From 7b15b88d4cdc60daf7cc7e60badea8f844abb57e Mon Sep 17 00:00:00 2001 From: Sandro La Bruzzo Date: Fri, 15 Oct 2021 15:00:15 +0200 Subject: [PATCH] renamed wrong package, implemented last aggregation workflow for scholexplorer --- .../dhp/sx/bio/BioDBToOAF.scala | 2 +- .../bio/SparkTransformBioDatabaseToOAF.scala | 6 +- .../ebi/SparkCreateBaselineDataFrame.scala | 4 +- .../sx/bio/ebi/SparkDownloadEBILinks.scala | 7 +- .../dhp/sx/bio/ebi/SparkEBILinksToOaf.scala | 7 +- .../dhp/sx/bio/pubmed/PMArticle.java | 2 +- .../dhp/sx/bio/pubmed/PMAuthor.java | 2 +- .../dhp/sx/bio/pubmed/PMGrant.java | 2 +- .../dhp/sx/bio/pubmed/PMJournal.java | 2 +- .../dhp/sx/bio/pubmed/PMParser.scala | 2 +- .../dhp/sx/bio/pubmed/PMSubject.java | 2 +- .../dhp/sx/bio/pubmed/PubMedToOaf.scala | 2 +- .../sx/bio/db}/oozie_app/config-default.xml | 0 .../dhp/sx/bio/db/oozie_app/workflow.xml | 51 +++++ .../dhp/sx/bio/ebi}/bio_to_oaf_params.json | 0 .../dhp/sx/bio/BioScholixTest.scala | 6 +- .../dhp/sx/graph/bio/oozie_app/workflow.xml | 177 ------------------ 17 files changed, 75 insertions(+), 199 deletions(-) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/BioDBToOAF.scala (99%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala (91%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala (98%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala (95%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala (90%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/pubmed/PMArticle.java (97%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/pubmed/PMAuthor.java (93%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/pubmed/PMGrant.java (94%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/pubmed/PMJournal.java (95%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/pubmed/PMParser.scala (99%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/pubmed/PMSubject.java (94%) rename dhp-workflows/dhp-aggregation/src/main/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/pubmed/PubMedToOaf.scala (99%) rename dhp-workflows/{dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio => dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db}/oozie_app/config-default.xml (100%) create mode 100644 dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/workflow.xml rename dhp-workflows/{dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio => dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi}/bio_to_oaf_params.json (100%) rename dhp-workflows/dhp-aggregation/src/test/java/eu/{dnetllib => dnetlib}/dhp/sx/bio/BioScholixTest.scala (97%) delete mode 100644 dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/BioDBToOAF.scala b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala similarity index 99% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/BioDBToOAF.scala rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala index dffc88c6c..70dcc0184 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/BioDBToOAF.scala +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/BioDBToOAF.scala @@ -1,4 +1,4 @@ -package eu.dnetllib.dhp.sx.bio +package eu.dnetlib.dhp.sx.bio import eu.dnetlib.dhp.schema.common.ModelConstants import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, OafMapperUtils} diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala similarity index 91% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala index 16d2b25a6..7a62437a3 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala @@ -1,8 +1,8 @@ -package eu.dnetllib.dhp.sx.bio +package eu.dnetlib.dhp.sx.bio import eu.dnetlib.dhp.application.ArgumentApplicationParser import eu.dnetlib.dhp.schema.oaf.Oaf -import eu.dnetllib.dhp.sx.bio.BioDBToOAF.ScholixResolved +import BioDBToOAF.ScholixResolved import org.apache.commons.io.IOUtils import org.apache.spark.SparkConf import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession} @@ -13,7 +13,7 @@ object SparkTransformBioDatabaseToOAF { def main(args: Array[String]): Unit = { val conf: SparkConf = new SparkConf() val log: Logger = LoggerFactory.getLogger(getClass) - val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/bio_to_oaf_params.json"))) + val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json"))) parser.parseArgument(args) val database: String = parser.get("database") log.info("database: {}", database) diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala similarity index 98% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala index 17bf3fa6b..17d21f19c 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkCreateBaselineDataFrame.scala @@ -1,10 +1,10 @@ -package eu.dnetllib.dhp.sx.bio.ebi +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.utils.ISLookupClientFactory -import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal, PMParser, PubMedToOaf} import org.apache.commons.io.IOUtils import org.apache.hadoop.conf.Configuration import org.apache.hadoop.fs.{FSDataOutputStream, FileSystem, Path} diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala similarity index 95% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala index 85fbd99c4..eab6b1dc6 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala @@ -1,8 +1,9 @@ -package eu.dnetllib.dhp.sx.bio.ebi +package eu.dnetlib.dhp.sx.bio.ebi import eu.dnetlib.dhp.application.ArgumentApplicationParser -import eu.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem -import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal} +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 org.apache.commons.io.IOUtils import org.apache.http.client.config.RequestConfig import org.apache.http.client.methods.HttpGet diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala similarity index 90% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala index 10467884c..b19bfc23a 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala @@ -1,9 +1,10 @@ -package eu.dnetllib.dhp.sx.bio.ebi +package eu.dnetlib.dhp.sx.bio.ebi import eu.dnetlib.dhp.application.ArgumentApplicationParser import eu.dnetlib.dhp.schema.oaf.Oaf -import eu.dnetllib.dhp.sx.bio.BioDBToOAF -import eu.dnetllib.dhp.sx.bio.BioDBToOAF.EBILinkItem +import eu.dnetlib.dhp.sx.bio.BioDBToOAF +import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem +import BioDBToOAF.EBILinkItem import org.apache.commons.io.IOUtils import org.apache.spark.SparkConf import org.apache.spark.sql._ diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMArticle.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMArticle.java similarity index 97% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMArticle.java rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMArticle.java index 305bb89be..881528425 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMArticle.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMArticle.java @@ -1,5 +1,5 @@ -package eu.dnetllib.dhp.sx.bio.pubmed; +package eu.dnetlib.dhp.sx.bio.pubmed; import java.io.Serializable; import java.util.ArrayList; diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMAuthor.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMAuthor.java similarity index 93% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMAuthor.java rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMAuthor.java index c89929981..cef92d003 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMAuthor.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMAuthor.java @@ -1,5 +1,5 @@ -package eu.dnetllib.dhp.sx.bio.pubmed; +package eu.dnetlib.dhp.sx.bio.pubmed; import java.io.Serializable; diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMGrant.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMGrant.java similarity index 94% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMGrant.java rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMGrant.java index 7df5dd5f2..ce9420cc1 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMGrant.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMGrant.java @@ -1,5 +1,5 @@ -package eu.dnetllib.dhp.sx.bio.pubmed; +package eu.dnetlib.dhp.sx.bio.pubmed; public class PMGrant { diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMJournal.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMJournal.java similarity index 95% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMJournal.java rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMJournal.java index 6065416f8..863a23bd5 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMJournal.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMJournal.java @@ -1,5 +1,5 @@ -package eu.dnetllib.dhp.sx.bio.pubmed; +package eu.dnetlib.dhp.sx.bio.pubmed; import java.io.Serializable; diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMParser.scala b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMParser.scala similarity index 99% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMParser.scala rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMParser.scala index 8fa226b7d..80cb0667c 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMParser.scala +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMParser.scala @@ -1,4 +1,4 @@ -package eu.dnetllib.dhp.sx.bio.pubmed +package eu.dnetlib.dhp.sx.bio.pubmed import scala.xml.MetaData import scala.xml.pull.{EvElemEnd, EvElemStart, EvText, XMLEventReader} diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMSubject.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMSubject.java similarity index 94% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMSubject.java rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMSubject.java index e6ab61b87..862d39a94 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMSubject.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMSubject.java @@ -1,5 +1,5 @@ -package eu.dnetllib.dhp.sx.bio.pubmed; +package eu.dnetlib.dhp.sx.bio.pubmed; public class PMSubject { private String value; diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PubMedToOaf.scala b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala similarity index 99% rename from dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PubMedToOaf.scala rename to dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala index a1777a230..13f38408e 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PubMedToOaf.scala +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala @@ -1,4 +1,4 @@ -package eu.dnetllib.dhp.sx.bio.pubmed +package eu.dnetlib.dhp.sx.bio.pubmed import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup import eu.dnetlib.dhp.schema.common.ModelConstants diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/config-default.xml b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/config-default.xml rename to dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/workflow.xml b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/workflow.xml new file mode 100644 index 000000000..071d202b6 --- /dev/null +++ b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/workflow.xml @@ -0,0 +1,51 @@ + + + + sourcePath + the PDB Database Working Path + + + database + the PDB Database Working Path + + + + targetPath + the Target Working dir path + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + yarn + cluster + Convert Bio DB to OAF Dataset + eu.dnetlib.dhp.sx.bio.SparkTransformBioDatabaseToOAF + dhp-aggregation-${projectVersion}.jar + + --executor-memory=${sparkExecutorMemory} + --executor-cores=${sparkExecutorCores} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.shuffle.partitions=2000 + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --masteryarn + --dbPath${sourcePath} + --database${database} + --targetPath${targetPath} + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/bio_to_oaf_params.json b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json similarity index 100% rename from dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/bio_to_oaf_params.json rename to dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json diff --git a/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetllib/dhp/sx/bio/BioScholixTest.scala b/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala similarity index 97% rename from dhp-workflows/dhp-aggregation/src/test/java/eu/dnetllib/dhp/sx/bio/BioScholixTest.scala rename to dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala index c072f149c..893a6e628 100644 --- a/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetllib/dhp/sx/bio/BioScholixTest.scala +++ b/dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala @@ -1,10 +1,10 @@ -package eu.dnetllib.dhp.sx.bio +package eu.dnetlib.dhp.sx.bio import com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper, SerializationFeature} import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result} -import eu.dnetllib.dhp.sx.bio.BioDBToOAF.ScholixResolved -import eu.dnetllib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf} +import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved +import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf} import org.json4s.DefaultFormats import org.json4s.JsonAST.{JField, JObject, JString} import org.json4s.jackson.JsonMethods.parse diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml deleted file mode 100644 index 0df085ee1..000000000 --- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml +++ /dev/null @@ -1,177 +0,0 @@ - - - - PDBPath - the PDB Database Working Path - - - - UNIPROTDBPath - the UNIPROT Database Working Path - - - - EBIDataset - the EBI Links Dataset Path - - - - ScholixResolvedDBPath - the Scholix Resolved Dataset Path - - - - CrossrefLinksPath - the CrossrefLinks Path - - - targetPath - the Target Working dir path - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - yarn - cluster - Convert PDB to OAF Dataset - eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF - dhp-graph-mapper-${projectVersion}.jar - - --executor-memory=${sparkExecutorMemory} - --executor-cores=${sparkExecutorCores} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.shuffle.partitions=2000 - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --masteryarn - --dbPath${PDBPath} - --databasePDB - --targetPath${targetPath}/pdb_OAF - - - - - - - - - yarn - cluster - Convert UNIPROT to OAF Dataset - eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF - dhp-graph-mapper-${projectVersion}.jar - - --executor-memory=${sparkExecutorMemory} - --executor-cores=${sparkExecutorCores} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.shuffle.partitions=2000 - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --masteryarn - --dbPath${UNIPROTDBPath} - --databaseUNIPROT - --targetPath${targetPath}/uniprot_OAF - - - - - - - - - yarn - cluster - Convert EBI Links to OAF Dataset - eu.dnetlib.dhp.sx.graph.ebi.SparkEBILinksToOaf - dhp-graph-mapper-${projectVersion}.jar - - --executor-memory=${sparkExecutorMemory} - --executor-cores=${sparkExecutorCores} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.shuffle.partitions=2000 - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --masteryarn - --sourcePath${EBIDataset} - --targetPath${targetPath}/ebi_OAF - - - - - - - - - yarn - cluster - Convert Scholix to OAF Dataset - eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF - dhp-graph-mapper-${projectVersion}.jar - - --executor-memory=${sparkExecutorMemory} - --executor-cores=${sparkExecutorCores} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.shuffle.partitions=2000 - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --masteryarn - --dbPath${ScholixResolvedDBPath} - --databaseSCHOLIX - --targetPath${targetPath}/scholix_resolved_OAF - - - - - - - - - yarn - cluster - Convert Crossref Links to OAF Dataset - eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF - dhp-graph-mapper-${projectVersion}.jar - - --executor-memory=${sparkExecutorMemory} - --executor-cores=${sparkExecutorCores} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.shuffle.partitions=2000 - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --masteryarn - --dbPath${CrossrefLinksPath} - --databaseCROSSREF_LINKS - --targetPath${targetPath}/crossref_unresolved_relation_OAF - - - - - - - - - - - \ No newline at end of file