forked from D-Net/dnet-hadoop
Merge pull request 'Extract Information from Transformative Agreement' (#371) from transformativeagreement into beta
Reviewed-on: D-Net/dnet-hadoop#371
This commit is contained in:
commit
e0c315b07b
|
|
@ -64,6 +64,9 @@ public class PrepareAffiliationRelations implements Serializable {
|
|||
final String pubmedInputPath = parser.get("pubmedInputPath");
|
||||
log.info("pubmedInputPath: {}", pubmedInputPath);
|
||||
|
||||
final String openapcInputPath = parser.get("openapcInputPath");
|
||||
log.info("openapcInputPath: {}", openapcInputPath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
|
|
@ -85,8 +88,14 @@ public class PrepareAffiliationRelations implements Serializable {
|
|||
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
|
||||
spark, pubmedInputPath, collectedFromPubmed);
|
||||
|
||||
List<KeyValue> collectedFromOpenAPC = OafMapperUtils
|
||||
.listKeyValues(ModelConstants.OPEN_APC_ID, "OpenAPC");
|
||||
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelations(
|
||||
spark, openapcInputPath, collectedFromOpenAPC);
|
||||
|
||||
crossrefRelations
|
||||
.union(pubmedRelations)
|
||||
.union(openAPCRelations)
|
||||
.saveAsHadoopFile(
|
||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,195 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.transformativeagreement;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.Serializable;
|
||||
import java.util.*;
|
||||
|
||||
import org.apache.commons.cli.ParseException;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.hadoop.io.compress.GzipCodec;
|
||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.function.FilterFunction;
|
||||
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.transformativeagreement.model.TransformativeAgreementModel;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Country;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.*;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class CreateActionSetSparkJob implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
private static final String IREL_PROJECT = "40|100018998___::1e5e62235d094afd01cd56e65112fc63";
|
||||
private static final String TRANSFORMATIVE_AGREEMENT = "openapc::transformativeagreement";
|
||||
|
||||
public static void main(final String[] args) throws IOException, ParseException {
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
CreateActionSetSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/transformativeagreement/as_parameters.json"))));
|
||||
|
||||
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("inputPath");
|
||||
log.info("inputPath {}", inputPath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> createActionSet(spark, inputPath, outputPath));
|
||||
|
||||
}
|
||||
|
||||
private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
|
||||
JavaRDD<AtomicAction> relations = spark
|
||||
.read()
|
||||
.textFile(inputPath)
|
||||
.map(
|
||||
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
|
||||
.readValue(value, TransformativeAgreementModel.class),
|
||||
Encoders.bean(TransformativeAgreementModel.class))
|
||||
.flatMap(
|
||||
(FlatMapFunction<TransformativeAgreementModel, Relation>) value -> createRelation(
|
||||
value)
|
||||
.iterator(),
|
||||
Encoders.bean(Relation.class))
|
||||
.filter((FilterFunction<Relation>) Objects::nonNull)
|
||||
.toJavaRDD()
|
||||
.map(p -> new AtomicAction(p.getClass(), p));
|
||||
//TODO relations in stand-by waiting to know if we need to create them or not In case we need just make a union before saving the sequence file
|
||||
spark
|
||||
.read()
|
||||
.textFile(inputPath)
|
||||
.map(
|
||||
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
|
||||
.readValue(value, TransformativeAgreementModel.class),
|
||||
Encoders.bean(TransformativeAgreementModel.class))
|
||||
.map(
|
||||
(MapFunction<TransformativeAgreementModel, Result>) value -> createResult(
|
||||
value),
|
||||
Encoders.bean(Result.class))
|
||||
.filter((FilterFunction<Result>) r -> r != null)
|
||||
.toJavaRDD()
|
||||
.map(p -> new AtomicAction(p.getClass(), p))
|
||||
.mapToPair(
|
||||
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
|
||||
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
|
||||
.saveAsHadoopFile(
|
||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||
|
||||
}
|
||||
|
||||
private static Result createResult(TransformativeAgreementModel value) {
|
||||
Result r = new Result();
|
||||
r
|
||||
.setId(
|
||||
"50|doi_________::"
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi())));
|
||||
r.setTransformativeAgreement(value.getAgreement());
|
||||
Country country = new Country();
|
||||
country.setClassid(value.getCountry());
|
||||
country.setClassname(value.getCountry());
|
||||
country
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, ModelConstants.SYSIMPORT_ACTIONSET, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
"openapc::transformativeagreement",
|
||||
"Harvested from Trnasformative Agreement file from OpenAPC",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"));
|
||||
country.setSchemeid(ModelConstants.DNET_COUNTRY_TYPE);
|
||||
country.setSchemename(ModelConstants.DNET_COUNTRY_TYPE);
|
||||
r.setCountry(Arrays.asList(country));
|
||||
return r;
|
||||
}
|
||||
|
||||
private static List<Relation> createRelation(TransformativeAgreementModel value) {
|
||||
|
||||
List<Relation> relationList = new ArrayList<>();
|
||||
|
||||
if (value.getAgreement().startsWith("IReL")) {
|
||||
String paper;
|
||||
|
||||
paper = "50|doi_________::"
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi()));
|
||||
|
||||
relationList
|
||||
.add(
|
||||
getRelation(
|
||||
paper,
|
||||
IREL_PROJECT, ModelConstants.IS_PRODUCED_BY));
|
||||
|
||||
relationList.add(getRelation(IREL_PROJECT, paper, ModelConstants.PRODUCES));
|
||||
}
|
||||
return relationList;
|
||||
}
|
||||
|
||||
public static Relation getRelation(
|
||||
String source,
|
||||
String target,
|
||||
String relClass) {
|
||||
|
||||
return OafMapperUtils
|
||||
.getRelation(
|
||||
source,
|
||||
target,
|
||||
ModelConstants.RESULT_PROJECT,
|
||||
ModelConstants.OUTCOME,
|
||||
relClass,
|
||||
Arrays
|
||||
.asList(
|
||||
OafMapperUtils.keyValue(ModelConstants.OPEN_APC_ID, ModelConstants.OPEN_APC_NAME)),
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
TRANSFORMATIVE_AGREEMENT, "Transformative Agreement",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"),
|
||||
null);
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,51 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.transformativeagreement.model;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 18/12/23
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
|
||||
public class TransformativeAgreementModel implements Serializable {
|
||||
private String institution;
|
||||
private String doi;
|
||||
private String agreement;
|
||||
private String country;
|
||||
|
||||
public String getCountry() {
|
||||
return country;
|
||||
}
|
||||
|
||||
public void setCountry(String country) {
|
||||
this.country = country;
|
||||
}
|
||||
|
||||
public String getInstitution() {
|
||||
return institution;
|
||||
}
|
||||
|
||||
public void setInstitution(String institution) {
|
||||
this.institution = institution;
|
||||
}
|
||||
|
||||
public String getDoi() {
|
||||
return doi;
|
||||
}
|
||||
|
||||
public void setDoi(String doi) {
|
||||
this.doi = doi;
|
||||
}
|
||||
|
||||
public String getAgreement() {
|
||||
return agreement;
|
||||
}
|
||||
|
||||
public void setAgreement(String agreement) {
|
||||
this.agreement = agreement;
|
||||
}
|
||||
}
|
||||
|
|
@ -17,6 +17,12 @@
|
|||
"paramDescription": "the path to get the input data from Pubmed",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "oip",
|
||||
"paramLongName": "openapcInputPath",
|
||||
"paramDescription": "the path to get the input data from OpenAPC",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "o",
|
||||
"paramLongName": "outputPath",
|
||||
|
|
|
|||
|
|
@ -31,6 +31,7 @@ spark2SqlQueryExecutionListeners=com.cloudera.spark.lineage.NavigatorQueryListen
|
|||
# The following is needed as a property of a workflow
|
||||
oozie.wf.application.path=${oozieTopWfApplicationPath}
|
||||
|
||||
crossrefInputPath=/data/bip-affiliations/data.json
|
||||
crossrefInputPath=/data/bip-affiliations/crossref-data.json
|
||||
pubmedInputPath=/data/bip-affiliations/pubmed-data.json
|
||||
openapcInputPath=/data/bip-affiliations/openapc-data.json
|
||||
outputPath=/tmp/crossref-affiliations-output-v5
|
||||
|
|
|
|||
|
|
@ -9,6 +9,10 @@
|
|||
<name>pubmedInputPath</name>
|
||||
<description>the path where to find the inferred affiliation relations from Pubmed</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>openapcInputPath</name>
|
||||
<description>the path where to find the inferred affiliation relations from OpenAPC</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the path where to store the actionset</description>
|
||||
|
|
@ -102,6 +106,7 @@
|
|||
</spark-opts>
|
||||
<arg>--crossrefInputPath</arg><arg>${crossrefInputPath}</arg>
|
||||
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
|
||||
<arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
|
|
|
|||
|
|
@ -0,0 +1,20 @@
|
|||
[
|
||||
{
|
||||
"paramName": "ip",
|
||||
"paramLongName": "inputPath",
|
||||
"paramDescription": "the zipped opencitations file",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "op",
|
||||
"paramLongName": "outputPath",
|
||||
"paramDescription": "the working path",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "issm",
|
||||
"paramLongName": "isSparkSessionManaged",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
}
|
||||
]
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
[
|
||||
|
||||
{
|
||||
"paramName": "issm",
|
||||
"paramLongName": "isSparkSessionManaged",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "d",
|
||||
"paramLongName": "delimiter",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "op",
|
||||
"paramLongName": "outputPath",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "if",
|
||||
"paramLongName": "inputFile",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": true
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
<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>oozie.action.sharelib.for.spark</name>
|
||||
<value>spark2</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>hive_metastore_uris</name>
|
||||
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2YarnHistoryServerAddress</name>
|
||||
<value>http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2ExtraListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2SqlQueryExecutionListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorNumber</name>
|
||||
<value>4</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2EventLogDir</name>
|
||||
<value>/user/spark/spark2ApplicationHistory</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkDriverMemory</name>
|
||||
<value>15G</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorMemory</name>
|
||||
<value>6G</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorCores</name>
|
||||
<value>1</value>
|
||||
</property>
|
||||
</configuration>
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
#!/bin/bash
|
||||
curl -L $1 | hdfs dfs -put - $2
|
||||
|
|
@ -0,0 +1,82 @@
|
|||
<workflow-app name="Transfomative Agreement Integration" xmlns="uri:oozie:workflow:0.5">
|
||||
|
||||
<global>
|
||||
<job-tracker>${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="resume_from"/>
|
||||
|
||||
<decision name="resume_from">
|
||||
<switch>
|
||||
<case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
|
||||
<default to="create_actionset"/> <!-- first action to be done when downloadDump is to be performed -->
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="download">
|
||||
<shell xmlns="uri:oozie:shell-action:0.2">
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>mapred.job.queue.name</name>
|
||||
<value>${queueName}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<exec>download.sh</exec>
|
||||
<argument>${inputFile}</argument>
|
||||
<argument>${workingDir}/transformativeagreement/transformativeAgreement.json</argument>
|
||||
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
|
||||
<file>download.sh</file>
|
||||
<capture-output/>
|
||||
</shell>
|
||||
<ok to="create_actionset"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="create_actionset">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Produces the AS for the Transformative Agreement</name>
|
||||
<class>eu.dnetlib.dhp.actionmanager.transformativeagreement.CreateActionSetSparkJob</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--inputPath</arg><arg>${workingDir}/transformativeagreement/</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
||||
|
|
@ -78,10 +78,6 @@ public class PrepareAffiliationRelationsTest {
|
|||
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
|
||||
.getPath();
|
||||
|
||||
String pubmedAffiliationRelationsPath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
|
||||
.getPath();
|
||||
|
||||
String outputPath = workingDir.toString() + "/actionSet";
|
||||
|
||||
PrepareAffiliationRelations
|
||||
|
|
@ -89,7 +85,8 @@ public class PrepareAffiliationRelationsTest {
|
|||
new String[] {
|
||||
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"-crossrefInputPath", crossrefAffiliationRelationPath,
|
||||
"-pubmedInputPath", pubmedAffiliationRelationsPath,
|
||||
"-pubmedInputPath", crossrefAffiliationRelationPath,
|
||||
"-openapcInputPath", crossrefAffiliationRelationPath,
|
||||
"-outputPath", outputPath
|
||||
});
|
||||
|
||||
|
|
@ -106,7 +103,7 @@ public class PrepareAffiliationRelationsTest {
|
|||
// );
|
||||
// }
|
||||
// count the number of relations
|
||||
assertEquals(40, tmp.count());
|
||||
assertEquals(60, tmp.count());
|
||||
|
||||
Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
|
||||
dataset.createOrReplaceTempView("result");
|
||||
|
|
@ -117,7 +114,7 @@ public class PrepareAffiliationRelationsTest {
|
|||
// verify that we have equal number of bi-directional relations
|
||||
Assertions
|
||||
.assertEquals(
|
||||
20, execVerification
|
||||
30, execVerification
|
||||
.filter(
|
||||
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
|
||||
.collectAsList()
|
||||
|
|
@ -125,7 +122,7 @@ public class PrepareAffiliationRelationsTest {
|
|||
|
||||
Assertions
|
||||
.assertEquals(
|
||||
20, execVerification
|
||||
30, execVerification
|
||||
.filter(
|
||||
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
|
||||
.collectAsList()
|
||||
|
|
|
|||
|
|
@ -0,0 +1,324 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.transformativeagreement;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
|
||||
import org.apache.commons.io.FileUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.junit.jupiter.api.AfterAll;
|
||||
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.actionmanager.opencitations.CreateActionSetSparkJob;
|
||||
import eu.dnetlib.dhp.actionmanager.opencitations.CreateOpenCitationsASTest;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 13/02/24
|
||||
*/
|
||||
public class CreateTAActionSetTest {
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
private static SparkSession spark;
|
||||
|
||||
private static Path workingDir;
|
||||
private static final Logger log = LoggerFactory
|
||||
.getLogger(CreateOpenCitationsASTest.class);
|
||||
|
||||
@BeforeAll
|
||||
public static void beforeAll() throws IOException {
|
||||
workingDir = Files
|
||||
.createTempDirectory(CreateTAActionSetTest.class.getSimpleName());
|
||||
log.info("using work dir {}", workingDir);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.setAppName(CreateTAActionSetTest.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(CreateTAActionSetTest.class.getSimpleName())
|
||||
.config(conf)
|
||||
.getOrCreate();
|
||||
}
|
||||
|
||||
@AfterAll
|
||||
public static void afterAll() throws IOException {
|
||||
FileUtils.deleteDirectory(workingDir.toFile());
|
||||
spark.stop();
|
||||
}
|
||||
|
||||
@Test
|
||||
void createActionSet() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/transformativeagreement/facts.json")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.transformativeagreement.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet1"
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testNumberofRelations2() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet2"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet2", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
assertEquals(23, tmp.count());
|
||||
|
||||
// tmp.foreach(r -> System.out.println(OBJECT_MAPPER.writeValueAsString(r)));
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsCollectedFrom() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet3"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet3", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals(ModelConstants.OPENOCITATIONS_NAME, r.getCollectedfrom().get(0).getValue());
|
||||
assertEquals(ModelConstants.OPENOCITATIONS_ID, r.getCollectedfrom().get(0).getKey());
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsDataInfo() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet4"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet4", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals(false, r.getDataInfo().getInferred());
|
||||
assertEquals(false, r.getDataInfo().getDeletedbyinference());
|
||||
assertEquals("0.91", r.getDataInfo().getTrust());
|
||||
assertEquals(
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob.OPENCITATIONS_CLASSID,
|
||||
r.getDataInfo().getProvenanceaction().getClassid());
|
||||
assertEquals(
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob.OPENCITATIONS_CLASSNAME,
|
||||
r.getDataInfo().getProvenanceaction().getClassname());
|
||||
assertEquals(ModelConstants.DNET_PROVENANCE_ACTIONS, r.getDataInfo().getProvenanceaction().getSchemeid());
|
||||
assertEquals(ModelConstants.DNET_PROVENANCE_ACTIONS, r.getDataInfo().getProvenanceaction().getSchemename());
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsSemantics() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet5"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet5", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals("citation", r.getSubRelType());
|
||||
assertEquals("resultResult", r.getRelType());
|
||||
});
|
||||
assertEquals(23, tmp.filter(r -> r.getRelClass().equals("Cites")).count());
|
||||
assertEquals(0, tmp.filter(r -> r.getRelClass().equals("IsCitedBy")).count());
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsSourceTargetPrefix() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet6"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet6", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals("50|doi_________::", r.getSource().substring(0, 17));
|
||||
assertEquals("50|doi_________::", r.getTarget().substring(0, 17));
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsSourceTargetCouple() throws Exception {
|
||||
final String doi1 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-015-3684-x"));
|
||||
final String doi2 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1111/j.1551-2916.2008.02408.x"));
|
||||
final String doi3 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-014-2114-9"));
|
||||
final String doi4 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/j.ceramint.2013.09.069"));
|
||||
final String doi5 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-009-9913-4"));
|
||||
final String doi6 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/0038-1098(72)90370-5"));
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet7"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet7", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
JavaRDD<Relation> check = tmp.filter(r -> r.getSource().equals(doi1) || r.getTarget().equals(doi1));
|
||||
|
||||
assertEquals(5, check.count());
|
||||
|
||||
// check.foreach(r -> {
|
||||
// if (r.getSource().equals(doi2) || r.getSource().equals(doi3) || r.getSource().equals(doi4) ||
|
||||
// r.getSource().equals(doi5) || r.getSource().equals(doi6)) {
|
||||
// assertEquals(ModelConstants.IS_CITED_BY, r.getRelClass());
|
||||
// assertEquals(doi1, r.getTarget());
|
||||
// }
|
||||
// });
|
||||
|
||||
assertEquals(5, check.filter(r -> r.getSource().equals(doi1)).count());
|
||||
check.filter(r -> r.getSource().equals(doi1)).foreach(r -> assertEquals(ModelConstants.CITES, r.getRelClass()));
|
||||
|
||||
}
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
2
pom.xml
2
pom.xml
|
|
@ -888,7 +888,7 @@
|
|||
<mockito-core.version>3.3.3</mockito-core.version>
|
||||
<mongodb.driver.version>3.4.2</mongodb.driver.version>
|
||||
<vtd.version>[2.12,3.0)</vtd.version>
|
||||
<dhp-schemas.version>[4.17.2]</dhp-schemas.version>
|
||||
<dhp-schemas.version>[5.17.3]</dhp-schemas.version>
|
||||
<dnet-actionmanager-api.version>[4.0.3]</dnet-actionmanager-api.version>
|
||||
<dnet-actionmanager-common.version>[6.0.5]</dnet-actionmanager-common.version>
|
||||
<dnet-openaire-broker-common.version>[3.1.6]</dnet-openaire-broker-common.version>
|
||||
|
|
|
|||
Loading…
Reference in New Issue