added unit test

This commit is contained in:
Claudio Atzori 2022-01-19 17:13:21 +01:00
parent 62f135262e
commit 391aa1373b
9 changed files with 99 additions and 48 deletions

View File

@ -38,7 +38,7 @@ public class DispatchEntitiesSparkJob {
.requireNonNull(
DispatchEntitiesSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/group/dispatch_entities_parameters.json")));
"/eu/dnetlib/dhp/oa/merge/dispatch_entities_parameters.json")));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);

View File

@ -53,7 +53,7 @@ public class GroupEntitiesSparkJob {
.toString(
GroupEntitiesSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/group/group_graph_entities_parameters.json"));
"/eu/dnetlib/dhp/oa/merge/group_graph_entities_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);

View File

@ -1,26 +0,0 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "i",
"paramLongName": "inputPath",
"paramDescription": "the source path",
"paramRequired": true
},
{
"paramName": "o",
"paramLongName": "outputPath",
"paramDescription": "path of the output graph",
"paramRequired": true
},
{
"paramName": "c",
"paramLongName": "graphTableClassName",
"paramDescription": "the graph entity class name",
"paramRequired": true
}
]

View File

@ -1,20 +0,0 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "gin",
"paramLongName": "graphInputPath",
"paramDescription": "the graph root path",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramDescription": "the output merged graph root path",
"paramRequired": true
}
]

View File

@ -0,0 +1,91 @@
package eu.dnetlib.dhp.oa.graph.group;
import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.oa.merge.GroupEntitiesSparkJob;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Result;
import org.apache.commons.io.FileUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FilterFunction;
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.*;
import java.io.IOException;
import java.net.URISyntaxException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.nio.file.Paths;
public class GroupEntitiesSparkJobTest {
private static SparkSession spark;
private Path workingDir;
//private Path inputDir;
private Path graphInputPath;
private Path outputPath;
@BeforeAll
public static void beforeAll() {
SparkConf conf = new SparkConf();
conf.setAppName(GroupEntitiesSparkJob.class.getSimpleName());
conf.setMaster("local");
conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
conf.registerKryoClasses(ModelSupport.getOafModelClasses());
spark = SparkSession.builder().config(conf).getOrCreate();
}
@BeforeEach
public void beforeEach() throws IOException, URISyntaxException {
workingDir = Files.createTempDirectory(GroupEntitiesSparkJob.class.getSimpleName());
//inputDir = workingDir.resolve("input");
graphInputPath = Paths.get(ClassLoader.getSystemResource("eu/dnetlib/dhp/oa/graph/group").toURI());
outputPath = workingDir.resolve("output");
}
@AfterEach
public void afterEach() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
}
@AfterAll
public static void afterAll() {
spark.stop();
}
@Test
void testGroupEntities() throws Exception {
GroupEntitiesSparkJob.main(new String[] {
"-isSparkSessionManaged",
Boolean.FALSE.toString(),
"-graphInputPath",
graphInputPath.toString(),
"-outputPath",
outputPath.toString()
});
ObjectMapper mapper = new ObjectMapper().configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
Dataset<Result> output = spark
.read()
.textFile(outputPath.toString())
.map((MapFunction<String, String>) s -> StringUtils.substringAfter(s, "|"), Encoders.STRING())
.map((MapFunction<String, Result>) s -> mapper.readValue(s, Result.class), Encoders.bean(Result.class));
Assertions.assertEquals(
1,
output
.filter((FilterFunction<Result>) r ->
"50|doi_________::09821844208a5cd6300b2bfb13bca1b9".equals(r.getId()) &&
r.getCollectedfrom().stream().anyMatch(kv -> kv.getValue().equalsIgnoreCase("zenodo")) )
.count());
}
}

File diff suppressed because one or more lines are too long