClass}
import eu.dnetlib.dhp.oa.graph.hostedbymap.model.EntityInfo
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.{Datasource, Publication}
import eu.dnetlib.dhp.schema.oaf.Datasource
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.json4s.DefaultFormats
import org.slf4j.{Logger, LoggerFactory}

9
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkApplyHostedByMapToResult.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkApplyHostedByMapToResult.scala
View File

@ -5,16 +5,14 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.oa.graph.hostedbymap.model.EntityInfo
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils
import eu.dnetlib.dhp.schema.oaf.{Datasource, Instance, OpenAccessRoute, Publication}
import eu.dnetlib.dhp.schema.oaf.{Instance, OpenAccessRoute, Publication}
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.json4s.DefaultFormats
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
object SparkApplyHostedByMapToResult {
def applyHBtoPubs(join: Dataset[EntityInfo], pubs: Dataset[Publication]) = {
@ -25,7 +23,7 @@ object SparkApplyHostedByMapToResult {
val ei: EntityInfo = t2._2
val i = p.getInstance().asScala
if (i.size == 1) {
val inst: Instance = i(0)
val inst: Instance = i.head
inst.getHostedby.setKey(ei.getHostedById)
inst.getHostedby.setValue(ei.getName)
if (ei.getOpenAccess) {
@ -39,6 +37,7 @@ object SparkApplyHostedByMapToResult {
p
})(Encoders.bean(classOf[Publication]))
}
def main(args: Array[String]): Unit = {

5
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkPrepareHostedByInfoToApply.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkPrepareHostedByInfoToApply.scala
View File

@ -3,18 +3,15 @@ package eu.dnetlib.dhp.oa.graph.hostedbymap
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.oa.graph.hostedbymap.model.EntityInfo
import eu.dnetlib.dhp.schema.oaf.{Journal, Publication}
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import org.slf4j.{Logger, LoggerFactory}
object SparkPrepareHostedByInfoToApply {
implicit val mapEncoderPInfo: Encoder[EntityInfo] = Encoders.bean(classOf[EntityInfo])

17
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkProduceHostedByMap.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/SparkProduceHostedByMap.scala
View File

@ -1,22 +1,20 @@
package eu.dnetlib.dhp.oa.graph.hostedbymap
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.oa.graph.hostedbymap.model.{DOAJModel, UnibiGoldModel}
import eu.dnetlib.dhp.schema.oaf.Datasource
import org.apache.commons.io.IOUtils
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.json4s.DefaultFormats
import org.slf4j.{Logger, LoggerFactory}
import com.fasterxml.jackson.databind.ObjectMapper
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.FileSystem
import org.apache.hadoop.fs.Path
import java.io.PrintWriter
import org.apache.hadoop.io.compress.GzipCodec
object SparkProduceHostedByMap {
@ -52,7 +50,6 @@ object SparkProduceHostedByMap {
}
def getHostedByItemType(id: String, officialname: String, issn: String, eissn: String, issnl: String, oa: Boolean): HostedByItemType = {
if (issn != null) {
if (eissn != null) {
@ -163,7 +160,6 @@ object SparkProduceHostedByMap {
}
def writeToHDFS(input: Array[String], outputPath: String, hdfsNameNode: String): Unit = {
val conf = new Configuration()
@ -182,7 +178,6 @@ object SparkProduceHostedByMap {
}
def main(args: Array[String]): Unit = {
val logger: Logger = LoggerFactory.getLogger(getClass)

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

@ -4,17 +4,11 @@ import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.HdfsSupport
import eu.dnetlib.dhp.schema.common.ModelSupport
import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo
import eu.dnetlib.dhp.schema.oaf.Oaf
import eu.dnetlib.dhp.utils.DHPUtils
import org.apache.commons.io.IOUtils
import org.apache.commons.lang3.StringUtils
import org.apache.http.client.methods.HttpGet
import org.apache.http.impl.client.HttpClients
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.{SparkConf, SparkContext}
import org.slf4j.LoggerFactory
import scala.collection.JavaConverters._
import scala.io.Source

3
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/resolution/SparkResolveEntities.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/resolution/SparkResolveEntities.scala
View File

@ -2,9 +2,8 @@ package eu.dnetlib.dhp.oa.graph.resolution
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.HdfsSupport
import eu.dnetlib.dhp.schema.common.EntityType
import eu.dnetlib.dhp.schema.oaf.{OtherResearchProduct, Publication, Result, Software, Dataset => OafDataset}
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset,_}
import org.apache.commons.io.IOUtils
import org.apache.hadoop.fs.{FileSystem, Path}
import org.apache.spark.SparkConf

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/resolution/SparkResolveRelation.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/resolution/SparkResolveRelation.scala
View File

@ -3,7 +3,7 @@ package eu.dnetlib.dhp.oa.graph.resolution
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.HdfsSupport
import eu.dnetlib.dhp.schema.oaf.{Relation, Result}
import eu.dnetlib.dhp.schema.oaf.Relation
import eu.dnetlib.dhp.utils.DHPUtils
import org.apache.commons.io.IOUtils
import org.apache.hadoop.fs.{FileSystem, Path}

1
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/sx/graphimport/SparkDataciteToOAF.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/sx/graphimport/SparkDataciteToOAF.scala
View File

@ -18,7 +18,6 @@ object SparkDataciteToOAF {
.config(conf)
.appName(getClass.getSimpleName)
.master(parser.get("master")).getOrCreate()
import spark.implicits._
val sc = spark.sparkContext

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkConvertDatasetToJsonRDD.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkConvertDatasetToJsonRDD.scala
View File

@ -2,7 +2,7 @@ package eu.dnetlib.dhp.sx.graph
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.{Oaf, OtherResearchProduct, Publication, Result, Software, Dataset => OafDataset}
import eu.dnetlib.dhp.schema.oaf.Result
import org.apache.commons.io.IOUtils
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.spark.SparkConf

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkConvertObjectToJson.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkConvertObjectToJson.scala
View File

@ -5,10 +5,10 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.sx.scholix.Scholix
import eu.dnetlib.dhp.schema.sx.summary.ScholixSummary
import org.apache.commons.io.IOUtils
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import org.apache.hadoop.io.compress._
object SparkConvertObjectToJson {

3
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkConvertRDDtoDataset.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkConvertRDDtoDataset.scala
View File

@ -2,11 +2,12 @@ package eu.dnetlib.dhp.sx.graph
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.{OtherResearchProduct, Publication, Relation, Result, Software, Dataset => OafDataset}
import eu.dnetlib.dhp.schema.oaf.{OtherResearchProduct, Publication, Relation, Software,Dataset => OafDataset}
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
object SparkConvertRDDtoDataset {
def main(args: Array[String]): Unit = {

9
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkCreateInputGraph.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkCreateInputGraph.scala
View File

@ -1,14 +1,12 @@
package eu.dnetlib.dhp.sx.graph
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.{Oaf, OtherResearchProduct, Publication, Relation, Result, Software, Dataset => OafDataset}
import eu.dnetlib.dhp.schema.oaf.{Dataset => OafDataset,_}
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
object SparkCreateInputGraph {
def main(args: Array[String]): Unit = {
@ -41,9 +39,6 @@ object SparkCreateInputGraph {
implicit val relEncoder: Encoder[Relation] = Encoders.kryo(classOf[Relation])
val sourcePath = parser.get("sourcePath")
log.info(s"sourcePath -> $sourcePath")
val targetPath = parser.get("targetPath")

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkCreateScholix.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkCreateScholix.scala
View File

@ -9,7 +9,7 @@ import eu.dnetlib.dhp.sx.graph.scholix.ScholixUtils.RelatedEntities
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.functions.count
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
object SparkCreateScholix {

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/SparkCreateSummaryObject.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/SparkCreateSummaryObject.scala
View File

@ -6,7 +6,7 @@ import eu.dnetlib.dhp.schema.sx.summary.ScholixSummary
import eu.dnetlib.dhp.sx.graph.scholix.ScholixUtils
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
object SparkCreateSummaryObject {

1
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/pangaea/PangaeaUtils.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/pangaea/PangaeaUtils.scala
View File

@ -5,6 +5,7 @@ import org.apache.spark.sql.{Encoder, Encoders}
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import java.util.regex.Pattern
import scala.language.postfixOps
import scala.xml.{Elem, Node, XML}

7
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/pangaea/SparkGeneratePanagaeaDataset.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/pangaea/SparkGeneratePanagaeaDataset.scala
View File

@ -2,11 +2,11 @@ package eu.dnetlib.dhp.sx.graph.pangaea
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.{SparkConf, SparkContext}
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
import scala.io.Source
object SparkGeneratePanagaeaDataset {
@ -46,7 +46,4 @@ object SparkGeneratePanagaeaDataset {
}
}

15
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/sx/graph/scholix/ScholixUtils.scala → dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/sx/graph/scholix/ScholixUtils.scala
View File

@ -1,6 +1,5 @@
package eu.dnetlib.dhp.sx.graph.scholix
import eu.dnetlib.dhp.schema.oaf.{Publication, Relation, Result, StructuredProperty}
import eu.dnetlib.dhp.schema.sx.scholix._
import eu.dnetlib.dhp.schema.sx.summary.{CollectedFromType, SchemeValue, ScholixSummary, Typology}
@ -10,10 +9,8 @@ import org.apache.spark.sql.{Encoder, Encoders}
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import scala.collection.JavaConverters._
import scala.io.Source
import scala.language.postfixOps
object ScholixUtils {
@ -21,6 +18,7 @@ object ScholixUtils {
val DNET_IDENTIFIER_SCHEMA: String = "DNET Identifier"
val DATE_RELATION_KEY: String = "RelationDate"
case class RelationVocabulary(original: String, inverse: String) {}
case class RelatedEntities(id: String, relatedDataset: Long, relatedPublication: Long) {}
@ -66,7 +64,6 @@ object ScholixUtils {
}
val statsAggregator: Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] = new Aggregator[(String, String, Long), RelatedEntities, RelatedEntities] with Serializable {
override def zero: RelatedEntities = null
@ -85,8 +82,7 @@ object ScholixUtils {
if (b1 != null && b2 != null)
RelatedEntities(b1.id, b1.relatedDataset + b2.relatedDataset, b1.relatedPublication + b2.relatedPublication)
else
if (b1!= null)
else if (b1 != null)
b1
else
b2
@ -144,7 +140,6 @@ object ScholixUtils {
s
}
@ -203,8 +198,7 @@ object ScholixUtils {
if (summaryObject.getDate != null && !summaryObject.getDate.isEmpty)
r.setPublicationDate(summaryObject.getDate.get(0))
if (summaryObject.getPublisher!= null && !summaryObject.getPublisher.isEmpty)
{
if (summaryObject.getPublisher != null && !summaryObject.getPublisher.isEmpty) {
val plist: List[ScholixEntityId] = summaryObject.getPublisher.asScala.map(p => new ScholixEntityId(p, null)).toList
if (plist.nonEmpty)
@ -228,9 +222,6 @@ object ScholixUtils {
}
def scholixFromSource(relation: Relation, source: ScholixSummary): Scholix = {
if (relation == null || source == null)

18
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/DumpJobTest.java
View File

@ -171,24 +171,6 @@ public class DumpJobTest {
GraphResult gr = verificationDataset.first();
Assertions.assertEquals(2, gr.getMeasures().size());
Assertions
.assertTrue(
gr
.getMeasures()
.stream()
.anyMatch(
m -> m.getKey().equals("influence")
&& m.getValue().equals("1.62759106106e-08")));
Assertions
.assertTrue(
gr
.getMeasures()
.stream()
.anyMatch(
m -> m.getKey().equals("popularity")
&& m.getValue().equals("0.22519296")));
Assertions.assertEquals(6, gr.getAuthor().size());
Assertions
.assertTrue(

4
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/addProjectInfo/publication_extendedmodel
View File

File diff suppressed because one or more lines are too long

0
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/hostedbymap/TestApply.scala → dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/TestApply.scala
View File

4
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/hostedbymap/TestPrepare.scala → dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/TestPrepare.scala
View File

@ -3,13 +3,9 @@ package eu.dnetlib.dhp.oa.graph.hostedbymap
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.oa.graph.hostedbymap.SparkPrepareHostedByInfoToApply.{joinResHBM, prepareResultInfo, toEntityInfo}
import eu.dnetlib.dhp.oa.graph.hostedbymap.model.EntityInfo
import eu.dnetlib.dhp.schema.oaf.{Datasource, OpenAccessRoute, Publication}
import javax.management.openmbean.OpenMBeanAttributeInfo
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.json4s
import org.json4s.DefaultFormats
import eu.dnetlib.dhp.schema.common.ModelConstants
import org.junit.jupiter.api.Assertions.{assertEquals, assertTrue}
import org.junit.jupiter.api.Test

5
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/hostedbymap/TestPreprocess.scala → dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/oa/graph/hostedbymap/TestPreprocess.scala
View File

@ -4,10 +4,9 @@ import eu.dnetlib.dhp.schema.oaf.Datasource
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.json4s.DefaultFormats
import org.junit.jupiter.api.Assertions.{assertNotNull, assertTrue}
import org.junit.jupiter.api.Test
import org.junit.jupiter.api.Assertions._
import org.json4s.jackson.Serialization.write
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.Test
class TestPreprocess extends java.io.Serializable{

0
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/resolution/ResolveEntitiesTest.scala → dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/oa/graph/resolution/ResolveEntitiesTest.scala
View File

3
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/sx/graph/scholix/ScholixGraphTest.scala → dhp-workflows/dhp-graph-mapper/src/test/scala/eu/dnetlib/dhp/sx/graph/scholix/ScholixGraphTest.scala
View File

@ -37,7 +37,8 @@ class ScholixGraphTest extends AbstractVocabularyTest{
val input = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/scholix/result.json")).mkString
val res =SparkResolveRelation.extractPidsFromRecord(input)
assertNotNull(res)
assertTrue(res._2.size == 2)
assertEquals(1,res._2.size)
}