D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

[Enrichment single step] changed test for country propagation and fixed inconsistencies

This commit is contained in:
Miriam Baglioni 2022-11-24 09:36:10 +01:00
parent 2e6af7c655
commit 481c4e28d1
18 changed files with 915 additions and 154 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java
View File

@ -80,10 +80,9 @@ public class SparkBulkTagJob {
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
execBulkTag(spark, inputPath, outputPath, protoMappingParams, resultClazz, cc);
});
spark ->
execBulkTag(spark, inputPath, outputPath, protoMappingParams, resultClazz, cc)
);
}
private static <R extends Result> void execBulkTag(

58
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/eosc/SparkEoscBulkTag.java
View File

@ -16,6 +16,7 @@ import javax.print.attribute.DocAttributeSet;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
import org.apache.spark.api.java.function.ForeachFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
@ -34,6 +35,7 @@ import eu.dnetlib.dhp.bulktag.community.*;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.*;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import scala.Tuple2;
/**
* @author miriam.baglioni
@ -44,6 +46,11 @@ public class SparkEoscBulkTag implements Serializable {
private static final Logger log = LoggerFactory.getLogger(SparkEoscBulkTag.class);
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static String OPENAIRE_3 = "openaire3.0";
private static String OPENAIRE_4 = "openaire-pub_4.0";
private static String OPENAIRE_CRIS = "openaire-cris_1.1";
private static String OPENAIRE_DATA = "openaire2.0_data";
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
@ -72,6 +79,9 @@ public class SparkEoscBulkTag implements Serializable {
final String resultClassName = parser.get("resultTableName");
log.info("resultTableName: {}", resultClassName);
final String resultType = parser.get("resultType");
log.info("resultType: {}", resultType);
Class<? extends Result> resultClazz = (Class<? extends Result>) Class.forName(resultClassName);
SparkConf conf = new SparkConf();
@ -82,41 +92,71 @@ public class SparkEoscBulkTag implements Serializable {
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, workingPath);
execBulkTag(spark, inputPath, workingPath, datasourceMapPath, resultClazz);
selectCompliantDatasources(spark, inputPath, workingPath, datasourceMapPath);
execBulkTag(spark, inputPath, workingPath, resultType, resultClazz);
});
}
private static void selectCompliantDatasources(SparkSession spark, String inputPath, String workingPath,
String datasourceMapPath) {
Dataset<Datasource> datasources = readPath(spark, inputPath + "datasource", Datasource.class)
.filter((FilterFunction<Datasource>) ds -> {
final String compatibility = ds.getOpenairecompatibility().getClassid();
return compatibility.equalsIgnoreCase(OPENAIRE_3) ||
compatibility.equalsIgnoreCase(OPENAIRE_4) ||
compatibility.equalsIgnoreCase(OPENAIRE_CRIS) ||
compatibility.equalsIgnoreCase(OPENAIRE_DATA);
});
Dataset<DatasourceMaster> datasourceMaster = readPath(spark, datasourceMapPath, DatasourceMaster.class);
datasources
.joinWith(datasourceMaster, datasources.col("id").equalTo(datasourceMaster.col("master")), "left")
.map(
(MapFunction<Tuple2<Datasource, DatasourceMaster>, DatasourceMaster>) t2 -> t2._2(),
Encoders.bean(DatasourceMaster.class))
.filter(Objects::nonNull)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingPath + "datasource");
}
private static <R extends Result> void execBulkTag(
SparkSession spark,
String inputPath,
String workingPath,
String datasourceMapPath,
String resultType,
Class<R> resultClazz) {
List<String> hostedByList = readPath(spark, datasourceMapPath, DatasourceMaster.class)
List<String> hostedByList = readPath(spark, workingPath + "datasource", DatasourceMaster.class)
.map((MapFunction<DatasourceMaster, String>) dm -> dm.getMaster(), Encoders.STRING())
.collectAsList();
readPath(spark, inputPath, resultClazz)
.map(patchResult(), Encoders.bean(resultClazz))
.filter(Objects::nonNull)
readPath(spark, inputPath + resultType, resultClazz)
.map(
(MapFunction<R, R>) value -> enrich(value, hostedByList),
Encoders.bean(resultClazz))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingPath);
.json(workingPath + resultType);
readPath(spark, workingPath, resultClazz)
readPath(spark, workingPath + resultType, resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath);
.json(inputPath + resultType);
}
private static <R extends Result> R enrich(R value, List<String> hostedByList) {
if (value.getDataInfo().getDeletedbyinference() == null) {
value.getDataInfo().setDeletedbyinference(false);
}
if (value.getContext() == null) {
value.setContext(new ArrayList<>());
}
if (value
.getInstance()
.stream()

2
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java
View File

@ -66,7 +66,7 @@ public class PrepareDatasourceCountryAssociation {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, workingPath);
removeOutputDir(spark, workingPath + "/datasourceCountry");
prepareDatasourceCountryAssociation(
spark,
Arrays.asList(parser.get("whitelist").split(";")),

27
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java
View File

@ -8,11 +8,13 @@ import java.util.ArrayList;
import java.util.HashSet;
import java.util.Set;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.countrypropagation.pojo.CountrySbs;
import eu.dnetlib.dhp.countrypropagation.pojo.DatasourceCountry;
import eu.dnetlib.dhp.countrypropagation.pojo.ResultCountrySet;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.ForeachFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
import org.apache.spark.sql.*;
@ -44,6 +46,7 @@ public class PrepareResultCountrySet {
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String workingPath = parser.get("workingPath");
log.info("workingPath: {}", workingPath);
String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
@ -54,11 +57,6 @@ public class PrepareResultCountrySet {
final String resultType = resultClassName.substring(resultClassName.lastIndexOf(".") + 1).toLowerCase();
log.info("resultType: {}", resultType);
String outputPath = workingPath + "/" + resultType; // parser.get("outputPath");
log.info("outputPath: {}", outputPath);
final String datasourcecountrypath = workingPath + "/datasourceCountry";// parser.get("preparedInfoPath");
log.info("preparedInfoPath: {}", datasourcecountrypath);
Class<? extends Result> resultClazz = (Class<? extends Result>) Class.forName(resultClassName);
@ -68,13 +66,12 @@ public class PrepareResultCountrySet {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
removeOutputDir(spark, workingPath + "/preparedInfo/" + resultType);
getPotentialResultToUpdate(
spark,
inputPath,
outputPath,
datasourcecountrypath,
workingPath + "/resultCfHb/" + resultType,
workingPath,
resultType,
resultClazz);
});
}
@ -82,16 +79,18 @@ public class PrepareResultCountrySet {
private static <R extends Result> void getPotentialResultToUpdate(
SparkSession spark,
String inputPath,
String outputPath,
String datasourcecountrypath,
String workingPath,
String resultType,
Class<R> resultClazz) {
PropagationConstant.createCfHbforResult(spark, inputPath, workingPath, resultClazz);
final String datasourcecountrypath = workingPath + "/datasourceCountry";
final String cfhbpath = workingPath + "/resultCfHb/" + resultType;
final String outputPath = workingPath + "/preparedInfo/" + resultType;
PropagationConstant.createCfHbforResult(spark, inputPath, cfhbpath, resultClazz);
Dataset<DatasourceCountry> datasource_country = readPath(spark, datasourcecountrypath, DatasourceCountry.class);
Dataset<EntityEntityRel> cfhb = readPath(spark, workingPath, EntityEntityRel.class);
Dataset<EntityEntityRel> cfhb = readPath(spark, cfhbpath, EntityEntityRel.class);
datasource_country
.joinWith(

27
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java
View File

@ -52,12 +52,14 @@ public class SparkCountryPropagationJob {
String workingPath = parser.get("workingPath");
log.info("workingPath: {}", workingPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
final String resultClassName = parser.get("resultTableName");
log.info("resultTableName: {}", resultClassName);
final String resultType = resultClassName.substring(resultClassName.lastIndexOf(".") + 1).toLowerCase();
log.info("resultType: {}", resultType);
Class<? extends Result> resultClazz = (Class<? extends Result>) Class.forName(resultClassName);
SparkConf conf = new SparkConf();
@ -65,12 +67,12 @@ public class SparkCountryPropagationJob {
conf,
isSparkSessionManaged,
spark -> {
removeOutputDir(spark, outputPath);
removeOutputDir(spark, workingPath + "/" + resultType);
execPropagation(
spark,
sourcePath,
workingPath,
outputPath,
resultType,
resultClazz);
});
}
@ -78,18 +80,15 @@ public class SparkCountryPropagationJob {
private static <R extends Result> void execPropagation(
SparkSession spark,
String sourcePath,
String preparedInfoPath,
String outputPath,
String workingPath,
String resultType,
Class<R> resultClazz) {
log.info("Reading Graph table from: {}", sourcePath);
Dataset<R> res = readPath(spark, sourcePath, resultClazz);
log.info("Reading prepared info: {}", preparedInfoPath);
Dataset<ResultCountrySet> prepared = spark
.read()
.json(preparedInfoPath)
.as(Encoders.bean(ResultCountrySet.class));
log.info("Reading prepared info: {}", workingPath + "/preparedInfo/" + resultType);
Dataset<ResultCountrySet> prepared = readPath(spark, workingPath + "/preparedInfo/" + resultType, ResultCountrySet.class);
res
.joinWith(prepared, res.col("id").equalTo(prepared.col("resultId")), "left_outer")
@ -97,9 +96,9 @@ public class SparkCountryPropagationJob {
.write()
.option("compression", "gzip")
.mode(SaveMode.Overwrite)
.json(outputPath);
.json(workingPath + "/" + resultType);
readPath(spark, outputPath, resultClazz)
readPath(spark, workingPath + "/" + resultType, resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")

7
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json
View File

@ -29,6 +29,13 @@
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
},
{
"paramName": "rt",
"paramLongName": "resultType",
"paramDescription": "the result type",
"paramRequired": true
}
]

9
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json
View File

@ -11,17 +11,12 @@
"paramDescription": "the name of the result table we are currently working on",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},
{
"paramName": "wp",
"paramLongName": "workingPath",
"paramDescription": "the path where prepared info have been stored",
"paramRequired": false
"paramRequired": true
},
{
"paramName": "ssm",

4
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json
View File

@ -6,8 +6,8 @@
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramName": "wp",
"paramLongName": "workingPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},

4
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml
View File

@ -293,10 +293,6 @@
<name>sourcePath</name>
<value>${outputPath}</value>
</property>
<property>
<name>outputPath</name>
<value>${workingDir}/country/result</value>
</property>
<property>
<name>whitelist</name>
<value>${datasourceWhitelistForCountryPropagation}</value>

58
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml
View File

@ -12,11 +12,6 @@
<name>allowedtypes</name>
<description>the allowed types</description>
</property>
<property>
<name>outputPath</name>
<description>the output path</description>
</property>
</parameters>
<global>
@ -60,18 +55,18 @@
<arg>--allowedtypes</arg><arg>${allowedtypes}</arg>
<arg>--workingPath</arg><arg>${workingDir}/country</arg>
</spark>
<ok to="fork_join_prepare_result_country"/>
<ok to="fork_prepare_result_country"/>
<error to="Kill"/>
</action>
<fork name="fork_join_prepare_result_country">
<path start="join_prepareresult_publication"/>
<path start="join_prepareresult_dataset"/>
<path start="join_prepareresult_otherresearchproduct"/>
<path start="join_prepareresult_software"/>
<fork name="fork_prepare_result_country">
<path start="prepareresult_publication"/>
<path start="prepareresult_dataset"/>
<path start="prepareresult_otherresearchproduct"/>
<path start="prepareresult_software"/>
</fork>
<action name="join_prepareresult_publication">
<action name="prepareresult_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -99,7 +94,7 @@
<error to="Kill"/>
</action>
<action name="join_prepareresult_dataset">
<action name="prepareresult_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -127,7 +122,7 @@
<error to="Kill"/>
</action>
<action name="join_prepareresult_otherresearchproduct">
<action name="prepareresult_otherresearchproduct">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -155,7 +150,7 @@
<error to="Kill"/>
</action>
<action name="join_prepareresult_software">
<action name="prepareresult_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -185,14 +180,14 @@
<join name="wait_prepare" to="fork_join_apply_country_propagation"/>
<fork name="fork_join_apply_country_propagation">
<path start="join_propagation_publication"/>
<path start="join_propagation_dataset"/>
<path start="join_propagation_otherresearchproduct"/>
<path start="join_propagation_software"/>
<fork name="fork_apply_country_propagation">
<path start="propagation_publication"/>
<path start="propagation_dataset"/>
<path start="propagation_otherresearchproduct"/>
<path start="propagation_software"/>
</fork>
<action name="join_propagation_publication">
<action name="propagation_publication">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -213,15 +208,15 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/publication</arg>
<arg>--workingPath</arg><arg>${workingDir}/country</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/result/publication</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="join_propagation_dataset">
<action name="propagation_dataset">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -242,15 +237,15 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/dataset</arg>
<arg>--workingPath</arg><arg>${workingDir}/country</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/result/dataset</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="join_propagation_otherresearchproduct">
<action name="propagation_otherresearchproduct">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -271,15 +266,15 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/otherresearchproduct</arg>
<arg>--workingPath</arg><arg>${workingDir}/country</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/result/otherresearchproduct</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<action name="join_propagation_software">
<action name="propagation_software">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
@ -300,9 +295,8 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/software</arg>
<arg>--workingPath</arg><arg>${workingDir}/country</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/result/software</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>

108
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/bulktag/EOSCContextTaggingTest.java
View File

@ -27,16 +27,11 @@ import org.slf4j.LoggerFactory;
*/
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.bulktag.eosc.DatasourceMaster;
import eu.dnetlib.dhp.bulktag.eosc.SparkEoscBulkTag;
import eu.dnetlib.dhp.schema.oaf.Dataset;
import eu.dnetlib.dhp.schema.oaf.OtherResearchProduct;
import eu.dnetlib.dhp.schema.oaf.Software;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.*;
//"50|475c1990cbb2::0fecfb874d9395aa69d2f4d7cd1acbea" has instance hostedby eosc
//"50|475c1990cbb2::3185cd5d8a2b0a06bb9b23ef11748eb1" has instance hostedby eosc
//"50|475c1990cbb2::449f28eefccf9f70c04ad70d61e041c7" has two instance one hostedby eosc
//"50|475c1990cbb2::3894c94123e96df8a21249957cf160cb" has EoscTag
public class EOSCContextTaggingTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@ -78,6 +73,22 @@ public class EOSCContextTaggingTest {
@Test
void EoscContextTagTest() throws Exception {
//"50|475c1990cbb2::0fecfb874d9395aa69d2f4d7cd1acbea" has instance hostedby eosc (cris)
//"50|475c1990cbb2::3185cd5d8a2b0a06bb9b23ef11748eb1" has instance hostedby eosc (zenodo)
//"50|475c1990cbb2::449f28eefccf9f70c04ad70d61e041c7" has two instance one hostedby eosc (wrong compatibility)
//"50|475c1990cbb2::3894c94123e96df8a21249957cf160cb" has EoscTag
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/bulktag/eosc/datasource/datasource_1").getPath())
.map(
(MapFunction<String, Datasource>) value -> OBJECT_MAPPER.readValue(value, Datasource.class),
Encoders.bean(Datasource.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/datasource");
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/bulktag/eosc/dataset/dataset_10.json").getPath())
@ -94,17 +105,24 @@ public class EOSCContextTaggingTest {
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input/dataset",
"-workingPath", workingDir.toString() + "/working/dataset",
workingDir.toString() + "/input/",
"-workingPath", workingDir.toString() + "/working/",
"-datasourceMapPath",
getClass()
.getResource("/eu/dnetlib/dhp/bulktag/eosc/datasourceMasterAssociation/datasourceMaster")
.getPath(),
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Dataset"
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Dataset",
"-resultType", "dataset"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
Assertions
.assertEquals(
2, sc
.textFile(workingDir.toString() + "/working/datasource")
.map(item -> OBJECT_MAPPER.readValue(item, DatasourceMaster.class))
.count());
JavaRDD<Dataset> tmp = sc
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
@ -113,7 +131,7 @@ public class EOSCContextTaggingTest {
Assertions
.assertEquals(
4,
2,
tmp
.filter(
s -> s.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
@ -140,17 +158,17 @@ public class EOSCContextTaggingTest {
Assertions
.assertEquals(
1,
0,
tmp
.filter(
d -> d.getId().equals("50|475c1990cbb2::3894c94123e96df8a21249957cf160cb")
d -> d.getId().equals("50|475c1990cbb2::449f28eefccf9f70c04ad70d61e041c7")
&&
d.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
.count());
Assertions
.assertEquals(
1,
0,
tmp
.filter(
d -> d.getId().equals("50|475c1990cbb2::3894c94123e96df8a21249957cf160cb")
@ -159,4 +177,62 @@ public class EOSCContextTaggingTest {
.count());
}
@Test
void EoscContextTagTestEmptyDatasource() throws Exception {
spark
.read()
.textFile(getClass().getResource("/eu/dnetlib/dhp/bulktag/eosc/dataset/dataset_10.json").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/bulktag/eosc/datasource/datasource").getPath())
.map(
(MapFunction<String, Datasource>) value -> OBJECT_MAPPER.readValue(value, Datasource.class),
Encoders.bean(Datasource.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingDir.toString() + "/input/datasource");
SparkEoscBulkTag
.main(
new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(),
"-sourcePath",
workingDir.toString() + "/input/",
"-workingPath", workingDir.toString() + "/working/",
"-datasourceMapPath",
getClass()
.getResource("/eu/dnetlib/dhp/bulktag/eosc/datasourceMasterAssociation/datasourceMaster")
.getPath(),
"-resultTableName", "eu.dnetlib.dhp.schema.oaf.Dataset",
"-resultType", "dataset"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Dataset> tmp = sc
.textFile(workingDir.toString() + "/input/dataset")
.map(item -> OBJECT_MAPPER.readValue(item, Dataset.class));
Assertions.assertEquals(10, tmp.count());
Assertions
.assertEquals(
0,
tmp
.filter(
s -> s.getContext().stream().anyMatch(c -> c.getId().equals("eosc")))
.count());
}
}

634
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/countrypropagation/CountryPropagationAllStepsTest.java Normal file
View File

@ -0,0 +1,634 @@
package eu.dnetlib.dhp.countrypropagation;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.countrypropagation.pojo.DatasourceCountry;
import eu.dnetlib.dhp.countrypropagation.pojo.ResultCountrySet;
import eu.dnetlib.dhp.schema.oaf.Country;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Qualifier;
import eu.dnetlib.dhp.schema.oaf.Software;
import org.apache.commons.io.FileUtils;
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.FlatMapFunction;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SparkSession;
import org.junit.jupiter.api.AfterAll;
import org.junit.jupiter.api.Assertions;
import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test;
import scala.Tuple2;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
/**
* @author miriam.baglioni
* @Date 23/11/22
*/
public class CountryPropagationAllStepsTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static SparkSession spark;
private static Path workingDir;
@BeforeAll
public static void beforeAll() throws IOException {
workingDir = Files.createTempDirectory(DatasourceCountryPreparationTest.class.getSimpleName());
SparkConf conf = new SparkConf();
conf.setAppName(DatasourceCountryPreparationTest.class.getSimpleName());
conf.setMaster("local[*]");
conf.set("spark.driver.host", "localhost");
conf.set("hive.metastore.local", "true");
conf.set("spark.ui.enabled", "false");
conf.set("spark.sql.warehouse.dir", workingDir.toString());
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
spark = SparkSession
.builder()
.appName(DatasourceCountryPreparationTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
spark.stop();
}
@Test
public void allStepsTest() throws Exception {
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/graph")
.getPath();
PrepareDatasourceCountryAssociation
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"--workingPath", workingDir.toString() + "/country",
"--allowedtypes", "pubsrepository::institutional",
"--whitelist",
"10|openaire____::3795d6478e30e2c9f787d427ff160944;10|opendoar____::16e6a3326dd7d868cbc926602a61e4d0;10|eurocrisdris::fe4903425d9040f680d8610d9079ea14;10|openaire____::5b76240cc27a58c6f7ceef7d8c36660e;10|openaire____::172bbccecf8fca44ab6a6653e84cb92a;10|openaire____::149c6590f8a06b46314eed77bfca693f;10|eurocrisdris::a6026877c1a174d60f81fd71f62df1c1;10|openaire____::4692342f0992d91f9e705c26959f09e0;10|openaire____::8d529dbb05ec0284662b391789e8ae2a;10|openaire____::345c9d171ef3c5d706d08041d506428c;10|opendoar____::1c1d4df596d01da60385f0bb17a4a9e0;10|opendoar____::7a614fd06c325499f1680b9896beedeb;10|opendoar____::1ee3dfcd8a0645a25a35977997223d22;10|opendoar____::d296c101daa88a51f6ca8cfc1ac79b50;10|opendoar____::798ed7d4ee7138d49b8828958048130a;10|openaire____::c9d2209ecc4d45ba7b4ca7597acb88a2;10|eurocrisdris::c49e0fe4b9ba7b7fab717d1f0f0a674d;10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539;10|eurocrisdris::432ca599953ff50cd4eeffe22faf3e48"
});
sc.textFile(
getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/graph/publication")
.getPath()).saveAsTextFile(workingDir.toString() + "/source/publication");
sc
.textFile(
getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/graph/software")
.getPath()).saveAsTextFile(workingDir.toString() + "/source/software");
verifyDatasourceCountry();
PrepareResultCountrySet
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--workingPath", workingDir.toString() + "/country",
"--sourcePath", workingDir.toString() + "/source/publication",
"--resultTableName", Publication.class.getCanonicalName()
});
verifyResultCountrySet();
PrepareResultCountrySet
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--workingPath", workingDir.toString() + "/country",
"--sourcePath", workingDir.toString() + "/source/software",
"--resultTableName", Software.class.getCanonicalName()
});
SparkCountryPropagationJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath",workingDir.toString() + "/source/publication",
"-resultTableName", Publication.class.getCanonicalName(),
"-workingPath", workingDir.toString() +"/country"
});
verifyPropagationPublication();
SparkCountryPropagationJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath",workingDir.toString() + "/source/software",
"-resultTableName", Software.class.getCanonicalName(),
"-workingPath", workingDir.toString() + "/country"
});
verifyPropagationSoftware();
}
void verifyDatasourceCountry(){
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<DatasourceCountry> tmp = sc
.textFile(workingDir.toString() + "/country/datasourceCountry")
.map(item -> OBJECT_MAPPER.readValue(item, DatasourceCountry.class));
Assertions.assertEquals(3, tmp.count());
Assertions
.assertEquals(
1, tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|eurocrisdris::fe4903425d9040f680d8610d9079ea14"))
.count());
Assertions
.assertEquals(
1, tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|opendoar____::f0dd4a99fba6075a9494772b58f95280"))
.count());
Assertions
.assertEquals(
1, tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539"))
.count());
Assertions
.assertEquals(
"NL", tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|eurocrisdris::fe4903425d9040f680d8610d9079ea14"))
.collect()
.get(0)
.getCountry()
.getClassid());
Assertions
.assertEquals(
"Netherlands", tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|eurocrisdris::fe4903425d9040f680d8610d9079ea14"))
.collect()
.get(0)
.getCountry()
.getClassname());
Assertions
.assertEquals(
"IT", tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|opendoar____::f0dd4a99fba6075a9494772b58f95280"))
.collect()
.get(0)
.getCountry()
.getClassid());
Assertions
.assertEquals(
"Italy", tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|opendoar____::f0dd4a99fba6075a9494772b58f95280"))
.collect()
.get(0)
.getCountry()
.getClassname());
Assertions
.assertEquals(
"FR", tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539"))
.collect()
.get(0)
.getCountry()
.getClassid());
Assertions
.assertEquals(
"France", tmp
.filter(
dsc -> dsc
.getDataSourceId()
.equals("10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539"))
.collect()
.get(0)
.getCountry()
.getClassname());
tmp.foreach(e -> System.out.println(OBJECT_MAPPER.writeValueAsString(e)));
}
void verifyResultCountrySet(){
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<ResultCountrySet> tmp = sc
.textFile(workingDir.toString() + "/country/preparedInfo/publication")
.map(item -> OBJECT_MAPPER.readValue(item, ResultCountrySet.class));
Assertions.assertEquals(5, tmp.count());
ResultCountrySet rc = tmp
.filter(r -> r.getResultId().equals("50|06cdd3ff4700::49ec404cee4e1452808aabeaffbd3072"))
.collect()
.get(0);
Assertions.assertEquals(1, rc.getCountrySet().size());
Assertions.assertEquals("NL", rc.getCountrySet().get(0).getClassid());
Assertions.assertEquals("Netherlands", rc.getCountrySet().get(0).getClassname());
rc = tmp
.filter(r -> r.getResultId().equals("50|07b5c0ccd4fe::e7f5459cc97865f2af6e3da964c1250b"))
.collect()
.get(0);
Assertions.assertEquals(1, rc.getCountrySet().size());
Assertions.assertEquals("NL", rc.getCountrySet().get(0).getClassid());
Assertions.assertEquals("Netherlands", rc.getCountrySet().get(0).getClassname());
rc = tmp
.filter(r -> r.getResultId().equals("50|355e65625b88::e7d48a470b13bda61f7ebe3513e20cb6"))
.collect()
.get(0);
Assertions.assertEquals(2, rc.getCountrySet().size());
Assertions
.assertTrue(
rc
.getCountrySet()
.stream()
.anyMatch(cs -> cs.getClassid().equals("IT") && cs.getClassname().equals("Italy")));
Assertions
.assertTrue(
rc
.getCountrySet()
.stream()
.anyMatch(cs -> cs.getClassid().equals("FR") && cs.getClassname().equals("France")));
rc = tmp
.filter(r -> r.getResultId().equals("50|355e65625b88::74009c567c81b4aa55c813db658734df"))
.collect()
.get(0);
Assertions.assertEquals(2, rc.getCountrySet().size());
Assertions
.assertTrue(
rc
.getCountrySet()
.stream()
.anyMatch(cs -> cs.getClassid().equals("IT") && cs.getClassname().equals("Italy")));
Assertions
.assertTrue(
rc
.getCountrySet()
.stream()
.anyMatch(cs -> cs.getClassid().equals("NL") && cs.getClassname().equals("Netherlands")));
rc = tmp
.filter(r -> r.getResultId().equals("50|355e65625b88::54a1c76f520bb2c8da27d12e42891088"))
.collect()
.get(0);
Assertions.assertEquals(2, rc.getCountrySet().size());
Assertions
.assertTrue(
rc
.getCountrySet()
.stream()
.anyMatch(cs -> cs.getClassid().equals("IT") && cs.getClassname().equals("Italy")));
Assertions
.assertTrue(
rc
.getCountrySet()
.stream()
.anyMatch(cs -> cs.getClassid().equals("FR") && cs.getClassname().equals("France")));
}
void verifyPropagationPublication(){
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Publication> tmp = sc
.textFile(workingDir.toString() + "/country/publication")
.map(item -> OBJECT_MAPPER.readValue(item, Publication.class));
Assertions.assertEquals(12, tmp.count());
Assertions.assertEquals(5, tmp.filter(r -> r.getCountry().size() > 0).count());
tmp
.foreach(
r -> r.getCountry().stream().forEach(c -> Assertions.assertEquals("dnet:countries", c.getSchemeid())));
tmp
.foreach(
r -> r
.getCountry()
.stream()
.forEach(c -> Assertions.assertEquals("dnet:countries", c.getSchemename())));
tmp
.foreach(
r -> r
.getCountry()
.stream()
.forEach(c -> Assertions.assertFalse(c.getDataInfo().getDeletedbyinference())));
tmp.foreach(r -> r.getCountry().stream().forEach(c -> Assertions.assertFalse(c.getDataInfo().getInvisible())));
tmp.foreach(r -> r.getCountry().stream().forEach(c -> Assertions.assertTrue(c.getDataInfo().getInferred())));
tmp
.foreach(
r -> r.getCountry().stream().forEach(c -> Assertions.assertEquals("0.85", c.getDataInfo().getTrust())));
tmp
.foreach(
r -> r
.getCountry()
.stream()
.forEach(c -> Assertions.assertEquals("propagation", c.getDataInfo().getInferenceprovenance())));
tmp
.foreach(
r -> r
.getCountry()
.stream()
.forEach(
c -> Assertions
.assertEquals("country:instrepos", c.getDataInfo().getProvenanceaction().getClassid())));
tmp
.foreach(
r -> r
.getCountry()
.stream()
.forEach(
c -> Assertions
.assertEquals(
"dnet:provenanceActions", c.getDataInfo().getProvenanceaction().getSchemeid())));
tmp
.foreach(
r -> r
.getCountry()
.stream()
.forEach(
c -> Assertions
.assertEquals(
"dnet:provenanceActions", c.getDataInfo().getProvenanceaction().getSchemename())));
List<Country> countries = tmp
.filter(r -> r.getId().equals("50|06cdd3ff4700::49ec404cee4e1452808aabeaffbd3072"))
.collect()
.get(0)
.getCountry();
Assertions.assertEquals(1, countries.size());
Assertions.assertEquals("NL", countries.get(0).getClassid());
Assertions.assertEquals("Netherlands", countries.get(0).getClassname());
countries = tmp
.filter(r -> r.getId().equals("50|07b5c0ccd4fe::e7f5459cc97865f2af6e3da964c1250b"))
.collect()
.get(0)
.getCountry();
Assertions.assertEquals(1, countries.size());
Assertions.assertEquals("NL", countries.get(0).getClassid());
Assertions.assertEquals("Netherlands", countries.get(0).getClassname());
countries = tmp
.filter(r -> r.getId().equals("50|355e65625b88::e7d48a470b13bda61f7ebe3513e20cb6"))
.collect()
.get(0)
.getCountry();
Assertions.assertEquals(2, countries.size());
Assertions
.assertTrue(
countries.stream().anyMatch(cs -> cs.getClassid().equals("IT") && cs.getClassname().equals("Italy")));
Assertions
.assertTrue(
countries.stream().anyMatch(cs -> cs.getClassid().equals("FR") && cs.getClassname().equals("France")));
countries = tmp
.filter(r -> r.getId().equals("50|355e65625b88::74009c567c81b4aa55c813db658734df"))
.collect()
.get(0)
.getCountry();
Assertions.assertEquals(2, countries.size());
Assertions
.assertTrue(
countries.stream().anyMatch(cs -> cs.getClassid().equals("IT") && cs.getClassname().equals("Italy")));
Assertions
.assertTrue(
countries
.stream()
.anyMatch(cs -> cs.getClassid().equals("NL") && cs.getClassname().equals("Netherlands")));
countries = tmp
.filter(r -> r.getId().equals("50|355e65625b88::54a1c76f520bb2c8da27d12e42891088"))
.collect()
.get(0)
.getCountry();
Assertions.assertEquals(2, countries.size());
Assertions
.assertTrue(
countries.stream().anyMatch(cs -> cs.getClassid().equals("IT") && cs.getClassname().equals("Italy")));
Assertions
.assertTrue(
countries.stream().anyMatch(cs -> cs.getClassid().equals("FR") && cs.getClassname().equals("France")));
}
void verifyPropagationSoftware(){
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Software> tmp = sc
.textFile(workingDir.toString() + "/source/software")
.map(item -> OBJECT_MAPPER.readValue(item, Software.class));
Assertions.assertEquals(10, tmp.count());
Dataset<Software> verificationDs = spark.createDataset(tmp.rdd(), Encoders.bean(Software.class));
Assertions.assertEquals(6, verificationDs.filter("size(country) > 0").count());
Assertions.assertEquals(3, verificationDs.filter("size(country) = 1").count());
Assertions.assertEquals(3, verificationDs.filter("size(country) = 2").count());
Assertions.assertEquals(0, verificationDs.filter("size(country) > 2").count());
Dataset<String> countryExploded = verificationDs
.flatMap(
(FlatMapFunction<Software, Country>) row -> row.getCountry().iterator(), Encoders.bean(Country.class))
.map((MapFunction<Country, String>) Qualifier::getClassid, Encoders.STRING());
Assertions.assertEquals(9, countryExploded.count());
Assertions.assertEquals(1, countryExploded.filter("value = 'FR'").count());
Assertions.assertEquals(1, countryExploded.filter("value = 'TR'").count());
Assertions.assertEquals(2, countryExploded.filter("value = 'IT'").count());
Assertions.assertEquals(1, countryExploded.filter("value = 'US'").count());
Assertions.assertEquals(1, countryExploded.filter("value = 'MX'").count());
Assertions.assertEquals(1, countryExploded.filter("value = 'CH'").count());
Assertions.assertEquals(2, countryExploded.filter("value = 'JP'").count());
Dataset<Tuple2<String, String>> countryExplodedWithCountryclassid = verificationDs
.flatMap((FlatMapFunction<Software, Tuple2<String, String>>) row -> {
List<Tuple2<String, String>> prova = new ArrayList<>();
List<Country> countryList = row.getCountry();
countryList
.forEach(
c -> prova
.add(
new Tuple2<>(
row.getId(), c.getClassid())));
return prova.iterator();
}, Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
Assertions.assertEquals(9, countryExplodedWithCountryclassid.count());
//countryExplodedWithCountryclassid.show(false);
Assertions
.assertEquals(
1,
countryExplodedWithCountryclassid
.filter(
"_1 = '50|od______1582::6e7a9b21a2feef45673890432af34244' and _2 = 'FR' ")
.count());
Assertions
.assertEquals(
1,
countryExplodedWithCountryclassid
.filter(
"_1 = '50|dedup_wf_001::40ea2f24181f6ae77b866ebcbffba523' and _2 = 'TR' ")
.count());
Assertions
.assertEquals(
2,
countryExplodedWithCountryclassid
.filter(
"_1 = '50|od______1106::2b7ca9726230be8e862be224fd463ac4' and (_2 = 'IT' or _2 = 'MX') ")
.count());
Assertions
.assertEquals(
2,
countryExplodedWithCountryclassid
.filter(
"_1 = '50|od_______935::46a0ad9964171c3dd13373f5427b9a1c' and (_2 = 'IT' or _2 = 'US') ")
.count());
Assertions
.assertEquals(
1,
countryExplodedWithCountryclassid
.filter(
"_1 = '50|dedup_wf_001::b67bc915603fc01e445f2b5888ba7218' and _2 = 'JP'")
.count());
Assertions
.assertEquals(
2,
countryExplodedWithCountryclassid
.filter(
"_1 = '50|od_______109::f375befa62a741e9250e55bcfa88f9a6' and (_2 = 'CH' or _2 = 'JP') ")
.count());
Dataset<Tuple2<String, String>> countryExplodedWithCountryclassname = verificationDs
.flatMap(
(FlatMapFunction<Software, Tuple2<String, String>>) row -> {
List<Tuple2<String, String>> prova = new ArrayList<>();
List<Country> countryList = row.getCountry();
countryList
.forEach(
c -> prova
.add(
new Tuple2<>(
row.getId(),
c.getClassname())));
return prova.iterator();
},
Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
//countryExplodedWithCountryclassname.show(false);
Assertions
.assertEquals(
1,
countryExplodedWithCountryclassname
.filter(
"_1 = '50|od______1582::6e7a9b21a2feef45673890432af34244' and _2 = 'France' ")
.count());
Assertions
.assertEquals(
1,
countryExplodedWithCountryclassname
.filter(
"_1 = '50|dedup_wf_001::40ea2f24181f6ae77b866ebcbffba523' and _2 = 'Turkey' ")
.count());
Assertions
.assertEquals(
2,
countryExplodedWithCountryclassname
.filter(
"_1 = '50|od______1106::2b7ca9726230be8e862be224fd463ac4' and (_2 = 'Italy' or _2 = 'Mexico') ")
.count());
Assertions
.assertEquals(
2,
countryExplodedWithCountryclassname
.filter(
"_1 = '50|od_______935::46a0ad9964171c3dd13373f5427b9a1c' and (_2 = 'Italy' or _2 = 'United States') ")
.count());
Assertions
.assertEquals(
1,
countryExplodedWithCountryclassname
.filter(
"_1 = '50|dedup_wf_001::b67bc915603fc01e445f2b5888ba7218' and _2 = 'Japan' ")
.count());
Assertions
.assertEquals(
2,
countryExplodedWithCountryclassname
.filter(
"_1 = '50|od_______109::f375befa62a741e9250e55bcfa88f9a6' and (_2 = 'Switzerland' or _2 = 'Japan') ")
.count());
Dataset<Tuple2<String, String>> countryExplodedWithCountryProvenance = verificationDs
.flatMap(
(FlatMapFunction<Software, Tuple2<String, String>>) row -> {
List<Tuple2<String, String>> prova = new ArrayList<>();
List<Country> countryList = row.getCountry();
countryList
.forEach(
c -> prova
.add(
new Tuple2<>(
row.getId(),
c
.getDataInfo()
.getInferenceprovenance())));
return prova.iterator();
},
Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
Assertions
.assertEquals(
7, countryExplodedWithCountryProvenance.filter("_2 = 'propagation'").count());
}
}

56
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/countrypropagation/CountryPropagationJobTest.java
View File

@ -7,6 +7,7 @@ import java.nio.file.Path;
import java.util.ArrayList;
import java.util.List;
import org.antlr.v4.runtime.misc.Utils;
import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
@ -69,26 +70,35 @@ public class CountryPropagationJobTest {
@Test
void testCountryPropagationSoftware() throws Exception {
final String sourcePath = getClass()
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
sc
.textFile(
getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/graph/software")
.getPath();
final String preparedInfoPath = getClass()
.getPath()).saveAsTextFile(workingDir.toString() + "/source/software");
sc
.textFile(
getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/preparedInfo/software")
.getPath();
.getPath()).saveAsTextFile(workingDir.toString() + "/preparedInfo/software");
SparkCountryPropagationJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"--sourcePath",workingDir.toString() + "/source/software",
"-resultTableName", Software.class.getCanonicalName(),
"-outputPath", workingDir.toString() + "/software",
"-preparedInfoPath", preparedInfoPath
"-workingPath", workingDir.toString(),
"-resultType", "software"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Software> tmp = sc
.textFile(workingDir.toString() + "/software")
.textFile(workingDir.toString() + "/source/software")
.map(item -> OBJECT_MAPPER.readValue(item, Software.class));
Assertions.assertEquals(10, tmp.count());
@ -130,7 +140,7 @@ public class CountryPropagationJobTest {
Assertions.assertEquals(9, countryExplodedWithCountryclassid.count());
countryExplodedWithCountryclassid.show(false);
//countryExplodedWithCountryclassid.show(false);
Assertions
.assertEquals(
1,
@ -190,7 +200,7 @@ public class CountryPropagationJobTest {
},
Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
countryExplodedWithCountryclassname.show(false);
//countryExplodedWithCountryclassname.show(false);
Assertions
.assertEquals(
1,
@ -259,23 +269,31 @@ public class CountryPropagationJobTest {
@Test
void testCountryPropagationPublication() throws Exception {
final String sourcePath = getClass()
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
sc
.textFile(
getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/graph/publication")
.getPath();
final String preparedInfoPath = getClass()
.getPath()).saveAsTextFile(workingDir.toString() + "/source/publication");
sc
.textFile(
getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/preparedInfo/publication")
.getPath();
.getPath()).saveAsTextFile(workingDir.toString() + "/preparedInfo/publication");
SparkCountryPropagationJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"--sourcePath",workingDir.toString() + "/source/publication",
"-resultTableName", Publication.class.getCanonicalName(),
"-outputPath", workingDir.toString() + "/publication",
"-preparedInfoPath", preparedInfoPath
"-workingPath", workingDir.toString(),
"-resultType", "publication"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Publication> tmp = sc
.textFile(workingDir.toString() + "/publication")

4
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/countrypropagation/DatasourceCountryPreparationTest.java
View File

@ -64,7 +64,7 @@ public class DatasourceCountryPreparationTest {
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"--outputPath", workingDir.toString() + "/datasourceCountry",
"--workingPath", workingDir.toString() + "/country",
"--allowedtypes", "pubsrepository::institutional",
"--whitelist",
"10|openaire____::3795d6478e30e2c9f787d427ff160944;10|opendoar____::16e6a3326dd7d868cbc926602a61e4d0;10|eurocrisdris::fe4903425d9040f680d8610d9079ea14;10|openaire____::5b76240cc27a58c6f7ceef7d8c36660e;10|openaire____::172bbccecf8fca44ab6a6653e84cb92a;10|openaire____::149c6590f8a06b46314eed77bfca693f;10|eurocrisdris::a6026877c1a174d60f81fd71f62df1c1;10|openaire____::4692342f0992d91f9e705c26959f09e0;10|openaire____::8d529dbb05ec0284662b391789e8ae2a;10|openaire____::345c9d171ef3c5d706d08041d506428c;10|opendoar____::1c1d4df596d01da60385f0bb17a4a9e0;10|opendoar____::7a614fd06c325499f1680b9896beedeb;10|opendoar____::1ee3dfcd8a0645a25a35977997223d22;10|opendoar____::d296c101daa88a51f6ca8cfc1ac79b50;10|opendoar____::798ed7d4ee7138d49b8828958048130a;10|openaire____::c9d2209ecc4d45ba7b4ca7597acb88a2;10|eurocrisdris::c49e0fe4b9ba7b7fab717d1f0f0a674d;10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539;10|eurocrisdris::432ca599953ff50cd4eeffe22faf3e48"
@ -73,7 +73,7 @@ public class DatasourceCountryPreparationTest {
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<DatasourceCountry> tmp = sc
.textFile(workingDir.toString() + "/datasourceCountry")
.textFile(workingDir.toString() + "/country/datasourceCountry")
.map(item -> OBJECT_MAPPER.readValue(item, DatasourceCountry.class));
Assertions.assertEquals(3, tmp.count());

14
dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/countrypropagation/ResultCountryPreparationTest.java
View File

@ -60,25 +60,25 @@ public class ResultCountryPreparationTest {
.getResource("/eu/dnetlib/dhp/countrypropagation/graph/publication")
.getPath();
final String preparedInfoPath = getClass()
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
sc.textFile(getClass()
.getResource("/eu/dnetlib/dhp/countrypropagation/datasourcecountry")
.getPath();
.getPath()).saveAsTextFile(workingDir+"/country/datasourceCountry"); ;
PrepareResultCountrySet
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--workingPath", workingDir.toString() + "/working",
"--workingPath", workingDir.toString() + "/country",
"--sourcePath", sourcePath,
"--outputPath", workingDir.toString() + "/resultCountry",
"--preparedInfoPath", preparedInfoPath,
"--resultTableName", Publication.class.getCanonicalName()
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<ResultCountrySet> tmp = sc
.textFile(workingDir.toString() + "/resultCountry")
.textFile(workingDir.toString() + "/country/preparedInfo/publication")
.map(item -> OBJECT_MAPPER.readValue(item, ResultCountrySet.class));
Assertions.assertEquals(5, tmp.count());

2
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/eosc/dataset/dataset_10.json
View File

File diff suppressed because one or more lines are too long

0
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/eosc/datasource/datasource Normal file
View File

4
dhp-workflows/dhp-enrichment/src/test/resources/eu/dnetlib/dhp/bulktag/eosc/datasource/datasource_1 Normal file
View File

File diff suppressed because one or more lines are too long