lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

Merge branch 'beta' into dump

This commit is contained in:
Claudio Atzori 2021-10-19 16:15:03 +02:00
parent c7f6cd2591 98f37c8d81
commit e9157c67aa
27 changed files with 540 additions and 444 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -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}

6
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/SparkTransformBioDatabaseToOAF.scala
View File

@ -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)

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

@ -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}

7
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkDownloadEBILinks.scala
View File

@ -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

7
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/ebi/SparkEBILinksToOaf.scala
View File

@ -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._

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMArticle.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMArticle.java
View File

@ -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;

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMAuthor.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMAuthor.java
View File

@ -1,5 +1,5 @@
package eu.dnetllib.dhp.sx.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
import java.io.Serializable;

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMGrant.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMGrant.java
View File

@ -1,5 +1,5 @@
package eu.dnetllib.dhp.sx.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
public class PMGrant {

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMJournal.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMJournal.java
View File

@ -1,5 +1,5 @@
package eu.dnetllib.dhp.sx.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
import java.io.Serializable;

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMParser.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMParser.scala
View File

@ -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}

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PMSubject.java → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PMSubject.java
View File

@ -1,5 +1,5 @@
package eu.dnetllib.dhp.sx.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
public class PMSubject {
private String value;

2
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetllib/dhp/sx/bio/pubmed/PubMedToOaf.scala → dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/sx/bio/pubmed/PubMedToOaf.scala
View File

@ -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

0
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/config-default.xml → dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/config-default.xml
View File

51
dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/db/oozie_app/workflow.xml Normal file
View File

@ -0,0 +1,51 @@
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the PDB Database Working Path</description>
</property>
<property>
<name>database</name>
<description>the PDB Database Working Path</description>
</property>
<property>
<name>targetPath</name>
<description>the Target Working dir path</description>
</property>
</parameters>
<start to="ConvertDB"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ConvertDB">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert Bio DB to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.bio.SparkTransformBioDatabaseToOAF</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--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}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--dbPath</arg><arg>${sourcePath}</arg>
<arg>--database</arg><arg>${database}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

0
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/bio_to_oaf_params.json → dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json
View File

6
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetllib/dhp/sx/bio/BioScholixTest.scala → dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/sx/bio/BioScholixTest.scala
View File

@ -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

4
dhp-workflows/dhp-blacklist/src/main/java/eu/dnetlib/dhp/blacklist/ReadBlacklistFromDB.java
View File

@ -91,8 +91,8 @@ public class ReadBlacklistFromDB implements Closeable {
String encoding = rs.getString("relationship");
RelationInverse ri = ModelSupport.relationInverseMap.get(encoding);
direct.setRelClass(ri.getRelation());
inverse.setRelClass(ri.getInverse());
direct.setRelClass(ri.getRelClass());
inverse.setRelClass(ri.getInverseRelClass());
direct.setRelType(ri.getRelType());
inverse.setRelType(ri.getRelType());
direct.setSubRelType(ri.getSubReltype());

134
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafApplication.java Normal file
View File

@ -0,0 +1,134 @@
package eu.dnetlib.dhp.oa.graph.raw;
import com.clearspring.analytics.util.Lists;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
import eu.dnetlib.dhp.oa.graph.raw.common.AbstractMigrationApplication;
import eu.dnetlib.dhp.schema.common.EntityType;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.util.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
public class CopyHdfsOafApplication extends AbstractMigrationApplication {
private static final Logger log = LoggerFactory.getLogger(CopyHdfsOafApplication.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
CopyHdfsOafApplication.class
.getResourceAsStream("/eu/dnetlib/dhp/oa/graph/copy_hdfs_oaf_parameters.json")));
parser.parseArgument(args);
final Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String mdstoreManagerUrl = parser.get("mdstoreManagerUrl");
log.info("mdstoreManagerUrl: {}", mdstoreManagerUrl);
final String mdFormat = parser.get("mdFormat");
log.info("mdFormat: {}", mdFormat);
final String mdLayout = parser.get("mdLayout");
log.info("mdLayout: {}", mdLayout);
final String mdInterpretation = parser.get("mdInterpretation");
log.info("mdInterpretation: {}", mdInterpretation);
final String hdfsPath = parser.get("hdfsPath");
log.info("hdfsPath: {}", hdfsPath);
final String isLookupUrl = parser.get("isLookupUrl");
log.info("isLookupUrl: {}", isLookupUrl);
final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
final VocabularyGroup vocs = VocabularyGroup.loadVocsFromIS(isLookupService);
final Set<String> paths = mdstorePaths(mdstoreManagerUrl, mdFormat, mdLayout, mdInterpretation);
final SparkConf conf = new SparkConf();
runWithSparkSession(conf, isSparkSessionManaged, spark -> processPaths(spark, vocs, hdfsPath, paths));
}
public static void processPaths(final SparkSession spark,
final VocabularyGroup vocs,
final String outputPath,
final Set<String> paths) {
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
log.info("Found {} mdstores", paths.size());
paths.forEach(log::info);
final String[] validPaths = paths
.stream()
.filter(p -> HdfsSupport.exists(p, sc.hadoopConfiguration()))
.toArray(String[]::new);
log.info("Non empty mdstores {}", validPaths.length);
if (validPaths.length > 0) {
// load the dataset
Dataset<Oaf> oaf = spark
.read()
.load(validPaths)
.as(Encoders.kryo(Oaf.class));
// dispatch each entity type individually in the respective graph subdirectory in append mode
for(Map.Entry<String, Class> e : ModelSupport.oafTypes.entrySet()) {
oaf
.filter((FilterFunction<Oaf>) o -> o.getClass().getSimpleName().toLowerCase().equals(e.getKey()))
.map((MapFunction<Oaf, String>) OBJECT_MAPPER::writeValueAsString, Encoders.bean(e.getValue()))
.write()
.option("compression", "gzip")
.mode(SaveMode.Append)
.text(outputPath + "/" + e.getKey());
}
}
}
private static Relation getInverse(Relation rel, VocabularyGroup vocs) {
final Relation inverse = new Relation();
inverse.setProperties(rel.getProperties());
inverse.setValidated(rel.getValidated());
inverse.setValidationDate(rel.getValidationDate());
inverse.setCollectedfrom(rel.getCollectedfrom());
inverse.setDataInfo(rel.getDataInfo());
inverse.setLastupdatetimestamp(rel.getLastupdatetimestamp());
inverse.setSource(rel.getTarget());
inverse.setTarget(rel.getSource());
inverse.setRelType(rel.getRelType());
inverse.setSubRelType(rel.getSubRelType());
return inverse;
}
}

26
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/MigrateHdfsMdstoresApplication.java
View File

@ -135,30 +135,4 @@ public class MigrateHdfsMdstoresApplication extends AbstractMigrationApplication
}
}
private static Set<String> mdstorePaths(final String mdstoreManagerUrl,
final String format,
final String layout,
final String interpretation) throws IOException {
final String url = mdstoreManagerUrl + "/mdstores/";
final ObjectMapper objectMapper = new ObjectMapper();
final HttpGet req = new HttpGet(url);
try (final CloseableHttpClient client = HttpClients.createDefault()) {
try (final CloseableHttpResponse response = client.execute(req)) {
final String json = IOUtils.toString(response.getEntity().getContent());
final MDStoreWithInfo[] mdstores = objectMapper.readValue(json, MDStoreWithInfo[].class);
return Arrays
.stream(mdstores)
.filter(md -> md.getFormat().equalsIgnoreCase(format))
.filter(md -> md.getLayout().equalsIgnoreCase(layout))
.filter(md -> md.getInterpretation().equalsIgnoreCase(interpretation))
.filter(md -> StringUtils.isNotBlank(md.getHdfsPath()))
.filter(md -> StringUtils.isNotBlank(md.getCurrentVersion()))
.filter(md -> md.getSize() > 0)
.map(md -> md.getHdfsPath() + "/" + md.getCurrentVersion() + "/store")
.collect(Collectors.toSet());
}
}
}
}

47
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/common/AbstractMigrationApplication.java
View File

@ -3,8 +3,14 @@ package eu.dnetlib.dhp.oa.graph.raw.common;
import java.io.Closeable;
import java.io.IOException;
import java.util.Arrays;
import java.util.Set;
import java.util.concurrent.atomic.AtomicInteger;
import java.util.stream.Collectors;
import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.conf.Configuration;
@ -16,6 +22,10 @@ import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.oaf.Oaf;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
public class AbstractMigrationApplication implements Closeable {
@ -47,6 +57,43 @@ public class AbstractMigrationApplication implements Closeable {
SequenceFile.Writer.valueClass(Text.class));
}
/**
* Retrieves from the metadata store manager application the list of paths associated with mdstores characterized
* by he given format, layout, interpretation
* @param mdstoreManagerUrl the URL of the mdstore manager service
* @param format the mdstore format
* @param layout the mdstore layout
* @param interpretation the mdstore interpretation
* @return the set of hdfs paths
* @throws IOException in case of HTTP communication issues
*/
protected static Set<String> mdstorePaths(final String mdstoreManagerUrl,
final String format,
final String layout,
final String interpretation) throws IOException {
final String url = mdstoreManagerUrl + "/mdstores/";
final ObjectMapper objectMapper = new ObjectMapper();
final HttpGet req = new HttpGet(url);
try (final CloseableHttpClient client = HttpClients.createDefault()) {
try (final CloseableHttpResponse response = client.execute(req)) {
final String json = IOUtils.toString(response.getEntity().getContent());
final MDStoreWithInfo[] mdstores = objectMapper.readValue(json, MDStoreWithInfo[].class);
return Arrays
.stream(mdstores)
.filter(md -> md.getFormat().equalsIgnoreCase(format))
.filter(md -> md.getLayout().equalsIgnoreCase(layout))
.filter(md -> md.getInterpretation().equalsIgnoreCase(interpretation))
.filter(md -> StringUtils.isNotBlank(md.getHdfsPath()))
.filter(md -> StringUtils.isNotBlank(md.getCurrentVersion()))
.filter(md -> md.getSize() > 0)
.map(md -> md.getHdfsPath() + "/" + md.getCurrentVersion() + "/store")
.collect(Collectors.toSet());
}
}
}
private Configuration getConf() {
return new Configuration();
/*

38
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/copy_hdfs_oaf_parameters.json Normal file
View File

@ -0,0 +1,38 @@
[
{
"paramName": "p",
"paramLongName": "hdfsPath",
"paramDescription": "the path where storing the sequential file",
"paramRequired": true
},
{
"paramName": "u",
"paramLongName": "mdstoreManagerUrl",
"paramDescription": "the MdstoreManager url",
"paramRequired": true
},
{
"paramName": "f",
"paramLongName": "mdFormat",
"paramDescription": "metadata format",
"paramRequired": true
},
{
"paramName": "l",
"paramLongName": "mdLayout",
"paramDescription": "metadata layout",
"paramRequired": true
},
{
"paramName": "i",
"paramLongName": "mdInterpretation",
"paramDescription": "metadata interpretation",
"paramRequired": true
},
{
"paramName": "isu",
"paramLongName": "isLookupUrl",
"paramDescription": "the url of the ISLookupService",
"paramRequired": true
}
]

27
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/raw_all/oozie_app/workflow.xml
View File

@ -544,6 +544,33 @@
<arg>--sourcePath</arg><arg>${workingDir}/entities</arg>
<arg>--graphRawPath</arg><arg>${workingDir}/graph_raw</arg>
</spark>
<ok to="Import_oaf_store_graph"/>
<error to="Kill"/>
</action>
<action name="Import_oaf_store_graph">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>ImportOAF_hdfs_graph</name>
<class>eu.dnetlib.dhp.oa.graph.raw.CopyHdfsOafApplication</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--hdfsPath</arg><arg>${workingDir}/graph_raw</arg>
<arg>--mdstoreManagerUrl</arg><arg>${mdstoreManagerUrl}</arg>
<arg>--mdFormat</arg><arg>OAF</arg>
<arg>--mdLayout</arg><arg>store</arg>
<arg>--mdInterpretation</arg><arg>graph</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
</spark>
<ok to="wait_graphs"/>
<error to="Kill"/>
</action>

177
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/sx/graph/bio/oozie_app/workflow.xml
View File

@ -1,177 +0,0 @@
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>PDBPath</name>
<description>the PDB Database Working Path</description>
</property>
<property>
<name>UNIPROTDBPath</name>
<description>the UNIPROT Database Working Path</description>
</property>
<property>
<name>EBIDataset</name>
<description>the EBI Links Dataset Path</description>
</property>
<property>
<name>ScholixResolvedDBPath</name>
<description>the Scholix Resolved Dataset Path</description>
</property>
<property>
<name>CrossrefLinksPath</name>
<description>the CrossrefLinks Path</description>
</property>
<property>
<name>targetPath</name>
<description>the Target Working dir path</description>
</property>
</parameters>
<start to="ConvertPDB"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ConvertPDB">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert PDB to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--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}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--dbPath</arg><arg>${PDBPath}</arg>
<arg>--database</arg><arg>PDB</arg>
<arg>--targetPath</arg><arg>${targetPath}/pdb_OAF</arg>
</spark>
<ok to="ConvertUNIPROT"/>
<error to="Kill"/>
</action>
<action name="ConvertUNIPROT">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert UNIPROT to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${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}${spark2EventLogDir}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--dbPath</arg><arg>${UNIPROTDBPath}</arg>
<arg>--database</arg><arg>UNIPROT</arg>
<arg>--targetPath</arg><arg>${targetPath}/uniprot_OAF</arg>
</spark>
<ok to="ConvertEBILinks"/>
<error to="Kill"/>
</action>
<action name="ConvertEBILinks">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert EBI Links to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.graph.ebi.SparkEBILinksToOaf</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--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}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--sourcePath</arg><arg>${EBIDataset}</arg>
<arg>--targetPath</arg><arg>${targetPath}/ebi_OAF</arg>
</spark>
<ok to="ConvertScholixResolved"/>
<error to="Kill"/>
</action>
<action name="ConvertScholixResolved">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert Scholix to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${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}${spark2EventLogDir}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--dbPath</arg><arg>${ScholixResolvedDBPath}</arg>
<arg>--database</arg><arg>SCHOLIX</arg>
<arg>--targetPath</arg><arg>${targetPath}/scholix_resolved_OAF</arg>
</spark>
<ok to="ConvertCrossrefLinks"/>
<error to="Kill"/>
</action>
<action name="ConvertCrossrefLinks">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert Crossref Links to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.graph.bio.SparkTransformBioDatabaseToOAF</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--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}
</spark-opts>
<arg>--master</arg><arg>yarn</arg>
<arg>--dbPath</arg><arg>${CrossrefLinksPath}</arg>
<arg>--database</arg><arg>CROSSREF_LINKS</arg>
<arg>--targetPath</arg><arg>${targetPath}/crossref_unresolved_relation_OAF</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

10
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/SolrConfigExploreTest.java
View File

@ -74,7 +74,6 @@ public class SolrConfigExploreTest extends SolrExploreTest {
.config(conf)
.getOrCreate();
}
@AfterAll
@ -87,7 +86,8 @@ public class SolrConfigExploreTest extends SolrExploreTest {
String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null).run(isLookupClient);
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null)
.run(isLookupClient);
Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
String[] queryStrings = {
@ -108,7 +108,8 @@ public class SolrConfigExploreTest extends SolrExploreTest {
// System.out.println(rsp.getExplainMap());
for (SolrDocument doc : rsp.getResults()) {
System.out.println(
System.out
.println(
doc.get("score") + "\t" +
doc.get("__indexrecordidentifier") + "\t" +
doc.get("resultidentifier") + "\t" +
@ -118,8 +119,7 @@ public class SolrConfigExploreTest extends SolrExploreTest {
doc.get("resulttitle") + "\t" +
doc.get("relprojectname") + "\t" +
doc.get("resultdescription") + "\t" +
doc.get("__all") + "\t"
);
doc.get("__all") + "\t");
}
}
}

10
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/SolrConfigTest.java
View File

@ -83,7 +83,6 @@ public class SolrConfigTest extends SolrTest {
.config(conf)
.getOrCreate();
}
@AfterAll
@ -96,7 +95,8 @@ public class SolrConfigTest extends SolrTest {
String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null).run(isLookupClient);
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null)
.run(isLookupClient);
Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
String[] queryStrings = {
@ -113,7 +113,8 @@ public class SolrConfigTest extends SolrTest {
QueryResponse rsp = miniCluster.getSolrClient().query(query);
for (SolrDocument doc : rsp.getResults()) {
System.out.println(
System.out
.println(
doc.get("score") + "\t" +
doc.get("__indexrecordidentifier") + "\t" +
doc.get("resultidentifier") + "\t" +
@ -123,8 +124,7 @@ public class SolrConfigTest extends SolrTest {
doc.get("resulttitle") + "\t" +
doc.get("relprojectname") + "\t" +
doc.get("resultdescription") + "\t" +
doc.get("__all") + "\t"
);
doc.get("__all") + "\t");
}
}
}

2
pom.xml
View File

@ -753,7 +753,7 @@
<mockito-core.version>3.3.3</mockito-core.version>
<mongodb.driver.version>3.4.2</mongodb.driver.version>
<vtd.version>[2.12,3.0)</vtd.version>
<dhp-schemas.version>[2.8.20]</dhp-schemas.version>
<dhp-schemas.version>[2.8.21]</dhp-schemas.version>
<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>