fix problem in parameters

This commit is contained in:
Miriam Baglioni 2020-02-18 17:23:34 +01:00
parent 5868ff8a86
commit e0a777028a
9 changed files with 111 additions and 124 deletions

View File

@ -1,66 +0,0 @@
package eu.dnetlib.dhp.graph;
import eu.dnetlib.dhp.graph.model.EntityRelEntity;
import eu.dnetlib.dhp.graph.model.RelatedEntity;
import eu.dnetlib.dhp.graph.utils.GraphMappingUtils;
import org.codehaus.jackson.map.ObjectMapper;
import org.junit.Before;
import org.junit.Test;
import java.io.IOException;
import java.io.InputStreamReader;
public class MappingUtilsTest {
private GraphMappingUtils utils;
@Before
public void setUp() {
utils = new GraphMappingUtils();
}
@Test
public void testOafMappingDatasource() throws IOException {
final InputStreamReader in = new InputStreamReader(getClass().getResourceAsStream("datasource.json"));
final EntityRelEntity e = new ObjectMapper().readValue(in, EntityRelEntity.class);
e.getSource().setType("datasource");
final EntityRelEntity out = utils.asRelatedEntity(e);
System.out.println(out);
}
//@Test
public void testOafMappingResult() throws IOException {
final InputStreamReader in = new InputStreamReader(getClass().getResourceAsStream("result.json"));
final EntityRelEntity e = new ObjectMapper().readValue(in, EntityRelEntity.class);
final EntityRelEntity out = utils.asRelatedEntity(e);
System.out.println(out);
}
@Test
public void testOafMappingSoftware() throws IOException {
final InputStreamReader in = new InputStreamReader(getClass().getResourceAsStream("software.json"));
final EntityRelEntity e = new ObjectMapper().readValue(in, EntityRelEntity.class);
final EntityRelEntity out = utils.asRelatedEntity(e);
System.out.println(out);
}
@Test
public void testParseRelatedEntity() throws IOException {
final InputStreamReader in = new InputStreamReader(getClass().getResourceAsStream("related_entity.json"));
final RelatedEntity e = new ObjectMapper().readValue(in, RelatedEntity.class);
System.out.println(e);
}
}

View File

@ -1,55 +0,0 @@
package eu.dnetlib.dhp.graph;
import eu.dnetlib.dhp.graph.utils.ContextMapper;
import org.apache.commons.io.FileUtils;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.spark.sql.SparkSession;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import java.io.File;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
public class XmlRecordFactoryTest {
private static final Log log = LogFactory.getLog(XmlRecordFactoryTest.class);
private Path testDir;
@Before
public void setup() throws IOException {
testDir = Files.createTempDirectory(getClass().getSimpleName());
log.info("created test directory " + testDir.toString());
}
@After
public void tearDown() throws IOException {
FileUtils.deleteDirectory(testDir.toFile());
log.info("deleted test directory " + testDir.toString());
}
@Test
public void testXmlSerialization() throws Exception {
final SparkSession spark = SparkSession
.builder()
.appName(SparkXmlRecordBuilderJob.class.getSimpleName())
.master("local[*]")
.getOrCreate();
final String inputDir = testDir.toString() + "/3_joined_entities";
FileUtils.forceMkdir(new File(inputDir));
FileUtils.copyFile(new File("/Users/claudio/Downloads/joined_entities-part-00000"), new File(inputDir + "/joined_entities-part-00000"));
final ContextMapper ctx = ContextMapper.fromIS("https://dev-openaire.d4science.org:443/is/services/isLookUp");
final GraphJoiner g = new GraphJoiner(spark, ctx, inputDir, testDir.toString());
g.asXML();
}
}

View File

@ -0,0 +1,4 @@
package eu.dnetlib.dhp;
public class PropagationConstant {
}

View File

@ -3,13 +3,13 @@
"paramName":"mt", "paramName":"mt",
"paramLongName":"master", "paramLongName":"master",
"paramDescription": "should be local or yarn", "paramDescription": "should be local or yarn",
"paramRequired": true, "paramRequired": true
}, },
{ {
"paramName":"s", "paramName":"s",
"paramLongName":"sourcePath", "paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read", "paramDescription": "the path of the sequencial file to read",
"paramRequired": true, "paramRequired": true
}, },
{ {
"paramName":"wl", "paramName":"wl",

View File

@ -49,7 +49,7 @@
</spark-opts> </spark-opts>
<arg>-mt</arg> <arg>yarn-cluster</arg> <arg>-mt</arg> <arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--withelist</arg><arg>${whitelist}</arg> <arg>--whitelist</arg><arg>${whitelist}</arg>
<arg>--allowedtypes</arg><arg>${allowedtypes}</arg> <arg>--allowedtypes</arg><arg>${allowedtypes}</arg>
</spark> </spark>
<ok to="End"/> <ok to="End"/>

View File

@ -0,0 +1,26 @@
[
{
"paramName":"mt",
"paramLongName":"master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName":"wl",
"paramLongName":"whitelist",
"paramDescription": "datasource id that will be considered even if not in the allowed typology list. Split by ;",
"paramRequired": true
},
{
"paramName":"at",
"paramLongName":"allowedtypes",
"paramDescription": "the types of the allowed datasources. Split by ;",
"paramRequired": true
}
]

View File

@ -0,0 +1,18 @@
<configuration>
<property>
<name>jobTracker</name>
<value>yarnRM</value>
</property>
<property>
<name>nameNode</name>
<value>hdfs://nameservice1</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
</configuration>

View File

@ -0,0 +1,60 @@
<workflow-app name="country_propagation" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>whitelist</name>
<description>the white list</description>
</property>
<property>
<name>allowedtypes</name>
<description>the allowed types</description>
</property>
<property>
<name>sparkDriverMemory</name>
<description>memory for driver process</description>
</property>
<property>
<name>sparkExecutorMemory</name>
<description>memory for individual executor</description>
</property>
<property>
<name>sparkExecutorCores</name>
<description>number of cores used by single executor</description>
</property>
</parameters>
<start to="CountryPropagation"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="CountryPropagation">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>CountryPropagation</name>
<class>eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob</class>
<jar>dhp-propagation-${projectVersion}.jar</jar>
<spark-opts>--executor-memory ${sparkExecutorMemory}
--executor-cores ${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners="com.cloudera.spark.lineage.NavigatorAppListener"
--conf spark.sql.queryExecutionListeners="com.cloudera.spark.lineage.NavigatorQueryListener"
</spark-opts>
<arg>-mt</arg> <arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--whitelist</arg><arg>${whitelist}</arg>
<arg>--allowedtypes</arg><arg>${allowedtypes}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>