miriam.baglioni
/
dnet-hadoop
forked from D-Net/dnet-hadoop
2
0
Fork 0
Code Issues 2 Pull Requests Releases Wiki Activity

changed to match the requirements for short titles in level and long titles in classification

This commit is contained in:
Miriam Baglioni 2020-10-20 17:03:25 +02:00
parent fed711da80
commit a2ce527fae
5 changed files with 67 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

68
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/PrepareProgramme.java
View File

@ -4,6 +4,7 @@ package eu.dnetlib.dhp.actionmanager.project;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import java.util.Optional;
@ -11,6 +12,7 @@ import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.*;
import org.slf4j.Logger;
@ -175,43 +177,54 @@ public class PrepareProgramme {
return csvProgramme;
});
prepareClassification(h2020Programmes);
// prepareClassification(h2020Programmes);
h2020Programmes
.map(csvProgramme -> OBJECT_MAPPER.writeValueAsString(csvProgramme))
JavaSparkContext jsc = new JavaSparkContext(spark.sparkContext());
JavaRDD<CSVProgramme> rdd = jsc.parallelize(prepareClassification(h2020Programmes), 1);
rdd
.map(csvProgramme -> {
String tmp = OBJECT_MAPPER.writeValueAsString(csvProgramme);
return tmp;
})
.saveAsTextFile(outputPath);
}
private static void prepareClassification(JavaRDD<CSVProgramme> h2020Programmes) {
private static List<CSVProgramme> prepareClassification(JavaRDD<CSVProgramme> h2020Programmes) {
Object[] codedescription = h2020Programmes
.map(value -> new Tuple2<>(value.getCode(), value.getTitle()))
.map(
value -> new Tuple2<>(value.getCode(),
new Tuple2<String, String>(value.getTitle(), value.getShortTitle())))
.collect()
.toArray();
for (int i = 0; i < codedescription.length - 1; i++) {
for (int j = i + 1; j < codedescription.length; j++) {
Tuple2<String, String> t2i = (Tuple2<String, String>) codedescription[i];
Tuple2<String, String> t2j = (Tuple2<String, String>) codedescription[j];
Tuple2<String, Tuple2<String, String>> t2i = (Tuple2<String, Tuple2<String, String>>) codedescription[i];
Tuple2<String, Tuple2<String, String>> t2j = (Tuple2<String, Tuple2<String, String>>) codedescription[j];
if (t2i._1().compareTo(t2j._1()) > 0) {
Tuple2<String, String> temp = t2i;
Tuple2<String, Tuple2<String, String>> temp = t2i;
codedescription[i] = t2j;
codedescription[j] = temp;
}
}
}
Map<String, String> map = new HashMap<>();
Map<String, Tuple2<String, String>> map = new HashMap<>();
for (int j = 0; j < codedescription.length; j++) {
Tuple2<String, String> entry = (Tuple2<String, String>) codedescription[j];
Tuple2<String, Tuple2<String, String>> entry = (Tuple2<String, Tuple2<String, String>>) codedescription[j];
String ent = entry._1();
if (ent.contains("Euratom-")) {
ent = ent.replace("-Euratom-", ".Euratom.");
}
String[] tmp = ent.split("\\.");
if (tmp.length <= 2) {
map.put(entry._1(), entry._2());
if (StringUtils.isEmpty(entry._2()._2())) {
map.put(entry._1(), new Tuple2<String, String>(entry._2()._1(), entry._2()._1()));
} else {
map.put(entry._1(), entry._2());
}
} else {
if (ent.endsWith(".")) {
ent = ent.substring(0, ent.length() - 1);
@ -224,14 +237,14 @@ public class PrepareProgramme {
key = key.substring(0, key.length() - 1);
}
}
String current = entry._2();
String current = entry._2()._1();
if (!ent.contains("Euratom")) {
String parent;
String tmp_key = tmp[0] + ".";
for (int i = 1; i < tmp.length - 1; i++) {
tmp_key += tmp[i] + ".";
parent = map.get(tmp_key).toLowerCase().trim();
parent = map.get(tmp_key)._1().toLowerCase().trim();
if (parent.contains("|")) {
parent = parent.substring(parent.lastIndexOf("|") + 1).trim();
}
@ -246,18 +259,29 @@ public class PrepareProgramme {
}
}
map.put(ent + ".", map.get(key) + " | " + current);
String shortTitle = entry._2()._2();
if (StringUtils.isEmpty(shortTitle)) {
shortTitle = current;
}
Tuple2<String, String> newEntry = new Tuple2<>(map.get(key)._1() + " | " + current,
map.get(key)._2() + " | " + shortTitle);
map.put(ent + ".", newEntry);
}
}
h2020Programmes.foreach(csvProgramme -> {
if (!csvProgramme.getCode().endsWith(".") && !csvProgramme.getCode().contains("Euratom")
&& !csvProgramme.getCode().equals("H2020-EC"))
csvProgramme.setClassification(map.get(csvProgramme.getCode() + "."));
else
csvProgramme.setClassification(map.get(csvProgramme.getCode()));
});
return h2020Programmes.map(csvProgramme -> {
String code = csvProgramme.getCode();
if (!code.endsWith(".") && !code.contains("Euratom")
&& !code.equals("H2020-EC"))
code += ".";
csvProgramme.setClassification(map.get(code)._1());
csvProgramme.setClassification_short(map.get(code)._2());
return csvProgramme;
}).collect();
}
public static <R> Dataset<R> readPath(

14
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/SparkAtomicActionJob.java
View File

@ -9,7 +9,6 @@ import java.util.Objects;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.spark.SparkConf;
@ -138,7 +137,8 @@ public class SparkAtomicActionJob {
pm.setCode(csvProject.getProgramme());
h2020classification.setClassification(ocsvProgramme.get().getClassification());
h2020classification.setH2020Programme(pm);
setLevelsAndProgramme(h2020classification, ocsvProgramme.get().getClassification());
setLevelsandProgramme(h2020classification, ocsvProgramme.get().getClassification_short());
// setProgramme(h2020classification, ocsvProgramme.get().getClassification());
pp.setH2020classification(Arrays.asList(h2020classification));
return pp;
@ -177,8 +177,8 @@ public class SparkAtomicActionJob {
}
private static void setLevelsAndProgramme(H2020Classification h2020Classification, String classification) {
String[] tmp = classification.split(" \\| ");
private static void setLevelsandProgramme(H2020Classification h2020Classification, String classification_short) {
String[] tmp = classification_short.split(" \\| ");
h2020Classification.setLevel1(tmp[0]);
if (tmp.length > 1) {
h2020Classification.setLevel2(tmp[1]);
@ -189,6 +189,12 @@ public class SparkAtomicActionJob {
h2020Classification.getH2020Programme().setDescription(tmp[tmp.length - 1]);
}
// private static void setProgramme(H2020Classification h2020Classification, String classification) {
// String[] tmp = classification.split(" \\| ");
//
// h2020Classification.getH2020Programme().setDescription(tmp[tmp.length - 1]);
// }
public static <R> Dataset<R> readPath(
SparkSession spark, String inputPath, Class<R> clazz) {
return spark

9
dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/project/utils/CSVProgramme.java
View File

@ -22,6 +22,15 @@ public class CSVProgramme implements Serializable {
private String shortTitle;
private String language;
private String classification;
private String classification_short;
public String getClassification_short() {
return classification_short;
}
public void setClassification_short(String classification_short) {
this.classification_short = classification_short;
}
public String getClassification() {
return classification;

2
dhp-workflows/dhp-aggregation/src/test/java/eu/dnetlib/dhp/actionmanager/project/PrepareH2020ProgrammeTest.java
View File

@ -92,6 +92,8 @@ public class PrepareH2020ProgrammeTest {
Assertions.assertEquals(0, verificationDataset.filter("classification = ''").count());
// tmp.foreach(csvProgramme -> System.out.println(OBJECT_MAPPER.writeValueAsString(csvProgramme)));
Assertions
.assertEquals(
"Societal challenges | Smart, Green And Integrated Transport | CLEANSKY2 | IADP Fast Rotorcraft",

BIN
dhp-workflows/dhp-aggregation/src/test/resources/eu/dnetlib/dhp/actionmanager/project/whole_programme.json.gz
View File

Binary file not shown.