Merge pull request 'enrichmentSingleStep' (#373) from enrichmentSingleStep into beta

Reviewed-on: D-Net/dnet-hadoop#373
This commit is contained in:
Claudio Atzori 2024-01-10 16:58:49 +01:00
commit 16d858fbf0
74 changed files with 894 additions and 944 deletions

View File

@ -167,4 +167,11 @@ public class Utils implements Serializable {
});
return projectMap;
}
public static List<String> getCommunityIdList(String baseURL) throws IOException {
return getValidCommunities(baseURL)
.stream()
.map(community -> community.getId())
.collect(Collectors.toList());
}
}

View File

@ -45,7 +45,7 @@ public class SparkBulkTagJob {
.toString(
SparkBulkTagJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
@ -105,7 +105,6 @@ public class SparkBulkTagJob {
Map<String, List<Pair<String, SelectionConstraints>>> dsm = cc.getEoscDatasourceMap();
for (String ds : datasources.collectAsList()) {
// final String dsId = ds.substring(3);
if (!dsm.containsKey(ds)) {
ArrayList<Pair<String, SelectionConstraints>> eoscList = new ArrayList<>();
dsm.put(ds, eoscList);
@ -116,13 +115,11 @@ public class SparkBulkTagJob {
private static boolean isOKDatasource(Datasource ds) {
final String compatibility = ds.getOpenairecompatibility().getClassid();
boolean isOk = (compatibility.equalsIgnoreCase(OPENAIRE_3) ||
return (compatibility.equalsIgnoreCase(OPENAIRE_3) ||
compatibility.equalsIgnoreCase(OPENAIRE_4) ||
compatibility.equalsIgnoreCase(OPENAIRE_CRIS) ||
compatibility.equalsIgnoreCase(OPENAIRE_DATA)) &&
ds.getCollectedfrom().stream().anyMatch(cf -> cf.getKey().equals(EOSC));
return isOk;
}
private static <R extends Result> void execBulkTag(
@ -151,7 +148,13 @@ public class SparkBulkTagJob {
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
.json(outputPath + e.name());// writing the tagging in the working dir for entity
readPath(spark, outputPath + e.name(), resultClazz) // copy the tagging in the actual result output path
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + e.name());
});
}

View File

@ -45,7 +45,7 @@ public class PrepareDatasourceCountryAssociation {
.toString(
PrepareDatasourceCountryAssociation.class
.getResourceAsStream(
"/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -66,7 +66,7 @@ public class PrepareDatasourceCountryAssociation {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
// removeOutputDir(spark, outputPath);
prepareDatasourceCountryAssociation(
spark,
Arrays.asList(parser.get("whitelist").split(";")),
@ -90,7 +90,8 @@ public class PrepareDatasourceCountryAssociation {
(FilterFunction<Datasource>) ds -> !ds.getDataInfo().getDeletedbyinference() &&
Optional.ofNullable(ds.getDatasourcetype()).isPresent() &&
Optional.ofNullable(ds.getDatasourcetype().getClassid()).isPresent() &&
(allowedtypes.contains(ds.getDatasourcetype().getClassid()) ||
((Optional.ofNullable(ds.getJurisdiction()).isPresent() &&
allowedtypes.contains(ds.getJurisdiction().getClassid())) ||
whitelist.contains(ds.getId())));
// filtering of the relations taking the non deleted by inference and those with IsProvidedBy as relclass

View File

@ -32,7 +32,7 @@ public class PrepareResultCountrySet {
.toString(
PrepareResultCountrySet.class
.getResourceAsStream(
"/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -35,7 +35,7 @@ public class SparkCountryPropagationJob {
.toString(
SparkCountryPropagationJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -97,6 +97,12 @@ public class SparkCountryPropagationJob {
.mode(SaveMode.Overwrite)
.json(outputPath);
readPath(spark, outputPath, resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(sourcePath);
}
private static <R extends Result> MapFunction<Tuple2<R, ResultCountrySet>, R> getCountryMergeFn() {

View File

@ -60,7 +60,7 @@ public class PrepareInfo implements Serializable {
.toString(
SparkResultToOrganizationFromIstRepoJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json"));
"/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -27,8 +27,8 @@ import eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganization
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation;
public class SparkResultToOrganizationFromSemRel implements Serializable {
private static final Logger log = LoggerFactory.getLogger(SparkResultToOrganizationFromSemRel.class);
public class SparkEntityToOrganizationFromSemRel implements Serializable {
private static final Logger log = LoggerFactory.getLogger(SparkEntityToOrganizationFromSemRel.class);
private static final int MAX_ITERATION = 5;
public static final String NEW_RESULT_RELATION_PATH = "/newResultRelation";
public static final String NEW_PROJECT_RELATION_PATH = "/newProjectRelation";
@ -39,7 +39,7 @@ public class SparkResultToOrganizationFromSemRel implements Serializable {
.toString(
SparkResultToOrganizationFromIstRepoJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json"));
"/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -3,8 +3,8 @@ package eu.dnetlib.dhp.entitytoorganizationfromsemrel;
import static eu.dnetlib.dhp.PropagationConstant.*;
import static eu.dnetlib.dhp.PropagationConstant.readPath;
import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel.NEW_PROJECT_RELATION_PATH;
import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel.NEW_RESULT_RELATION_PATH;
import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel.NEW_PROJECT_RELATION_PATH;
import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel.NEW_RESULT_RELATION_PATH;
import java.io.Serializable;
import java.util.*;
@ -20,7 +20,6 @@ import org.jetbrains.annotations.NotNull;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.KeyValueSet;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation;
import scala.Tuple2;

View File

@ -31,7 +31,7 @@ public class PrepareResultOrcidAssociationStep1 {
.toString(
PrepareResultOrcidAssociationStep1.class
.getResourceAsStream(
"/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConf);
parser.parseArgument(args);

View File

@ -29,7 +29,7 @@ public class PrepareResultOrcidAssociationStep2 {
.toString(
PrepareResultOrcidAssociationStep2.class
.getResourceAsStream(
"/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json"));
"/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -2,7 +2,7 @@
package eu.dnetlib.dhp.orcidtoresultfromsemrel;
import static eu.dnetlib.dhp.PropagationConstant.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.List;
import java.util.Optional;
@ -36,7 +36,7 @@ public class SparkOrcidToResultFromSemRelJob {
.toString(
SparkOrcidToResultFromSemRelJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
@ -65,9 +65,8 @@ public class SparkOrcidToResultFromSemRelJob {
Class<? extends Result> resultClazz = (Class<? extends Result>) Class.forName(resultClassName);
SparkConf conf = new SparkConf();
conf.set("hive.metastore.uris", parser.get("hive_metastore_uris"));
runWithSparkHiveSession(
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {

View File

@ -28,7 +28,7 @@ public class PrepareProjectResultsAssociation {
.toString(
PrepareProjectResultsAssociation.class
.getResourceAsStream(
"/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -33,7 +33,7 @@ public class SparkResultToProjectThroughSemRelJob {
.toString(
SparkResultToProjectThroughSemRelJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -34,7 +34,7 @@ public class PrepareResultCommunitySet {
.toString(
PrepareResultCommunitySet.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);

View File

@ -36,7 +36,7 @@ public class SparkResultToCommunityFromOrganizationJob {
.toString(
SparkResultToCommunityFromOrganizationJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -92,6 +92,12 @@ public class SparkResultToCommunityFromOrganizationJob {
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
readPath(spark, outputPath + e.name(), resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + e.name());
}
});

View File

@ -38,7 +38,7 @@ public class PrepareResultCommunitySet {
.toString(
PrepareResultCommunitySet.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);

View File

@ -44,7 +44,7 @@ public class SparkResultToCommunityFromProject implements Serializable {
.toString(
SparkResultToCommunityFromProject.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -102,6 +102,12 @@ public class SparkResultToCommunityFromProject implements Serializable {
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
readPath(spark, outputPath + e.name(), resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + e.name());
}
});

View File

@ -4,6 +4,7 @@ package eu.dnetlib.dhp.resulttocommunityfromsemrel;
import static eu.dnetlib.dhp.PropagationConstant.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
import java.io.IOException;
import java.util.Arrays;
import java.util.List;
@ -15,6 +16,7 @@ import org.slf4j.LoggerFactory;
import com.google.gson.Gson;
import eu.dnetlib.dhp.api.Utils;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.resulttocommunityfromorganization.ResultCommunityList;
import eu.dnetlib.dhp.schema.oaf.Relation;
@ -26,11 +28,6 @@ import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
public class PrepareResultCommunitySetStep1 {
private static final Logger log = LoggerFactory.getLogger(PrepareResultCommunitySetStep1.class);
private static final String COMMUNITY_LIST_XQUERY = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType')"
+ " where $x//CONFIGURATION/context[./@type='community' or ./@type='ri']"
+ " and $x//CONFIGURATION/context/param[./@name='status']/text() != 'hidden'"
+ " return $x//CONFIGURATION/context/@id/string()";
/**
* associates to each result the set of community contexts they are associated to; associates to each target of a
* relation with allowed semantics the set of community context it could possibly inherit from the source of the
@ -64,7 +61,7 @@ public class PrepareResultCommunitySetStep1 {
.toString(
PrepareResultCommunitySetStep1.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -88,10 +85,10 @@ public class PrepareResultCommunitySetStep1 {
final List<String> allowedsemrel = Arrays.asList(parser.get("allowedsemrels").split(";"));
log.info("allowedSemRel: {}", new Gson().toJson(allowedsemrel));
final String isLookupUrl = parser.get("isLookUpUrl");
log.info("isLookupUrl: {}", isLookupUrl);
final String baseURL = parser.get("baseURL");
log.info("baseURL: {}", baseURL);
final List<String> communityIdList = getCommunityList(isLookupUrl);
final List<String> communityIdList = getCommunityList(baseURL);
log.info("communityIdList: {}", new Gson().toJson(communityIdList));
final String resultType = resultClassName.substring(resultClassName.lastIndexOf(".") + 1).toLowerCase();
@ -159,9 +156,8 @@ public class PrepareResultCommunitySetStep1 {
.json(outputResultPath);
}
public static List<String> getCommunityList(final String isLookupUrl) throws ISLookUpException {
ISLookUpService isLookUp = ISLookupClientFactory.getLookUpService(isLookupUrl);
return isLookUp.quickSearchProfile(COMMUNITY_LIST_XQUERY);
public static List<String> getCommunityList(final String baseURL) throws IOException {
return Utils.getCommunityIdList(baseURL);
}
}

View File

@ -31,7 +31,7 @@ public class PrepareResultCommunitySetStep2 {
.toString(
PrepareResultCommunitySetStep2.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);

View File

@ -33,7 +33,7 @@ public class SparkResultToCommunityThroughSemRelJob {
.toString(
SparkResultToCommunityThroughSemRelJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -100,6 +100,12 @@ public class SparkResultToCommunityThroughSemRelJob {
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
readPath(spark, outputPath, resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath);
}
private static <R extends Result> MapFunction<Tuple2<R, ResultCommunityList>, R> contextUpdaterFn() {

View File

@ -0,0 +1,68 @@
package eu.dnetlib.dhp.resulttoorganizationfrominstrepo;
import static eu.dnetlib.dhp.PropagationConstant.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Relation;
/**
* @author miriam.baglioni
* @Date 09/12/23
*/
public class AppendNewRelations implements Serializable {
private static final Logger log = LoggerFactory.getLogger(AppendNewRelations.class);
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
AppendNewRelations.class
.getResourceAsStream(
"/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> appendNewRelation(spark, inputPath, outputPath));
}
private static void appendNewRelation(SparkSession spark, String inputPath, String outputPath) {
readPath(spark, inputPath + "publication/relation", Relation.class)
.union(readPath(spark, inputPath + "dataset/relation", Relation.class))
.union(readPath(spark, inputPath + "otherresearchproduct/relation", Relation.class))
.union(readPath(spark, inputPath + "software/relation", Relation.class))
.write()
.mode(SaveMode.Append)
.option("compression", "gzip")
.json(outputPath);
}
}

View File

@ -40,7 +40,7 @@ public class PrepareResultInstRepoAssociation {
.toString(
PrepareResultInstRepoAssociation.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -52,10 +52,13 @@ public class PrepareResultInstRepoAssociation {
String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String datasourceOrganizationPath = parser.get("datasourceOrganizationPath");
final String workingPath = parser.get("workingPath");
log.info("workingPath : {}", workingPath);
final String datasourceOrganizationPath = workingPath + "/preparedInfo/datasourceOrganization";
log.info("datasourceOrganizationPath {}: ", datasourceOrganizationPath);
final String alreadyLinkedPath = parser.get("alreadyLinkedPath");
final String alreadyLinkedPath = workingPath + "/preparedInfo/alreadyLinked";
log.info("alreadyLinkedPath {}: ", alreadyLinkedPath);
List<String> blacklist = Optional

View File

@ -47,7 +47,7 @@ public class SparkResultToOrganizationFromIstRepoJob {
.toString(
SparkResultToOrganizationFromIstRepoJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json"));
"/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
@ -119,7 +119,7 @@ public class SparkResultToOrganizationFromIstRepoJob {
"left_outer")
.flatMap(createRelationFn(), Encoders.bean(Relation.class))
.write()
.mode(SaveMode.Append)
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
}

View File

@ -1,32 +0,0 @@
[
{
"paramName": "p",
"paramLongName": "hdfsPath",
"paramDescription": "the path where storing the sequential file",
"paramRequired": true
},
{
"paramName": "nn",
"paramLongName": "hdfsNameNode",
"paramDescription": "the name node on hdfs",
"paramRequired": true
},
{
"paramName": "pgurl",
"paramLongName": "postgresUrl",
"paramDescription": "postgres url, example: jdbc:postgresql://localhost:5432/testdb",
"paramRequired": true
},
{
"paramName": "pguser",
"paramLongName": "postgresUser",
"paramDescription": "postgres user",
"paramRequired": false
},
{
"paramName": "pgpasswd",
"paramLongName": "postgresPassword",
"paramDescription": "postgres password",
"paramRequired": false
}
]

View File

@ -1,21 +0,0 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "wp",
"paramLongName": "workingPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
}
]

View File

@ -1,41 +0,0 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "dmp",
"paramLongName":"datasourceMapPath",
"paramDescription": "the path where the association datasource master has been stored",
"paramRequired": true
},
{
"paramName":"tn",
"paramLongName":"resultTableName",
"paramDescription": "the name of the result table we are currently working on",
"paramRequired": true
},
{
"paramName": "wp",
"paramLongName": "workingPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
},
{
"paramName": "rt",
"paramLongName": "resultType",
"paramDescription": "the result type",
"paramRequired": true
}
]

View File

@ -1,197 +0,0 @@
<workflow-app name="affiliation_from_semrel_propagation" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>outputPath</name>
<description>sets the outputPath</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="resume_from"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<decision name="resume_from">
<switch>
<case to="prepare_info">${wf:conf('resumeFrom') eq 'PrepareInfo'}</case>
<default to="reset_outputpath"/> <!-- first action to be done when downloadDump is to be performed -->
</switch>
</decision>
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
</fs>
<ok to="copy_entities"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_publication"/>
<path start="copy_dataset"/>
<path start="copy_orp"/>
<path start="copy_software"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_publication">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/publication</arg>
<arg>${nameNode}/${outputPath}/publication</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_dataset">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/dataset</arg>
<arg>${nameNode}/${outputPath}/dataset</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_orp">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/otherresearchproduct</arg>
<arg>${nameNode}/${outputPath}/otherresearchproduct</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_software">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/software</arg>
<arg>${nameNode}/${outputPath}/software</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<join name="wait" to="prepare_info"/>
<action name="prepare_info">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>PrepareResultOrganizationAssociation</name>
<class>eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--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>--graphPath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--leavesPath</arg><arg>${workingDir}/preparedInfo/leavesPath</arg>
<arg>--childParentPath</arg><arg>${workingDir}/preparedInfo/childParentPath</arg>
<arg>--resultOrgPath</arg><arg>${workingDir}/preparedInfo/resultOrgPath</arg>
<arg>--projectOrganizationPath</arg><arg>${workingDir}/preparedInfo/projectOrganizationPath</arg>
<arg>--relationPath</arg><arg>${workingDir}/preparedInfo/relation</arg>
</spark>
<ok to="apply_resulttoorganization_propagation"/>
<error to="Kill"/>
</action>
<action name="apply_resulttoorganization_propagation">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>resultToOrganizationFromSemRel</name>
<class>eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--relationPath</arg><arg>${workingDir}/preparedInfo/relation</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--leavesPath</arg><arg>${workingDir}/preparedInfo/leavesPath</arg>
<arg>--childParentPath</arg><arg>${workingDir}/preparedInfo/childParentPath</arg>
<arg>--resultOrgPath</arg><arg>${workingDir}/preparedInfo/resultOrgPath</arg>
<arg>--projectOrganizationPath</arg><arg>${workingDir}/preparedInfo/projectOrganizationPath</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--workingDir</arg><arg>${workingDir}/working</arg>
<arg>--iterations</arg><arg>${iterations}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -0,0 +1,28 @@
sourcePath=/tmp/beta_provision/graph/09_graph_dedup_enriched
resumeFrom=CountryPropagation
allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo
allowedsemrelsresultproject=isSupplementedBy;isSupplementTo
allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo
datasourceWhitelistForCountryPropagation=10|opendoar____::16e6a3326dd7d868cbc926602a61e4d0;10|openaire____::fdb035c8b3e0540a8d9a561a6c44f4de;10|eurocrisdris::fe4903425d9040f680d8610d9079ea14;10|openaire____::5b76240cc27a58c6f7ceef7d8c36660e;10|openaire____::172bbccecf8fca44ab6a6653e84cb92a;10|openaire____::149c6590f8a06b46314eed77bfca693f;10|eurocrisdris::a6026877c1a174d60f81fd71f62df1c1;10|openaire____::4692342f0992d91f9e705c26959f09e0;10|openaire____::8d529dbb05ec0284662b391789e8ae2a;10|openaire____::345c9d171ef3c5d706d08041d506428c;10|opendoar____::1c1d4df596d01da60385f0bb17a4a9e0;10|opendoar____::7a614fd06c325499f1680b9896beedeb;10|opendoar____::1ee3dfcd8a0645a25a35977997223d22;10|opendoar____::d296c101daa88a51f6ca8cfc1ac79b50;10|opendoar____::798ed7d4ee7138d49b8828958048130a;10|openaire____::c9d2209ecc4d45ba7b4ca7597acb88a2;10|eurocrisdris::c49e0fe4b9ba7b7fab717d1f0f0a674d;10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539;10|eurocrisdris::432ca599953ff50cd4eeffe22faf3e48
#allowedtypes=pubsrepository::institutional
allowedtypes=Institutional
outputPath=/tmp/miriam/enrichment_one_step
pathMap ={"author":"$['author'][*]['fullname']", \
"title":"$['title'][*]['value']",\
"orcid":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']" ,\
"orcid_pending":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid_pending')]['value']" ,\
"contributor" : "$['contributor'][*]['value']",\
"description" : "$['description'][*]['value']",\
"subject" :"$['subject'][*]['value']" , \
"fos" : "$['subject'][?(@['qualifier']['classid']=='FOS')].value" ,\
"sdg" : "$['subject'][?(@['qualifier']['classid']=='SDG')].value",\
"journal":"$['journal'].name",\
"hostedby":"$['instance'][*]['hostedby']['key']",\
"collectedfrom":"$['instance'][*]['collectedfrom']['key']",\
"publisher":"$['publisher'].value",\
"publicationyear":"$['dateofacceptance'].value"}
blacklist=empty
allowedpids=orcid;orcid_pending
baseURL = https://services.openaire.eu/openaire/community/
iterations=1

View File

@ -0,0 +1,30 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>hiveMetastoreUris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>hiveJdbcUrl</name>
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000</value>
</property>
<property>
<name>hiveDbName</name>
<value>openaire</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -0,0 +1,10 @@
## This is a classpath-based import file (this header is required)
orcid_propagation classpath eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app
bulk_tagging classpath eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app
affiliation_inst_repo classpath eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app
entity_semantic_relation classpath eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app
community_organization classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app
result_project classpath eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app
community_project classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app
community_sem_rel classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app
country_propagation classpath eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app

View File

@ -0,0 +1,324 @@
<workflow-app name="enrichment_main" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>allowedsemrelsorcidprop</name>
<description>the semantic relationships allowed for propagation</description>
</property>
<property>
<name>allowedsemrelsresultproject</name>
<description>the allowed semantics </description>
</property>
<property>
<name>allowedsemrelscommunitysemrel</name>
<description>the semantic relationships allowed for propagation</description>
</property>
<property>
<name>datasourceWhitelistForCountryPropagation</name>
<description>the white list</description>
</property>
<property>
<name>allowedtypes</name>
<description>the allowed types</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
<property>
<name>pathMap</name>
<description>the json path associated to each selection field</description>
</property>
<property>
<name>blacklist</name>
<description>list of datasources in blacklist for the affiliation from instrepo propagation</description>
</property>
<property>
<name>hiveDbName</name>
<description>the target hive database name</description>
</property>
<property>
<name>hiveJdbcUrl</name>
<description>hive server jdbc url</description>
</property>
<property>
<name>hiveMetastoreUris</name>
<description>hive server metastore URIs</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
</property>
<property>
<name>oozieActionShareLibForSpark2</name>
<description>oozie action sharelib for spark 2.*</description>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
<description>spark 2.* extra listeners classname</description>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
<description>spark 2.* sql query execution listeners classname</description>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<description>spark 2.* yarn history server address</description>
</property>
<property>
<name>spark2EventLogDir</name>
<description>spark 2.* event log dir location</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="resumeFrom"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<decision name="resumeFrom">
<switch>
<case to="bulk_tagging">${wf:conf('resumeFrom') eq 'BulkTagging'}</case>
<case to="affiliation_inst_repo">${wf:conf('resumeFrom') eq 'AffiliationInstitutionalRepository'}</case>
<case to="entity_semantic_relation">${wf:conf('resumeFrom') eq 'AffiliationSemanticRelation'}</case>
<case to="community_organization">${wf:conf('resumeFrom') eq 'CommunityOrganization'}</case>
<case to="result_project">${wf:conf('resumeFrom') eq 'ResultProject'}</case>
<case to="community_project">${wf:conf('resumeFrom') eq 'CommunityProject'}</case>
<case to="community_sem_rel">${wf:conf('resumeFrom') eq 'CommunitySemanticRelation'}</case>
<case to="country_propagation">${wf:conf('resumeFrom') eq 'CountryPropagation'}</case>
<default to="orcid_propagation"/>
</switch>
</decision>
<action name="orcid_propagation">
<sub-workflow>
<app-path>${wf:appPath()}/orcid_propagation
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${sourcePath}</value>
</property>
<property>
<name>allowedsemrels</name>
<value>${allowedsemrelsorcidprop}</value>
</property>
<property>
<name>outputPath</name>
<value>${outputPath}</value>
</property>
</configuration>
</sub-workflow>
<ok to="bulk_tagging" />
<error to="Kill" />
</action>
<action name="bulk_tagging">
<sub-workflow>
<app-path>${wf:appPath()}/bulk_tagging
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>baseURL</name>
<value>${baseURL}</value>
</property>
<property>
<name>pathMap</name>
<value>${pathMap}</value>
</property>
</configuration>
</sub-workflow>
<ok to="affiliation_inst_repo" />
<error to="Kill" />
</action>
<action name="affiliation_inst_repo">
<sub-workflow>
<app-path>${wf:appPath()}/affiliation_inst_repo
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>blacklist</name>
<value>${blacklist}</value>
</property>
</configuration>
</sub-workflow>
<ok to="entity_semantic_relation" />
<error to="Kill" />
</action>
<action name="entity_semantic_relation">
<sub-workflow>
<app-path>${wf:appPath()}/entity_semantic_relation
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>iterations</name>
<value>${iterations}</value>
</property>
</configuration>
</sub-workflow>
<ok to="community_organization" />
<error to="Kill" />
</action>
<action name="community_organization">
<sub-workflow>
<app-path>${wf:appPath()}/community_organization
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>baseURL</name>
<value>${baseURL}</value>
</property>
</configuration>
</sub-workflow>
<ok to="result_project" />
<error to="Kill" />
</action>
<action name="result_project">
<sub-workflow>
<app-path>${wf:appPath()}/result_project
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>allowedsemrels</name>
<value>${allowedsemrelsresultproject}</value>
</property>
</configuration>
</sub-workflow>
<ok to="community_project" />
<error to="Kill" />
</action>
<action name="community_project">
<sub-workflow>
<app-path>${wf:appPath()}/community_project
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
</configuration>
</sub-workflow>
<ok to="community_sem_rel" />
<error to="Kill" />
</action>
<action name="community_sem_rel">
<sub-workflow>
<app-path>${wf:appPath()}/community_sem_rel
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>allowedsemrels</name>
<value>${allowedsemrelscommunitysemrel}</value>
</property>
<property>
<name>baseURL</name>
<value>${baseURL}</value>
</property>
</configuration>
</sub-workflow>
<ok to="country_propagation" />
<error to="Kill" />
</action>
<action name="country_propagation">
<sub-workflow>
<app-path>${wf:appPath()}/country_propagation
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>whitelist</name>
<value>${datasourceWhitelistForCountryPropagation}</value>
</property>
<property>
<name>allowedtypes</name>
<value>${allowedtypes}</value>
</property>
</configuration>
</sub-workflow>
<ok to="End" />
<error to="Kill" />
</action>
<end name="End"/>
</workflow-app>

View File

@ -8,14 +8,11 @@
<name>pathMap</name>
<description>the json path associated to each selection field</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
<property>
<name>baseURL</name>
<description>the community API base URL</description>
<description>The URL to access the community APIs</description>
</property>
</parameters>
<global>
@ -37,63 +34,18 @@
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="copy_entities"/>
<ok to="exec_bulktag"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<join name="copy_wait" to="exec_bulktag"/>
<action name="exec_bulktag">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>bulkTagging-result</name>
<name>bulkTagging-publication</name>
<class>eu.dnetlib.dhp.bulktag.SparkBulkTagJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
@ -107,7 +59,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${outputPath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/bulktag/</arg>
<arg>--pathMap</arg><arg>${pathMap}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
@ -115,6 +67,8 @@
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -12,11 +12,6 @@
<name>allowedtypes</name>
<description>the allowed types</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
</parameters>
<global>
@ -38,57 +33,13 @@
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="copy_entities"/>
<ok to="prepare_datasource_country_association"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<join name="copy_wait" to="prepare_datasource_country_association"/>
<action name="prepare_datasource_country_association">
<spark xmlns="uri:oozie:spark-action:0.2">
@ -112,18 +63,18 @@
<arg>--allowedtypes</arg><arg>${allowedtypes}</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="fork_join_prepare_result_country"/>
<ok to="fork_prepare_result_country"/>
<error to="Kill"/>
</action>
<fork name="fork_join_prepare_result_country">
<path start="join_prepareresult_publication"/>
<path start="join_prepareresult_dataset"/>
<path start="join_prepareresult_otherresearchproduct"/>
<path start="join_prepareresult_software"/>
<fork name="fork_prepare_result_country">
<path start="prepareresult_publication"/>
<path start="prepareresult_dataset"/>
<path start="prepareresult_otherresearchproduct"/>
<path start="prepareresult_software"/>
</fork>
<action name="join_prepareresult_publication">
<action name="prepareresult_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -153,7 +104,7 @@
<error to="Kill"/>
</action>
<action name="join_prepareresult_dataset">
<action name="prepareresult_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -183,7 +134,7 @@
<error to="Kill"/>
</action>
<action name="join_prepareresult_otherresearchproduct">
<action name="prepareresult_otherresearchproduct">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -213,7 +164,7 @@
<error to="Kill"/>
</action>
<action name="join_prepareresult_software">
<action name="prepareresult_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -243,16 +194,16 @@
<error to="Kill"/>
</action>
<join name="wait_prepare" to="fork_join_apply_country_propagation"/>
<join name="wait_prepare" to="fork_apply_country_propagation"/>
<fork name="fork_join_apply_country_propagation">
<path start="join_propagation_publication"/>
<path start="join_propagation_dataset"/>
<path start="join_propagation_otherresearchproduct"/>
<path start="join_propagation_software"/>
<fork name="fork_apply_country_propagation">
<path start="propagation_publication"/>
<path start="propagation_dataset"/>
<path start="propagation_otherresearchproduct"/>
<path start="propagation_software"/>
</fork>
<action name="join_propagation_publication">
<action name="propagation_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -275,13 +226,13 @@
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/publication</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="join_propagation_dataset">
<action name="propagation_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -304,13 +255,13 @@
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/dataset</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="join_propagation_otherresearchproduct">
<action name="propagation_otherresearchproduct">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -333,13 +284,13 @@
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/otherresearchproduct</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="join_propagation_software">
<action name="propagation_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -362,14 +313,21 @@
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${outputPath}/software</arg>
</spark>
<arg>--outputPath</arg><arg>${workingDir}/country/software</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<join name="wait" to="End"/>
<join name="wait" to="reset_workingDir"/>
<action name="reset_workingDir">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -0,0 +1,101 @@
<workflow-app name="affiliation_from_semrel_propagation" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="reset_outputpath"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="reset_outputpath">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="prepare_info"/>
<error to="Kill"/>
</action>
<action name="prepare_info">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>PrepareResultProjectOrganizationAssociation</name>
<class>eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--graphPath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--leavesPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/leavesPath</arg>
<arg>--childParentPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/childParentPath</arg>
<arg>--resultOrgPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/resultOrgPath</arg>
<arg>--projectOrganizationPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/projectOrganizationPath</arg>
<arg>--relationPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/relation</arg>
</spark>
<ok to="apply_resulttoorganization_propagation"/>
<error to="Kill"/>
</action>
<action name="apply_resulttoorganization_propagation">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>entityToOrganizationFromSemRel</name>
<class>eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--relationPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/relation</arg>
<arg>--outputPath</arg><arg>${sourcePath}/relation</arg>
<arg>--leavesPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/leavesPath</arg>
<arg>--childParentPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/childParentPath</arg>
<arg>--resultOrgPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/resultOrgPath</arg>
<arg>--projectOrganizationPath</arg><arg>${workingDir}/entitiesSemanticRelation/preparedInfo/projectOrganizationPath</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--workingDir</arg><arg>${workingDir}/entitiesSemanticRelation/working</arg>
<arg>--iterations</arg><arg>${iterations}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -11,12 +11,6 @@
"paramDescription": "true if the new version of the graph must be saved",
"paramRequired": false
},
{
"paramName":"h",
"paramLongName":"hive_metastore_uris",
"paramDescription": "the hive metastore uris",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",

View File

@ -225,8 +225,8 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${workingDir}/orcidprop</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
</spark>
<ok to="fork-join-exec-propagation"/>
<error to="Kill"/>
@ -261,9 +261,8 @@
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
</spark>
@ -292,9 +291,8 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
</spark>
@ -323,9 +321,8 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
</spark>
@ -354,9 +351,8 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/preparedInfo/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${outputPath}/software</arg>
</spark>
@ -365,6 +361,15 @@
</action>
<join name="wait2" to="End"/>
<!-- <action name="reset_workingDir">-->
<!-- <fs>-->
<!-- <delete path="${workingDir}"/>-->
<!-- <mkdir path="${workingDir}"/>-->
<!-- </fs>-->
<!-- <ok to="End"/>-->
<!-- <error to="Kill"/>-->
<!-- </action>-->
<end name="End"/>

View File

@ -8,10 +8,7 @@
<name>allowedsemrels</name>
<description>the allowed semantics </description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
</parameters>
<global>
@ -33,98 +30,13 @@
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="copy_entities"/>
<ok to="prepare_project_results_association"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_publication"/>
<path start="copy_dataset"/>
<path start="copy_orp"/>
<path start="copy_software"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_publication">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/publication</arg>
<arg>${nameNode}/${outputPath}/publication</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_dataset">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/dataset</arg>
<arg>${nameNode}/${outputPath}/dataset</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_orp">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/otherresearchproduct</arg>
<arg>${nameNode}/${outputPath}/otherresearchproduct</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_software">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/software</arg>
<arg>${nameNode}/${outputPath}/software</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<join name="wait" to="prepare_project_results_association"/>
<action name="prepare_project_results_association">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -144,8 +56,8 @@
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--potentialUpdatePath</arg><arg>${workingDir}/preparedInfo/potentialUpdates</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--potentialUpdatePath</arg><arg>${workingDir}/resultproject/preparedInfo/potentialUpdates</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/resultproject/preparedInfo/alreadyLinked</arg>
</spark>
<ok to="apply_propagation"/>
<error to="Kill"/>
@ -169,16 +81,22 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--potentialUpdatePath</arg><arg>${workingDir}/preparedInfo/potentialUpdates</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--outputPath</arg><arg>${sourcePath}/relation</arg>
<arg>--potentialUpdatePath</arg><arg>${workingDir}/resultproject/preparedInfo/potentialUpdates</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/resultproject/preparedInfo/alreadyLinked</arg>
</spark>
<ok to="reset_workingDir"/>
<error to="Kill"/>
</action>
<action name="reset_workingDir">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -4,13 +4,9 @@
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
<property>
<name>baseURL</name>
<description>the community API base URL</description>
<description>the baseURL from where to reach the community APIs</description>
</property>
</parameters>
@ -33,58 +29,13 @@
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="copy_entities"/>
<ok to="prepare_result_communitylist"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<join name="copy_wait" to="prepare_result_communitylist"/>
<action name="prepare_result_communitylist">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -102,10 +53,11 @@
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--outputPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
@ -117,7 +69,7 @@
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>community2resultfromorganization</name>
<name>community2resultfromorganization-Publication</name>
<class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
@ -132,16 +84,14 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/communityorganization/preparedInfo/resultCommunityList</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${outputPath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/communityorganization/resulttocommunityfromorganization/</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -4,13 +4,9 @@
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
<property>
<name>baseURL</name>
<description>the community API base URL</description>
<description>the base URL to use to select the right community APIs</description>
</property>
</parameters>
@ -30,61 +26,15 @@
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="copy_entities"/>
<ok to="prepare_result_communitylist"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<join name="copy_wait" to="prepare_result_communitylist"/>
<action name="prepare_result_communitylist">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
@ -106,7 +56,7 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitythroughproject/preparedInfo/resultCommunityList</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
<ok to="exec-propagation"/>
@ -132,9 +82,9 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/resultCommunityList</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/communitythroughproject/preparedInfo/resultCommunityList</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${outputPath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitythroughproject/</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

View File

@ -1,7 +1,7 @@
[
{
"paramName":"is",
"paramLongName":"isLookUpUrl",
"paramName":"bu",
"paramLongName":"baseURL",
"paramDescription": "URL of the isLookUp Service",
"paramRequired": true
},
@ -36,9 +36,9 @@
"paramRequired": true
},
{
"paramName":"tn",
"paramLongName":"resultTableName",
"paramDescription": "the name of the result table we are currently working on",
"paramRequired": true
}
"paramName":"tn",
"paramLongName":"resultTableName",
"paramDescription": "the name of the result table we are currently working on",
"paramRequired": true
}
]

View File

@ -9,7 +9,7 @@
<description>the semantic relationships allowed for propagation</description>
</property>
<property>
<name>isLookUpUrl</name>
<name>baseURL</name>
<description>the isLookup service endpoint</description>
</property>
<property>
@ -26,66 +26,13 @@
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="copy_entities"/>
<ok to="fork_prepare_assoc_step1"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="copy_wait"/>
<error to="Kill"/>
</action>
<join name="copy_wait" to="fork_prepare_assoc_step1"/>
<fork name="fork_prepare_assoc_step1">
<path start="join_prepare_publication"/>
<path start="join_prepare_dataset"/>
@ -101,8 +48,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -114,9 +63,9 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetCommunityAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
@ -130,8 +79,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -143,9 +94,9 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetCommunityAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
@ -159,8 +110,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -172,9 +125,9 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetCommunityAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
@ -188,8 +141,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -201,9 +156,9 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetCommunityAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
<arg>--baseURL</arg><arg>${baseURL}</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
@ -219,8 +174,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep2</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -229,8 +186,8 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/preparedInfo/targetCommunityAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/mergedCommunityAssoc</arg>
<arg>--sourcePath</arg><arg>${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc</arg>
</spark>
<ok to="fork-join-exec-propagation"/>
<error to="Kill"/>
@ -251,8 +208,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -261,12 +220,12 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/mergedCommunityAssoc</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/publication</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>
@ -280,8 +239,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -290,12 +251,12 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/mergedCommunityAssoc</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/dataset</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>
@ -309,8 +270,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -319,12 +282,12 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/mergedCommunityAssoc</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/otherresearchproduct</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>
@ -338,8 +301,10 @@
<class>eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -348,12 +313,12 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo/mergedCommunityAssoc</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${outputPath}/software</arg>
<arg>--saveGraph</arg><arg>${saveGraph}</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitysemrel/software</arg>
</spark>
<ok to="wait2"/>
<error to="Kill"/>

View File

@ -0,0 +1,20 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "the path where prepared info have been stored",
"paramRequired": false
},{
"paramName": "o",
"paramLongName": "outputPath",
"paramDescription": "institutional repositories that should not be considered for the propagation",
"paramRequired": false
}
]

View File

@ -11,16 +11,11 @@
"paramDescription": "the hive metastore uris",
"paramRequired": true
},
{
"paramName":"dop",
"paramLongName":"datasourceOrganizationPath",
"paramDescription": "path where to store/find association from datasource and organization",
"paramRequired": true
},
{
"paramName":"alp",
"paramLongName":"alreadyLinkedPath",
"paramDescription": "path where to store/find already linked results and organizations",
"paramName":"wp",
"paramLongName":"workingPath",
"paramDescription": "the working path",
"paramRequired": true
},
{

View File

@ -5,8 +5,8 @@
<description>the source path</description>
</property>
<property>
<name>outputPath</name>
<description>sets the outputPath</description>
<name>blacklist</name>
<description>The list of institutional repositories that should not be used for the propagation</description>
</property>
</parameters>
@ -29,97 +29,13 @@
<action name="reset_outputpath">
<fs>
<delete path="${outputPath}"/>
<mkdir path="${outputPath}"/>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="copy_entities"/>
<ok to="prepare_result_organization_association"/>
<error to="Kill"/>
</action>
<fork name="copy_entities">
<path start="copy_relation"/>
<path start="copy_publication"/>
<path start="copy_dataset"/>
<path start="copy_orp"/>
<path start="copy_software"/>
<path start="copy_organization"/>
<path start="copy_projects"/>
<path start="copy_datasources"/>
</fork>
<action name="copy_relation">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/relation</arg>
<arg>${nameNode}/${outputPath}/relation</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_publication">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/publication</arg>
<arg>${nameNode}/${outputPath}/publication</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_dataset">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/dataset</arg>
<arg>${nameNode}/${outputPath}/dataset</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_orp">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/otherresearchproduct</arg>
<arg>${nameNode}/${outputPath}/otherresearchproduct</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_software">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/software</arg>
<arg>${nameNode}/${outputPath}/software</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_organization">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/organization</arg>
<arg>${nameNode}/${outputPath}/organization</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_projects">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/project</arg>
<arg>${nameNode}/${outputPath}/project</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="copy_datasources">
<distcp xmlns="uri:oozie:distcp-action:0.2">
<arg>${nameNode}/${sourcePath}/datasource</arg>
<arg>${nameNode}/${outputPath}/datasource</arg>
</distcp>
<ok to="wait"/>
<error to="Kill"/>
</action>
<join name="wait" to="prepare_result_organization_association"/>
<action name="prepare_result_organization_association">
<spark xmlns="uri:oozie:spark-action:0.2">
@ -138,10 +54,9 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--workingPath</arg><arg>${workingDir}/affiliationInstRepo</arg>
<arg>--blacklist</arg><arg>${blacklist}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
</spark>
<ok to="fork_join_apply_resulttoorganization_propagation"/>
<error to="Kill"/>
@ -173,9 +88,9 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--outputPath</arg><arg>${workingDir}/affiliationInstRepo/publication/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
</spark>
@ -202,9 +117,9 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--outputPath</arg><arg>${workingDir}/affiliationInstRepo/dataset/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
</spark>
@ -231,9 +146,9 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--outputPath</arg><arg>${workingDir}/affiliationInstRepo/otherresearchproduct/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
</spark>
@ -260,9 +175,9 @@
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--outputPath</arg><arg>${outputPath}/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/preparedInfo/alreadyLinked</arg>
<arg>--outputPath</arg><arg>${workingDir}/affiliationInstRepo/software/relation</arg>
<arg>--datasourceOrganizationPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
</spark>
@ -270,7 +185,32 @@
<error to="Kill"/>
</action>
<join name="wait2" to="End"/>
<join name="wait2" to="append_new_relations"/>
<action name="append_new_relations">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>append new relations</name>
<class>eu.dnetlib.dhp.resulttoorganizationfrominstrepo.AppendNewRelations</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=${sparkExecutorCores}
--executor-memory=${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--outputPath</arg><arg>${sourcePath}/relation</arg>
<arg>--sourcePath</arg><arg>${workingDir}/affiliationInstRepo/</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>

View File

@ -114,7 +114,7 @@ public class SparkJobTest {
.option("compression", "gzip")
.json(workingDir.toString() + "/projectInput");
SparkResultToOrganizationFromSemRel
SparkEntityToOrganizationFromSemRel
.main(
new String[] {
@ -395,7 +395,7 @@ public class SparkJobTest {
.option("compression", "gzip")
.json(workingDir.toString() + "/projectInput");
SparkResultToOrganizationFromSemRel
SparkEntityToOrganizationFromSemRel
.main(
new String[] {
@ -678,7 +678,7 @@ public class SparkJobTest {
.option("compression", "gzip")
.json(workingDir.toString() + "/projectInput");
SparkResultToOrganizationFromSemRel
SparkEntityToOrganizationFromSemRel
.main(
new String[] {

View File

@ -1,3 +1,3 @@
#!/bin/bash
curl -LSs $1 | hdfs dfs -put - $2/$3
curl -LSs http://api.crossref.org/works/10.1099/jgv.0.001453 > prova.txt
#curl -LSs http://api.crossref.org/works/10.1099/jgv.0.001453 > prova.txt

View File

@ -82,7 +82,7 @@ public class IndexRecordTransformerTest {
void testPeerReviewed() throws IOException, TransformerException {
final XmlRecordFactory xmlRecordFactory = new XmlRecordFactory(contextMapper, false,
XmlConverterJob.schemaLocation);
XmlConverterJob.schemaLocation);
final Publication p = load("publication.json", Publication.class);

View File

@ -1,6 +1,8 @@
package eu.dnetlib.dhp.oa.provision;
import static org.junit.jupiter.api.Assertions.assertEquals;
import java.io.IOException;
import java.io.StringReader;
import java.net.URI;
@ -32,8 +34,6 @@ import eu.dnetlib.dhp.oa.provision.utils.ISLookupClient;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import static org.junit.jupiter.api.Assertions.assertEquals;
@ExtendWith(MockitoExtension.class)
public class XmlIndexingJobTest extends SolrTest {
@ -110,34 +110,33 @@ public class XmlIndexingJobTest extends SolrTest {
QueryResponse rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "*:*"));
assertEquals(
nRecord, rsp.getResults().getNumFound(),
"the number of indexed records should be equal to the number of input records");
nRecord, rsp.getResults().getNumFound(),
"the number of indexed records should be equal to the number of input records");
rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "isgreen:true"));
assertEquals(
0, rsp.getResults().getNumFound(),
"the number of indexed records having isgreen = true");
0, rsp.getResults().getNumFound(),
"the number of indexed records having isgreen = true");
rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "openaccesscolor:bronze"));
assertEquals(
0, rsp.getResults().getNumFound(),
"the number of indexed records having openaccesscolor = bronze");
0, rsp.getResults().getNumFound(),
"the number of indexed records having openaccesscolor = bronze");
rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "isindiamondjournal:true"));
assertEquals(
0, rsp.getResults().getNumFound(),
"the number of indexed records having isindiamondjournal = true");
0, rsp.getResults().getNumFound(),
"the number of indexed records having isindiamondjournal = true");
rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "publiclyfunded:true"));
assertEquals(
0, rsp.getResults().getNumFound(),
"the number of indexed records having publiclyfunded = true");
0, rsp.getResults().getNumFound(),
"the number of indexed records having publiclyfunded = true");
rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "peerreviewed:true"));
assertEquals(
0, rsp.getResults().getNumFound(),
"the number of indexed records having peerreviewed = true");
0, rsp.getResults().getNumFound(),
"the number of indexed records having peerreviewed = true");
}
@Test