[Graph DUMP] add code to produce the delta of new projects with respect to the previous delta/dump #221

Merged
claudio.atzori merged 4 commits from dump_delta_projects into master 2022-07-01 10:30:11 +02:00
1 changed files with 106 additions and 98 deletions
Showing only changes of commit 1d1fe3b151 - Show all commits

View File

@ -1,8 +1,11 @@
package eu.dnetlib.dhp.oa.graph.dump.projectssubset; package eu.dnetlib.dhp.oa.graph.dump.projectssubset;
import java.io.IOException; import java.io.IOException;
import java.nio.file.Files; import java.nio.file.Files;
import java.nio.file.Path; import java.nio.file.Path;
import java.util.HashMap; 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;
@ -15,104 +18,109 @@ import org.junit.jupiter.api.BeforeAll;
import org.junit.jupiter.api.Test; import org.junit.jupiter.api.Test;
import org.slf4j.Logger; import org.slf4j.Logger;
import org.slf4j.LoggerFactory; import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper; import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import eu.dnetlib.dhp.schema.dump.oaf.graph.Project; import eu.dnetlib.dhp.schema.dump.oaf.graph.Project;
public class ProjectSubsetTest { public class ProjectSubsetTest {
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 private static final Logger log = LoggerFactory
.getLogger(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class); .getLogger(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class);
private static final HashMap<String, String> map = new HashMap<>();
@BeforeAll
public static void beforeAll() throws IOException { @BeforeAll
workingDir = Files public static void beforeAll() throws IOException {
.createTempDirectory( workingDir = Files
eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName()); .createTempDirectory(
log.info("using work dir {}", workingDir); eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName());
SparkConf conf = new SparkConf(); log.info("using work dir {}", workingDir);
conf.setAppName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName()); SparkConf conf = new SparkConf();
conf.setMaster("local[*]"); conf.setAppName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName());
conf.set("spark.driver.host", "localhost"); conf.setMaster("local[*]");
conf.set("hive.metastore.local", "true"); conf.set("spark.driver.host", "localhost");
conf.set("spark.ui.enabled", "false"); conf.set("hive.metastore.local", "true");
conf.set("spark.sql.warehouse.dir", workingDir.toString()); conf.set("spark.ui.enabled", "false");
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString()); conf.set("spark.sql.warehouse.dir", workingDir.toString());
spark = SparkSession conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
.builder() spark = SparkSession
.appName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName()) .builder()
.config(conf) .appName(eu.dnetlib.dhp.oa.graph.dump.projectssubset.ProjectSubsetTest.class.getSimpleName())
.getOrCreate(); .config(conf)
} .getOrCreate();
@AfterAll }
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile()); @AfterAll
spark.stop(); public static void afterAll() throws IOException {
} FileUtils.deleteDirectory(workingDir.toFile());
@Test spark.stop();
void testAllNew() throws Exception { }
final String projectListPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId") @Test
.getPath(); void testAllNew() throws Exception {
final String sourcePath = getClass() final String projectListPath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/allnew/projects") .getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId")
.getPath(); .getPath();
spark final String sourcePath = getClass()
.read() .getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/allnew/projects")
.textFile(projectListPath) .getPath();
.write() spark
.mode(SaveMode.Overwrite) .read()
.text(workingDir.toString() + "/projectIds"); .textFile(projectListPath)
ProjectsSubsetSparkJob.main(new String[] { .write()
"-isSparkSessionManaged", Boolean.FALSE.toString(), .mode(SaveMode.Overwrite)
"-outputPath", workingDir.toString() + "/projects", .text(workingDir.toString() + "/projectIds");
"-sourcePath", sourcePath, ProjectsSubsetSparkJob.main(new String[] {
"-projectListPath", workingDir.toString() + "/projectIds" "-isSparkSessionManaged", Boolean.FALSE.toString(),
}); "-outputPath", workingDir.toString() + "/projects",
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); "-sourcePath", sourcePath,
JavaRDD<Project> tmp = sc "-projectListPath", workingDir.toString() + "/projectIds"
.textFile(workingDir.toString() + "/projects") });
.map(item -> OBJECT_MAPPER.readValue(item, Project.class)); final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
Assertions.assertEquals(12, tmp.count()); JavaRDD<Project> tmp = sc
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count()); .textFile(workingDir.toString() + "/projects")
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count()); .map(item -> OBJECT_MAPPER.readValue(item, Project.class));
Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count()); Assertions.assertEquals(12, tmp.count());
Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count()); Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count());
Assertions.assertEquals(1, tmp.filter(p -> p.getId().substring(3, 15).equals("corda_______")).count()); Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count());
Assertions.assertEquals(40, sc.textFile(workingDir.toString() + "/projectIds").count()); Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count());
} Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count());
@Test Assertions.assertEquals(1, tmp.filter(p -> p.getId().substring(3, 15).equals("corda_______")).count());
void testMatchOne() throws Exception { Assertions.assertEquals(40, sc.textFile(workingDir.toString() + "/projectIds").count());
final String projectListPath = getClass() }
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId")
.getPath(); @Test
final String sourcePath = getClass() void testMatchOne() throws Exception {
.getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/matchOne/projects") final String projectListPath = getClass()
.getPath(); .getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/projectId")
spark .getPath();
.read() final String sourcePath = getClass()
.textFile(projectListPath) .getResource("/eu/dnetlib/dhp/oa/graph/dump/projectsubset/matchOne/projects")
.write() .getPath();
.mode(SaveMode.Overwrite) spark
.text(workingDir.toString() + "/projectIds"); .read()
ProjectsSubsetSparkJob.main(new String[] { .textFile(projectListPath)
"-isSparkSessionManaged", Boolean.FALSE.toString(), .write()
"-outputPath", workingDir.toString() + "/projects", .mode(SaveMode.Overwrite)
"-sourcePath", sourcePath, .text(workingDir.toString() + "/projectIds");
"-projectListPath", workingDir.toString() + "/projectIds" ProjectsSubsetSparkJob.main(new String[] {
}); "-isSparkSessionManaged", Boolean.FALSE.toString(),
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); "-outputPath", workingDir.toString() + "/projects",
JavaRDD<Project> tmp = sc "-sourcePath", sourcePath,
.textFile(workingDir.toString() + "/projects") "-projectListPath", workingDir.toString() + "/projectIds"
.map(item -> OBJECT_MAPPER.readValue(item, Project.class)); });
Assertions.assertEquals(11, tmp.count()); final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count()); JavaRDD<Project> tmp = sc
Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count()); .textFile(workingDir.toString() + "/projects")
Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count()); .map(item -> OBJECT_MAPPER.readValue(item, Project.class));
Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count()); Assertions.assertEquals(11, tmp.count());
Assertions.assertEquals(0, tmp.filter(p -> p.getId().substring(3, 15).equals("corda__h2020")).count()); Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("aka_________")).count());
Assertions.assertEquals(39, sc.textFile(workingDir.toString() + "/projectIds").count()); Assertions.assertEquals(2, tmp.filter(p -> p.getId().substring(3, 15).equals("anr_________")).count());
} Assertions.assertEquals(4, tmp.filter(p -> p.getId().substring(3, 15).equals("arc_________")).count());
} Assertions.assertEquals(3, tmp.filter(p -> p.getId().substring(3, 15).equals("conicytf____")).count());
Assertions.assertEquals(0, tmp.filter(p -> p.getId().substring(3, 15).equals("corda__h2020")).count());
Assertions.assertEquals(39, sc.textFile(workingDir.toString() + "/projectIds").count());
}
}