D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 13 Projects 2 Releases 2 Wiki Activity

orcid-no-doi #43

Merged
claudio.atzori merged 45 commits from enrico.ottonello/dnet-hadoop:orcid-no-doi into master 2020-12-02 10:55:12 +01:00
Conversation 5 Commits 45 Files Changed 68 +483 -47
8 changed files with 483 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit b2213b6435 - Show all commits

2
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/ActivitiesDecompressor.java
View File

@ -19,9 +19,9 @@ import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.mortbay.log.Log;
import eu.dnetlib.doiboost.orcidnodoi.json.JsonWriter;
import eu.dnetlib.doiboost.orcid.model.WorkData;
import eu.dnetlib.doiboost.orcid.xml.XMLRecordParser;
import eu.dnetlib.doiboost.orcidnodoi.json.JsonWriter;
public class ActivitiesDecompressor {

2
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SummariesDecompressor.java
View File

@ -19,9 +19,9 @@ import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.mortbay.log.Log;
import eu.dnetlib.doiboost.orcidnodoi.json.JsonWriter;
import eu.dnetlib.doiboost.orcid.model.AuthorData;
import eu.dnetlib.doiboost.orcid.xml.XMLRecordParser;
import eu.dnetlib.doiboost.orcidnodoi.json.JsonWriter;
public class SummariesDecompressor {

1
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/json/JsonHelper.java
View File

@ -3,6 +3,7 @@ package eu.dnetlib.doiboost.orcid.json;
import com.google.gson.Gson;
import com.google.gson.JsonObject;
import eu.dnetlib.doiboost.orcidnodoi.model.WorkDataNoDoi;
public class JsonHelper {

30
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/ActivitiesDumpReader.java
View File

@ -1,10 +1,12 @@
package eu.dnetlib.doiboost.orcidnodoi;
import eu.dnetlib.doiboost.orcid.json.JsonHelper;
import eu.dnetlib.doiboost.orcidnodoi.json.JsonWriter;
import eu.dnetlib.doiboost.orcidnodoi.model.WorkDataNoDoi;
import eu.dnetlib.doiboost.orcidnodoi.xml.XMLRecordParserNoDoi;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URI;
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
import org.apache.hadoop.conf.Configuration;
@ -17,11 +19,10 @@ import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.mortbay.log.Log;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.net.URI;
import eu.dnetlib.doiboost.orcid.json.JsonHelper;
import eu.dnetlib.doiboost.orcidnodoi.json.JsonWriter;
import eu.dnetlib.doiboost.orcidnodoi.model.WorkDataNoDoi;
import eu.dnetlib.doiboost.orcidnodoi.xml.XMLRecordParserNoDoi;
public class ActivitiesDumpReader {
@ -82,7 +83,8 @@ public class ActivitiesDumpReader {
while ((line = br.readLine()) != null) {
buffer.append(line);
}
WorkDataNoDoi workDataNoDoi = XMLRecordParserNoDoi.VTDParseWorkData(buffer.toString().getBytes());
WorkDataNoDoi workDataNoDoi = XMLRecordParserNoDoi
.VTDParseWorkData(buffer.toString().getBytes());
if (workDataNoDoi != null) {
if (workDataNoDoi.getErrorCode() != null) {
errorFromOrcidFound += 1;
@ -94,9 +96,11 @@ public class ActivitiesDumpReader {
+ entry.getName());
continue;
}
boolean isDoiFound = workDataNoDoi.getExtIds().stream()
.filter(e -> e.getType()!=null)
.anyMatch(e -> e.getType().equals("doi"));
boolean isDoiFound = workDataNoDoi
.getExtIds()
.stream()
.filter(e -> e.getType() != null)
.anyMatch(e -> e.getType().equals("doi"));
if (!isDoiFound) {
String jsonData = JsonHelper.createOidWork(workDataNoDoi);
Log.debug("oid: " + workDataNoDoi.getOid() + " data: " + jsonData);

7
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/GenOrcidAuthorWork.java
View File

@ -1,15 +1,16 @@
package eu.dnetlib.doiboost.orcidnodoi;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.doiboost.orcid.OrcidDSManager;
import java.io.IOException;
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.mortbay.log.Log;
import java.io.IOException;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.doiboost.orcid.OrcidDSManager;
public class GenOrcidAuthorWork extends OrcidDSManager {

59
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/SparkGenEnrichedOrcidWorks.java
View File

@ -1,13 +1,12 @@
package eu.dnetlib.doiboost.orcidnodoi;
import com.google.gson.Gson;
import com.google.gson.JsonElement;
import com.google.gson.JsonParser;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.doiboost.orcid.model.AuthorData;
import eu.dnetlib.doiboost.orcidnodoi.model.WorkDataNoDoi;
import eu.dnetlib.doiboost.orcidnodoi.similarity.AuthorMatcher;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.IOException;
import java.util.Objects;
import java.util.Optional;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.Text;
import org.apache.spark.SparkConf;
@ -19,14 +18,17 @@ import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Encoders;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.gson.Gson;
import com.google.gson.JsonElement;
import com.google.gson.JsonParser;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.doiboost.orcid.model.AuthorData;
import eu.dnetlib.doiboost.orcidnodoi.model.WorkDataNoDoi;
import eu.dnetlib.doiboost.orcidnodoi.similarity.AuthorMatcher;
import scala.Tuple2;
import java.io.IOException;
import java.util.Objects;
import java.util.Optional;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
public class SparkGenEnrichedOrcidWorks {
public static void main(String[] args) throws IOException, Exception {
@ -67,27 +69,28 @@ public class SparkGenEnrichedOrcidWorks {
Encoders.bean(AuthorData.class));
JavaPairRDD<Text, Text> activitiesRDD = sc
.sequenceFile(workingPath + outputWorksPath + "works_X.seq" , Text.class, Text.class);
.sequenceFile(workingPath + outputWorksPath + "works_X.seq", Text.class, Text.class);
Dataset<WorkDataNoDoi> activitiesDataset = spark
.createDataset(
activitiesRDD.map(seq -> loadWorkFromJson(seq._1(), seq._2())).rdd(),
Encoders.bean(WorkDataNoDoi.class));
activitiesDataset
.joinWith(
summariesDataset,
activitiesDataset.col("oid").equalTo(summariesDataset.col("oid")), "inner")
.map(
(MapFunction<Tuple2<WorkDataNoDoi, AuthorData>, Tuple2<String, WorkDataNoDoi>>) value -> {
WorkDataNoDoi w = value._1;
AuthorData a = value._2;
AuthorMatcher.match(a, w.getContributors());
return new Tuple2<>(a.getOid(), w);
},
Encoders.tuple(Encoders.STRING(), Encoders.bean(WorkDataNoDoi.class)))
.filter(Objects::nonNull)
.toJavaRDD()
.saveAsTextFile(workingPath + outputEnrichedWorksPath);;
.joinWith(
summariesDataset,
activitiesDataset.col("oid").equalTo(summariesDataset.col("oid")), "inner")
.map(
(MapFunction<Tuple2<WorkDataNoDoi, AuthorData>, Tuple2<String, WorkDataNoDoi>>) value -> {
WorkDataNoDoi w = value._1;
AuthorData a = value._2;
AuthorMatcher.match(a, w.getContributors());
return new Tuple2<>(a.getOid(), w);
},
Encoders.tuple(Encoders.STRING(), Encoders.bean(WorkDataNoDoi.class)))
.filter(Objects::nonNull)
.toJavaRDD()
.saveAsTextFile(workingPath + outputEnrichedWorksPath);
;
});
}

427
dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcidnodoi/proto/ProtoWriter.java Normal file
View File

@ -0,0 +1,427 @@
package eu.dnetlib.doiboost.orcidnodoi.proto;
public class ProtoWriter {
}
//
//import static eu.dnetlib.data.mapreduce.hbase.dataimport.DumpToActionsUtility.getArrayValues;
//import static eu.dnetlib.data.mapreduce.hbase.dataimport.DumpToActionsUtility.getDefaultResulttype;
//import static eu.dnetlib.data.mapreduce.hbase.dataimport.DumpToActionsUtility.getQualifier;
//import static eu.dnetlib.data.mapreduce.hbase.dataimport.DumpToActionsUtility.getStringValue;
//import static eu.dnetlib.data.mapreduce.hbase.dataimport.DumpToActionsUtility.isValidDate;
//
//import java.io.IOException;
//import java.io.InputStream;
//import java.util.ArrayList;
//import java.util.HashMap;
//import java.util.List;
//import java.util.Map;
//
//import org.apache.commons.io.IOUtils;
//import org.apache.commons.lang3.StringUtils;
//
//import com.google.gson.Gson;
//import com.google.gson.JsonArray;
//import com.google.gson.JsonElement;
//import com.google.gson.JsonObject;
//import com.googlecode.protobuf.format.JsonFormat;
//
//import eu.dnetlib.actionmanager.actions.ActionFactory;
//import eu.dnetlib.actionmanager.actions.AtomicAction;
//import eu.dnetlib.actionmanager.common.Agent;
//import eu.dnetlib.data.mapreduce.hbase.Reporter;
//import eu.dnetlib.data.mapreduce.util.StreamUtils;
//import eu.dnetlib.data.proto.FieldTypeProtos;
//import eu.dnetlib.data.proto.FieldTypeProtos.Author;
//import eu.dnetlib.data.proto.FieldTypeProtos.DataInfo;
//import eu.dnetlib.data.proto.FieldTypeProtos.KeyValue;
//import eu.dnetlib.data.proto.FieldTypeProtos.Qualifier;
//import eu.dnetlib.data.proto.FieldTypeProtos.StringField;
//import eu.dnetlib.data.proto.FieldTypeProtos.StructuredProperty;
//import eu.dnetlib.data.proto.KindProtos;
//import eu.dnetlib.data.proto.OafProtos;
//import eu.dnetlib.data.proto.ResultProtos;
//import eu.dnetlib.data.proto.TypeProtos;
//import eu.dnetlib.data.transform.xml.AbstractDNetXsltFunctions;
//import eu.dnetlib.miscutils.collections.Pair;
//import eu.dnetlib.miscutils.datetime.DateUtils;
//import eu.dnetlib.pace.model.Person;
//
//public class ProtoWriter {
//
// public static final String ORCID = "ORCID";
// public final static String orcidPREFIX = "orcid_______";
// public static final String OPENAIRE_PREFIX = "openaire____";
// public static final String SEPARATOR = "::";
//
// private static Map<String, Pair<String, String>> datasources = new HashMap<String, Pair<String, String>>() {
//
// {
// put(ORCID.toLowerCase(), new Pair<>(ORCID, OPENAIRE_PREFIX + SEPARATOR + "orcid"));
//
// }
// };
//
// // json external id will be mapped to oaf:pid/@classid Map to oaf:pid/@classname
// private static Map<String, Pair<String, String>> externalIds = new HashMap<String, Pair<String, String>>() {
//
// {
// put("ark".toLowerCase(), new Pair<>("ark", "ark"));
// put("arxiv".toLowerCase(), new Pair<>("arxiv", "arXiv"));
// put("pmc".toLowerCase(), new Pair<>("pmc", "pmc"));
// put("pmid".toLowerCase(), new Pair<>("pmid", "pmid"));
// put("source-work-id".toLowerCase(), new Pair<>("orcidworkid", "orcidworkid"));
// put("urn".toLowerCase(), new Pair<>("urn", "urn"));
// }
// };
//
// static Map<String, Map<String, String>> typologiesMapping;
//
// static {
// try {
// final InputStream is = OrcidToActions.class.getResourceAsStream("/eu/dnetlib/data/mapreduce/hbase/dataimport/mapping_typologies_orcid.json");
// final String tt = IOUtils.toString(is);
// typologiesMapping = new Gson().fromJson(tt, Map.class);
// } catch (final IOException e) {
// e.printStackTrace();
// }
// }
//
// public static final String PID_TYPES = "dnet:pid_types";
//
// public static List<AtomicAction> generatePublicationActionsFromDump(final JsonObject rootElement,
// final ActionFactory factory,
// final String setName,
// final Agent agent,
// final Reporter context) {
//
// if (!isValid(rootElement, context)) { return null; }
//
// // Create OAF proto
//
// final OafProtos.Oaf.Builder oaf = OafProtos.Oaf.newBuilder();
//
// oaf.setDataInfo(
// DataInfo.newBuilder()
// .setDeletedbyinference(false)
// .setInferred(false)
// .setTrust("0.9")
// .setProvenanceaction(getQualifier("sysimport:actionset:orcidworks-no-doi", "dnet:provenanceActions"))
// .build());
//
// // Adding kind
// oaf.setKind(KindProtos.Kind.entity);
//
// oaf.setLastupdatetimestamp(DateUtils.now());
//
// // creating result proto
// final OafProtos.OafEntity.Builder entity = OafProtos.OafEntity.newBuilder().setType(TypeProtos.Type.result);
//
// entity.setDateofcollection("2018-10-22");
// entity.setDateoftransformation(DateUtils.now_ISO8601());
//
// // Adding external ids
// StreamUtils.toStream(externalIds.keySet().iterator())
// .forEach(jsonExtId -> {
// final String classid = externalIds.get(jsonExtId.toLowerCase()).getValue();
// final String classname = externalIds.get(jsonExtId.toLowerCase()).getKey();
// final String extId = getStringValue(rootElement, jsonExtId);
// if (StringUtils.isNotBlank(extId)) {
// entity.addPid(StructuredProperty.newBuilder()
// .setValue(extId)
// .setQualifier(Qualifier.newBuilder().setClassid(classid).setClassname(classname).setSchemeid("dnet:pid_types")
// .setSchemename("dnet:pid_types").build())
// .build());
// }
// });
//
// // Create result field
// final ResultProtos.Result.Builder result = ResultProtos.Result.newBuilder();
//
// // Create metadata proto
// final ResultProtos.Result.Metadata.Builder metadata = ResultProtos.Result.Metadata.newBuilder();
//
// // Adding source
// final String source = getStringValue(rootElement, "source");
// if (StringUtils.isNotBlank(source)) {
// metadata.addSource(StringField.newBuilder().setValue(source).build());
// }
//
// // Adding title
// final String title = createRepeatedField(rootElement, "titles");
// if (StringUtils.isBlank(title)) {
// context.incrementCounter("filtered", "title_not_found", 1);
// return null;
// }
// metadata.addTitle(FieldTypeProtos.StructuredProperty.newBuilder()
// .setValue(title)
// .setQualifier(getQualifier("main title", "dnet:dataCite_title"))
// .build());
//
// // Adding identifier
// final String id = getStringValue(rootElement, "id");
// String sourceId = null;
// if (id != null) {
// entity.addOriginalId(id);
// sourceId = String.format("50|%s" + SEPARATOR + "%s", orcidPREFIX, AbstractDNetXsltFunctions.md5(id));
// } else {
// sourceId = String.format("50|%s" + SEPARATOR + "%s", orcidPREFIX, AbstractDNetXsltFunctions.md5(title));
// }
// entity.setId(sourceId);
//
// // Adding relevant date
// settingRelevantDate(rootElement, metadata, "publication_date", "issued", true);
//
// // Adding collectedfrom
// final FieldTypeProtos.KeyValue collectedFrom = FieldTypeProtos.KeyValue.newBuilder()
// .setValue(ORCID)
// .setKey("10|" + OPENAIRE_PREFIX + SEPARATOR + "806360c771262b4d6770e7cdf04b5c5a")
// .build();
// entity.addCollectedfrom(collectedFrom);
//
// // Adding type
// final String type = getStringValue(rootElement, "type");
// String cobjValue = "";
// if (StringUtils.isNotBlank(type)) {
//
// metadata.setResourcetype(FieldTypeProtos.Qualifier.newBuilder()
// .setClassid(type)
// .setClassname(type)
// .setSchemeid("dnet:dataCite_resource")
// .setSchemename("dnet:dataCite_resource")
// .build());
//
// final String typeValue = typologiesMapping.get(type).get("value");
// cobjValue = typologiesMapping.get(type).get("cobj");
// final ResultProtos.Result.Instance.Builder instance = ResultProtos.Result.Instance.newBuilder();
//
// // Adding hostedby
// instance.setHostedby(FieldTypeProtos.KeyValue.newBuilder()
// .setKey("10|" + OPENAIRE_PREFIX + SEPARATOR + "55045bd2a65019fd8e6741a755395c8c")
// .setValue("Unknown Repository")
// .build());
//
// // Adding url
// final String url = createRepeatedField(rootElement, "urls");
// if (StringUtils.isNotBlank(url)) {
// instance.addUrl(url);
// }
//
// final String pubDate = getPublicationDate(rootElement, "publication_date");
// if (StringUtils.isNotBlank(pubDate)) {
// instance.setDateofacceptance(FieldTypeProtos.StringField.newBuilder().setValue(pubDate).build());
// }
//
// instance.setCollectedfrom(collectedFrom);
//
// // Adding accessright
// instance.setAccessright(FieldTypeProtos.Qualifier.newBuilder()
// .setClassid("UNKNOWN")
// .setClassname("UNKNOWN")
// .setSchemeid("dnet:access_modes")
// .setSchemename("dnet:access_modes")
// .build());
//
// // Adding type
// instance.setInstancetype(FieldTypeProtos.Qualifier.newBuilder()
// .setClassid(cobjValue)
// .setClassname(typeValue)
// .setSchemeid("dnet:publication_resource")
// .setSchemename("dnet:publication_resource")
// .build());
//
// result.addInstance(instance);
// } else {
// context.incrementCounter("filtered", "type_not_found", 1);
// return null;
// }
//
// // Adding authors
// final List<Author> authors = createAuthors(rootElement);
// if (authors != null && authors.size() > 0) {
// metadata.addAllAuthor(authors);
// } else {
// context.incrementCounter("filtered", "author_not_found", 1);
// return null;
// }
//
// metadata.setResulttype(getQualifier(getDefaultResulttype(cobjValue), "dnet:result_typologies"));
// result.setMetadata(metadata.build());
// entity.setResult(result.build());
// oaf.setEntity(entity.build());
//
// final List<AtomicAction> actionList = new ArrayList<>();
//
// actionList.add(factory.createAtomicAction(setName, agent, oaf.getEntity().getId(), "result", "body", oaf.build().toByteArray()));
//
//// System.out.println(JsonFormat.printToString(oaf.build()));
// return actionList;
//
// }
//
// public static List<Author> createAuthors(final JsonObject root) {
//
// final String authorsJSONFieldName = "authors";
//
// if (root.has(authorsJSONFieldName) && root.get(authorsJSONFieldName).isJsonArray()) {
//
// final List<Author> authors = new ArrayList<>();
// final JsonArray jsonAuthors = root.getAsJsonArray(authorsJSONFieldName);
// int firstCounter = 0;
// int defaultCounter = 0;
// int rank = 1;
// int currentRank = 0;
//
// for (final JsonElement item : jsonAuthors) {
// final JsonObject author = item.getAsJsonObject();
// final Author.Builder result = Author.newBuilder();
// if (item.isJsonObject()) {
// final String surname = getStringValue(author, "surname");
// final String name = getStringValue(author, "name");
// final String oid = getStringValue(author, "oid");
// final String seq = getStringValue(author, "seq");
// if (StringUtils.isNotBlank(seq)) {
// if (seq.equals("first")) {
// firstCounter += 1;
// rank = firstCounter;
//
// } else if (seq.equals("additional")) {
// rank = currentRank + 1;
// } else {
// defaultCounter += 1;
// rank = defaultCounter;
// }
// }
//
// if (StringUtils.isNotBlank(oid)) {
// result.addPid(KeyValue.newBuilder()
// .setValue(oid)
// .setKey("ORCID")
// .build());
// result.setFullname(name + " " + surname);
// if (StringUtils.isNotBlank(name)) {
// result.setName(name);
// }
// if (StringUtils.isNotBlank(surname)) {
// result.setSurname(surname);
// }
// } else {
// String fullname = "";
// if (StringUtils.isNotBlank(name)) {
// fullname = name;
// } else {
// if (StringUtils.isNotBlank(surname)) {
// fullname = surname;
// }
// }
// Person p = new Person(fullname, false);
// if (p.isAccurate()) {
// result.setName(p.getNormalisedFirstName());
// result.setSurname(p.getNormalisedSurname());
// result.setFullname(p.getNormalisedFullname());
// }
// else {
// result.setFullname(fullname);
// }
// }
// }
// result.setRank(rank);
// authors.add(result.build());
// currentRank = rank;
// }
// return authors;
//
// }
// return null;
// }
//
// private static String createRepeatedField(final JsonObject rootElement, final String fieldName) {
// String field = "";
// if (!rootElement.has(fieldName)) { return null; }
// if (rootElement.has(fieldName) && rootElement.get(fieldName).isJsonNull()) { return null; }
// if (rootElement.get(fieldName).isJsonArray()) {
// if (!isValidJsonArray(rootElement, fieldName)) { return null; }
// final StringBuilder ttl = new StringBuilder();
// getArrayValues(rootElement, fieldName).forEach(ttl::append);
// field = ttl.toString();
// } else {
// field = getStringValue(rootElement, fieldName);
// }
//
// if (field != null && !field.isEmpty() && field.charAt(0) == '"' && field.charAt(field.length() - 1) == '"') {
// field = field.substring(1, field.length() - 1);
// }
// return field;
// }
//
// private static void settingRelevantDate(final JsonObject rootElement,
// final ResultProtos.Result.Metadata.Builder metadata,
// final String jsonKey,
// final String dictionaryKey,
// final boolean addToDateOfAcceptance) {
//
// final String pubDate = getPublicationDate(rootElement, "publication_date");
// if (StringUtils.isNotBlank(pubDate)) {
// if (addToDateOfAcceptance) {
// metadata.setDateofacceptance(FieldTypeProtos.StringField.newBuilder().setValue(pubDate).build());
// }
// metadata.addRelevantdate(FieldTypeProtos.StructuredProperty.newBuilder()
// .setValue(pubDate)
// .setQualifier(getQualifier(dictionaryKey, "dnet:dataCite_date"))
// .build());
// }
// }
//
// private static String getPublicationDate(final JsonObject rootElement,
// final String jsonKey) {
//
// final JsonObject pubDateJson = rootElement.getAsJsonObject(jsonKey);
// if (pubDateJson == null) { return null; }
// final String year = getStringValue(pubDateJson, "year");
// final String month = getStringValue(pubDateJson, "month");
// final String day = getStringValue(pubDateJson, "day");
//
// if (StringUtils.isBlank(year)) { return null; }
// String pubDate = "".concat(year);
// if (StringUtils.isNotBlank(month)) {
// pubDate = pubDate.concat("-" + month);
// if (StringUtils.isNotBlank(day)) {
// pubDate = pubDate.concat("-" + day);
// } else {
// pubDate += "-01";
// }
// } else {
// pubDate += "-01-01";
// }
// if (isValidDate(pubDate)) { return pubDate; }
// return null;
// }
//
// protected static boolean isValid(final JsonObject rootElement, final Reporter context) {
//
// final String type = getStringValue(rootElement, "type");
// if (!typologiesMapping.containsKey(type)) {
// context.incrementCounter("filtered", "unknowntype_" + type, 1);
// return false;
// }
//
// if (!isValidJsonArray(rootElement, "titles")) {
// context.incrementCounter("filtered", "invalid_title", 1);
// return false;
// }
// return true;
// }
//
// private static boolean isValidJsonArray(final JsonObject rootElement, final String fieldName) {
// if (!rootElement.has(fieldName)) { return false; }
// final JsonElement jsonElement = rootElement.get(fieldName);
// if (jsonElement.isJsonNull()) { return false; }
// if (jsonElement.isJsonArray()) {
// final JsonArray jsonArray = jsonElement.getAsJsonArray();
// if (jsonArray.isJsonNull()) { return false; }
// if (jsonArray.get(0).isJsonNull()) { return false; }
// }
// return true;
// }
//}

2
dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/gen_enriched_orcid_works/oozie_app/workflow.xml
View File

@ -509,7 +509,7 @@
<mode>cluster</mode>
<name>Gen_Enriched_Orcid_Works</name>
<class>eu.dnetlib.doiboost.orcidnodoi.SparkGenEnrichedOrcidWorks</class>
<jar>dhp-doiboost-1.2.3-SNAPSHOT.jar</jar>
<jar>dhp-doiboost-1.2.2-SNAPSHOT.jar</jar>
<spark-opts>--num-executors 10 --conf spark.yarn.jars=&quot;hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2&quot; --executor-memory=${sparkExecutorMemory} --executor-cores=${sparkExecutorCores} --driver-memory=${sparkDriverMemory}
</spark-opts>
<arg>-w</arg><arg>${workingPath}/</arg>