lsmyrnaios
/
dnet-hadoop
forked from D-Net/dnet-hadoop
1
0
Fork 0
Code Pull Requests Activity

[Clean Country] first implementation to remove country NL from results collected from NARCIS when doi starts with mendely prefix

This commit is contained in:
Miriam Baglioni 2022-07-20 17:05:56 +02:00
parent 18b505d6a3
commit 65cc736e2f
4 changed files with 313 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

128
dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/clean/CleanCountrySparkJob.java Normal file
View File

@ -0,0 +1,128 @@
package eu.dnetlib.dhp.oa.graph.clean;
/**
* @author miriam.baglioni
* @Date 20/07/22
*/
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
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.MapFunction;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.Serializable;
import java.util.Optional;
import java.util.stream.Collectors;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
public class CleanCountrySparkJob implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CleanCountrySparkJob.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
CleanContextSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/graph/input_clean_country_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String inputPath = parser.get("inputPath");
log.info("inputPath: {}", inputPath);
String workingPath = parser.get("workingPath");
log.info("workingPath: {}", workingPath);
String country = parser.get("country");
log.info("country: {}", country);
String verifyParam = parser.get("verifyParam");
log.info("verifyParam: {}", verifyParam);
String collectedfrom = parser.get("collectedfrom");
log.info("collectedfrom: {}", collectedfrom);
String graphTableClassName = parser.get("graphTableClassName");
log.info("graphTableClassName: {}", graphTableClassName);
Class<? extends Result> entityClazz = (Class<? extends Result>) Class.forName(graphTableClassName);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
cleanCountry(spark, country, verifyParam, inputPath, entityClazz, workingPath,collectedfrom);
});
}
private static <T extends Result> void cleanCountry(SparkSession spark, String country, String verifyParam,
String inputPath, Class<T> entityClazz, String workingPath, String collectedfrom) {
Dataset<T> res = spark
.read()
.textFile(inputPath)
.map(
(MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, entityClazz),
Encoders.bean(entityClazz))
;
res.map((MapFunction<T, T>) r -> {
for(StructuredProperty p: r.getPid()){
if (p.getQualifier().getClassid().equalsIgnoreCase("doi") &&
p.getValue().startsWith(verifyParam) && r.getCollectedfrom().stream().anyMatch(cf -> cf.getValue().equalsIgnoreCase(collectedfrom))) {
r
.setCountry(
r
.getCountry()
.stream()
.filter(
c -> !c.getClassid()
.equalsIgnoreCase(country))
.collect(Collectors.toList()));
}
}
return r;
}, Encoders.bean(entityClazz))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(workingPath);
spark
.read()
.textFile(workingPath)
.map(
(MapFunction<String, T>) value -> OBJECT_MAPPER.readValue(value, entityClazz),
Encoders.bean(entityClazz))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath);
}
}

43
dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/input_clean_country_parameters.json Normal file
View File

@ -0,0 +1,43 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "in",
"paramLongName": "inputPath",
"paramDescription": "the path to the graph data dump to read",
"paramRequired": true
},
{
"paramName": "wp",
"paramLongName": "workingPath",
"paramDescription": "the path to store the output graph",
"paramRequired": true
},
{
"paramName": "c",
"paramLongName": "country",
"paramDescription": "the id of the context to be removed",
"paramRequired": true
},
{
"paramName": "class",
"paramLongName": "graphTableClassName",
"paramDescription": "class name moelling the graph table",
"paramRequired": true
},{
"paramName": "vf",
"paramLongName": "verifyParam",
"paramDescription": "the parameter to be verified to remove the country",
"paramRequired": true
},
{
"paramName": "cf",
"paramLongName": "collectedfrom",
"paramDescription": "the collectedfrom value for which we should apply the cleaning",
"paramRequired": true
}
]

135
dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/clean/CleanCountryTest.java Normal file
View File

@ -0,0 +1,135 @@
package eu.dnetlib.dhp.oa.graph.clean;
/**
* @author miriam.baglioni
* @Date 20/07/22
*/
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.oa.graph.dump.DumpJobTest;
import eu.dnetlib.dhp.schema.oaf.Publication;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
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.MapFunction;
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 org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.List;
public class CleanCountryTest {
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static SparkSession spark;
private static Path workingDir;
private static final Logger log = LoggerFactory.getLogger(CleanContextTest.class);
@BeforeAll
public static void beforeAll() throws IOException {
workingDir = Files.createTempDirectory(DumpJobTest.class.getSimpleName());
log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf();
conf.setAppName(DumpJobTest.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(DumpJobTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
spark.stop();
}
@Test
public void testResultClean() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/oa/graph/clean/publication_clean_country.json")
.getPath();
final String prefix = "gcube ";
spark
.read()
.textFile(sourcePath)
.map(
(MapFunction<String, Publication>) r -> OBJECT_MAPPER.readValue(r, Publication.class),
Encoders.bean(Publication.class))
.write()
.json(workingDir.toString() + "/publication");
CleanCountrySparkJob.main(new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--inputPath", workingDir.toString() + "/publication",
"-graphTableClassName", Publication.class.getCanonicalName(),
"-workingPath", workingDir.toString() + "/working",
"-country", "NL",
"-verifyParam", "10.17632",
"-collectedfrom", "NARCIS"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Publication> tmp = sc
.textFile(workingDir.toString() + "/publication")
.map(item -> OBJECT_MAPPER.readValue(item, Publication.class));
Assertions.assertEquals(7, tmp.count());
// original result with NL country and doi starting with Mendely prefix, but not collectedfrom NARCIS
Assertions
.assertEquals(
1,
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::0224aae28af558f21768dbc6439c7a95"))
.collect()
.get(0)
.getCountry()
.size());
// original result with NL country and pid not starting with Mendely prefix
Assertions
.assertEquals(
1,
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::20c414a3b1c742d5dd3851f1b67df2d9"))
.collect()
.get(0)
.getCountry()
.size());
// original result with NL country and doi starting with Mendely prefix and collectedfrom NARCIS
Assertions
.assertEquals(
0,
tmp
.filter(p -> p.getId().equals("50|DansKnawCris::3c81248c335f0aa07e06817ece6fa6af"))
.collect()
.get(0)
.getCountry()
.size());
}
}

7
dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/clean/publication_clean_country.json Normal file
View File

File diff suppressed because one or more lines are too long