forked from D-Net/dnet-hadoop
Compare commits
9 Commits
3c3e3537e0
...
e0ca4cead0
| Author | SHA1 | Date |
|---|---|---|
 Miriam Baglioni
|
e0ca4cead0 | |
|
Miriam Baglioni
|
f5ecd0d3ab | |
|
Miriam Baglioni
|
85bd6ab5d0 | |
|
Miriam Baglioni
|
b8f25fbf39 | |
|
Miriam Baglioni
|
c6cadacd24 | |
|
Miriam Baglioni
|
25c5dd744f | |
|
Miriam Baglioni
|
e902699afa | |
|
Miriam Baglioni
|
bcbadeb107 | |
|
Miriam Baglioni
|
952d6dc2fb |
|
|
@ -17,7 +17,7 @@ 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() = 'all') "
|
||||
|
|
@ -28,9 +28,22 @@ 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 community_id)
|
||||
throws ISLookUpException, DocumentException {
|
||||
return getMap(isLookUp.quickSearchProfile(XQUERY));
|
||||
if (singleCommunity)
|
||||
return getMap(isLookUp.quickSearchProfile(XQUERY_CI.replace("%s", "'" + community_id + "'")));
|
||||
return getMap(isLookUp.quickSearchProfile(XQUERY_ALL));
|
||||
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -6,6 +6,7 @@ import java.io.IOException;
|
|||
import java.io.OutputStreamWriter;
|
||||
import java.io.Serializable;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.Optional;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
|
|
@ -71,14 +72,25 @@ public class SaveCommunityMap implements Serializable {
|
|||
final String isLookUpUrl = parser.get("isLookUpUrl");
|
||||
log.info("isLookUpUrl: {}", isLookUpUrl);
|
||||
|
||||
final Boolean singleCommunity = Optional
|
||||
.ofNullable(parser.get("singleDeposition"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(false);
|
||||
|
||||
final String community_id = Optional.ofNullable(parser.get("communityId")).orElse(null);
|
||||
|
||||
final SaveCommunityMap scm = new SaveCommunityMap(outputPath, nameNode, isLookUpUrl);
|
||||
|
||||
scm.saveCommunityMap();
|
||||
scm.saveCommunityMap(singleCommunity, community_id);
|
||||
|
||||
}
|
||||
|
||||
private void saveCommunityMap() throws ISLookUpException, IOException, DocumentException {
|
||||
writer.write(Utils.OBJECT_MAPPER.writeValueAsString(queryInformationSystem.getCommunityMap()));
|
||||
private void saveCommunityMap(boolean singleCommunity, String community_id)
|
||||
throws ISLookUpException, IOException, DocumentException {
|
||||
writer
|
||||
.write(
|
||||
Utils.OBJECT_MAPPER
|
||||
.writeValueAsString(queryInformationSystem.getCommunityMap(singleCommunity, community_id)));
|
||||
writer.close();
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,85 +0,0 @@
|
|||
|
||||
package eu.dnetlib.dhp.oa.graph.dump.community;
|
||||
|
||||
import java.io.*;
|
||||
import java.nio.charset.StandardCharsets;
|
||||
import java.util.Objects;
|
||||
import java.util.Set;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FSDataInputStream;
|
||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
|
||||
public class RemoveCommunities implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(RemoveCommunities.class);
|
||||
private final static ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
private final Configuration conf;
|
||||
private final BufferedWriter writer;
|
||||
private final CommunityMap communityMap;
|
||||
|
||||
public RemoveCommunities(String path, String hdfsNameNode) throws IOException {
|
||||
conf = new Configuration();
|
||||
conf.set("fs.defaultFS", hdfsNameNode);
|
||||
FileSystem fileSystem = FileSystem.get(conf);
|
||||
Path hdfsPath = new Path(path);
|
||||
// FSDataInputStream p = fileSystem.open(hdfsPath);
|
||||
// ObjectMapper mapper = new ObjectMapper();
|
||||
communityMap = OBJECT_MAPPER.readValue((InputStream) fileSystem.open(hdfsPath), CommunityMap.class);
|
||||
FSDataOutputStream fsDataOutputStream = null;
|
||||
if (fileSystem.exists(hdfsPath)) {
|
||||
fileSystem.delete(hdfsPath);
|
||||
}
|
||||
fsDataOutputStream = fileSystem.create(hdfsPath);
|
||||
|
||||
writer = new BufferedWriter(new OutputStreamWriter(fsDataOutputStream, StandardCharsets.UTF_8));
|
||||
|
||||
}
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
RemoveCommunities.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/oa/graph/dump/input_rc_parameters.json"));
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
parser.parseArgument(args);
|
||||
|
||||
final String nameNode = parser.get("nameNode");
|
||||
log.info("nameNode: {}", nameNode);
|
||||
|
||||
final String outputPath = parser.get("path");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
final String communityId = parser.get("communityId");
|
||||
|
||||
final RemoveCommunities scm = new RemoveCommunities(outputPath, nameNode);
|
||||
|
||||
scm.removeCommunities(communityId);
|
||||
|
||||
}
|
||||
|
||||
private void removeCommunities(String communityId) throws IOException {
|
||||
Set<String> toRemove = communityMap.keySet().stream().map(key -> {
|
||||
if (key.equals(communityId))
|
||||
return null;
|
||||
return key;
|
||||
}).filter(Objects::nonNull).collect(Collectors.toSet());
|
||||
|
||||
toRemove.forEach(key -> communityMap.remove(key));
|
||||
writer.write(OBJECT_MAPPER.writeValueAsString(communityMap));
|
||||
writer.close();
|
||||
}
|
||||
|
||||
}
|
||||
|
|
@ -54,8 +54,8 @@ public class SparkDumpFunderResults implements Serializable {
|
|||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
final String relationPath = parser.get("relationPath");
|
||||
log.info("relationPath: {}", relationPath);
|
||||
final String graphPath = parser.get("graphPath");
|
||||
log.info("relationPath: {}", graphPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
|
||||
|
|
@ -64,18 +64,18 @@ public class SparkDumpFunderResults implements Serializable {
|
|||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
Utils.removeOutputDir(spark, outputPath);
|
||||
writeResultProjectList(spark, inputPath, outputPath, relationPath);
|
||||
writeResultProjectList(spark, inputPath, outputPath, graphPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static void writeResultProjectList(SparkSession spark, String inputPath, String outputPath,
|
||||
String relationPath) {
|
||||
String graphPath) {
|
||||
|
||||
Dataset<Relation> relation = Utils
|
||||
.readPath(spark, relationPath + "/relation", Relation.class)
|
||||
.filter(
|
||||
"dataInfo.deletedbyinference = false and lower(relClass) = '"
|
||||
+ ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
|
||||
Dataset<eu.dnetlib.dhp.schema.oaf.Project> project = Utils
|
||||
.readPath(spark, graphPath + "/project", eu.dnetlib.dhp.schema.oaf.Project.class);
|
||||
// .filter(
|
||||
// "dataInfo.deletedbyinference = false and lower(relClass) = '"
|
||||
// + ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
|
||||
|
||||
Dataset<CommunityResult> result = Utils
|
||||
.readPath(spark, inputPath + "/publication", CommunityResult.class)
|
||||
|
|
@ -83,8 +83,14 @@ public class SparkDumpFunderResults implements Serializable {
|
|||
.union(Utils.readPath(spark, inputPath + "/orp", CommunityResult.class))
|
||||
.union(Utils.readPath(spark, inputPath + "/software", CommunityResult.class));
|
||||
|
||||
List<String> funderList = relation
|
||||
.select("target")
|
||||
// List<String> funderList = relation
|
||||
// .select("target")
|
||||
// .map((MapFunction<Row, String>) value -> value.getString(0).substring(0, 15), Encoders.STRING())
|
||||
// .distinct()
|
||||
// .collectAsList();
|
||||
|
||||
List<String> funderList = project
|
||||
.select("id")
|
||||
.map((MapFunction<Row, String>) value -> value.getString(0).substring(0, 15), Encoders.STRING())
|
||||
.distinct()
|
||||
.collectAsList();
|
||||
|
|
|
|||
|
|
@ -10,10 +10,7 @@ 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.Dataset;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.SaveMode;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.apache.spark.sql.*;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
|
|
@ -21,6 +18,7 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
|||
import eu.dnetlib.dhp.oa.graph.dump.Constants;
|
||||
import eu.dnetlib.dhp.oa.graph.dump.Utils;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Project;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
import scala.Tuple2;
|
||||
|
|
@ -59,8 +57,8 @@ public class SparkResultLinkedToProject implements Serializable {
|
|||
final String resultClassName = parser.get("resultTableName");
|
||||
log.info("resultTableName: {}", resultClassName);
|
||||
|
||||
final String relationPath = parser.get("relationPath");
|
||||
log.info("relationPath: {}", relationPath);
|
||||
final String graphPath = parser.get("graphPath");
|
||||
log.info("graphPath: {}", graphPath);
|
||||
|
||||
Class<? extends Result> inputClazz = (Class<? extends Result>) Class.forName(resultClassName);
|
||||
SparkConf conf = new SparkConf();
|
||||
|
|
@ -70,34 +68,58 @@ public class SparkResultLinkedToProject implements Serializable {
|
|||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
Utils.removeOutputDir(spark, outputPath);
|
||||
writeResultsLinkedToProjects(spark, inputClazz, inputPath, outputPath, relationPath);
|
||||
writeResultsLinkedToProjects(spark, inputClazz, inputPath, outputPath, graphPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static <R extends Result> void writeResultsLinkedToProjects(SparkSession spark, Class<R> inputClazz,
|
||||
String inputPath, String outputPath, String relationPath) {
|
||||
String inputPath, String outputPath, String graphPath) {
|
||||
|
||||
Dataset<R> results = Utils
|
||||
.readPath(spark, inputPath, inputClazz)
|
||||
.filter("dataInfo.deletedbyinference = false and datainfo.invisible = false");
|
||||
Dataset<Relation> relations = Utils
|
||||
.readPath(spark, relationPath, Relation.class)
|
||||
.readPath(spark, graphPath + "/relation", Relation.class)
|
||||
.filter(
|
||||
"dataInfo.deletedbyinference = false and lower(relClass) = '"
|
||||
+ ModelConstants.IS_PRODUCED_BY.toLowerCase() + "'");
|
||||
Dataset<Project> project = Utils.readPath(spark, graphPath + "/project", Project.class);
|
||||
|
||||
relations
|
||||
.joinWith(
|
||||
results, relations.col("source").equalTo(results.col("id")),
|
||||
"inner")
|
||||
.groupByKey(
|
||||
(MapFunction<Tuple2<Relation, R>, String>) value -> value
|
||||
._2()
|
||||
results.createOrReplaceTempView("result");
|
||||
relations.createOrReplaceTempView("relation");
|
||||
project.createOrReplaceTempView("project");
|
||||
|
||||
Dataset<R> tmp = spark
|
||||
.sql(
|
||||
"Select res.* " +
|
||||
"from relation rel " +
|
||||
"join result res " +
|
||||
"on rel.source = res.id " +
|
||||
"join project p " +
|
||||
"on rel.target = p.id " +
|
||||
"")
|
||||
.as(Encoders.bean(inputClazz))
|
||||
;
|
||||
tmp.groupByKey(
|
||||
(MapFunction< R, String>) value -> value
|
||||
.getId(),
|
||||
Encoders.STRING())
|
||||
.mapGroups((MapGroupsFunction<String, Tuple2<Relation, R>, R>) (k, it) -> {
|
||||
return it.next()._2();
|
||||
}, Encoders.bean(inputClazz))
|
||||
.mapGroups((MapGroupsFunction<String, R, R>) (k, it) -> it.next(), Encoders.bean(inputClazz))
|
||||
|
||||
//
|
||||
// relations
|
||||
// .joinWith(
|
||||
// results, relations.col("source").equalTo(results.col("id")),
|
||||
// "inner")
|
||||
// .groupByKey(
|
||||
// (MapFunction<Tuple2<Relation, R>, String>) value -> value
|
||||
// ._2()
|
||||
// .getId(),
|
||||
// Encoders.STRING())
|
||||
// .mapGroups((MapGroupsFunction<String, Tuple2<Relation, R>, R>) (k, it) -> {
|
||||
// return it.next()._2();
|
||||
// }, Encoders.bean(inputClazz))
|
||||
//tmp
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
|
|
|
|||
|
|
@ -134,29 +134,14 @@
|
|||
<arg>--outputPath</arg><arg>${workingDir}/communityMap</arg>
|
||||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
|
||||
</java>
|
||||
<ok to="single_deposition"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<decision name="single_deposition">
|
||||
<switch>
|
||||
<case to="remove_communities">${wf:conf('singleDeposition') eq true}</case>
|
||||
<default to="fork_dump"/>
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<action name="remove_communities">
|
||||
<java>
|
||||
<main-class>eu.dnetlib.dhp.oa.graph.dump.community.RemoveCommunities</main-class>
|
||||
<arg>--path</arg><arg>${workingDir}/communityMap</arg>
|
||||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--singleDeposition</arg><arg>${singleDeposition}</arg>
|
||||
<arg>--communityId</arg><arg>${communityId}</arg>
|
||||
</java>
|
||||
<ok to="fork_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<fork name="fork_dump">
|
||||
<path start="dump_publication"/>
|
||||
<path start="dump_dataset"/>
|
||||
|
|
|
|||
|
|
@ -0,0 +1,495 @@
|
|||
{
|
||||
"$schema": "http://json-schema.org/draft-07/schema#",
|
||||
"definitions": {
|
||||
"AccessRight": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "COAR access mode code: http://vocabularies.coar-repositories.org/documentation/access_rights/"
|
||||
},
|
||||
"label": {
|
||||
"type": "string",
|
||||
"description": "Label for the access mode"
|
||||
},
|
||||
"scheme": {
|
||||
"type": "string",
|
||||
"description": "Scheme of reference for access right code. Always set to COAR access rights vocabulary: http://vocabularies.coar-repositories.org/documentation/access_rights/"
|
||||
}
|
||||
}
|
||||
},
|
||||
"ControlledField": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"scheme": {
|
||||
"type": "string",
|
||||
"description": "The scheme for the resource"
|
||||
},
|
||||
"value": {
|
||||
"type": "string",
|
||||
"description": "the value in the scheme"
|
||||
}
|
||||
}
|
||||
},
|
||||
"KeyValue": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"key": {
|
||||
"type": "string",
|
||||
"description": "Description of key"
|
||||
},
|
||||
"value": {
|
||||
"type": "string",
|
||||
"description": "Description of value"
|
||||
}
|
||||
}
|
||||
},
|
||||
"Provenance": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"provenance": {
|
||||
"type": "string",
|
||||
"description": "The provenance of the information"
|
||||
},
|
||||
"trust": {
|
||||
"type": "string",
|
||||
"description": "The trust associated to the information"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"author": {
|
||||
"description": "List of authors of the research results",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"affiliation": {
|
||||
"description": "Affiliations of the author",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string",
|
||||
"description": "One of the affiliation of the author"
|
||||
}
|
||||
},
|
||||
"fullname": {
|
||||
"type": "string",
|
||||
"description": "Fullname of the author"
|
||||
},
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "First name of the author"
|
||||
},
|
||||
"pid": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"id": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/ControlledField"},
|
||||
{"description": "The author's id and scheme. OpenAIRE currently supports 'ORCID'"}
|
||||
]
|
||||
},
|
||||
"provenance": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/Provenance"},
|
||||
{"description": "The provenance of the author's pid"}
|
||||
]
|
||||
}
|
||||
},
|
||||
"description": "Persistent identifier of the author (e.g. ORCID)"
|
||||
},
|
||||
"rank": {
|
||||
"type": "integer",
|
||||
"description": "Order in which the author appears in the authors list"
|
||||
},
|
||||
"surname": {
|
||||
"type": "string",
|
||||
"description": "Surname of the author"
|
||||
}
|
||||
},
|
||||
"description": "One of the author of the research result"
|
||||
}
|
||||
},
|
||||
"bestaccessright": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/AccessRight"},
|
||||
{"description": "The openest access right associated to the manifestations of this research results"}
|
||||
]
|
||||
},
|
||||
"codeRepositoryUrl": {
|
||||
"type": "string",
|
||||
"description": "Only for results with type 'software': the URL to the repository with the source code"
|
||||
},
|
||||
"collectedfrom": {
|
||||
"description": "Information about the sources from which the record has been collected",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/KeyValue"},
|
||||
{"description": "Key is the OpenAIRE identifier of the data source, value is its name"}
|
||||
]
|
||||
}
|
||||
},
|
||||
"contactgroup": {
|
||||
"description": "Only for results with type 'software': Information on the group responsible for providing further information regarding the resource",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"contactperson": {
|
||||
"description": "Only for results with type 'software': Information on the person responsible for providing further information regarding the resource",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"container": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"conferencedate": {
|
||||
"type": "string",
|
||||
"description": "Date of the conference"
|
||||
},
|
||||
"conferenceplace": {
|
||||
"type": "string",
|
||||
"description": "Place of the conference"
|
||||
},
|
||||
"edition": {
|
||||
"type": "string",
|
||||
"description": "Edition of the journal or conference proceeding"
|
||||
},
|
||||
"ep": {
|
||||
"type": "string",
|
||||
"description": "End page"
|
||||
},
|
||||
"iss": {
|
||||
"type": "string",
|
||||
"description": "Journal issue"
|
||||
},
|
||||
"issnLinking": {
|
||||
"type": "string",
|
||||
"description": "Journal linking iisn"
|
||||
},
|
||||
"issnOnline": {
|
||||
"type": "string",
|
||||
"description": "Journal online issn"
|
||||
},
|
||||
"issnPrinted": {
|
||||
"type": "string",
|
||||
"description": "Journal printed issn"
|
||||
},
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "Name of the journal or conference"
|
||||
},
|
||||
"sp": {
|
||||
"type": "string",
|
||||
"description": "Start page"
|
||||
},
|
||||
"vol": {
|
||||
"type": "string",
|
||||
"description": "Volume"
|
||||
}
|
||||
},
|
||||
"description": "Container has information about the conference or journal where the result has been presented or published"
|
||||
},
|
||||
"context": {
|
||||
"description": "Reference to a relevant research infrastructure, initiative or community (RI/RC) among those collaborating with OpenAIRE. Please see https://connect.openaire.eu",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "Code identifying the RI/RC"
|
||||
},
|
||||
"label": {
|
||||
"type": "string",
|
||||
"description": "Label of the RI/RC"
|
||||
},
|
||||
"provenance": {
|
||||
"description": "Why this result is associated to the RI/RC.",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/Provenance"}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"contributor": {
|
||||
"description": "Contributors of this result",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"country": {
|
||||
"description": "Country associated to this result",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "ISO 3166-1 alpha-2 country code"
|
||||
},
|
||||
"label": {
|
||||
"type": "string",
|
||||
"description": "English label of the country"
|
||||
},
|
||||
"provenance": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/Provenance"},
|
||||
{"description": "Why this result is associated to the country."}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"coverage": {
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"dateofcollection": {
|
||||
"type": "string",
|
||||
"description": "When OpenAIRE collected the record the last time"
|
||||
},
|
||||
"description": {
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"documentationUrl": {
|
||||
"description": "Only for results with type 'software': URL to the software documentation",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"embargoenddate": {
|
||||
"type": "string",
|
||||
"description": "Date when the embargo ends and this result turns Open Access"
|
||||
},
|
||||
"format": {
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"geolocation": {
|
||||
"description": "Geolocation information",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"box": {"type": "string"},
|
||||
"place": {"type": "string"},
|
||||
"point": {"type": "string"}
|
||||
}
|
||||
}
|
||||
},
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "OpenAIRE identifier"
|
||||
},
|
||||
"instance": {
|
||||
"description": "Manifestations (i.e. different versions) of the result. For example: the pre-print and the published versions are two manifestations of the same research result",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"accessright": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/AccessRight"},
|
||||
{"description": "Access right of this instance"}
|
||||
]
|
||||
},
|
||||
"articleprocessingcharge": {
|
||||
"description": "The money spent to make this book or article available in Open Access. Source for this information is the OpenAPC initiative.",
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"amount": {"type": "string"},
|
||||
"currency": {"type": "string"}
|
||||
}
|
||||
},
|
||||
"collectedfrom": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/KeyValue"},
|
||||
{"description": "Information about the source from which the instance has been collected. Key is the OpenAIRE identifier of the data source, value is its name"}
|
||||
]
|
||||
},
|
||||
"hostedby": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/KeyValue"},
|
||||
{"description": "Information about the source from which the instance can be viewed or downloaded. Key is the OpenAIRE identifier of the data source, value is its name"}
|
||||
]
|
||||
},
|
||||
"license": {
|
||||
"type": "string",
|
||||
"description": "License applied to the instance"
|
||||
},
|
||||
"publicationdate": {
|
||||
"type": "string",
|
||||
"description": "Publication date of the instance"
|
||||
},
|
||||
"refereed": {
|
||||
"type": "string",
|
||||
"description": "Was the instance subject to peer-review? Possible values are 'Unknown', 'nonPeerReviewed', 'peerReviewed' (see also https://api.openaire.eu/vocabularies/dnet:review_levels)"
|
||||
},
|
||||
"type": {
|
||||
"type": "string",
|
||||
"description": "Type of the instance. Possible values are listed at https://api.openaire.eu/vocabularies/dnet:publication_resource"
|
||||
},
|
||||
"url": {
|
||||
"description": "Location where the instance is accessible",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"language": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "alpha-3/ISO 639-2 code of the language"
|
||||
},
|
||||
"label": {
|
||||
"type": "string",
|
||||
"description": "English label"
|
||||
}
|
||||
}
|
||||
},
|
||||
"lastupdatetimestamp": {
|
||||
"type": "integer",
|
||||
"description": "Timestamp of last update of the record in OpenAIRE"
|
||||
},
|
||||
"maintitle": {
|
||||
"type": "string",
|
||||
"description": "Title"
|
||||
},
|
||||
"originalId": {
|
||||
"description": "Identifiers of the record at the original sources",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"pid": {
|
||||
"description": "Persistent identifiers of the result",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/ControlledField"},
|
||||
{"description": "scheme: list of available schemes are at https://api.openaire.eu/vocabularies/dnet:pid_types, value: the PID of the result "}
|
||||
]
|
||||
}
|
||||
},
|
||||
"programmingLanguage": {
|
||||
"type": "string",
|
||||
"description": "Only for results with type 'software': the programming language"
|
||||
},
|
||||
"projects": {
|
||||
"description": "List of projects (i.e. grants) that (co-)funded the production ofn the research results",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"acronym": {
|
||||
"type": "string",
|
||||
"description": "Project acronym"
|
||||
},
|
||||
"code": {
|
||||
"type": "string",
|
||||
"description": "Grant code"
|
||||
},
|
||||
"funder": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"fundingStream": {
|
||||
"type": "string",
|
||||
"description": "Stream of funding (e.g. for European Commission can be H2020 or FP7)"
|
||||
},
|
||||
"jurisdiction": {
|
||||
"type": "string",
|
||||
"description": "Geographical jurisdiction (e.g. for European Commission is EU, for Croatian Science Foundation is HR)"
|
||||
},
|
||||
"name": {
|
||||
"type": "string",
|
||||
"description": "Name of the funder"
|
||||
},
|
||||
"shortName": {
|
||||
"type": "string",
|
||||
"description": "Short name or acronym of the funder"
|
||||
}
|
||||
},
|
||||
"description": "Information about the funder funding the project"
|
||||
},
|
||||
"id": {
|
||||
"type": "string",
|
||||
"description": "OpenAIRE identifier of the project"
|
||||
},
|
||||
"provenance": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/Provenance"},
|
||||
{"description": "Why this project is associated to the result"}
|
||||
]
|
||||
},
|
||||
"title": {
|
||||
"type": "string",
|
||||
"description": "Title of the project"
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"publicationdate": {
|
||||
"type": "string",
|
||||
"description": "Date of publication"
|
||||
},
|
||||
"publisher": {
|
||||
"type": "string",
|
||||
"description": "Publisher"
|
||||
},
|
||||
"size": {
|
||||
"type": "string",
|
||||
"description": "Only for results with type 'dataset': the declared size of the dataset"
|
||||
},
|
||||
"source": {
|
||||
"description": "See definition of Dublin Core field dc:source",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"subjects": {
|
||||
"description": "Keywords associated to the result",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"provenance": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/Provenance"},
|
||||
{"description": "Why this subject is associated to the result"}
|
||||
]
|
||||
},
|
||||
"subject": {
|
||||
"allOf": [
|
||||
{"$ref": "#/definitions/ControlledField"},
|
||||
{"description": "OpenAIRE subject classification scheme (https://api.openaire.eu/vocabularies/dnet:subject_classification_typologies) and value. When the scheme is 'keyword', it means that the subject is free-text (i.e. not a term from a controlled vocabulary). "}
|
||||
]
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"subtitle": {
|
||||
"type": "string",
|
||||
"description": "Sub-title of the result"
|
||||
},
|
||||
"tool": {
|
||||
"description": "Only for results with type 'other': tool useful for the interpretation and/or re-used of the research product",
|
||||
"type": "array",
|
||||
"items": {"type": "string"}
|
||||
},
|
||||
"type": {
|
||||
"type": "string",
|
||||
"description": "Type of the result: one of 'publication', 'dataset', 'software', 'other' (see also https://api.openaire.eu/vocabularies/dnet:result_typologies)"
|
||||
},
|
||||
"version": {
|
||||
"type": "string",
|
||||
"description": "Version of the result"
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -1,6 +1,10 @@
|
|||
<workflow-app name="dump_complete_graph" xmlns="uri:oozie:workflow:0.5">
|
||||
|
||||
<parameters>
|
||||
<property>
|
||||
<name>upload</name>
|
||||
<description>true if the dump should be upload in zenodo</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the source path</description>
|
||||
|
|
@ -584,9 +588,16 @@
|
|||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--sourcePath</arg><arg>${workingDir}/collect</arg>
|
||||
</java>
|
||||
<ok to="send_zenodo"/>
|
||||
<ok to="should_upload"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<decision name="should_upload">
|
||||
<switch>
|
||||
<case to="send_zenodo">${wf:conf('upload') eq true}</case>
|
||||
<default to="End"/>
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<action name="send_zenodo">
|
||||
<java>
|
||||
|
|
|
|||
|
|
@ -18,8 +18,8 @@
|
|||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "rp",
|
||||
"paramLongName": "relationPath",
|
||||
"paramName": "gp",
|
||||
"paramLongName": "graphPath",
|
||||
"paramDescription": "the relationPath",
|
||||
"paramRequired": true
|
||||
}
|
||||
|
|
|
|||
|
|
@ -162,7 +162,7 @@
|
|||
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/publication</arg>
|
||||
<arg>--relationPath</arg><arg>${sourcePath}/relation</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
|
|
@ -188,7 +188,7 @@
|
|||
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/dataset</arg>
|
||||
<arg>--relationPath</arg><arg>${sourcePath}/relation</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
|
|
@ -214,7 +214,7 @@
|
|||
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/otherresearchproduct</arg>
|
||||
<arg>--relationPath</arg><arg>${sourcePath}/relation</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
|
|
@ -240,7 +240,7 @@
|
|||
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/software</arg>
|
||||
<arg>--relationPath</arg><arg>${sourcePath}/relation</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
|
|
@ -516,7 +516,7 @@
|
|||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${workingDir}/ext</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/resultperfunder</arg>
|
||||
<arg>--relationPath</arg><arg>${sourcePath}</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="make_archive"/>
|
||||
<error to="Kill"/>
|
||||
|
|
|
|||
|
|
@ -18,6 +18,18 @@
|
|||
"paramLongName": "outputPath",
|
||||
"paramDescription": "the path used to store temporary output files",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "sd",
|
||||
"paramLongName": "singleDeposition",
|
||||
"paramDescription": "true if the dump should be created for a single community",
|
||||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "ci",
|
||||
"paramLongName": "communityId",
|
||||
"paramDescription": "the id of the community for which to create the dump",
|
||||
"paramRequired": false
|
||||
}
|
||||
]
|
||||
|
||||
|
|
|
|||
|
|
@ -24,9 +24,9 @@
|
|||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName":"rp",
|
||||
"paramLongName":"relationPath",
|
||||
"paramDescription": "the path to the relations",
|
||||
"paramName":"gp",
|
||||
"paramLongName":"graphPath",
|
||||
"paramDescription": "the path to the graph",
|
||||
"paramRequired": true
|
||||
}
|
||||
]
|
||||
|
|
|
|||
|
|
@ -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>
|
||||
|
|
@ -0,0 +1,4 @@
|
|||
## This is a classpath-based import file (this header is required)
|
||||
dump_complete classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/complete/oozie_app
|
||||
dump_funder classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/funder/oozie_app
|
||||
dump_community classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/community/oozie_app
|
||||
|
|
@ -0,0 +1,306 @@
|
|||
<workflow-app name="dump_graph" xmlns="uri:oozie:workflow:0.5">
|
||||
|
||||
<parameters>
|
||||
<property>
|
||||
<name>singleDeposition</name>
|
||||
<description>Indicates if it is a single community deposition</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>communityId</name>
|
||||
<description>the id of the community to be dumped if a dump for a single community should be done</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>dumpType</name>
|
||||
<description>the type of the dump one of {complete, community, funder}</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>onlyUpload</name>
|
||||
<description>true if the dump is already done and should only be upload in zenodo</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>upload</name>
|
||||
<description>true if the dump should be upload in zenodo</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the source path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>isLookUpUrl</name>
|
||||
<description>the isLookup service endpoint</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the output path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>resultAggregation</name>
|
||||
<description>true if all the result type have to be dumped under result. false otherwise</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>accessToken</name>
|
||||
<description>the access token used for the deposition in Zenodo</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>connectionUrl</name>
|
||||
<description>the connection url for Zenodo</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>metadata</name>
|
||||
<description> the metadata associated to the deposition</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>depositionType</name>
|
||||
<description>the type of deposition we want to perform. "new" for brand new deposition, "version" for a new version of a published deposition (in this case the concept record id must be provided), "upload" to upload content to an open deposition for which we already have the deposition id (in this case the deposition id should be provided)</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>conceptRecordId</name>
|
||||
<description>for new version, the id of the record for the old deposition</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>depositionId</name>
|
||||
<description>the depositionId of a deposition open that has to be added content</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>organizationCommunityMap</name>
|
||||
<description>the organization community map</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>hiveDbName</name>
|
||||
<description>the target hive database name</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveJdbcUrl</name>
|
||||
<description>hive server jdbc url</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveMetastoreUris</name>
|
||||
<description>hive server metastore URIs</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>${oozieActionShareLibForSpark2}</value>
|
||||
</property>
|
||||
|
||||
</configuration>
|
||||
</global>
|
||||
|
||||
<start to="only_upload"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<decision name="only_upload">
|
||||
<switch>
|
||||
<case to="send_zenodo">${wf:conf('onlyUpload') eq true}</case>
|
||||
<default to="reset_outputpath"/>
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<action name="reset_outputpath">
|
||||
<fs>
|
||||
<delete path="${outputPath}"/>
|
||||
<mkdir path="${outputPath}"/>
|
||||
</fs>
|
||||
<ok to="save_community_map"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="save_community_map">
|
||||
<java>
|
||||
<main-class>eu.dnetlib.dhp.oa.graph.dump.SaveCommunityMap</main-class>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/communityMap</arg>
|
||||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
|
||||
<arg>--singleDeposition</arg><arg>${singleDeposition}</arg>
|
||||
<arg>--communityId</arg><arg>${communityId}</arg>
|
||||
</java>
|
||||
<ok to="choose_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<decision name="choose_dump">
|
||||
<switch>
|
||||
<case to="dump_funder">${wf:conf('dumpType') eq "funder"}</case>
|
||||
<case to="dump_community">${wf:conf('dumpType') eq "community"}</case>
|
||||
<default to="dump_complete"/>
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<!-- Sub-workflow which runs the dump for the complete graph -->
|
||||
<action name="dump_complete">
|
||||
<sub-workflow>
|
||||
<app-path>${wf:appPath()}/dump_complete
|
||||
</app-path>
|
||||
<propagate-configuration/>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>communityMapPath</name>
|
||||
<value>${workingDir}/communityMap</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<value>${workingDir}/tar</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<value>${sourcePath}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>organizationCommunityMap</name>
|
||||
<value>${organizationCommunityMap}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>isLookUpUrl</name>
|
||||
<value>${isLookUpUrl}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>resultAggregation</name>
|
||||
<value>${resultAggregation}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</sub-workflow>
|
||||
<ok to="make_archive" />
|
||||
<error to="Kill" />
|
||||
</action>
|
||||
|
||||
<!-- Sub-workflow which runs the dump for the complete graph -->
|
||||
<action name="dump_community">
|
||||
<sub-workflow>
|
||||
<app-path>${wf:appPath()}/dump_community
|
||||
</app-path>
|
||||
<propagate-configuration/>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<value>${sourcePath}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>communityMapPath</name>
|
||||
<value>${workingDir}/communityMap</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<value>${workingDir}/tar</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</sub-workflow>
|
||||
<ok to="make_archive" />
|
||||
<error to="Kill" />
|
||||
</action>
|
||||
|
||||
<action name="dump_funder">
|
||||
<sub-workflow>
|
||||
<app-path>${wf:appPath()}/dump_funder
|
||||
</app-path>
|
||||
<propagate-configuration/>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>communityMapPath</name>
|
||||
<value>${workingDir}/communityMap</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<value>${workingDir}/tar</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<value>${sourcePath}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>dumpType</name>
|
||||
<value>${dumpType}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</sub-workflow>
|
||||
<ok to="make_archive" />
|
||||
<error to="Kill" />
|
||||
</action>
|
||||
|
||||
<action name="make_archive">
|
||||
<java>
|
||||
<main-class>eu.dnetlib.dhp.oa.graph.dump.MakeTar</main-class>
|
||||
<arg>--hdfsPath</arg><arg>${outputPath}</arg>
|
||||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--sourcePath</arg><arg>${workingDir}/tar</arg>
|
||||
</java>
|
||||
<ok to="should_upload"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<decision name="should_upload">
|
||||
<switch>
|
||||
<case to="send_zenodo">${wf:conf('upload') eq true}</case>
|
||||
<default to="End"/>
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<action name="send_zenodo">
|
||||
<java>
|
||||
<main-class>eu.dnetlib.dhp.oa.graph.dump.SendToZenodoHDFS</main-class>
|
||||
<arg>--hdfsPath</arg><arg>${outputPath}</arg>
|
||||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--accessToken</arg><arg>${accessToken}</arg>
|
||||
<arg>--connectionUrl</arg><arg>${connectionUrl}</arg>
|
||||
<arg>--metadata</arg><arg>${metadata}</arg>
|
||||
<arg>--conceptRecordId</arg><arg>${conceptRecordId}</arg>
|
||||
<arg>--depositionType</arg><arg>${depositionType}</arg>
|
||||
<arg>--depositionId</arg><arg>${depositionId}</arg>
|
||||
</java>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
||||
|
|
@ -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>
|
||||
|
|
@ -0,0 +1,347 @@
|
|||
<workflow-app name="sub_dump_community_funder_results" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the source path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the output path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>communityMapPath</name>
|
||||
<description>the path to the community map</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>selectedResults</name>
|
||||
<description>the path the the possible subset ot results to be dumped</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveDbName</name>
|
||||
<description>the target hive database name</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveJdbcUrl</name>
|
||||
<description>hive server jdbc url</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveMetastoreUris</name>
|
||||
<description>hive server metastore URIs</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>${oozieActionShareLibForSpark2}</value>
|
||||
</property>
|
||||
|
||||
</configuration>
|
||||
</global>
|
||||
|
||||
<start to="fork_dump"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
|
||||
|
||||
|
||||
<fork name="fork_dump">
|
||||
<path start="dump_publication"/>
|
||||
<path start="dump_dataset"/>
|
||||
<path start="dump_orp"/>
|
||||
<path start="dump_software"/>
|
||||
</fork>
|
||||
|
||||
<action name="dump_publication">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table publication for community/funder related products</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${selectedResults}/publication</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/dump/publication</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
<arg>--dumpType</arg><arg>${dumpType}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_dataset">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table dataset for community/funder related products</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${selectedResults}/dataset</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/dump/dataset</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_orp">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table ORP for community related products</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${selectedResults}/otherresearchproduct</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/dump/otherresearchproduct</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_software">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table software for community related products</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkDumpCommunityProducts</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${selectedResults}/software</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/dump/software</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<join name="join_dump" to="prepareResultProject"/>
|
||||
|
||||
<action name="prepareResultProject">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Prepare association result subset of project info</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkPrepareResultProject</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
|
||||
</spark>
|
||||
<ok to="fork_extendWithProject"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<fork name="fork_extendWithProject">
|
||||
<path start="extend_publication"/>
|
||||
<path start="extend_dataset"/>
|
||||
<path start="extend_orp"/>
|
||||
<path start="extend_software"/>
|
||||
</fork>
|
||||
|
||||
<action name="extend_publication">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Extend dumped publications with information about project</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
|
||||
<jar>dhp-graph-mapper-${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}/dump/publication</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}/ext/publication</arg>
|
||||
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
|
||||
</spark>
|
||||
<ok to="join_extend"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="extend_dataset">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Extend dumped dataset with information about project</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${workingDir}/dump/dataset</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}/ext/dataset</arg>
|
||||
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
|
||||
</spark>
|
||||
<ok to="join_extend"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="extend_orp">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Extend dumped ORP with information about project</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
|
||||
<jar>dhp-graph-mapper-${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}/dump/otherresearchproduct</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}/ext/orp</arg>
|
||||
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
|
||||
</spark>
|
||||
<ok to="join_extend"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="extend_software">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Extend dumped software with information about project</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkUpdateProjectInfo</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${workingDir}/dump/software</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}/ext/software</arg>
|
||||
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
|
||||
</spark>
|
||||
<ok to="join_extend"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<join name="join_extend" to="End"/>
|
||||
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
||||
|
||||
|
||||
|
|
@ -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>
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
## This is a classpath-based import file (this header is required)
|
||||
dump_common classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app
|
||||
|
|
@ -0,0 +1,145 @@
|
|||
<workflow-app name="sub_dump_community_products" xmlns="uri:oozie:workflow:0.5">
|
||||
|
||||
<parameters>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the source path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the output path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveDbName</name>
|
||||
<description>the target hive database name</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveJdbcUrl</name>
|
||||
<description>hive server jdbc url</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveMetastoreUris</name>
|
||||
<description>hive server metastore URIs</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="common_action_community_funder"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="common_action_community_funder">
|
||||
<sub-workflow>
|
||||
<app-path>${wf:appPath()}/dump_common
|
||||
</app-path>
|
||||
<propagate-configuration/>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<value>${sourcePath}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>selectedResults</name>
|
||||
<value>${sourcePath}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>communityMapPath</name>
|
||||
<value>${workingDir}/communityMap</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<value>${workingDir}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</sub-workflow>
|
||||
<ok to="splitForCommunities" />
|
||||
<error to="Kill" />
|
||||
</action>
|
||||
|
||||
|
||||
|
||||
<action name="splitForCommunities">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Split dumped result for community</name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.community.SparkSplitForCommunity</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${workingDir}/ext</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
||||
|
|
@ -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>
|
||||
|
|
@ -0,0 +1,538 @@
|
|||
|
||||
<workflow-app name="sub-dump_complete" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the source path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the output path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>resultAggregation</name>
|
||||
<description>true if all the result type have to be dumped under result. false otherwise</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>organizationCommunityMap</name>
|
||||
<description>the organization community map</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>hiveDbName</name>
|
||||
<description>the target hive database name</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveJdbcUrl</name>
|
||||
<description>hive server jdbc url</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveMetastoreUris</name>
|
||||
<description>hive server metastore URIs</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="fork_dump" />
|
||||
|
||||
|
||||
|
||||
<fork name="fork_dump">
|
||||
<path start="dump_publication"/>
|
||||
<path start="dump_dataset"/>
|
||||
<path start="dump_orp"/>
|
||||
<path start="dump_software"/>
|
||||
<path start="dump_organization"/>
|
||||
<path start="dump_project"/>
|
||||
<path start="dump_datasource"/>
|
||||
<path start="select_relation"/>
|
||||
</fork>
|
||||
|
||||
<action name="dump_publication">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table publication </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/publication</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/publication</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_dataset">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table dataset </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/dataset</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_orp">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table ORP </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/otherresearchproduct</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/otherresearchproduct</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_software">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table software </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/software</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_organization">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table organization </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/organization</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Organization</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}/organization</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_project">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table project </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/project</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Project</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}/project</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_datasource">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table datasource </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpEntitiesJob</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/datasource</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Datasource</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}/datasource</arg>
|
||||
<arg>--communityMapPath</arg><arg>${workingDir}/communityMap</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="select_relation">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Select valid table relation </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkSelectValidRelationsJob</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/validrelation</arg>
|
||||
</spark>
|
||||
<ok to="dump_relation"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="dump_relation">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table relation </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkDumpRelationJob</class>
|
||||
<jar>dhp-graph-mapper-${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}/validrelation</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/relation/relation</arg>
|
||||
</spark>
|
||||
<ok to="join_dump"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<join name="join_dump" to="fork_context"/>
|
||||
|
||||
<fork name="fork_context">
|
||||
<path start="create_entities_fromcontext"/>
|
||||
<path start="create_relation_fromcontext"/>
|
||||
<path start="create_relation_fromorgs"/>
|
||||
</fork>
|
||||
|
||||
<action name="create_entities_fromcontext">
|
||||
<java>
|
||||
<main-class>eu.dnetlib.dhp.oa.graph.dump.complete.CreateContextEntities</main-class>
|
||||
<arg>--hdfsPath</arg><arg>${outputPath}/communities_infrastructures/communities_infrastructure.json.gz</arg>
|
||||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
|
||||
</java>
|
||||
<ok to="join_context"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="create_relation_fromcontext">
|
||||
<java>
|
||||
<main-class>eu.dnetlib.dhp.oa.graph.dump.complete.CreateContextRelation</main-class>
|
||||
<arg>--hdfsPath</arg><arg>${workingDir}/relation/context</arg>
|
||||
<arg>--nameNode</arg><arg>${nameNode}</arg>
|
||||
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
|
||||
</java>
|
||||
<ok to="join_context"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="create_relation_fromorgs">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table relation </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkOrganizationRelation</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/relation</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/relation/contextOrg</arg>
|
||||
<arg>--organizationCommunityMap</arg><arg>${organizationCommunityMap}</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_context"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<join name="join_context" to="fork_extract_relations"/>
|
||||
|
||||
<fork name="fork_extract_relations">
|
||||
<path start="rels_from_pubs"/>
|
||||
<path start="rels_from_dats"/>
|
||||
<path start="rels_from_orp"/>
|
||||
<path start="rels_from_sw"/>
|
||||
</fork>
|
||||
|
||||
<action name="rels_from_pubs">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Extract Relations from publication </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkExtractRelationFromEntities</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/relation/publication</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_extract_relations"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="rels_from_dats">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table dataset </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkExtractRelationFromEntities</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/dataset</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/relation/dataset</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_extract_relations"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="rels_from_orp">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table ORP </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkExtractRelationFromEntities</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/relation/orp</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_extract_relations"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="rels_from_sw">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump table software </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkExtractRelationFromEntities</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/software</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/relation/software</arg>
|
||||
<arg>--communityMapPath</arg><arg>${communityMapPath}</arg>
|
||||
</spark>
|
||||
<ok to="join_extract_relations"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<join name="join_extract_relations" to="collect_and_save"/>
|
||||
|
||||
<action name="collect_and_save">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Collect Results and Relations and put them in the right path </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.complete.SparkCollectAndSave</class>
|
||||
<jar>dhp-graph-mapper-${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}</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
<arg>--resultAggregation</arg><arg>${resultAggregation}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Sub-workflow dump complete failed with error message ${wf:errorMessage()}
|
||||
</message>
|
||||
</kill>
|
||||
|
||||
<end name="End" />
|
||||
</workflow-app>
|
||||
|
|
@ -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>
|
||||
|
|
@ -0,0 +1,2 @@
|
|||
## This is a classpath-based import file (this header is required)
|
||||
dump_common classpath eu/dnetlib/dhp/oa/graph/dump/wf/subworkflows/commoncommunityfunder/oozie_app
|
||||
|
|
@ -0,0 +1,258 @@
|
|||
<workflow-app name="sub_dump_funder_results" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<description>the source path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the output path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveDbName</name>
|
||||
<description>the target hive database name</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveJdbcUrl</name>
|
||||
<description>hive server jdbc url</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveMetastoreUris</name>
|
||||
<description>hive server metastore URIs</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="fork_result_linked_to_projects"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
|
||||
<fork name="fork_result_linked_to_projects">
|
||||
<path start="select_publication_linked_to_projects"/>
|
||||
<path start="select_dataset_linked_to_projects"/>
|
||||
<path start="select_orp_linked_to_project"/>
|
||||
<path start="select_software_linked_to_projects"/>
|
||||
</fork>
|
||||
|
||||
<action name="select_publication_linked_to_projects">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump funder results </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/publication</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="select_dataset_linked_to_projects">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump funder results </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/dataset</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/dataset</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="select_orp_linked_to_project">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump funder results </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</class>
|
||||
<jar>dhp-graph-mapper-${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=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/otherresearchproduct</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="select_software_linked_to_projects">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump funder results </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkResultLinkedToProject</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${sourcePath}/software</arg>
|
||||
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/result/software</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="join_link"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<join name="join_link" to="common_action_community_funder"/>
|
||||
|
||||
<action name="common_action_community_funder">
|
||||
<sub-workflow>
|
||||
<app-path>${wf:appPath()}/dump_common
|
||||
</app-path>
|
||||
<propagate-configuration/>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
<value>${sourcePath}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>selectedResults</name>
|
||||
<value>${workingDir}/result</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>communityMapPath</name>
|
||||
<value>${workingDir}/communityMap</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<value>${workingDir}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
</sub-workflow>
|
||||
<ok to="dump_funder_results" />
|
||||
<error to="Kill" />
|
||||
</action>
|
||||
|
||||
<action name="dump_funder_results">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Dump funder results </name>
|
||||
<class>eu.dnetlib.dhp.oa.graph.dump.funderresults.SparkDumpFunderResults</class>
|
||||
<jar>dhp-graph-mapper-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${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>${workingDir}/ext</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
<arg>--graphPath</arg><arg>${sourcePath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
||||
|
||||
|
||||
|
|
@ -9,7 +9,7 @@ import com.github.victools.jsonschema.generator.*;
|
|||
|
||||
import eu.dnetlib.dhp.schema.dump.oaf.graph.*;
|
||||
|
||||
//@Disabled
|
||||
@Disabled
|
||||
public class GenerateJsonSchema {
|
||||
|
||||
@Test
|
||||
|
|
|
|||
|
|
@ -70,7 +70,7 @@ public class QueryInformationSystemTest {
|
|||
lenient().when(isLookUpService.quickSearchProfile(XQUERY)).thenReturn(communityMap);
|
||||
queryInformationSystem = new QueryInformationSystem();
|
||||
queryInformationSystem.setIsLookUp(isLookUpService);
|
||||
map = queryInformationSystem.getCommunityMap();
|
||||
map = queryInformationSystem.getCommunityMap(false, null);
|
||||
}
|
||||
|
||||
@Test
|
||||
|
|
|
|||
|
|
@ -1,60 +0,0 @@
|
|||
|
||||
package eu.dnetlib.dhp.oa.graph.dump.community;
|
||||
|
||||
import java.io.FileInputStream;
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.LocalFileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.junit.jupiter.api.Assertions;
|
||||
import org.junit.jupiter.api.BeforeAll;
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.oa.graph.dump.MakeTar;
|
||||
import eu.dnetlib.dhp.oa.graph.dump.MakeTarTest;
|
||||
|
||||
public class RemoveCommunityTest {
|
||||
|
||||
private static String workingDir;
|
||||
|
||||
@BeforeAll
|
||||
public static void beforeAll() throws IOException {
|
||||
workingDir = Files
|
||||
.createTempDirectory(MakeTarTest.class.getSimpleName())
|
||||
.toString();
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testRemove() throws Exception {
|
||||
LocalFileSystem fs = FileSystem.getLocal(new Configuration());
|
||||
|
||||
fs
|
||||
.copyFromLocalFile(
|
||||
false, new Path(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/oa/graph/dump/communityMapPath/communitymap.json")
|
||||
.getPath()),
|
||||
new Path(workingDir + "/communityMap"));
|
||||
|
||||
String path = workingDir + "/communityMap";
|
||||
|
||||
RemoveCommunities.main(new String[] {
|
||||
"-nameNode", "local",
|
||||
"-path", path,
|
||||
"-communityId", "beopen"
|
||||
}
|
||||
|
||||
);
|
||||
|
||||
CommunityMap cm = new ObjectMapper()
|
||||
.readValue(new FileInputStream(workingDir + "/communityMap"), CommunityMap.class);
|
||||
|
||||
Assertions.assertEquals(1, cm.size());
|
||||
Assertions.assertTrue(cm.containsKey("beopen"));
|
||||
|
||||
}
|
||||
}
|
||||
Loading…
Reference in New Issue