workflow to generate seq(doi,AuthorList)
This commit is contained in:
parent
d4e9075f22
commit
7362bc3e9d
|
|
@ -0,0 +1,114 @@
|
|||
|
||||
package eu.dnetlib.doiboost.orcid;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.text.SimpleDateFormat;
|
||||
import java.util.Date;
|
||||
import java.util.List;
|
||||
import java.util.Optional;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.http.client.methods.CloseableHttpResponse;
|
||||
import org.apache.http.client.methods.HttpGet;
|
||||
import org.apache.http.impl.client.CloseableHttpClient;
|
||||
import org.apache.http.impl.client.HttpClients;
|
||||
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.sql.Dataset;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.SaveMode;
|
||||
import org.apache.spark.util.LongAccumulator;
|
||||
import org.mortbay.log.Log;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.google.gson.JsonElement;
|
||||
import com.google.gson.JsonParser;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.scholexplorer.DLIRelation;
|
||||
import eu.dnetlib.doiboost.orcid.model.AuthorData;
|
||||
import eu.dnetlib.doiboost.orcid.model.DownloadedRecordData;
|
||||
import eu.dnetlib.doiboost.orcid.model.WorkData;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class SparkGenerateDoiAuthorList {
|
||||
|
||||
public static void main(String[] args) throws IOException, Exception {
|
||||
Logger logger = LoggerFactory.getLogger(SparkGenerateDoiAuthorList.class);
|
||||
logger.info("[ SparkGenerateDoiAuthorList STARTED]");
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
SparkGenerateDoiAuthorList.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/doiboost/gen_doi_author_list_orcid_parameters.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 outputDoiAuthorListPath = parser.get("outputDoiAuthorListPath");
|
||||
logger.info("outputDoiAuthorListPath: ", outputDoiAuthorListPath);
|
||||
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
JavaPairRDD<Text, Text> summariesRDD = sc.sequenceFile(workingPath + "../orcid_summaries/output/authors.seq", Text.class, Text.class);
|
||||
Dataset<AuthorData> summariesDataset = spark
|
||||
.createDataset(summariesRDD.map(seq -> loadAuthorFromJson(seq._1(), seq._2())).rdd(),
|
||||
Encoders.bean(AuthorData.class));
|
||||
|
||||
JavaPairRDD<Text, Text> activitiesRDD = sc.sequenceFile(workingPath + "/output/*.seq", Text.class, Text.class);
|
||||
Dataset<WorkData> activitiesDataset = spark
|
||||
.createDataset(activitiesRDD.map(seq -> loadWorkFromJson(seq._1(), seq._2())).rdd(),
|
||||
Encoders.bean(WorkData.class));
|
||||
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
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.isJsonObject()) {
|
||||
return name.getAsString();
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
[{"paramName":"w", "paramLongName":"workingPath", "paramDescription": "the working path", "paramRequired": true},
|
||||
{"paramName":"o", "paramLongName":"outputDoiAuthorListPath", "paramDescription": "the relative folder of the sequencial file to write the data", "paramRequired": true}
|
||||
]
|
||||
|
|
@ -0,0 +1,18 @@
|
|||
<configuration>
|
||||
<property>
|
||||
<name>jobTracker</name>
|
||||
<value>hadoop-rm3.garr-pa1.d4science.org:8032</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>nameNode</name>
|
||||
<value>hdfs://hadoop-rm1.garr-pa1.d4science.org:8020</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>queueName</name>
|
||||
<value>default</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>spark2</value>
|
||||
</property>
|
||||
</configuration>
|
||||
|
|
@ -0,0 +1,55 @@
|
|||
<workflow-app name="Gen Orcid Authors" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>workingPath</name>
|
||||
<description>the working dir base path</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>
|
||||
</parameters>
|
||||
|
||||
<start to="ResetWorkingPath"/>
|
||||
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="ResetWorkingPath">
|
||||
<fs>
|
||||
<delete path='${workingPath_activities}/doi_author_list'/>
|
||||
</fs>
|
||||
<ok to="Gen_Doi_Author_List"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="Gen_Doi_Author_List">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Gen_Doi_Author_List</name>
|
||||
<class>eu.dnetlib.doiboost.orcid.SparkGenerateDoiAuthorList</class>
|
||||
<jar>dhp-doiboost-1.2.1-SNAPSHOT.jar</jar>
|
||||
<spark-opts>--num-executors 1 --conf spark.yarn.jars="hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2" --executor-memory=${sparkExecutorMemory} --executor-cores=${sparkExecutorCores} --driver-memory=${sparkDriverMemory}
|
||||
</spark-opts>
|
||||
<arg>-w</arg><arg>${workingPath}/</arg>
|
||||
<arg>-o</arg><arg>doi_author_list/</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
||||
Loading…
Reference in New Issue