D-Net
/
dnet-hadoop
14
5
Fork 11
Code Issues 14 Pull Requests 10 Projects 2 Releases 2 Wiki Activity

[enrichment single step] #378

Merged
claudio.atzori merged 3 commits from enrichmentSingleStepFixed into beta 2024-01-18 09:41:10 +01:00
Conversation 0 Commits 3 Files Changed 19 +458 -151
19 changed files with 458 additions and 151 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

84
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/MoveResult.java Normal file
View File

@ -0,0 +1,84 @@
package eu.dnetlib.dhp;
import static eu.dnetlib.dhp.PropagationConstant.isSparkSessionManaged;
import static eu.dnetlib.dhp.PropagationConstant.readPath;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.Serializable;
import org.apache.commons.io.IOUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.SaveMode;
import org.apache.spark.sql.SparkSession;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob;
import eu.dnetlib.dhp.schema.common.ModelSupport;
import eu.dnetlib.dhp.schema.oaf.Result;
/**
* @author miriam.baglioni
* @Date 15/01/24
*/
public class MoveResult implements Serializable {
private static final Logger log = LoggerFactory.getLogger(MoveResult.class);
public static void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
SparkResultToCommunityFromOrganizationJob.class
.getResourceAsStream(
"/eu/dnetlib/dhp/wf/subworkflows/input_moveresult_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
Boolean isSparkSessionManaged = isSparkSessionManaged(parser);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
String inputPath = parser.get("sourcePath");
log.info("inputPath: {}", inputPath);
final String outputPath = parser.get("outputPath");
log.info("outputPath: {}", outputPath);
SparkConf conf = new SparkConf();
runWithSparkSession(
conf,
isSparkSessionManaged,
spark -> {
moveResults(spark, inputPath, outputPath);
});
}
public static <R extends Result> void moveResults(SparkSession spark, String inputPath, String outputPath) {
ModelSupport.entityTypes
.keySet()
.parallelStream()
.filter(e -> ModelSupport.isResult(e))
// .parallelStream()
.forEach(e -> {
Class<R> resultClazz = ModelSupport.entityTypes.get(e);
Dataset<R> resultDataset = readPath(spark, inputPath + e.name(), resultClazz);
if (resultDataset.count() > 0) {
resultDataset
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
}
});
}
}

6
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java
View File

@ -97,12 +97,6 @@ public class SparkCountryPropagationJob {
.mode(SaveMode.Overwrite)
.json(outputPath);
readPath(spark, outputPath, resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(sourcePath);
}
private static <R extends Result> MapFunction<Tuple2<R, ResultCountrySet>, R> getCountryMergeFn() {

29
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java
View File

@ -64,7 +64,7 @@ public class SparkResultToProjectThroughSemRelJob {
removeOutputDir(spark, outputPath);
}
execPropagation(
spark, outputPath, alreadyLinkedPath, potentialUpdatePath, saveGraph);
spark, outputPath, alreadyLinkedPath, potentialUpdatePath);
});
}
@ -72,24 +72,23 @@ public class SparkResultToProjectThroughSemRelJob {
SparkSession spark,
String outputPath,
String alreadyLinkedPath,
String potentialUpdatePath,
Boolean saveGraph) {
String potentialUpdatePath) {
Dataset<ResultProjectSet> toaddrelations = readPath(spark, potentialUpdatePath, ResultProjectSet.class);
Dataset<ResultProjectSet> alreadyLinked = readPath(spark, alreadyLinkedPath, ResultProjectSet.class);
if (saveGraph) {
toaddrelations
.joinWith(
alreadyLinked,
toaddrelations.col("resultId").equalTo(alreadyLinked.col("resultId")),
"left_outer")
.flatMap(mapRelationRn(), Encoders.bean(Relation.class))
.write()
.mode(SaveMode.Append)
.option("compression", "gzip")
.json(outputPath);
}
// if (saveGraph) {
toaddrelations
.joinWith(
alreadyLinked,
toaddrelations.col("resultId").equalTo(alreadyLinked.col("resultId")),
"left_outer")
.flatMap(mapRelationRn(), Encoders.bean(Relation.class))
.write()
.mode(SaveMode.Append)
.option("compression", "gzip")
.json(outputPath);
// }
}
private static FlatMapFunction<Tuple2<ResultProjectSet, ResultProjectSet>, Relation> mapRelationRn() {

66
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java
View File

@ -76,29 +76,41 @@ public class SparkResultToCommunityFromOrganizationJob {
ModelSupport.entityTypes
.keySet()
.parallelStream()
.filter(e -> ModelSupport.isResult(e))
// .parallelStream()
.forEach(e -> {
if (ModelSupport.isResult(e)) {
Class<R> resultClazz = ModelSupport.entityTypes.get(e);
removeOutputDir(spark, outputPath + e.name());
Dataset<R> result = readPath(spark, inputPath + e.name(), resultClazz);
// if () {
Class<R> resultClazz = ModelSupport.entityTypes.get(e);
removeOutputDir(spark, outputPath + e.name());
Dataset<R> result = readPath(spark, inputPath + e.name(), resultClazz);
result
.joinWith(
possibleUpdates,
result.col("id").equalTo(possibleUpdates.col("resultId")),
"left_outer")
.map(resultCommunityFn(), Encoders.bean(resultClazz))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
log.info("executing left join");
result
.joinWith(
possibleUpdates,
result.col("id").equalTo(possibleUpdates.col("resultId")),
"left_outer")
.map(resultCommunityFn(), Encoders.bean(resultClazz))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
readPath(spark, outputPath + e.name(), resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + e.name());
}
// log
// .info(
// "reading results from " + outputPath + e.name() + " and copying them to " + inputPath
// + e.name());
// Dataset<R> tmp = readPath(spark, outputPath + e.name(), resultClazz);
// if (tmp.count() > 0){
//
// tmp
// .write()
// .mode(SaveMode.Overwrite)
// .option("compression", "gzip")
// .json(inputPath + e.name());
// }
// }
});
}
@ -115,11 +127,11 @@ public class SparkResultToCommunityFromOrganizationJob {
.map(Context::getId)
.collect(Collectors.toList());
@SuppressWarnings("unchecked")
R res = (R) ret.getClass().newInstance();
// @SuppressWarnings("unchecked")
// R res = (R) ret.getClass().newInstance();
res.setId(ret.getId());
List<Context> propagatedContexts = new ArrayList<>();
// res.setId(ret.getId());
// List<Context> propagatedContexts = new ArrayList<>();
for (String cId : communitySet) {
if (!contextList.contains(cId)) {
Context newContext = new Context();
@ -133,11 +145,11 @@ public class SparkResultToCommunityFromOrganizationJob {
PROPAGATION_RESULT_COMMUNITY_ORGANIZATION_CLASS_ID,
PROPAGATION_RESULT_COMMUNITY_ORGANIZATION_CLASS_NAME,
ModelConstants.DNET_PROVENANCE_ACTIONS)));
propagatedContexts.add(newContext);
ret.getContext().add(newContext);
}
}
res.setContext(propagatedContexts);
ret.mergeFrom(res);
// res.setContext(propagatedContexts);
// ret.mergeFrom(res);
}
return ret;
};

41
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java
View File

@ -86,29 +86,30 @@ public class SparkResultToCommunityFromProject implements Serializable {
ModelSupport.entityTypes
.keySet()
.parallelStream()
.filter(e -> ModelSupport.isResult(e))
.forEach(e -> {
if (ModelSupport.isResult(e)) {
removeOutputDir(spark, outputPath + e.name());
Class<R> resultClazz = ModelSupport.entityTypes.get(e);
Dataset<R> result = readPath(spark, inputPath + e.name(), resultClazz);
// if () {
removeOutputDir(spark, outputPath + e.name());
Class<R> resultClazz = ModelSupport.entityTypes.get(e);
Dataset<R> result = readPath(spark, inputPath + e.name(), resultClazz);
result
.joinWith(
possibleUpdates,
result.col("id").equalTo(possibleUpdates.col("resultId")),
"left_outer")
.map(resultCommunityFn(), Encoders.bean(resultClazz))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
result
.joinWith(
possibleUpdates,
result.col("id").equalTo(possibleUpdates.col("resultId")),
"left_outer")
.map(resultCommunityFn(), Encoders.bean(resultClazz))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(outputPath + e.name());
readPath(spark, outputPath + e.name(), resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath + e.name());
}
// readPath(spark, outputPath + e.name(), resultClazz)
// .write()
// .mode(SaveMode.Overwrite)
// .option("compression", "gzip")
// .json(inputPath + e.name());
// }
});
}

21
dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java
View File

@ -101,11 +101,6 @@ public class SparkResultToCommunityThroughSemRelJob {
.option("compression", "gzip")
.json(outputPath);
readPath(spark, outputPath, resultClazz)
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")
.json(inputPath);
}
private static <R extends Result> MapFunction<Tuple2<R, ResultCommunityList>, R> contextUpdaterFn() {
@ -115,11 +110,11 @@ public class SparkResultToCommunityThroughSemRelJob {
if (rcl.isPresent()) {
Set<String> contexts = new HashSet<>();
ret.getContext().forEach(c -> contexts.add(c.getId()));
List<Context> contextList = rcl
rcl
.get()
.getCommunityList()
.stream()
.map(
.forEach(
c -> {
if (!contexts.contains(c)) {
Context newContext = new Context();
@ -133,19 +128,11 @@ public class SparkResultToCommunityThroughSemRelJob {
PROPAGATION_RESULT_COMMUNITY_SEMREL_CLASS_ID,
PROPAGATION_RESULT_COMMUNITY_SEMREL_CLASS_NAME,
ModelConstants.DNET_PROVENANCE_ACTIONS)));
return newContext;
ret.getContext().add(newContext);
}
return null;
})
.filter(Objects::nonNull)
.collect(Collectors.toList());
@SuppressWarnings("unchecked")
R r = (R) ret.getClass().newInstance();
});
r.setId(ret.getId());
r.setContext(contextList);
ret.mergeFrom(r);
}
return ret;

6
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties
View File

@ -1,12 +1,12 @@
sourcePath=/tmp/beta_provision/graph/09_graph_dedup_enriched
resumeFrom=CountryPropagation
sourcePath=/tmp/beta_provision/graph/10_graph_orcid_enriched
resumeFrom=ResultProject
allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo
allowedsemrelsresultproject=isSupplementedBy;isSupplementTo
allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo
datasourceWhitelistForCountryPropagation=10|opendoar____::16e6a3326dd7d868cbc926602a61e4d0;10|openaire____::fdb035c8b3e0540a8d9a561a6c44f4de;10|eurocrisdris::fe4903425d9040f680d8610d9079ea14;10|openaire____::5b76240cc27a58c6f7ceef7d8c36660e;10|openaire____::172bbccecf8fca44ab6a6653e84cb92a;10|openaire____::149c6590f8a06b46314eed77bfca693f;10|eurocrisdris::a6026877c1a174d60f81fd71f62df1c1;10|openaire____::4692342f0992d91f9e705c26959f09e0;10|openaire____::8d529dbb05ec0284662b391789e8ae2a;10|openaire____::345c9d171ef3c5d706d08041d506428c;10|opendoar____::1c1d4df596d01da60385f0bb17a4a9e0;10|opendoar____::7a614fd06c325499f1680b9896beedeb;10|opendoar____::1ee3dfcd8a0645a25a35977997223d22;10|opendoar____::d296c101daa88a51f6ca8cfc1ac79b50;10|opendoar____::798ed7d4ee7138d49b8828958048130a;10|openaire____::c9d2209ecc4d45ba7b4ca7597acb88a2;10|eurocrisdris::c49e0fe4b9ba7b7fab717d1f0f0a674d;10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539;10|eurocrisdris::432ca599953ff50cd4eeffe22faf3e48
#allowedtypes=pubsrepository::institutional
allowedtypes=Institutional
outputPath=/tmp/miriam/enrichment_one_step
outputPath=/tmp/miriam/graph/11_graph_orcid
pathMap ={"author":"$['author'][*]['fullname']", \
"title":"$['title'][*]['value']",\
"orcid":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']" ,\

12
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml
View File

@ -45,10 +45,18 @@
</property>
<property>
<name>sparkExecutorMemory</name>
<value>6G</value>
<value>5G</value>
</property>
<property>
<name>sparkExecutorCores</name>
<value>1</value>
<value>4</value>
</property>
<property>
<name>memoryOverhead</name>
<value>3G</value>
</property>
<property>
<name>partitions</name>
<value>3284</value>
</property>
</configuration>

18
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml
View File

@ -12,6 +12,10 @@
<name>baseURL</name>
<description>The URL to access the community APIs</description>
</property>
<property>
<name>startFrom></name>
<value>undelete</value>
</property>
</parameters>
@ -26,12 +30,20 @@
</configuration>
</global>
<start to="reset_outputpath"/>
<start to="startFrom"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<decision name="startFrom">
<switch>
<case to="exec_bulktag">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<action name="reset_outputpath">
<fs>
<delete path="${workingDir}"/>
@ -45,7 +57,7 @@
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn-cluster</master>
<mode>cluster</mode>
<name>bulkTagging-publication</name>
<name>bulkTagging</name>
<class>eu.dnetlib.dhp.bulktag.SparkBulkTagJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
@ -53,6 +65,8 @@
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.executor.memoryOverhead=${memoryOverhead}
--conf spark.sql.shuffle.partitions=${partitions}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}

4
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml
View File

@ -45,11 +45,11 @@
</property>
<property>
<name>sparkExecutorMemory</name>
<value>6G</value>
<value>5G</value>
</property>
<property>
<name>sparkExecutorCores</name>
<value>1</value>
<value>4</value>
</property>
<property>
<name>spark2MaxExecutors</name>

92
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml
View File

@ -12,6 +12,10 @@
<name>allowedtypes</name>
<description>the allowed types</description>
</property>
<property>
<name>startFrom</name>
<value>undelete</value>
</property>
</parameters>
<global>
@ -25,7 +29,15 @@
</configuration>
</global>
<start to="reset_outputpath"/>
<start to="resumeFrom"/>
<decision name="resumeFrom">
<switch>
<case to="prepare_datasource_country_association">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
@ -61,7 +73,7 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--whitelist</arg><arg>${whitelist}</arg>
<arg>--allowedtypes</arg><arg>${allowedtypes}</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/preparedInfo</arg>
</spark>
<ok to="fork_prepare_result_country"/>
<error to="Kill"/>
@ -95,10 +107,10 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/publication</arg>
<arg>--workingPath</arg><arg>${workingDir}/workingP</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/publication</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/workingP</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
</spark>
<ok to="wait_prepare"/>
<error to="Kill"/>
@ -125,10 +137,10 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/dataset</arg>
<arg>--workingPath</arg><arg>${workingDir}/workingD</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/dataset</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/workingD</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
</spark>
<ok to="wait_prepare"/>
<error to="Kill"/>
@ -155,10 +167,10 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/otherresearchproduct</arg>
<arg>--workingPath</arg><arg>${workingDir}/workingO</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/otherresearchproduct</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/workingO</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
</spark>
<ok to="wait_prepare"/>
<error to="Kill"/>
@ -185,10 +197,10 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--outputPath</arg><arg>${workingDir}/software</arg>
<arg>--workingPath</arg><arg>${workingDir}/workingS</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/software</arg>
<arg>--workingPath</arg><arg>${workingDir}/country/workingS</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/preparedInfo</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/preparedInfo</arg>
</spark>
<ok to="wait_prepare"/>
<error to="Kill"/>
@ -224,9 +236,9 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/publication</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/country/publication</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
@ -253,9 +265,9 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/dataset</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/country/dataset</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
@ -282,9 +294,9 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/otherresearchproduct</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/otherresearchproduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/country/otherresearchproduct</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
@ -311,15 +323,49 @@
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/software</arg>
<arg>--preparedInfoPath</arg><arg>${workingDir}/country/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/software</arg>
<arg>--outputPath</arg><arg>${workingDir}/country/country/software</arg>
</spark>
<ok to="wait"/>
<error to="Kill"/>
</action>
<join name="wait" to="reset_workingDir"/>
<join name="wait" to="move-results"/>
<action name="move-results">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>community2resultfromorganization - move results</name>
<class>eu.dnetlib.dhp.MoveResult</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--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.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/country/country/</arg>
<arg>--outputPath</arg><arg>${sourcePath}/</arg>
<!-- <arg>&#45;&#45;outputPath</arg><arg>/tmp/miriam/rescomm/</arg>-->
</spark>
<ok to="deleteWD"/>
<error to="Kill"/>
</action>
<decision name="deleteWD">
<switch>
<case to="End">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_workingDir"/>
</switch>
</decision>
<action name="reset_workingDir">
<fs>
<delete path="${workingDir}"/>

15
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml
View File

@ -4,7 +4,10 @@
<name>sourcePath</name>
<description>the source path</description>
</property>
<property>
<name>startFrom</name>
<value>undelete</value>
</property>
</parameters>
<global>
@ -18,7 +21,15 @@
</configuration>
</global>
<start to="reset_outputpath"/>
<start to="startFrom"/>
<decision name="startFrom">
<switch>
<case to="prepare_info">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>

20
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml
View File

@ -114,7 +114,7 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
</spark>
<ok to="wait"/>
@ -142,7 +142,7 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
</spark>
<ok to="wait"/>
@ -170,7 +170,7 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
</spark>
<ok to="wait"/>
@ -198,7 +198,7 @@
<arg>--sourcePath</arg><arg>${sourcePath}</arg>
<arg>--hive_metastore_uris</arg><arg>${hive_metastore_uris}</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${workingDir}/preparedInfo/targetOrcidAssoc</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcid/preparedInfo/targetOrcidAssoc</arg>
<arg>--allowedsemrels</arg><arg>${allowedsemrels}</arg>
</spark>
<ok to="wait"/>
@ -225,8 +225,8 @@
--conf spark.dynamicAllocation.enabled=true
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/orcidprop</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${workingDir}/orcid/orcidprop</arg>
<arg>--outputPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
</spark>
<ok to="fork-join-exec-propagation"/>
<error to="Kill"/>
@ -261,7 +261,7 @@
--conf spark.hadoop.mapreduce.reduce.speculative=false
--conf spark.sql.shuffle.partitions=3840
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/publication</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Publication</arg>
<arg>--outputPath</arg><arg>${outputPath}/publication</arg>
@ -291,7 +291,7 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/dataset</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Dataset</arg>
<arg>--outputPath</arg><arg>${outputPath}/dataset</arg>
@ -321,7 +321,7 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/otherresearchproduct</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.OtherResearchProduct</arg>
<arg>--outputPath</arg><arg>${outputPath}/otherresearchproduct</arg>
@ -351,7 +351,7 @@
--conf spark.hadoop.mapreduce.map.speculative=false
--conf spark.hadoop.mapreduce.reduce.speculative=false
</spark-opts>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcidprop/mergedOrcidAssoc</arg>
<arg>--possibleUpdatesPath</arg><arg>${workingDir}/orcid/orcidprop/mergedOrcidAssoc</arg>
<arg>--sourcePath</arg><arg>${sourcePath}/software</arg>
<arg>--resultTableName</arg><arg>eu.dnetlib.dhp.schema.oaf.Software</arg>
<arg>--outputPath</arg><arg>${outputPath}/software</arg>

24
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml
View File

@ -8,7 +8,10 @@
<name>allowedsemrels</name>
<description>the allowed semantics </description>
</property>
<property>
<name>startFrom</name>
<value>undelete</value>
</property>
</parameters>
<global>
@ -22,7 +25,15 @@
</configuration>
</global>
<start to="reset_outputpath"/>
<start to="startFrom"/>
<decision name="startFrom">
<switch>
<case to="prepare_project_results_association">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
@ -86,17 +97,8 @@
<arg>--potentialUpdatePath</arg><arg>${workingDir}/resultproject/preparedInfo/potentialUpdates</arg>
<arg>--alreadyLinkedPath</arg><arg>${workingDir}/resultproject/preparedInfo/alreadyLinked</arg>
</spark>
<ok to="reset_workingDir"/>
<error to="Kill"/>
</action>
<action name="reset_workingDir">
<fs>
<delete path="${workingDir}"/>
<mkdir path="${workingDir}"/>
</fs>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

22
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_moveresult_parameters.json Normal file
View File

@ -0,0 +1,22 @@
[
{
"paramName":"s",
"paramLongName":"sourcePath",
"paramDescription": "the path of the sequencial file to read",
"paramRequired": true
},
{
"paramName": "out",
"paramLongName": "outputPath",
"paramDescription": "the path used to store temporary output files",
"paramRequired": true
},
{
"paramName": "ssm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "true if the spark session is managed, false otherwise",
"paramRequired": false
}
]

43
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml
View File

@ -8,6 +8,10 @@
<name>baseURL</name>
<description>the baseURL from where to reach the community APIs</description>
</property>
<property>
<name>startFrom</name>
<value>undelete</value>
</property>
</parameters>
<global>
@ -21,7 +25,15 @@
</configuration>
</global>
<start to="reset_outputpath"/>
<start to="startFrom"/>
<decision name="startFrom">
<switch>
<case to="prepare_result_communitylist">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
@ -69,7 +81,7 @@
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>community2resultfromorganization-Publication</name>
<name>community2resultfromorganization</name>
<class>eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
@ -88,6 +100,33 @@
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/communityorganization/resulttocommunityfromorganization/</arg>
</spark>
<ok to="move-results"/>
<error to="Kill"/>
</action>
<action name="move-results">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>community2resultfromorganization - move results</name>
<class>eu.dnetlib.dhp.MoveResult</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--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.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/communityorganization/resulttocommunityfromorganization/</arg>
<arg>--outputPath</arg><arg>${sourcePath}/</arg>
<!-- <arg>&#45;&#45;outputPath</arg><arg>/tmp/miriam/rescomm/</arg>-->
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>

43
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml
View File

@ -8,6 +8,10 @@
<name>baseURL</name>
<description>the base URL to use to select the right community APIs</description>
</property>
<property>
<name>startFrom</name>
<value>undelete</value>
</property>
</parameters>
<global>
@ -21,7 +25,15 @@
</configuration>
</global>
<start to="reset_outputpath"/>
<start to="startFrom"/>
<decision name="startFrom">
<switch>
<case to="prepare_result_communitylist">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
@ -86,12 +98,37 @@
<arg>--sourcePath</arg><arg>${sourcePath}/</arg>
<arg>--outputPath</arg><arg>${workingDir}/communitythroughproject/</arg>
</spark>
<ok to="move-results"/>
<error to="Kill"/>
</action>
<action name="move-results">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>move results</name>
<class>eu.dnetlib.dhp.MoveResult</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/communitythroughproject/</arg>
<arg>--outputPath</arg><arg>${sourcePath}/</arg>
<!-- <arg>outputPath</arg><arg>/tmp/miriam/rescomm/</arg>-->
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

49
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml
View File

@ -16,9 +16,21 @@
<name>outputPath</name>
<description>the output path</description>
</property>
<property>
<name>startFrom</name>
<value>undelete</value>
</property>
</parameters>
<start to="reset_outputpath"/>
<start to="startFrom"/>
<decision name="startFrom">
<switch>
<case to="fork_prepare_assoc_step1">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
@ -209,9 +221,9 @@
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--executor-memory=4G
--conf spark.executor.memoryOverhead=5G
--conf spark.sql.shuffle.partitions=15000
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
@ -324,7 +336,34 @@
<error to="Kill"/>
</action>
<join name="wait2" to="End"/>
<join name="wait2" to="move-results"/>
<action name="move-results">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>move results</name>
<class>eu.dnetlib.dhp.MoveResult</class>
<jar>dhp-enrichment-${projectVersion}.jar</jar>
<spark-opts>
--executor-cores=6
--executor-memory=5G
--conf spark.executor.memoryOverhead=3g
--conf spark.sql.shuffle.partitions=3284
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors}
</spark-opts>
<arg>--sourcePath</arg><arg>${workingDir}/communitysemrel/</arg>
<arg>--outputPath</arg><arg>${sourcePath}/</arg>
<!-- <arg>outputPath</arg><arg>/tmp/miriam/rescomm/</arg>-->
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>

14
dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml
View File

@ -8,6 +8,10 @@
<name>blacklist</name>
<description>The list of institutional repositories that should not be used for the propagation</description>
</property>
<property>
<name>startFrom</name>
<value>undelete</value>
</property>
</parameters>
<global>
@ -21,7 +25,15 @@
</configuration>
</global>
<start to="reset_outputpath"/>
<start to="startFrom"/>
<decision name="startFrom">
<switch>
<case to="prepare_result_organization_association">${wf:conf('startFrom') eq 'undelete'}</case>
<default to="reset_outputpath"/>
</switch>
</decision>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>