D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 12 Projects 2 Releases 2 Wiki Activity

Merge branch 'beta' of https://code-repo.d4science.org/D-Net/dnet-hadoop into beta

This commit is contained in:
Claudio Atzori 2021-10-19 16:09:54 +02:00
parent 7a73010acd c9870c5122
commit c8850456e9
22 changed files with 294 additions and 418 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());

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>

154
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/SolrConfigExploreTest.java
View File

@ -25,102 +25,102 @@ import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
@ExtendWith(MockitoExtension.class)
public class SolrConfigExploreTest extends SolrExploreTest {
protected static SparkSession spark;
protected static SparkSession spark;
private static final Integer batchSize = 100;
private static final Integer batchSize = 100;
@Mock
private ISLookUpService isLookUpService;
@Mock
private ISLookUpService isLookUpService;
@Mock
private ISLookupClient isLookupClient;
@Mock
private ISLookupClient isLookupClient;
@BeforeEach
public void prepareMocks() throws ISLookUpException, IOException {
isLookupClient.setIsLookup(isLookUpService);
@BeforeEach
public void prepareMocks() throws ISLookUpException, IOException {
isLookupClient.setIsLookup(isLookUpService);
int solrPort = URI.create("http://" + miniCluster.getZkClient().getZkServerAddress()).getPort();
int solrPort = URI.create("http://" + miniCluster.getZkClient().getZkServerAddress()).getPort();
Mockito
.when(isLookupClient.getDsId(Mockito.anyString()))
.thenReturn("313f0381-23b6-466f-a0b8-c72a9679ac4b_SW5kZXhEU1Jlc291cmNlcy9JbmRleERTUmVzb3VyY2VUeXBl");
Mockito.when(isLookupClient.getZkHost()).thenReturn(String.format("127.0.0.1:%s/solr", solrPort));
Mockito
.when(isLookupClient.getLayoutSource(Mockito.anyString()))
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("fields.xml")));
Mockito
.when(isLookupClient.getLayoutTransformer())
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("layoutToRecordTransformer.xsl")));
}
Mockito
.when(isLookupClient.getDsId(Mockito.anyString()))
.thenReturn("313f0381-23b6-466f-a0b8-c72a9679ac4b_SW5kZXhEU1Jlc291cmNlcy9JbmRleERTUmVzb3VyY2VUeXBl");
Mockito.when(isLookupClient.getZkHost()).thenReturn(String.format("127.0.0.1:%s/solr", solrPort));
Mockito
.when(isLookupClient.getLayoutSource(Mockito.anyString()))
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("fields.xml")));
Mockito
.when(isLookupClient.getLayoutTransformer())
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("layoutToRecordTransformer.xsl")));
}
@BeforeAll
public static void before() {
@BeforeAll
public static void before() {
SparkConf conf = new SparkConf();
conf.setAppName(XmlIndexingJobTest.class.getSimpleName());
conf.registerKryoClasses(new Class[] {
SerializableSolrInputDocument.class
});
SparkConf conf = new SparkConf();
conf.setAppName(XmlIndexingJobTest.class.getSimpleName());
conf.registerKryoClasses(new Class[] {
SerializableSolrInputDocument.class
});
conf.setMaster("local[1]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.resolve("spark").toString());
conf.setMaster("local[1]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.resolve("spark").toString());
spark = SparkSession
.builder()
.appName(XmlIndexingJobTest.class.getSimpleName())
.config(conf)
.getOrCreate();
spark = SparkSession
.builder()
.appName(XmlIndexingJobTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
}
@AfterAll
public static void tearDown() {
spark.stop();
}
@AfterAll
public static void tearDown() {
spark.stop();
}
@Test
public void testSolrConfig() throws Exception {
@Test
public void testSolrConfig() throws Exception {
String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null)
.run(isLookupClient);
Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null).run(isLookupClient);
Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
String[] queryStrings = {
"cancer",
"graph",
"graphs"
};
String[] queryStrings = {
"cancer",
"graph",
"graphs"
};
for (String q : queryStrings) {
SolrQuery query = new SolrQuery();
query.setRequestHandler("/exploreSearch");
query.add(CommonParams.Q, q);
query.set("debugQuery", "on");
for (String q : queryStrings) {
SolrQuery query = new SolrQuery();
query.setRequestHandler("/exploreSearch");
query.add(CommonParams.Q, q);
query.set("debugQuery", "on");
log.info("Submit query to Solr with params: {}", query.toString());
QueryResponse rsp = miniCluster.getSolrClient().query(query);
log.info("Submit query to Solr with params: {}", query.toString());
QueryResponse rsp = miniCluster.getSolrClient().query(query);
// System.out.println(rsp.getHighlighting());
// System.out.println(rsp.getExplainMap());
for (SolrDocument doc : rsp.getResults()) {
System.out.println(
doc.get("score") + "\t" +
doc.get("__indexrecordidentifier") + "\t" +
doc.get("resultidentifier") + "\t" +
doc.get("resultauthor") + "\t" +
doc.get("resultacceptanceyear") + "\t" +
doc.get("resultsubject") + "\t" +
doc.get("resulttitle") + "\t" +
doc.get("relprojectname") + "\t" +
doc.get("resultdescription") + "\t" +
doc.get("__all") + "\t"
);
}
}
}
for (SolrDocument doc : rsp.getResults()) {
System.out
.println(
doc.get("score") + "\t" +
doc.get("__indexrecordidentifier") + "\t" +
doc.get("resultidentifier") + "\t" +
doc.get("resultauthor") + "\t" +
doc.get("resultacceptanceyear") + "\t" +
doc.get("resultsubject") + "\t" +
doc.get("resulttitle") + "\t" +
doc.get("relprojectname") + "\t" +
doc.get("resultdescription") + "\t" +
doc.get("__all") + "\t");
}
}
}
}

150
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/SolrConfigTest.java
View File

@ -34,98 +34,98 @@ import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
@ExtendWith(MockitoExtension.class)
public class SolrConfigTest extends SolrTest {
protected static SparkSession spark;
protected static SparkSession spark;
private static final Integer batchSize = 100;
private static final Integer batchSize = 100;
@Mock
private ISLookUpService isLookUpService;
@Mock
private ISLookUpService isLookUpService;
@Mock
private ISLookupClient isLookupClient;
@Mock
private ISLookupClient isLookupClient;
@BeforeEach
public void prepareMocks() throws ISLookUpException, IOException {
isLookupClient.setIsLookup(isLookUpService);
@BeforeEach
public void prepareMocks() throws ISLookUpException, IOException {
isLookupClient.setIsLookup(isLookUpService);
int solrPort = URI.create("http://" + miniCluster.getZkClient().getZkServerAddress()).getPort();
int solrPort = URI.create("http://" + miniCluster.getZkClient().getZkServerAddress()).getPort();
Mockito
.when(isLookupClient.getDsId(Mockito.anyString()))
.thenReturn("313f0381-23b6-466f-a0b8-c72a9679ac4b_SW5kZXhEU1Jlc291cmNlcy9JbmRleERTUmVzb3VyY2VUeXBl");
Mockito.when(isLookupClient.getZkHost()).thenReturn(String.format("127.0.0.1:%s/solr", solrPort));
Mockito
.when(isLookupClient.getLayoutSource(Mockito.anyString()))
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("fields.xml")));
Mockito
.when(isLookupClient.getLayoutTransformer())
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("layoutToRecordTransformer.xsl")));
}
Mockito
.when(isLookupClient.getDsId(Mockito.anyString()))
.thenReturn("313f0381-23b6-466f-a0b8-c72a9679ac4b_SW5kZXhEU1Jlc291cmNlcy9JbmRleERTUmVzb3VyY2VUeXBl");
Mockito.when(isLookupClient.getZkHost()).thenReturn(String.format("127.0.0.1:%s/solr", solrPort));
Mockito
.when(isLookupClient.getLayoutSource(Mockito.anyString()))
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("fields.xml")));
Mockito
.when(isLookupClient.getLayoutTransformer())
.thenReturn(IOUtils.toString(getClass().getResourceAsStream("layoutToRecordTransformer.xsl")));
}
@BeforeAll
public static void before() {
@BeforeAll
public static void before() {
SparkConf conf = new SparkConf();
conf.setAppName(XmlIndexingJobTest.class.getSimpleName());
conf.registerKryoClasses(new Class[] {
SerializableSolrInputDocument.class
});
SparkConf conf = new SparkConf();
conf.setAppName(XmlIndexingJobTest.class.getSimpleName());
conf.registerKryoClasses(new Class[] {
SerializableSolrInputDocument.class
});
conf.setMaster("local[1]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.resolve("spark").toString());
conf.setMaster("local[1]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.resolve("spark").toString());
spark = SparkSession
.builder()
.appName(XmlIndexingJobTest.class.getSimpleName())
.config(conf)
.getOrCreate();
spark = SparkSession
.builder()
.appName(XmlIndexingJobTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
}
@AfterAll
public static void tearDown() {
spark.stop();
}
@AfterAll
public static void tearDown() {
spark.stop();
}
@Test
public void testSolrConfig() throws Exception {
@Test
public void testSolrConfig() throws Exception {
String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
String inputPath = "src/test/resources/eu/dnetlib/dhp/oa/provision/xml";
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null)
.run(isLookupClient);
Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
new XmlIndexingJob(spark, inputPath, FORMAT, batchSize, XmlIndexingJob.OutputFormat.SOLR, null).run(isLookupClient);
Assertions.assertEquals(0, miniCluster.getSolrClient().commit().getStatus());
String[] queryStrings = {
"cancer",
"graph",
"graphs"
};
String[] queryStrings = {
"cancer",
"graph",
"graphs"
};
for (String q : queryStrings) {
SolrQuery query = new SolrQuery();
query.add(CommonParams.Q, q);
for (String q : queryStrings) {
SolrQuery query = new SolrQuery();
query.add(CommonParams.Q, q);
log.info("Submit query to Solr with params: {}", query.toString());
QueryResponse rsp = miniCluster.getSolrClient().query(query);
log.info("Submit query to Solr with params: {}", query.toString());
QueryResponse rsp = miniCluster.getSolrClient().query(query);
for (SolrDocument doc : rsp.getResults()) {
System.out.println(
doc.get("score") + "\t" +
doc.get("__indexrecordidentifier") + "\t" +
doc.get("resultidentifier") + "\t" +
doc.get("resultauthor") + "\t" +
doc.get("resultacceptanceyear") + "\t" +
doc.get("resultsubject") + "\t" +
doc.get("resulttitle") + "\t" +
doc.get("relprojectname") + "\t" +
doc.get("resultdescription") + "\t" +
doc.get("__all") + "\t"
);
}
}
}
for (SolrDocument doc : rsp.getResults()) {
System.out
.println(
doc.get("score") + "\t" +
doc.get("__indexrecordidentifier") + "\t" +
doc.get("resultidentifier") + "\t" +
doc.get("resultauthor") + "\t" +
doc.get("resultacceptanceyear") + "\t" +
doc.get("resultsubject") + "\t" +
doc.get("resulttitle") + "\t" +
doc.get("relprojectname") + "\t" +
doc.get("resultdescription") + "\t" +
doc.get("__all") + "\t");
}
}
}
}

128
dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/SolrExploreTest.java
View File

@ -23,87 +23,87 @@ import org.slf4j.LoggerFactory;
public abstract class SolrExploreTest {
protected static final Logger log = LoggerFactory.getLogger(SolrTest.class);
protected static final Logger log = LoggerFactory.getLogger(SolrTest.class);
protected static final String FORMAT = "test";
protected static final String DEFAULT_COLLECTION = FORMAT + "-index-openaire";
protected static final String CONFIG_NAME = "testConfig";
protected static final String FORMAT = "test";
protected static final String DEFAULT_COLLECTION = FORMAT + "-index-openaire";
protected static final String CONFIG_NAME = "testConfig";
protected static MiniSolrCloudCluster miniCluster;
protected static MiniSolrCloudCluster miniCluster;
@TempDir
public static Path workingDir;
@TempDir
public static Path workingDir;
@BeforeAll
public static void setup() throws Exception {
@BeforeAll
public static void setup() throws Exception {
// random unassigned HTTP port
final int jettyPort = 0;
final JettyConfig jettyConfig = JettyConfig.builder().setPort(jettyPort).build();
// random unassigned HTTP port
final int jettyPort = 0;
final JettyConfig jettyConfig = JettyConfig.builder().setPort(jettyPort).build();
log.info(String.format("working directory: %s", workingDir.toString()));
System.setProperty("solr.log.dir", workingDir.resolve("logs").toString());
log.info(String.format("working directory: %s", workingDir.toString()));
System.setProperty("solr.log.dir", workingDir.resolve("logs").toString());
// create a MiniSolrCloudCluster instance
miniCluster = new MiniSolrCloudCluster(2, workingDir.resolve("solr"), jettyConfig);
// create a MiniSolrCloudCluster instance
miniCluster = new MiniSolrCloudCluster(2, workingDir.resolve("solr"), jettyConfig);
// Upload Solr configuration directory to ZooKeeper
String solrZKConfigDir = "src/test/resources/eu/dnetlib/dhp/oa/provision/solr/conf/exploreTestConfig";
File configDir = new File(solrZKConfigDir);
// Upload Solr configuration directory to ZooKeeper
String solrZKConfigDir = "src/test/resources/eu/dnetlib/dhp/oa/provision/solr/conf/exploreTestConfig";
File configDir = new File(solrZKConfigDir);
miniCluster.uploadConfigSet(configDir.toPath(), CONFIG_NAME);
miniCluster.uploadConfigSet(configDir.toPath(), CONFIG_NAME);
// override settings in the solrconfig include
System.setProperty("solr.tests.maxBufferedDocs", "100000");
System.setProperty("solr.tests.maxIndexingThreads", "-1");
System.setProperty("solr.tests.ramBufferSizeMB", "100");
// override settings in the solrconfig include
System.setProperty("solr.tests.maxBufferedDocs", "100000");
System.setProperty("solr.tests.maxIndexingThreads", "-1");
System.setProperty("solr.tests.ramBufferSizeMB", "100");
// use non-test classes so RandomizedRunner isn't necessary
System.setProperty("solr.tests.mergeScheduler", "org.apache.lucene.index.ConcurrentMergeScheduler");
System.setProperty("solr.directoryFactory", "solr.RAMDirectoryFactory");
System.setProperty("solr.lock.type", "single");
// use non-test classes so RandomizedRunner isn't necessary
System.setProperty("solr.tests.mergeScheduler", "org.apache.lucene.index.ConcurrentMergeScheduler");
System.setProperty("solr.directoryFactory", "solr.RAMDirectoryFactory");
System.setProperty("solr.lock.type", "single");
log.info(new ConfigSetAdminRequest.List().process(miniCluster.getSolrClient()).toString());
log
.info(
CollectionAdminRequest.ClusterStatus
.getClusterStatus()
.process(miniCluster.getSolrClient())
.toString());
log.info(new ConfigSetAdminRequest.List().process(miniCluster.getSolrClient()).toString());
log
.info(
CollectionAdminRequest.ClusterStatus
.getClusterStatus()
.process(miniCluster.getSolrClient())
.toString());
NamedList<Object> res = createCollection(
miniCluster.getSolrClient(), DEFAULT_COLLECTION, 4, 2, 20, CONFIG_NAME);
res.forEach(o -> log.info(o.toString()));
NamedList<Object> res = createCollection(
miniCluster.getSolrClient(), DEFAULT_COLLECTION, 4, 2, 20, CONFIG_NAME);
res.forEach(o -> log.info(o.toString()));
miniCluster.getSolrClient().setDefaultCollection(DEFAULT_COLLECTION);
miniCluster.getSolrClient().setDefaultCollection(DEFAULT_COLLECTION);
log
.info(
CollectionAdminRequest.ClusterStatus
.getClusterStatus()
.process(miniCluster.getSolrClient())
.toString());
log
.info(
CollectionAdminRequest.ClusterStatus
.getClusterStatus()
.process(miniCluster.getSolrClient())
.toString());
}
}
@AfterAll
public static void shutDown() throws Exception {
miniCluster.shutdown();
FileUtils.deleteDirectory(workingDir.toFile());
}
@AfterAll
public static void shutDown() throws Exception {
miniCluster.shutdown();
FileUtils.deleteDirectory(workingDir.toFile());
}
protected static NamedList<Object> createCollection(CloudSolrClient client, String name, int numShards,
int replicationFactor, int maxShardsPerNode, String configName) throws Exception {
ModifiableSolrParams modParams = new ModifiableSolrParams();
modParams.set(CoreAdminParams.ACTION, CollectionParams.CollectionAction.CREATE.name());
modParams.set("name", name);
modParams.set("numShards", numShards);
modParams.set("replicationFactor", replicationFactor);
modParams.set("collection.configName", configName);
modParams.set("maxShardsPerNode", maxShardsPerNode);
QueryRequest request = new QueryRequest(modParams);
request.setPath("/admin/collections");
return client.request(request);
}
protected static NamedList<Object> createCollection(CloudSolrClient client, String name, int numShards,
int replicationFactor, int maxShardsPerNode, String configName) throws Exception {
ModifiableSolrParams modParams = new ModifiableSolrParams();
modParams.set(CoreAdminParams.ACTION, CollectionParams.CollectionAction.CREATE.name());
modParams.set("name", name);
modParams.set("numShards", numShards);
modParams.set("replicationFactor", replicationFactor);
modParams.set("collection.configName", configName);
modParams.set("maxShardsPerNode", maxShardsPerNode);
QueryRequest request = new QueryRequest(modParams);
request.setPath("/admin/collections");
return client.request(request);
}
}

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>