D-Net
/
dnet-hadoop
13
4
Fork 10
Code Issues 14 Pull Requests 8 Projects 2 Releases 1 Wiki Activity

[scala-refactor] Module dhp-doiboost: 

Moved all scala source into src/main/scala and src/test/scala
This commit is contained in:
Sandro La Bruzzo 2021-12-06 14:24:03 +01:00
parent bf880e2508
commit e9f285ec4d
23 changed files with 181 additions and 316 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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) {