forked from D-Net/dnet-hadoop
OpenCitations: creation of AS from OC
This commit is contained in:
parent
eedf7c3310
commit
5ec69889db
|
|
@ -10,6 +10,7 @@ import org.apache.hadoop.fs.FileSystem;
|
|||
import org.apache.hadoop.fs.Path;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import com.opencsv.bean.CsvToBeanBuilder;
|
||||
|
||||
public class GetCSV {
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,178 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||
|
||||
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.mapred.SequenceFileOutputFormat;
|
||||
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.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.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.*;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class CreateActionSetSparkJob implements Serializable {
|
||||
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
|
||||
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
|
||||
private static final String ID_PREFIX = "50|doi_________::";
|
||||
private static final String TRUST = "0.91";
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
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/opencitations/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.toString());
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}", outputPath);
|
||||
|
||||
final boolean shouldDuplicateRels = Boolean.valueOf(parser.get("shouldDuplicateRels"));
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
extractContent(spark, inputPath, outputPath, shouldDuplicateRels);
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
private static void extractContent(SparkSession spark, String inputPath, String outputPath,
|
||||
boolean shouldDuplicateRels) {
|
||||
spark
|
||||
.sqlContext()
|
||||
.createDataset(spark.sparkContext().textFile(inputPath + "/*", 6000), Encoders.STRING())
|
||||
.flatMap(
|
||||
(FlatMapFunction<String, Relation>) value -> createRelation(value, shouldDuplicateRels).iterator(),
|
||||
Encoders.bean(Relation.class))
|
||||
.filter((FilterFunction<Relation>) value -> value != 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);
|
||||
|
||||
}
|
||||
|
||||
private static List<Relation> createRelation(String value, boolean duplicate) {
|
||||
String[] line = value.split(",");
|
||||
if (!line[1].startsWith("10.")) {
|
||||
return new ArrayList<>();
|
||||
}
|
||||
List<Relation> relationList = new ArrayList<>();
|
||||
|
||||
String citing = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[1]));
|
||||
final String cited = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[2]));
|
||||
|
||||
relationList
|
||||
.addAll(
|
||||
getRelations(
|
||||
citing,
|
||||
cited));
|
||||
|
||||
if (duplicate && line[1].endsWith(".refs")) {
|
||||
citing = ID_PREFIX + IdentifierFactory
|
||||
.md5(CleaningFunctions.normalizePidValue("doi", line[1].substring(0, line[1].indexOf(".refs"))));
|
||||
relationList.addAll(getRelations(citing, cited));
|
||||
}
|
||||
|
||||
return relationList;
|
||||
}
|
||||
|
||||
private static Collection<Relation> getRelations(String citing, String cited) {
|
||||
|
||||
return Arrays
|
||||
.asList(
|
||||
getRelation(citing, cited, ModelConstants.CITES),
|
||||
getRelation(cited, citing, ModelConstants.IS_CITED_BY));
|
||||
}
|
||||
|
||||
public static Relation getRelation(
|
||||
String source,
|
||||
String target,
|
||||
String relclass) {
|
||||
Relation r = new Relation();
|
||||
r.setCollectedfrom(getCollectedFrom());
|
||||
r.setSource(source);
|
||||
r.setTarget(target);
|
||||
r.setRelClass(relclass);
|
||||
r.setRelType(ModelConstants.RESULT_RESULT);
|
||||
r.setSubRelType(ModelConstants.CITATION);
|
||||
r
|
||||
.setDataInfo(
|
||||
getDataInfo());
|
||||
return r;
|
||||
}
|
||||
|
||||
public static List<KeyValue> getCollectedFrom() {
|
||||
KeyValue kv = new KeyValue();
|
||||
kv.setKey(ModelConstants.OPENOCITATIONS_ID);
|
||||
kv.setValue(ModelConstants.OPENOCITATIONS_NAME);
|
||||
|
||||
return Arrays.asList(kv);
|
||||
}
|
||||
|
||||
public static DataInfo getDataInfo() {
|
||||
DataInfo di = new DataInfo();
|
||||
di.setInferred(false);
|
||||
di.setDeletedbyinference(false);
|
||||
di.setTrust(TRUST);
|
||||
|
||||
di
|
||||
.setProvenanceaction(
|
||||
getQualifier(OPENCITATIONS_CLASSID, OPENCITATIONS_CLASSNAME, ModelConstants.DNET_PROVENANCE_ACTIONS));
|
||||
return di;
|
||||
}
|
||||
|
||||
public static Qualifier getQualifier(String class_id, String class_name,
|
||||
String qualifierSchema) {
|
||||
Qualifier pa = new Qualifier();
|
||||
pa.setClassid(class_id);
|
||||
pa.setClassname(class_name);
|
||||
pa.setSchemeid(qualifierSchema);
|
||||
pa.setSchemename(qualifierSchema);
|
||||
return pa;
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -0,0 +1,176 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||
|
||||
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.mapred.SequenceFileOutputFormat;
|
||||
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.sql.Encoders;
|
||||
import org.apache.spark.sql.SaveMode;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
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.DataInfo;
|
||||
import eu.dnetlib.dhp.schema.oaf.KeyValue;
|
||||
import eu.dnetlib.dhp.schema.oaf.Qualifier;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class CreateRelationsJson implements Serializable {
|
||||
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
|
||||
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
|
||||
private static final String ID_PREFIX = "50|doi_________::";
|
||||
private static final String TRUST = "0.91";
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CreateRelationsJson.class);
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static void main(final String[] args) throws IOException, ParseException {
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
CreateRelationsJson.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/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.toString());
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
extractContent(spark, inputPath, outputPath);
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
private static void extractContent(SparkSession spark, String inputPath, String outputPath) {
|
||||
spark
|
||||
.sqlContext()
|
||||
.createDataset(spark.sparkContext().textFile(inputPath + "/*", 6000), Encoders.STRING())
|
||||
.flatMap(
|
||||
(FlatMapFunction<String, Relation>) value -> createRelation(value).iterator(),
|
||||
Encoders.bean(Relation.class))
|
||||
.filter((FilterFunction<Relation>) value -> value != null)
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath);
|
||||
|
||||
}
|
||||
|
||||
private static List<Relation> createRelation(String value) {
|
||||
String[] line = value.split(",");
|
||||
if (!line[1].startsWith("10.")) {
|
||||
return new ArrayList<>();
|
||||
}
|
||||
List<Relation> relationList = new ArrayList<>();
|
||||
|
||||
String citing = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[1]));
|
||||
final String cited = ID_PREFIX + IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", line[2]));
|
||||
|
||||
relationList
|
||||
.addAll(
|
||||
getRelations(
|
||||
citing,
|
||||
cited));
|
||||
|
||||
if (line[1].endsWith(".refs")) {
|
||||
citing = ID_PREFIX + IdentifierFactory
|
||||
.md5(CleaningFunctions.normalizePidValue("doi", line[1].substring(0, line[1].indexOf(".refs"))));
|
||||
relationList.addAll(getRelations(citing, cited));
|
||||
}
|
||||
|
||||
return relationList;
|
||||
}
|
||||
|
||||
private static Collection<Relation> getRelations(String citing, String cited) {
|
||||
|
||||
return Arrays
|
||||
.asList(
|
||||
getRelation(citing, cited, ModelConstants.CITES),
|
||||
getRelation(cited, citing, ModelConstants.IS_CITED_BY));
|
||||
}
|
||||
|
||||
public static Relation getRelation(
|
||||
String source,
|
||||
String target,
|
||||
String relclass) {
|
||||
Relation r = new Relation();
|
||||
r.setCollectedfrom(getCollectedFrom());
|
||||
r.setSource(source);
|
||||
r.setTarget(target);
|
||||
r.setRelClass(relclass);
|
||||
r.setRelType(ModelConstants.RESULT_RESULT);
|
||||
r.setSubRelType(ModelConstants.CITATION);
|
||||
r
|
||||
.setDataInfo(
|
||||
getDataInfo());
|
||||
return r;
|
||||
}
|
||||
|
||||
public static List<KeyValue> getCollectedFrom() {
|
||||
KeyValue kv = new KeyValue();
|
||||
kv.setKey(ModelConstants.OPENOCITATIONS_ID);
|
||||
kv.setValue(ModelConstants.OPENOCITATIONS_NAME);
|
||||
|
||||
return Arrays.asList(kv);
|
||||
}
|
||||
|
||||
public static DataInfo getDataInfo() {
|
||||
DataInfo di = new DataInfo();
|
||||
di.setInferred(false);
|
||||
di.setDeletedbyinference(false);
|
||||
di.setTrust(TRUST);
|
||||
|
||||
di
|
||||
.setProvenanceaction(
|
||||
getQualifier(OPENCITATIONS_CLASSID, OPENCITATIONS_CLASSNAME, ModelConstants.DNET_PROVENANCE_ACTIONS));
|
||||
return di;
|
||||
}
|
||||
|
||||
public static Qualifier getQualifier(String class_id, String class_name,
|
||||
String qualifierSchema) {
|
||||
Qualifier pa = new Qualifier();
|
||||
pa.setClassid(class_id);
|
||||
pa.setClassname(class_name);
|
||||
pa.setSchemeid(qualifierSchema);
|
||||
pa.setSchemename(qualifierSchema);
|
||||
return pa;
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -1,63 +0,0 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||
|
||||
import java.io.BufferedOutputStream;
|
||||
import java.net.URI;
|
||||
import java.util.zip.GZIPOutputStream;
|
||||
|
||||
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
|
||||
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
|
||||
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FSDataInputStream;
|
||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.mortbay.log.Log;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
|
||||
public class ExtractOpenCitationRefs {
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
ExtractOpenCitationRefs.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/a/ccionmanager/opencitations/opencitations_parameters.json")));
|
||||
parser.parseArgument(args);
|
||||
final String hdfsServerUri = parser.get("hdfsServerUri");
|
||||
final String workingPath = hdfsServerUri.concat(parser.get("workingPath"));
|
||||
final String outputPath = parser.get("outputPath");
|
||||
final String opencitationFile = parser.get("opencitationFile");
|
||||
|
||||
Path hdfsreadpath = new Path(workingPath.concat("/").concat(opencitationFile));
|
||||
Configuration conf = new Configuration();
|
||||
conf.set("fs.defaultFS", workingPath);
|
||||
conf.set("fs.hdfs.impl", org.apache.hadoop.hdfs.DistributedFileSystem.class.getName());
|
||||
conf.set("fs.file.impl", org.apache.hadoop.fs.LocalFileSystem.class.getName());
|
||||
FileSystem fs = FileSystem.get(URI.create(workingPath), conf);
|
||||
FSDataInputStream crossrefFileStream = fs.open(hdfsreadpath);
|
||||
try (TarArchiveInputStream tais = new TarArchiveInputStream(
|
||||
new GzipCompressorInputStream(crossrefFileStream))) {
|
||||
TarArchiveEntry entry = null;
|
||||
while ((entry = tais.getNextTarEntry()) != null) {
|
||||
if (!entry.isDirectory()) {
|
||||
try (
|
||||
FSDataOutputStream out = fs
|
||||
.create(new Path(outputPath.concat(entry.getName()).concat(".gz")));
|
||||
GZIPOutputStream gzipOs = new GZIPOutputStream(new BufferedOutputStream(out))) {
|
||||
|
||||
IOUtils.copy(tais, gzipOs);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
}
|
||||
}
|
||||
Log.info("Crossref dump reading completed");
|
||||
|
||||
}
|
||||
}
|
||||
|
|
@ -36,8 +36,8 @@ public class GetOpenCitationsRefs implements Serializable {
|
|||
|
||||
parser.parseArgument(args);
|
||||
|
||||
final String inputFile = parser.get("inputFile");
|
||||
log.info("inputFile {}", inputFile);
|
||||
final String[] inputFile = parser.get("inputFile").split(";");
|
||||
log.info("inputFile {}", inputFile.toString());
|
||||
|
||||
final String workingPath = parser.get("workingPath");
|
||||
log.info("workingPath {}", workingPath);
|
||||
|
|
@ -45,14 +45,17 @@ public class GetOpenCitationsRefs implements Serializable {
|
|||
final String hdfsNameNode = parser.get("hdfsNameNode");
|
||||
log.info("hdfsNameNode {}", hdfsNameNode);
|
||||
|
||||
|
||||
|
||||
Configuration conf = new Configuration();
|
||||
conf.set("fs.defaultFS", hdfsNameNode);
|
||||
|
||||
FileSystem fileSystem = FileSystem.get(conf);
|
||||
|
||||
new GetOpenCitationsRefs().doExtract(inputFile, workingPath, fileSystem);
|
||||
GetOpenCitationsRefs ocr = new GetOpenCitationsRefs();
|
||||
|
||||
for (String file : inputFile) {
|
||||
ocr.doExtract(workingPath + "/Original/" + file, workingPath, fileSystem);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
private void doExtract(String inputFile, String workingPath, FileSystem fileSystem)
|
||||
|
|
|
|||
|
|
@ -0,0 +1,5 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||
|
||||
public class OpenCitationModel {
|
||||
}
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
[
|
||||
{
|
||||
"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
|
||||
}, {
|
||||
"paramName": "sdr",
|
||||
"paramLongName": "shouldDuplicateRels",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
}
|
||||
]
|
||||
|
|
@ -1,2 +1,2 @@
|
|||
#!/bin/bash
|
||||
wget -i $1
|
||||
for file in $(echo $1 | tr ";" "\n"); do curl -L $(echo $file | cut -d '@' -f 1 ) | hdfs dfs -put - $2/$(echo $file | cut -d '@' -f 2) ; done;
|
||||
|
|
@ -20,9 +20,16 @@
|
|||
</configuration>
|
||||
</global>
|
||||
|
||||
<start to="resume_from"/>
|
||||
|
||||
<decision name="resume_from">
|
||||
<switch>
|
||||
<case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
|
||||
<case to="extract">${wf:conf('resumeFrom') eq 'ExtractContent'}</case>
|
||||
<default to="create_actionset"/> <!-- first action to be done when downloadDump is to be performed -->
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<start to="download"/>
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
|
@ -37,15 +44,13 @@
|
|||
</property>
|
||||
</configuration>
|
||||
<exec>download.sh</exec>
|
||||
<argument>${url}</argument>
|
||||
<argument>${crossrefDumpPath}</argument>
|
||||
<argument>${crossrefdumpfilename}</argument>
|
||||
<argument>${crossrefdumptoken}</argument>
|
||||
<argument>${filelist}</argument>
|
||||
<argument>${workingPath}/Original</argument>
|
||||
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
|
||||
<file>download.sh</file>
|
||||
<capture-output/>
|
||||
</shell>
|
||||
<ok to="ImportCrossRef"/>
|
||||
<ok to="extract"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<action name="extract">
|
||||
|
|
@ -53,12 +58,34 @@
|
|||
<main-class>eu.dnetlib.dhp.actionmanager.opencitations.GetOpenCitationsRefs</main-class>
|
||||
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--inputFile</arg><arg>${inputFile}</arg>
|
||||
<arg>--workingPath</arg><arg>${workingDir}/OpenCitations</arg>
|
||||
<arg>--workingPath</arg><arg>${workingPath}</arg>
|
||||
</java>
|
||||
<ok to="End"/>
|
||||
<ok to="create_actionset"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="create_actionset">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Produces the AS for OC</name>
|
||||
<class>eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob</class>
|
||||
<jar>dhp-aggregation-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--inputPath</arg><arg>${workingPath}/COCI</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
||||
|
|
@ -0,0 +1,301 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.opencitations;
|
||||
|
||||
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.Dataset;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.Row;
|
||||
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.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Publication;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
|
||||
|
||||
public class CreateOpenCitationsASTest {
|
||||
|
||||
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(CreateOpenCitationsASTest.class.getSimpleName());
|
||||
log.info("using work dir {}", workingDir);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.setAppName(CreateOpenCitationsASTest.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(CreateOpenCitationsASTest.class.getSimpleName())
|
||||
.config(conf)
|
||||
.getOrCreate();
|
||||
}
|
||||
|
||||
@AfterAll
|
||||
public static void afterAll() throws IOException {
|
||||
FileUtils.deleteDirectory(workingDir.toFile());
|
||||
spark.stop();
|
||||
}
|
||||
|
||||
@Test
|
||||
void testNumberofRelations() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
assertEquals(60, 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/inputFiles")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet", 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/inputFiles")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet", 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(
|
||||
CreateActionSetSparkJob.OPENCITATIONS_CLASSID, r.getDataInfo().getProvenanceaction().getClassid());
|
||||
assertEquals(
|
||||
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/inputFiles")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet", 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(30, tmp.filter(r -> r.getRelClass().equals("Cites")).count());
|
||||
assertEquals(30, tmp.filter(r -> r.getRelClass().equals("IsCitedBy")).count());
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsSourceTargetPrefix() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/inputFiles")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet", 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/inputFiles")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet", 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(10, 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()));
|
||||
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
oci,citing,cited,creation,timespan,journal_sc,author_sc
|
||||
02001000007362801000805046300010563030608046333-0200101010136193701050501630209010637020000083700020400083733,10.1007/s10854-015-3684-x,10.1111/j.1551-2916.2008.02408.x,2015-09-01,P7Y2M,no,no
|
||||
02001000007362801000805046300010563030608046333-02001000007362801000805046300010463020101046309,10.1007/s10854-015-3684-x,10.1007/s10854-014-2114-9,2015-09-01,P1Y2M4D,yes,no
|
||||
02001000007362801000805046300010563030608046333-020010001063619371214271022182329370200010337000937000609,10.1007/s10854-015-3684-x,10.1016/j.ceramint.2013.09.069,2015-09-01,P1Y6M,no,no
|
||||
02001000007362801000805046300010563030608046333-02001000007362801000805046300000963090901036304,10.1007/s10854-015-3684-x,10.1007/s10854-009-9913-4,2015-09-01,P6Y3M10D,yes,no
|
||||
02001000007362801000805046300010563030608046333-02001000106360000030863010009085807025909000307006305,10.1007/s10854-015-3684-x,10.1016/0038-1098(72)90370-5,2015-09-01,P43Y8M,no,no
|
||||
02001000007362801000805046300010563030608056309-02001000106361937281010370200010437000937000308,10.1007/s10854-015-3685-9,10.1016/j.saa.2014.09.038,2015-09-03,P0Y7M,no,no
|
||||
02001000007362801000805046300010563030608056309-0200100010636193722102912171027370200010537000437000106,10.1007/s10854-015-3685-9,10.1016/j.matchar.2015.04.016,2015-09-03,P0Y2M,no,no
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
oci,citing,cited,creation,timespan,journal_sc,author_sc
|
||||
02001000308362804010509076300010963000003086301-0200100020936020001003227000009010004,10.1038/s41597-019-0038-1,10.1029/2010wr009104,2019-04-15,P8Y1M,no,no
|
||||
02001000308362804010509076300010963000003086301-0200100010636280103060463080105025800015900000006006303,10.1038/s41597-019-0038-1,10.1016/s1364-8152(01)00060-3,2019-04-15,P17Y3M,no,no
|
||||
02001000308362804010509076300010963000003086301-02001000007362800000407076300010063000401066333,10.1038/s41597-019-0038-1,10.1007/s00477-010-0416-x,2019-04-15,P8Y9M6D,no,no
|
||||
02001000308362804010509076300010963000003086301-02001000007362800000700046300010363000905016308,10.1038/s41597-019-0038-1,10.1007/s00704-013-0951-8,2019-04-15,P5Y9M23D,no,no
|
||||
02001000308362804010509076300010963000003086301-02001000002361924123705070707,10.1038/s41597-019-0038-1,10.1002/joc.5777,2019-04-15,P0Y8M1D,no,no
|
||||
02001000308362804010509076300010963000003086301-02005010904361714282863020263040504076302000108,10.1038/s41597-019-0038-1,10.5194/hess-22-4547-2018,2019-04-15,P0Y7M18D,no,no
|
||||
02001000308362804010509076300010963000003086301-02001000002361924123703050404,10.1038/s41597-019-0038-1,10.1002/joc.3544,2019-04-15,P6Y9M6D,no,no
|
||||
|
|
@ -0,0 +1,9 @@
|
|||
oci,citing,cited,creation,timespan,journal_sc,author_sc
|
||||
0200100000236090708010101090307000202023727141528-020050302063600040000010307,10.1002/9781119370222.refs,10.5326/0400137,2020-06-22,P16Y3M,no,no
|
||||
0200100000236090708010101090307000202023727141528-0200101010136193701050302630905003337020000073700000301093733,10.1002/9781119370222.refs,10.1111/j.1532-950x.2007.00319.x,2020-06-22,P12Y8M,no,no
|
||||
0200100000236090708010101090307000202023727141528-0200101010136312830370102030509,10.1002/9781119370222.refs,10.1111/vsu.12359,2020-06-22,P4Y10M29D,no,no
|
||||
0200100000236090708010101090307000202023727141528-020050302063600030900020904,10.1002/9781119370222.refs,10.5326/0390294,2020-06-22,P17Y1M,no,no
|
||||
0200100000236090708010101090307000202023727141528-020050302063600040200030701,10.1002/9781119370222.refs,10.5326/0420371,2020-06-22,P13Y9M,no,no
|
||||
0200100000236090708010101090307000202023727141528-0200101010136193701050302630905003337020001033701020000003733,10.1002/9781119370222.refs,10.1111/j.1532-950x.2013.12000.x,2020-06-22,P7Y2M,no,no
|
||||
0200100000236090708010101090307000202023727141528-020010008003600000408000106093702000006370306070200,10.1002/9781119370222.refs,10.1080/00480169.2006.36720,2020-06-22,P13Y6M,no,no
|
||||
0200100000236090708010101090307000202023727141528-0200101010136193701070501630008010337020000063700000003033733,10.1002/9781119370222.refs,10.1111/j.1751-0813.2006.00033.x,2020-06-22,P13Y8M,no,no
|
||||
2
pom.xml
2
pom.xml
|
|
@ -753,7 +753,7 @@
|
|||
<mockito-core.version>3.3.3</mockito-core.version>
|
||||
<mongodb.driver.version>3.4.2</mongodb.driver.version>
|
||||
<vtd.version>[2.12,3.0)</vtd.version>
|
||||
<dhp-schemas.version>[2.7.18]</dhp-schemas.version>
|
||||
<dhp-schemas.version>[2.7.19-SNAPSHOT]</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