D-Net
/
dnet-hadoop
13
4
Fork 10
Code Issues 14 Pull Requests 8 Projects 2 Releases 1 Wiki Activity

[EOSCTag] last test and change in the implementation to search in title and descriptio

This commit is contained in:
Miriam Baglioni 2022-05-02 17:43:20 +02:00
parent e37177e1ce
commit a21fe310e5
7 changed files with 620 additions and 291 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
dhp-workflows/dhp-doiboost/src/main/scala/eu/dnetlib/doiboost/crossref/Crossref2Oaf.scala
View File

@ -584,12 +584,10 @@ case object Crossref2Oaf {
if (dp.length == 10) { if (dp.length == 10) {
return GraphCleaningFunctions.cleanDate(dp) return GraphCleaningFunctions.cleanDate(dp)
} }
} } else if (res.size == 2) {
else if (res.size ==2) {
val dp = f"${res.head}-${res(1)}%02d-01" val dp = f"${res.head}-${res(1)}%02d-01"
return GraphCleaningFunctions.cleanDate(dp) return GraphCleaningFunctions.cleanDate(dp)
} } else if (res.size == 1) {
else if (res.size ==1) {
return GraphCleaningFunctions.cleanDate(s"${res.head}-01-01") return GraphCleaningFunctions.cleanDate(s"${res.head}-01-01")
} }
} }

4
dhp-workflows/dhp-doiboost/src/test/scala/eu/dnetlib/dhp/doiboost/crossref/CrossrefMappingTest.scala
View File

@ -73,10 +73,10 @@ class CrossrefMappingTest {
} }
@Test @Test
def crossrefIssueDateTest(): Unit = { def crossrefIssueDateTest(): Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/issue_date.json")).mkString val json =
Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/issue_date.json")).mkString
assertNotNull(json) assertNotNull(json)
assertFalse(json.isEmpty) assertFalse(json.isEmpty)
val resultList: List[Oaf] = Crossref2Oaf.convert(json) val resultList: List[Oaf] = Crossref2Oaf.convert(json)

105
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkEoscTag.java
View File

@ -1,10 +1,14 @@
package eu.dnetlib.dhp.bulktag; package eu.dnetlib.dhp.bulktag;
import com.fasterxml.jackson.databind.ObjectMapper; import static eu.dnetlib.dhp.PropagationConstant.readPath;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*; import java.util.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils; import java.util.function.Function;
import java.util.stream.Collectors;
import java.util.stream.Stream;
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.MapFunction; import org.apache.spark.api.java.function.MapFunction;
@ -14,28 +18,37 @@ import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import java.util.ArrayList; import com.fasterxml.jackson.databind.ObjectMapper;
import java.util.Arrays;
import java.util.List;
import java.util.Optional;
import static eu.dnetlib.dhp.PropagationConstant.readPath; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
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 static final Qualifier EOSC_QUALIFIER = OafMapperUtils.qualifier("eosc", public static final Qualifier EOSC_QUALIFIER = OafMapperUtils
.qualifier(
"eosc",
"European Open Science Cloud", "European Open Science Cloud",
ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES); ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES);
public static final DataInfo EOSC_DATAINFO = OafMapperUtils.dataInfo(false, "propagation", true, false, public static final DataInfo EOSC_DATAINFO = OafMapperUtils
OafMapperUtils.qualifier("propagation:subject","Inferred by OpenAIRE", .dataInfo(
ModelConstants.DNET_PROVENANCE_ACTIONS,ModelConstants.DNET_PROVENANCE_ACTIONS), "0.9"); false, "propagation", true, false,
public final static StructuredProperty EOSC_NOTEBOOK = OafMapperUtils.structuredProperty( OafMapperUtils
.qualifier(
"propagation:subject", "Inferred by OpenAIRE",
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
"0.9");
public final static StructuredProperty EOSC_NOTEBOOK = OafMapperUtils
.structuredProperty(
"EOSC::Jupyter Notebook", EOSC_QUALIFIER, EOSC_DATAINFO); "EOSC::Jupyter Notebook", EOSC_QUALIFIER, EOSC_DATAINFO);
public final static StructuredProperty EOSC_GALAXY = OafMapperUtils.structuredProperty( public final static StructuredProperty EOSC_GALAXY = OafMapperUtils
.structuredProperty(
"EOSC::Galaxy Workflow", EOSC_QUALIFIER, EOSC_DATAINFO); "EOSC::Galaxy Workflow", EOSC_QUALIFIER, EOSC_DATAINFO);
public final static StructuredProperty EOSC_TWITTER = OafMapperUtils.structuredProperty( public final static StructuredProperty EOSC_TWITTER = OafMapperUtils
.structuredProperty(
"EOSC::Twitter Data", EOSC_QUALIFIER, EOSC_DATAINFO); "EOSC::Twitter Data", EOSC_QUALIFIER, EOSC_DATAINFO);
public static void main(String[] args) throws Exception { public static void main(String[] args) throws Exception {
@ -101,8 +114,7 @@ public class SparkEoscTag {
.json(inputPath + "/software"); .json(inputPath + "/software");
readPath(spark, inputPath + "/otherresearchproduct", OtherResearchProduct.class) readPath(spark, inputPath + "/otherresearchproduct", OtherResearchProduct.class)
.map((MapFunction<OtherResearchProduct, OtherResearchProduct>) orp -> .map((MapFunction<OtherResearchProduct, OtherResearchProduct>) orp -> {
{
List<StructuredProperty> sbject; List<StructuredProperty> sbject;
if (!Optional.ofNullable(orp.getSubject()).isPresent()) if (!Optional.ofNullable(orp.getSubject()).isPresent())
orp.setSubject(new ArrayList<>()); orp.setSubject(new ArrayList<>());
@ -150,12 +162,13 @@ public class SparkEoscTag {
} }
private static boolean containscriteriaTwitter(Result r) { private static boolean containscriteriaTwitter(Result r) {
if (r.getTitle().stream().anyMatch(t -> t.getValue().toLowerCase().contains("twitter") && Set<String> words = getWordsSP(r.getTitle());
t.getValue().toLowerCase().contains("data"))) words.addAll(getWordsF(r.getDescription()));
return true;
if(r.getDescription().stream().anyMatch(d -> d.getValue().toLowerCase().contains("twitter") && if (words.contains("twitter") &&
d.getValue().toLowerCase().contains("data") )) (words.contains("data") || words.contains("dataset")))
return true; return true;
if (r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("twitter")) && if (r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("twitter")) &&
r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("data"))) r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("data")))
return true; return true;
@ -163,12 +176,12 @@ public class SparkEoscTag {
} }
private static boolean containsCriteriaGalaxy(Result r) { private static boolean containsCriteriaGalaxy(Result r) {
if (r.getTitle().stream().anyMatch(t -> t.getValue().toLowerCase().contains("galaxy") && Set<String> words = getWordsSP(r.getTitle());
(t.getValue().toLowerCase().contains("workflow") || t.getValue().toLowerCase().contains("software")))) words.addAll(getWordsF(r.getDescription()));
return true; if (words.contains("galaxy") &&
if(r.getDescription().stream().anyMatch(d -> d.getValue().toLowerCase().contains("galaxy") && (words.contains("workflow") || words.contains("software")))
(d.getValue().toLowerCase().contains("workflow") || d.getValue().toLowerCase().contains("software"))))
return true; return true;
if (r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("galaxy")) && if (r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("galaxy")) &&
(r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("workflow"))) || (r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("workflow"))) ||
r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("software"))) r.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("software")))
@ -179,7 +192,11 @@ public class SparkEoscTag {
private static boolean containsCriteriaNotebook(Software s) { private static boolean containsCriteriaNotebook(Software s) {
if (s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("jupyter"))) if (s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("jupyter")))
return true; return true;
if(s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("python") && if (s
.getSubject()
.stream()
.anyMatch(
sbj -> sbj.getValue().toLowerCase().contains("python") &&
sbj.getValue().toLowerCase().contains("notebook"))) sbj.getValue().toLowerCase().contains("notebook")))
return true; return true;
if (s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("python")) && if (s.getSubject().stream().anyMatch(sbj -> sbj.getValue().toLowerCase().contains("python")) &&
@ -188,11 +205,27 @@ public class SparkEoscTag {
return false; return false;
} }
private static boolean containsTitleNotebook(Software s) { private static Set<String> getSubjects(List<StructuredProperty> s) {
if (s.getTitle().stream().anyMatch(t -> t.getValue().toLowerCase().contains("jupyter") && Set<String> subjects = new HashSet<>();
t.getValue().toLowerCase().contains("notebook"))) s.stream().forEach(sbj -> subjects.addAll(Arrays.asList(sbj.getValue().toLowerCase().split(" "))));
return true; s.stream().forEach(sbj -> subjects.add(sbj.getValue().toLowerCase()));
return false; return subjects;
} }
private static Set<String> getWordsSP(List<StructuredProperty> elem) {
Set<String> words = new HashSet<>();
elem
.forEach(
t -> words.addAll(Arrays.asList(t.getValue().toLowerCase().replaceAll("[^a-zA-Z ]", "").split(" "))));
return words;
}
private static Set<String> getWordsF(List<Field<String>> elem) {
Set<String> words = new HashSet<>();
elem
.forEach(
t -> words.addAll(Arrays.asList(t.getValue().toLowerCase().replaceAll("[^a-zA-Z ]", "").split(" "))));
return words;
}
} }

470
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/bulktag/EOSCTagJobTest.java
View File

@ -1,8 +1,13 @@
package eu.dnetlib.dhp.bulktag; package eu.dnetlib.dhp.bulktag;
import com.fasterxml.jackson.databind.ObjectMapper; import static eu.dnetlib.dhp.bulktag.community.TaggingConstants.ZENODO_COMMUNITY_INDICATOR;
import eu.dnetlib.dhp.schema.oaf.*;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.List;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils; import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
@ -11,6 +16,7 @@ import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.MapFunction; import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Encoders; import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.Row; import org.apache.spark.sql.Row;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession; import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll; import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.Assertions; import org.junit.jupiter.api.Assertions;
@ -19,26 +25,20 @@ import org.junit.jupiter.api.Test;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import java.io.IOException; import com.fasterxml.jackson.databind.ObjectMapper;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.List;
import static eu.dnetlib.dhp.bulktag.community.TaggingConstants.ZENODO_COMMUNITY_INDICATOR; import eu.dnetlib.dhp.schema.oaf.*;
public class EOSCTagJobTest { public class EOSCTagJobTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper(); private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static SparkSession spark; private static SparkSession spark;
private static Path workingDir; private static Path workingDir;
private static final Logger log = LoggerFactory.getLogger(EOSCTagJobTest.class); private static final Logger log = LoggerFactory.getLogger(EOSCTagJobTest.class);
@BeforeAll @BeforeAll
public static void beforeAll() throws IOException { public static void beforeAll() throws IOException {
workingDir = Files.createTempDirectory(EOSCTagJobTest.class.getSimpleName()); workingDir = Files.createTempDirectory(EOSCTagJobTest.class.getSimpleName());
@ -70,21 +70,37 @@ public class EOSCTagJobTest {
@Test @Test
void jupyterUpdatesTest() throws Exception { void jupyterUpdatesTest() throws Exception {
spark.read().textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/software").getPath()) spark
.map((MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class), Encoders.bean(Software.class)) .read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/software").getPath())
.map(
(MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class),
Encoders.bean(Software.class))
.write() .write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")
.json(workingDir.toString() + "/input/software"); .json(workingDir.toString() + "/input/software");
spark.read().textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/dataset").getPath()) spark
.map((MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class), Encoders.bean(Dataset.class)) .read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/dataset").getPath())
.map(
(MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class),
Encoders.bean(Dataset.class))
.write() .write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")
.json(workingDir.toString() + "/input/dataset"); .json(workingDir.toString() + "/input/dataset");
spark.read().textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/otherresearchproduct").getPath()) spark
.map((MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER.readValue(value, OtherResearchProduct.class), Encoders.bean(OtherResearchProduct.class)) .read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/jupyter/otherresearchproduct").getPath())
.map(
(MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER
.readValue(value, OtherResearchProduct.class),
Encoders.bean(OtherResearchProduct.class))
.write() .write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")
.json(workingDir.toString() + "/input/otherresearchproduct"); .json(workingDir.toString() + "/input/otherresearchproduct");
@ -106,36 +122,109 @@ public class EOSCTagJobTest {
Assertions.assertEquals(10, tmp.count()); Assertions.assertEquals(10, tmp.count());
Assertions.assertEquals(4, tmp.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook"))).count()); Assertions
.assertEquals(
4,
tmp
.filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook")))
.count());
Assertions.assertEquals(2, tmp.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertTrue(tmp.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4")).collect() 2, tmp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook"))); .filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions
.assertEquals(
5, tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions.assertEquals(5, tmp.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertFalse(tmp.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11")).collect() 9, tmp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook"))); .filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions.assertEquals(9, tmp.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertTrue(tmp.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56")).collect() 5, tmp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook"))); .filter(sw -> sw.getId().equals("50|od______1582::5aec1186054301b66c0c5dc35972a589"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::5aec1186054301b66c0c5dc35972a589"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions.assertEquals(5, tmp.filter(sw -> sw.getId().equals("50|od______1582::5aec1186054301b66c0c5dc35972a589")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertFalse(tmp.filter(sw -> sw.getId().equals("50|od______1582::5aec1186054301b66c0c5dc35972a589")).collect() 9, tmp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook"))); .filter(sw -> sw.getId().equals("50|od______1582::639909adfad9d708308f2aedb733e4a0"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::639909adfad9d708308f2aedb733e4a0"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions.assertEquals(9, tmp.filter(sw -> sw.getId().equals("50|od______1582::639909adfad9d708308f2aedb733e4a0")).collect() List<StructuredProperty> subjects = tmp
.get(0).getSubject().size()); .filter(sw -> sw.getId().equals("50|od______1582::6e7a9b21a2feef45673890432af34244"))
Assertions.assertTrue(tmp.filter(sw -> sw.getId().equals("50|od______1582::639909adfad9d708308f2aedb733e4a0")).collect() .collect()
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook"))); .get(0)
.getSubject();
List<StructuredProperty> subjects = tmp.filter(sw -> sw.getId().equals("50|od______1582::6e7a9b21a2feef45673890432af34244")).collect()
.get(0).getSubject();
Assertions.assertEquals(8, subjects.size()); Assertions.assertEquals(8, subjects.size());
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook"))); Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("EOSC::Jupyter Notebook")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("jupyter"))); Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("jupyter")));
@ -146,43 +235,74 @@ public class EOSCTagJobTest {
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("flux de gaz"))); Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("flux de gaz")));
Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("flux de liquide"))); Assertions.assertTrue(subjects.stream().anyMatch(s -> s.getValue().equals("flux de liquide")));
Assertions
Assertions.assertEquals(10, sc .assertEquals(
10, sc
.textFile(workingDir.toString() + "/input/dataset") .textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class)).count()); .map(item -> OBJECT_MAPPER.readValue(item, Dataset.class))
.count());
Assertions.assertEquals(0, sc Assertions
.assertEquals(
0, sc
.textFile(workingDir.toString() + "/input/dataset") .textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class)).filter(ds -> ds.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook"))).count()); .map(item -> OBJECT_MAPPER.readValue(item, Dataset.class))
.filter(
ds -> ds.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook")))
.count());
Assertions
Assertions.assertEquals(10, sc .assertEquals(
10, sc
.textFile(workingDir.toString() + "/input/otherresearchproduct") .textFile(workingDir.toString() + "/input/otherresearchproduct")
.map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class)).count()); .map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class))
.count());
Assertions.assertEquals(0, sc Assertions
.assertEquals(
0, sc
.textFile(workingDir.toString() + "/input/otherresearchproduct") .textFile(workingDir.toString() + "/input/otherresearchproduct")
.map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class)).filter(ds -> ds.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook"))).count()); .map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class))
.filter(
ds -> ds.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Jupyter Notebook")))
.count());
// spark.stop();
} }
@Test @Test
void galaxyUpdatesTest() throws Exception { void galaxyUpdatesTest() throws Exception {
spark.read().textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/software").getPath()) spark
.map((MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class), Encoders.bean(Software.class)) .read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/software").getPath())
.map(
(MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class),
Encoders.bean(Software.class))
.write() .write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")
.json(workingDir.toString() + "/input/software"); .json(workingDir.toString() + "/input/software");
spark.read().textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/dataset").getPath()) spark
.map((MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class), Encoders.bean(Dataset.class)) .read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/dataset").getPath())
.map(
(MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class),
Encoders.bean(Dataset.class))
.write() .write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")
.json(workingDir.toString() + "/input/dataset"); .json(workingDir.toString() + "/input/dataset");
spark.read().textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/otherresearchproduct").getPath()) spark
.map((MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER.readValue(value, OtherResearchProduct.class), Encoders.bean(OtherResearchProduct.class)) .read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/galaxy/otherresearchproduct").getPath())
.map(
(MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER
.readValue(value, OtherResearchProduct.class),
Encoders.bean(OtherResearchProduct.class))
.write() .write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip") .option("compression", "gzip")
.json(workingDir.toString() + "/input/otherresearchproduct"); .json(workingDir.toString() + "/input/otherresearchproduct");
@ -204,46 +324,224 @@ public class EOSCTagJobTest {
Assertions.assertEquals(10, tmp.count()); Assertions.assertEquals(10, tmp.count());
Assertions.assertEquals(2, tmp.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow"))).count()); Assertions
.assertEquals(
2,
tmp
.filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow")))
.count());
Assertions.assertEquals(2, tmp.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertTrue(tmp.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4")).collect() 2, tmp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow"))); .filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::4132f5ec9496f0d6adc7b00a50a56ff4"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions
.assertEquals(
6, tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions.assertEquals(6, tmp.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertTrue(tmp.filter(sw -> sw.getId().equals("50|od______1582::501b25d420f808c8eddcd9b16e917f11")).collect() 8, tmp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow"))); .filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
tmp
.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions.assertEquals(8, tmp.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56")).collect() JavaRDD<OtherResearchProduct> orp = sc
.get(0).getSubject().size()); .textFile(workingDir.toString() + "/input/otherresearchproduct")
Assertions.assertFalse(tmp.filter(sw -> sw.getId().equals("50|od______1582::581621232a561b7e8b4952b18b8b0e56")).collect() .map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class));
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
JavaRDD<OtherResearchProduct> orp = sc.textFile(workingDir.toString() + "/input/otherresearchproduct").map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class));
Assertions.assertEquals(10, orp.count()); Assertions.assertEquals(10, orp.count());
Assertions.assertEquals(2, orp.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow"))).count()); Assertions
.assertEquals(
2,
orp
.filter(
s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Galaxy Workflow")))
.count());
Assertions
.assertEquals(
3, orp
.filter(sw -> sw.getId().equals("50|od______2017::0750a4d0782265873d669520f5e33c07"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertTrue(
orp
.filter(sw -> sw.getId().equals("50|od______2017::0750a4d0782265873d669520f5e33c07"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions.assertEquals(3, orp.filter(sw -> sw.getId().equals("50|od______2017::0750a4d0782265873d669520f5e33c07")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertTrue(orp.filter(sw -> sw.getId().equals("50|od______2017::0750a4d0782265873d669520f5e33c07")).collect() 2, orp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow"))); .filter(sw -> sw.getId().equals("50|od______2017::1bd97baef19dbd2db3203b112bb83bc5"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertFalse(
orp
.filter(sw -> sw.getId().equals("50|od______2017::1bd97baef19dbd2db3203b112bb83bc5"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
Assertions.assertEquals(2, orp.filter(sw -> sw.getId().equals("50|od______2017::1bd97baef19dbd2db3203b112bb83bc5")).collect() Assertions
.get(0).getSubject().size()); .assertEquals(
Assertions.assertFalse(orp.filter(sw -> sw.getId().equals("50|od______2017::1bd97baef19dbd2db3203b112bb83bc5")).collect() 3, orp
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow"))); .filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72"))
.collect()
Assertions.assertEquals(3, orp.filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72")).collect() .get(0)
.get(0).getSubject().size()); .getSubject()
Assertions.assertTrue(orp.filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72")).collect() .size());
.get(0).getSubject().stream().anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow"))); Assertions
.assertTrue(
orp
.filter(sw -> sw.getId().equals("50|od______2017::1e400f1747487fd15998735c41a55c72"))
.collect()
.get(0)
.getSubject()
.stream()
.anyMatch(s -> s.getValue().equals("EOSC::Galaxy Workflow")));
} }
@Test
void twitterUpdatesTest() throws Exception {
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/twitter/software").getPath())
.map(
(MapFunction<String, Software>) value -> OBJECT_MAPPER.readValue(value, Software.class),
Encoders.bean(Software.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/software");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/twitter/dataset").getPath())
.map(
(MapFunction<String, Dataset>) value -> OBJECT_MAPPER.readValue(value, Dataset.class),
Encoders.bean(Dataset.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/dataset");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/eosctag/twitter/otherresearchproduct").getPath())
.map(
(MapFunction<String, OtherResearchProduct>) value -> OBJECT_MAPPER
.readValue(value, OtherResearchProduct.class),
Encoders.bean(OtherResearchProduct.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/otherresearchproduct");
SparkEoscTag
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input",
"-workingPath", workingDir.toString() + "/working"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Software> tmp = sc
.textFile(workingDir.toString() + "/input/software")
.map(item -> OBJECT_MAPPER.readValue(item, Software.class));
Assertions.assertEquals(10, tmp.count());
Assertions
.assertEquals(
0,
tmp
.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Twitter Data")))
.count());
JavaRDD<OtherResearchProduct> orp = sc
.textFile(workingDir.toString() + "/input/otherresearchproduct")
.map(item -> OBJECT_MAPPER.readValue(item, OtherResearchProduct.class));
Assertions.assertEquals(10, orp.count());
Assertions
.assertEquals(
3,
orp
.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Twitter Data")))
.count());
JavaRDD<Dataset> dats = sc
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
Assertions.assertEquals(10, dats.count());
Assertions
.assertEquals(
2,
dats
.filter(s -> s.getSubject().stream().anyMatch(sbj -> sbj.getValue().equals("EOSC::Twitter Data")))
.count());
}
} }

4
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/twitter/dataset/dataset_10.json
View File

File diff suppressed because one or more lines are too long

10
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/twitter/otherresearchproduct/otherresearchproduct_10.json
View File

File diff suppressed because one or more lines are too long

2
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/eosctag/twitter/software/software_10.json
View File

File diff suppressed because one or more lines are too long