alessia.bardi
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

refactoring

This commit is contained in:
Miriam Baglioni 2020-11-25 18:23:28 +01:00
parent 1a89f8211c
commit 124591a7f3
6 changed files with 188 additions and 186 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/Constants.java
View File

@ -26,7 +26,6 @@ public class Constants {
public static String ORCID = "orcid"; public static String ORCID = "orcid";
static { static {
accessRightsCoarMap.put("OPEN", "c_abf2"); accessRightsCoarMap.put("OPEN", "c_abf2");
accessRightsCoarMap.put("RESTRICTED", "c_16ec"); accessRightsCoarMap.put("RESTRICTED", "c_16ec");

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/funderresults/SparkDumpFunderResults.java
View File

@ -6,7 +6,6 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable; import java.io.Serializable;
import java.util.*; import java.util.*;
import eu.dnetlib.dhp.schema.common.ModelConstants;
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;
@ -20,6 +19,7 @@ import eu.dnetlib.dhp.oa.graph.dump.Constants;
import eu.dnetlib.dhp.oa.graph.dump.ResultMapper; import eu.dnetlib.dhp.oa.graph.dump.ResultMapper;
import eu.dnetlib.dhp.oa.graph.dump.Utils; import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap; import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult; import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import eu.dnetlib.dhp.schema.dump.oaf.community.Project; import eu.dnetlib.dhp.schema.dump.oaf.community.Project;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;

2
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/dump/funderresults/SparkResultLinkedToProject.java
View File

@ -6,7 +6,6 @@ import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable; import java.io.Serializable;
import java.util.Optional; import java.util.Optional;
import eu.dnetlib.dhp.schema.common.ModelConstants;
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;
@ -21,6 +20,7 @@ import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.oa.graph.dump.Constants; import eu.dnetlib.dhp.oa.graph.dump.Constants;
import eu.dnetlib.dhp.oa.graph.dump.Utils; import eu.dnetlib.dhp.oa.graph.dump.Utils;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Relation; import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.schema.oaf.Result; import eu.dnetlib.dhp.schema.oaf.Result;
import scala.Tuple2; import scala.Tuple2;

22
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/funderresult/ResultLinkedToProjectTest.java
View File

@ -1,9 +1,11 @@
package eu.dnetlib.dhp.oa.graph.dump.funderresult; package eu.dnetlib.dhp.oa.graph.dump.funderresult;
import com.fasterxml.jackson.databind.ObjectMapper; import java.io.IOException;
import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject; import java.nio.file.Files;
import eu.dnetlib.dhp.schema.oaf.Publication; import java.nio.file.Path;
import eu.dnetlib.dhp.schema.oaf.Result; import java.util.HashMap;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaRDD;
@ -17,10 +19,11 @@ 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 eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject;
import java.util.HashMap; import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.Result;
public class ResultLinkedToProjectTest { public class ResultLinkedToProjectTest {
@ -38,7 +41,8 @@ public class ResultLinkedToProjectTest {
@BeforeAll @BeforeAll
public static void beforeAll() throws IOException { public static void beforeAll() throws IOException {
workingDir = Files workingDir = Files
.createTempDirectory(eu.dnetlib.dhp.oa.graph.dump.funderresult.ResultLinkedToProjectTest.class.getSimpleName()); .createTempDirectory(
eu.dnetlib.dhp.oa.graph.dump.funderresult.ResultLinkedToProjectTest.class.getSimpleName());
log.info("using work dir {}", workingDir); log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf(); SparkConf conf = new SparkConf();

25
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/dump/funderresult/SplitPerFunderTest.java
View File

@ -1,11 +1,10 @@
package eu.dnetlib.dhp.oa.graph.dump.funderresult; package eu.dnetlib.dhp.oa.graph.dump.funderresult;
import com.fasterxml.jackson.databind.ObjectMapper; import java.io.IOException;
import eu.dnetlib.dhp.oa.graph.dump.DumpJobTest; import java.nio.file.Files;
import eu.dnetlib.dhp.oa.graph.dump.SplitForCommunityTest; import java.nio.file.Path;
import eu.dnetlib.dhp.oa.graph.dump.community.CommunitySplit;
import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkDumpFunderResults;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import org.apache.commons.io.FileUtils; import org.apache.commons.io.FileUtils;
import org.apache.spark.SparkConf; import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD; import org.apache.spark.api.java.JavaRDD;
@ -19,9 +18,13 @@ 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 eu.dnetlib.dhp.oa.graph.dump.DumpJobTest;
import eu.dnetlib.dhp.oa.graph.dump.SplitForCommunityTest;
import eu.dnetlib.dhp.oa.graph.dump.community.CommunitySplit;
import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkDumpFunderResults;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
public class SplitPerFunderTest { public class SplitPerFunderTest {
@ -64,12 +67,10 @@ public class SplitPerFunderTest {
@Test @Test
public void test1() throws Exception { public void test1() throws Exception {
final String sourcePath = getClass() final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/extendeddump") .getResource("/eu/dnetlib/dhp/oa/graph/dump/funderresource/extendeddump")
.getPath(); .getPath();
SparkDumpFunderResults.main(new String[] { SparkDumpFunderResults.main(new String[] {
"-isSparkSessionManaged", Boolean.FALSE.toString(), "-isSparkSessionManaged", Boolean.FALSE.toString(),
"-outputPath", workingDir.toString() + "/split", "-outputPath", workingDir.toString() + "/split",
@ -78,7 +79,6 @@ public class SplitPerFunderTest {
}); });
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
// FP7 3 // FP7 3
@ -95,7 +95,6 @@ public class SplitPerFunderTest {
.assertEquals( .assertEquals(
1, verificationDataset.filter("id = '50|dedup_wf_001::0d16b1714ab3077df73893a8ea57d776'").count()); 1, verificationDataset.filter("id = '50|dedup_wf_001::0d16b1714ab3077df73893a8ea57d776'").count());
// CIHR 2 // CIHR 2
tmp = sc tmp = sc
.textFile(workingDir.toString() + "/split/CIHR") .textFile(workingDir.toString() + "/split/CIHR")