wf to generate orcid dataset
parent
8812ab65e1
commit
b1b589ada1
@ -0,0 +1,79 @@
|
||||
|
||||
package eu.dnetlib.dhp.schema.orcid;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
public class Summary implements Serializable {
|
||||
private String creationMethod;
|
||||
private String completionDate;
|
||||
private String submissionDate;
|
||||
private String lastModifiedDate;
|
||||
private boolean claimed;
|
||||
private String deactivationDate;
|
||||
private boolean verifiedEmail;
|
||||
private boolean verifiedPrimaryEmail;
|
||||
|
||||
public String getCreationMethod() {
|
||||
return creationMethod;
|
||||
}
|
||||
|
||||
public void setCreationMethod(String creationMethod) {
|
||||
this.creationMethod = creationMethod;
|
||||
}
|
||||
|
||||
public String getCompletionDate() {
|
||||
return completionDate;
|
||||
}
|
||||
|
||||
public void setCompletionDate(String completionDate) {
|
||||
this.completionDate = completionDate;
|
||||
}
|
||||
|
||||
public String getSubmissionDate() {
|
||||
return submissionDate;
|
||||
}
|
||||
|
||||
public void setSubmissionDate(String submissionDate) {
|
||||
this.submissionDate = submissionDate;
|
||||
}
|
||||
|
||||
public String getLastModifiedDate() {
|
||||
return lastModifiedDate;
|
||||
}
|
||||
|
||||
public void setLastModifiedDate(String lastModifiedDate) {
|
||||
this.lastModifiedDate = lastModifiedDate;
|
||||
}
|
||||
|
||||
public boolean isClaimed() {
|
||||
return claimed;
|
||||
}
|
||||
|
||||
public void setClaimed(boolean claimed) {
|
||||
this.claimed = claimed;
|
||||
}
|
||||
|
||||
public String getDeactivationDate() {
|
||||
return deactivationDate;
|
||||
}
|
||||
|
||||
public void setDeactivationDate(String deactivationDate) {
|
||||
this.deactivationDate = deactivationDate;
|
||||
}
|
||||
|
||||
public boolean isVerifiedEmail() {
|
||||
return verifiedEmail;
|
||||
}
|
||||
|
||||
public void setVerifiedEmail(boolean verifiedEmail) {
|
||||
this.verifiedEmail = verifiedEmail;
|
||||
}
|
||||
|
||||
public boolean isVerifiedPrimaryEmail() {
|
||||
return verifiedPrimaryEmail;
|
||||
}
|
||||
|
||||
public void setVerifiedPrimaryEmail(boolean verifiedPrimaryEmail) {
|
||||
this.verifiedPrimaryEmail = verifiedPrimaryEmail;
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,140 @@
|
||||
|
||||
package eu.dnetlib.doiboost.orcid;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.*;
|
||||
import java.util.stream.Collectors;
|
||||
import java.util.stream.Stream;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaPairRDD;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.api.java.function.Function;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.Dataset;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.esotericsoftware.minlog.Log;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import com.google.gson.JsonElement;
|
||||
import com.google.gson.JsonParser;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.oaf.Publication;
|
||||
import eu.dnetlib.dhp.schema.orcid.AuthorData;
|
||||
import eu.dnetlib.doiboost.orcid.model.WorkData;
|
||||
import eu.dnetlib.doiboost.orcid.xml.XMLRecordParser;
|
||||
import eu.dnetlib.doiboost.orcidnodoi.json.JsonWriter;
|
||||
import eu.dnetlib.doiboost.orcidnodoi.model.WorkDataNoDoi;
|
||||
import eu.dnetlib.doiboost.orcidnodoi.xml.XMLRecordParserNoDoi;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class SparkUpdateOrcidDatasets {
|
||||
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static void main(String[] args) throws IOException, Exception {
|
||||
Logger logger = LoggerFactory.getLogger(SparkUpdateOrcidDatasets.class);
|
||||
logger.info("[ SparkUpdateOrcidDatasets STARTED]");
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
SparkUpdateOrcidDatasets.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/doiboost/download_orcid_data.json")));
|
||||
parser.parseArgument(args);
|
||||
Boolean isSparkSessionManaged = Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
logger.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
final String workingPath = parser.get("workingPath");
|
||||
logger.info("workingPath: ", workingPath);
|
||||
// final String outputPath = parser.get("outputPath");
|
||||
// logger.info("outputPath: ", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
sc.hadoopConfiguration().set("mapreduce.output.fileoutputformat.compress", "true");
|
||||
|
||||
JavaPairRDD<Text, Text> xmlSummariesRDD = sc
|
||||
.sequenceFile(workingPath.concat("xml/authors/xml_authors.seq"), Text.class, Text.class);
|
||||
xmlSummariesRDD
|
||||
.repartition(5)
|
||||
.map(seq -> XMLRecordParser.VTDParseAuthorData(seq._2().toString().getBytes()))
|
||||
.filter(summary -> summary != null)
|
||||
.mapToPair(
|
||||
summary -> new Tuple2<>(summary.getOid(),
|
||||
OBJECT_MAPPER.writeValueAsString(summary)))
|
||||
.mapToPair(t -> new Tuple2(new Text(t._1()), new Text(t._2())))
|
||||
.saveAsNewAPIHadoopFile(
|
||||
workingPath.concat("orcid_dataset/authors"),
|
||||
Text.class,
|
||||
Text.class,
|
||||
SequenceFileOutputFormat.class,
|
||||
sc.hadoopConfiguration());
|
||||
|
||||
JavaPairRDD<Text, Text> xmlWorksRDD = sc
|
||||
.sequenceFile(workingPath.concat("xml/works/*"), Text.class, Text.class);
|
||||
|
||||
xmlWorksRDD
|
||||
.map(seq -> XMLRecordParserNoDoi.VTDParseWorkData(seq._2().toString().getBytes()))
|
||||
.filter(work -> work != null)
|
||||
.mapToPair(
|
||||
work -> new Tuple2<>(work.getOid().concat("_").concat(work.getId()),
|
||||
OBJECT_MAPPER.writeValueAsString(work)))
|
||||
.mapToPair(t -> new Tuple2(new Text(t._1()), new Text(t._2())))
|
||||
.saveAsNewAPIHadoopFile(
|
||||
workingPath.concat("orcid_dataset/works"),
|
||||
Text.class,
|
||||
Text.class,
|
||||
SequenceFileOutputFormat.class,
|
||||
sc.hadoopConfiguration());
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
private static AuthorData loadAuthorFromJson(Text orcidId, Text json) {
|
||||
AuthorData authorData = new AuthorData();
|
||||
authorData.setOid(orcidId.toString());
|
||||
JsonElement jElement = new JsonParser().parse(json.toString());
|
||||
authorData.setName(getJsonValue(jElement, "name"));
|
||||
authorData.setSurname(getJsonValue(jElement, "surname"));
|
||||
authorData.setCreditName(getJsonValue(jElement, "creditname"));
|
||||
return authorData;
|
||||
}
|
||||
|
||||
private static WorkData loadWorkFromJson(Text orcidId, Text json) {
|
||||
WorkData workData = new WorkData();
|
||||
workData.setOid(orcidId.toString());
|
||||
JsonElement jElement = new JsonParser().parse(json.toString());
|
||||
workData.setDoi(getJsonValue(jElement, "doi"));
|
||||
return workData;
|
||||
}
|
||||
|
||||
private static String getJsonValue(JsonElement jElement, String property) {
|
||||
if (jElement.getAsJsonObject().has(property)) {
|
||||
JsonElement name = null;
|
||||
name = jElement.getAsJsonObject().get(property);
|
||||
if (name != null && !name.isJsonNull()) {
|
||||
return name.getAsString();
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
@ -0,0 +1,92 @@
|
||||
<workflow-app name="update_orcid_datasets" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>spark2MaxExecutors</name>
|
||||
<value>5</value>
|
||||
</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>
|
||||
<property>
|
||||
<name>workingPath</name>
|
||||
<description>the working dir base path</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<global>
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>${oozieActionShareLibForSpark2}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</global>
|
||||
|
||||
<start to="UpdateOrcidDatasets"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="UpdateOrcidDatasets">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn-cluster</master>
|
||||
<mode>cluster</mode>
|
||||
<name>UpdateOrcidDatasets</name>
|
||||
<class>eu.dnetlib.doiboost.orcid.SparkUpdateOrcidDatasets</class>
|
||||
<jar>dhp-doiboost-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--conf spark.dynamicAllocation.enabled=true
|
||||
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
</spark-opts>
|
||||
<arg>-w</arg><arg>${workingPath}/</arg>
|
||||
<arg>-n</arg><arg>${nameNode}</arg>
|
||||
<arg>-f</arg><arg>-</arg>
|
||||
<arg>-o</arg><arg>-</arg>
|
||||
<arg>-t</arg><arg>-</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
||||
Loading…
Reference in New Issue