Added index wf

This commit is contained in:
Sandro La Bruzzo 2020-02-24 10:15:55 +01:00
parent 2b8675462f
commit b021b8a2e1
25 changed files with 1057 additions and 20 deletions

View File

@ -65,7 +65,7 @@ public class DHPUtils {
return (String) o; return (String) o;
if (o instanceof JSONArray && ((JSONArray) o).size() > 0) if (o instanceof JSONArray && ((JSONArray) o).size() > 0)
return (String) ((JSONArray) o).get(0); return (String) ((JSONArray) o).get(0);
return ""; return o.toString();
} catch (Exception e) { } catch (Exception e) {
return ""; return "";
} }

View File

@ -27,7 +27,6 @@ public class SparkPropagateRelationsJob {
SOURCE, SOURCE,
TARGET TARGET
} }
final static String IDJSONPATH = "$.id";
final static String SOURCEJSONPATH = "$.source"; final static String SOURCEJSONPATH = "$.source";
final static String TARGETJSONPATH = "$.target"; final static String TARGETJSONPATH = "$.target";

View File

@ -44,6 +44,7 @@ public class SparkUpdateEntityJob {
final String mergeRelPath = parser.get("mergeRelPath"); final String mergeRelPath = parser.get("mergeRelPath");
final String dedupRecordPath = parser.get("dedupRecordPath"); final String dedupRecordPath = parser.get("dedupRecordPath");
final String entity = parser.get("entity"); final String entity = parser.get("entity");
final String destination = parser.get("targetPath");
final Dataset<Relation> df = spark.read().load(mergeRelPath).as(Encoders.bean(Relation.class)); final Dataset<Relation> df = spark.read().load(mergeRelPath).as(Encoders.bean(Relation.class));
final JavaPairRDD<String, String> mergedIds = df final JavaPairRDD<String, String> mergedIds = df
@ -63,7 +64,7 @@ public class SparkUpdateEntityJob {
.mapToPair((PairFunction<String, String, String>) s -> new Tuple2<>(DHPUtils.getJPathString(TARGETJSONPATH, s), s)) .mapToPair((PairFunction<String, String, String>) s -> new Tuple2<>(DHPUtils.getJPathString(TARGETJSONPATH, s), s))
.leftOuterJoin(mergedIds) .leftOuterJoin(mergedIds)
.map(k -> k._2()._2().isPresent() ? updateDeletedByInference(k._2()._1(), Relation.class) : k._2()._1()) .map(k -> k._2()._2().isPresent() ? updateDeletedByInference(k._2()._1(), Relation.class) : k._2()._1())
.saveAsTextFile(entityPath + "_new", GzipCodec.class); .saveAsTextFile(destination, GzipCodec.class);
} else { } else {
final JavaRDD<String> dedupEntity = sc.textFile(dedupRecordPath); final JavaRDD<String> dedupEntity = sc.textFile(dedupRecordPath);
JavaPairRDD<String, String> entitiesWithId = sourceEntity.mapToPair((PairFunction<String, String, String>) s -> new Tuple2<>(DHPUtils.getJPathString(IDJSONPATH, s), s)); JavaPairRDD<String, String> entitiesWithId = sourceEntity.mapToPair((PairFunction<String, String, String>) s -> new Tuple2<>(DHPUtils.getJPathString(IDJSONPATH, s), s));
@ -86,7 +87,7 @@ public class SparkUpdateEntityJob {
JavaRDD<String> map = entitiesWithId.leftOuterJoin(mergedIds).map(k -> k._2()._2().isPresent() ? updateDeletedByInference(k._2()._1(), mainClass) : k._2()._1()); JavaRDD<String> map = entitiesWithId.leftOuterJoin(mergedIds).map(k -> k._2()._2().isPresent() ? updateDeletedByInference(k._2()._1(), mainClass) : k._2()._1());
map.union(dedupEntity).saveAsTextFile(entityPath + "_new", GzipCodec.class); map.union(dedupEntity).saveAsTextFile(destination, GzipCodec.class);
} }

View File

@ -22,10 +22,17 @@
"paramLongName": "dedupRecordPath", "paramLongName": "dedupRecordPath",
"paramDescription": "the inputPath of dedup record", "paramDescription": "the inputPath of dedup record",
"paramRequired": true "paramRequired": true
}, { },
{
"paramName": "e", "paramName": "e",
"paramLongName": "entity", "paramLongName": "entity",
"paramDescription": "the type of entity", "paramDescription": "the type of entity",
"paramRequired": true "paramRequired": true
} },
{
"paramName": "t",
"paramLongName": "targetPath",
"paramDescription": "the targetPath",
"paramRequired": true
}
] ]

View File

@ -26,7 +26,7 @@
</property> </property>
</parameters> </parameters>
<start to="DeleteWorkingPath"/> <start to="updateDeletedByInferenceRelation"/>
<kill name="Kill"> <kill name="Kill">
@ -55,8 +55,7 @@
<spark-opts> <spark-opts>
--executor-memory ${sparkExecutorMemory} --executor-memory ${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--num-executors 100 ${sparkExtraOPT}
--conf spark.yarn.jars="hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2"
</spark-opts> </spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg> <arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
@ -80,8 +79,7 @@
<spark-opts> <spark-opts>
--executor-memory ${sparkExecutorMemory} --executor-memory ${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--num-executors 100 ${sparkExtraOPT}
--conf spark.yarn.jars="hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2"
</spark-opts> </spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg> <arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
@ -105,8 +103,7 @@
<spark-opts> <spark-opts>
--executor-memory ${sparkExecutorMemory} --executor-memory ${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--num-executors 100 ${sparkExtraOPT}
--conf spark.yarn.jars="hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2"
</spark-opts> </spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg> <arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${sourcePath}</arg> <arg>--sourcePath</arg><arg>${sourcePath}</arg>
@ -130,14 +127,76 @@
<spark-opts> <spark-opts>
--executor-memory ${sparkExecutorMemory} --executor-memory ${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory} --driver-memory=${sparkDriverMemory}
--num-executors 100 ${sparkExtraOPT}
--conf spark.yarn.jars="hdfs://hadoop-rm1.garr-pa1.d4science.org:8020/user/oozie/share/lib/lib_20180405103059/spark2"
</spark-opts> </spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg> <arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--mergeRelPath</arg><arg>${targetPath}/${entity}/mergeRel</arg> <arg>--mergeRelPath</arg><arg>${targetPath}/${entity}/mergeRel</arg>
<arg>--relationPath</arg><arg>${sourcePath}/relation</arg> <arg>--relationPath</arg><arg>${sourcePath}/relation</arg>
<arg>--targetRelPath</arg><arg>${targetPath}/${entity}/relation_updated</arg> <arg>--targetRelPath</arg><arg>${targetPath}/${entity}/relation_propagated</arg>
</spark> </spark>
<ok to="updateDeletedByInferenceEntity"/>
<error to="Kill"/>
</action>
<action name="updateDeletedByInferenceEntity">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Update ${entity} and add DedupRecord</name>
<class>eu.dnetlib.dedup.SparkUpdateEntityJob</class>
<jar>dhp-dedup-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
${sparkExtraOPT}
</spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--entityPath</arg><arg>${sourcePath}/${entity}</arg>
<arg>--mergeRelPath</arg><arg>${targetPath}/${entity}/mergeRel</arg>
<arg>--entity</arg><arg>${entity}</arg>
<arg>--dedupRecordPath</arg><arg>${targetPath}/${entity}/dedup_records</arg>
<arg>--targetPath</arg><arg>${targetPath}/${entity}/updated_record</arg>
</spark>
<ok to="updateDeletedByInferenceRelation"/>
<error to="Kill"/>
</action>
<action name="updateDeletedByInferenceRelation">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>Update ${entity} set deleted by Inference</name>
<class>eu.dnetlib.dedup.SparkUpdateEntityJob</class>
<jar>dhp-dedup-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory ${sparkExecutorMemory}
--driver-memory=${sparkDriverMemory}
${sparkExtraOPT}
</spark-opts>
<arg>-mt</arg><arg>yarn-cluster</arg>
<arg>--entityPath</arg><arg>${targetPath}/${entity}/relation_propagated</arg>
<arg>--mergeRelPath</arg><arg>${targetPath}/${entity}/mergeRel</arg>
<arg>--entity</arg><arg>relation</arg>
<arg>--dedupRecordPath</arg><arg>${targetPath}/${entity}/dedup_records</arg>
<arg>--targetPath</arg><arg>${targetPath}/${entity}/updated_relation</arg>
</spark>
<ok to="replaceEntity"/>
<error to="Kill"/>
</action>
<action name="replaceEntity">
<fs>
<delete path='${sourcePath}/${entity}'/>
<delete path='${sourcePath}/relation'/>
<move source="${targetPath}/${entity}/updated_relation" target="${sourcePath}/relation" />
<move source="${targetPath}/${entity}/updated_record" target="${sourcePath}/${entity}" />
</fs>
<ok to="End"/> <ok to="End"/>
<error to="Kill"/> <error to="Kill"/>
</action> </action>

View File

@ -0,0 +1,45 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<parent>
<artifactId>dhp-workflows</artifactId>
<groupId>eu.dnetlib.dhp</groupId>
<version>1.0.5-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>dhp-graph-provision</artifactId>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-schemas</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>org.elasticsearch</groupId>
<artifactId>elasticsearch-hadoop</artifactId>
</dependency>
</dependencies>
</project>

View File

@ -0,0 +1,47 @@
package eu.dnetlib.dhp.provision;
import eu.dnetlib.dhp.provision.scholix.Typology;
import eu.dnetlib.dhp.utils.DHPUtils;
import org.apache.commons.lang3.StringUtils;
public class ProvisionUtil {
public final static String deletedByInferenceJPATH = "$.dataInfo.deletedbyinference";
public final static String TARGETJSONPATH = "$.target";
public final static String SOURCEJSONPATH = "$.source";
public static RelatedItemInfo getItemType(final String item, final String idPath) {
String targetId = DHPUtils.getJPathString(idPath, item);
switch (StringUtils.substringBefore(targetId, "|")) {
case "50":
return new RelatedItemInfo().setRelatedPublication(1);
case "60":
return new RelatedItemInfo().setRelatedDataset(1);
case "70":
return new RelatedItemInfo().setRelatedUnknown(1);
default:
throw new RuntimeException("Unknonw target ID");
}
}
public static Boolean isNotDeleted(final String item) {
return !"true".equalsIgnoreCase(DHPUtils.getJPathString(deletedByInferenceJPATH, item));
}
public static Typology getItemTypeFromId(String id) {
switch (StringUtils.substringBefore(id, "|")) {
case "50":
return Typology.publication;
case "60":
return Typology.dataset;
case "70":
return Typology.unknown;
default:
throw new RuntimeException("Unknonw ID type");
}
}
}

View File

@ -0,0 +1,64 @@
package eu.dnetlib.dhp.provision;
import java.io.Serializable;
/**
* This class models the information of related items
*/
public class RelatedItemInfo implements Serializable {
private String id;
private int relatedDataset = 0;
private int relatedPublication = 0;
private int relatedUnknown = 0;
public String getId() {
return id;
}
public RelatedItemInfo setId(String id) {
this.id = id;
return this;
}
public RelatedItemInfo add(RelatedItemInfo other) {
if (other != null) {
relatedDataset += other.getRelatedDataset();
relatedPublication += other.getRelatedPublication();
relatedUnknown += other.getRelatedUnknown();
}
return this;
}
public int getRelatedDataset() {
return relatedDataset;
}
public RelatedItemInfo setRelatedDataset(int relatedDataset) {
this.relatedDataset = relatedDataset;
return this;
}
public int getRelatedPublication() {
return relatedPublication;
}
public RelatedItemInfo setRelatedPublication(int relatedPublication) {
this.relatedPublication = relatedPublication;
return this;
}
public int getRelatedUnknown() {
return relatedUnknown;
}
public RelatedItemInfo setRelatedUnknown(int relatedUnknown) {
this.relatedUnknown = relatedUnknown;
return this;
}
}

View File

@ -0,0 +1,74 @@
package eu.dnetlib.dhp.provision;
import com.fasterxml.jackson.databind.ObjectMapper;
import com.jayway.jsonpath.JsonPath;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.utils.DHPUtils;
import net.minidev.json.JSONArray;
import org.apache.commons.io.IOUtils;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function2;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.SparkSession;
import scala.Tuple2;
/**
* SparkExtractRelationCount is a spark job that takes in input relation RDD
* and retrieve for each item in relation which are the number of
* - Related Dataset
* - Related Publication
* - Related Unknown
*/
public class SparkExtractRelationCount {
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkExtractRelationCount.class.getResourceAsStream("/eu/dnetlib/dhp/provision/input_related_entities_parameters.json")));
parser.parseArgument(args);
final SparkSession spark = SparkSession
.builder()
.appName(SparkExtractRelationCount.class.getSimpleName())
.master(parser.get("master"))
.getOrCreate();
final String workingDirPath = parser.get("workingDirPath");
final String relationPath = parser.get("relationPath");
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
sc.textFile(relationPath)
// We start to Filter the relation not deleted by Inference
.filter(ProvisionUtil::isNotDeleted)
// Then we create a PairRDD<String, RelatedItem>
.mapToPair((PairFunction<String, String, RelatedItemInfo>) f
-> new Tuple2<>(DHPUtils.getJPathString(ProvisionUtil.SOURCEJSONPATH, f), ProvisionUtil.getItemType(f, ProvisionUtil.TARGETJSONPATH)))
//We reduce and sum the number of Relations
.reduceByKey((Function2<RelatedItemInfo, RelatedItemInfo, RelatedItemInfo>) (v1, v2) -> {
if (v1 == null && v2 == null)
return new RelatedItemInfo();
return v1 != null ? v1.add(v2) : v2;
})
//Set the source Id in RelatedItem object
.map(k -> k._2().setId(k._1()))
// Convert to JSON and save as TextFile
.map(k -> {
ObjectMapper mapper = new ObjectMapper();
return mapper.writeValueAsString(k);
}).saveAsTextFile(workingDirPath + "/relatedItemCount", GzipCodec.class);
}
}

View File

@ -0,0 +1,57 @@
package eu.dnetlib.dhp.provision;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.provision.scholix.ScholixSummary;
import eu.dnetlib.dhp.utils.DHPUtils;
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.io.compress.GzipCodec;
import org.apache.spark.api.java.JavaPairRDD;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.api.java.function.Function;
import org.apache.spark.api.java.function.PairFunction;
import org.apache.spark.sql.SparkSession;
import scala.Tuple2;
public class SparkGenerateSummary {
private static final String jsonIDPath = "$.id";
public static void main(String[] args) throws Exception {
final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkGenerateSummary.class.getResourceAsStream("/eu/dnetlib/dhp/provision/input_generate_summary_parameters.json")));
parser.parseArgument(args);
final SparkSession spark = SparkSession
.builder()
.appName(SparkExtractRelationCount.class.getSimpleName())
.master(parser.get("master"))
.getOrCreate();
final String graphPath = parser.get("graphPath");
final String workingDirPath = parser.get("workingDirPath");
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaPairRDD<String, String> relationCount = sc.textFile(workingDirPath+"/relatedItemCount").mapToPair((PairFunction<String, String, String>) i -> new Tuple2<>(DHPUtils.getJPathString(jsonIDPath, i), i));
JavaPairRDD<String, String> entities =
sc.textFile(graphPath + "/publication")
.filter(ProvisionUtil::isNotDeleted)
.mapToPair((PairFunction<String, String, String>) i -> new Tuple2<>(DHPUtils.getJPathString(jsonIDPath, i), i))
.union(
sc.textFile(graphPath + "/dataset")
.filter(ProvisionUtil::isNotDeleted)
.mapToPair((PairFunction<String, String, String>) i -> new Tuple2<>(DHPUtils.getJPathString(jsonIDPath, i), i))
)
.union(
sc.textFile(graphPath + "/unknown")
.filter(ProvisionUtil::isNotDeleted)
.mapToPair((PairFunction<String, String, String>) i -> new Tuple2<>(DHPUtils.getJPathString(jsonIDPath, i), i))
);
entities.join(relationCount).map((Function<Tuple2<String, Tuple2<String, String>>, String>) k ->
ScholixSummary.fromJsonOAF(ProvisionUtil.getItemTypeFromId(k._1()), k._2()._1(), k._2()._2())).saveAsTextFile(workingDirPath+"/summary", GzipCodec.class);
;
}
}

View File

@ -0,0 +1,49 @@
package eu.dnetlib.dhp.provision;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.provision.scholix.ScholixSummary;
import org.apache.commons.io.IOUtils;
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.elasticsearch.spark.rdd.api.java.JavaEsSpark;
import java.util.HashMap;
import java.util.Map;
public class SparkIndexCollectionOnES {
public static void main(String[] args) throws Exception{
final ArgumentApplicationParser parser = new ArgumentApplicationParser(IOUtils.toString(SparkIndexCollectionOnES.class.getResourceAsStream("/eu/dnetlib/dhp/provision/index_on_es.json")));
parser.parseArgument(args);
SparkConf conf = new SparkConf().setAppName(SparkIndexCollectionOnES.class.getSimpleName())
.setMaster(parser.get("master"));
final String sourcePath = parser.get("sourcePath");
final String index = parser.get("index");
final SparkSession spark = SparkSession.builder().config(conf).getOrCreate();
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
JavaRDD<String> inputRdd = sc.textFile(sourcePath);
Map<String, String> esCfg = new HashMap<>();
esCfg.put("es.nodes", "10.19.65.51, 10.19.65.52, 10.19.65.53, 10.19.65.54");
esCfg.put("es.mapping.id", "id");
esCfg.put("es.batch.write.retry.count", "8");
esCfg.put("es.batch.write.retry.wait", "60s");
esCfg.put("es.batch.size.entries", "200");
esCfg.put("es.nodes.wan.only", "true");
JavaEsSpark.saveJsonToEs(inputRdd,index, esCfg);
}
}

View File

@ -0,0 +1,44 @@
package eu.dnetlib.dhp.provision.scholix;
import java.io.Serializable;
public class CollectedFromType implements Serializable {
private String datasourceName;
private String datasourceId;
private String completionStatus;
public CollectedFromType() {
}
public CollectedFromType(String datasourceName, String datasourceId, String completionStatus) {
this.datasourceName = datasourceName;
this.datasourceId = datasourceId;
this.completionStatus = completionStatus;
}
public String getDatasourceName() {
return datasourceName;
}
public void setDatasourceName(String datasourceName) {
this.datasourceName = datasourceName;
}
public String getDatasourceId() {
return datasourceId;
}
public void setDatasourceId(String datasourceId) {
this.datasourceId = datasourceId;
}
public String getCompletionStatus() {
return completionStatus;
}
public void setCompletionStatus(String completionStatus) {
this.completionStatus = completionStatus;
}
}

View File

@ -0,0 +1,33 @@
package eu.dnetlib.dhp.provision.scholix;
import java.io.Serializable;
public class SchemeValue implements Serializable {
private String scheme;
private String value;
public SchemeValue() {
}
public SchemeValue(String scheme, String value) {
this.scheme = scheme;
this.value = value;
}
public String getScheme() {
return scheme;
}
public void setScheme(String scheme) {
this.scheme = scheme;
}
public String getValue() {
return value;
}
public void setValue(String value) {
this.value = value;
}
}

View File

@ -0,0 +1,289 @@
package eu.dnetlib.dhp.provision.scholix;
import com.fasterxml.jackson.annotation.JsonProperty;
import com.fasterxml.jackson.databind.DeserializationFeature;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.provision.RelatedItemInfo;
import eu.dnetlib.dhp.schema.oaf.Author;
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
import eu.dnetlib.dhp.schema.scholexplorer.DLIDataset;
import eu.dnetlib.dhp.schema.scholexplorer.DLIPublication;
import eu.dnetlib.dhp.schema.scholexplorer.DLIUnknown;
import java.io.Serializable;
import java.util.List;
import java.util.stream.Collectors;
public class ScholixSummary implements Serializable {
private String id;
private List<TypedIdentifier> localIdentifier;
private Typology typology;
private List<String> title;
private List<String> author;
private List<String> date;
private String description;
private List<SchemeValue> subject;
private List<String> publisher;
private int relatedPublications;
private int relatedDatasets;
private int relatedUnknown;
private List<CollectedFromType> datasources;
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public List<TypedIdentifier> getLocalIdentifier() {
return localIdentifier;
}
public void setLocalIdentifier(List<TypedIdentifier> localIdentifier) {
this.localIdentifier = localIdentifier;
}
public Typology getTypology() {
return typology;
}
public void setTypology(Typology typology) {
this.typology = typology;
}
public List<String> getTitle() {
return title;
}
public void setTitle(List<String> title) {
this.title = title;
}
public List<String> getAuthor() {
return author;
}
public void setAuthor(List<String> author) {
this.author = author;
}
public List<String> getDate() {
return date;
}
public void setDate(List<String> date) {
this.date = date;
}
@JsonProperty("abstract")
public String getDescription() {
return description;
}
@JsonProperty("abstract")
public void setDescription(String description) {
this.description = description;
}
public List<SchemeValue> getSubject() {
return subject;
}
public void setSubject(List<SchemeValue> subject) {
this.subject = subject;
}
public List<String> getPublisher() {
return publisher;
}
public void setPublisher(List<String> publisher) {
this.publisher = publisher;
}
public int getRelatedPublications() {
return relatedPublications;
}
public void setRelatedPublications(int relatedPublications) {
this.relatedPublications = relatedPublications;
}
public int getRelatedDatasets() {
return relatedDatasets;
}
public void setRelatedDatasets(int relatedDatasets) {
this.relatedDatasets = relatedDatasets;
}
public int getRelatedUnknown() {
return relatedUnknown;
}
public void setRelatedUnknown(int relatedUnknown) {
this.relatedUnknown = relatedUnknown;
}
public List<CollectedFromType> getDatasources() {
return datasources;
}
public void setDatasources(List<CollectedFromType> datasources) {
this.datasources = datasources;
}
public static String fromJsonOAF(final Typology oafType, final String oafJson, final String relEntityJson) {
try {
final ObjectMapper mapper = new ObjectMapper();
mapper.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
RelatedItemInfo relatedItemInfo = mapper.readValue(relEntityJson, RelatedItemInfo.class);
switch (oafType) {
case dataset:
return mapper.writeValueAsString(summaryFromDataset(mapper.readValue(oafJson, DLIDataset.class), relatedItemInfo));
case publication:
return mapper.writeValueAsString(summaryFromPublication(mapper.readValue(oafJson, DLIPublication.class), relatedItemInfo));
case unknown:
return mapper.writeValueAsString(summaryFromUnknown(mapper.readValue(oafJson, DLIUnknown.class), relatedItemInfo));
}
} catch (Throwable e) {
throw new RuntimeException(e);
}
return null;
}
private static ScholixSummary summaryFromDataset(final DLIDataset item, final RelatedItemInfo relatedItemInfo) {
ScholixSummary summary = new ScholixSummary();
summary.setId(item.getId());
if (item.getPid() != null)
summary.setLocalIdentifier(item.getPid().stream()
.map(p -> new TypedIdentifier(p.getValue(), p.getQualifier().getClassid()))
.collect(Collectors.toList())
);
summary.setTypology(Typology.dataset);
if (item.getTitle() != null)
summary.setTitle(item.getTitle().stream().map(StructuredProperty::getValue).collect(Collectors.toList()));
if (item.getAuthor() != null) {
summary.setAuthor(item.getAuthor().stream().map(Author::getFullname).collect(Collectors.toList()));
}
if (item.getRelevantdate() != null)
summary.setDate(
item.getRelevantdate().stream()
.filter(d -> "date".equalsIgnoreCase(d.getQualifier().getClassname()))
.map(StructuredProperty::getValue)
.collect(Collectors.toList())
);
if (item.getDescription() != null && item.getDescription().size() > 0)
summary.setDescription(item.getDescription().get(0).getValue());
if (item.getSubject() != null) {
summary.setSubject(item.getSubject().stream()
.map(s -> new SchemeValue(s.getQualifier().getClassid(), s.getValue()))
.collect(Collectors.toList())
);
}
summary.setRelatedDatasets(relatedItemInfo.getRelatedDataset());
summary.setRelatedPublications(relatedItemInfo.getRelatedPublication());
summary.setRelatedUnknown(relatedItemInfo.getRelatedUnknown());
if (item.getDlicollectedfrom() != null)
summary.setDatasources(item.getDlicollectedfrom().stream()
.map(
c -> new CollectedFromType(c.getName(), c.getId(), c.getCompletionStatus())
).collect(Collectors.toList()));
return summary;
}
private static ScholixSummary summaryFromPublication(final DLIPublication item, final RelatedItemInfo relatedItemInfo) {
ScholixSummary summary = new ScholixSummary();
summary.setId(item.getId());
if (item.getPid() != null)
summary.setLocalIdentifier(item.getPid().stream()
.map(p -> new TypedIdentifier(p.getValue(), p.getQualifier().getClassid()))
.collect(Collectors.toList())
);
summary.setTypology(Typology.dataset);
if (item.getTitle() != null)
summary.setTitle(item.getTitle().stream().map(StructuredProperty::getValue).collect(Collectors.toList()));
if (item.getAuthor() != null) {
summary.setAuthor(item.getAuthor().stream().map(Author::getFullname).collect(Collectors.toList()));
}
if (item.getRelevantdate() != null)
summary.setDate(
item.getRelevantdate().stream()
.filter(d -> "date".equalsIgnoreCase(d.getQualifier().getClassname()))
.map(StructuredProperty::getValue)
.collect(Collectors.toList())
);
if (item.getDescription() != null && item.getDescription().size() > 0)
summary.setDescription(item.getDescription().get(0).getValue());
if (item.getSubject() != null) {
summary.setSubject(item.getSubject().stream()
.map(s -> new SchemeValue(s.getQualifier().getClassid(), s.getValue()))
.collect(Collectors.toList())
);
}
summary.setRelatedDatasets(relatedItemInfo.getRelatedDataset());
summary.setRelatedPublications(relatedItemInfo.getRelatedPublication());
summary.setRelatedUnknown(relatedItemInfo.getRelatedUnknown());
if (item.getDlicollectedfrom() != null)
summary.setDatasources(item.getDlicollectedfrom().stream()
.map(
c -> new CollectedFromType(c.getName(), c.getId(), c.getCompletionStatus())
).collect(Collectors.toList()));
return summary;
}
private static ScholixSummary summaryFromUnknown(final DLIUnknown item, final RelatedItemInfo relatedItemInfo) {
ScholixSummary summary = new ScholixSummary();
summary.setId(item.getId());
if (item.getPid() != null)
summary.setLocalIdentifier(item.getPid().stream()
.map(p -> new TypedIdentifier(p.getValue(), p.getQualifier().getClassid()))
.collect(Collectors.toList())
);
summary.setRelatedDatasets(relatedItemInfo.getRelatedDataset());
summary.setRelatedPublications(relatedItemInfo.getRelatedPublication());
summary.setRelatedUnknown(relatedItemInfo.getRelatedUnknown());
if (item.getDlicollectedfrom() != null)
summary.setDatasources(item.getDlicollectedfrom().stream()
.map(
c -> new CollectedFromType(c.getName(), c.getId(), c.getCompletionStatus())
).collect(Collectors.toList()));
return summary;
}
}

View File

@ -0,0 +1,32 @@
package eu.dnetlib.dhp.provision.scholix;
import java.io.Serializable;
public class TypedIdentifier implements Serializable {
private String id;
private String type;
public TypedIdentifier() {
}
public TypedIdentifier(String id, String type) {
this.id = id;
this.type = type;
}
public String getId() {
return id;
}
public void setId(String id) {
this.id = id;
}
public String getType() {
return type;
}
public void setType(String type) {
this.type = type;
}
}

View File

@ -0,0 +1,9 @@
package eu.dnetlib.dhp.provision.scholix;
import java.io.Serializable;
public enum Typology implements Serializable {
dataset,
publication,
unknown
}

View File

@ -0,0 +1,10 @@
<configuration>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
</configuration>

View File

@ -0,0 +1,100 @@
<workflow-app name="import_infospace_graph" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>workingDirPath</name>
<description>the source path</description>
</property>
<property>
<name>graphPath</name>
<description>the graph path</description>
</property>
<property>
<name>index</name>
<description>index name</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>
</parameters>
<start to="indexSummary"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="DeleteTargetPath">
<fs>
<delete path='${workingDirPath}'/>
<mkdir path='${workingDirPath}'/>
</fs>
<ok to="CalculateRelatedItem"/>
<error to="Kill"/>
</action>
<action name="CalculateRelatedItem">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>calculate for each ID the number of related Dataset, publication and Unknown</name>
<class>eu.dnetlib.dhp.provision.SparkExtractRelationCount</class>
<jar>dhp-graph-provision-${projectVersion}.jar</jar>
<spark-opts>--executor-memory ${sparkExecutorMemory} --driver-memory=${sparkDriverMemory} ${sparkExtraOPT}</spark-opts>
<arg>-mt</arg> <arg>yarn-cluster</arg>
<arg>--workingDirPath</arg><arg>${workingDirPath}</arg>
<arg>--relationPath</arg><arg>${graphPath}/relation</arg>
</spark>
<ok to="generateSummary"/>
<error to="Kill"/>
</action>
<action name="generateSummary">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>generate Summary</name>
<class>eu.dnetlib.dhp.provision.SparkGenerateSummary</class>
<jar>dhp-graph-provision-${projectVersion}.jar</jar>
<spark-opts>--executor-memory ${sparkExecutorMemory} --driver-memory=${sparkDriverMemory} ${sparkExtraOPT}</spark-opts>
<arg>-mt</arg> <arg>yarn-cluster</arg>
<arg>--workingDirPath</arg><arg>${workingDirPath}</arg>
<arg>--graphPath</arg><arg>${graphPath}</arg>
</spark>
<ok to="indexSummary"/>
<error to="Kill"/>
</action>
<action name="indexSummary">
<spark xmlns="uri:oozie:spark-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>generate Summary</name>
<class>eu.dnetlib.dhp.provision.SparkIndexCollectionOnES</class>
<jar>dhp-graph-provision-${projectVersion}.jar</jar>
<spark-opts>--executor-memory ${sparkExecutorMemory} --num-executors 20 --driver-memory=${sparkDriverMemory} ${sparkExtraOPT} </spark-opts>
<arg>-mt</arg> <arg>yarn-cluster</arg>
<arg>--sourcePath</arg><arg>${workingDirPath}/summary</arg>
<arg>--index</arg><arg>${index}_object</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -0,0 +1,20 @@
[
{
"paramName": "mt",
"paramLongName": "master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName": "s",
"paramLongName": "sourcePath",
"paramDescription": "the working path where generated files",
"paramRequired": true
},
{
"paramName": "i",
"paramLongName": "index",
"paramDescription": "the index name",
"paramRequired": true
}
]

View File

@ -0,0 +1,20 @@
[
{
"paramName": "mt",
"paramLongName": "master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName": "w",
"paramLongName": "workingDirPath",
"paramDescription": "the working path where generated files",
"paramRequired": true
},
{
"paramName": "g",
"paramLongName": "graphPath",
"paramDescription": "the relationPath path ",
"paramRequired": true
}
]

View File

@ -0,0 +1,20 @@
[
{
"paramName": "mt",
"paramLongName": "master",
"paramDescription": "should be local or yarn",
"paramRequired": true
},
{
"paramName": "w",
"paramLongName": "workingDirPath",
"paramDescription": "the working path where generated files",
"paramRequired": true
},
{
"paramName": "r",
"paramLongName": "relationPath",
"paramDescription": "the relationPath path ",
"paramRequired": true
}
]

View File

@ -0,0 +1,48 @@
package eu.dnetlib.dhp.provision;
import com.fasterxml.jackson.core.JsonProcessingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.provision.scholix.ScholixSummary;
import org.apache.commons.io.IOUtils;
import org.junit.Ignore;
import org.junit.Test;
public class ExtractInfoTest {
@Test
public void test() throws Exception {
final String json = IOUtils.toString(getClass().getResourceAsStream("record.json"));
ProvisionUtil.getItemType(json,ProvisionUtil.TARGETJSONPATH);
}
@Test
public void testSerialization() throws Exception {
ScholixSummary summary = new ScholixSummary();
summary.setDescription("descrizione");
ObjectMapper mapper = new ObjectMapper();
String json = mapper.writeValueAsString(summary);
System.out.println(json);
System.out.println(mapper.readValue(json, ScholixSummary.class).getDescription());
}
@Test
@Ignore
public void testIndex() throws Exception {
SparkIndexCollectionOnES.main(
new String[] {
"-mt", "local[*]",
"-s", "/home/sandro/dli",
"-i", "dli_object"
}
);
}
}

View File

@ -0,0 +1 @@
{"dataInfo":{"invisible":false,"inferred":null,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":null},"lastupdatetimestamp":null,"relType":"references","subRelType":null,"relClass":"datacite","source":"50|f2123fce7e56c73dc8f1bf64ec59b477","target":"50|b618cbe39ba940a29993ac324e5f9621","collectedFrom":[{"key":"dli_________::datacite","value":"Datasets in Datacite","dataInfo":null}]}

View File

@ -18,6 +18,7 @@
<module>dhp-distcp</module> <module>dhp-distcp</module>
<module>dhp-graph-mapper</module> <module>dhp-graph-mapper</module>
<module>dhp-dedup</module> <module>dhp-dedup</module>
<module>dhp-graph-provision</module>
</modules> </modules>
<pluginRepositories> <pluginRepositories>

View File

@ -243,6 +243,14 @@
<version>${vtd.version}</version> <version>${vtd.version}</version>
</dependency> </dependency>
<dependency>
<groupId>org.elasticsearch</groupId>
<artifactId>elasticsearch-hadoop</artifactId>
<version>7.6.0</version>
</dependency>
<dependency> <dependency>
<groupId>org.apache.oozie</groupId> <groupId>org.apache.oozie</groupId>
<artifactId>oozie-client</artifactId> <artifactId>oozie-client</artifactId>