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

Merge branch 'master' into clean_context_master

This commit is contained in:
Claudio Atzori 2022-07-13 15:59:08 +02:00
parent ca373979eb 446699c59d
commit 2f0d3dffe3
36 changed files with 997 additions and 557 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
dhp-common/src/main/java/eu/dnetlib/dhp/common/api/ZenodoAPIClient.java
View File

@ -255,7 +255,8 @@ public class ZenodoAPIClient implements Serializable {
private void setDepositionId(String concept_rec_id, Integer page) throws IOException, MissingConceptDoiException {
ZenodoModelList zenodoModelList = new Gson().fromJson(getPrevDepositions(String.valueOf(page)), ZenodoModelList.class);
ZenodoModelList zenodoModelList = new Gson()
.fromJson(getPrevDepositions(String.valueOf(page)), ZenodoModelList.class);
for (ZenodoModel zm : zenodoModelList) {
if (zm.getConceptrecid().equals(concept_rec_id)) {
@ -263,8 +264,9 @@ public class ZenodoAPIClient implements Serializable {
return;
}
}
if(zenodoModelList.size() == 0)
throw new MissingConceptDoiException("The concept record id specified was missing in the list of depositions");
if (zenodoModelList.size() == 0)
throw new MissingConceptDoiException(
"The concept record id specified was missing in the list of depositions");
setDepositionId(concept_rec_id, page + 1);
}
@ -278,11 +280,11 @@ public class ZenodoAPIClient implements Serializable {
String url = urlBuilder.build().toString();
Request request = new Request.Builder()
.url(url)
.addHeader(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString()) // add request headers
.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
.get()
.build();
.url(url)
.addHeader(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString()) // add request headers
.addHeader(HttpHeaders.AUTHORIZATION, "Bearer " + access_token)
.get()
.build();
try (Response response = httpClient.newCall(request).execute()) {
@ -295,7 +297,6 @@ public class ZenodoAPIClient implements Serializable {
}
private String getBucket(String url) throws IOException {
OkHttpClient httpClient = new OkHttpClient.Builder()
.connectTimeout(600, TimeUnit.SECONDS)

10
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/transformation/TransformationJobTest.java
View File

@ -142,7 +142,8 @@ class TransformationJobTest extends AbstractVocabularyTest {
@Test
@DisplayName("Test TransformSparkJobNode.main with oaiOpenaire_datacite (v4)")
void transformTestITGv4OAIdatacite(@TempDir final Path testDir) throws Exception {
void transformTestITGv4OAIdatacite(@TempDir
final Path testDir) throws Exception {
try (SparkSession spark = SparkSession.builder().config(sparkConf).getOrCreate()) {
@ -152,7 +153,9 @@ class TransformationJobTest extends AbstractVocabularyTest {
.getFile();
final String mdstore_output = testDir.toString() + "/version";
mockupTrasformationRule("simpleTRule", "/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid.xsl");
mockupTrasformationRule(
"simpleTRule",
"/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid.xsl");
final Map<String, String> parameters = Stream.of(new String[][] {
{
@ -203,7 +206,8 @@ class TransformationJobTest extends AbstractVocabularyTest {
@Test
@DisplayName("Test TransformSparkJobNode.main")
void transformTest(@TempDir final Path testDir) throws Exception {
void transformTest(@TempDir
final Path testDir) throws Exception {
try (SparkSession spark = SparkSession.builder().config(sparkConf).getOrCreate()) {

2
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java
View File

@ -103,7 +103,7 @@ public class SparkBulkTagJob {
ResultTagger resultTagger = new ResultTagger();
readPath(spark, inputPath, resultClazz)
.map(patchResult(), Encoders.bean(resultClazz))
.filter(Objects::nonNull)
.filter(Objects::nonNull)
.map(
(MapFunction<R, R>) value -> resultTagger
.enrichContextCriteria(

6
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/community/SparkPrepareResultProject.java
View File

@ -10,6 +10,7 @@ import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
import org.apache.spark.sql.Dataset;
@ -81,8 +82,9 @@ public class SparkPrepareResultProject implements Serializable {
Dataset<Relation> relation = Utils
.readPath(spark, inputPath + "/relation", Relation.class)
.filter(
"dataInfo.deletedbyinference = false and lower(relClass) = '"
+ ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
(FilterFunction<Relation>) r -> !r.getDataInfo().getDeletedbyinference() &&
r.getRelClass().equalsIgnoreCase(ModelConstants.IS_PRODUCED_BY));
Dataset<eu.dnetlib.dhp.schema.oaf.Project> projects = Utils
.readPath(spark, inputPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);

109
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/funderresults/SparkDumpFunderResults.java
View File

@ -7,17 +7,22 @@ import java.io.Serializable;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.ForeachFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*;
import org.jetbrains.annotations.NotNull;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import eu.dnetlib.dhp.schema.dump.oaf.community.Funder;
import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
/**
@ -33,87 +38,83 @@ public class SparkDumpFunderResults implements Serializable {
SparkDumpFunderResults.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/dump/funder_result_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
final String graphPath = parser.get("graphPath");
log.info("relationPath: {}", graphPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
Utils.removeOutputDir(spark, outputPath);
writeResultProjectList(spark, inputPath, outputPath, graphPath);
writeResultProjectList(spark, inputPath, outputPath);
});
}
private static void writeResultProjectList(SparkSession spark, String inputPath, String outputPath,
String graphPath) {
Dataset<eu.dnetlib.dhp.schema.oaf.Project> project = Utils
.readPath(spark, graphPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
private static void writeResultProjectList(SparkSession spark, String inputPath, String outputPath) {
Dataset<CommunityResult> result = Utils
.readPath(spark, inputPath + "/publication", CommunityResult.class)
.union(Utils.readPath(spark, inputPath + "/dataset", CommunityResult.class))
.union(Utils.readPath(spark, inputPath + "/orp", CommunityResult.class))
.union(Utils.readPath(spark, inputPath + "/otherresearchproduct", CommunityResult.class))
.union(Utils.readPath(spark, inputPath + "/software", CommunityResult.class));
List<String> funderList = project
.select("id")
.map((MapFunction<Row, String>) value -> value.getString(0).substring(0, 15), Encoders.STRING())
.distinct()
.collectAsList();
log.info("Number of result {}", result.count());
Dataset<String> tmp = result
.flatMap((FlatMapFunction<CommunityResult, String>) cr -> cr.getProjects().stream().map(p -> {
return getFunderName(p);
}).collect(Collectors.toList()).iterator(), Encoders.STRING())
.distinct();
List<String> funderList = tmp.collectAsList();
funderList.forEach(funder -> {
String fundernsp = funder.substring(3);
String funderdump;
if (fundernsp.startsWith("corda")) {
funderdump = "EC_";
if (fundernsp.endsWith("h2020")) {
funderdump += "H2020";
} else {
funderdump += "FP7";
}
} else {
funderdump = fundernsp.substring(0, fundernsp.indexOf("_")).toUpperCase();
}
writeFunderResult(funder, result, outputPath, funderdump);
dumpResults(funder, result, outputPath);
});
}
private static void dumpResults(String nsp, Dataset<CommunityResult> results, String outputPath,
String funderName) {
@NotNull
private static String getFunderName(Project p) {
Optional<Funder> ofunder = Optional.ofNullable(p.getFunder());
if (ofunder.isPresent()) {
String fName = ofunder.get().getShortName();
if (fName.equalsIgnoreCase("ec")) {
fName += "_" + ofunder.get().getFundingStream();
}
return fName;
} else {
String fName = p.getId().substring(3, p.getId().indexOf("_")).toUpperCase();
if (fName.equalsIgnoreCase("ec")) {
if (p.getId().contains("h2020")) {
fName += "_H2020";
} else {
fName += "_FP7";
}
} else if (fName.equalsIgnoreCase("conicytf")) {
fName = "CONICYT";
} else if (fName.equalsIgnoreCase("dfgf")) {
fName = "DFG";
} else if (fName.equalsIgnoreCase("tubitakf")) {
fName = "TUBITAK";
} else if (fName.equalsIgnoreCase("euenvagency")) {
fName = "EEA";
}
return fName;
}
}
private static void dumpResults(String funder, Dataset<CommunityResult> results, String outputPath) {
results.map((MapFunction<CommunityResult, CommunityResult>) r -> {
if (!Optional.ofNullable(r.getProjects()).isPresent()) {
return null;
}
for (Project p : r.getProjects()) {
if (p.getId().startsWith(nsp)) {
if (nsp.startsWith("40|irb")) {
if (p.getFunder().getShortName().equals(funderName))
return r;
else
return null;
}
String fName = getFunderName(p);
if (fName.equalsIgnoreCase(funder)) {
return r;
}
}
@ -123,18 +124,6 @@ public class SparkDumpFunderResults implements Serializable {
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "/" + funderName);
.json(outputPath + "/" + funder);
}
private static void writeFunderResult(String funder, Dataset<CommunityResult> results, String outputPath,
String funderDump) {
if (funder.startsWith("40|irb")) {
dumpResults(funder, results, outputPath, "HRZZ");
dumpResults(funder, results, outputPath, "MZOS");
} else
dumpResults(funder, results, outputPath, funderDump);
}
}

66
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/funderresults/SparkResultLinkedToProject.java
View File

@ -5,9 +5,12 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
import org.apache.spark.sql.Dataset;
@ -18,11 +21,18 @@ import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.graph.dump.Constants;
import eu.dnetlib.dhp.oa.graph.dump.DumpProducts;
import eu.dnetlib.dhp.oa.graph.dump.ResultMapper;
import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
import eu.dnetlib.dhp.oa.graph.dump.community.ResultProject;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import eu.dnetlib.dhp.schema.oaf.Project;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result;
import scala.Tuple2;
/**
* Selects the results linked to projects. Only for these results the dump will be performed.
@ -58,8 +68,10 @@ public class SparkResultLinkedToProject implements Serializable {
final String resultClassName = parser.get("resultTableName");
log.info("resultTableName: {}", resultClassName);
final String graphPath = parser.get("graphPath");
log.info("graphPath: {}", graphPath);
final String resultProjectsPath = parser.get("graphPath");
log.info("graphPath: {}", resultProjectsPath);
String communityMapPath = parser.get("communityMapPath");
@SuppressWarnings("unchecked")
Class<? extends Result> inputClazz = (Class<? extends Result>) Class.forName(resultClassName);
@ -70,43 +82,33 @@ public class SparkResultLinkedToProject implements Serializable {
isSparkSessionManaged,
spark -> {
Utils.removeOutputDir(spark, outputPath);
writeResultsLinkedToProjects(spark, inputClazz, inputPath, outputPath, graphPath);
writeResultsLinkedToProjects(
communityMapPath, spark, inputClazz, inputPath, outputPath, resultProjectsPath);
});
}
private static <R extends Result> void writeResultsLinkedToProjects(SparkSession spark, Class<R> inputClazz,
String inputPath, String outputPath, String graphPath) {
private static <R extends Result> void writeResultsLinkedToProjects(String communityMapPath, SparkSession spark,
Class<R> inputClazz,
String inputPath, String outputPath, String resultProjectsPath) {
Dataset<R> results = Utils
.readPath(spark, inputPath, inputClazz)
.filter("dataInfo.deletedbyinference = false and datainfo.invisible = false");
Dataset<Relation> relations = Utils
.readPath(spark, graphPath + "/relation", Relation.class)
.filter(
"dataInfo.deletedbyinference = false and lower(relClass) = '"
+ ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
Dataset<Project> project = Utils.readPath(spark, graphPath + "/project", Project.class);
results.createOrReplaceTempView("result");
relations.createOrReplaceTempView("relation");
project.createOrReplaceTempView("project");
Dataset<R> tmp = spark
.sql(
"Select res.* " +
"from relation rel " +
"join result res " +
"on rel.source = res.id " +
"join project p " +
"on rel.target = p.id " +
"")
.as(Encoders.bean(inputClazz));
tmp
.groupByKey(
(MapFunction<R, String>) value -> value
.getId(),
Encoders.STRING())
.mapGroups((MapGroupsFunction<String, R, R>) (k, it) -> it.next(), Encoders.bean(inputClazz))
(FilterFunction<R>) r -> !r.getDataInfo().getDeletedbyinference() &&
!r.getDataInfo().getInvisible());
Dataset<ResultProject> resultProjectDataset = Utils
.readPath(spark, resultProjectsPath, ResultProject.class);
CommunityMap communityMap = Utils.getCommunityMap(spark, communityMapPath);
results
.joinWith(resultProjectDataset, results.col("id").equalTo(resultProjectDataset.col("resultId")))
.map((MapFunction<Tuple2<R, ResultProject>, CommunityResult>) t2 -> {
CommunityResult cr = (CommunityResult) ResultMapper
.map(
t2._1(),
communityMap, Constants.DUMPTYPE.FUNDER.getType());
cr.setProjects(t2._2().getProjectsList());
return cr;
}, Encoders.bean(CommunityResult.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")

82
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/projectssubset/ProjectsSubsetSparkJob.java Normal file
View File

@ -0,0 +1,82 @@
package eu.dnetlib.dhp.oa.graph.dump.projectssubset;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import java.util.Objects;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.schema.dump.oaf.graph.Project;
import scala.Tuple2;
public class ProjectsSubsetSparkJob implements Serializable {
private static final Logger log = LoggerFactory.getLogger(ProjectsSubsetSparkJob.class);
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
ProjectsSubsetSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/dump/project_subset_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
final String projectListPath = parser.get("projectListPath");
log.info("projectListPath: {}", projectListPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
Utils.removeOutputDir(spark, outputPath);
getNewProjectList(spark, inputPath, outputPath, projectListPath);
});
}
private static void getNewProjectList(SparkSession spark, String inputPath, String outputPath,
String projectListPath) {
Dataset<String> projectList = spark.read().textFile(projectListPath);
Dataset<Project> projects;
projects = Utils.readPath(spark, inputPath, Project.class);
projects
.joinWith(projectList, projects.col("id").equalTo(projectList.col("value")), "left")
.map((MapFunction<Tuple2<Project, String>, Project>) t2 -> {
if (Optional.ofNullable(t2._2()).isPresent())
return null;
return t2._1();
}, Encoders.bean(Project.class))
.filter(Objects::nonNull)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
Utils
.readPath(spark, outputPath, Project.class)
.map((MapFunction<Project, String>) p -> p.getId(), Encoders.STRING())
.write()
.mode(SaveMode.Append)
.option("compression", "gzip")
.text(projectListPath);
}
}

12
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/funder_result_parameters.json
View File

@ -17,10 +17,10 @@
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
},
{
"paramName": "gp",
"paramLongName": "graphPath",
"paramDescription": "the relationPath",
"paramRequired": true
}
{
"paramName": "gp",
"paramLongName": "graphPath",
"paramDescription": "the relationPath",
"paramRequired": false
}
]

20
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/input_parameter_select_relation.json Normal file
View File

@ -0,0 +1,20 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"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
}
]

6
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/input_parameters_link_prj.json
View File

@ -28,6 +28,12 @@
"paramLongName":"graphPath",
"paramDescription": "the path to the relations",
"paramRequired": true
},
{
"paramName":"cmp",
"paramLongName":"communityMapPath",
"paramDescription": "the path to the relations",
"paramRequired": true
}
]

27
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/project_subset_parameters.json Normal file
View File

@ -0,0 +1,27 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"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": "pl",
"paramLongName": "projectListPath",
"paramDescription": "the path of the association result projectlist",
"paramRequired": true
}
]

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app/config-default.xml → dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/oozie_app/config-default.xml
View File

@ -27,4 +27,4 @@
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
</configuration>

171
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/oozie_app/workflow.xml Normal file
View File

@ -0,0 +1,171 @@
<workflow-app name="dump_graph" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>projectListPath</name>
<description>the path to the project list</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
<property>
<name>accessToken</name>
<description>the access token used for the deposition in Zenodo</description>
</property>
<property>
<name>connectionUrl</name>
<description>the connection url for Zenodo</description>
</property>
<property>
<name>metadata</name>
<description> the metadata associated to the deposition</description>
</property>
<property>
<name>depositionType</name>
<description>the type of deposition we want to perform. "new" for brand new deposition, "version" for a new version of a published deposition (in this case the concept record id must be provided), "upload" to upload content to an open deposition for which we already have the deposition id (in this case the deposition id should be provided)</description>
</property>
<property>
<name>conceptRecordId</name>
<description>for new version, the id of the record for the old deposition</description>
</property>
<property>
<name>depositionId</name>
<description>the depositionId of a deposition open that has to be added content</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>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="dump_project"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="dump_project">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table project </name>
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/project</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
<arg>--outputPath</arg><arg>${workingDir}/project</arg>
<arg>--communityMapPath</arg><arg>noneed</arg>
</spark>
<ok to="get_new_projects"/>
<error to="Kill"/>
</action>
<action name="get_new_projects">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table project </name>
<class>eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectsSubsetSparkJob</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/project</arg>
<arg>--outputPath</arg><arg>${workingDir}/tar/project</arg>
<arg>--projectListPath</arg><arg>${projectListPath}</arg>
</spark>
<ok to="make_archive"/>
<error to="Kill"/>
</action>
<action name="make_archive">
<java>
<main-class>eu.dnetlib.dhp.oa.graph.dump.MakeTar</main-class>
<arg>--hdfsPath</arg><arg>${outputPath}</arg>
<arg>--nameNode</arg><arg>${nameNode}</arg>
<arg>--sourcePath</arg><arg>${workingDir}/tar</arg>
</java>
<ok to="send_zenodo"/>
<error to="Kill"/>
</action>
<action name="send_zenodo">
<java>
<main-class>eu.dnetlib.dhp.oa.graph.dump.SendToZenodoHDFS</main-class>
<arg>--hdfsPath</arg><arg>${outputPath}</arg>
<arg>--nameNode</arg><arg>${nameNode}</arg>
<arg>--accessToken</arg><arg>${accessToken}</arg>
<arg>--connectionUrl</arg><arg>${connectionUrl}</arg>
<arg>--metadata</arg><arg>${metadata}</arg>
<arg>--conceptRecordId</arg><arg>${conceptRecordId}</arg>
<arg>--depositionType</arg><arg>${depositionType}</arg>
<arg>--depositionId</arg><arg>${depositionId}</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

347
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app/workflow.xml
View File

@ -1,347 +0,0 @@
<workflow-app name="sub_dump_community_funder_results" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
<property>
<name>communityMapPath</name>
<description>the path to the community map</description>
</property>
<property>
<name>selectedResults</name>
<description>the path the the possible subset ot results to be dumped</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>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="fork_dump"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<fork name="fork_dump">
<path start="dump_publication"/>
<path start="dump_dataset"/>
<path start="dump_orp"/>
<path start="dump_software"/>
</fork>
<action name="dump_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table publication for community/funder related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${selectedResults}/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/publication</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
<arg>--dumpType</arg><arg>${dumpType}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<action name="dump_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table dataset for community/funder related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${selectedResults}/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/dataset</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<action name="dump_orp">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table ORP for community related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${selectedResults}/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<action name="dump_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table software for community related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${selectedResults}/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/software</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<join name="join_dump" to="prepareResultProject"/>
<action name="prepareResultProject">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Prepare association result subset of project info</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="fork_extendWithProject"/>
<error to="Kill"/>
</action>
<fork name="fork_extendWithProject">
<path start="extend_publication"/>
<path start="extend_dataset"/>
<path start="extend_orp"/>
<path start="extend_software"/>
</fork>
<action name="extend_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped publications with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/ext/publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped dataset with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/ext/dataset</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_orp">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped ORP with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/ext/orp</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped software with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/software</arg>
<arg>--outputPath</arg><arg>${outputPath}/ext/software</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<join name="join_extend" to="End"/>
<end name="End"/>
</workflow-app>

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/community/oozie_app/import.txt
View File

@ -1,2 +0,0 @@
## This is a classpath-based import file (this header is required)
dump_common classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app

273
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/community/oozie_app/workflow.xml
View File

@ -77,42 +77,259 @@
</configuration>
</global>
<start to="common_action_community_funder"/>
<start to="fork_dump"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="common_action_community_funder">
<sub-workflow>
<app-path>${wf:appPath()}/dump_common
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${sourcePath}</value>
</property>
<property>
<name>selectedResults</name>
<value>${sourcePath}</value>
</property>
<property>
<name>communityMapPath</name>
<value>${workingDir}/communityMap</value>
</property>
<property>
<name>outputPath</name>
<value>${workingDir}</value>
</property>
</configuration>
</sub-workflow>
<ok to="splitForCommunities" />
<error to="Kill" />
<fork name="fork_dump">
<path start="dump_publication"/>
<path start="dump_dataset"/>
<path start="dump_orp"/>
<path start="dump_software"/>
</fork>
<action name="dump_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table publication for community/funder related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/publication</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
<arg>--dumpType</arg><arg>${dumpType}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<action name="dump_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table dataset for community/funder related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/dataset</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<action name="dump_orp">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table ORP for community related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<action name="dump_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Dump table software for community related products</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/dump/software</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_dump"/>
<error to="Kill"/>
</action>
<join name="join_dump" to="prepareResultProject"/>
<action name="prepareResultProject">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Prepare association result subset of project info</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="fork_extendWithProject"/>
<error to="Kill"/>
</action>
<fork name="fork_extendWithProject">
<path start="extend_publication"/>
<path start="extend_dataset"/>
<path start="extend_orp"/>
<path start="extend_software"/>
</fork>
<action name="extend_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped publications with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/ext/publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped dataset with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/ext/dataset</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_orp">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped ORP with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/ext/orp</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<action name="extend_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Extend dumped software with information about project</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/dump/software</arg>
<arg>--outputPath</arg><arg>${workingDir}/ext/software</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="join_extend"/>
<error to="Kill"/>
</action>
<join name="join_extend" to="splitForCommunities"/>
<action name="splitForCommunities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>

1
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/complete/oozie_app/workflow.xml
View File

@ -298,6 +298,7 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/validrelation</arg>

2
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/funder/oozie_app/import.txt
View File

@ -1,2 +0,0 @@
## This is a classpath-based import file (this header is required)
dump_common classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app

71
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/funder/oozie_app/workflow.xml
View File

@ -77,12 +77,36 @@
</configuration>
</global>
<start to="fork_result_linked_to_projects"/>
<start to="prepareResultProject"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="prepareResultProject">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Prepare association result subset of project info</name>
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
</spark>
<ok to="fork_result_linked_to_projects"/>
<error to="Kill"/>
</action>
<fork name="fork_result_linked_to_projects">
<path start="select_publication_linked_to_projects"/>
@ -111,7 +135,8 @@
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/publication</arg>
<arg>--graphPath</arg><arg>${sourcePath}</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
@ -137,7 +162,8 @@
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/dataset</arg>
<arg>--graphPath</arg><arg>${sourcePath}</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
@ -163,7 +189,8 @@
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/otherresearchproduct</arg>
<arg>--graphPath</arg><arg>${sourcePath}</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
@ -189,41 +216,14 @@
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/result/software</arg>
<arg>--graphPath</arg><arg>${sourcePath}</arg>
<arg>--graphPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
</spark>
<ok to="join_link"/>
<error to="Kill"/>
</action>
<join name="join_link" to="common_action_community_funder"/>
<action name="common_action_community_funder">
<sub-workflow>
<app-path>${wf:appPath()}/dump_common
</app-path>
<propagate-configuration/>
<configuration>
<property>
<name>sourcePath</name>
<value>${sourcePath}</value>
</property>
<property>
<name>selectedResults</name>
<value>${workingDir}/result</value>
</property>
<property>
<name>communityMapPath</name>
<value>${workingDir}/communityMap</value>
</property>
<property>
<name>outputPath</name>
<value>${workingDir}</value>
</property>
</configuration>
</sub-workflow>
<ok to="dump_funder_results" />
<error to="Kill" />
</action>
<join name="join_link" to="dump_funder_results"/>
<action name="dump_funder_results">
<spark xmlns="uri:oozie:spark-action:0.2">
@ -242,9 +242,8 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/ext</arg>
<arg>--sourcePath</arg><arg>${workingDir}/result</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
<arg>--graphPath</arg><arg>${sourcePath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

23
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/PrepareResultProjectJobTest.java
View File

@ -321,4 +321,27 @@ public class PrepareResultProjectJobTest {
3, resultExplodedProvenance.filter("provenance = 'sysimport:crosswalk:entityregistry'").count());
}
@Test
void testMatchx() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/match")
.getPath();
SparkPrepareResultProject.main(new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-outputPath", workingDir.toString() + "/preparedInfo",
"-sourcePath", sourcePath
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<ResultProject> tmp = sc
.textFile(workingDir.toString() + "/preparedInfo")
.map(item -> OBJECT_MAPPER.readValue(item, ResultProject.class));
tmp.foreach(r -> System.out.println(OBJECT_MAPPER.writeValueAsString(r)));
}
}

39
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/funderresult/ResultLinkedToProjectTest.java
View File

@ -22,6 +22,7 @@ import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Result;
@ -76,7 +77,11 @@ public class ResultLinkedToProjectTest {
.getPath();
final String graphPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/nomatch")
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/preparedInfo")
.getPath();
final String communityMapPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/communityMapPath")
.getPath();
SparkResultLinkedToProject.main(new String[] {
@ -84,20 +89,18 @@ public class ResultLinkedToProjectTest {
"-outputPath", workingDir.toString() + "/preparedInfo",
"-sourcePath", sourcePath,
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
"-graphPath", graphPath
"-graphPath", graphPath,
"-communityMapPath", communityMapPath
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
JavaRDD<CommunityResult> tmp = sc
.textFile(workingDir.toString() + "/preparedInfo")
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
org.apache.spark.sql.Dataset<Result> verificationDataset = spark
.createDataset(tmp.rdd(), Encoders.bean(Result.class));
Assertions.assertEquals(0, verificationDataset.count());
Assertions.assertEquals(0, tmp.count());
}
@ -108,8 +111,12 @@ public class ResultLinkedToProjectTest {
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/match/papers.json")
.getPath();
final String relationPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/match")
final String graphPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/preparedInfo")
.getPath();
final String communityMapPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/communityMapPath")
.getPath();
SparkResultLinkedToProject.main(new String[] {
@ -117,20 +124,18 @@ public class ResultLinkedToProjectTest {
"-outputPath", workingDir.toString() + "/preparedInfo",
"-sourcePath", sourcePath,
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Publication",
"-graphPath", relationPath
"-graphPath", graphPath,
"-communityMapPath", communityMapPath
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Publication> tmp = sc
JavaRDD<CommunityResult> tmp = sc
.textFile(workingDir.toString() + "/preparedInfo")
.map(item -> OBJECT_MAPPER.readValue(item, Publication.class));
.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
org.apache.spark.sql.Dataset<Publication> verificationDataset = spark
.createDataset(tmp.rdd(), Encoders.bean(Publication.class));
Assertions.assertEquals(1, verificationDataset.count());
Assertions.assertEquals(1, tmp.count());
}

18
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/funderresult/SplitPerFunderTest.java
View File

@ -5,10 +5,14 @@ import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
// import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkDumpFunderResults2;
// import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkGetFunderList;
import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.ForeachFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
@ -68,20 +72,19 @@ public class SplitPerFunderTest {
void test1() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/extendeddump")
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/ext")
.getPath();
SparkDumpFunderResults.main(new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-outputPath", workingDir.toString() + "/split",
"-sourcePath", sourcePath,
"-graphPath", sourcePath
"-sourcePath", sourcePath
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
// FP7 3
// FP7 3 and H2020 3
JavaRDD<CommunityResult> tmp = sc
.textFile(workingDir.toString() + "/split/EC_FP7")
.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
@ -143,11 +146,6 @@ public class SplitPerFunderTest {
.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
Assertions.assertEquals(1, tmp.count());
// CONICYT 0
tmp = sc
.textFile(workingDir.toString() + "/split/CONICYTF")
.map(item -> OBJECT_MAPPER.readValue(item, CommunityResult.class));
Assertions.assertEquals(0, tmp.count());
}
}

125
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/projectssubset/ProjectSubsetTest.java Normal file
View File

@ -0,0 +1,125 @@
package eu.dnetlib.dhp.oa.graph.dump.projectssubset;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.HashMap;
import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.dump.oaf.graph.Project;
public class ProjectSubsetTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static SparkSession spark;
private static Path workingDir;
private static final Logger log = LoggerFactory
.getLogger(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class);
@BeforeAll
public static void beforeAll() throws IOException {
workingDir = Files
.createTempDirectory(
eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName());
log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf();
conf.setAppName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName());
conf.setMaster("local[*]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.toString());
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
spark = SparkSession
.builder()
.appName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
spark.stop();
}
@Test
void testAllNew() throws Exception {
final String projectListPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId")
.getPath();
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/allnew/projects")
.getPath();
spark
.read()
.textFile(projectListPath)
.write()
.mode(SaveMode.Overwrite)
.text(workingDir.toString() + "/projectIds");
ProjectsSubsetSparkJob.main(new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-outputPath", workingDir.toString() + "/projects",
"-sourcePath", sourcePath,
"-projectListPath", workingDir.toString() + "/projectIds"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Project> tmp = sc
.textFile(workingDir.toString() + "/projects")
.map(item -> OBJECT_MAPPER.readValue(item, Project.class));
Assertions.assertEquals(12, tmp.count());
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count());
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count());
Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count());
Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count());
Assertions.assertEquals(1, tmp.filter(p -> p.getId().substring(3, 15).equals("corda_______")).count());
Assertions.assertEquals(40, sc.textFile(workingDir.toString() + "/projectIds").count());
}
@Test
void testMatchOne() throws Exception {
final String projectListPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId")
.getPath();
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/matchOne/projects")
.getPath();
spark
.read()
.textFile(projectListPath)
.write()
.mode(SaveMode.Overwrite)
.text(workingDir.toString() + "/projectIds");
ProjectsSubsetSparkJob.main(new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-outputPath", workingDir.toString() + "/projects",
"-sourcePath", sourcePath,
"-projectListPath", workingDir.toString() + "/projectIds"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Project> tmp = sc
.textFile(workingDir.toString() + "/projects")
.map(item -> OBJECT_MAPPER.readValue(item, Project.class));
Assertions.assertEquals(11, tmp.count());
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count());
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count());
Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count());
Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count());
Assertions.assertEquals(0, tmp.filter(p -> p.getId().substring(3, 15).equals("corda__h2020")).count());
Assertions.assertEquals(39, sc.textFile(workingDir.toString() + "/projectIds").count());
}
}

1
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/communityMapPath/communityMap Normal file
View File

@ -0,0 +1 @@
{"ee":"SDSN - Greece","epos":"EPOS","enrmaps":"Energy Research","fet-h2020":"FET H2020","instruct":"Instruct-Eric","egi":"EGI Federation","euromarine":"Euromarine","covid-19":"COVID-19","dariah":"DARIAH EU","rda":"Research Data Alliance","clarin":"CLARIN","aginfra":"Agricultural and Food Sciences","risis":"RISI","fam":"Fisheries and Aquaculture Management","beopen":"Transport Research","elixir-gr":"ELIXIR GR","fet-fp7":"FET FP7","ifremer":"Ifremer","science-innovation-policy":"Science and Innovation Policy Studies","mes":"European Marine Scinece","oa-pg":"EC Post-Grant Open Access Pilot","ni":"Neuroinformatics","dh-ch":"Digital Humanities and Cultural Heritage"}

0
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/extendeddump/orp → dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/ext/dataset
View File

0
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/ext/otherresearchproduct Normal file
View File

12
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/ext/project Normal file
View File

File diff suppressed because one or more lines are too long

13
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/ext/publication Normal file
View File

File diff suppressed because one or more lines are too long

0
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/ext/software Normal file
View File

32
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/extendeddump/otherresearchproduct Normal file
View File

File diff suppressed because one or more lines are too long

8
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/fundersList/list Normal file
View File

@ -0,0 +1,8 @@
NSF
CIHR
NWO
NHMRC
NIH
MZOS
SNSF
EC

2
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/nomatch/papers.json
View File

File diff suppressed because one or more lines are too long

1
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/funderresource/preparedInfo/resultProject Normal file
View File

@ -0,0 +1 @@
{"resultId":"50|a89337edbe55::43e8b61e5e8d682545cb867be8118585","projectsList":[{"id":"40|aka_________::01bb7b48e29d732a1c7bc5150b9195c4","code":"135027","acronym":null,"title":"Dynamic 3D resolution-enhanced low-coherence interferometric imaging / Consortium: Hi-Lo","funder":{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","fundingStream":null},"provenance":{"provenance":"Harvested","trust":"0.900000000000000022"},"validated":null},{"id":"40|aka_________::9d1af21dbd0f5bc719f71553d19a6b3a","code":"316061","acronym":null,"title":"Finnish Imaging of Degenerative Shoulder Study (FIMAGE): A study on the prevalence of degenerative imaging changes of the shoulder and their relevance to clinical symptoms in the general population.","funder":{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","fundingStream":null},"provenance":{"provenance":"Harvested","trust":"0.900000000000000022"},"validated":null}]}

12
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/allnew/projects Normal file
View File

@ -0,0 +1,12 @@
{"id":"40|aka_________::01bb7b48e29d732a1c7bc5150b9195c4","websiteurl":null,"code":"135027","acronym":null,"title":"Dynamic 3D resolution-enhanced low-coherence interferometric imaging / Consortium: Hi-Lo","startdate":null,"enddate":null,"callidentifier":"Fotoniikka ja modernit kuvantamismenetelmät LT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|aka_________::9d1af21dbd0f5bc719f71553d19a6b3a","websiteurl":null,"code":"316061","acronym":null,"title":"Finnish Imaging of Degenerative Shoulder Study (FIMAGE): A study on the prevalence of degenerative imaging changes of the shoulder and their relevance to clinical symptoms in the general population.","startdate":null,"enddate":null,"callidentifier":"Academy Project Funding TT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|anr_________::1f21edc5c902be305ee47148955c6e50","websiteurl":null,"code":"ANR-17-CE05-0033","acronym":"MOISE","title":"METAL OXIDES AS LOW LOADED NANO-IRIDIUM SUPPORT FOR COMPETITIVE WATER ELECTROLYSIS","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|anr_________::547e78ffdcb7d72a1ef31058dede3a33","websiteurl":null,"code":"ANR-09-SEGI-0005","acronym":"GALAXY","title":"DEVELOPPEMENT COLLABORATIF DE SYSTEMES COMPLEXES SELON UNE APPROCHE GUIDEE PAR LES MODELES","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::838e781a8d479e27a11101421fd8b296","websiteurl":"http://purl.org/au-research/grants/arc/LE0347462","code":"LE0347462","acronym":null,"title":"Femtosecond laser micromachining facility","startdate":"2003-01-01","enddate":"2003-12-31","callidentifier":null,"keywords":"biomedical nanostructures,femtosecond laser machining,laser manufacturing,laser micromachining,microphotonics,photonic bandgap structures","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::a461f180f7b6700c0499d4d3d53e58c7","websiteurl":"http://purl.org/au-research/grants/arc/LP140100567","code":"LP140100567","acronym":null,"title":"Linkage Projects - Grant ID: LP140100567","startdate":"2014-01-01","enddate":"2017-12-31","callidentifier":null,"keywords":"EDUCATIONAL MEASUREMENT; EDUCATIONAL MEASUREMENT; HIGH-STAKES TESTING; HIGH-STAKES TESTING; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Projects","description":"Linkage Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::b46b9e07d4cea67ccf497520a75ad0c8","websiteurl":"http://purl.org/au-research/grants/arc/DP180101235","code":"DP180101235","acronym":null,"title":"Discovery Projects - Grant ID: DP180101235","startdate":"2018-01-01","enddate":"2023-12-31","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Discovery Projects","description":"Discovery Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::c5f86314ce288f91a7f31c219b128fab","websiteurl":"http://purl.org/au-research/grants/arc/LE0989831","code":"LE0989831","acronym":null,"title":"The Australian Music Navigator: research infrastructure for discovering, accessing and analysing Australia's musical landscape","startdate":"2009-01-01","enddate":"2009-12-31","callidentifier":null,"keywords":"database metadata,digital sound,electroacoustic music,film music,music,music information retrieval","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|conicytf____::05539f3427ad605d7c1de0168f3e337f","websiteurl":"http://repositorio.conicyt.cl/handle/10533/183109","code":"3120023","acronym":null,"title":"SYNTHESIS AND STRUCTURE-ACTIVITY RELATIONSHIPS OF HETEROARYLISOQUINOLINE- AND PHENANTHRIDINEQUINONES AS ANTITUMOR AGENTS","startdate":"2011-01-01","enddate":"2014-01-28","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::POSTDOCTORADO","description":"Fondecyt fundings - Fondecyt stream, POSTDOCTORADO"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|conicytf____::96b47b91a6c061e31f626612b1650c03","websiteurl":"http://repositorio.conicyt.cl/handle/10533/163340","code":"1040240","acronym":null,"title":"ESTUDIO TEORICO-EXPERIMENTAL DE LA PERMEACION DE FLUIDOS SUPERCRITICOS Y LA SEPARACION DE MEZCLAS A ALTA PRESION A TRAVES DE MEMBRANAS MICROPOROSAS.","startdate":"2004-01-15","enddate":"2007-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|conicytf____::b122147e0a13f34cdb6311a9d714f9a5","websiteurl":"http://repositorio.conicyt.cl/handle/10533/162452","code":"1020683","acronym":null,"title":"SINTESIS Y CARACTERIZACION DE SALES CUATERNARIAS CON EL ANION CALCOFOSFATO [P2Qy]4- (Q=S,Se;y=6,7) PROPIEDADES FISICAS Y REACCIONES DE INCLUSION.","startdate":"2002-01-15","enddate":"2006-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|corda_______::132bac68f17bb81c451d9071be6e4d6d","websiteurl":null,"code":"628405","acronym":"ANIM","title":"Precisely Defined, Surface-Engineered Nanostructures via Crystallization-Driven Self-Assembly of Linear-Dendritic Block Copolymers","startdate":"2014-05-01","enddate":"2016-04-30","callidentifier":"FP7-PEOPLE-2013-IIF","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"EC","name":"European Commission","jurisdiction":"EU","funding_stream":{"id":"EC::FP7::SP3::PEOPLE","description":"SEVENTH FRAMEWORK PROGRAMME - SP3-People - Marie-Curie Actions"}}],"summary":null,"granted":null,"h2020programme":[]}

12
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/matchOne/projects Normal file
View File

@ -0,0 +1,12 @@
{"id":"40|aka_________::01bb7b48e29d732a1c7bc5150b9195c4","websiteurl":null,"code":"135027","acronym":null,"title":"Dynamic 3D resolution-enhanced low-coherence interferometric imaging / Consortium: Hi-Lo","startdate":null,"enddate":null,"callidentifier":"Fotoniikka ja modernit kuvantamismenetelmät LT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|aka_________::9d1af21dbd0f5bc719f71553d19a6b3a","websiteurl":null,"code":"316061","acronym":null,"title":"Finnish Imaging of Degenerative Shoulder Study (FIMAGE): A study on the prevalence of degenerative imaging changes of the shoulder and their relevance to clinical symptoms in the general population.","startdate":null,"enddate":null,"callidentifier":"Academy Project Funding TT","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"AKA","name":"Academy of Finland","jurisdiction":"FI","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|anr_________::1f21edc5c902be305ee47148955c6e50","websiteurl":null,"code":"ANR-17-CE05-0033","acronym":"MOISE","title":"METAL OXIDES AS LOW LOADED NANO-IRIDIUM SUPPORT FOR COMPETITIVE WATER ELECTROLYSIS","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|anr_________::547e78ffdcb7d72a1ef31058dede3a33","websiteurl":null,"code":"ANR-09-SEGI-0005","acronym":"GALAXY","title":"DEVELOPPEMENT COLLABORATIF DE SYSTEMES COMPLEXES SELON UNE APPROCHE GUIDEE PAR LES MODELES","startdate":null,"enddate":null,"callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ANR","name":"French National Research Agency (ANR)","jurisdiction":"FR","funding_stream":null}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::838e781a8d479e27a11101421fd8b296","websiteurl":"http://purl.org/au-research/grants/arc/LE0347462","code":"LE0347462","acronym":null,"title":"Femtosecond laser micromachining facility","startdate":"2003-01-01","enddate":"2003-12-31","callidentifier":null,"keywords":"biomedical nanostructures,femtosecond laser machining,laser manufacturing,laser micromachining,microphotonics,photonic bandgap structures","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::a461f180f7b6700c0499d4d3d53e58c7","websiteurl":"http://purl.org/au-research/grants/arc/LP140100567","code":"LP140100567","acronym":null,"title":"Linkage Projects - Grant ID: LP140100567","startdate":"2014-01-01","enddate":"2017-12-31","callidentifier":null,"keywords":"EDUCATIONAL MEASUREMENT; EDUCATIONAL MEASUREMENT; HIGH-STAKES TESTING; HIGH-STAKES TESTING; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT; PERFORMANCE ASSESSMENT","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Projects","description":"Linkage Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::b46b9e07d4cea67ccf497520a75ad0c8","websiteurl":"http://purl.org/au-research/grants/arc/DP180101235","code":"DP180101235","acronym":null,"title":"Discovery Projects - Grant ID: DP180101235","startdate":"2018-01-01","enddate":"2023-12-31","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Discovery Projects","description":"Discovery Projects"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|arc_________::c5f86314ce288f91a7f31c219b128fab","websiteurl":"http://purl.org/au-research/grants/arc/LE0989831","code":"LE0989831","acronym":null,"title":"The Australian Music Navigator: research infrastructure for discovering, accessing and analysing Australia's musical landscape","startdate":"2009-01-01","enddate":"2009-12-31","callidentifier":null,"keywords":"database metadata,digital sound,electroacoustic music,film music,music,music information retrieval","openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"ARC","name":"Australian Research Council (ARC)","jurisdiction":"AU","funding_stream":{"id":"ARC::Linkage Infrastructure, Equipment and Facilities","description":"Linkage Infrastructure, Equipment and Facilities"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|conicytf____::05539f3427ad605d7c1de0168f3e337f","websiteurl":"http://repositorio.conicyt.cl/handle/10533/183109","code":"3120023","acronym":null,"title":"SYNTHESIS AND STRUCTURE-ACTIVITY RELATIONSHIPS OF HETEROARYLISOQUINOLINE- AND PHENANTHRIDINEQUINONES AS ANTITUMOR AGENTS","startdate":"2011-01-01","enddate":"2014-01-28","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::POSTDOCTORADO","description":"Fondecyt fundings - Fondecyt stream, POSTDOCTORADO"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|conicytf____::96b47b91a6c061e31f626612b1650c03","websiteurl":"http://repositorio.conicyt.cl/handle/10533/163340","code":"1040240","acronym":null,"title":"ESTUDIO TEORICO-EXPERIMENTAL DE LA PERMEACION DE FLUIDOS SUPERCRITICOS Y LA SEPARACION DE MEZCLAS A ALTA PRESION A TRAVES DE MEMBRANAS MICROPOROSAS.","startdate":"2004-01-15","enddate":"2007-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|conicytf____::b122147e0a13f34cdb6311a9d714f9a5","websiteurl":"http://repositorio.conicyt.cl/handle/10533/162452","code":"1020683","acronym":null,"title":"SINTESIS Y CARACTERIZACION DE SALES CUATERNARIAS CON EL ANION CALCOFOSFATO [P2Qy]4- (Q=S,Se;y=6,7) PROPIEDADES FISICAS Y REACCIONES DE INCLUSION.","startdate":"2002-01-15","enddate":"2006-01-15","callidentifier":null,"keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"CONICYT","name":"Comisión Nacional de Investigación Científica y Tecnológica","jurisdiction":"CL","funding_stream":{"id":"CONICYT::FONDECYT::REGULAR","description":"Fondecyt fundings - Fondecyt stream, REGULAR"}}],"summary":null,"granted":null,"h2020programme":[]}
{"id":"40|corda__h2020::bf5d35ec8d24ae4abfb4a1c6a0af3856","websiteurl":null,"code":"628405","acronym":"ANIM","title":"Precisely Defined, Surface-Engineered Nanostructures via Crystallization-Driven Self-Assembly of Linear-Dendritic Block Copolymers","startdate":"2014-05-01","enddate":"2016-04-30","callidentifier":"FP7-PEOPLE-2013-IIF","keywords":null,"openaccessmandateforpublications":false,"openaccessmandatefordataset":false,"subject":[],"funding":[{"shortName":"EC","name":"European Commission","jurisdiction":"EU","funding_stream":{"id":"EC::FP7::SP3::PEOPLE","description":"SEVENTH FRAMEWORK PROGRAMME - SP3-People - Marie-Curie Actions"}}],"summary":null,"granted":null,"h2020programme":[]}

28
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId Normal file
View File

@ -0,0 +1,28 @@
40|nih_________::4c32cdbc4c9949853f02219fc4780a30
40|nih_________::b485512ef116af73bee79d50c8f9ca01
40|nih_________::b44d9bc8e99d9a0477ac06897e3e9c19
40|nih_________::7d2d2b7d1644a722a6bbcb031d82fec6
40|nsf_________::6b2674b0341e07b818a56c6f0daa2633
40|nih_________::96bb39aecc8f7b9f3b02ed36ef09538b
40|nsf_________::88d92bdf20ec2fac3ed9740f962b4fad
40|nih_________::4bb8c14729a0082378bb04db8321ce14
40|nih_________::08a8eed6c17c6d8e427afcfd29f87c7b
40|nsf_________::c314f3d35af1990121bf5b803937e112
40|nih_________::3ad6a2e6ebd561206f0da69468337f50
40|nih_________::d02c60c65a59629e69a30abcf2ceaed1
40|nih_________::d5a241cc94253feb72181cde15f51e96
40|nih_________::b5df718bbca69af50d4b7213e26af3f0
40|nih_________::bc90893c1be80503578e48f6ef6b7061
40|rcuk________::2c39b38c26c260b14a9816b88c91c132
40|nih_________::ab103ad117cd0579df66f7592a7d4adf
40|nih_________::147aa6ad8bd201e2a02c7b6cc3f68348
40|corda__h2020::bf5d35ec8d24ae4abfb4a1c6a0af3856
40|nih_________::b8083208156f2764d07c736ba9b49dd2
40|nih_________::f4d1e0aece0e6a9eff8d054c28e082db
40|nsf_________::56297da8b472a4be8ac3f09af813c9f6
40|nsf_________::6b6dc3398eeebb3de1ab66e6eb8c5cb3
40|nih_________::93289a36ebffb0bee3d6b01c6fc0a3d6
40|nih_________::6c3b00dd4ae9d43d6630ff18f189ebae
40|nih_________::1d983a87768f13bc8377b1b7d17290a2
40|nih_________::c3b56e91859b114644c1403e892eb80f
40|rcuk________::c1e15330fc7956063652f9c06e584548