forked from D-Net/dnet-hadoop
[EOSCTag] -
This commit is contained in:
parent
d012d125d7
commit
6dc68c48e0
|
@ -7,11 +7,18 @@ import eu.dnetlib.dhp.bulktag.community.CommunityConfiguration;
|
||||||
import eu.dnetlib.dhp.bulktag.community.CommunityConfigurationFactory;
|
import eu.dnetlib.dhp.bulktag.community.CommunityConfigurationFactory;
|
||||||
import eu.dnetlib.dhp.bulktag.community.ProtoMap;
|
import eu.dnetlib.dhp.bulktag.community.ProtoMap;
|
||||||
import eu.dnetlib.dhp.bulktag.community.QueryInformationSystem;
|
import eu.dnetlib.dhp.bulktag.community.QueryInformationSystem;
|
||||||
|
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||||
import eu.dnetlib.dhp.schema.oaf.Software;
|
import eu.dnetlib.dhp.schema.oaf.Software;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||||
|
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
||||||
import org.apache.commons.io.IOUtils;
|
import org.apache.commons.io.IOUtils;
|
||||||
import org.apache.spark.SparkConf;
|
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.sql.Dataset;
|
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.apache.spark.sql.SparkSession;
|
||||||
import org.slf4j.Logger;
|
import org.slf4j.Logger;
|
||||||
import org.slf4j.LoggerFactory;
|
import org.slf4j.LoggerFactory;
|
||||||
|
@ -25,6 +32,12 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||||
public class SparkEoscTag {
|
public class SparkEoscTag {
|
||||||
private static final Logger log = LoggerFactory.getLogger(SparkEoscTag.class);
|
private static final Logger log = LoggerFactory.getLogger(SparkEoscTag.class);
|
||||||
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||||
|
public final static StructuredProperty EOSC_NOTEBOOK = OafMapperUtils.structuredProperty(
|
||||||
|
"EOSC::Jupyter Notebook", OafMapperUtils.qualifier("eosc","European Open Science Cloud",
|
||||||
|
ModelConstants.DNET_SUBJECT_TYPOLOGIES,ModelConstants.DNET_SUBJECT_TYPOLOGIES)
|
||||||
|
,OafMapperUtils.dataInfo(false, "propagation", true, false,
|
||||||
|
OafMapperUtils.qualifier("propagation:subject","Inferred by OpenAIRE",
|
||||||
|
ModelConstants.DNET_PROVENANCE_ACTIONS,ModelConstants.DNET_PROVENANCE_ACTIONS), "0.9"));
|
||||||
|
|
||||||
public static void main(String[] args) throws Exception {
|
public static void main(String[] args) throws Exception {
|
||||||
String jsonConfiguration = IOUtils
|
String jsonConfiguration = IOUtils
|
||||||
|
@ -45,23 +58,63 @@ public class SparkEoscTag {
|
||||||
final String inputPath = parser.get("sourcePath");
|
final String inputPath = parser.get("sourcePath");
|
||||||
log.info("inputPath: {}", inputPath);
|
log.info("inputPath: {}", inputPath);
|
||||||
|
|
||||||
|
final String workingPath = parser.get("workingPath");
|
||||||
|
log.info("workingPath: {}", workingPath);
|
||||||
|
|
||||||
SparkConf conf = new SparkConf();
|
SparkConf conf = new SparkConf();
|
||||||
|
|
||||||
runWithSparkSession(
|
runWithSparkSession(
|
||||||
conf,
|
conf,
|
||||||
isSparkSessionManaged,
|
isSparkSessionManaged,
|
||||||
spark -> {
|
spark -> {
|
||||||
execEoscTag(spark, inputPath);
|
execEoscTag(spark, inputPath, workingPath);
|
||||||
|
|
||||||
});
|
});
|
||||||
}
|
}
|
||||||
|
|
||||||
private static void execEoscTag(SparkSession spark, String inputPath) {
|
private static void execEoscTag(SparkSession spark, String inputPath, String workingPath) {
|
||||||
//search for notebook
|
//search for notebook
|
||||||
//subject contiene jupyter.
|
//subject contiene jupyter.
|
||||||
//esistono python e notebook nei subject non necessariamente nello stesso
|
//esistono python e notebook nei subject non necessariamente nello stesso
|
||||||
//si cerca fra i prodotto di tipo software
|
//si cerca fra i prodotti di tipo software
|
||||||
Dataset<Software> sw = readPath(spark, inputPath + "/software", Software.class)
|
|
||||||
|
|
||||||
|
readPath(spark, inputPath + "/software", Software.class)
|
||||||
|
.map((MapFunction<Software, Software>) s -> {
|
||||||
|
if(containsSubjectNotebook(s)){
|
||||||
|
s.getSubject().add(EOSC_NOTEBOOK);
|
||||||
|
}
|
||||||
|
return s;
|
||||||
|
}, Encoders.bean(Software.class) )
|
||||||
|
.write()
|
||||||
|
.mode(SaveMode.Overwrite)
|
||||||
|
.option("compression","gzip")
|
||||||
|
.json(workingPath + "/software");
|
||||||
|
|
||||||
|
readPath(spark, workingPath + "/software" , Software.class)
|
||||||
|
.write()
|
||||||
|
.mode(SaveMode.Overwrite)
|
||||||
|
.option("compression","gzip")
|
||||||
|
.json(inputPath + "/software");
|
||||||
|
|
||||||
}
|
}
|
||||||
|
|
||||||
|
private static boolean containsSubjectNotebook(Software s) {
|
||||||
|
if(s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("jupyter")))
|
||||||
|
return true;
|
||||||
|
if(s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("python") &&
|
||||||
|
sbj.getValue().toLowerCase().contains("notebook")))
|
||||||
|
return true;
|
||||||
|
if(s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("python")) &&
|
||||||
|
s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("notebook")))
|
||||||
|
return true;
|
||||||
|
return false;
|
||||||
|
}
|
||||||
|
|
||||||
|
private static boolean containsTitleNotebook(Software s) {
|
||||||
|
if (s.getTitle().stream().anyMatch(t -> t.getValue().toLowerCase().contains("jupyter") &&
|
||||||
|
t.getValue().toLowerCase().contains("notebook")))
|
||||||
|
return true;
|
||||||
|
return false;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in New Issue