1
0
Fork 0

merge with beta - resolved conflict in pom

This commit is contained in:
Miriam Baglioni 2021-11-15 10:52:16 +01:00
commit 4ec88c718c
273 changed files with 19141 additions and 1931 deletions

View File

@ -28,7 +28,7 @@ public class HdfsSupport {
* @param configuration Configuration of hadoop env
*/
public static boolean exists(String path, Configuration configuration) {
logger.info("Removing path: {}", path);
logger.info("Checking existence for path: {}", path);
return rethrowAsRuntimeException(
() -> {
Path f = new Path(path);

View File

@ -85,6 +85,13 @@ public class MakeTarArchive implements Serializable {
String p_string = p.toString();
if (!p_string.endsWith("_SUCCESS")) {
String name = p_string.substring(p_string.lastIndexOf("/") + 1);
if (name.startsWith("part-") & name.length() > 10) {
String tmp = name.substring(0, 10);
if (name.contains(".")) {
tmp += name.substring(name.indexOf("."));
}
name = tmp;
}
TarArchiveEntry entry = new TarArchiveEntry(dir_name + "/" + name);
entry.setSize(fileStatus.getLen());
current_size += fileStatus.getLen();

View File

@ -4,19 +4,19 @@ package eu.dnetlib.dhp.utils;
import java.io.*;
import java.nio.charset.StandardCharsets;
import java.security.MessageDigest;
import java.util.List;
import java.util.Map;
import java.util.Properties;
import java.util.zip.GZIPInputStream;
import java.util.zip.GZIPOutputStream;
import java.util.*;
import java.util.stream.Collectors;
import org.apache.commons.codec.binary.Base64;
import org.apache.commons.codec.binary.Base64OutputStream;
import org.apache.commons.codec.binary.Hex;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.SaveMode;
import org.slf4j.Logger;
@ -26,6 +26,8 @@ import com.fasterxml.jackson.databind.ObjectMapper;
import com.google.common.collect.Maps;
import com.jayway.jsonpath.JsonPath;
import eu.dnetlib.dhp.schema.mdstore.MDStoreWithInfo;
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
import net.minidev.json.JSONArray;
import scala.collection.JavaConverters;
import scala.collection.Seq;
@ -52,10 +54,56 @@ public class DHPUtils {
}
}
/**
* Retrieves from the metadata store manager application the list of paths associated with mdstores characterized
* by he given format, layout, interpretation
* @param mdstoreManagerUrl the URL of the mdstore manager service
* @param format the mdstore format
* @param layout the mdstore layout
* @param interpretation the mdstore interpretation
* @param includeEmpty include Empty mdstores
* @return the set of hdfs paths
* @throws IOException in case of HTTP communication issues
*/
public static Set<String> mdstorePaths(final String mdstoreManagerUrl,
final String format,
final String layout,
final String interpretation,
boolean includeEmpty) throws IOException {
final String url = mdstoreManagerUrl + "/mdstores/";
final ObjectMapper objectMapper = new ObjectMapper();
final HttpGet req = new HttpGet(url);
try (final CloseableHttpClient client = HttpClients.createDefault()) {
try (final CloseableHttpResponse response = client.execute(req)) {
final String json = IOUtils.toString(response.getEntity().getContent());
final MDStoreWithInfo[] mdstores = objectMapper.readValue(json, MDStoreWithInfo[].class);
return Arrays
.stream(mdstores)
.filter(md -> md.getFormat().equalsIgnoreCase(format))
.filter(md -> md.getLayout().equalsIgnoreCase(layout))
.filter(md -> md.getInterpretation().equalsIgnoreCase(interpretation))
.filter(md -> StringUtils.isNotBlank(md.getHdfsPath()))
.filter(md -> StringUtils.isNotBlank(md.getCurrentVersion()))
.filter(md -> includeEmpty || md.getSize() > 0)
.map(md -> md.getHdfsPath() + "/" + md.getCurrentVersion() + "/store")
.collect(Collectors.toSet());
}
}
}
public static String generateIdentifier(final String originalId, final String nsPrefix) {
return String.format("%s::%s", nsPrefix, DHPUtils.md5(originalId));
}
public static String generateUnresolvedIdentifier(final String pid, final String pidType) {
final String cleanedPid = CleaningFunctions.normalizePidValue(pidType, pid);
return String.format("unresolved::%s::%s", cleanedPid, pidType.toLowerCase().trim());
}
public static String getJPathString(final String jsonPath, final String json) {
try {
Object o = JsonPath.read(json, jsonPath);

View File

@ -0,0 +1,49 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import java.util.Optional;
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 com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
public class Constants {
public static final String DOI = "doi";
public static final String UPDATE_DATA_INFO_TYPE = "update";
public static final String UPDATE_SUBJECT_FOS_CLASS_ID = "subject:fos";
public static final String UPDATE_CLASS_NAME = "Inferred by OpenAIRE";
public static final String UPDATE_MEASURE_BIP_CLASS_ID = "measure:bip";
public static final String FOS_CLASS_ID = "FOS";
public static final String FOS_CLASS_NAME = "Fields of Science and Technology classification";
public static final String NULL = "NULL";
public static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private Constants() {
}
public static Boolean isSparkSessionManaged(ArgumentApplicationParser parser) {
return Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
}
public static <R> Dataset<R> readPath(
SparkSession spark, String inputPath, Class<R> clazz) {
return spark
.read()
.textFile(inputPath)
.map((MapFunction<String, R>) value -> OBJECT_MAPPER.readValue(value, clazz), Encoders.bean(clazz));
}
}

View File

@ -0,0 +1,77 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.Serializable;
import java.util.Objects;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.collection.GetCSV;
public class GetFOSData implements Serializable {
private static final Logger log = LoggerFactory.getLogger(GetFOSData.class);
public static final char DEFAULT_DELIMITER = '\t';
public static void main(final String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
Objects
.requireNonNull(
GetFOSData.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/get_fos_parameters.json"))));
parser.parseArgument(args);
// the path where the original fos csv file is stored
final String sourcePath = parser.get("sourcePath");
log.info("sourcePath {}", sourcePath);
// the path where to put the file as json
final String outputPath = parser.get("outputPath");
log.info("outputPath {}", outputPath);
final String hdfsNameNode = parser.get("hdfsNameNode");
log.info("hdfsNameNode {}", hdfsNameNode);
final String classForName = parser.get("classForName");
log.info("classForName {}", classForName);
final char delimiter = Optional
.ofNullable(parser.get("delimiter"))
.map(s -> s.charAt(0))
.orElse(DEFAULT_DELIMITER);
log.info("delimiter {}", delimiter);
Configuration conf = new Configuration();
conf.set("fs.defaultFS", hdfsNameNode);
FileSystem fileSystem = FileSystem.get(conf);
new GetFOSData().doRewrite(sourcePath, outputPath, classForName, delimiter, fileSystem);
}
public void doRewrite(String inputPath, String outputFile, String classForName, char delimiter, FileSystem fs)
throws IOException, ClassNotFoundException {
// reads the csv and writes it as its json equivalent
try (InputStreamReader reader = new InputStreamReader(fs.open(new Path(inputPath)))) {
GetCSV.getCsv(fs, reader, outputFile, classForName, delimiter);
}
}
}

View File

@ -0,0 +1,145 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import static eu.dnetlib.dhp.actionmanager.createunresolvedentities.Constants.*;
import static eu.dnetlib.dhp.actionmanager.createunresolvedentities.Constants.UPDATE_CLASS_NAME;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import java.util.List;
import java.util.Optional;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.hdfs.client.HdfsUtils;
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.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.BipDeserialize;
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.BipScore;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.common.HdfsSupport;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.KeyValue;
import eu.dnetlib.dhp.schema.oaf.Measure;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.utils.DHPUtils;
public class PrepareBipFinder implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareBipFinder.class);
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
public static <I extends Result> void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
PrepareBipFinder.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_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);
final String sourcePath = parser.get("sourcePath");
log.info("sourcePath {}: ", sourcePath);
final String outputPath = parser.get("outputPath");
log.info("outputPath {}: ", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
HdfsSupport.remove(outputPath, spark.sparkContext().hadoopConfiguration());
prepareResults(spark, sourcePath, outputPath);
});
}
private static <I extends Result> void prepareResults(SparkSession spark, String inputPath, String outputPath) {
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<BipDeserialize> bipDeserializeJavaRDD = sc
.textFile(inputPath)
.map(item -> OBJECT_MAPPER.readValue(item, BipDeserialize.class));
spark
.createDataset(bipDeserializeJavaRDD.flatMap(entry -> entry.keySet().stream().map(key -> {
BipScore bs = new BipScore();
bs.setId(key);
bs.setScoreList(entry.get(key));
return bs;
}).collect(Collectors.toList()).iterator()).rdd(), Encoders.bean(BipScore.class))
.map((MapFunction<BipScore, Result>) v -> {
Result r = new Result();
r.setId(DHPUtils.generateUnresolvedIdentifier(v.getId(), DOI));
r.setMeasures(getMeasure(v));
return r;
}, Encoders.bean(Result.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "/bip");
}
private static List<Measure> getMeasure(BipScore value) {
return value
.getScoreList()
.stream()
.map(score -> {
Measure m = new Measure();
m.setId(score.getId());
m
.setUnit(
score
.getUnit()
.stream()
.map(unit -> {
KeyValue kv = new KeyValue();
kv.setValue(unit.getValue());
kv.setKey(unit.getKey());
kv
.setDataInfo(
OafMapperUtils
.dataInfo(
false,
UPDATE_DATA_INFO_TYPE,
true,
false,
OafMapperUtils
.qualifier(
UPDATE_MEASURE_BIP_CLASS_ID,
UPDATE_CLASS_NAME,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
""));
return kv;
})
.collect(Collectors.toList()));
return m;
})
.collect(Collectors.toList());
}
}

View File

@ -0,0 +1,133 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import static eu.dnetlib.dhp.actionmanager.createunresolvedentities.Constants.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import java.util.*;
import java.util.stream.Collectors;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
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 eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.Result;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
import eu.dnetlib.dhp.utils.DHPUtils;
public class PrepareFOSSparkJob implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareFOSSparkJob.class);
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
PrepareFOSSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/prepare_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String sourcePath = parser.get("sourcePath");
log.info("sourcePath: {}", sourcePath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
distributeFOSdois(
spark,
sourcePath,
outputPath);
});
}
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
fosDataset.flatMap((FlatMapFunction<FOSDataModel, FOSDataModel>) v -> {
List<FOSDataModel> fosList = new ArrayList<>();
final String level1 = v.getLevel1();
final String level2 = v.getLevel2();
final String level3 = v.getLevel3();
Arrays
.stream(v.getDoi().split("\u0002"))
.forEach(d -> fosList.add(FOSDataModel.newInstance(d, level1, level2, level3)));
return fosList.iterator();
}, Encoders.bean(FOSDataModel.class))
.map((MapFunction<FOSDataModel, Result>) value -> {
Result r = new Result();
r.setId(DHPUtils.generateUnresolvedIdentifier(value.getDoi(), DOI));
r.setSubject(getSubjects(value));
return r;
}, Encoders.bean(Result.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + "/fos");
}
private static List<StructuredProperty> getSubjects(FOSDataModel fos) {
return Arrays
.asList(getSubject(fos.getLevel1()), getSubject(fos.getLevel2()), getSubject(fos.getLevel3()))
.stream()
.filter(Objects::nonNull)
.collect(Collectors.toList());
}
private static StructuredProperty getSubject(String sbj) {
if (sbj.equals(NULL))
return null;
StructuredProperty sp = new StructuredProperty();
sp.setValue(sbj);
sp
.setQualifier(
OafMapperUtils
.qualifier(
FOS_CLASS_ID,
FOS_CLASS_NAME,
ModelConstants.DNET_SUBJECT_TYPOLOGIES,
ModelConstants.DNET_SUBJECT_TYPOLOGIES));
sp
.setDataInfo(
OafMapperUtils
.dataInfo(
false,
UPDATE_DATA_INFO_TYPE,
true,
false,
OafMapperUtils
.qualifier(
UPDATE_SUBJECT_FOS_CLASS_ID,
UPDATE_CLASS_NAME,
ModelConstants.DNET_PROVENANCE_ACTIONS,
ModelConstants.DNET_PROVENANCE_ACTIONS),
""));
return sp;
}
}

View File

@ -0,0 +1,79 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import static eu.dnetlib.dhp.actionmanager.createunresolvedentities.Constants.*;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.MapGroupsFunction;
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 eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.Result;
public class SparkSaveUnresolved implements Serializable {
private static final Logger log = LoggerFactory.getLogger(PrepareFOSSparkJob.class);
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
PrepareFOSSparkJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/actionmanager/createunresolvedentities/produce_unresolved_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String sourcePath = parser.get("sourcePath");
log.info("sourcePath: {}", sourcePath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
saveUnresolved(
spark,
sourcePath,
outputPath);
});
}
private static void saveUnresolved(SparkSession spark, String sourcePath, String outputPath) {
spark
.read()
.textFile(sourcePath + "/*")
.map(
(MapFunction<String, Result>) l -> OBJECT_MAPPER.readValue(l, Result.class),
Encoders.bean(Result.class))
.groupByKey((MapFunction<Result, String>) r -> r.getId(), Encoders.STRING())
.mapGroups((MapGroupsFunction<String, Result, Result>) (k, it) -> {
Result ret = it.next();
it.forEachRemaining(r -> ret.mergeFrom(r));
return ret;
}, Encoders.bean(Result.class))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath);
}
}

View File

@ -0,0 +1,28 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.List;
/**
* Class that maps the model of the bipFinder! input data.
* Only needed for deserialization purposes
*/
public class BipDeserialize extends HashMap<String, List<Score>> implements Serializable {
public BipDeserialize() {
super();
}
public List<Score> get(String key) {
if (super.get(key) == null) {
return new ArrayList<>();
}
return super.get(key);
}
}

View File

@ -0,0 +1,30 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
import java.io.Serializable;
import java.util.List;
/**
* Rewriting of the bipFinder input data by extracting the identifier of the result (doi)
*/
public class BipScore implements Serializable {
private String id; // doi
private List<Score> scoreList; // unit as given in the inputfile
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public List<Score> getScoreList() {
return scoreList;
}
public void setScoreList(List<Score> scoreList) {
this.scoreList = scoreList;
}
}

View File

@ -0,0 +1,71 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
import java.io.Serializable;
import com.opencsv.bean.CsvBindByPosition;
public class FOSDataModel implements Serializable {
@CsvBindByPosition(position = 1)
// @CsvBindByName(column = "doi")
private String doi;
@CsvBindByPosition(position = 2)
// @CsvBindByName(column = "level1")
private String level1;
@CsvBindByPosition(position = 3)
// @CsvBindByName(column = "level2")
private String level2;
@CsvBindByPosition(position = 4)
// @CsvBindByName(column = "level3")
private String level3;
public FOSDataModel() {
}
public FOSDataModel(String doi, String level1, String level2, String level3) {
this.doi = doi;
this.level1 = level1;
this.level2 = level2;
this.level3 = level3;
}
public static FOSDataModel newInstance(String d, String level1, String level2, String level3) {
return new FOSDataModel(d, level1, level2, level3);
}
public String getDoi() {
return doi;
}
public void setDoi(String doi) {
this.doi = doi;
}
public String getLevel1() {
return level1;
}
public void setLevel1(String level1) {
this.level1 = level1;
}
public String getLevel2() {
return level2;
}
public void setLevel2(String level2) {
this.level2 = level2;
}
public String getLevel3() {
return level3;
}
public void setLevel3(String level3) {
this.level3 = level3;
}
}

View File

@ -0,0 +1,26 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
import java.io.Serializable;
public class KeyValue implements Serializable {
private String key;
private String value;
public String getKey() {
return key;
}
public void setKey(String key) {
this.key = key;
}
public String getValue() {
return value;
}
public void setValue(String value) {
this.value = value;
}
}

View File

@ -0,0 +1,30 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities.model;
import java.io.Serializable;
import java.util.List;
/**
* represents the score in the input file
*/
public class Score implements Serializable {
private String id;
private List<KeyValue> unit;
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public List<KeyValue> getUnit() {
return unit;
}
public void setUnit(List<KeyValue> unit) {
this.unit = unit;
}
}

View File

@ -1,41 +0,0 @@
package eu.dnetlib.dhp.actionmanager.datacite
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.Oaf
import org.apache.hadoop.io.Text
import org.apache.hadoop.io.compress.GzipCodec
import org.apache.hadoop.mapred.SequenceFileOutputFormat
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.io.Source
object ExportActionSetJobNode {
val log: Logger = LoggerFactory.getLogger(ExportActionSetJobNode.getClass)
def main(args: Array[String]): Unit = {
val conf = new SparkConf
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/exportDataset_parameters.json")).mkString)
parser.parseArgument(args)
val master = parser.get("master")
val sourcePath = parser.get("sourcePath")
val targetPath = parser.get("targetPath")
val spark: SparkSession = SparkSession.builder().config(conf)
.appName(ExportActionSetJobNode.getClass.getSimpleName)
.master(master)
.getOrCreate()
implicit val resEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
implicit val tEncoder:Encoder[(String,String)] = Encoders.tuple(Encoders.STRING,Encoders.STRING)
spark.read.load(sourcePath).as[Oaf]
.map(o =>DataciteToOAFTransformation.toActionSet(o))
.filter(o => o!= null)
.rdd.map(s => (new Text(s._1), new Text(s._2))).saveAsHadoopFile(s"$targetPath", classOf[Text], classOf[Text], classOf[SequenceFileOutputFormat[Text,Text]], classOf[GzipCodec])
}
}

View File

@ -1,46 +0,0 @@
package eu.dnetlib.dhp.actionmanager.datacite
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.mdstore.MetadataRecord
import eu.dnetlib.dhp.schema.oaf.{Oaf, Result}
import eu.dnetlib.dhp.utils.ISLookupClientFactory
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.io.Source
object FilterCrossrefEntitiesSpark {
val log: Logger = LoggerFactory.getLogger(getClass.getClass)
def main(args: Array[String]): Unit = {
val conf = new SparkConf
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/filter_crossref_param.json")).mkString)
parser.parseArgument(args)
val master = parser.get("master")
val sourcePath = parser.get("sourcePath")
log.info("sourcePath: {}", sourcePath)
val targetPath = parser.get("targetPath")
log.info("targetPath: {}", targetPath)
val spark: SparkSession = SparkSession.builder().config(conf)
.appName(getClass.getSimpleName)
.master(master)
.getOrCreate()
implicit val oafEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
implicit val resEncoder: Encoder[Result] = Encoders.kryo[Result]
val d:Dataset[Oaf]= spark.read.load(sourcePath).as[Oaf]
d.filter(r => r.isInstanceOf[Result]).map(r => r.asInstanceOf[Result]).write.mode(SaveMode.Overwrite).save(targetPath)
}
}

View File

@ -60,14 +60,10 @@ object SparkCreateActionset {
val entities: Dataset[(String, Result)] = spark.read.load(s"$sourcePath/entities/*").as[Result].map(p => (p.getId, p))(Encoders.tuple(Encoders.STRING, resultEncoders))
entities.filter(r => r.isInstanceOf[Result]).map(r => r.asInstanceOf[Result])
entities
.joinWith(idRelation, entities("_1").equalTo(idRelation("value")))
.map(p => p._1._2)
.write.mode(SaveMode.Append).save(s"$workingDirFolder/actionSetOaf")
}
}

View File

@ -0,0 +1,49 @@
package eu.dnetlib.dhp.collection
import eu.dnetlib.dhp.schema.common.ModelSupport
import eu.dnetlib.dhp.schema.oaf.{Oaf, OafEntity, Relation}
object CollectionUtils {
/**
* This method in pipeline to the transformation phase,
* generates relations in both verse, typically it should be a phase of flatMap
*
* @param i input OAF
* @return
* If the input OAF is an entity -> List(i)
* If the input OAF is a relation -> List(relation, inverseRelation)
*
*/
def fixRelations(i: Oaf): List[Oaf] = {
if (i.isInstanceOf[OafEntity])
return List(i)
else {
val r: Relation = i.asInstanceOf[Relation]
val currentRel = ModelSupport.findRelation(r.getRelClass)
if (currentRel != null) {
// Cleaning relation
r.setRelType(currentRel.getRelType)
r.setSubRelType(currentRel.getSubReltype)
r.setRelClass(currentRel.getRelClass)
val inverse = new Relation
inverse.setSource(r.getTarget)
inverse.setTarget(r.getSource)
inverse.setRelType(currentRel.getRelType)
inverse.setSubRelType(currentRel.getSubReltype)
inverse.setRelClass(currentRel.getInverseRelClass)
inverse.setCollectedfrom(r.getCollectedfrom)
inverse.setDataInfo(r.getDataInfo)
inverse.setProperties(r.getProperties)
inverse.setLastupdatetimestamp(r.getLastupdatetimestamp)
inverse.setValidated(r.getValidated)
inverse.setValidationDate(r.getValidationDate)
return List(r, inverse)
}
}
List()
}
}

View File

@ -1,12 +1,10 @@
package eu.dnetlib.dhp.actionmanager.datacite
package eu.dnetlib.dhp.datacite
import org.apache.commons.io.IOUtils
import org.apache.http.client.config.RequestConfig
import org.apache.http.client.methods.{HttpGet, HttpPost, HttpRequestBase, HttpUriRequest}
import org.apache.http.client.methods.{HttpGet, HttpPost, HttpUriRequest}
import org.apache.http.entity.StringEntity
import org.apache.http.impl.client.{HttpClientBuilder, HttpClients}
import java.io.IOException
import org.apache.http.impl.client.HttpClientBuilder
abstract class AbstractRestClient extends Iterator[String] {

View File

@ -1,7 +1,7 @@
package eu.dnetlib.dhp.actionmanager.datacite
package eu.dnetlib.dhp.datacite
import org.json4s.{DefaultFormats, JValue}
import org.json4s.jackson.JsonMethods.{compact, parse, render}
import org.json4s.{DefaultFormats, JValue}
class DataciteAPIImporter(timestamp: Long = 0, blocks: Long = 10, until:Long = -1) extends AbstractRestClient {

View File

@ -1,4 +1,4 @@
package eu.dnetlib.dhp.actionmanager.datacite
package eu.dnetlib.dhp.datacite
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
@ -325,8 +325,9 @@ object DataciteToOAFTransformation {
val grantId = m.matcher(awardUri).replaceAll("$2")
val targetId = s"$p${DHPUtils.md5(grantId)}"
List(
generateRelation(sourceId, targetId, "isProducedBy", DATACITE_COLLECTED_FROM, dataInfo),
generateRelation(targetId, sourceId, "produces", DATACITE_COLLECTED_FROM, dataInfo)
generateRelation(sourceId, targetId, "isProducedBy", DATACITE_COLLECTED_FROM, dataInfo)
// REMOVED INVERSE RELATION since there is a specific method that should generate later
// generateRelation(targetId, sourceId, "produces", DATACITE_COLLECTED_FROM, dataInfo)
)
}
else
@ -580,11 +581,11 @@ object DataciteToOAFTransformation {
rel.setProperties(List(dateProps).asJava)
rel.setSource(id)
rel.setTarget(s"unresolved::${r.relatedIdentifier}::${r.relatedIdentifierType}")
rel.setTarget(DHPUtils.generateUnresolvedIdentifier(r.relatedIdentifier,r.relatedIdentifierType))
rel.setCollectedfrom(List(DATACITE_COLLECTED_FROM).asJava)
rel.getCollectedfrom.asScala.map(c => c.getValue)(collection.breakOut)
rel.getCollectedfrom.asScala.map(c => c.getValue).toList
rel
})(collection breakOut)
}).toList
}
def generateDataInfo(trust: String): DataInfo = {

View File

@ -1,9 +1,14 @@
package eu.dnetlib.dhp.actionmanager.datacite
package eu.dnetlib.dhp.datacite
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.collection.CollectionUtils.fixRelations
import eu.dnetlib.dhp.common.Constants.MDSTORE_DATA_PATH
import eu.dnetlib.dhp.common.Constants.MDSTORE_SIZE_PATH
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.mdstore.MetadataRecord
import eu.dnetlib.dhp.schema.mdstore.{MDStoreVersion, MetadataRecord}
import eu.dnetlib.dhp.schema.oaf.Oaf
import eu.dnetlib.dhp.utils.DHPUtils.writeHdfsFile
import eu.dnetlib.dhp.utils.ISLookupClientFactory
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
@ -17,11 +22,10 @@ object GenerateDataciteDatasetSpark {
def main(args: Array[String]): Unit = {
val conf = new SparkConf
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/actionmanager/datacite/generate_dataset_params.json")).mkString)
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/datacite/generate_dataset_params.json")).mkString)
parser.parseArgument(args)
val master = parser.get("master")
val sourcePath = parser.get("sourcePath")
val targetPath = parser.get("targetPath")
val exportLinks = "true".equalsIgnoreCase(parser.get("exportLinks"))
val isLookupUrl: String = parser.get("isLookupUrl")
log.info("isLookupUrl: {}", isLookupUrl)
@ -33,16 +37,28 @@ object GenerateDataciteDatasetSpark {
.master(master)
.getOrCreate()
import spark.implicits._
implicit val mrEncoder: Encoder[MetadataRecord] = Encoders.kryo[MetadataRecord]
implicit val resEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
import spark.implicits._
val mdstoreOutputVersion = parser.get("mdstoreOutputVersion")
val mapper = new ObjectMapper()
val cleanedMdStoreVersion = mapper.readValue(mdstoreOutputVersion, classOf[MDStoreVersion])
val outputBasePath = cleanedMdStoreVersion.getHdfsPath
log.info("outputBasePath: {}", outputBasePath)
val targetPath = s"$outputBasePath/$MDSTORE_DATA_PATH"
spark.read.load(sourcePath).as[DataciteType]
.filter(d => d.isActive)
.flatMap(d => DataciteToOAFTransformation.generateOAF(d.json, d.timestamp, d.timestamp, vocabularies, exportLinks))
.filter(d => d != null)
.flatMap(i => fixRelations(i)).filter(i => i != null)
.write.mode(SaveMode.Overwrite).save(targetPath)
val total_items = spark.read.load(targetPath).as[Oaf].count()
writeHdfsFile(spark.sparkContext.hadoopConfiguration, s"$total_items", outputBasePath + MDSTORE_SIZE_PATH)
}
}

View File

@ -1,6 +1,5 @@
package eu.dnetlib.dhp.actionmanager.datacite
package eu.dnetlib.dhp.datacite
import eu.dnetlib.dhp.actionmanager.datacite.DataciteToOAFTransformation.df_it
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FileSystem, LocalFileSystem, Path}
@ -9,14 +8,14 @@ import org.apache.hadoop.io.{IntWritable, SequenceFile, Text}
import org.apache.spark.SparkContext
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.functions.max
import org.apache.spark.sql.{Dataset, Encoder, SaveMode, SparkSession}
import org.json4s.DefaultFormats
import org.json4s.jackson.JsonMethods.parse
import org.apache.spark.sql.functions.max
import org.slf4j.{Logger, LoggerFactory}
import java.time.format.DateTimeFormatter._
import java.time.{LocalDate, LocalDateTime, ZoneOffset}
import java.time.format.DateTimeFormatter.ISO_DATE_TIME
import java.time.{LocalDateTime, ZoneOffset}
import scala.io.Source
object ImportDatacite {

View File

@ -0,0 +1,49 @@
package eu.dnetlib.dhp.datacite
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.{Oaf, Result}
import org.apache.spark.SparkConf
import org.apache.spark.sql.functions.max
import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import java.text.SimpleDateFormat
import java.util.Locale
import scala.io.Source
object SparkDownloadUpdateDatacite {
val log: Logger = LoggerFactory.getLogger(getClass)
def main(args: Array[String]): Unit = {
val conf = new SparkConf
val parser = new ArgumentApplicationParser(Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/datacite/generate_dataset_params.json")).mkString)
parser.parseArgument(args)
val master = parser.get("master")
val sourcePath = parser.get("sourcePath")
val workingPath = parser.get("workingPath")
val hdfsuri = parser.get("namenode")
log.info(s"namenode is $hdfsuri")
val spark: SparkSession = SparkSession.builder().config(conf)
.appName(getClass.getSimpleName)
.master(master)
.getOrCreate()
implicit val oafEncoder: Encoder[Oaf] = Encoders.kryo[Oaf]
implicit val resEncoder: Encoder[Result] = Encoders.kryo[Result]
import spark.implicits._
val maxDate: String = spark.read.load(workingPath).as[Oaf].filter(s => s.isInstanceOf[Result]).map(r => r.asInstanceOf[Result].getDateofcollection).select(max("value")).first().getString(0)
val ISO8601FORMAT = new SimpleDateFormat("yyyy-MM-dd'T'HH:mm:ssZ", Locale.US)
val string_to_date = ISO8601FORMAT.parse(maxDate)
val ts = string_to_date.getTime
}
}

View File

@ -1,14 +1,12 @@
package eu.dnetlib.dhp.sx.graph.bio
package eu.dnetlib.dhp.sx.bio
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, OafMapperUtils}
import eu.dnetlib.dhp.schema.oaf.{Author, DataInfo, Dataset, Instance, KeyValue, Oaf, Relation, StructuredProperty}
import eu.dnetlib.dhp.schema.oaf._
import org.json4s.DefaultFormats
import org.json4s.JsonAST.{JField, JObject, JString}
import org.json4s.jackson.JsonMethods.{compact, parse, render}
import scala.collection.JavaConverters._
import collection.JavaConverters._
object BioDBToOAF {
case class EBILinkItem(id: Long, links: String) {}
@ -231,7 +229,6 @@ object BioDBToOAF {
}
def generate_unresolved_id(pid: String, pidType: String): String = {
s"unresolved::$pid::$pidType"
}

View File

@ -1,8 +1,9 @@
package eu.dnetlib.dhp.sx.graph.bio
package eu.dnetlib.dhp.sx.bio
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.{Oaf, Result}
import eu.dnetlib.dhp.schema.oaf.Oaf
import BioDBToOAF.ScholixResolved
import eu.dnetlib.dhp.collection.CollectionUtils
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
@ -13,7 +14,7 @@ object SparkTransformBioDatabaseToOAF {
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf()
val log: Logger = LoggerFactory.getLogger(getClass)
val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/bio_to_oaf_params.json")))
val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/bio/ebi/bio_to_oaf_params.json")))
parser.parseArgument(args)
val database: String = parser.get("database")
log.info("database: {}", database)
@ -33,16 +34,15 @@ object SparkTransformBioDatabaseToOAF {
implicit val resultEncoder: Encoder[Oaf] = Encoders.kryo(classOf[Oaf])
import spark.implicits._
database.toUpperCase() match {
case "UNIPROT" =>
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.uniprotToOAF(i))).write.mode(SaveMode.Overwrite).save(targetPath)
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.uniprotToOAF(i))).flatMap(i=> CollectionUtils.fixRelations(i)).filter(i => i != null).write.mode(SaveMode.Overwrite).save(targetPath)
case "PDB" =>
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.pdbTOOaf(i))).write.mode(SaveMode.Overwrite).save(targetPath)
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.pdbTOOaf(i))).flatMap(i=> CollectionUtils.fixRelations(i)).filter(i => i != null).write.mode(SaveMode.Overwrite).save(targetPath)
case "SCHOLIX" =>
spark.read.load(dbPath).as[ScholixResolved].map(i => BioDBToOAF.scholixResolvedToOAF(i)).write.mode(SaveMode.Overwrite).save(targetPath)
spark.read.load(dbPath).as[ScholixResolved].map(i => BioDBToOAF.scholixResolvedToOAF(i)).flatMap(i=> CollectionUtils.fixRelations(i)).filter(i => i != null).write.mode(SaveMode.Overwrite).save(targetPath)
case "CROSSREF_LINKS" =>
spark.createDataset(sc.textFile(dbPath).map(i => BioDBToOAF.crossrefLinksToOaf(i))).write.mode(SaveMode.Overwrite).save(targetPath)
spark.createDataset(sc.textFile(dbPath).map(i => BioDBToOAF.crossrefLinksToOaf(i))).flatMap(i=> CollectionUtils.fixRelations(i)).filter(i => i != null).write.mode(SaveMode.Overwrite).save(targetPath)
}
}

View File

@ -0,0 +1,200 @@
package eu.dnetlib.dhp.sx.bio.ebi
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.oaf.Result
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal, PMParser, PubMedToOaf}
import eu.dnetlib.dhp.utils.ISLookupClientFactory
import org.apache.commons.io.IOUtils
import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.fs.{FSDataOutputStream, FileSystem, Path}
import org.apache.http.client.config.RequestConfig
import org.apache.http.client.methods.HttpGet
import org.apache.http.impl.client.HttpClientBuilder
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
import java.io.InputStream
import scala.io.Source
import scala.xml.pull.XMLEventReader
object SparkCreateBaselineDataFrame {
def requestBaseLineUpdatePage(maxFile: String): List[(String, String)] = {
val data = requestPage("https://ftp.ncbi.nlm.nih.gov/pubmed/updatefiles/")
val result = data.lines.filter(l => l.startsWith("<a href=")).map { l =>
val end = l.lastIndexOf("\">")
val start = l.indexOf("<a href=\"")
if (start >= 0 && end > start)
l.substring(start + 9, end - start)
else
""
}.filter(s => s.endsWith(".gz")).filter(s => s > maxFile).map(s => (s, s"https://ftp.ncbi.nlm.nih.gov/pubmed/updatefiles/$s")).toList
result
}
def downloadBaselinePart(url: String): InputStream = {
val r = new HttpGet(url)
val timeout = 60; // seconds
val config = RequestConfig.custom()
.setConnectTimeout(timeout * 1000)
.setConnectionRequestTimeout(timeout * 1000)
.setSocketTimeout(timeout * 1000).build()
val client = HttpClientBuilder.create().setDefaultRequestConfig(config).build()
val response = client.execute(r)
println(s"get response with status${response.getStatusLine.getStatusCode}")
response.getEntity.getContent
}
def requestPage(url: String): String = {
val r = new HttpGet(url)
val timeout = 60; // seconds
val config = RequestConfig.custom()
.setConnectTimeout(timeout * 1000)
.setConnectionRequestTimeout(timeout * 1000)
.setSocketTimeout(timeout * 1000).build()
val client = HttpClientBuilder.create().setDefaultRequestConfig(config).build()
try {
var tries = 4
while (tries > 0) {
println(s"requesting ${r.getURI}")
try {
val response = client.execute(r)
println(s"get response with status${response.getStatusLine.getStatusCode}")
if (response.getStatusLine.getStatusCode > 400) {
tries -= 1
}
else
return IOUtils.toString(response.getEntity.getContent)
} catch {
case e: Throwable =>
println(s"Error on requesting ${r.getURI}")
e.printStackTrace()
tries -= 1
}
}
""
} finally {
if (client != null)
client.close()
}
}
def downloadBaseLineUpdate(baselinePath: String, hdfsServerUri: String): Unit = {
val conf = new Configuration
conf.set("fs.defaultFS", hdfsServerUri)
val fs = FileSystem.get(conf)
val p = new Path(baselinePath)
val files = fs.listFiles(p, false)
var max_file = ""
while (files.hasNext) {
val c = files.next()
val data = c.getPath.toString
val fileName = data.substring(data.lastIndexOf("/") + 1)
if (fileName > max_file)
max_file = fileName
}
val files_to_download = requestBaseLineUpdatePage(max_file)
files_to_download.foreach { u =>
val hdfsWritePath: Path = new Path(s"$baselinePath/${u._1}")
val fsDataOutputStream: FSDataOutputStream = fs.create(hdfsWritePath, true)
val i = downloadBaselinePart(u._2)
IOUtils.copy(i, fsDataOutputStream)
println(s"Downloaded ${u._2} into $baselinePath/${u._1}")
fsDataOutputStream.close()
}
}
val pmArticleAggregator: Aggregator[(String, PMArticle), PMArticle, PMArticle] = new Aggregator[(String, PMArticle), PMArticle, PMArticle] with Serializable {
override def zero: PMArticle = new PMArticle
override def reduce(b: PMArticle, a: (String, PMArticle)): PMArticle = {
if (b != null && b.getPmid != null) b else a._2
}
override def merge(b1: PMArticle, b2: PMArticle): PMArticle = {
if (b1 != null && b1.getPmid != null) b1 else b2
}
override def finish(reduction: PMArticle): PMArticle = reduction
override def bufferEncoder: Encoder[PMArticle] = Encoders.kryo[PMArticle]
override def outputEncoder: Encoder[PMArticle] = Encoders.kryo[PMArticle]
}
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf()
val log: Logger = LoggerFactory.getLogger(getClass)
val parser = new ArgumentApplicationParser(IOUtils.toString(SparkEBILinksToOaf.getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/bio/ebi/baseline_to_oaf_params.json")))
parser.parseArgument(args)
val isLookupUrl: String = parser.get("isLookupUrl")
log.info("isLookupUrl: {}", isLookupUrl)
val workingPath = parser.get("workingPath")
log.info("workingPath: {}", workingPath)
val targetPath = parser.get("targetPath")
log.info("targetPath: {}", targetPath)
val hdfsServerUri = parser.get("hdfsServerUri")
log.info("hdfsServerUri: {}", targetPath)
val skipUpdate = parser.get("skipUpdate")
log.info("skipUpdate: {}", skipUpdate)
val isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl)
val vocabularies = VocabularyGroup.loadVocsFromIS(isLookupService)
val spark: SparkSession =
SparkSession
.builder()
.config(conf)
.appName(SparkEBILinksToOaf.getClass.getSimpleName)
.master(parser.get("master")).getOrCreate()
val sc = spark.sparkContext
import spark.implicits._
implicit val PMEncoder: Encoder[PMArticle] = Encoders.kryo(classOf[PMArticle])
implicit val PMJEncoder: Encoder[PMJournal] = Encoders.kryo(classOf[PMJournal])
implicit val PMAEncoder: Encoder[PMAuthor] = Encoders.kryo(classOf[PMAuthor])
implicit val resultEncoder: Encoder[Result] = Encoders.kryo(classOf[Result])
if (!"true".equalsIgnoreCase(skipUpdate)) {
downloadBaseLineUpdate(s"$workingPath/baseline", hdfsServerUri)
val k: RDD[(String, String)] = sc.wholeTextFiles(s"$workingPath/baseline", 2000)
val ds: Dataset[PMArticle] = spark.createDataset(k.filter(i => i._1.endsWith(".gz")).flatMap(i => {
val xml = new XMLEventReader(Source.fromBytes(i._2.getBytes()))
new PMParser(xml)
}))
ds.map(p => (p.getPmid, p))(Encoders.tuple(Encoders.STRING, PMEncoder)).groupByKey(_._1)
.agg(pmArticleAggregator.toColumn)
.map(p => p._2).write.mode(SaveMode.Overwrite).save(s"$workingPath/baseline_dataset")
}
val exported_dataset = spark.read.load(s"$workingPath/baseline_dataset").as[PMArticle]
exported_dataset
.map(a => PubMedToOaf.convert(a, vocabularies)).as[Result]
.filter(p => p != null)
.write.mode(SaveMode.Overwrite).save(targetPath)
}
}

View File

@ -0,0 +1,118 @@
package eu.dnetlib.dhp.sx.bio.ebi
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMAuthor, PMJournal}
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
import eu.dnetlib.dhp.sx.bio.pubmed.PMJournal
import org.apache.commons.io.IOUtils
import org.apache.http.client.config.RequestConfig
import org.apache.http.client.methods.HttpGet
import org.apache.http.impl.client.HttpClientBuilder
import org.apache.spark.SparkConf
import org.apache.spark.sql.functions.max
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
object SparkDownloadEBILinks {
def createEBILinks(pmid: Long): EBILinkItem = {
val res = requestLinks(pmid)
if (res != null)
return EBILinkItem(pmid, res)
null
}
def requestPage(url: String): String = {
val r = new HttpGet(url)
val timeout = 60; // seconds
val config = RequestConfig.custom()
.setConnectTimeout(timeout * 1000)
.setConnectionRequestTimeout(timeout * 1000)
.setSocketTimeout(timeout * 1000).build()
val client = HttpClientBuilder.create().setDefaultRequestConfig(config).build()
try {
var tries = 4
while (tries > 0) {
println(s"requesting ${r.getURI}")
try {
val response = client.execute(r)
println(s"get response with status${response.getStatusLine.getStatusCode}")
if (response.getStatusLine.getStatusCode > 400) {
tries -= 1
}
else
return IOUtils.toString(response.getEntity.getContent)
} catch {
case e: Throwable =>
println(s"Error on requesting ${r.getURI}")
e.printStackTrace()
tries -= 1
}
}
""
} finally {
if (client != null)
client.close()
}
}
def requestLinks(PMID: Long): String = {
requestPage(s"https://www.ebi.ac.uk/europepmc/webservices/rest/MED/$PMID/datalinks?format=json")
}
def main(args: Array[String]): Unit = {
val log: Logger = LoggerFactory.getLogger(getClass)
val MAX_ITEM_PER_PARTITION = 20000
val conf: SparkConf = new SparkConf()
val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/bio/ebi/ebi_download_update.json")))
parser.parseArgument(args)
val spark: SparkSession =
SparkSession
.builder()
.config(conf)
.appName(SparkEBILinksToOaf.getClass.getSimpleName)
.master(parser.get("master")).getOrCreate()
import spark.implicits._
implicit val PMEncoder: Encoder[PMArticle] = Encoders.kryo(classOf[PMArticle])
implicit val PMJEncoder: Encoder[PMJournal] = Encoders.kryo(classOf[PMJournal])
implicit val PMAEncoder: Encoder[PMAuthor] = Encoders.kryo(classOf[PMAuthor])
val sourcePath = parser.get("sourcePath")
log.info(s"sourcePath -> $sourcePath")
val workingPath = parser.get("workingPath")
log.info(s"workingPath -> $workingPath")
log.info("Getting max pubmedId where the links have already requested")
val links: Dataset[EBILinkItem] = spark.read.load(s"$sourcePath/ebi_links_dataset").as[EBILinkItem]
val lastPMIDRequested = links.map(l => l.id).select(max("value")).first.getLong(0)
log.info("Retrieving PMID to request links")
val pubmed = spark.read.load(s"$sourcePath/baseline_dataset").as[PMArticle]
pubmed.map(p => p.getPmid.toLong).where(s"value > $lastPMIDRequested").write.mode(SaveMode.Overwrite).save(s"$workingPath/id_to_request")
val pmidToReq: Dataset[Long] = spark.read.load(s"$workingPath/id_to_request").as[Long]
val total = pmidToReq.count()
spark.createDataset(pmidToReq.rdd.repartition((total / MAX_ITEM_PER_PARTITION).toInt).map(pmid => createEBILinks(pmid)).filter(l => l != null)).write.mode(SaveMode.Overwrite).save(s"$workingPath/links_update")
val updates: Dataset[EBILinkItem] = spark.read.load(s"$workingPath/links_update").as[EBILinkItem]
links.union(updates).groupByKey(_.id)
.reduceGroups { (x, y) =>
if (x == null || x.links == null)
y
if (y == null || y.links == null)
x
if (x.links.length > y.links.length)
x
else
y
}.map(_._2).write.mode(SaveMode.Overwrite).save(s"$workingPath/links_final")
}
}

View File

@ -1,21 +1,22 @@
package eu.dnetlib.dhp.sx.graph.ebi
package eu.dnetlib.dhp.sx.bio.ebi
import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.schema.oaf.Oaf
import eu.dnetlib.dhp.sx.graph.bio
import eu.dnetlib.dhp.sx.graph.bio.BioDBToOAF
import eu.dnetlib.dhp.sx.graph.bio.BioDBToOAF.EBILinkItem
import eu.dnetlib.dhp.sx.bio.BioDBToOAF
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.EBILinkItem
import BioDBToOAF.EBILinkItem
import eu.dnetlib.dhp.collection.CollectionUtils
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.apache.spark.sql._
import org.slf4j.{Logger, LoggerFactory}
object SparkEBILinksToOaf {
def main(args: Array[String]): Unit = {
val log: Logger = LoggerFactory.getLogger(getClass)
val conf: SparkConf = new SparkConf()
val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/ebi/ebi_to_df_params.json")))
val parser = new ArgumentApplicationParser(IOUtils.toString(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/bio/ebi/ebi_to_df_params.json")))
parser.parseArgument(args)
val spark: SparkSession =
SparkSession
@ -24,24 +25,20 @@ object SparkEBILinksToOaf {
.appName(SparkEBILinksToOaf.getClass.getSimpleName)
.master(parser.get("master")).getOrCreate()
import spark.implicits._
val sourcePath = parser.get("sourcePath")
log.info(s"sourcePath -> $sourcePath")
val targetPath = parser.get("targetPath")
log.info(s"targetPath -> $targetPath")
import spark.implicits._
implicit val PMEncoder: Encoder[Oaf] = Encoders.kryo(classOf[Oaf])
val ebi_rdd:Dataset[EBILinkItem] = spark.createDataset(spark.sparkContext.textFile(sourcePath).map(s => BioDBToOAF.extractEBILinksFromDump(s))).as[EBILinkItem]
ebi_rdd.write.mode(SaveMode.Overwrite).save(s"${sourcePath}_dataset")
val ebLinks:Dataset[EBILinkItem] = spark.read.load(s"${sourcePath}_dataset").as[EBILinkItem].filter(l => l.links!= null)
val ebLinks: Dataset[EBILinkItem] = spark.read.load(sourcePath).as[EBILinkItem].filter(l => l.links != null && l.links.startsWith("{"))
ebLinks.flatMap(j => BioDBToOAF.parse_ebi_links(j.links))
.repartition(4000)
.filter(p => BioDBToOAF.EBITargetLinksFilter(p))
.flatMap(p => BioDBToOAF.convertEBILinksToOaf(p))
.flatMap(i=> CollectionUtils.fixRelations(i)).filter(i => i != null)
.write.mode(SaveMode.Overwrite).save(targetPath)
}
}

View File

@ -1,5 +1,5 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
import java.io.Serializable;
import java.util.ArrayList;

View File

@ -1,5 +1,5 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
import java.io.Serializable;

View File

@ -1,5 +1,5 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
public class PMGrant {

View File

@ -1,5 +1,5 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
import java.io.Serializable;

View File

@ -1,4 +1,4 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed
package eu.dnetlib.dhp.sx.bio.pubmed
import scala.xml.MetaData
import scala.xml.pull.{EvElemEnd, EvElemStart, EvText, XMLEventReader}

View File

@ -1,5 +1,5 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed;
package eu.dnetlib.dhp.sx.bio.pubmed;
public class PMSubject {
private String value;

View File

@ -1,11 +1,12 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed
package eu.dnetlib.dhp.sx.bio.pubmed
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf._
import eu.dnetlib.dhp.schema.oaf.utils.{GraphCleaningFunctions, IdentifierFactory, OafMapperUtils, PidType}
import eu.dnetlib.dhp.schema.oaf._
import scala.collection.JavaConverters._
import java.util.regex.Pattern
import scala.collection.JavaConverters._
object PubMedToOaf {
@ -71,7 +72,7 @@ object PubMedToOaf {
if (article.getPublicationTypes == null)
return null
val i = new Instance
var pidList: List[StructuredProperty] = List(OafMapperUtils.structuredProperty(article.getPmid, PidType.pmid.toString, PidType.pmid.toString, ModelConstants.DNET_PID_TYPES, ModelConstants.DNET_PID_TYPES, dataInfo))
val pidList: List[StructuredProperty] = List(OafMapperUtils.structuredProperty(article.getPmid, PidType.pmid.toString, PidType.pmid.toString, ModelConstants.DNET_PID_TYPES, ModelConstants.DNET_PID_TYPES, dataInfo))
if (pidList == null)
return null
@ -105,7 +106,7 @@ object PubMedToOaf {
if (alternateIdentifier != null)
i.setAlternateIdentifier(List(alternateIdentifier).asJava)
result.setInstance(List(i).asJava)
i.getPid.asScala.filter(p => "pmid".equalsIgnoreCase(p.getQualifier.getClassid)).map(p => p.getValue)(collection breakOut)
i.getPid.asScala.filter(p => "pmid".equalsIgnoreCase(p.getQualifier.getClassid)).map(p => p.getValue)(collection.breakOut)
val urlLists: List[String] = pidList
.map(s => (urlMap.getOrElse(s.getQualifier.getClassid, ""), s.getValue))
.filter(t => t._1.nonEmpty)
@ -136,7 +137,7 @@ object PubMedToOaf {
}
val subjects: List[StructuredProperty] = article.getSubjects.asScala.map(s => OafMapperUtils.structuredProperty(s.getValue, SUBJ_CLASS, SUBJ_CLASS, ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES, dataInfo))(collection breakOut)
val subjects: List[StructuredProperty] = article.getSubjects.asScala.map(s => OafMapperUtils.structuredProperty(s.getValue, SUBJ_CLASS, SUBJ_CLASS, ModelConstants.DNET_SUBJECT_TYPOLOGIES, ModelConstants.DNET_SUBJECT_TYPOLOGIES, dataInfo))(collection.breakOut)
if (subjects != null)
result.setSubject(subjects.asJava)
@ -148,7 +149,7 @@ object PubMedToOaf {
author.setFullname(a.getFullName)
author.setRank(index + 1)
author
}(collection breakOut)
}(collection.breakOut)
if (authors != null && authors.nonEmpty)

View File

@ -0,0 +1,33 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName":"out",
"paramLongName":"outputPath",
"paramDescription": "the output path",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
},
{
"paramName": "hnn",
"paramLongName": "hdfsNameNode",
"paramDescription": "the path used to store the HostedByMap",
"paramRequired": true
},
{
"paramName": "cfn",
"paramLongName": "classForName",
"paramDescription": "the path used to store the HostedByMap",
"paramRequired": true
}
]

View File

@ -0,0 +1,30 @@
<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>hiveMetastoreUris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>hiveJdbcUrl</name>
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000</value>
</property>
<property>
<name>hiveDbName</name>
<value>openaire</value>
</property>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>

View File

@ -0,0 +1,174 @@
<workflow-app name="UnresolvedEntities" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>fosPath</name>
<description>the input path of the resources to be extended</description>
</property>
<property>
<name>bipScorePath</name>
<description>the path where to find the bipFinder scores</description>
</property>
<property>
<name>outputPath</name>
<description>the path where to store the actionset</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>
<property>
<name>oozieActionShareLibForSpark2</name>
<description>oozie action sharelib for spark 2.*</description>
</property>
<property>
<name>spark2ExtraListeners</name>
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
<description>spark 2.* extra listeners classname</description>
</property>
<property>
<name>spark2SqlQueryExecutionListeners</name>
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
<description>spark 2.* sql query execution listeners classname</description>
</property>
<property>
<name>spark2YarnHistoryServerAddress</name>
<description>spark 2.* yarn history server address</description>
</property>
<property>
<name>spark2EventLogDir</name>
<description>spark 2.* event log dir location</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>${oozieActionShareLibForSpark2}</value>
</property>
</configuration>
</global>
<start to="prepareInfo"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<fork name="prepareInfo">
<path start="prepareBip"/>
<path start="getFOS"/>
</fork>
<action name="prepareBip">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the unresolved from bip finder!</name>
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareBipFinder</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${bipScorePath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/prepared</arg>
</spark>
<ok to="join"/>
<error to="Kill"/>
</action>
<action name="getFOS">
<java>
<main-class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.GetFOSData</main-class>
<arg>--hdfsNameNode</arg><arg>${nameNode}</arg>
<arg>--sourcePath</arg><arg>${fosPath}</arg>
<arg>--outputPath</arg><arg>${workingDir}/input/fos</arg>
<arg>--classForName</arg><arg>eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel</arg>
</java>
<ok to="prepareFos"/>
<error to="Kill"/>
</action>
<action name="prepareFos">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Produces the unresolved from FOS!</name>
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareFOSSparkJob</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/input/fos</arg>
<arg>--outputPath</arg><arg>${workingDir}/prepared</arg>
</spark>
<ok to="join"/>
<error to="Kill"/>
</action>
<join name="join" to="produceUnresolved"/>
<action name="produceUnresolved">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Saves the result produced for bip and fos by grouping results with the same id</name>
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.SparkSaveUnresolved</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/prepared</arg>
<arg>--outputPath</arg><arg>${outputPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -0,0 +1,20 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "sp",
"paramLongName": "sourcePath",
"paramDescription": "the URL from where to get the programme file",
"paramRequired": true
},
{
"paramName": "o",
"paramLongName": "outputPath",
"paramDescription": "the path of the new ActionSet",
"paramRequired": true
}
]

View File

@ -0,0 +1,20 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "sp",
"paramLongName": "sourcePath",
"paramDescription": "the URL from where to get the programme file",
"paramRequired": true
},
{
"paramName": "o",
"paramLongName": "outputPath",
"paramDescription": "the path of the new ActionSet",
"paramRequired": true
}
]

View File

@ -1,81 +0,0 @@
<workflow-app name="Import_Datacite_and_transform_to_OAF" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>mainPath</name>
<description>the working path of Datacite stores</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>blocksize</name>
<value>100</value>
<description>The request block size</description>
</property>
</parameters>
<start to="ImportDatacite"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ImportDatacite">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ImportDatacite</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.ImportDatacite</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--targetPath</arg><arg>${mainPath}/datacite_update</arg>
<arg>--dataciteDumpPath</arg><arg>${mainPath}/datacite_dump</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
<arg>--blocksize</arg><arg>${blocksize}</arg>
</spark>
<ok to="TransformJob"/>
<error to="Kill"/>
</action>
<action name="TransformJob">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>TransformJob</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.GenerateDataciteDatasetSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${mainPath}/datacite_dump</arg>
<arg>--targetPath</arg><arg>${mainPath}/datacite_oaf</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--exportLinks</arg><arg>false</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,84 +0,0 @@
<workflow-app name="Generate_Datacite_and_Crossref_dump_for_Scholexplorer" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>datacitePath</name>
<description>the path of Datacite spark dataset</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>crossrefPath</name>
<description>the path of Crossref spark dataset</description>
</property>
<property>
<name>targetPath</name>
<description>the path of Crossref spark dataset</description>
</property>
</parameters>
<start to="ImportDatacite"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ImportDatacite">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ImportDatacite</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.GenerateDataciteDatasetSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${datacitePath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/datacite_oaf</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--exportLinks</arg><arg>true</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="FilterCrossrefEntities"/>
<error to="Kill"/>
</action>
<action name="FilterCrossrefEntities">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>FilterCrossrefEntities</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.FilterCrossrefEntitiesSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${crossrefPath}</arg>
<arg>--targetPath</arg><arg>${targetPath}/crossref_oaf</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,46 +1,52 @@
<workflow-app name="Datacite_to_ActionSet_Workflow" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="Collect_Datacite" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<name>mainPath</name>
<description>the working path of Datacite stores</description>
</property>
<property>
<name>outputPath</name>
<description>the path of Datacite ActionSet</description>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>blocksize</name>
<value>100</value>
<description>The request block size</description>
</property>
</parameters>
<start to="ExportDataset"/>
<start to="ImportDatacite"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ExportDataset">
<action name="ImportDatacite">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>ExportDataset</name>
<class>eu.dnetlib.dhp.actionmanager.datacite.ExportActionSetJobNode</class>
<name>ImportDatacite</name>
<class>eu.dnetlib.dhp.datacite.ImportDatacite</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--targetPath</arg><arg>${outputPath}</arg>
<arg>--targetPath</arg><arg>${mainPath}/datacite_update</arg>
<arg>--dataciteDumpPath</arg><arg>${mainPath}/datacite_dump</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
<arg>--blocksize</arg><arg>${blocksize}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -7,8 +7,8 @@
},
{
"paramName": "t",
"paramLongName": "targetPath",
"paramName": "mo",
"paramLongName": "mdstoreOutputVersion",
"paramDescription": "the target mdstore path",
"paramRequired": true
},

View File

@ -0,0 +1,126 @@
<workflow-app name="transform_Datacite" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>mainPath</name>
<description>the working path of Datacite stores</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>mdStoreOutputId</name>
<description>the identifier of the cleaned MDStore</description>
</property>
<property>
<name>mdStoreManagerURI</name>
<description>the path of the cleaned mdstore</description>
</property>
</parameters>
<start to="StartTransaction"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="StartTransaction">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>NEW_VERSION</arg>
<arg>--mdStoreID</arg><arg>${mdStoreOutputId}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
<capture-output/>
</java>
<ok to="TransformJob"/>
<error to="EndReadRollBack"/>
</action>
<action name="TransformJob">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>TransformJob</name>
<class>eu.dnetlib.dhp.datacite.GenerateDataciteDatasetSpark</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=3840
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${mainPath}/datacite_dump</arg>
<arg>--mdstoreOutputVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--exportLinks</arg><arg>true</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
<ok to="CommitVersion"/>
<error to="Kill"/>
</action>
<action name="CommitVersion">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>COMMIT</arg>
<arg>--namenode</arg><arg>${nameNode}</arg>
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>
<action name="EndReadRollBack">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>READ_UNLOCK</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
<arg>--readMDStoreId</arg><arg>${wf:actionData('BeginRead')['mdStoreReadLockVersion']}</arg>
<capture-output/>
</java>
<ok to="RollBack"/>
<error to="Kill"/>
</action>
<action name="RollBack">
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
<arg>--action</arg><arg>ROLLBACK</arg>
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
</java>
<ok to="Kill"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,42 +1,33 @@
<workflow-app name="Create EBI Dataset" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the Working Path</description>
<description>the PDB Database Working Path</description>
</property>
<property>
<name>workingPath</name>
<description>the Working Path</description>
<name>database</name>
<description>the PDB Database Working Path</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>
<name>targetPath</name>
<description>the Target Working dir path</description>
</property>
</parameters>
<start to="DownloadEBILinks"/>
<start to="ConvertDB"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="DownloadEBILinks">
<action name="ConvertDB">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<master>yarn</master>
<mode>cluster</mode>
<name>Incremental Download EBI Links</name>
<class>eu.dnetlib.dhp.sx.graph.ebi.SparkDownloadEBILinks</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<name>Convert Bio DB to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.bio.SparkTransformBioDatabaseToOAF</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -47,13 +38,14 @@
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--workingPath</arg><arg>${workingPath}</arg>
<arg>--master</arg><arg>yarn</arg>
<arg>--dbPath</arg><arg>${sourcePath}</arg>
<arg>--database</arg><arg>${database}</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -0,0 +1,8 @@
[
{"paramName":"mt", "paramLongName":"master", "paramDescription": "should be local or yarn", "paramRequired": true},
{"paramName":"i", "paramLongName":"isLookupUrl", "paramDescription": "isLookupUrl", "paramRequired": true},
{"paramName":"w", "paramLongName":"workingPath", "paramDescription": "the path of the sequencial file to read", "paramRequired": true},
{"paramName":"t", "paramLongName":"targetPath", "paramDescription": "the oaf path ", "paramRequired": true},
{"paramName":"s", "paramLongName":"skipUpdate", "paramDescription": "skip update ", "paramRequired": false},
{"paramName":"h", "paramLongName":"hdfsServerUri", "paramDescription": "the working path ", "paramRequired": true}
]

View File

@ -0,0 +1,5 @@
[
{"paramName":"mt", "paramLongName":"master", "paramDescription": "should be local or yarn", "paramRequired": true},
{"paramName":"s", "paramLongName":"sourcePath", "paramDescription": "the source Path", "paramRequired": true},
{"paramName":"w", "paramLongName":"workingPath", "paramDescription": "the working path ", "paramRequired": true}
]

View File

@ -0,0 +1,105 @@
<workflow-app name="Create EBI Dataset" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>sourcePath</name>
<description>the Working Path</description>
</property>
<property>
<name>workingPath</name>
<description>the Working Path</description>
</property>
<property>
<name>targetPath</name>
<description>the OAF MDStore Path</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>
<property>
<name>resumeFrom</name>
<value>DownloadEBILinks</value>
<description>node to start</description>
</property>
</parameters>
<start to="resume_from"/>
<decision name="resume_from">
<switch>
<case to="DownloadEBILinks">${wf:conf('resumeFrom') eq 'DownloadEBILinks'}</case>
<case to="CreateEBIDataSet">${wf:conf('resumeFrom') eq 'CreateEBIDataSet'}</case>
<default to="DownloadEBILinks"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="DownloadEBILinks">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Incremental Download EBI Links</name>
<class>eu.dnetlib.dhp.sx.bio.ebi.SparkDownloadEBILinks</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.shuffle.partitions=2000
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--workingPath</arg><arg>${workingPath}</arg>
<arg>--master</arg><arg>yarn</arg>
</spark>
<ok to="OverrideFolders"/>
<error to="Kill"/>
</action>
<action name="OverrideFolders">
<fs>
<delete path="${sourcePath}/ebi_links_dataset_old"/>
<move source="${sourcePath}/ebi_links_dataset" target="${sourcePath}/ebi_links_dataset_old"/>
<move source="${workingPath}/links_final" target="${sourcePath}/ebi_links_dataset"/>
</fs>
<ok to="CreateEBIDataSet"/>
<error to="Kill"/>
</action>
<action name="CreateEBIDataSet">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Create OAF DataSet</name>
<class>eu.dnetlib.dhp.sx.bio.ebi.SparkEBILinksToOaf</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.sql.shuffle.partitions=2000
${sparkExtraOPT}
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/ebi_links_dataset</arg>
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--master</arg><arg>yarn</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -1,17 +1,22 @@
<workflow-app name="Transform_Pubmed_Workflow" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="Download_Transform_Pubmed_Workflow" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>baselineWorkingPath</name>
<description>the Baseline Working Path</description>
</property>
<property>
<name>targetPath</name>
<description>the Target Path</description>
</property>
<property>
<name>isLookupUrl</name>
<description>The IS lookUp service endopoint</description>
</property>
<property>
<name>targetPath</name>
<description>The target path</description>
</property>
<property>
<name>skipUpdate</name>
<value>false</value>
<description>The request block size</description>
</property>
</parameters>
<start to="ConvertDataset"/>
@ -24,9 +29,9 @@
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Convert Baseline to Dataset</name>
<class>eu.dnetlib.dhp.sx.graph.ebi.SparkCreateBaselineDataFrame</class>
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
<name>Convert Baseline to OAF Dataset</name>
<class>eu.dnetlib.dhp.sx.bio.ebi.SparkCreateBaselineDataFrame</class>
<jar>dhp-aggregation-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
@ -41,6 +46,8 @@
<arg>--targetPath</arg><arg>${targetPath}</arg>
<arg>--master</arg><arg>yarn</arg>
<arg>--isLookupUrl</arg><arg>${isLookupUrl}</arg>
<arg>--hdfsServerUri</arg><arg>${nameNode}</arg>
<arg>--skipUpdate</arg><arg>${skipUpdate}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>

View File

@ -0,0 +1,250 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import static org.junit.jupiter.api.Assertions.*;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStreamReader;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.stream.Collectors;
import org.apache.commons.io.FileUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocalFileSystem;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
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 com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
import eu.dnetlib.dhp.common.collection.CollectorException;
import eu.dnetlib.dhp.schema.oaf.Result;
public class PrepareTest {
private static final Logger log = LoggerFactory.getLogger(ProduceTest.class);
private static Path workingDir;
private static SparkSession spark;
private static LocalFileSystem fs;
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
@BeforeAll
public static void beforeAll() throws IOException {
workingDir = Files.createTempDirectory(PrepareTest.class.getSimpleName());
fs = FileSystem.getLocal(new Configuration());
log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf();
conf.setAppName(ProduceTest.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(PrepareTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
spark.stop();
}
@Test
void bipPrepareTest() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/bip/bip.json")
.getPath();
PrepareBipFinder
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"--outputPath", workingDir.toString() + "/work"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
.textFile(workingDir.toString() + "/work/bip")
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
Assertions.assertEquals(86, tmp.count());
String doi1 = "unresolved::10.0000/096020199389707::doi";
Assertions.assertEquals(1, tmp.filter(r -> r.getId().equals(doi1)).count());
Assertions.assertEquals(3, tmp.filter(r -> r.getId().equals(doi1)).collect().get(0).getMeasures().size());
Assertions
.assertEquals(
"6.34596412687e-09", tmp
.filter(r -> r.getId().equals(doi1))
.collect()
.get(0)
.getMeasures()
.stream()
.filter(sl -> sl.getId().equals("influence"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
Assertions
.assertEquals(
"0.641151896994", tmp
.filter(r -> r.getId().equals(doi1))
.collect()
.get(0)
.getMeasures()
.stream()
.filter(sl -> sl.getId().equals("popularity_alt"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
Assertions
.assertEquals(
"2.33375102921e-09", tmp
.filter(r -> r.getId().equals(doi1))
.collect()
.get(0)
.getMeasures()
.stream()
.filter(sl -> sl.getId().equals("popularity"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
}
@Test
void getFOSFileTest() throws IOException, ClassNotFoundException {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/h2020_fos_sbs.csv")
.getPath();
final String outputPath = workingDir.toString() + "/fos.json";
new GetFOSData()
.doRewrite(
sourcePath, outputPath, "eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel",
'\t', fs);
BufferedReader in = new BufferedReader(
new InputStreamReader(fs.open(new org.apache.hadoop.fs.Path(outputPath))));
String line;
int count = 0;
while ((line = in.readLine()) != null) {
FOSDataModel fos = new ObjectMapper().readValue(line, FOSDataModel.class);
System.out.println(new ObjectMapper().writeValueAsString(fos));
count += 1;
}
assertEquals(38, count);
}
@Test
void fosPrepareTest() throws Exception {
final String sourcePath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos.json")
.getPath();
PrepareFOSSparkJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", sourcePath,
"-outputPath", workingDir.toString() + "/work"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
.textFile(workingDir.toString() + "/work/fos")
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
String doi1 = "unresolved::10.3390/s18072310::doi";
assertEquals(50, tmp.count());
assertEquals(1, tmp.filter(row -> row.getId().equals(doi1)).count());
assertTrue(
tmp
.filter(r -> r.getId().equals(doi1))
.flatMap(r -> r.getSubject().iterator())
.map(sbj -> sbj.getValue())
.collect()
.contains("engineering and technology"));
assertTrue(
tmp
.filter(r -> r.getId().equals(doi1))
.flatMap(r -> r.getSubject().iterator())
.map(sbj -> sbj.getValue())
.collect()
.contains("nano-technology"));
assertTrue(
tmp
.filter(r -> r.getId().equals(doi1))
.flatMap(r -> r.getSubject().iterator())
.map(sbj -> sbj.getValue())
.collect()
.contains("nanoscience & nanotechnology"));
String doi = "unresolved::10.1111/1365-2656.12831::doi";
assertEquals(1, tmp.filter(row -> row.getId().equals(doi)).count());
assertTrue(
tmp
.filter(r -> r.getId().equals(doi))
.flatMap(r -> r.getSubject().iterator())
.map(sbj -> sbj.getValue())
.collect()
.contains("psychology and cognitive sciences"));
assertTrue(
tmp
.filter(r -> r.getId().equals(doi))
.flatMap(r -> r.getSubject().iterator())
.map(sbj -> sbj.getValue())
.collect()
.contains("social sciences"));
assertFalse(
tmp
.filter(r -> r.getId().equals(doi))
.flatMap(r -> r.getSubject().iterator())
.map(sbj -> sbj.getValue())
.collect()
.contains("NULL"));
}
}

View File

@ -0,0 +1,234 @@
package eu.dnetlib.dhp.actionmanager.createunresolvedentities;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Path;
import java.util.List;
import java.util.stream.Collectors;
import org.apache.commons.io.FileUtils;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocalFileSystem;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
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 com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
public class ProduceTest {
private static final Logger log = LoggerFactory.getLogger(ProduceTest.class);
private static Path workingDir;
private static SparkSession spark;
private static LocalFileSystem fs;
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
private static final String ID_PREFIX = "50|doi_________";
@BeforeAll
public static void beforeAll() throws IOException {
workingDir = Files.createTempDirectory(ProduceTest.class.getSimpleName());
fs = FileSystem.getLocal(new Configuration());
log.info("using work dir {}", workingDir);
SparkConf conf = new SparkConf();
conf.setAppName(ProduceTest.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(ProduceTest.class.getSimpleName())
.config(conf)
.getOrCreate();
}
@AfterAll
public static void afterAll() throws IOException {
FileUtils.deleteDirectory(workingDir.toFile());
spark.stop();
}
@Test
void produceTest() throws Exception {
final String bipPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/bip/bip.json")
.getPath();
PrepareBipFinder
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", bipPath,
"--outputPath", workingDir.toString() + "/work"
});
final String fosPath = getClass()
.getResource("/eu/dnetlib/dhp/actionmanager/createunresolvedentities/fos/fos.json")
.getPath();
PrepareFOSSparkJob
.main(
new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", fosPath,
"-outputPath", workingDir.toString() + "/work"
});
SparkSaveUnresolved.main(new String[] {
"--isSparkSessionManaged", Boolean.FALSE.toString(),
"--sourcePath", workingDir.toString() + "/work",
"-outputPath", workingDir.toString() + "/unresolved"
});
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
JavaRDD<Result> tmp = sc
.textFile(workingDir.toString() + "/unresolved")
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
Assertions.assertEquals(135, tmp.count());
Assertions.assertEquals(1, tmp.filter(row -> row.getId().equals("unresolved::10.3390/s18072310::doi")).count());
Assertions
.assertEquals(
3, tmp
.filter(row -> row.getId().equals("unresolved::10.3390/s18072310::doi"))
.collect()
.get(0)
.getSubject()
.size());
Assertions
.assertEquals(
3, tmp
.filter(row -> row.getId().equals("unresolved::10.3390/s18072310::doi"))
.collect()
.get(0)
.getMeasures()
.size());
List<StructuredProperty> sbjs = tmp
.filter(row -> row.getId().equals("unresolved::10.3390/s18072310::doi"))
.flatMap(row -> row.getSubject().iterator())
.collect();
sbjs.forEach(sbj -> Assertions.assertEquals("FOS", sbj.getQualifier().getClassid()));
sbjs
.forEach(
sbj -> Assertions
.assertEquals(
"Fields of Science and Technology classification", sbj.getQualifier().getClassname()));
sbjs
.forEach(
sbj -> Assertions
.assertEquals(ModelConstants.DNET_SUBJECT_TYPOLOGIES, sbj.getQualifier().getSchemeid()));
sbjs
.forEach(
sbj -> Assertions
.assertEquals(ModelConstants.DNET_SUBJECT_TYPOLOGIES, sbj.getQualifier().getSchemename()));
sbjs.forEach(sbj -> Assertions.assertEquals(false, sbj.getDataInfo().getDeletedbyinference()));
sbjs.forEach(sbj -> Assertions.assertEquals(true, sbj.getDataInfo().getInferred()));
sbjs.forEach(sbj -> Assertions.assertEquals(false, sbj.getDataInfo().getInvisible()));
sbjs.forEach(sbj -> Assertions.assertEquals("", sbj.getDataInfo().getTrust()));
sbjs.forEach(sbj -> Assertions.assertEquals("update", sbj.getDataInfo().getInferenceprovenance()));
sbjs
.forEach(
sbj -> Assertions.assertEquals("subject:fos", sbj.getDataInfo().getProvenanceaction().getClassid()));
sbjs
.forEach(
sbj -> Assertions
.assertEquals("Inferred by OpenAIRE", sbj.getDataInfo().getProvenanceaction().getClassname()));
sbjs
.forEach(
sbj -> Assertions
.assertEquals(
ModelConstants.DNET_PROVENANCE_ACTIONS, sbj.getDataInfo().getProvenanceaction().getSchemeid()));
sbjs
.forEach(
sbj -> Assertions
.assertEquals(
ModelConstants.DNET_PROVENANCE_ACTIONS,
sbj.getDataInfo().getProvenanceaction().getSchemename()));
sbjs.stream().anyMatch(sbj -> sbj.getValue().equals("engineering and technology"));
sbjs.stream().anyMatch(sbj -> sbj.getValue().equals("nano-technology"));
sbjs.stream().anyMatch(sbj -> sbj.getValue().equals("nanoscience & nanotechnology"));
List<Measure> measures = tmp
.filter(row -> row.getId().equals("unresolved::10.3390/s18072310::doi"))
.flatMap(row -> row.getMeasures().iterator())
.collect();
Assertions
.assertEquals(
"7.5597134689e-09", measures
.stream()
.filter(mes -> mes.getId().equals("influence"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
Assertions
.assertEquals(
"4.903880192", measures
.stream()
.filter(mes -> mes.getId().equals("popularity_alt"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
Assertions
.assertEquals(
"1.17977512835e-08", measures
.stream()
.filter(mes -> mes.getId().equals("popularity"))
.collect(Collectors.toList())
.get(0)
.getUnit()
.get(0)
.getValue());
Assertions
.assertEquals(
49, tmp
.filter(row -> !row.getId().equals("unresolved::10.3390/s18072310::doi"))
.filter(row -> row.getSubject() != null)
.count());
Assertions
.assertEquals(
85,
tmp
.filter(row -> !row.getId().equals("unresolved::10.3390/s18072310::doi"))
.filter(r -> r.getMeasures() != null)
.count());
}
}

View File

@ -1,8 +1,7 @@
package eu.dnetlib.dhp.actionmanager.datacite
package eu.dnetlib.dhp.datacite
import com.fasterxml.jackson.databind.ObjectMapper
import com.fasterxml.jackson.databind.SerializationFeature
import com.fasterxml.jackson.databind.{ObjectMapper, SerializationFeature}
import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest
import eu.dnetlib.dhp.schema.oaf.Oaf
import org.junit.jupiter.api.extension.ExtendWith

View File

@ -1,12 +1,10 @@
package eu.dnetlib.dhp.sx.graph.bio.pubmed
package eu.dnetlib.dhp.sx.bio
import com.fasterxml.jackson.databind.{DeserializationFeature, ObjectMapper, SerializationFeature}
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.{CleaningFunctions, OafMapperUtils, PidType}
import eu.dnetlib.dhp.aggregation.AbstractVocabularyTest
import eu.dnetlib.dhp.schema.oaf.{Oaf, Relation, Result}
import eu.dnetlib.dhp.sx.graph.bio.BioDBToOAF.ScholixResolved
import eu.dnetlib.dhp.sx.graph.bio.BioDBToOAF
import eu.dnetlib.dhp.sx.graph.bio.pubmed.PubMedToOaf.dataInfo
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
import eu.dnetlib.dhp.sx.bio.pubmed.{PMArticle, PMParser, PubMedToOaf}
import org.json4s.DefaultFormats
import org.json4s.JsonAST.{JField, JObject, JString}
import org.json4s.jackson.JsonMethods.parse
@ -50,9 +48,11 @@ class BioScholixTest extends AbstractVocabularyTest{
}
@Test
def testEBIData() = {
val inputXML = Source.fromInputStream(getClass.getResourceAsStream("pubmed.xml")).mkString
val inputXML = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/pubmed.xml")).mkString
val xml = new XMLEventReader(Source.fromBytes(inputXML.getBytes()))
new PMParser(xml).foreach(s =>println(mapper.writeValueAsString(s)))
}
@ -62,7 +62,7 @@ class BioScholixTest extends AbstractVocabularyTest{
def testPubmedToOaf(): Unit = {
assertNotNull(vocabularies)
assertTrue(vocabularies.vocabularyExists("dnet:publication_resource"))
val records:String =Source.fromInputStream(getClass.getResourceAsStream("pubmed_dump")).mkString
val records:String =Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/dhp/sx/graph/bio/pubmed_dump")).mkString
val r:List[Oaf] = records.lines.toList.map(s=>mapper.readValue(s, classOf[PMArticle])).map(a => PubMedToOaf.convert(a, vocabularies))
assertEquals(10, r.size)
assertTrue(r.map(p => p.asInstanceOf[Result]).flatMap(p => p.getInstance().asScala.map(i => i.getInstancetype.getClassid)).exists(p => "0037".equalsIgnoreCase(p)))

View File

@ -0,0 +1,86 @@
{"10.3390/s18072310": [{"id": "influence", "unit": [{"value": "7.5597134689e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "4.903880192", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "1.17977512835e-08", "key": "score"}]}]}
{"10.0000/096020199389707": [{"id": "influence", "unit": [{"value": "6.34596412687e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.641151896994", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "2.33375102921e-09", "key": "score"}]}]}
{"10.00000/jpmc.2017.106": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "5.39172290649e-09", "key": "score"}]}]}
{"10.0000/9781845416881": [{"id": "influence", "unit": [{"value": "5.96492048955e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "1.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "1.12641925838e-08", "key": "score"}]}]}
{"10.0000/anziamj.v0i0.266": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "3.76260934675e-10", "key": "score"}]}]}
{"10.0000/anziamj.v48i0.79": [{"id": "influence", "unit": [{"value": "6.93311506443e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.002176782336", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "1.7668105708e-09", "key": "score"}]}]}
{"10.0000/anziamj.v50i0.1472": [{"id": "influence", "unit": [{"value": "6.26777280882e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.406656", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "3.39745193285e-09", "key": "score"}]}]}
{"10.0000/cja5553": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/czastest.16": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/czastest.17": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "3.47956715615e-09", "key": "score"}]}]}
{"10.0000/czastest.18": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "3.47956715615e-09", "key": "score"}]}]}
{"10.0000/czastest.20": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/czastest.21": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "3.47956715615e-09", "key": "score"}]}]}
{"10.0000/czastest.28": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "3.47956715615e-09", "key": "score"}]}]}
{"10.0000/czastest.60": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/czt.2019.1.2.15": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v4i02.36": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v4i02.37": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v4i02.38": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v5i01.32": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v6i01.24": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v6i01.27": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v6i02.41": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v6i02.44": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i01.40": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.01810569717e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i01.42": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i01.47": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i01.51": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i01.52": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i02.86": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i02.88": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v7i02.91": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v8i01.129": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v8i01.180": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "5.39172290649e-09", "key": "score"}]}]}
{"10.0000/geoekonomi.v8i01.87": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "4.65008652949e-09", "key": "score"}]}]}
{"10.0000/hbv2004w010": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hbv2101w001": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2101w002": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2101w003": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2101w004": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2101w005": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2101w006": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2101w007": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2102w001": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hbv2102w010": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "9.88840807598e-09", "key": "score"}]}]}
{"10.0000/hoplos.v1i1.13207": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v1i1.13208": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "5.39172290649e-09", "key": "score"}]}]}
{"10.0000/hoplos.v1i1.13209": [{"id": "influence", "unit": [{"value": "6.32078461509e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "1.6", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.3168486939e-09", "key": "score"}]}]}
{"10.0000/hoplos.v1i1.13210": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v1i1.13211": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "5.39172290649e-09", "key": "score"}]}]}
{"10.0000/hoplos.v1i1.13212": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "5.39172290649e-09", "key": "score"}]}]}
{"10.0000/hoplos.v1i2.13231": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i2.28782": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i2.28783": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i2.28784": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i2.28786": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i2.28787": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i2.28788": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i3.28234": [{"id": "influence", "unit": [{"value": "6.40470414877e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.6", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.89465099068e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i3.28236": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i3.28238": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i3.28239": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i3.28242": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v2i3.28243": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "6.26204125721e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i4.38186": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i4.38187": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i4.38190": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i4.38207": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i4.38209": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i5.41163": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i5.41166": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i5.41167": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i5.41168": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "7.28336930301e-09", "key": "score"}]}]}
{"10.0000/hoplos.v3i5.41229": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.36360": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.40796": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.41153": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.42511": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.42555": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.42752": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.42768": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i6.42795": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i7.41295": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i7.42830": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i7.42861": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}
{"10.0000/hoplos.v4i7.43096": [{"id": "influence", "unit": [{"value": "5.91019644836e-09", "key": "score"}]}, {"id": "popularity_alt", "unit": [{"value": "0.0", "key": "score"}]}, {"id": "popularity", "unit": [{"value": "8.48190886761e-09", "key": "score"}]}]}

View File

@ -0,0 +1,38 @@
{"doi":"10.3390/s18072310","level1":"engineering and technology","level2":"nano-technology","level3":"nanoscience & nanotechnology"}
{"doi":"10.1111/1365-2656.12831\u000210.17863/cam.24369","level1":"social sciences","level2":"psychology and cognitive sciences","level3":"NULL"}
{"doi":"10.3929/ethz-b-000187584\u000210.1002/chem.201701644","level1":"natural sciences","level2":"NULL","level3":"NULL"}
{"doi":"10.1080/01913123.2017.1367361","level1":"medical and health sciences","level2":"clinical medicine","level3":"oncology & carcinogenesis"}
{"doi":"10.1051/e3sconf/20199207011","level1":"natural sciences","level2":"earth and related environmental sciences","level3":"environmental sciences"}
{"doi":"10.1038/onc.2015.333","level1":"medical and health sciences","level2":"clinical medicine","level3":"oncology & carcinogenesis"}
{"doi":"10.1093/mnras/staa256","level1":"natural sciences","level2":"physical sciences","level3":"NULL"}
{"doi":"10.1016/j.jclepro.2018.07.166","level1":"engineering and technology","level2":"other engineering and technologies","level3":"building & construction"}
{"doi":"10.1103/physrevlett.125.037403","level1":"natural sciences","level2":"physical sciences","level3":"nuclear & particles physics"}
{"doi":"10.1080/03602532.2017.1316285","level1":"natural sciences","level2":"NULL","level3":"NULL"}
{"doi":"10.1001/jamanetworkopen.2019.1868","level1":"medical and health sciences","level2":"other medical science","level3":"health policy & services"}
{"doi":"10.1128/mra.00874-18","level1":"natural sciences","level2":"biological sciences","level3":"plant biology & botany"}
{"doi":"10.1016/j.nancom.2018.03.001","level1":"engineering and technology","level2":"NULL","level3":"NULL"}
{"doi":"10.1112/topo.12174","level1":"natural sciences","level2":"NULL","level3":"NULL"}
{"doi":"10.12688/wellcomeopenres.15846.1","level1":"medical and health sciences","level2":"health sciences","level3":"NULL"}
{"doi":"10.21468/scipostphys.3.1.001","level1":"natural sciences","level2":"physical sciences","level3":"NULL"}
{"doi":"10.1088/1741-4326/ab6c77","level1":"natural sciences","level2":"physical sciences","level3":"nuclear & particles physics"}
{"doi":"10.1109/tpwrs.2019.2944747","level1":"engineering and technology","level2":"electrical engineering, electronic engineering, information engineering","level3":"electrical & electronic engineering"}
{"doi":"10.1016/j.expthermflusci.2019.109994\u000210.17863/cam.46212","level1":"engineering and technology","level2":"mechanical engineering","level3":"mechanical engineering & transports"}
{"doi":"10.1109/tc.2018.2860012","level1":"engineering and technology","level2":"electrical engineering, electronic engineering, information engineering","level3":"computer hardware & architecture"}
{"doi":"10.1002/mma.6622","level1":"natural sciences","level2":"mathematics","level3":"numerical & computational mathematics"}
{"doi":"10.1051/radiopro/2020020","level1":"natural sciences","level2":"chemical sciences","level3":"NULL"}
{"doi":"10.1007/s12268-019-1003-4","level1":"medical and health sciences","level2":"basic medicine","level3":"NULL"}
{"doi":"10.3390/cancers12010236","level1":"medical and health sciences","level2":"health sciences","level3":"biochemistry & molecular biology"}
{"doi":"10.6084/m9.figshare.9912614\u000210.6084/m9.figshare.9912614.v1\u000210.1080/00268976.2019.1665199","level1":"natural sciences","level2":"chemical sciences","level3":"physical chemistry"}
{"doi":"10.1175/jpo-d-17-0239.1","level1":"natural sciences","level2":"biological sciences","level3":"marine biology & hydrobiology"}
{"doi":"10.1007/s13218-020-00674-7","level1":"engineering and technology","level2":"industrial biotechnology","level3":"industrial engineering & automation"}
{"doi":"10.1016/j.psyneuen.2016.02.003\u000210.1016/j.psyneuen.2016.02.00310.7892/boris.78886\u000210.7892/boris.78886","level1":"medical and health sciences","level2":"basic medicine","level3":"NULL"}
{"doi":"10.1109/ted.2018.2813542","level1":"engineering and technology","level2":"electrical engineering, electronic engineering, information engineering","level3":"electrical & electronic engineering"}
{"doi":"10.3989/scimar.04739.25a","level1":"natural sciences","level2":"biological sciences","level3":"NULL"}
{"doi":"10.3390/su12187503","level1":"natural sciences","level2":"earth and related environmental sciences","level3":"NULL"}
{"doi":"10.1016/j.ccell.2018.08.017","level1":"medical and health sciences","level2":"basic medicine","level3":"biochemistry & molecular biology"}
{"doi":"10.1103/physrevresearch.2.023322","level1":"natural sciences","level2":"physical sciences","level3":"nuclear & particles physics"}
{"doi":"10.1039/c8cp03234c","level1":"natural sciences","level2":"NULL","level3":"NULL"}
{"doi":"10.5281/zenodo.3696557\u000210.5281/zenodo.3696556\u000210.1109/jsac.2016.2545384","level1":"engineering and technology","level2":"electrical engineering, electronic engineering, information engineering","level3":"networking & telecommunications"}
{"doi":"10.1038/ng.3667\u000210.1038/ng.3667.\u000210.17615/tct6-4m26\u000210.17863/cam.15649","level1":"medical and health sciences","level2":"health sciences","level3":"genetics & heredity"}
{"doi":"10.1016/j.jclepro.2019.119065","level1":"engineering and technology","level2":"other engineering and technologies","level3":"building & construction"}
{"doi":"10.1111/pce.13392","level1":"agricultural and veterinary sciences","level2":"agriculture, forestry, and fisheries","level3":"agronomy & agriculture"}

View File

@ -0,0 +1,38 @@
dedup_wf_001::ddcc7a56fa13e49bcc59c6bdd19ad26c 10.3390/s18072310 engineering and technology nano-technology nanoscience & nanotechnology
dedup_wf_001::b76062d56e28224eac56111a4e1e5ecf 10.1111/1365-2656.1283110.17863/cam.24369 social sciences psychology and cognitive sciences NULL
dedup_wf_001::bb752acb8f403a25fa7851a302f7b7ac 10.3929/ethz-b-00018758410.1002/chem.201701644 natural sciences NULL NULL
dedup_wf_001::2f1435a9201ecf5cbbcb12c9b2d971cd 10.1080/01913123.2017.1367361 medical and health sciences clinical medicine oncology & carcinogenesis
dedup_wf_001::fc9e47ec16c67b101724320d4b030514 10.1051/e3sconf/20199207011 natural sciences earth and related environmental sciences environmental sciences
dedup_wf_001::caa1e5b4de387cb31751552f4f0f5d72 10.1038/onc.2015.333 medical and health sciences clinical medicine oncology & carcinogenesis
dedup_wf_001::c2a98df5637d69bf0524eaf40fe6bf11 10.1093/mnras/staa256 natural sciences physical sciences NULL
dedup_wf_001::c221262bdc77cbfd59859a402f0e3991 10.1016/j.jclepro.2018.07.166 engineering and technology other engineering and technologies building & construction
doiboost____::d56d9dc21f317b3e009d5b6c8ea87212 10.1103/physrevlett.125.037403 natural sciences physical sciences nuclear & particles physics
dedup_wf_001::8a7269c8ee6470b2fb4fd384bc389e08 10.1080/03602532.2017.1316285 natural sciences NULL NULL
dedup_wf_001::28342ebbc19833e4e1f4a2b23cf5ee20 10.1001/jamanetworkopen.2019.1868 medical and health sciences other medical science health policy & services
dedup_wf_001::c1e1daf2b55dd9ec8e1c7c7458bbc7bc 10.1128/mra.00874-18 natural sciences biological sciences plant biology & botany
dedup_wf_001::a2ef4a2720c71907180750e5871298ef 10.1016/j.nancom.2018.03.001 engineering and technology NULL NULL
dedup_wf_001::676f46a31519e83a89efcb1c626286fb 10.1112/topo.12174 natural sciences NULL NULL
dedup_wf_001::6f2761642f1e39313388e2c4060657dd 10.12688/wellcomeopenres.15846.1 medical and health sciences health sciences NULL
dedup_wf_001::e414c1dec599521a9635a60de0f6755b 10.21468/scipostphys.3.1.001 natural sciences physical sciences NULL
dedup_wf_001::f3395fe0f330164ea424dc61c86c9a3d 10.1088/1741-4326/ab6c77 natural sciences physical sciences nuclear & particles physics
dedup_wf_001::a4f32a97a783117012f1de11797e73f2 10.1109/tpwrs.2019.2944747 engineering and technology electrical engineering, electronic engineering, information engineering electrical & electronic engineering
dedup_wf_001::313ae1cd083ae1696d12dd1909f97df8 10.1016/j.expthermflusci.2019.10999410.17863/cam.46212 engineering and technology mechanical engineering mechanical engineering & transports
dedup_wf_001::2a300a7d3ca7347791ebcef986bc0682 10.1109/tc.2018.2860012 engineering and technology electrical engineering, electronic engineering, information engineering computer hardware & architecture
doiboost____::5b79bd7bd9f87361b4a4abc3cbb2df75 10.1002/mma.6622 natural sciences mathematics numerical & computational mathematics
dedup_wf_001::6a3f61f217a2519fbaddea1094e3bfc2 10.1051/radiopro/2020020 natural sciences chemical sciences NULL
dedup_wf_001::a3f0430309a639f4234a0e57b10f2dee 10.1007/s12268-019-1003-4 medical and health sciences basic medicine NULL
dedup_wf_001::b6b8a3a1cccbee459cf3343485efdb12 10.3390/cancers12010236 medical and health sciences health sciences biochemistry & molecular biology
dedup_wf_001::dd06ee7974730e7b09a4f03c83b3f9bd 10.6084/m9.figshare.991261410.6084/m9.figshare.9912614.v110.1080/00268976.2019.1665199 natural sciences chemical sciences physical chemistry
dedup_wf_001::027c78bef6f972b5e26dfea55d30fbe3 10.1175/jpo-d-17-0239.1 natural sciences biological sciences marine biology & hydrobiology
dedup_wf_001::43edc179aa9e1fbaf582c5203b18b519 10.1007/s13218-020-00674-7 engineering and technology industrial biotechnology industrial engineering & automation
dedup_wf_001::e7770e11cd6eb514bb52c07b5a8a80f0 10.1016/j.psyneuen.2016.02.00310.1016/j.psyneuen.2016.02.00310.7892/boris.7888610.7892/boris.78886 medical and health sciences basic medicine NULL
dedup_wf_001::80bc15d69bdc589149631f3439dde5aa 10.1109/ted.2018.2813542 engineering and technology electrical engineering, electronic engineering, information engineering electrical & electronic engineering
dedup_wf_001::42c1cfa33e7872944b920cff90f4d99e 10.3989/scimar.04739.25a natural sciences biological sciences NULL
dedup_wf_001::9bacdbbaa9da3658b7243d5de8e3ce14 10.3390/su12187503 natural sciences earth and related environmental sciences NULL
dedup_wf_001::59e43d3527dcfecb6097fbd5740c8950 10.1016/j.ccell.2018.08.017 medical and health sciences basic medicine biochemistry & molecular biology
doiboost____::e024d1b738df3b24bc58fa0228542571 10.1103/physrevresearch.2.023322 natural sciences physical sciences nuclear & particles physics
dedup_wf_001::66e9a3237fa8178886d26d3c2d5b9e66 10.1039/c8cp03234c natural sciences NULL NULL
dedup_wf_001::83737ab4205bae751571bb3b166efa18 10.5281/zenodo.369655710.5281/zenodo.369655610.1109/jsac.2016.2545384 engineering and technology electrical engineering, electronic engineering, information engineering networking & telecommunications
dedup_wf_001::e3f892db413a689e572dd256acad55fe 10.1038/ng.366710.1038/ng.3667.10.17615/tct6-4m2610.17863/cam.15649 medical and health sciences health sciences genetics & heredity
dedup_wf_001::14ba594e8fd081847bc3f50f56335003 10.1016/j.jclepro.2019.119065 engineering and technology other engineering and technologies building & construction
dedup_wf_001::08ac7b33a41bcea2d055ecd8585d632e 10.1111/pce.13392 agricultural and veterinary sciences agriculture, forestry, and fisheries agronomy & agriculture
1 dedup_wf_001::ddcc7a56fa13e49bcc59c6bdd19ad26c 10.3390/s18072310 engineering and technology nano-technology nanoscience & nanotechnology
2 dedup_wf_001::b76062d56e28224eac56111a4e1e5ecf 10.1111/1365-2656.1283110.17863/cam.24369 social sciences psychology and cognitive sciences NULL
3 dedup_wf_001::bb752acb8f403a25fa7851a302f7b7ac 10.3929/ethz-b-00018758410.1002/chem.201701644 natural sciences NULL NULL
4 dedup_wf_001::2f1435a9201ecf5cbbcb12c9b2d971cd 10.1080/01913123.2017.1367361 medical and health sciences clinical medicine oncology & carcinogenesis
5 dedup_wf_001::fc9e47ec16c67b101724320d4b030514 10.1051/e3sconf/20199207011 natural sciences earth and related environmental sciences environmental sciences
6 dedup_wf_001::caa1e5b4de387cb31751552f4f0f5d72 10.1038/onc.2015.333 medical and health sciences clinical medicine oncology & carcinogenesis
7 dedup_wf_001::c2a98df5637d69bf0524eaf40fe6bf11 10.1093/mnras/staa256 natural sciences physical sciences NULL
8 dedup_wf_001::c221262bdc77cbfd59859a402f0e3991 10.1016/j.jclepro.2018.07.166 engineering and technology other engineering and technologies building & construction
9 doiboost____::d56d9dc21f317b3e009d5b6c8ea87212 10.1103/physrevlett.125.037403 natural sciences physical sciences nuclear & particles physics
10 dedup_wf_001::8a7269c8ee6470b2fb4fd384bc389e08 10.1080/03602532.2017.1316285 natural sciences NULL NULL
11 dedup_wf_001::28342ebbc19833e4e1f4a2b23cf5ee20 10.1001/jamanetworkopen.2019.1868 medical and health sciences other medical science health policy & services
12 dedup_wf_001::c1e1daf2b55dd9ec8e1c7c7458bbc7bc 10.1128/mra.00874-18 natural sciences biological sciences plant biology & botany
13 dedup_wf_001::a2ef4a2720c71907180750e5871298ef 10.1016/j.nancom.2018.03.001 engineering and technology NULL NULL
14 dedup_wf_001::676f46a31519e83a89efcb1c626286fb 10.1112/topo.12174 natural sciences NULL NULL
15 dedup_wf_001::6f2761642f1e39313388e2c4060657dd 10.12688/wellcomeopenres.15846.1 medical and health sciences health sciences NULL
16 dedup_wf_001::e414c1dec599521a9635a60de0f6755b 10.21468/scipostphys.3.1.001 natural sciences physical sciences NULL
17 dedup_wf_001::f3395fe0f330164ea424dc61c86c9a3d 10.1088/1741-4326/ab6c77 natural sciences physical sciences nuclear & particles physics
18 dedup_wf_001::a4f32a97a783117012f1de11797e73f2 10.1109/tpwrs.2019.2944747 engineering and technology electrical engineering, electronic engineering, information engineering electrical & electronic engineering
19 dedup_wf_001::313ae1cd083ae1696d12dd1909f97df8 10.1016/j.expthermflusci.2019.10999410.17863/cam.46212 engineering and technology mechanical engineering mechanical engineering & transports
20 dedup_wf_001::2a300a7d3ca7347791ebcef986bc0682 10.1109/tc.2018.2860012 engineering and technology electrical engineering, electronic engineering, information engineering computer hardware & architecture
21 doiboost____::5b79bd7bd9f87361b4a4abc3cbb2df75 10.1002/mma.6622 natural sciences mathematics numerical & computational mathematics
22 dedup_wf_001::6a3f61f217a2519fbaddea1094e3bfc2 10.1051/radiopro/2020020 natural sciences chemical sciences NULL
23 dedup_wf_001::a3f0430309a639f4234a0e57b10f2dee 10.1007/s12268-019-1003-4 medical and health sciences basic medicine NULL
24 dedup_wf_001::b6b8a3a1cccbee459cf3343485efdb12 10.3390/cancers12010236 medical and health sciences health sciences biochemistry & molecular biology
25 dedup_wf_001::dd06ee7974730e7b09a4f03c83b3f9bd 10.6084/m9.figshare.991261410.6084/m9.figshare.9912614.v110.1080/00268976.2019.1665199 natural sciences chemical sciences physical chemistry
26 dedup_wf_001::027c78bef6f972b5e26dfea55d30fbe3 10.1175/jpo-d-17-0239.1 natural sciences biological sciences marine biology & hydrobiology
27 dedup_wf_001::43edc179aa9e1fbaf582c5203b18b519 10.1007/s13218-020-00674-7 engineering and technology industrial biotechnology industrial engineering & automation
28 dedup_wf_001::e7770e11cd6eb514bb52c07b5a8a80f0 10.1016/j.psyneuen.2016.02.00310.1016/j.psyneuen.2016.02.00310.7892/boris.7888610.7892/boris.78886 medical and health sciences basic medicine NULL
29 dedup_wf_001::80bc15d69bdc589149631f3439dde5aa 10.1109/ted.2018.2813542 engineering and technology electrical engineering, electronic engineering, information engineering electrical & electronic engineering
30 dedup_wf_001::42c1cfa33e7872944b920cff90f4d99e 10.3989/scimar.04739.25a natural sciences biological sciences NULL
31 dedup_wf_001::9bacdbbaa9da3658b7243d5de8e3ce14 10.3390/su12187503 natural sciences earth and related environmental sciences NULL
32 dedup_wf_001::59e43d3527dcfecb6097fbd5740c8950 10.1016/j.ccell.2018.08.017 medical and health sciences basic medicine biochemistry & molecular biology
33 doiboost____::e024d1b738df3b24bc58fa0228542571 10.1103/physrevresearch.2.023322 natural sciences physical sciences nuclear & particles physics
34 dedup_wf_001::66e9a3237fa8178886d26d3c2d5b9e66 10.1039/c8cp03234c natural sciences NULL NULL
35 dedup_wf_001::83737ab4205bae751571bb3b166efa18 10.5281/zenodo.369655710.5281/zenodo.369655610.1109/jsac.2016.2545384 engineering and technology electrical engineering, electronic engineering, information engineering networking & telecommunications
36 dedup_wf_001::e3f892db413a689e572dd256acad55fe 10.1038/ng.366710.1038/ng.3667.10.17615/tct6-4m2610.17863/cam.15649 medical and health sciences health sciences genetics & heredity
37 dedup_wf_001::14ba594e8fd081847bc3f50f56335003 10.1016/j.jclepro.2019.119065 engineering and technology other engineering and technologies building & construction
38 dedup_wf_001::08ac7b33a41bcea2d055ecd8585d632e 10.1111/pce.13392 agricultural and veterinary sciences agriculture, forestry, and fisheries agronomy & agriculture

View File

@ -91,8 +91,8 @@ public class ReadBlacklistFromDB implements Closeable {
String encoding = rs.getString("relationship");
RelationInverse ri = ModelSupport.relationInverseMap.get(encoding);
direct.setRelClass(ri.getRelation());
inverse.setRelClass(ri.getInverse());
direct.setRelClass(ri.getRelClass());
inverse.setRelClass(ri.getInverseRelClass());
direct.setRelType(ri.getRelType());
inverse.setRelType(ri.getRelType());
direct.setSubRelType(ri.getSubReltype());

View File

@ -0,0 +1,154 @@
package eu.dnetlib.dhp.oa.dedup;
import java.io.IOException;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.MapFunction;
import org.apache.spark.api.java.function.PairFunction;
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.dom4j.DocumentException;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.xml.sax.SAXException;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Relation;
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
import eu.dnetlib.pace.config.DedupConfig;
import eu.dnetlib.pace.model.MapDocument;
import eu.dnetlib.pace.util.MapDocumentUtil;
import scala.Tuple2;
public class SparkWhitelistSimRels extends AbstractSparkAction {
private static final Logger log = LoggerFactory.getLogger(SparkCreateSimRels.class);
private static final String WHITELIST_SEPARATOR = "####";
public SparkWhitelistSimRels(ArgumentApplicationParser parser, SparkSession spark) {
super(parser, spark);
}
public static void main(String[] args) throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
SparkCreateSimRels.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/dedup/whitelistSimRels_parameters.json")));
parser.parseArgument(args);
SparkConf conf = new SparkConf();
new SparkWhitelistSimRels(parser, getSparkSession(conf))
.run(ISLookupClientFactory.getLookUpService(parser.get("isLookUpUrl")));
}
@Override
public void run(ISLookUpService isLookUpService)
throws DocumentException, IOException, ISLookUpException, SAXException {
// read oozie parameters
final String graphBasePath = parser.get("graphBasePath");
final String isLookUpUrl = parser.get("isLookUpUrl");
final String actionSetId = parser.get("actionSetId");
final String workingPath = parser.get("workingPath");
final int numPartitions = Optional
.ofNullable(parser.get("numPartitions"))
.map(Integer::valueOf)
.orElse(NUM_PARTITIONS);
final String whiteListPath = parser.get("whiteListPath");
log.info("numPartitions: '{}'", numPartitions);
log.info("graphBasePath: '{}'", graphBasePath);
log.info("isLookUpUrl: '{}'", isLookUpUrl);
log.info("actionSetId: '{}'", actionSetId);
log.info("workingPath: '{}'", workingPath);
log.info("whiteListPath: '{}'", whiteListPath);
JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
// file format: source####target
Dataset<Tuple2<String, String>> whiteListRels = spark
.createDataset(
sc
.textFile(whiteListPath)
// check if the line is in the correct format: id1####id2
.filter(s -> s.contains(WHITELIST_SEPARATOR) && s.split(WHITELIST_SEPARATOR).length == 2)
.map(s -> new Tuple2<>(s.split(WHITELIST_SEPARATOR)[0], s.split(WHITELIST_SEPARATOR)[1]))
.rdd(),
Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
// for each dedup configuration
for (DedupConfig dedupConf : getConfigurations(isLookUpService, actionSetId)) {
final String entity = dedupConf.getWf().getEntityType();
final String subEntity = dedupConf.getWf().getSubEntityValue();
log.info("Adding whitelist simrels for: '{}'", subEntity);
final String outputPath = DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity);
Dataset<Tuple2<String, String>> entities = spark
.createDataset(
sc
.textFile(DedupUtility.createEntityPath(graphBasePath, subEntity))
.repartition(numPartitions)
.mapToPair(
(PairFunction<String, String, String>) s -> {
MapDocument d = MapDocumentUtil.asMapDocumentWithJPath(dedupConf, s);
return new Tuple2<>(d.getIdentifier(), "present");
})
.rdd(),
Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
Dataset<Tuple2<String, String>> whiteListRels1 = whiteListRels
.joinWith(entities, whiteListRels.col("_1").equalTo(entities.col("_1")), "inner")
.map(
(MapFunction<Tuple2<Tuple2<String, String>, Tuple2<String, String>>, Tuple2<String, String>>) Tuple2::_1,
Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
Dataset<Tuple2<String, String>> whiteListRels2 = whiteListRels1
.joinWith(entities, whiteListRels1.col("_2").equalTo(entities.col("_1")), "inner")
.map(
(MapFunction<Tuple2<Tuple2<String, String>, Tuple2<String, String>>, Tuple2<String, String>>) Tuple2::_1,
Encoders.tuple(Encoders.STRING(), Encoders.STRING()));
Dataset<Relation> whiteListSimRels = whiteListRels2
.map(
(MapFunction<Tuple2<String, String>, Relation>) r -> createSimRel(r._1(), r._2(), entity),
Encoders.bean(Relation.class));
saveParquet(whiteListSimRels, outputPath, SaveMode.Append);
}
}
private Relation createSimRel(String source, String target, String entity) {
final Relation r = new Relation();
r.setSource(source);
r.setTarget(target);
r.setSubRelType("dedupSimilarity");
r.setRelClass("isSimilarTo");
r.setDataInfo(new DataInfo());
switch (entity) {
case "result":
r.setRelType("resultResult");
break;
case "organization":
r.setRelType("organizationOrganization");
break;
default:
throw new IllegalArgumentException("unmanaged entity type: " + entity);
}
return r;
}
}

View File

@ -0,0 +1,117 @@
package eu.dnetlib.dhp.oa.dedup;
import java.util.concurrent.TimeUnit;
import org.apache.commons.io.IOUtils;
import org.apache.http.client.methods.CloseableHttpResponse;
import org.apache.http.client.methods.HttpGet;
import org.apache.http.impl.client.CloseableHttpClient;
import org.apache.http.impl.client.HttpClients;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
public class UpdateOpenorgsJob {
private static final Logger log = LoggerFactory.getLogger(UpdateOpenorgsJob.class);
public static void main(String[] args) throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
SparkCreateSimRels.class
.getResourceAsStream("/eu/dnetlib/dhp/oa/dedup/updateOpenorgsJob_parameters.json")));
parser.parseArgument(args);
final String apiUrl = parser.get("apiUrl");
final int delay = Integer.parseInt(parser.get("delay"));
log.info("apiUrl: '{}'", apiUrl);
log.info("delay: '{}'", delay);
APIResponse res = httpCall(apiUrl);
while (res != null && res.getStatus().equals(ImportStatus.RUNNING)) {
TimeUnit.MINUTES.sleep(delay);
res = httpCall(apiUrl + "/status");
}
if (res == null) {
log.error("Openorgs Update FAILED: No response");
throw new RuntimeException("Openorgs Update FAILED: No response");
}
if (res.getStatus() == null || !res.getStatus().equals(ImportStatus.SUCCESS)) {
log.error("Openorgs Update FAILED: '{}' - '{}'", res.getStatus(), res.getMessage());
throw new RuntimeException(res.getMessage());
}
}
private static APIResponse httpCall(final String url) throws Exception {
final HttpGet req = new HttpGet(url);
try (final CloseableHttpClient client = HttpClients.createDefault()) {
try (final CloseableHttpResponse response = client.execute(req)) {
final String s = IOUtils.toString(response.getEntity().getContent());
return (new ObjectMapper()).readValue(s, APIResponse.class);
}
}
}
}
class APIResponse {
private String id;
private Long dateStart;
private Long dateEnd;
private ImportStatus status;
private String message;
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public Long getDateStart() {
return dateStart;
}
public void setDateStart(Long dateStart) {
this.dateStart = dateStart;
}
public Long getDateEnd() {
return dateEnd;
}
public void setDateEnd(Long dateEnd) {
this.dateEnd = dateEnd;
}
public ImportStatus getStatus() {
return status;
}
public void setStatus(ImportStatus status) {
this.status = status;
}
public String getMessage() {
return message;
}
public void setMessage(String message) {
this.message = message;
}
}
enum ImportStatus {
SUCCESS, FAILED, RUNNING, NOT_LAUNCHED, NOT_YET_STARTED
}

View File

@ -28,6 +28,11 @@
<name>dbPwd</name>
<description>password to access the OpenOrgs database</description>
</property>
<property>
<name>dbConnections</name>
<value>10</value>
<description>number of connections to the postgres db</description>
</property>
<property>
<name>workingPath</name>
<description>path for the working directory</description>
@ -223,7 +228,7 @@
<arg>--dbTable</arg><arg>${dbTable}</arg>
<arg>--dbUser</arg><arg>${dbUser}</arg>
<arg>--dbPwd</arg><arg>${dbPwd}</arg>
<arg>--numConnections</arg><arg>20</arg>
<arg>--numConnections</arg><arg>${dbConnections}</arg>
</spark>
<ok to="PrepareNewOrgs"/>
<error to="Kill"/>
@ -254,19 +259,24 @@
<arg>--dbTable</arg><arg>${dbTable}</arg>
<arg>--dbUser</arg><arg>${dbUser}</arg>
<arg>--dbPwd</arg><arg>${dbPwd}</arg>
<arg>--numConnections</arg><arg>20</arg>
<arg>--numConnections</arg><arg>${dbConnections}</arg>
</spark>
<ok to="update_openorgs"/>
<error to="Kill"/>
</action>
<action name="update_openorgs">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<exec>/usr/bin/curl</exec>
<argument>${apiUrl}</argument>
</shell>
<java>
<configuration>
<property>
<name>oozie.launcher.mapreduce.user.classpath.first</name>
<value>true</value>
</property>
</configuration>
<main-class>eu.dnetlib.dhp.oa.dedup.UpdateOpenorgsJob</main-class>
<arg>--apiUrl</arg><arg>${apiUrl}</arg>
<arg>--delay</arg><arg>5</arg>
</java>
<ok to="End"/>
<error to="Kill"/>
</action>

View File

@ -20,6 +20,10 @@
<name>workingPath</name>
<description>path for the working directory</description>
</property>
<property>
<name>whiteListPath</name>
<description>path for the whitelist of similarity relations</description>
</property>
<property>
<name>dedupGraphPath</name>
<description>path for the output graph</description>
@ -130,6 +134,34 @@
<arg>--workingPath</arg><arg>${workingPath}</arg>
<arg>--numPartitions</arg><arg>8000</arg>
</spark>
<ok to="WhitelistSimRels"/>
<error to="Kill"/>
</action>
<action name="WhitelistSimRels">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Add Whitelist Similarity Relations</name>
<class>eu.dnetlib.dhp.oa.dedup.SparkWhitelistSimRels</class>
<jar>dhp-dedup-openaire-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--graphBasePath</arg><arg>${graphBasePath}</arg>
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
<arg>--actionSetId</arg><arg>${actionSetId}</arg>
<arg>--workingPath</arg><arg>${workingPath}</arg>
<arg>--whiteListPath</arg><arg>${whiteListPath}</arg>
<arg>--numPartitions</arg><arg>8000</arg>
</spark>
<ok to="CreateMergeRel"/>
<error to="Kill"/>
</action>

View File

@ -0,0 +1,14 @@
[
{
"paramName": "api",
"paramLongName": "apiUrl",
"paramDescription": "the url of the API",
"paramRequired": true
},
{
"paramName": "d",
"paramLongName": "delay",
"paramDescription": "delay for the HTTP call in minutes",
"paramRequired": true
}
]

View File

@ -0,0 +1,38 @@
[
{
"paramName": "la",
"paramLongName": "isLookUpUrl",
"paramDescription": "address for the LookUp",
"paramRequired": true
},
{
"paramName": "asi",
"paramLongName": "actionSetId",
"paramDescription": "action set identifier (name of the orchestrator)",
"paramRequired": true
},
{
"paramName": "i",
"paramLongName": "graphBasePath",
"paramDescription": "the base path of the raw graph",
"paramRequired": true
},
{
"paramName": "w",
"paramLongName": "workingPath",
"paramDescription": "path of the working directory",
"paramRequired": true
},
{
"paramName": "np",
"paramLongName": "numPartitions",
"paramDescription": "number of partitions for the similarity relations intermediate phases",
"paramRequired": false
},
{
"paramName": "wl",
"paramLongName": "whiteListPath",
"paramDescription": "whitelist file path for the addition of custom simrels",
"paramRequired": true
}
]

View File

@ -5,13 +5,16 @@ import static java.nio.file.Files.createTempDirectory;
import static org.apache.spark.sql.functions.count;
import static org.junit.jupiter.api.Assertions.assertEquals;
import static org.junit.jupiter.api.Assertions.assertTrue;
import static org.mockito.Mockito.lenient;
import java.io.File;
import java.io.FileReader;
import java.io.IOException;
import java.io.Serializable;
import java.net.URISyntaxException;
import java.nio.file.Paths;
import java.util.List;
import org.apache.commons.io.FileUtils;
import org.apache.commons.io.IOUtils;
@ -55,6 +58,10 @@ public class SparkDedupTest implements Serializable {
private static String testOutputBasePath;
private static String testDedupGraphBasePath;
private static final String testActionSetId = "test-orchestrator";
private static String whitelistPath;
private static List<String> whiteList;
private static String WHITELIST_SEPARATOR = "####";
@BeforeAll
public static void cleanUp() throws IOException, URISyntaxException {
@ -71,6 +78,12 @@ public class SparkDedupTest implements Serializable {
.toAbsolutePath()
.toString();
whitelistPath = Paths
.get(SparkDedupTest.class.getResource("/eu/dnetlib/dhp/dedup/whitelist.simrels.txt").toURI())
.toFile()
.getAbsolutePath();
whiteList = IOUtils.readLines(new FileReader(whitelistPath));
FileUtils.deleteDirectory(new File(testOutputBasePath));
FileUtils.deleteDirectory(new File(testDedupGraphBasePath));
@ -202,6 +215,84 @@ public class SparkDedupTest implements Serializable {
@Test
@Order(2)
void whitelistSimRelsTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
IOUtils
.toString(
SparkWhitelistSimRels.class
.getResourceAsStream(
"/eu/dnetlib/dhp/oa/dedup/whitelistSimRels_parameters.json")));
parser
.parseArgument(
new String[] {
"-i", testGraphBasePath,
"-asi", testActionSetId,
"-la", "lookupurl",
"-w", testOutputBasePath,
"-np", "50",
"-wl", whitelistPath
});
new SparkWhitelistSimRels(parser, spark).run(isLookUpService);
long orgs_simrel = spark
.read()
.load(DedupUtility.createSimRelPath(testOutputBasePath, testActionSetId, "organization"))
.count();
long pubs_simrel = spark
.read()
.load(DedupUtility.createSimRelPath(testOutputBasePath, testActionSetId, "publication"))
.count();
long ds_simrel = spark
.read()
.load(DedupUtility.createSimRelPath(testOutputBasePath, testActionSetId, "dataset"))
.count();
long orp_simrel = spark
.read()
.load(DedupUtility.createSimRelPath(testOutputBasePath, testActionSetId, "otherresearchproduct"))
.count();
// entities simrels supposed to be equal to the number of previous step (no rels in whitelist)
assertEquals(3082, orgs_simrel);
assertEquals(7036, pubs_simrel);
assertEquals(442, ds_simrel);
assertEquals(6750, orp_simrel);
// entities simrels to be different from the number of previous step (new simrels in the whitelist)
Dataset<Row> sw_simrel = spark
.read()
.load(DedupUtility.createSimRelPath(testOutputBasePath, testActionSetId, "software"));
// check if the first relation in the whitelist exists
assertTrue(
sw_simrel
.as(Encoders.bean(Relation.class))
.toJavaRDD()
.filter(
rel -> rel.getSource().equalsIgnoreCase(whiteList.get(0).split(WHITELIST_SEPARATOR)[0])
&& rel.getTarget().equalsIgnoreCase(whiteList.get(0).split(WHITELIST_SEPARATOR)[1]))
.count() > 0);
// check if the second relation in the whitelist exists
assertTrue(
sw_simrel
.as(Encoders.bean(Relation.class))
.toJavaRDD()
.filter(
rel -> rel.getSource().equalsIgnoreCase(whiteList.get(1).split(WHITELIST_SEPARATOR)[0])
&& rel.getTarget().equalsIgnoreCase(whiteList.get(1).split(WHITELIST_SEPARATOR)[1]))
.count() > 0);
assertEquals(338, sw_simrel.count());
}
@Test
@Order(3)
void cutMergeRelsTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
@ -297,7 +388,7 @@ public class SparkDedupTest implements Serializable {
}
@Test
@Order(3)
@Order(4)
void createMergeRelsTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
@ -353,7 +444,7 @@ public class SparkDedupTest implements Serializable {
}
@Test
@Order(4)
@Order(5)
void createDedupRecordTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
@ -394,13 +485,13 @@ public class SparkDedupTest implements Serializable {
assertEquals(85, orgs_deduprecord);
assertEquals(65, pubs_deduprecord);
assertEquals(51, sw_deduprecord);
assertEquals(49, sw_deduprecord);
assertEquals(97, ds_deduprecord);
assertEquals(89, orp_deduprecord);
}
@Test
@Order(5)
@Order(6)
void updateEntityTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
@ -479,7 +570,7 @@ public class SparkDedupTest implements Serializable {
assertEquals(838, organizations);
assertEquals(100, projects);
assertEquals(100, datasource);
assertEquals(200, softwares);
assertEquals(198, softwares);
assertEquals(389, dataset);
assertEquals(517, otherresearchproduct);
@ -516,7 +607,7 @@ public class SparkDedupTest implements Serializable {
}
@Test
@Order(6)
@Order(7)
void propagateRelationTest() throws Exception {
ArgumentApplicationParser parser = new ArgumentApplicationParser(
@ -566,7 +657,7 @@ public class SparkDedupTest implements Serializable {
}
@Test
@Order(7)
@Order(8)
void testRelations() throws Exception {
testUniqueness("/eu/dnetlib/dhp/dedup/test/relation_1.json", 12, 10);
testUniqueness("/eu/dnetlib/dhp/dedup/test/relation_2.json", 10, 2);

View File

@ -0,0 +1,2 @@
50|r37b0ad08687::f645b9729d1e1025a72c57883f0f2cac####50|r37b0ad08687::4c55b436743b5c49fa32cd582fd9e1aa
50|datacite____::a90f49f9fde5393c00633bea6e4e374a####50|datacite____::5f55cdee77303ba8a2bf9996c32a330c

View File

@ -13,10 +13,30 @@ import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
import org.json4s.DefaultFormats
import org.json4s.JsonAST.{JField, JObject, JString,JArray}
import org.json4s.jackson.JsonMethods.parse
object SparkGenerateDoiBoost {
def extractIdGRID(input:String):List[(String,String)] = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: org.json4s.JValue = parse(input)
val id:String = (json \ "id").extract[String]
val grids:List[String] = for {
JObject(pid) <- json \ "pid"
JField("qualifier", JObject(qualifier)) <- pid
JField("classid", JString(classid)) <-qualifier
JField("value", JString(vl)) <- pid
if classid == "GRID"
} yield vl
grids.map(g => (id, s"unresolved::grid::${g.toLowerCase}"))(collection.breakOut)
}
def main(args: Array[String]): Unit = {
@ -36,6 +56,7 @@ object SparkGenerateDoiBoost {
val hostedByMapPath = parser.get("hostedByMapPath")
val workingDirPath = parser.get("workingPath")
val openaireOrganizationPath = parser.get("openaireOrganizationPath")
val crossrefAggregator = new Aggregator[(String, Publication), Publication, Publication] with Serializable {
override def zero: Publication = new Publication
@ -156,7 +177,7 @@ object SparkGenerateDoiBoost {
magPubs.joinWith(a,magPubs("_1").equalTo(a("PaperId"))).flatMap(item => {
val pub:Publication = item._1._2
val affiliation = item._2
val affId:String = if (affiliation.GridId.isDefined) DoiBoostMappingUtil.generateGridAffiliationId(affiliation.GridId.get) else DoiBoostMappingUtil.generateMAGAffiliationId(affiliation.AffiliationId.toString)
val affId:String = if (affiliation.GridId.isDefined) s"unresolved::grid::${affiliation.GridId.get.toLowerCase}" else DoiBoostMappingUtil.generateMAGAffiliationId(affiliation.AffiliationId.toString)
val r:Relation = new Relation
r.setSource(pub.getId)
r.setTarget(affId)
@ -174,9 +195,35 @@ object SparkGenerateDoiBoost {
r1.setDataInfo(pub.getDataInfo)
r1.setCollectedfrom(List(DoiBoostMappingUtil.createMAGCollectedFrom()).asJava)
List(r, r1)
})(mapEncoderRel).write.mode(SaveMode.Overwrite).save(s"$workingDirPath/doiBoostPublicationAffiliation")
})(mapEncoderRel).write.mode(SaveMode.Overwrite).save(s"$workingDirPath/doiBoostPublicationAffiliation_unresolved")
val unresolvedRels:Dataset[(String, Relation)] = spark.read.load(s"$workingDirPath/doiBoostPublicationAffiliation_unresolved").as[Relation].map(r => {
if (r.getSource.startsWith("unresolved"))
(r.getSource, r)
else if (r.getTarget.startsWith("unresolved"))
(r.getTarget,r)
else
("resolved", r)
})(Encoders.tuple(Encoders.STRING, mapEncoderRel))
val openaireOrganization:Dataset[(String,String)] = spark.read.text(openaireOrganizationPath).as[String].flatMap(s => extractIdGRID(s)).groupByKey(_._2).reduceGroups((x,y) => if (x != null) x else y ).map(_._2)
unresolvedRels.joinWith(openaireOrganization,unresolvedRels("_1").equalTo(openaireOrganization("_2")))
.map { x =>
val currentRels = x._1._2
val currentOrgs = x._2
if (currentOrgs!= null)
if(currentRels.getSource.startsWith("unresolved"))
currentRels.setSource(currentOrgs._1)
else
currentRels.setTarget(currentOrgs._1)
currentRels
}.filter(r=> !r.getSource.startsWith("unresolved") && !r.getTarget.startsWith("unresolved")).write.mode(SaveMode.Overwrite).save(s"$workingDirPath/doiBoostPublicationAffiliation")
magPubs.joinWith(a,magPubs("_1").equalTo(a("PaperId"))).map( item => {
val affiliation = item._2
if (affiliation.GridId.isEmpty) {

View File

@ -70,7 +70,7 @@ case object Crossref2Oaf {
"reference-book" -> "0002 Book",
"monograph" -> "0002 Book",
"journal-article" -> "0001 Article",
"dissertation" -> "0006 Doctoral thesis",
"dissertation" -> "0044 Thesis",
"other" -> "0038 Other literature type",
"peer-review" -> "0015 Review",
"proceedings" -> "0004 Conference object",
@ -206,11 +206,16 @@ case object Crossref2Oaf {
else {
instance.setDateofacceptance(asField(createdDate.getValue))
}
val s: String = (json \ "URL").extract[String]
val links: List[String] = ((for {JString(url) <- json \ "link" \ "URL"} yield url) ::: List(s)).filter(p => p != null).distinct
if (links.nonEmpty) {
instance.setUrl(links.asJava)
val s: List[String] = List("https://doi.org/" + doi)
// val links: List[String] = ((for {JString(url) <- json \ "link" \ "URL"} yield url) ::: List(s)).filter(p => p != null && p.toLowerCase().contains(doi.toLowerCase())).distinct
// if (links.nonEmpty) {
// instance.setUrl(links.asJava)
// }
if(s.nonEmpty)
{
instance.setUrl(s.asJava)
}
result.setInstance(List(instance).asJava)
//IMPORTANT

View File

@ -111,26 +111,9 @@ object SparkProcessMAG {
.map(item => ConversionUtil.updatePubsWithConferenceInfo(item))
.write
.mode(SaveMode.Overwrite)
.save(s"$workingPath/merge_step_2_conference")
magPubs= spark.read.load(s"$workingPath/merge_step_2_conference").as[Publication]
.map(p => (ConversionUtil.extractMagIdentifier(p.getOriginalId.asScala), p)).as[(String, Publication)]
val paperUrlDataset = spark.read.load(s"$sourcePath/PaperUrls").as[MagPaperUrl].groupBy("PaperId").agg(collect_list(struct("sourceUrl")).as("instances")).as[MagUrl]
logger.info("Phase 5) enrich publication with URL and Instances")
magPubs.joinWith(paperUrlDataset, col("_1").equalTo(paperUrlDataset("PaperId")), "left")
.map { a: ((String, Publication), MagUrl) => ConversionUtil.addInstances((a._1._2, a._2)) }
.write.mode(SaveMode.Overwrite)
.save(s"$workingPath/merge_step_3")
// logger.info("Phase 6) Enrich Publication with description")
// val pa = spark.read.load(s"${parser.get("sourcePath")}/PaperAbstractsInvertedIndex").as[MagPaperAbstract]
// pa.map(ConversionUtil.transformPaperAbstract).write.mode(SaveMode.Overwrite).save(s"${parser.get("targetPath")}/PaperAbstract")
val paperAbstract = spark.read.load((s"$workingPath/PaperAbstract")).as[MagPaperAbstract]
@ -162,12 +145,14 @@ object SparkProcessMAG {
.write.mode(SaveMode.Overwrite)
.save(s"$workingPath/mag_publication")
val s:RDD[Publication] = spark.read.load(s"$workingPath/mag_publication").as[Publication]
.map(p=>Tuple2(p.getId, p)).rdd.reduceByKey((a:Publication, b:Publication) => ConversionUtil.mergePublication(a,b))
spark.read.load(s"$workingPath/mag_publication").as[Publication]
.filter(p => p.getId == null)
.groupByKey(p => p.getId)
.reduceGroups((a:Publication, b:Publication) => ConversionUtil.mergePublication(a,b))
.map(_._2)
.write.mode(SaveMode.Overwrite).save(s"$targetPath/magPublication")
spark.createDataset(s).as[Publication].write.mode(SaveMode.Overwrite).save(s"$targetPath/magPublication")
}
}

View File

@ -1,6 +1,7 @@
[
{"paramName": "m", "paramLongName":"master", "paramDescription": "the master name", "paramRequired": true},
{"paramName": "hb", "paramLongName":"hostedByMapPath", "paramDescription": "the hosted By Map Path", "paramRequired": true},
{"paramName": "oo", "paramLongName":"openaireOrganizationPath", "paramDescription": "the openaire Organization Path", "paramRequired": true},
{"paramName": "ap", "paramLongName":"affiliationPath", "paramDescription": "the Affliation Path", "paramRequired": true},
{"paramName": "pa", "paramLongName":"paperAffiliationPath", "paramDescription": "the paperAffiliation Path", "paramRequired": true},
{"paramName": "w", "paramLongName":"workingPath", "paramDescription": "the Working Path", "paramRequired": true}

View File

@ -107,7 +107,6 @@
<action name="ResetMagWorkingPath">
<fs>
<delete path="${inputPathMAG}/dataset"/>
<delete path="${inputPathMAG}/process"/>
</fs>
<ok to="ConvertMagToDataset"/>
<error to="Kill"/>

View File

@ -27,6 +27,12 @@
<name>hostedByMapPath</name>
<description>the hostedByMap Path</description>
</property>
<property>
<name>openaireOrganizationPath</name>
<description>the OpenAire Organizations Path</description>
</property>
<property>
<name>outputPath</name>
<description>the Path of the sequence file action set</description>
@ -42,7 +48,7 @@
<!-- MAG Parameters -->
<property>
<name>inputPathMAG</name>
<description>the MAG working path</description>
<description>the MAG input path</description>
</property>
@ -132,7 +138,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${inputPathMAG}/dataset</arg>
<arg>--workingPath</arg><arg>${inputPathMAG}/process_p</arg>
<arg>--workingPath</arg><arg>${workingPath}/MAG</arg>
<arg>--targetPath</arg><arg>${workingPath}</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>
@ -214,6 +220,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--hostedByMapPath</arg><arg>${hostedByMapPath}</arg>
<arg>--openaireOrganizationPath</arg><arg>${openaireOrganizationPath}</arg>
<arg>--affiliationPath</arg><arg>${inputPathMAG}/dataset/Affiliations</arg>
<arg>--paperAffiliationPath</arg><arg>${inputPathMAG}/dataset/PaperAuthorAffiliations</arg>
<arg>--workingPath</arg><arg>${workingPath}</arg>

View File

@ -612,4 +612,26 @@ class CrossrefMappingTest {
}
@Test
def testMultipleURLs() :Unit = {
val json = Source.fromInputStream(getClass.getResourceAsStream("multiple_urls.json")).mkString
assertNotNull(json)
assertFalse(json.isEmpty);
val resultList: List[Oaf] = Crossref2Oaf.convert(json)
assertTrue(resultList.nonEmpty)
val item : Result = resultList.filter(p => p.isInstanceOf[Result]).head.asInstanceOf[Result]
assertEquals(1, item.getInstance().size())
assertEquals(1, item.getInstance().get(0).getUrl().size())
assertEquals("https://doi.org/10.1016/j.jas.2019.105013", item.getInstance().get(0).getUrl().get(0))
//println(mapper.writeValueAsString(item))
}
}

View File

@ -0,0 +1,614 @@
{
"indexed": {
"date-parts": [
[
2021,
10,
31
]
],
"date-time": "2021-10-31T15:48:01Z",
"timestamp": 1635695281393
},
"reference-count": 39,
"publisher": "Elsevier BV",
"license": [
{
"start": {
"date-parts": [
[
2019,
12,
1
]
],
"date-time": "2019-12-01T00:00:00Z",
"timestamp": 1575158400000
},
"content-version": "tdm",
"delay-in-days": 0,
"URL": "https://www.elsevier.com/tdm/userlicense/1.0/"
},
{
"start": {
"date-parts": [
[
2019,
9,
13
]
],
"date-time": "2019-09-13T00:00:00Z",
"timestamp": 1568332800000
},
"content-version": "vor",
"delay-in-days": 0,
"URL": "http://creativecommons.org/licenses/by/4.0/"
}
],
"funder": [
{
"DOI": "10.13039/100001182",
"name": "INSTAP",
"doi-asserted-by": "publisher"
},
{
"DOI": "10.13039/100014440",
"name": "Ministry of Science, Innovation and Universities",
"doi-asserted-by": "publisher",
"award": [
"RYC-2016-19637"
]
},
{
"DOI": "10.13039/100010661",
"name": "European Unions Horizon 2020",
"doi-asserted-by": "publisher",
"award": [
"746446"
]
}
],
"content-domain": {
"domain": [
"elsevier.com",
"sciencedirect.com"
],
"crossmark-restriction": true
},
"short-container-title": [
"Journal of Archaeological Science"
],
"published-print": {
"date-parts": [
[
2019,
12
]
]
},
"DOI": "10.1016/j.jas.2019.105013",
"type": "journal-article",
"created": {
"date-parts": [
[
2019,
9,
25
]
],
"date-time": "2019-09-25T20:05:08Z",
"timestamp": 1569441908000
},
"page": "105013",
"update-policy": "http://dx.doi.org/10.1016/elsevier_cm_policy",
"source": "Crossref",
"is-referenced-by-count": 21,
"title": [
"A brave new world for archaeological survey: Automated machine learning-based potsherd detection using high-resolution drone imagery"
],
"prefix": "10.1016",
"volume": "112",
"author": [
{
"given": "H.A.",
"family": "Orengo",
"sequence": "first",
"affiliation": [
]
},
{
"given": "A.",
"family": "Garcia-Molsosa",
"sequence": "additional",
"affiliation": [
]
}
],
"member": "78",
"reference": [
{
"key": "10.1016/j.jas.2019.105013_bib1",
"doi-asserted-by": "crossref",
"first-page": "85",
"DOI": "10.1080/17538947.2016.1250829",
"article-title": "Remote sensing heritage in a petabyte-scale: satellite data and heritage Earth Engine© applications",
"volume": "10",
"author": "Agapiou",
"year": "2017",
"journal-title": "Int. J. Digit. Earth"
},
{
"key": "10.1016/j.jas.2019.105013_bib2",
"series-title": "Extracting Meaning from Ploughsoil Assemblages",
"first-page": "1",
"article-title": "Extracting meaning from ploughsoil assemblages: assessments of the past, strategies for the future",
"author": "Alcock",
"year": "2000"
},
{
"key": "10.1016/j.jas.2019.105013_bib3",
"series-title": "Side-by-Side Survey. Comparative Regional Studies in the Mediterranean World",
"first-page": "1",
"article-title": "Introduction",
"author": "Alcock",
"year": "2004"
},
{
"key": "10.1016/j.jas.2019.105013_bib4",
"doi-asserted-by": "crossref",
"first-page": "93",
"DOI": "10.1111/j.1538-4632.1995.tb00338.x",
"article-title": "Local indicators of spatial association—LISA",
"volume": "27",
"author": "Anselin",
"year": "1995",
"journal-title": "Geogr. Anal."
},
{
"key": "10.1016/j.jas.2019.105013_bib5",
"series-title": "Archaeological Survey",
"author": "Banning",
"year": "2002"
},
{
"issue": "1/2",
"key": "10.1016/j.jas.2019.105013_bib6",
"doi-asserted-by": "crossref",
"first-page": "123",
"DOI": "10.2307/3181488",
"article-title": "GIS, archaeological survey and landscape archaeology on the island of Kythera, Greece",
"volume": "29",
"author": "Bevan",
"year": "2004",
"journal-title": "J. Field Archaeol."
},
{
"issue": "1",
"key": "10.1016/j.jas.2019.105013_bib8",
"doi-asserted-by": "crossref",
"first-page": "5",
"DOI": "10.1023/A:1010933404324",
"article-title": "Random forests",
"volume": "45",
"author": "Breiman",
"year": "2001",
"journal-title": "Mach. Learn."
},
{
"key": "10.1016/j.jas.2019.105013_bib9",
"series-title": "Sampling in Contemporary British Archaeology",
"author": "Cherry",
"year": "1978"
},
{
"issue": "3",
"key": "10.1016/j.jas.2019.105013_bib10",
"doi-asserted-by": "crossref",
"first-page": "273",
"DOI": "10.1016/0734-189X(84)90197-X",
"article-title": "Segmentation of a high-resolution urban scene using texture operators",
"volume": "25",
"author": "Conners",
"year": "1984",
"journal-title": "Comput. Vis. Graph Image Process"
},
{
"key": "10.1016/j.jas.2019.105013_bib11",
"first-page": "31",
"article-title": "Old land surfaces and modern ploughsoil: implications of recent work at Maxey, Cambridgeshire",
"volume": "2",
"author": "Crowther",
"year": "1983",
"journal-title": "Scott. Archaeol. Rev."
},
{
"key": "10.1016/j.jas.2019.105013_bib12",
"series-title": "Settlement Pattern Studies in the Americas: Fifty Years since Virú",
"first-page": "203",
"article-title": "Conclusions: the settlement pattern concept from an Americanist perspective",
"author": "Fish",
"year": "1999"
},
{
"key": "10.1016/j.jas.2019.105013_bib13",
"doi-asserted-by": "crossref",
"first-page": "21",
"DOI": "10.3390/geosciences9010021",
"article-title": "Remote sensing and historical morphodynamics of alluvial plains. The 1909 indus flood and the city of Dera Gazhi Khan (province of Punjab, Pakistan)",
"volume": "9",
"author": "Garcia",
"year": "2019",
"journal-title": "Geosciences"
},
{
"key": "10.1016/j.jas.2019.105013_bib14",
"unstructured": "Georgiadis, M.; Garcia-Molsosa, A.; Orengo, H.A.; Kefalidou, E. and Kallintzi, K. In Preparation. APAX Project 2015-2018: A Preliminary Report. (Hesperia)."
},
{
"key": "10.1016/j.jas.2019.105013_bib15",
"series-title": "Geographical Information Systems and Landscape Archaeology",
"first-page": "35",
"article-title": "Regional survey and GIS: the boeotia project",
"author": "Gillings",
"year": "1999"
},
{
"key": "10.1016/j.jas.2019.105013_bib16",
"doi-asserted-by": "crossref",
"first-page": "18",
"DOI": "10.1016/j.rse.2017.06.031",
"article-title": "Google Earth engine: planetary-scale geospatial analysis for everyone",
"volume": "202",
"author": "Gorelick",
"year": "2017",
"journal-title": "Remote Sens. Environ."
},
{
"issue": "107",
"key": "10.1016/j.jas.2019.105013_bib17",
"doi-asserted-by": "crossref",
"first-page": "177",
"DOI": "10.1111/j.0031-868X.2004.00278.x",
"article-title": "Photogrammetric reconstruction of the great buddha of Bamiyan, Afghanistan",
"volume": "19",
"author": "Grün",
"year": "2004",
"journal-title": "Photogramm. Rec."
},
{
"issue": "6",
"key": "10.1016/j.jas.2019.105013_bib18",
"doi-asserted-by": "crossref",
"first-page": "610",
"DOI": "10.1109/TSMC.1973.4309314",
"article-title": "Textural features for image classification",
"author": "Haralick",
"year": "1973",
"journal-title": "IEEE Trans. Syst., Man, Cybernet., SMC-3"
},
{
"key": "10.1016/j.jas.2019.105013_bib19",
"doi-asserted-by": "crossref",
"first-page": "76",
"DOI": "10.1558/jmea.v14i1.76",
"article-title": "Excavating to excess? Implications of the last decade of archaeology in Israel",
"volume": "14",
"author": "Kletter",
"year": "2001",
"journal-title": "J. Mediterr. Archaeol."
},
{
"key": "10.1016/j.jas.2019.105013_bib20",
"first-page": "299",
"article-title": "Testing Google Earth Engine for the automatic identification and vectorization of archaeological features: a case study from Faynan, Jordan",
"volume": "15",
"author": "Liss",
"year": "2017",
"journal-title": "J. Archaeol. Sci.: Report"
},
{
"key": "10.1016/j.jas.2019.105013_bib21",
"series-title": "Geographical Information Systems and Landscape Archaeology",
"first-page": "55",
"article-title": "Towards a methodology for modelling surface survey data: the sangro valley project",
"author": "Lock",
"year": "1999"
},
{
"key": "10.1016/j.jas.2019.105013_bib22",
"series-title": "Extracting Meaning from Ploughsoil Assemblages",
"first-page": "5",
"article-title": "Methods of collection recording and quantification",
"author": "Mattingly",
"year": "2000"
},
{
"issue": "14",
"key": "10.1016/j.jas.2019.105013_bib23",
"doi-asserted-by": "crossref",
"first-page": "E778",
"DOI": "10.1073/pnas.1115472109",
"article-title": "Mapping patterns of long-term settlement in Northern Mesopotamia at a large scale",
"volume": "109",
"author": "Menze",
"year": "2012",
"journal-title": "Proc. Natl. Acad. Sci."
},
{
"key": "10.1016/j.jas.2019.105013_bib24",
"doi-asserted-by": "crossref",
"first-page": "80",
"DOI": "10.1016/j.jas.2015.04.002",
"article-title": "A supervised machine-learning approach towards geochemical predictive modelling in archaeology",
"volume": "59",
"author": "Oonk",
"year": "2015",
"journal-title": "J. Archaeol. Sci."
},
{
"key": "10.1016/j.jas.2019.105013_bib25",
"doi-asserted-by": "crossref",
"first-page": "49",
"DOI": "10.1016/j.isprsjprs.2012.07.005",
"article-title": "Combining terrestrial stereophotogrammetry, DGPS and GIS-based 3D voxel modelling in the volumetric recording of archaeological features",
"volume": "76",
"author": "Orengo",
"year": "2013",
"journal-title": "ISPRS J. Photogrammetry Remote Sens."
},
{
"key": "10.1016/j.jas.2019.105013_bib26",
"doi-asserted-by": "crossref",
"first-page": "100",
"DOI": "10.1016/j.jas.2015.10.008",
"article-title": "Photogrammetric re-discovery of the Eastern Thessalian hidden long-term landscapes",
"volume": "64",
"author": "Orengo",
"year": "2015",
"journal-title": "J. Archaeol. Sci."
},
{
"issue": "3",
"key": "10.1016/j.jas.2019.105013_bib27",
"doi-asserted-by": "crossref",
"first-page": "479",
"DOI": "10.3764/aja.122.3.0479",
"article-title": "Towards a definition of Minoan agro-pastoral landscapes: results of the survey at Palaikastro (Crete)",
"volume": "122",
"author": "Orengo",
"year": "2018",
"journal-title": "Am. J. Archaeol."
},
{
"issue": "7",
"key": "10.1016/j.jas.2019.105013_bib28",
"doi-asserted-by": "crossref",
"first-page": "735",
"DOI": "10.3390/rs9070735",
"article-title": "Large-scale, multi-temporal remote sensing of palaeo-river networks: a case study from Northwest India and its implications for the Indus civilisation",
"volume": "9",
"author": "Orengo",
"year": "2017",
"journal-title": "Remote Sens."
},
{
"key": "10.1016/j.jas.2019.105013_bib29",
"doi-asserted-by": "crossref",
"first-page": "1361",
"DOI": "10.1002/esp.4317",
"article-title": "Multi-scale relief model (MSRM): a new algorithm for the visualization of subtle topographic change of variable size in digital elevation models",
"volume": "43",
"author": "Orengo",
"year": "2018",
"journal-title": "Earth Surf. Process. Landforms"
},
{
"key": "10.1016/j.jas.2019.105013_bib30",
"series-title": "Submitted to Proceedings of the National Academy of Sciences",
"article-title": "Living on the edge of the desert: automated detection of archaeological mounds in Cholistan (Pakistan) using machine learning classification of multi-sensor multi-temporal satellite data",
"author": "Orengo",
"year": "2019"
},
{
"key": "10.1016/j.jas.2019.105013_bib31",
"first-page": "154",
"article-title": "How many trees in a random forest?",
"volume": "vol. 7376",
"author": "Oshiro",
"year": "2012"
},
{
"key": "10.1016/j.jas.2019.105013_bib32",
"article-title": "Decision-making in modern surveys",
"volume": "ume 1",
"author": "Plog",
"year": "1978"
},
{
"issue": "4",
"key": "10.1016/j.jas.2019.105013_bib33",
"doi-asserted-by": "crossref",
"first-page": "100",
"DOI": "10.3390/geosciences7040100",
"article-title": "From above and on the ground: geospatial methods for recording endangered archaeology in the Middle East and north africa",
"volume": "7",
"author": "Rayne",
"year": "2017",
"journal-title": "Geosciences"
},
{
"issue": "1",
"key": "10.1016/j.jas.2019.105013_bib34",
"doi-asserted-by": "crossref",
"first-page": "1",
"DOI": "10.1080/00438243.1978.9979712",
"article-title": "The design of archaeological surveys",
"volume": "10",
"author": "Schiffer",
"year": "1978",
"journal-title": "World Archaeol."
},
{
"key": "10.1016/j.jas.2019.105013_bib35",
"series-title": "Experiments in the Collection and Analysis of Archaeological Survey Data: the East Hampshire Survey",
"author": "Shennan",
"year": "1985"
},
{
"key": "10.1016/j.jas.2019.105013_bib36",
"doi-asserted-by": "crossref",
"first-page": "1066",
"DOI": "10.1016/j.culher.2016.06.006",
"article-title": "Drones over Mediterranean landscapes. The potential of small UAV's (drones) for site detection and heritage management in archaeological survey projects: a case study from Le Pianelle in the Tappino Valley, Molise (Italy)",
"volume": "22",
"author": "Stek",
"year": "2016",
"journal-title": "J. Cult. Herit."
},
{
"key": "10.1016/j.jas.2019.105013_bib37",
"series-title": "Side-by-Side Survey. Comparative Regional Studies in the Mediterranean World",
"first-page": "65",
"article-title": "Side-by-side and back to front: exploring intra-regional latitudinal and longitudinal comparability in survey data. Three case studies from Metaponto, southern Italy",
"author": "Thomson",
"year": "2004"
},
{
"key": "10.1016/j.jas.2019.105013_bib38",
"series-title": "Digital Discovery. Exploring New Frontiers in Human Heritage. Computer Applications and Quantitative Methods in Archaeology",
"article-title": "Computer vision and machine learning for archaeology",
"author": "van der Maaten",
"year": "2007"
},
{
"key": "10.1016/j.jas.2019.105013_bib39",
"doi-asserted-by": "crossref",
"first-page": "1114",
"DOI": "10.1111/j.1475-4754.2012.00667.x",
"article-title": "Computer vision-based orthophoto mapping of complex archaeological sites: the ancient quarry of Pitaranha (Portugal-Spain)",
"volume": "54",
"author": "Verhoeven",
"year": "2012",
"journal-title": "Archaeometry"
},
{
"key": "10.1016/j.jas.2019.105013_bib40",
"series-title": "A Guide for Salvage Archeology",
"author": "Wendorf",
"year": "1962"
}
],
"container-title": [
"Journal of Archaeological Science"
],
"original-title": [
],
"language": "en",
"link": [
{
"URL": "https://api.elsevier.com/content/article/PII:S0305440319301001?httpAccept=text/xml",
"content-type": "text/xml",
"content-version": "vor",
"intended-application": "text-mining"
},
{
"URL": "https://api.elsevier.com/content/article/PII:S0305440319301001?httpAccept=text/plain",
"content-type": "text/plain",
"content-version": "vor",
"intended-application": "text-mining"
}
],
"deposited": {
"date-parts": [
[
2019,
11,
25
]
],
"date-time": "2019-11-25T06:46:34Z",
"timestamp": 1574664394000
},
"score": 1,
"subtitle": [
],
"short-title": [
],
"issued": {
"date-parts": [
[
2019,
12
]
]
},
"references-count": 39,
"alternative-id": [
"S0305440319301001"
],
"URL": "http://dx.doi.org/10.1016/j.jas.2019.105013",
"relation": {
},
"ISSN": [
"0305-4403"
],
"issn-type": [
{
"value": "0305-4403",
"type": "print"
}
],
"subject": [
"Archaeology",
"Archaeology"
],
"published": {
"date-parts": [
[
2019,
12
]
]
},
"assertion": [
{
"value": "Elsevier",
"name": "publisher",
"label": "This article is maintained by"
},
{
"value": "A brave new world for archaeological survey: Automated machine learning-based potsherd detection using high-resolution drone imagery",
"name": "articletitle",
"label": "Article Title"
},
{
"value": "Journal of Archaeological Science",
"name": "journaltitle",
"label": "Journal Title"
},
{
"value": "https://doi.org/10.1016/j.jas.2019.105013",
"name": "articlelink",
"label": "CrossRef DOI link to publisher maintained version"
},
{
"value": "article",
"name": "content_type",
"label": "Content Type"
},
{
"value": "© 2019 The Authors. Published by Elsevier Ltd.",
"name": "copyright",
"label": "Copyright"
}
],
"article-number": "105013"
}

View File

@ -25,6 +25,24 @@ public class PropagationConstant {
private PropagationConstant() {
}
public static final String DOI = "doi";
public static final String REF_DOI = ".refs";
public static final String UPDATE_DATA_INFO_TYPE = "update";
public static final String UPDATE_SUBJECT_FOS_CLASS_ID = "subject:fos";
public static final String UPDATE_CLASS_NAME = "Inferred by OpenAIRE";
public static final String UPDATE_MEASURE_BIP_CLASS_ID = "measure:bip";
public static final String FOS_CLASS_ID = "FOS";
public static final String FOS_CLASS_NAME = "Fields of Science and Technology classification";
public static final String OPENCITATIONS_CLASSID = "sysimport:crosswalk:opencitations";
public static final String OPENCITATIONS_CLASSNAME = "Imported from OpenCitations";
public static final String ID_PREFIX = "50|doi_________::";
public static final String OC_TRUST = "0.91";
public final static String NULL = "NULL";
public static final String INSTITUTIONAL_REPO_TYPE = "pubsrepository::institutional";
public static final String PROPAGATION_DATA_INFO_TYPE = "propagation";
@ -75,10 +93,25 @@ public class PropagationConstant {
public static DataInfo getDataInfo(
String inference_provenance, String inference_class_id, String inference_class_name, String qualifierSchema) {
return getDataInfo(inference_provenance, inference_class_id, inference_class_name, qualifierSchema, "0.85");
}
public static DataInfo getDataInfo(
String inference_provenance, String inference_class_id, String inference_class_name, String qualifierSchema,
String trust) {
return getDataInfo(
inference_provenance, inference_class_id, inference_class_name, qualifierSchema, trust, true);
}
public static DataInfo getDataInfo(
String inference_provenance, String inference_class_id, String inference_class_name, String qualifierSchema,
String trust, boolean inferred) {
DataInfo di = new DataInfo();
di.setInferred(true);
di.setInferred(inferred);
di.setDeletedbyinference(false);
di.setTrust("0.85");
di.setTrust(trust);
di.setInferenceprovenance(inference_provenance);
di.setProvenanceaction(getQualifier(inference_class_id, inference_class_name, qualifierSchema));
return di;

View File

@ -5,37 +5,40 @@ import java.util.Map;
import com.google.common.collect.Maps;
import eu.dnetlib.dhp.schema.common.ModelConstants;
public class Constants {
public static final Map<String, String> accessRightsCoarMap = Maps.newHashMap();
public static final Map<String, String> coarCodeLabelMap = Maps.newHashMap();
protected static final Map<String, String> accessRightsCoarMap = Maps.newHashMap();
protected static final Map<String, String> coarCodeLabelMap = Maps.newHashMap();
public static final String INFERRED = "Inferred by OpenAIRE";
public static final String CABF2 = "c_abf2";
public static final String HARVESTED = "Harvested";
public static final String DEFAULT_TRUST = "0.9";
public static final String USER_CLAIM = "Linked by user";
public static String COAR_ACCESS_RIGHT_SCHEMA = "http://vocabularies.coar-repositories.org/documentation/access_rights/";
public static final String COAR_ACCESS_RIGHT_SCHEMA = "http://vocabularies.coar-repositories.org/documentation/access_rights/";
public static String ZENODO_COMMUNITY_PREFIX = "https://zenodo.org/communities/";
public static final String ZENODO_COMMUNITY_PREFIX = "https://zenodo.org/communities/";
public static String RESEARCH_COMMUNITY = "Research Community";
public static final String RESEARCH_COMMUNITY = "Research Community";
public static String RESEARCH_INFRASTRUCTURE = "Research Infrastructure/Initiative";
public static final String RESEARCH_INFRASTRUCTURE = "Research Infrastructure/Initiative";
static {
accessRightsCoarMap.put("OPEN", "c_abf2");
accessRightsCoarMap.put(ModelConstants.ACCESS_RIGHT_OPEN, CABF2);
accessRightsCoarMap.put("RESTRICTED", "c_16ec");
accessRightsCoarMap.put("OPEN SOURCE", "c_abf2");
accessRightsCoarMap.put("CLOSED", "c_14cb");
accessRightsCoarMap.put("EMBARGO", "c_f1cf");
accessRightsCoarMap.put("OPEN SOURCE", CABF2);
accessRightsCoarMap.put(ModelConstants.ACCESS_RIGHT_CLOSED, "c_14cb");
accessRightsCoarMap.put(ModelConstants.ACCESS_RIGHT_EMBARGO, "c_f1cf");
}
static {
coarCodeLabelMap.put("c_abf2", "OPEN");
coarCodeLabelMap.put(CABF2, ModelConstants.ACCESS_RIGHT_OPEN);
coarCodeLabelMap.put("c_16ec", "RESTRICTED");
coarCodeLabelMap.put("c_14cb", "CLOSED");
coarCodeLabelMap.put("c_14cb", ModelConstants.ACCESS_RIGHT_CLOSED);
coarCodeLabelMap.put("c_f1cf", "EMBARGO");
}

View File

@ -11,12 +11,14 @@ import java.util.Set;
import java.util.stream.Collectors;
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.Encoders;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import eu.dnetlib.dhp.oa.graph.dump.community.CommunityMap;
import eu.dnetlib.dhp.oa.graph.dump.exceptions.NoAvailableEntityTypeException;
import eu.dnetlib.dhp.schema.oaf.*;
/**
@ -37,7 +39,8 @@ public class DumpProducts implements Serializable {
isSparkSessionManaged,
spark -> {
Utils.removeOutputDir(spark, outputPath);
execDump(spark, inputPath, outputPath, communityMapPath, inputClazz, outputClazz, dumpType);
execDump(
spark, inputPath, outputPath, communityMapPath, inputClazz, outputClazz, dumpType);
});
}
@ -55,7 +58,7 @@ public class DumpProducts implements Serializable {
Utils
.readPath(spark, inputPath, inputClazz)
.map((MapFunction<I, O>) value -> execMap(value, communityMap, dumpType), Encoders.bean(outputClazz))
.filter(Objects::nonNull)
.filter((FilterFunction<O>) value -> value != null)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
@ -65,7 +68,7 @@ public class DumpProducts implements Serializable {
private static <I extends OafEntity, O extends eu.dnetlib.dhp.schema.dump.oaf.Result> O execMap(I value,
CommunityMap communityMap,
String dumpType) {
String dumpType) throws NoAvailableEntityTypeException {
Optional<DataInfo> odInfo = Optional.ofNullable(value.getDataInfo());
if (odInfo.isPresent()) {
@ -89,11 +92,11 @@ public class DumpProducts implements Serializable {
return c.getId();
}
if (c.getId().contains("::") && communities.contains(c.getId().substring(0, c.getId().indexOf("::")))) {
return c.getId().substring(0, 3);
return c.getId().substring(0, c.getId().indexOf("::"));
}
return null;
}).filter(Objects::nonNull).collect(Collectors.toList());
if (toDumpFor.size() == 0) {
if (toDumpFor.isEmpty()) {
return null;
}
}

View File

@ -57,16 +57,16 @@ public class MakeTar implements Serializable {
public static void makeTArArchive(FileSystem fileSystem, String inputPath, String outputPath, int gBperSplit)
throws IOException {
RemoteIterator<LocatedFileStatus> dir_iterator = fileSystem.listLocatedStatus(new Path(inputPath));
RemoteIterator<LocatedFileStatus> dirIterator = fileSystem.listLocatedStatus(new Path(inputPath));
while (dir_iterator.hasNext()) {
LocatedFileStatus fileStatus = dir_iterator.next();
while (dirIterator.hasNext()) {
LocatedFileStatus fileStatus = dirIterator.next();
Path p = fileStatus.getPath();
String p_string = p.toString();
String entity = p_string.substring(p_string.lastIndexOf("/") + 1);
String pathString = p.toString();
String entity = pathString.substring(pathString.lastIndexOf("/") + 1);
MakeTarArchive.tarMaxSize(fileSystem, p_string, outputPath + "/" + entity, entity, gBperSplit);
MakeTarArchive.tarMaxSize(fileSystem, pathString, outputPath + "/" + entity, entity, gBperSplit);
}
}

View File

@ -18,10 +18,10 @@ public class QueryInformationSystem {
private ISLookUpService isLookUp;
private static final String XQUERY = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType') "
private static final String XQUERY_ALL = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType') "
+
" where $x//CONFIGURATION/context[./@type='community' or ./@type='ri'] " +
" and ($x//context/param[./@name = 'status']/text() = 'manager' or $x//context/param[./@name = 'status']/text() = 'all') "
" and ($x//context/param[./@name = 'status']/text() = 'all') "
+
" return " +
"<community> " +
@ -29,9 +29,22 @@ public class QueryInformationSystem {
"{$x//CONFIGURATION/context/@label}" +
"</community>";
public CommunityMap getCommunityMap()
private static final String XQUERY_CI = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType') "
+
" where $x//CONFIGURATION/context[./@type='community' or ./@type='ri'] " +
" and $x//CONFIGURATION/context[./@id=%s] "
+
" return " +
"<community> " +
"{$x//CONFIGURATION/context/@id}" +
"{$x//CONFIGURATION/context/@label}" +
"</community>";
public CommunityMap getCommunityMap(boolean singleCommunity, String communityId)
throws ISLookUpException, DocumentException, SAXException {
return getMap(isLookUp.quickSearchProfile(XQUERY));
if (singleCommunity)
return getMap(isLookUp.quickSearchProfile(XQUERY_CI.replace("%s", "'" + communityId + "'")));
return getMap(isLookUp.quickSearchProfile(XQUERY_ALL));
}

View File

@ -7,21 +7,28 @@ import java.util.stream.Collectors;
import org.apache.commons.lang3.StringUtils;
import eu.dnetlib.dhp.oa.graph.dump.exceptions.NoAvailableEntityTypeException;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.dump.oaf.*;
import eu.dnetlib.dhp.schema.dump.oaf.AccessRight;
import eu.dnetlib.dhp.schema.dump.oaf.Author;
import eu.dnetlib.dhp.schema.dump.oaf.Country;
import eu.dnetlib.dhp.schema.dump.oaf.GeoLocation;
import eu.dnetlib.dhp.schema.dump.oaf.Instance;
import eu.dnetlib.dhp.schema.dump.oaf.KeyValue;
import eu.dnetlib.dhp.schema.dump.oaf.OpenAccessRoute;
import eu.dnetlib.dhp.schema.dump.oaf.Qualifier;
import eu.dnetlib.dhp.schema.dump.oaf.Result;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityInstance;
import eu.dnetlib.dhp.schema.dump.oaf.community.CommunityResult;
import eu.dnetlib.dhp.schema.dump.oaf.community.Context;
import eu.dnetlib.dhp.schema.dump.oaf.graph.GraphResult;
import eu.dnetlib.dhp.schema.oaf.DataInfo;
import eu.dnetlib.dhp.schema.oaf.Field;
import eu.dnetlib.dhp.schema.oaf.Journal;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.oaf.*;
public class ResultMapper implements Serializable {
public static <E extends eu.dnetlib.dhp.schema.oaf.OafEntity> Result map(
E in, Map<String, String> communityMap, String dumpType) {
E in, Map<String, String> communityMap, String dumpType) throws NoAvailableEntityTypeException {
Result out;
if (Constants.DUMPTYPE.COMPLETE.getType().equals(dumpType)) {
@ -33,101 +40,17 @@ public class ResultMapper implements Serializable {
eu.dnetlib.dhp.schema.oaf.Result input = (eu.dnetlib.dhp.schema.oaf.Result) in;
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> ort = Optional.ofNullable(input.getResulttype());
if (ort.isPresent()) {
switch (ort.get().getClassid()) {
case "publication":
Optional<Journal> journal = Optional
.ofNullable(((eu.dnetlib.dhp.schema.oaf.Publication) input).getJournal());
if (journal.isPresent()) {
Journal j = journal.get();
Container c = new Container();
c.setConferencedate(j.getConferencedate());
c.setConferenceplace(j.getConferenceplace());
c.setEdition(j.getEdition());
c.setEp(j.getEp());
c.setIss(j.getIss());
c.setIssnLinking(j.getIssnLinking());
c.setIssnOnline(j.getIssnOnline());
c.setIssnPrinted(j.getIssnPrinted());
c.setName(j.getName());
c.setSp(j.getSp());
c.setVol(j.getVol());
out.setContainer(c);
out.setType(ModelConstants.PUBLICATION_DEFAULT_RESULTTYPE.getClassname());
}
break;
case "dataset":
eu.dnetlib.dhp.schema.oaf.Dataset id = (eu.dnetlib.dhp.schema.oaf.Dataset) input;
Optional.ofNullable(id.getSize()).ifPresent(v -> out.setSize(v.getValue()));
Optional.ofNullable(id.getVersion()).ifPresent(v -> out.setVersion(v.getValue()));
try {
out
.setGeolocation(
Optional
.ofNullable(id.getGeolocation())
.map(
igl -> igl
.stream()
.filter(Objects::nonNull)
.map(gli -> {
GeoLocation gl = new GeoLocation();
gl.setBox(gli.getBox());
gl.setPlace(gli.getPlace());
gl.setPoint(gli.getPoint());
return gl;
})
.collect(Collectors.toList()))
.orElse(null));
out.setType(ModelConstants.DATASET_DEFAULT_RESULTTYPE.getClassname());
break;
case "software":
eu.dnetlib.dhp.schema.oaf.Software is = (eu.dnetlib.dhp.schema.oaf.Software) input;
Optional
.ofNullable(is.getCodeRepositoryUrl())
.ifPresent(value -> out.setCodeRepositoryUrl(value.getValue()));
Optional
.ofNullable(is.getDocumentationUrl())
.ifPresent(
value -> out
.setDocumentationUrl(
value
.stream()
.map(Field::getValue)
.collect(Collectors.toList())));
Optional
.ofNullable(is.getProgrammingLanguage())
.ifPresent(value -> out.setProgrammingLanguage(value.getClassid()));
out.setType(ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE.getClassname());
break;
case "other":
eu.dnetlib.dhp.schema.oaf.OtherResearchProduct ir = (eu.dnetlib.dhp.schema.oaf.OtherResearchProduct) input;
out
.setContactgroup(
Optional
.ofNullable(ir.getContactgroup())
.map(value -> value.stream().map(Field::getValue).collect(Collectors.toList()))
.orElse(null));
out
.setContactperson(
Optional
.ofNullable(ir.getContactperson())
.map(value -> value.stream().map(Field::getValue).collect(Collectors.toList()))
.orElse(null));
out
.setTool(
Optional
.ofNullable(ir.getTool())
.map(value -> value.stream().map(Field::getValue).collect(Collectors.toList()))
.orElse(null));
out.setType(ModelConstants.ORP_DEFAULT_RESULTTYPE.getClassname());
break;
addTypeSpecificInformation(out, input, ort);
Optional<List<Measure>> mes = Optional.ofNullable(input.getMeasures());
if (mes.isPresent()) {
List<KeyValue> measure = new ArrayList<>();
mes
.get()
.forEach(
m -> m.getUnit().forEach(u -> measure.add(KeyValue.newInstance(m.getId(), u.getValue()))));
out.setMeasures(measure);
}
Optional
@ -138,8 +61,7 @@ public class ResultMapper implements Serializable {
// I do not map Access Right UNKNOWN or OTHER
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> oar = Optional.ofNullable(input.getBestaccessright());
if (oar.isPresent()) {
if (Constants.accessRightsCoarMap.containsKey(oar.get().getClassid())) {
if (oar.isPresent() && Constants.accessRightsCoarMap.containsKey(oar.get().getClassid())) {
String code = Constants.accessRightsCoarMap.get(oar.get().getClassid());
out
.setBestaccessright(
@ -149,7 +71,6 @@ public class ResultMapper implements Serializable {
Constants.coarCodeLabelMap.get(code),
Constants.COAR_ACCESS_RIGHT_SCHEMA));
}
}
final List<String> contributorList = new ArrayList<>();
Optional
@ -225,7 +146,11 @@ public class ResultMapper implements Serializable {
} else {
((CommunityResult) out)
.setInstance(
oInst.get().stream().map(ResultMapper::getCommunityInstance).collect(Collectors.toList()));
oInst
.get()
.stream()
.map(ResultMapper::getCommunityInstance)
.collect(Collectors.toList()));
}
}
@ -245,7 +170,7 @@ public class ResultMapper implements Serializable {
.stream()
.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("main title"))
.collect(Collectors.toList());
if (iTitle.size() > 0) {
if (!iTitle.isEmpty()) {
out.setMaintitle(iTitle.get(0).getValue());
}
@ -254,24 +179,24 @@ public class ResultMapper implements Serializable {
.stream()
.filter(t -> t.getQualifier().getClassid().equalsIgnoreCase("subtitle"))
.collect(Collectors.toList());
if (iTitle.size() > 0) {
if (!iTitle.isEmpty()) {
out.setSubtitle(iTitle.get(0).getValue());
}
}
List<ControlledField> pids = new ArrayList<>();
Optional
.ofNullable(input.getPid())
.ifPresent(
value -> value
value -> out
.setPid(
value
.stream()
.forEach(
p -> pids
.add(
ControlledField
.newInstance(p.getQualifier().getClassid(), p.getValue()))));
out.setPid(pids);
.map(
p -> ControlledField
.newInstance(p.getQualifier().getClassid(), p.getValue()))
.collect(Collectors.toList())));
oStr = Optional.ofNullable(input.getDateofacceptance());
if (oStr.isPresent()) {
out.setPublicationdate(oStr.get().getValue());
@ -281,11 +206,11 @@ public class ResultMapper implements Serializable {
out.setPublisher(oStr.get().getValue());
}
List<String> sourceList = new ArrayList<>();
Optional
.ofNullable(input.getSource())
.ifPresent(value -> value.stream().forEach(s -> sourceList.add(s.getValue())));
// out.setSource(input.getSource().stream().map(s -> s.getValue()).collect(Collectors.toList()));
.ifPresent(
value -> out.setSource(value.stream().map(Field::getValue).collect(Collectors.toList())));
List<Subject> subjectList = new ArrayList<>();
Optional
.ofNullable(input.getSubject())
@ -296,7 +221,6 @@ public class ResultMapper implements Serializable {
out.setSubjects(subjectList);
out.setType(input.getResulttype().getClassid());
}
if (!Constants.DUMPTYPE.COMPLETE.getType().equals(dumpType)) {
((CommunityResult) out)
@ -316,14 +240,14 @@ public class ResultMapper implements Serializable {
value -> value
.stream()
.map(c -> {
String community_id = c.getId();
if (community_id.indexOf("::") > 0) {
community_id = community_id.substring(0, community_id.indexOf("::"));
String communityId = c.getId();
if (communityId.contains("::")) {
communityId = communityId.substring(0, communityId.indexOf("::"));
}
if (communities.contains(community_id)) {
if (communities.contains(communityId)) {
Context context = new Context();
context.setCode(community_id);
context.setLabel(communityMap.get(community_id));
context.setCode(communityId);
context.setLabel(communityMap.get(communityId));
Optional<List<DataInfo>> dataInfo = Optional.ofNullable(c.getDataInfo());
if (dataInfo.isPresent()) {
List<Provenance> provenance = new ArrayList<>();
@ -338,12 +262,17 @@ public class ResultMapper implements Serializable {
.map(
provenanceaction -> Provenance
.newInstance(
provenanceaction.getClassname(), di.getTrust()))
provenanceaction.getClassname(),
di.getTrust()))
.orElse(null))
.filter(Objects::nonNull)
.collect(Collectors.toSet()));
try {
context.setProvenance(getUniqueProvenance(provenance));
} catch (NoAvailableEntityTypeException e) {
e.printStackTrace();
}
}
return context;
}
@ -353,7 +282,7 @@ public class ResultMapper implements Serializable {
.collect(Collectors.toList()))
.orElse(new ArrayList<>());
if (contextList.size() > 0) {
if (!contextList.isEmpty()) {
Set<Integer> hashValue = new HashSet<>();
List<Context> remainigContext = new ArrayList<>();
contextList.forEach(c -> {
@ -365,10 +294,117 @@ public class ResultMapper implements Serializable {
((CommunityResult) out).setContext(remainigContext);
}
}
} catch (ClassCastException cce) {
return out;
}
}
return out;
}
private static void addTypeSpecificInformation(Result out, eu.dnetlib.dhp.schema.oaf.Result input,
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> ort) throws NoAvailableEntityTypeException {
switch (ort.get().getClassid()) {
case "publication":
Optional<Journal> journal = Optional
.ofNullable(((Publication) input).getJournal());
if (journal.isPresent()) {
Journal j = journal.get();
Container c = new Container();
c.setConferencedate(j.getConferencedate());
c.setConferenceplace(j.getConferenceplace());
c.setEdition(j.getEdition());
c.setEp(j.getEp());
c.setIss(j.getIss());
c.setIssnLinking(j.getIssnLinking());
c.setIssnOnline(j.getIssnOnline());
c.setIssnPrinted(j.getIssnPrinted());
c.setName(j.getName());
c.setSp(j.getSp());
c.setVol(j.getVol());
out.setContainer(c);
out.setType(ModelConstants.PUBLICATION_DEFAULT_RESULTTYPE.getClassname());
}
break;
case "dataset":
Dataset id = (Dataset) input;
Optional.ofNullable(id.getSize()).ifPresent(v -> out.setSize(v.getValue()));
Optional.ofNullable(id.getVersion()).ifPresent(v -> out.setVersion(v.getValue()));
out
.setGeolocation(
Optional
.ofNullable(id.getGeolocation())
.map(
igl -> igl
.stream()
.filter(Objects::nonNull)
.map(gli -> {
GeoLocation gl = new GeoLocation();
gl.setBox(gli.getBox());
gl.setPlace(gli.getPlace());
gl.setPoint(gli.getPoint());
return gl;
})
.collect(Collectors.toList()))
.orElse(null));
out.setType(ModelConstants.DATASET_DEFAULT_RESULTTYPE.getClassname());
break;
case "software":
Software is = (Software) input;
Optional
.ofNullable(is.getCodeRepositoryUrl())
.ifPresent(value -> out.setCodeRepositoryUrl(value.getValue()));
Optional
.ofNullable(is.getDocumentationUrl())
.ifPresent(
value -> out
.setDocumentationUrl(
value
.stream()
.map(Field::getValue)
.collect(Collectors.toList())));
Optional
.ofNullable(is.getProgrammingLanguage())
.ifPresent(value -> out.setProgrammingLanguage(value.getClassid()));
out.setType(ModelConstants.SOFTWARE_DEFAULT_RESULTTYPE.getClassname());
break;
case "other":
OtherResearchProduct ir = (OtherResearchProduct) input;
out
.setContactgroup(
Optional
.ofNullable(ir.getContactgroup())
.map(value -> value.stream().map(Field::getValue).collect(Collectors.toList()))
.orElse(null));
out
.setContactperson(
Optional
.ofNullable(ir.getContactperson())
.map(value -> value.stream().map(Field::getValue).collect(Collectors.toList()))
.orElse(null));
out
.setTool(
Optional
.ofNullable(ir.getTool())
.map(value -> value.stream().map(Field::getValue).collect(Collectors.toList()))
.orElse(null));
out.setType(ModelConstants.ORP_DEFAULT_RESULTTYPE.getClassname());
break;
default:
throw new NoAvailableEntityTypeException();
}
}
private static Instance getGraphInstance(eu.dnetlib.dhp.schema.oaf.Instance i) {
Instance instance = new Instance();
@ -397,11 +433,11 @@ public class ResultMapper implements Serializable {
}
private static <I extends Instance> void setCommonValue(eu.dnetlib.dhp.schema.oaf.Instance i, I instance) {
Optional<eu.dnetlib.dhp.schema.oaf.Qualifier> opAr = Optional
.ofNullable(i.getAccessright());
if (opAr.isPresent()) {
if (Constants.accessRightsCoarMap.containsKey(opAr.get().getClassid())) {
Optional<eu.dnetlib.dhp.schema.oaf.AccessRight> opAr = Optional.ofNullable(i.getAccessright());
if (opAr.isPresent() && Constants.accessRightsCoarMap.containsKey(opAr.get().getClassid())) {
String code = Constants.accessRightsCoarMap.get(opAr.get().getClassid());
instance
.setAccessright(
AccessRight
@ -409,9 +445,46 @@ public class ResultMapper implements Serializable {
code,
Constants.coarCodeLabelMap.get(code),
Constants.COAR_ACCESS_RIGHT_SCHEMA));
if (opAr.get().getOpenAccessRoute() != null) {
switch (opAr.get().getOpenAccessRoute()) {
case hybrid:
instance.getAccessright().setOpenAccessRoute(OpenAccessRoute.hybrid);
break;
case gold:
instance.getAccessright().setOpenAccessRoute(OpenAccessRoute.gold);
break;
case green:
instance.getAccessright().setOpenAccessRoute(OpenAccessRoute.green);
break;
case bronze:
instance.getAccessright().setOpenAccessRoute(OpenAccessRoute.bronze);
break;
}
}
}
Optional
.ofNullable(i.getPid())
.ifPresent(
pid -> instance
.setPid(
pid
.stream()
.map(p -> ControlledField.newInstance(p.getQualifier().getClassid(), p.getValue()))
.collect(Collectors.toList())));
Optional
.ofNullable(i.getAlternateIdentifier())
.ifPresent(
ai -> instance
.setAlternateIdentifier(
ai
.stream()
.map(p -> ControlledField.newInstance(p.getQualifier().getClassid(), p.getValue()))
.collect(Collectors.toList())));
Optional
.ofNullable(i.getLicense())
.ifPresent(value -> instance.setLicense(value.getValue()));
@ -424,11 +497,26 @@ public class ResultMapper implements Serializable {
Optional
.ofNullable(i.getInstancetype())
.ifPresent(value -> instance.setType(value.getClassname()));
Optional.ofNullable(i.getUrl()).ifPresent(value -> instance.setUrl(value));
Optional<Field<String>> oPca = Optional.ofNullable(i.getProcessingchargeamount());
Optional<Field<String>> oPcc = Optional.ofNullable(i.getProcessingchargecurrency());
if (oPca.isPresent() && oPcc.isPresent()) {
Field<String> pca = oPca.get();
Field<String> pcc = oPcc.get();
if (!pca.getValue().trim().equals("") && !pcc.getValue().trim().equals("")) {
APC apc = new APC();
apc.setCurrency(oPcc.get().getValue());
apc.setAmount(oPca.get().getValue());
instance.setArticleprocessingcharge(apc);
}
}
Optional.ofNullable(i.getUrl()).ifPresent(instance::setUrl);
}
private static List<Provenance> getUniqueProvenance(List<Provenance> provenance) {
private static List<Provenance> getUniqueProvenance(List<Provenance> provenance)
throws NoAvailableEntityTypeException {
Provenance iProv = new Provenance();
Provenance hProv = new Provenance();
@ -450,6 +538,8 @@ public class ResultMapper implements Serializable {
case Constants.USER_CLAIM:
lProv = getHighestTrust(lProv, p);
break;
default:
throw new NoAvailableEntityTypeException();
}
}
@ -503,9 +593,7 @@ public class ResultMapper implements Serializable {
return a;
}
private static Pid getOrcid(List<StructuredProperty> p) {
for (StructuredProperty pid : p) {
if (pid.getQualifier().getClassid().equals(ModelConstants.ORCID)) {
private static Pid getAuthorPid(StructuredProperty pid) {
Optional<DataInfo> di = Optional.ofNullable(pid.getDataInfo());
if (di.isPresent()) {
return Pid
@ -528,9 +616,44 @@ public class ResultMapper implements Serializable {
);
}
}
private static Pid getOrcid(List<StructuredProperty> p) {
List<StructuredProperty> pidList = p.stream().map(pid -> {
if (pid.getQualifier().getClassid().equals(ModelConstants.ORCID) ||
(pid.getQualifier().getClassid().equals(ModelConstants.ORCID_PENDING))) {
return pid;
}
return null;
}).filter(Objects::nonNull).collect(Collectors.toList());
if (pidList.size() == 1) {
return getAuthorPid(pidList.get(0));
}
List<StructuredProperty> orcid = pidList
.stream()
.filter(
ap -> ap
.getQualifier()
.getClassid()
.equals(ModelConstants.ORCID))
.collect(Collectors.toList());
if (orcid.size() == 1) {
return getAuthorPid(orcid.get(0));
}
orcid = pidList
.stream()
.filter(
ap -> ap
.getQualifier()
.getClassid()
.equals(ModelConstants.ORCID_PENDING))
.collect(Collectors.toList());
if (orcid.size() == 1) {
return getAuthorPid(orcid.get(0));
}
return null;
}

Some files were not shown because too many files have changed in this diff Show More