From 616622d2bb90f4a5e43a9da2dc864ef03dab1f00 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Thu, 7 Dec 2023 09:59:52 +0100 Subject: [PATCH 01/17] first version of the workflow single step --- .../main/java/eu/dnetlib/dhp/api/Utils.java | 5 + .../dnetlib/dhp/bulktag/SparkBulkTagJob.java | 8 +- .../PrepareDatasourceCountryAssociation.java | 2 +- .../SparkCountryPropagationJob.java | 6 + ...kResultToCommunityFromOrganizationJob.java | 6 + .../PrepareResultCommunitySet.java | 2 +- .../SparkResultToCommunityFromProject.java | 6 + .../PrepareResultCommunitySetStep1.java | 18 +- ...parkResultToCommunityThroughSemRelJob.java | 6 + ...t_preparecommunitytoresult_parameters.json | 4 +- .../oozie_app/workflow.xml | 6 +- .../dhp/wf/main/oozie_app/config-default.xml | 30 ++ .../dnetlib/dhp/wf/main/oozie_app/import.txt | 10 + .../dhp/wf/main/oozie_app/workflow.xml | 324 +++++++++++++++ .../bulktag/oozie_app/config-default.xml | 54 +++ .../bulktag/oozie_app/workflow.xml | 66 ++++ .../oozie_app/config-default.xml | 58 +++ .../countrypropagation/oozie_app/workflow.xml | 316 +++++++++++++++ .../input_preparation_parameter.json | 50 +++ .../input_propagation_parameter.json | 62 +++ .../oozie_app/config-default.xml | 58 +++ .../oozie_app/workflow.xml | 93 +++++ .../oozie_app/config-default.xml | 58 +++ .../oozie_app/workflow.xml | 369 ++++++++++++++++++ .../oozie_app/config-default.xml | 63 +++ .../projecttoresult/oozie_app/workflow.xml | 94 +++++ .../oozie_app/config-default.xml | 58 +++ .../oozie_app/workflow.xml | 88 +++++ .../input_communitytoresult_parameters.json | 28 ++ ...t_preparecommunitytoresult_parameters.json | 28 ++ .../oozie_app/config-default.xml | 58 +++ .../oozie_app/workflow.xml | 90 +++++ .../oozie_app/config-default.xml | 58 +++ .../oozie_app/workflow.xml | 305 +++++++++++++++ .../oozie_app/config-default.xml | 58 +++ .../oozie_app/workflow.xml | 182 +++++++++ .../oozie_app/config-default.xml | 58 +++ .../oozie_app/workflow.xml | 97 +++++ 38 files changed, 2863 insertions(+), 19 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/import.txt create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java index d121b8b7e2..bb30f55d6f 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java @@ -167,4 +167,9 @@ public class Utils implements Serializable { }); return projectMap; } + + public static List getCommunityIdList(String baseURL) throws IOException { + return getValidCommunities(baseURL).stream() + .map(community -> community.getId()).collect(Collectors.toList()); + } } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java index 5d1b2b38d1..5745515baa 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java @@ -151,7 +151,13 @@ public class SparkBulkTagJob { .write() .mode(SaveMode.Overwrite) .option("compression", "gzip") - .json(outputPath + e.name()); + .json(outputPath + e.name());//writing the tagging in the working dir for entity + + readPath(spark, outputPath + e.name(), resultClazz) //copy the tagging in the actual result output path + .write() + .mode(SaveMode.Overwrite) + .option("compression","gzip") + .json(inputPath + e.name()); }); } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java index b9f3bff523..b1720d19d1 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java @@ -66,7 +66,7 @@ public class PrepareDatasourceCountryAssociation { conf, isSparkSessionManaged, spark -> { - removeOutputDir(spark, outputPath); + //removeOutputDir(spark, outputPath); prepareDatasourceCountryAssociation( spark, Arrays.asList(parser.get("whitelist").split(";")), diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java index d9f6433a07..2b0dd76281 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java @@ -97,6 +97,12 @@ public class SparkCountryPropagationJob { .mode(SaveMode.Overwrite) .json(outputPath); + readPath(spark, outputPath, resultClazz) + .write() + .mode(SaveMode.Overwrite) + .option("compression","gzip") + .json(sourcePath); + } private static MapFunction, R> getCountryMergeFn() { diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java index df8ca3805b..9152b1f5a9 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java @@ -92,6 +92,12 @@ public class SparkResultToCommunityFromOrganizationJob { .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()); } }); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java index 7fed2606b4..467e11a969 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java @@ -53,7 +53,7 @@ public class PrepareResultCommunitySet { log.info("outputPath: {}", outputPath); final String baseURL = parser.get("baseURL"); - log.info("baseUEL: {}", baseURL); + log.info("baseURL: {}", baseURL); final CommunityEntityMap projectsMap = Utils.getCommunityProjects(baseURL); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java index 6e298cf946..5478915848 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java @@ -102,6 +102,12 @@ public class SparkResultToCommunityFromProject implements Serializable { .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()); } }); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java index 0c836a3ba9..73c4e2d7c0 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java @@ -4,9 +4,11 @@ package eu.dnetlib.dhp.resulttocommunityfromsemrel; import static eu.dnetlib.dhp.PropagationConstant.*; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; +import java.io.IOException; import java.util.Arrays; import java.util.List; +import eu.dnetlib.dhp.api.Utils; import org.apache.commons.io.IOUtils; import org.apache.spark.SparkConf; import org.apache.spark.sql.*; @@ -26,11 +28,6 @@ import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService; public class PrepareResultCommunitySetStep1 { private static final Logger log = LoggerFactory.getLogger(PrepareResultCommunitySetStep1.class); - private static final String COMMUNITY_LIST_XQUERY = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType')" - + " where $x//CONFIGURATION/context[./@type='community' or ./@type='ri']" - + " and $x//CONFIGURATION/context/param[./@name='status']/text() != 'hidden'" - + " return $x//CONFIGURATION/context/@id/string()"; - /** * associates to each result the set of community contexts they are associated to; associates to each target of a * relation with allowed semantics the set of community context it could possibly inherit from the source of the @@ -88,10 +85,10 @@ public class PrepareResultCommunitySetStep1 { final List allowedsemrel = Arrays.asList(parser.get("allowedsemrels").split(";")); log.info("allowedSemRel: {}", new Gson().toJson(allowedsemrel)); - final String isLookupUrl = parser.get("isLookUpUrl"); - log.info("isLookupUrl: {}", isLookupUrl); + final String baseURL = parser.get("baseURL"); + log.info("baseURL: {}", baseURL); - final List communityIdList = getCommunityList(isLookupUrl); + final List communityIdList = getCommunityList(baseURL); log.info("communityIdList: {}", new Gson().toJson(communityIdList)); final String resultType = resultClassName.substring(resultClassName.lastIndexOf(".") + 1).toLowerCase(); @@ -159,9 +156,8 @@ public class PrepareResultCommunitySetStep1 { .json(outputResultPath); } - public static List getCommunityList(final String isLookupUrl) throws ISLookUpException { - ISLookUpService isLookUp = ISLookupClientFactory.getLookUpService(isLookupUrl); - return isLookUp.quickSearchProfile(COMMUNITY_LIST_XQUERY); + public static List getCommunityList(final String baseURL) throws IOException { + return Utils.getCommunityIdList(baseURL); } } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java index f31a262307..bb7ff1fb7b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java @@ -100,6 +100,12 @@ public class SparkResultToCommunityThroughSemRelJob { .mode(SaveMode.Overwrite) .option("compression", "gzip") .json(outputPath); + + readPath(spark, outputPath, resultClazz) + .write() + .mode(SaveMode.Overwrite) + .option("compression","gzip") + .json(inputPath); } private static MapFunction, R> contextUpdaterFn() { diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json index 8c99da673c..271db10bb7 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json @@ -1,7 +1,7 @@ [ { - "paramName":"is", - "paramLongName":"isLookUpUrl", + "paramName":"bu", + "paramLongName":"baseURL", "paramDescription": "URL of the isLookUp Service", "paramRequired": true }, diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml index 81b51443c6..916eb8b7ce 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml @@ -9,8 +9,8 @@ the semantic relationships allowed for propagation - isLookUpUrl - the isLookup service endpoint + baseURL + the baseurl for the comminity APIs outputPath @@ -116,7 +116,7 @@ --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication --outputPath${workingDir}/preparedInfo/targetCommunityAssoc --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} + --baseURL${baseURL} diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/config-default.xml new file mode 100644 index 0000000000..d262cb6e05 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/config-default.xml @@ -0,0 +1,30 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + hiveMetastoreUris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + hiveJdbcUrl + jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000 + + + hiveDbName + openaire + + + oozie.launcher.mapreduce.user.classpath.first + true + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/import.txt b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/import.txt new file mode 100644 index 0000000000..b202594148 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/import.txt @@ -0,0 +1,10 @@ +## This is a classpath-based import file (this header is required) +orcid_propagation classpath eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app +bulk_tagging classpath eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app +affiliation_inst_repo classpath eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app +entity_semantic_relation classpath eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app +community_organization classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app +result_project classpath eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app +community_project classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app +community_sem_rel classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app +country_propagation classpath eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml new file mode 100644 index 0000000000..1e6736bf44 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml @@ -0,0 +1,324 @@ + + + + + sourcePath + the source path + + + allowedsemrelsorcidprop + the semantic relationships allowed for propagation + + + allowedsemrelsresultproject + the allowed semantics + + + allowedsemrelscommunitysemrel + the semantic relationships allowed for propagation + + + datasourceWhitelistForCountryPropagation + the white list + + + allowedtypes + the allowed types + + + outputPath + the output path + + + organizationtoresultcommunitymap + organization community map + + + pathMap + the json path associated to each selection field + + + blacklist + list of datasources in blacklist for the affiliation from instrepo propagation + + + + hiveDbName + the target hive database name + + + hiveJdbcUrl + hive server jdbc url + + + hiveMetastoreUris + hive server metastore URIs + + + sparkDriverMemory + memory for driver process + + + sparkExecutorMemory + memory for individual executor + + + sparkExecutorCores + number of cores used by single executor + + + oozieActionShareLibForSpark2 + oozie action sharelib for spark 2.* + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + spark 2.* extra listeners classname + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + spark 2.* sql query execution listeners classname + + + spark2YarnHistoryServerAddress + spark 2.* yarn history server address + + + spark2EventLogDir + spark 2.* event log dir location + + + + + ${jobTracker} + ${nameNode} + + + mapreduce.job.queuename + ${queueName} + + + oozie.launcher.mapred.job.queue.name + ${oozieLauncherQueueName} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + ${wf:conf('resumeFrom') eq 'BulkTagging'} + ${wf:conf('resumeFrom') eq 'AffiliationInstitutionalRepository'} + ${wf:conf('resumeFrom') eq 'AffiliationSemanticRelation'} + ${wf:conf('resumeFrom') eq 'CommunityOrganization'} + ${wf:conf('resumeFrom') eq 'ResultProject'} + ${wf:conf('resumeFrom') eq 'CommunityProject'} + ${wf:conf('resumeFrom') eq 'CommunitySemanticRelation'} + ${wf:conf('resumeFrom') eq 'CountryPropagation'} + + + + + + + + ${wf:appPath()}/orcid_propagation + + + + + sourcePath + ${sourcePath} + + + allowedsemrels + ${allowedsemrelsorcidprop} + + + outputPath + ${outputPath} + + + + + + + + + + ${wf:appPath()}/bulk_tagging + + + + + sourcePath + ${outputPath} + + + baseURL + ${baseURL} + + + pathMap + ${pathMap} + + + + + + + + + + ${wf:appPath()}/affiliation_inst_repo + + + + + sourcePath + ${outputPath} + + + blacklist + ${blacklist} + + + + + + + + + + ${wf:appPath()}/affiliation_semantic_relation + + + + + sourcePath + ${outputPath} + + + + + + + + + + ${wf:appPath()}/community_organization + + + + + sourcePath + ${outputPath} + + + baseURL + ${baseURL} + + + + + + + + + + ${wf:appPath()}/result_project + + + + + sourcePath + ${outputPath} + + + allowedsemrels + ${allowedsemrelsresultproject} + + + + + + + + + + ${wf:appPath()}/community_project + + + + + sourcePath + ${outputPath} + + + + + + + + + + ${wf:appPath()}/community_sem_rel + + + + + sourcePath + ${outputPath} + + + allowedsemrels + ${allowedsemrelscommunitysemrel} + + + baseURL + ${baseURL} + + + + + + + + + + ${wf:appPath()}/country_propagation + + + + + sourcePath + ${outputPath} + + + whitelist + ${datasourceWhitelistForCountryPropagation} + + + allowedtypes + ${allowedtupes} + + + + + + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml new file mode 100644 index 0000000000..fe82ae1940 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml @@ -0,0 +1,54 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml new file mode 100644 index 0000000000..a735e2b0ee --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml @@ -0,0 +1,66 @@ + + + + sourcePath + the source path + + + pathMap + the json path associated to each selection field + + + baseURL + The URL to access the community APIs + + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + yarn-cluster + cluster + bulkTagging-publication + eu.dnetlib.dhp.bulktag.SparkBulkTagJob + dhp-enrichment-${projectVersion}.jar + + --num-executors=${sparkExecutorNumber} + --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} + + --sourcePath${sourcePath}/ + --workingPath${workingDir}/bulktag/ + --pathMap${pathMap} + --baseURL${baseURL} + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml new file mode 100644 index 0000000000..2744ea92ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml new file mode 100644 index 0000000000..1fbaeb5d55 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml @@ -0,0 +1,316 @@ + + + + sourcePath + the source path + + + whitelist + the white list + + + allowedtypes + the allowed types + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + yarn + cluster + PrepareDatasourceCountryAssociation + eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath} + --whitelist${whitelist} + --allowedtypes${allowedtypes} + --workingPath${workingDir}/country + + + + + + + + + + + + + + + yarn + cluster + prepareResultCountry-Publication + eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/publication + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + + + + + + + + yarn + cluster + prepareResultCountry-Dataset + eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/dataset + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + + + + + + + + yarn + cluster + prepareResultCountry-ORP + eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/otherresearchproduct + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + + + + + + + + yarn + cluster + prepareResultCountry-Software + eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/software + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + + + + + + + + + + + + + + + + + yarn + cluster + countryPropagationForPublications + eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/publication + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + + + + + + + + + yarn + cluster + countryPropagationForDataset + eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/dataset + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + + + + + + + + + yarn + cluster + countryPropagationForORP + eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/otherresearchproduct + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + + + + + + + + + yarn + cluster + countryPropagationForSoftware + eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --sourcePath${sourcePath}/software + --workingPath${workingDir}/country + --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json new file mode 100644 index 0000000000..b599373318 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json @@ -0,0 +1,50 @@ +[ + { + "paramName":"gp", + "paramLongName":"graphPath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName":"lp", + "paramLongName":"leavesPath", + "paramDescription": "true if the new version of the graph must be saved", + "paramRequired": false + }, + { + "paramName":"cp", + "paramLongName":"childParentPath", + "paramDescription": "path where to store/find association from datasource and organization", + "paramRequired": true + }, + { + "paramName":"rp", + "paramLongName":"resultOrgPath", + "paramDescription": "path where to store/find already linked results and organizations", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + }, + { + "paramName": "rep", + "paramLongName": "relationPath", + "paramDescription": "the path where to store the selected subset of relations", + "paramRequired": false + }, + { + "paramName": "pop", + "paramLongName": "projectOrganizationPath", + "paramDescription": "the number of iterations to be computed", + "paramRequired": true + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json new file mode 100644 index 0000000000..66a7f5b2f5 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json @@ -0,0 +1,62 @@ +[ + { + "paramName":"rep", + "paramLongName":"relationPath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName":"lp", + "paramLongName":"leavesPath", + "paramDescription": "true if the new version of the graph must be saved", + "paramRequired": false + }, + { + "paramName":"cp", + "paramLongName":"childParentPath", + "paramDescription": "path where to store/find association from datasource and organization", + "paramRequired": true + }, + { + "paramName":"rp", + "paramLongName":"resultOrgPath", + "paramDescription": "path where to store/find already linked results and organizations", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + }, + { + "paramName": "wd", + "paramLongName": "workingDir", + "paramDescription": "true if it is a test running", + "paramRequired": false + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + }, + { + "paramName": "it", + "paramLongName": "iterations", + "paramDescription": "the number of iterations to be computed", + "paramRequired": false + }, + { + "paramName": "pop", + "paramLongName": "projectOrganizationPath", + "paramDescription": "the number of iterations to be computed", + "paramRequired": true + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/config-default.xml new file mode 100644 index 0000000000..2744ea92ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml new file mode 100644 index 0000000000..e3f3c1758d --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml @@ -0,0 +1,93 @@ + + + + sourcePath + the source path + + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + yarn + cluster + PrepareResultOrganizationAssociation + eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --graphPath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --leavesPath${workingDir}/entitiesSemanticRelation/preparedInfo/leavesPath + --childParentPath${workingDir}/entitiesSemanticRelation/preparedInfo/childParentPath + --resultOrgPath${workingDir}/entitiesSemanticRelation/preparedInfo/resultOrgPath + --projectOrganizationPath${workingDir}/entitiesSemanticRelation/preparedInfo/projectOrganizationPath + --relationPath${workingDir}/entitiesSemanticRelation/preparedInfo/relation + + + + + + + + yarn + cluster + resultToOrganizationFromSemRel + eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.sql.shuffle.partitions=3840 + + --relationPath${workingDir}/entitiesSemanticRelation/preparedInfo/relation + --outputPath${sourcePath}/relation + --leavesPath${workingDir}/entitiesSemanticRelation/preparedInfo/leavesPath + --childParentPath${workingDir}/entitiesSemanticRelation/preparedInfo/childParentPath + --resultOrgPath${workingDir}/entitiesSemanticRelation/preparedInfo/resultOrgPath + --projectOrganizationPath${workingDir}/entitiesSemanticRelation/preparedInfo/projectOrganizationPath + --hive_metastore_uris${hive_metastore_uris} + --workingDir${workingDir}/entitiesSemanticRelation/working + --iterations${iterations} + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/config-default.xml new file mode 100644 index 0000000000..8d2c341057 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml new file mode 100644 index 0000000000..6d800d6e20 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml @@ -0,0 +1,369 @@ + + + + sourcePath + the source path + + + allowedsemrels + the semantic relationships allowed for propagation + + + outputPath + the output path + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + + + + + + + + + + + + + + ${jobTracker} + ${nameNode} + ${nameNode}/${sourcePath}/relation + ${nameNode}/${outputPath}/relation + + + + + + + + ${jobTracker} + ${nameNode} + ${nameNode}/${sourcePath}/organization + ${nameNode}/${outputPath}/organization + + + + + + + + ${jobTracker} + ${nameNode} + ${nameNode}/${sourcePath}/project + ${nameNode}/${outputPath}/project + + + + + + + + ${jobTracker} + ${nameNode} + ${nameNode}/${sourcePath}/datasource + ${nameNode}/${outputPath}/datasource + + + + + + + + + + yarn + cluster + ORCIDPropagation-PreparePhase1-Publications + eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.sql.shuffle.partitions=3840 + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --allowedsemrels${allowedsemrels} + + + + + + + + yarn + cluster + ORCIDPropagation-PreparePhase1-Dataset + eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --allowedsemrels${allowedsemrels} + + + + + + + + yarn + cluster + ORCIDPropagation-PreparePhase1-ORP + eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --allowedsemrels${allowedsemrels} + + + + + + + + yarn + cluster + ORCIDPropagation-PreparePhase1-Software + eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --allowedsemrels${allowedsemrels} + + + + + + + + + + yarn + cluster + ORCIDPropagation-PreparePhase2 + eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep2 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${workingDir}/orcidprop + --outputPath${workingDir}/orcidprop/mergedOrcidAssoc + + + + + + + + + + + + + + + yarn + cluster + ORCIDPropagation-Publication + eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + --conf spark.sql.shuffle.partitions=3840 + + --possibleUpdatesPath${workingDir}/orcidprop/mergedOrcidAssoc + --sourcePath${sourcePath}/publication + --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + --outputPath${outputPath}/publication + + + + + + + + yarn + cluster + ORCIDPropagation-Dataset + eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + + --possibleUpdatesPath${workingDir}/orcidprop/mergedOrcidAssoc + --sourcePath${sourcePath}/dataset + --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + --outputPath${outputPath}/dataset + + + + + + + + yarn + cluster + ORCIDPropagation-ORP + eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + + --possibleUpdatesPath${workingDir}/orcidprop/mergedOrcidAssoc + --sourcePath${sourcePath}/otherresearchproduct + --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + --outputPath${outputPath}/otherresearchproduct + + + + + + + + yarn + cluster + ORCIDPropagation-Software + eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.speculation=false + --conf spark.hadoop.mapreduce.map.speculative=false + --conf spark.hadoop.mapreduce.reduce.speculative=false + + --possibleUpdatesPath${workingDir}/orcidprop/mergedOrcidAssoc + --sourcePath${sourcePath}/software + --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + --outputPath${outputPath}/software + + + + + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/config-default.xml new file mode 100644 index 0000000000..caf3c60500 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/config-default.xml @@ -0,0 +1,63 @@ + + + jobTracker + yarnRM + + + + nameNode + + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml new file mode 100644 index 0000000000..93a2f98be3 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml @@ -0,0 +1,94 @@ + + + + sourcePath + the source path + + + allowedsemrels + the allowed semantics + + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + yarn + cluster + PrepareProjectResultsAssociation + eu.dnetlib.dhp.projecttoresult.PrepareProjectResultsAssociation + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --sourcePath${sourcePath}/relation + --allowedsemrels${allowedsemrels} + --hive_metastore_uris${hive_metastore_uris} + --potentialUpdatePath${workingDir}/resultproject/preparedInfo/potentialUpdates + --alreadyLinkedPath${workingDir}/resultproject/preparedInfo/alreadyLinked + + + + + + + + yarn + cluster + ProjectToResultPropagation + eu.dnetlib.dhp.projecttoresult.SparkResultToProjectThroughSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --hive_metastore_uris${hive_metastore_uris} + --outputPath${sourcePath}/relation + --potentialUpdatePath${workingDir}/resultproject/preparedInfo/potentialUpdates + --alreadyLinkedPath${workingDir}/resultproject/preparedInfo/alreadyLinked + + + + + + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/config-default.xml new file mode 100644 index 0000000000..2744ea92ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml new file mode 100644 index 0000000000..8aec530cc9 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml @@ -0,0 +1,88 @@ + + + + sourcePath + the source path + + + baseURL + the baseURL from where to reach the community APIs + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + yarn + cluster + Prepare-Community-Result-Organization + eu.dnetlib.dhp.resulttocommunityfromorganization.PrepareResultCommunitySet + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${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} + + --sourcePath${sourcePath}/relation + --outputPath${workingDir}/communityorganization/preparedInfo/resultCommunityList + --hive_metastore_uris${hive_metastore_uris} + --baseURL${baseURL} + + + + + + + + yarn + cluster + community2resultfromorganization-Publication + eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${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} + + --preparedInfoPath${workingDir}/preparedInfo/resultCommunityList + --sourcePath${sourcePath}/ + --outputPath${workingDir}/resulttocommunityfromorganization/ + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json new file mode 100644 index 0000000000..0db8085d19 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json @@ -0,0 +1,28 @@ +[ + { + "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 + }, + { + "paramName": "p", + "paramLongName": "preparedInfoPath", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": true + } + +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json new file mode 100644 index 0000000000..cbc01c2d5a --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json @@ -0,0 +1,28 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + }, + { + "paramName": "bu", + "paramLongName": "baseURL", + "paramDescription": "the path used to store temporary output files", + "paramRequired": false + } + +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/config-default.xml new file mode 100644 index 0000000000..2744ea92ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml new file mode 100644 index 0000000000..90ed2e0b6f --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml @@ -0,0 +1,90 @@ + + + + sourcePath + the source path + + + baseURL + the base URL to use to select the right community APIs + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + yarn + cluster + Prepare-Community-Result-Organization + eu.dnetlib.dhp.resulttocommunityfromproject.PrepareResultCommunitySet + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${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} + + --sourcePath${sourcePath}/relation + --outputPath${workingDir}/communitythroughproject/preparedInfo/resultCommunityList + --baseURL${baseURL} + + + + + + + + yarn + cluster + community2resultfromproject + eu.dnetlib.dhp.resulttocommunityfromproject.SparkResultToCommunityFromProject + dhp-enrichment-${projectVersion}.jar + + --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=${spark2MaxExecutors} + + --preparedInfoPath${workingDir}/communitythroughproject/preparedInfo/resultCommunityList + --sourcePath${sourcePath}/ + --outputPath${workingDir}/communitythroughproject/ + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/config-default.xml new file mode 100644 index 0000000000..2744ea92ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml new file mode 100644 index 0000000000..be88c45bdc --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml @@ -0,0 +1,305 @@ + + + + sourcePath + the source path + + + allowedsemrels + the semantic relationships allowed for propagation + + + baseURL + the isLookup service endpoint + + + outputPath + the output path + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + + + + + + + yarn + cluster + ResultToCommunitySemRel-PreparePhase1-Publications + eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc + --allowedsemrels${allowedsemrels} + --baseURL${baseURL} + + + + + + + + yarn + cluster + ResultToCommunitySemRel-PreparePhase1-Dataset + eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc + --allowedsemrels${allowedsemrels} + --baseURL${baseURL} + + + + + + + + yarn + cluster + ResultToCommunitySemRel-PreparePhase1-ORP + eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc + --allowedsemrels${allowedsemrels} + --baseURL${baseURL} + + + + + + + + yarn + cluster + ResultToCommunitySemRel-PreparePhase1-Software + eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc + --allowedsemrels${allowedsemrels} + --baseURL${baseURL} + + + + + + + + + + yarn + cluster + ResultToCommunityEmRelPropagation-PreparePhase2 + eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep2 + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc + --outputPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc + + + + + + + + + + + + + + + yarn + cluster + Result2CommunitySemRelPropagation-Publication + eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc + --sourcePath${sourcePath}/publication + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + --outputPath${workingDir}/communitysemrel/publication + + + + + + + + + yarn + cluster + Result2CommunitySemRelPropagation-Dataset + eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc + --sourcePath${sourcePath}/dataset + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + --outputPath${workingDir}/communitysemrel/dataset + + + + + + + + + yarn + cluster + Result2CommunitySemRelPropagation-ORP + eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc + --sourcePath${sourcePath}/otherresearchproduct + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + --outputPath${workingDir}/communitysemrel/otherresearchproduct + + + + + + + + + yarn + cluster + Result2CommunitySemRelPropagation-Software + eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc + --sourcePath${sourcePath}/software + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + --outputPath${workingDir}/communitysemrel/software + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/config-default.xml new file mode 100644 index 0000000000..2744ea92ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml new file mode 100644 index 0000000000..8281130f37 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml @@ -0,0 +1,182 @@ + + + + sourcePath + the source path + + + blacklist + The list of institutional repositories that should not be used for the propagation + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + yarn + cluster + PrepareResultOrganizationAssociation + eu.dnetlib.dhp.resulttoorganizationfrominstrepo.PrepareResultInstRepoAssociation + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --sourcePath${sourcePath} + --workingPath${workingDir}/affiliationInstRepo + --blacklist${blacklist} + + + + + + + + + + + + + + + yarn + cluster + resultToOrganizationFromInstRepoPropagationForPublications + eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath}/publication + --outputPath${sourcePath}/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + + + + + + + + yarn + cluster + resultToOrganizationFromInstRepoPropagationForDataset + eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath}/dataset + --outputPath${sourcePath}/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + + + + + + + + yarn + cluster + resultToOrganizationFromInstRepoPropagationForORP + eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath}/otherresearchproduct + --outputPath${sourcePath}/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + + + + + + + + yarn + cluster + resultToOrganizationFromInstRepoPropagationForSoftware + eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${sourcePath}/software + --outputPath${sourcePath}/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked + --hive_metastore_uris${hive_metastore_uris} + --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml new file mode 100644 index 0000000000..2744ea92ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 6G + + + sparkExecutorCores + 1 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml new file mode 100644 index 0000000000..7918df120b --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml @@ -0,0 +1,97 @@ + + + + sourcePath + the source path + + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + yarn + cluster + PrepareResultOrganizationAssociation + eu.dnetlib.dhp.resulttoorganizationfromsemrel.PrepareInfo + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --graphPath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --leavesPath${workingDir}/affiliationSemanticRelation/preparedInfo/leavesPath + --childParentPath${workingDir}/affiliationSemanticRelation/preparedInfo/childParentPath + --resultOrgPath${workingDir}/affiliationSemanticRelation/preparedInfo/resultOrgPath + --relationPath${workingDir}/affiliationSemanticRelation/preparedInfo/relation + + + + + + + + yarn + cluster + resultToOrganizationFromSemRel + eu.dnetlib.dhp.resulttoorganizationfromsemrel.SparkResultToOrganizationFromSemRel + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --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.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.sql.shuffle.partitions=3840 + + --relationPath${workingDir}/affiliationSemanticRelation/preparedInfo/relation + --outputPath${sourcePath} + --leavesPath${workingDir}/affiliationSemanticRelation/preparedInfo/leavesPath + --childParentPath${workingDir}/affiliationSemanticRelation/preparedInfo/childParentPath + --resultOrgPath${workingDir}/affiliationSemanticRelation/preparedInfo/resultOrgPath + --hive_metastore_uris${hive_metastore_uris} + --workingDir${workingDir}/affiliationSemanticRelation/working + --iterations${iterations} + + + + + + + + + + + + + + + + + \ No newline at end of file From d4eedada71436a7cae1a5ab154598503b8f36e91 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Sat, 9 Dec 2023 15:20:11 +0100 Subject: [PATCH 02/17] adjusting workflow definition --- .../main/java/eu/dnetlib/dhp/api/Utils.java | 6 ++-- .../dnetlib/dhp/bulktag/SparkBulkTagJob.java | 17 +++++----- .../PrepareDatasourceCountryAssociation.java | 2 +- .../SparkCountryPropagationJob.java | 8 ++--- ...kResultToCommunityFromOrganizationJob.java | 8 ++--- .../SparkResultToCommunityFromProject.java | 8 ++--- .../PrepareResultCommunitySetStep1.java | 2 +- ...parkResultToCommunityThroughSemRelJob.java | 8 ++--- .../eu/dnetlib/dhp/wf/main/job.properties | 15 +++++++++ .../bulktag/oozie_app/workflow.xml | 2 +- .../oozie_app/workflow.xml | 31 +++++++++++++------ 11 files changed, 66 insertions(+), 41 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java index bb30f55d6f..06d0f95c25 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java @@ -169,7 +169,9 @@ public class Utils implements Serializable { } public static List getCommunityIdList(String baseURL) throws IOException { - return getValidCommunities(baseURL).stream() - .map(community -> community.getId()).collect(Collectors.toList()); + return getValidCommunities(baseURL) + .stream() + .map(community -> community.getId()) + .collect(Collectors.toList()); } } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java index 5745515baa..51307ccd1e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java @@ -105,7 +105,6 @@ public class SparkBulkTagJob { Map>> dsm = cc.getEoscDatasourceMap(); for (String ds : datasources.collectAsList()) { - // final String dsId = ds.substring(3); if (!dsm.containsKey(ds)) { ArrayList> eoscList = new ArrayList<>(); dsm.put(ds, eoscList); @@ -116,13 +115,11 @@ public class SparkBulkTagJob { private static boolean isOKDatasource(Datasource ds) { final String compatibility = ds.getOpenairecompatibility().getClassid(); - boolean isOk = (compatibility.equalsIgnoreCase(OPENAIRE_3) || + return (compatibility.equalsIgnoreCase(OPENAIRE_3) || compatibility.equalsIgnoreCase(OPENAIRE_4) || compatibility.equalsIgnoreCase(OPENAIRE_CRIS) || compatibility.equalsIgnoreCase(OPENAIRE_DATA)) && ds.getCollectedfrom().stream().anyMatch(cf -> cf.getKey().equals(EOSC)); - - return isOk; } private static void execBulkTag( @@ -151,13 +148,13 @@ public class SparkBulkTagJob { .write() .mode(SaveMode.Overwrite) .option("compression", "gzip") - .json(outputPath + e.name());//writing the tagging in the working dir for entity + .json(outputPath + e.name());// writing the tagging in the working dir for entity - readPath(spark, outputPath + e.name(), resultClazz) //copy the tagging in the actual result output path - .write() - .mode(SaveMode.Overwrite) - .option("compression","gzip") - .json(inputPath + e.name()); + readPath(spark, outputPath + e.name(), resultClazz) // copy the tagging in the actual result output path + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(inputPath + e.name()); }); } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java index b1720d19d1..2ffe6f36de 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java @@ -66,7 +66,7 @@ public class PrepareDatasourceCountryAssociation { conf, isSparkSessionManaged, spark -> { - //removeOutputDir(spark, outputPath); + // removeOutputDir(spark, outputPath); prepareDatasourceCountryAssociation( spark, Arrays.asList(parser.get("whitelist").split(";")), diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java index 2b0dd76281..17247f8125 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java @@ -98,10 +98,10 @@ public class SparkCountryPropagationJob { .json(outputPath); readPath(spark, outputPath, resultClazz) - .write() - .mode(SaveMode.Overwrite) - .option("compression","gzip") - .json(sourcePath); + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(sourcePath); } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java index 9152b1f5a9..adb7feef7e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java @@ -94,10 +94,10 @@ public class SparkResultToCommunityFromOrganizationJob { .json(outputPath + e.name()); readPath(spark, outputPath + e.name(), resultClazz) - .write() - .mode(SaveMode.Overwrite) - .option("compression","gzip") - .json(inputPath + e.name()); + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(inputPath + e.name()); } }); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java index 5478915848..229ac7e32e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java @@ -104,10 +104,10 @@ public class SparkResultToCommunityFromProject implements Serializable { .json(outputPath + e.name()); readPath(spark, outputPath + e.name(), resultClazz) - .write() - .mode(SaveMode.Overwrite) - .option("compression","gzip") - .json(inputPath + e.name()); + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(inputPath + e.name()); } }); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java index 73c4e2d7c0..40c074a6e5 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java @@ -8,7 +8,6 @@ import java.io.IOException; import java.util.Arrays; import java.util.List; -import eu.dnetlib.dhp.api.Utils; import org.apache.commons.io.IOUtils; import org.apache.spark.SparkConf; import org.apache.spark.sql.*; @@ -17,6 +16,7 @@ import org.slf4j.LoggerFactory; import com.google.gson.Gson; +import eu.dnetlib.dhp.api.Utils; import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.resulttocommunityfromorganization.ResultCommunityList; import eu.dnetlib.dhp.schema.oaf.Relation; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java index bb7ff1fb7b..a107378499 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java @@ -102,10 +102,10 @@ public class SparkResultToCommunityThroughSemRelJob { .json(outputPath); readPath(spark, outputPath, resultClazz) - .write() - .mode(SaveMode.Overwrite) - .option("compression","gzip") - .json(inputPath); + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(inputPath); } private static MapFunction, R> contextUpdaterFn() { diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties new file mode 100644 index 0000000000..6b9b5063fe --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties @@ -0,0 +1,15 @@ +sourcePath=/tmp/beta_provision/graph/09_graph_dedup_enriched +resumeFrom=OrcidPropagation +allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo +allowedsemrelsresultproject=isSupplementedBy;isSupplementTo +allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo +datasourceWhitelistForCountryPropagation=10|openaire____::3795d6478e30e2c9f787d427ff160944;10|opendoar____::16e6a3326dd7d868cbc926602a61e4d0;10|eurocrisdris::fe4903425d9040f680d8610d9079ea14 +allowedtypes=pubsrepository::institutional +outputPath=/tmp/miriam/enrichment_one_step +organizationtoresultcommunitymap={"20|corda__h2020::3fb05a9524c3f790391261347852f638":["mes","euromarine"], "20|corda__h2020::e8dbe14cca9bf6fce09d468872f813f8":["mes","euromarine"], "20|snsf________::9b253f265e3bef5cae6d881fdf61aceb":["mes","euromarine"],"20|ukri________::e054eea0a47665af8c3656b5785ccf76":["mes","euromarine"],"20|corda__h2020::edc18d67c9b11fb616ca9f6e1db1b151":["mes","euromarine"],"20|ukri________::d5736d9da90521ddcdc7828a05a85e9a":["mes","euromarine"],"20|corda__h2020::f5d418d3aa1cf817ddefcc3fdc039f27":["mes","euromarine"],"20|snsf________::8fa091f8f25a846779acb4ea97b50aef":["mes","euromarine"],"20|corda__h2020::81e020977211c2c40fae2e1a50bffd71":["mes","euromarine"],"20|corda_______::81e020977211c2c40fae2e1a50bffd71":["mes","euromarine"],"20|snsf________::31d0a100e54e3cdb3c6f52d91e638c78":["mes","euromarine"],"20|corda__h2020::ea379ef91b8cc86f9ac5edc4169292db":["mes","euromarine"],"20|corda__h2020::f75ee2ee48e5cb0ec8c8d30aaa8fef70":["mes","euromarine"],"20|ukri________::e16010089551a1a9182a94604fc0ea59":["mes","euromarine"],"20|corda__h2020::38531a2cce7c5c347ffc439b07c1f43b":["mes","euromarine"],"20|corda_______::38531a2cce7c5c347ffc439b07c1f43b":["mes","euromarine"],"20|grid________::b2cbbf5eadbbf87d534b022bad3191d7":["mes","euromarine"],"20|snsf________::74730ef1439d7f7636a8be58a6b471b8":["mes","euromarine"],"20|nsf_________::ad72e19043a5a467e35f9b444d11563e":["mes","euromarine"],"20|ukri________::0fc3e92500290902a2d38ec2445e74c3":["mes","euromarine"],"20|grid________::ad2c29905da0eb3c06b3fa80cacd89ea":["mes","euromarine"],"20|corda__h2020::30b53e4d63d3724f00acb9cbaca40860":["mes","euromarine"],"20|corda__h2020::f60f84bee14ad93f0db0e49af1d5c317":["mes","euromarine"], "20|corda__h2020::7bf251ac3765b5e89d82270a1763d09f":["mes","euromarine"], "20|corda__h2020::65531bd11be9935948c7f2f4db1c1832":["mes","euromarine"], "20|corda__h2020::e0e98f86bbc76638bbb72a8fe2302946":["mes","euromarine"], "20|snsf________::3eb43582ac27601459a8d8b3e195724b":["mes","euromarine"], "20|corda__h2020::af2481dab65d06c8ea0ae02b5517b9b6":["mes","euromarine"], "20|corda__h2020::c19d05cfde69a50d3ebc89bd0ee49929":["mes","euromarine"], "20|corda__h2020::af0bfd9fc09f80d9488f56d71a9832f0":["mes","euromarine"], "20|ukri________::f33c02afb0dc66c49d0ed97ca5dd5cb0":["beopen"], "20|grid________::a867f78acdc5041b34acfe4f9a349157":["beopen"], "20|grid________::7bb116a1a9f95ab812bf9d2dea2be1ff":["beopen"], "20|corda__h2020::6ab0e0739dbe625b99a2ae45842164ad":["beopen"], "20|corda__h2020::8ba50792bc5f4d51d79fca47d860c602":["beopen"], "20|corda_______::8ba50792bc5f4d51d79fca47d860c602":["beopen"], "20|corda__h2020::e70e9114979e963eef24666657b807c3":["beopen"], "20|corda_______::e70e9114979e963eef24666657b807c3":["beopen"], "20|corda_______::15911e01e9744d57205825d77c218737":["beopen"], "20|opendoar____::056a41e24e2a9a67215e87bbee6a80ab":["beopen"], "20|opendoar____::7f67f2e6c6fbb0628f8160fcd3d92ae3":["beopen"], "20|grid________::a8ecfd7c084e561168bcbe6bf0daf3e3":["beopen"], "20|corda_______::7bbe6cc5d8ec1864739a04b0d020c9e9":["beopen"], "20|corda_______::3ff558e30c2e434d688539548300b050":["beopen"], "20|corda__h2020::5ffee5b3b83b33a8cf0e046877bd3a39":["beopen"], "20|corda__h2020::5187217e2e806a6df3579c46f82401bc":["beopen"], "20|grid________::5fa7e2709bcd945e26bfa18689adeec1":["beopen"], "20|corda_______::d8696683c53027438031a96ad27c3c07":["beopen"], "20|corda__h2020::d8696683c53027438031a96ad27c3c07":["beopen"], "20|ukri________::23a79ebdfa59790864e4a485881568c1":["beopen"], "20|corda__h2020::b76cf8fe49590a966953c37e18608af9":["beopen"], "20|grid________::d2f0204126ee709244a488a4cd3b91c2":["beopen"], "20|corda__h2020::05aba9d2ed17533d15221e5655ac11e6":["beopen"], "20|grid________::802401579481dc32062bdee69f5e6a34":["beopen"], "20|corda__h2020::3f6d9d54cac975a517ba6b252c81582d":["beopen"], "20|openorgs____::d11f981828c485cd23d93f7f24f24db1":["eut"], "20|openorgs____::e66fe5dd092752e1dd6fd29fc699933a":["eut"], "20|openorgs____::526468206bca24c1c90da6a312295cf4":["eut"], "20|openorgs____::08e311e656e65ccb32e07c66b15b6ff7":["eut"], "20|openorgs____::55a1f889758964b77682904218fdb298":["eut"], "20|openorgs____::530092b6970d60a5329beb9f39e8d7d4":["eut"], "20|openorgs____::aadafa39392b3e200102596a3a4aad9d":["eut"], "20|openorgs____::c3fe999c74fad308132b8a5971367dce":["eut"], "20|openorgs____::1624ff7c01bb641b91f4518539a0c28a":["aurora"], "20|openorgs____::cdda7cfe17c89eb50628ec2eb1f8acd2":["aurora"], "20|openorgs____::818b75030e0e40612d69e049843ede7e":["aurora"], "20|openorgs____::0b0102bae51f4f4ef5ba57fbe1523b92":["aurora"], "20|openorgs____::ed47496b44722f0e9d7b98898189be0d":["aurora"], "20|openorgs____::eb0669daa9efeb898a3090d8aac7c953":["aurora"], "20|openorgs____::eb391317ed0dc684aa81ac16265de041":["aurora"], "20|openorgs____::f7cfcc98245e22c7d6e321cde930e746":["aurora"], "20|openorgs____::f33179d3306ba2599f7a898b056b604f":["aurora"], "20|pending_org_::75c41e6dd18466709ef359323d96fa05":["aurora"]} +pathMap={"author" : "$['author'][*]['fullname']", "title" : "$['title'][*]['value']", "orcid":"orcid":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']", "contributor" : "$['contributor'][*]['value']", "description" : "$['description'][*]['value']"} +blacklist=empty +allowedpids=orcid;orcid_pending +baseURL = https://services.openaire.eu/openaire/community/ + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml index a735e2b0ee..307997d4cd 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml @@ -51,7 +51,7 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --sourcePath${sourcePath}/ - --workingPath${workingDir}/bulktag/ + --outputPath${workingDir}/bulktag/ --pathMap${pathMap} --baseURL${baseURL} diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml index 6d800d6e20..8e945ee5ac 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml @@ -80,7 +80,14 @@ - + + + + + + + + @@ -258,6 +265,7 @@ --sourcePath${sourcePath}/publication --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication --outputPath${outputPath}/publication + --hive_metastore_uris${hive_metastore_uris} @@ -288,6 +296,7 @@ --sourcePath${sourcePath}/dataset --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset --outputPath${outputPath}/dataset + --hive_metastore_uris${hive_metastore_uris} @@ -318,6 +327,7 @@ --sourcePath${sourcePath}/otherresearchproduct --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct --outputPath${outputPath}/otherresearchproduct + --hive_metastore_uris${hive_metastore_uris} @@ -348,21 +358,22 @@ --sourcePath${sourcePath}/software --resultTableNameeu.dnetlib.dhp.schema.oaf.Software --outputPath${outputPath}/software + --hive_metastore_uris${hive_metastore_uris} - + - - - - - - - - + + + + + + + + From 8752d275fae9bc7764cd2ee049b6321d44b70528 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Sat, 9 Dec 2023 15:24:45 +0100 Subject: [PATCH 03/17] removed not needed parameter --- .../SparkOrcidToResultFromSemRelJob.java | 7 ++++--- .../input_orcidtoresult_parameters.json | 6 ------ .../orcidtoresultfromsemrel/oozie_app/workflow.xml | 4 ---- 3 files changed, 4 insertions(+), 13 deletions(-) diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java index a38b4da2e8..998f4719ad 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java @@ -2,7 +2,8 @@ package eu.dnetlib.dhp.orcidtoresultfromsemrel; import static eu.dnetlib.dhp.PropagationConstant.*; -import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; + +import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; import java.util.List; import java.util.Optional; @@ -65,9 +66,9 @@ public class SparkOrcidToResultFromSemRelJob { Class resultClazz = (Class) Class.forName(resultClassName); SparkConf conf = new SparkConf(); - conf.set("hive.metastore.uris", parser.get("hive_metastore_uris")); - runWithSparkHiveSession( + + runWithSparkSession( conf, isSparkSessionManaged, spark -> { diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json index d8aa7eb9a9..3cbaa23bb6 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json @@ -11,12 +11,6 @@ "paramDescription": "true if the new version of the graph must be saved", "paramRequired": false }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, { "paramName": "out", "paramLongName": "outputPath", diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml index 8e945ee5ac..483a805b10 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml @@ -265,7 +265,6 @@ --sourcePath${sourcePath}/publication --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication --outputPath${outputPath}/publication - --hive_metastore_uris${hive_metastore_uris} @@ -296,7 +295,6 @@ --sourcePath${sourcePath}/dataset --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset --outputPath${outputPath}/dataset - --hive_metastore_uris${hive_metastore_uris} @@ -327,7 +325,6 @@ --sourcePath${sourcePath}/otherresearchproduct --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct --outputPath${outputPath}/otherresearchproduct - --hive_metastore_uris${hive_metastore_uris} @@ -358,7 +355,6 @@ --sourcePath${sourcePath}/software --resultTableNameeu.dnetlib.dhp.schema.oaf.Software --outputPath${outputPath}/software - --hive_metastore_uris${hive_metastore_uris} From 0d8e496a6317943a28282ffdd0ee5a4d735f61f7 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 15 Dec 2023 12:16:43 +0100 Subject: [PATCH 04/17] - --- .../SparkOrcidToResultFromSemRelJob.java | 2 - .../AppendNewRelations.java | 75 +++++++++++++++++++ .../PrepareResultInstRepoAssociation.java | 7 +- ...arkResultToOrganizationFromIstRepoJob.java | 2 +- .../input_prepareresultorg_parameters.json | 13 +--- .../eu/dnetlib/dhp/wf/main/job.properties | 17 ++++- .../oozie_app/workflow.xml | 36 +++++++-- 7 files changed, 131 insertions(+), 21 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java index 998f4719ad..5f9260e5dc 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java @@ -2,7 +2,6 @@ package eu.dnetlib.dhp.orcidtoresultfromsemrel; import static eu.dnetlib.dhp.PropagationConstant.*; - import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; import java.util.List; @@ -67,7 +66,6 @@ public class SparkOrcidToResultFromSemRelJob { SparkConf conf = new SparkConf(); - runWithSparkSession( conf, isSparkSessionManaged, diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java new file mode 100644 index 0000000000..a5884873b1 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java @@ -0,0 +1,75 @@ + +package eu.dnetlib.dhp.resulttoorganizationfrominstrepo; + +import static eu.dnetlib.dhp.PropagationConstant.*; +import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; + +import java.io.Serializable; +import java.util.Objects; +import java.util.Optional; + +import org.apache.commons.io.IOUtils; +import org.apache.spark.SparkConf; +import org.apache.spark.api.java.function.MapFunction; +import org.apache.spark.sql.Encoders; +import org.apache.spark.sql.SaveMode; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import eu.dnetlib.dhp.application.ArgumentApplicationParser; +import eu.dnetlib.dhp.bulktag.community.ResultTagger; +import eu.dnetlib.dhp.schema.common.ModelSupport; +import eu.dnetlib.dhp.schema.oaf.Relation; +import eu.dnetlib.dhp.schema.oaf.Result; + +/** + * @author miriam.baglioni + * @Date 09/12/23 + */ +public class AppendNewRelations implements Serializable { + + private static final Logger log = LoggerFactory.getLogger(AppendNewRelations.class); + + public static void main(String[] args) throws Exception { + + String jsonConfiguration = IOUtils + .toString( + AppendNewRelations.class + .getResourceAsStream( + "/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_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(); + + runWithSparkHiveSession( + conf, + isSparkSessionManaged, + spark -> appendNewRelation(spark, inputPath, outputPath)); + } + + private static void appendNewRelation(SparkSession spark, String inputPath, String outputPath) { + + readPath(spark, inputPath + "publication/relation", Relation.class) + .union(readPath(spark, inputPath + "dataset/relation", Relation.class)) + .union(readPath(spark, inputPath + "otherresearchproduct/relation", Relation.class)) + .union(readPath(spark, inputPath + "software/relation", Relation.class)) + .write() + .mode(SaveMode.Append) + .option("compression", "gzip") + .json(outputPath); + } + +} diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java index 1663afb32e..deec6fedc6 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java @@ -52,10 +52,13 @@ public class PrepareResultInstRepoAssociation { String inputPath = parser.get("sourcePath"); log.info("inputPath: {}", inputPath); - final String datasourceOrganizationPath = parser.get("datasourceOrganizationPath"); + final String workingPath = parser.get("workingPath"); + log.info("workingPath : {}", workingPath); + + final String datasourceOrganizationPath = workingPath + "/preparedInfo/datasourceOrganization"; log.info("datasourceOrganizationPath {}: ", datasourceOrganizationPath); - final String alreadyLinkedPath = parser.get("alreadyLinkedPath"); + final String alreadyLinkedPath = workingPath + "/preparedInfo/alreadyLinked"; log.info("alreadyLinkedPath {}: ", alreadyLinkedPath); List blacklist = Optional diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java index 0757ebccd4..bbad20e2d5 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java @@ -119,7 +119,7 @@ public class SparkResultToOrganizationFromIstRepoJob { "left_outer") .flatMap(createRelationFn(), Encoders.bean(Relation.class)) .write() - .mode(SaveMode.Append) + .mode(SaveMode.Overwrite) .option("compression", "gzip") .json(outputPath); } diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json index 2f00bacae3..3f4b1d151b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json @@ -11,16 +11,11 @@ "paramDescription": "the hive metastore uris", "paramRequired": true }, + { - "paramName":"dop", - "paramLongName":"datasourceOrganizationPath", - "paramDescription": "path where to store/find association from datasource and organization", - "paramRequired": true - }, - { - "paramName":"alp", - "paramLongName":"alreadyLinkedPath", - "paramDescription": "path where to store/find already linked results and organizations", + "paramName":"wp", + "paramLongName":"workingPath", + "paramDescription": "the working path", "paramRequired": true }, { diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties index 6b9b5063fe..243c1e99d1 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties @@ -1,5 +1,5 @@ sourcePath=/tmp/beta_provision/graph/09_graph_dedup_enriched -resumeFrom=OrcidPropagation +resumeFrom=AffiliationInstitutionalRepository allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo allowedsemrelsresultproject=isSupplementedBy;isSupplementTo allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo @@ -7,7 +7,20 @@ datasourceWhitelistForCountryPropagation=10|openaire____::3795d6478e30e2c9f787d4 allowedtypes=pubsrepository::institutional outputPath=/tmp/miriam/enrichment_one_step organizationtoresultcommunitymap={"20|corda__h2020::3fb05a9524c3f790391261347852f638":["mes","euromarine"], "20|corda__h2020::e8dbe14cca9bf6fce09d468872f813f8":["mes","euromarine"], "20|snsf________::9b253f265e3bef5cae6d881fdf61aceb":["mes","euromarine"],"20|ukri________::e054eea0a47665af8c3656b5785ccf76":["mes","euromarine"],"20|corda__h2020::edc18d67c9b11fb616ca9f6e1db1b151":["mes","euromarine"],"20|ukri________::d5736d9da90521ddcdc7828a05a85e9a":["mes","euromarine"],"20|corda__h2020::f5d418d3aa1cf817ddefcc3fdc039f27":["mes","euromarine"],"20|snsf________::8fa091f8f25a846779acb4ea97b50aef":["mes","euromarine"],"20|corda__h2020::81e020977211c2c40fae2e1a50bffd71":["mes","euromarine"],"20|corda_______::81e020977211c2c40fae2e1a50bffd71":["mes","euromarine"],"20|snsf________::31d0a100e54e3cdb3c6f52d91e638c78":["mes","euromarine"],"20|corda__h2020::ea379ef91b8cc86f9ac5edc4169292db":["mes","euromarine"],"20|corda__h2020::f75ee2ee48e5cb0ec8c8d30aaa8fef70":["mes","euromarine"],"20|ukri________::e16010089551a1a9182a94604fc0ea59":["mes","euromarine"],"20|corda__h2020::38531a2cce7c5c347ffc439b07c1f43b":["mes","euromarine"],"20|corda_______::38531a2cce7c5c347ffc439b07c1f43b":["mes","euromarine"],"20|grid________::b2cbbf5eadbbf87d534b022bad3191d7":["mes","euromarine"],"20|snsf________::74730ef1439d7f7636a8be58a6b471b8":["mes","euromarine"],"20|nsf_________::ad72e19043a5a467e35f9b444d11563e":["mes","euromarine"],"20|ukri________::0fc3e92500290902a2d38ec2445e74c3":["mes","euromarine"],"20|grid________::ad2c29905da0eb3c06b3fa80cacd89ea":["mes","euromarine"],"20|corda__h2020::30b53e4d63d3724f00acb9cbaca40860":["mes","euromarine"],"20|corda__h2020::f60f84bee14ad93f0db0e49af1d5c317":["mes","euromarine"], "20|corda__h2020::7bf251ac3765b5e89d82270a1763d09f":["mes","euromarine"], "20|corda__h2020::65531bd11be9935948c7f2f4db1c1832":["mes","euromarine"], "20|corda__h2020::e0e98f86bbc76638bbb72a8fe2302946":["mes","euromarine"], "20|snsf________::3eb43582ac27601459a8d8b3e195724b":["mes","euromarine"], "20|corda__h2020::af2481dab65d06c8ea0ae02b5517b9b6":["mes","euromarine"], "20|corda__h2020::c19d05cfde69a50d3ebc89bd0ee49929":["mes","euromarine"], "20|corda__h2020::af0bfd9fc09f80d9488f56d71a9832f0":["mes","euromarine"], "20|ukri________::f33c02afb0dc66c49d0ed97ca5dd5cb0":["beopen"], "20|grid________::a867f78acdc5041b34acfe4f9a349157":["beopen"], "20|grid________::7bb116a1a9f95ab812bf9d2dea2be1ff":["beopen"], "20|corda__h2020::6ab0e0739dbe625b99a2ae45842164ad":["beopen"], "20|corda__h2020::8ba50792bc5f4d51d79fca47d860c602":["beopen"], "20|corda_______::8ba50792bc5f4d51d79fca47d860c602":["beopen"], "20|corda__h2020::e70e9114979e963eef24666657b807c3":["beopen"], "20|corda_______::e70e9114979e963eef24666657b807c3":["beopen"], "20|corda_______::15911e01e9744d57205825d77c218737":["beopen"], "20|opendoar____::056a41e24e2a9a67215e87bbee6a80ab":["beopen"], "20|opendoar____::7f67f2e6c6fbb0628f8160fcd3d92ae3":["beopen"], "20|grid________::a8ecfd7c084e561168bcbe6bf0daf3e3":["beopen"], "20|corda_______::7bbe6cc5d8ec1864739a04b0d020c9e9":["beopen"], "20|corda_______::3ff558e30c2e434d688539548300b050":["beopen"], "20|corda__h2020::5ffee5b3b83b33a8cf0e046877bd3a39":["beopen"], "20|corda__h2020::5187217e2e806a6df3579c46f82401bc":["beopen"], "20|grid________::5fa7e2709bcd945e26bfa18689adeec1":["beopen"], "20|corda_______::d8696683c53027438031a96ad27c3c07":["beopen"], "20|corda__h2020::d8696683c53027438031a96ad27c3c07":["beopen"], "20|ukri________::23a79ebdfa59790864e4a485881568c1":["beopen"], "20|corda__h2020::b76cf8fe49590a966953c37e18608af9":["beopen"], "20|grid________::d2f0204126ee709244a488a4cd3b91c2":["beopen"], "20|corda__h2020::05aba9d2ed17533d15221e5655ac11e6":["beopen"], "20|grid________::802401579481dc32062bdee69f5e6a34":["beopen"], "20|corda__h2020::3f6d9d54cac975a517ba6b252c81582d":["beopen"], "20|openorgs____::d11f981828c485cd23d93f7f24f24db1":["eut"], "20|openorgs____::e66fe5dd092752e1dd6fd29fc699933a":["eut"], "20|openorgs____::526468206bca24c1c90da6a312295cf4":["eut"], "20|openorgs____::08e311e656e65ccb32e07c66b15b6ff7":["eut"], "20|openorgs____::55a1f889758964b77682904218fdb298":["eut"], "20|openorgs____::530092b6970d60a5329beb9f39e8d7d4":["eut"], "20|openorgs____::aadafa39392b3e200102596a3a4aad9d":["eut"], "20|openorgs____::c3fe999c74fad308132b8a5971367dce":["eut"], "20|openorgs____::1624ff7c01bb641b91f4518539a0c28a":["aurora"], "20|openorgs____::cdda7cfe17c89eb50628ec2eb1f8acd2":["aurora"], "20|openorgs____::818b75030e0e40612d69e049843ede7e":["aurora"], "20|openorgs____::0b0102bae51f4f4ef5ba57fbe1523b92":["aurora"], "20|openorgs____::ed47496b44722f0e9d7b98898189be0d":["aurora"], "20|openorgs____::eb0669daa9efeb898a3090d8aac7c953":["aurora"], "20|openorgs____::eb391317ed0dc684aa81ac16265de041":["aurora"], "20|openorgs____::f7cfcc98245e22c7d6e321cde930e746":["aurora"], "20|openorgs____::f33179d3306ba2599f7a898b056b604f":["aurora"], "20|pending_org_::75c41e6dd18466709ef359323d96fa05":["aurora"]} -pathMap={"author" : "$['author'][*]['fullname']", "title" : "$['title'][*]['value']", "orcid":"orcid":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']", "contributor" : "$['contributor'][*]['value']", "description" : "$['description'][*]['value']"} +pathMap ={"author":"$['author'][*]['fullname']", \ + "title":"$['title'][*]['value']",\ + "orcid":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']" ,\ + "orcid_pending":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid_pending')]['value']" ,\ + "contributor" : "$['contributor'][*]['value']",\ + "description" : "$['description'][*]['value']",\ + "subject" :"$['subject'][*]['value']" , \ + "fos" : "$['subject'][?(@['qualifier']['classid']=='FOS')].value" ,\ + "sdg" : "$['subject'][?(@['qualifier']['classid']=='SDG')].value",\ + "journal":"$['journal'].name",\ + "hostedby":"$['instance'][*]['hostedby']['key']",\ + "collectedfrom":"$['instance'][*]['collectedfrom']['key']",\ + "publisher":"$['publisher'].value",\ + "publicationyear":"$['dateofacceptance'].value"} blacklist=empty allowedpids=orcid;orcid_pending baseURL = https://services.openaire.eu/openaire/community/ diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml index 8281130f37..dadea2d280 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml @@ -47,6 +47,7 @@ --sourcePath${sourcePath} --workingPath${workingDir}/affiliationInstRepo --blacklist${blacklist} + --hive_metastore_uris${hive_metastore_uris} @@ -78,7 +79,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/publication - --outputPath${sourcePath}/relation + --outputPath${workingDir}/affiliationinstrepo/publication/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -107,7 +108,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/dataset - --outputPath${sourcePath}/relation + --outputPath${workingDir}/affiliationinstrepo/dataset/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -136,7 +137,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/otherresearchproduct - --outputPath${sourcePath}/relation + --outputPath${workingDir}/affiliationinstrepo/otherresearchproduct/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -165,7 +166,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/software - --outputPath${sourcePath}/relation + --outputPath${workingDir}/affiliationinstrepo/software/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -175,7 +176,32 @@ - + + + + + yarn + cluster + append new relations + eu.dnetlib.dhp.resulttoorganizationfrominstrepo.AppendNewRelations + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --outputPath${sourcePath}/relation + --sourcePath${workingDir}/affiliationinstrepo/ + + + + From 3eca5d2e1c302a7427ffa735c95ac96a6419caec Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Mon, 18 Dec 2023 09:55:27 +0100 Subject: [PATCH 05/17] - --- ...SemRel.java => SparkEntityToOrganizationFromSemRel.java} | 4 ++-- .../dhp/entitytoorganizationfromsemrel/StepActions.java | 5 ++--- .../entitytoorganizationfromsemrel/oozie_app/workflow.xml | 2 +- .../main/resources/eu/dnetlib/dhp/wf/main/job.properties | 2 +- .../resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml | 2 +- .../entitytoorganizationfromsemrel/oozie_app/workflow.xml | 6 +++--- .../dhp/entitytoorganizationfromsemrel/SparkJobTest.java | 6 +++--- 7 files changed, 13 insertions(+), 14 deletions(-) rename dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/{SparkResultToOrganizationFromSemRel.java => SparkEntityToOrganizationFromSemRel.java} (98%) diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkResultToOrganizationFromSemRel.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java similarity index 98% rename from dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkResultToOrganizationFromSemRel.java rename to dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java index 27e502aba0..87c0ec2b9d 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkResultToOrganizationFromSemRel.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java @@ -27,8 +27,8 @@ import eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganization import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.oaf.Relation; -public class SparkResultToOrganizationFromSemRel implements Serializable { - private static final Logger log = LoggerFactory.getLogger(SparkResultToOrganizationFromSemRel.class); +public class SparkEntityToOrganizationFromSemRel implements Serializable { + private static final Logger log = LoggerFactory.getLogger(SparkEntityToOrganizationFromSemRel.class); private static final int MAX_ITERATION = 5; public static final String NEW_RESULT_RELATION_PATH = "/newResultRelation"; public static final String NEW_PROJECT_RELATION_PATH = "/newProjectRelation"; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java index 386ea1a5cd..36a7523c50 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java @@ -3,8 +3,8 @@ package eu.dnetlib.dhp.entitytoorganizationfromsemrel; import static eu.dnetlib.dhp.PropagationConstant.*; import static eu.dnetlib.dhp.PropagationConstant.readPath; -import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel.NEW_PROJECT_RELATION_PATH; -import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel.NEW_RESULT_RELATION_PATH; +import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel.NEW_PROJECT_RELATION_PATH; +import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel.NEW_RESULT_RELATION_PATH; import java.io.Serializable; import java.util.*; @@ -20,7 +20,6 @@ import org.jetbrains.annotations.NotNull; import com.fasterxml.jackson.databind.ObjectMapper; import eu.dnetlib.dhp.KeyValueSet; -import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.oaf.Relation; import scala.Tuple2; diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml index 16c8c4e19d..851aabe8b1 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml @@ -162,7 +162,7 @@ yarn cluster resultToOrganizationFromSemRel - eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel + eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel dhp-enrichment-${projectVersion}.jar --executor-cores=${sparkExecutorCores} diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties index 243c1e99d1..6085cd2b26 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties @@ -1,5 +1,5 @@ sourcePath=/tmp/beta_provision/graph/09_graph_dedup_enriched -resumeFrom=AffiliationInstitutionalRepository +resumeFrom=default allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo allowedsemrelsresultproject=isSupplementedBy;isSupplementTo allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml index 1e6736bf44..33f8496450 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml @@ -120,7 +120,7 @@ ${wf:conf('resumeFrom') eq 'BulkTagging'} ${wf:conf('resumeFrom') eq 'AffiliationInstitutionalRepository'} - ${wf:conf('resumeFrom') eq 'AffiliationSemanticRelation'} + ${wf:conf('resumeFrom') eq 'AffiliationSemanticRelation'} ${wf:conf('resumeFrom') eq 'CommunityOrganization'} ${wf:conf('resumeFrom') eq 'ResultProject'} ${wf:conf('resumeFrom') eq 'CommunityProject'} diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml index e3f3c1758d..dbb22b9948 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml @@ -29,7 +29,7 @@ yarn cluster - PrepareResultOrganizationAssociation + PrepareResultProjectOrganizationAssociation eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo dhp-enrichment-${projectVersion}.jar @@ -57,8 +57,8 @@ yarn cluster - resultToOrganizationFromSemRel - eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel + entityToOrganizationFromSemRel + eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel dhp-enrichment-${projectVersion}.jar --executor-cores=${sparkExecutorCores} diff --git a/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java b/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java index 517a20cd96..db917658a6 100644 --- a/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java +++ b/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java @@ -114,7 +114,7 @@ public class SparkJobTest { .option("compression", "gzip") .json(workingDir.toString() + "/projectInput"); - SparkResultToOrganizationFromSemRel + SparkEntityToOrganizationFromSemRel .main( new String[] { @@ -395,7 +395,7 @@ public class SparkJobTest { .option("compression", "gzip") .json(workingDir.toString() + "/projectInput"); - SparkResultToOrganizationFromSemRel + SparkEntityToOrganizationFromSemRel .main( new String[] { @@ -678,7 +678,7 @@ public class SparkJobTest { .option("compression", "gzip") .json(workingDir.toString() + "/projectInput"); - SparkResultToOrganizationFromSemRel + SparkEntityToOrganizationFromSemRel .main( new String[] { From d410ea8a4176341cdebaa76179c77b5fdd45c631 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Tue, 19 Dec 2023 12:15:01 +0100 Subject: [PATCH 06/17] added needed parameter --- .../AppendNewRelations.java | 11 +- .../oozie_app/workflow.xml | 112 ++---------------- .../input_newrelation_parameters.json | 20 ++++ .../eu/dnetlib/dhp/wf/main/job.properties | 4 +- .../dhp/wf/main/oozie_app/workflow.xml | 10 +- 5 files changed, 41 insertions(+), 116 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java index a5884873b1..636c14b655 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java @@ -2,26 +2,19 @@ package eu.dnetlib.dhp.resulttoorganizationfrominstrepo; import static eu.dnetlib.dhp.PropagationConstant.*; -import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; +import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; import java.io.Serializable; -import java.util.Objects; -import java.util.Optional; import org.apache.commons.io.IOUtils; import org.apache.spark.SparkConf; -import org.apache.spark.api.java.function.MapFunction; -import org.apache.spark.sql.Encoders; import org.apache.spark.sql.SaveMode; import org.apache.spark.sql.SparkSession; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import eu.dnetlib.dhp.application.ArgumentApplicationParser; -import eu.dnetlib.dhp.bulktag.community.ResultTagger; -import eu.dnetlib.dhp.schema.common.ModelSupport; import eu.dnetlib.dhp.schema.oaf.Relation; -import eu.dnetlib.dhp.schema.oaf.Result; /** * @author miriam.baglioni @@ -54,7 +47,7 @@ public class AppendNewRelations implements Serializable { SparkConf conf = new SparkConf(); - runWithSparkHiveSession( + runWithSparkSession( conf, isSparkSessionManaged, spark -> appendNewRelation(spark, inputPath, outputPath)); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml index 851aabe8b1..d7335d8408 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml @@ -5,9 +5,10 @@ the source path - outputPath - sets the outputPath + iterations + the number of hops to be done up on the hierarchy + @@ -21,119 +22,26 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - ${wf:conf('resumeFrom') eq 'PrepareInfo'} - - - - - - + + - + - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/publication - ${nameNode}/${outputPath}/publication - - - - - - - - ${nameNode}/${sourcePath}/dataset - ${nameNode}/${outputPath}/dataset - - - - - - - - ${nameNode}/${sourcePath}/otherresearchproduct - ${nameNode}/${outputPath}/otherresearchproduct - - - - - - - - ${nameNode}/${sourcePath}/software - ${nameNode}/${outputPath}/software - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - yarn cluster - PrepareResultOrganizationAssociation + PrepareResultProjectOrganizationAssociation eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo dhp-enrichment-${projectVersion}.jar @@ -161,7 +69,7 @@ yarn cluster - resultToOrganizationFromSemRel + resultProjectToOrganizationFromSemRel eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel dhp-enrichment-${projectVersion}.jar @@ -177,7 +85,7 @@ --conf spark.sql.shuffle.partitions=3840 --relationPath${workingDir}/preparedInfo/relation - --outputPath${outputPath}/relation + --outputPath${sourcePath}/relation --leavesPath${workingDir}/preparedInfo/leavesPath --childParentPath${workingDir}/preparedInfo/childParentPath --resultOrgPath${workingDir}/preparedInfo/resultOrgPath diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json new file mode 100644 index 0000000000..5fe92cff13 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json @@ -0,0 +1,20 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + },{ + "paramName": "o", + "paramLongName": "outputPath", + "paramDescription": "institutional repositories that should not be considered for the propagation", + "paramRequired": false +} +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties index 6085cd2b26..93e9e0ab1d 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties @@ -1,5 +1,5 @@ sourcePath=/tmp/beta_provision/graph/09_graph_dedup_enriched -resumeFrom=default +resumeFrom=AffiliationSemanticRelation allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo allowedsemrelsresultproject=isSupplementedBy;isSupplementTo allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo @@ -24,5 +24,5 @@ pathMap ={"author":"$['author'][*]['fullname']", \ blacklist=empty allowedpids=orcid;orcid_pending baseURL = https://services.openaire.eu/openaire/community/ - +iterations=1 diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml index 33f8496450..de054b962b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml @@ -195,13 +195,13 @@ - + - + - ${wf:appPath()}/affiliation_semantic_relation + ${wf:appPath()}/entity_semantic_relation @@ -209,6 +209,10 @@ sourcePath ${outputPath} + + iterations + ${iterations} + From 4740c808f735193e8975f09e1a6841eb4d9a676f Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Wed, 20 Dec 2023 14:26:54 +0100 Subject: [PATCH 07/17] - --- .../PrepareDatasourceCountryAssociation.java | 2 +- .../bulktag/datasourcemaster_parameters.json | 32 -- .../dhp/bulktag/input_bulkTag_parameters.json | 38 -- .../dhp/bulktag/input_eoscTag_parameters.json | 21 - .../input_eosc_bulkTag_parameters.json | 41 -- .../dhp/bulktag/oozie_app/config-default.xml | 54 --- .../dhp/bulktag/oozie_app/workflow.xml | 120 ------ .../input_countrypropagation_parameters.json | 32 -- .../input_prepareassoc_parameters.json | 32 -- ...input_prepareresultcountry_parameters.json | 38 -- .../oozie_app/config-default.xml | 58 --- .../countrypropagation/oozie_app/workflow.xml | 375 ------------------ .../input_preparation_parameter.json | 50 --- .../input_propagation_parameter.json | 62 --- .../oozie_app/config-default.xml | 58 --- .../oozie_app/workflow.xml | 105 ----- .../input_orcidtoresult_parameters.json | 44 -- ...input_prepareorcidtoresult_parameters.json | 38 -- ...nput_prepareorcidtoresult_parameters2.json | 20 - .../oozie_app/config-default.xml | 58 --- .../oozie_app/workflow.xml | 371 ----------------- ...put_prepareprojecttoresult_parameters.json | 33 -- .../input_projecttoresult_parameters.json | 44 -- .../oozie_app/config-default.xml | 63 --- .../projecttoresult/oozie_app/workflow.xml | 184 --------- .../input_communitytoresult_parameters.json | 28 -- ...t_preparecommunitytoresult_parameters.json | 33 -- .../oozie_app/config-default.xml | 58 --- .../oozie_app/workflow.xml | 147 ------- .../input_communitytoresult_parameters.json | 28 -- ...t_preparecommunitytoresult_parameters.json | 28 -- .../oozie_app/config-default.xml | 58 --- .../oozie_app/workflow.xml | 144 ------- .../input_communitytoresult_parameters.json | 52 --- ..._preparecommunitytoresult2_parameters.json | 20 - ...t_preparecommunitytoresult_parameters.json | 44 -- .../oozie_app/config-default.xml | 58 --- .../oozie_app/workflow.xml | 366 ----------------- .../input_newrelation_parameters.json | 20 - .../input_prepareresultorg_parameters.json | 32 -- ...sulaffiliationfrominstrepo_parameters.json | 56 --- .../oozie_app/config-default.xml | 58 --- .../oozie_app/workflow.xml | 277 ------------- .../eu/dnetlib/dhp/wf/main/job.properties | 8 +- .../dhp/wf/main/oozie_app/workflow.xml | 6 +- .../bulktag/oozie_app/workflow.xml | 10 +- .../countrypropagation/oozie_app/workflow.xml | 10 +- .../oozie_app/workflow.xml | 10 +- .../projecttoresult/oozie_app/workflow.xml | 12 +- .../oozie_app/workflow.xml | 15 +- .../oozie_app/workflow.xml | 11 +- .../oozie_app/workflow.xml | 68 +++- .../oozie_app/workflow.xml | 21 +- .../oozie_app/config-default.xml | 58 --- .../oozie_app/workflow.xml | 97 ----- .../graph/hostedbymap/oozie_app/download.sh | 2 +- 56 files changed, 127 insertions(+), 3681 deletions(-) delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/datasourcemaster_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/workflow.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml delete mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java index 2ffe6f36de..430c265924 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java @@ -90,7 +90,7 @@ public class PrepareDatasourceCountryAssociation { (FilterFunction) ds -> !ds.getDataInfo().getDeletedbyinference() && Optional.ofNullable(ds.getDatasourcetype()).isPresent() && Optional.ofNullable(ds.getDatasourcetype().getClassid()).isPresent() && - (allowedtypes.contains(ds.getDatasourcetype().getClassid()) || + (allowedtypes.contains(ds.getJurisdiction().getClassid()) || whitelist.contains(ds.getId()))); // filtering of the relations taking the non deleted by inference and those with IsProvidedBy as relclass diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/datasourcemaster_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/datasourcemaster_parameters.json deleted file mode 100644 index 9a2eadaa7d..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/datasourcemaster_parameters.json +++ /dev/null @@ -1,32 +0,0 @@ -[ - { - "paramName": "p", - "paramLongName": "hdfsPath", - "paramDescription": "the path where storing the sequential file", - "paramRequired": true - }, - { - "paramName": "nn", - "paramLongName": "hdfsNameNode", - "paramDescription": "the name node on hdfs", - "paramRequired": true - }, - { - "paramName": "pgurl", - "paramLongName": "postgresUrl", - "paramDescription": "postgres url, example: jdbc:postgresql://localhost:5432/testdb", - "paramRequired": true - }, - { - "paramName": "pguser", - "paramLongName": "postgresUser", - "paramDescription": "postgres user", - "paramRequired": false - }, - { - "paramName": "pgpasswd", - "paramLongName": "postgresPassword", - "paramDescription": "postgres password", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json deleted file mode 100644 index ce1a8ecab6..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json +++ /dev/null @@ -1,38 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName": "pm", - "paramLongName":"pathMap", - "paramDescription": "the json path associated to each selection field", - "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 - }, - { - "paramName": "tg", - "paramLongName": "taggingConf", - "paramDescription": "this parameter is intended for testing purposes only. It is a possible tagging configuration obtained via the XQUERY. Intended to be removed", - "paramRequired": false - }, - { - "paramName": "bu", - "paramLongName": "baseURL", - "paramDescription": "this parameter is to specify the api to be queried (beta or production)", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json deleted file mode 100644 index 4c25fea019..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json +++ /dev/null @@ -1,21 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName": "wp", - "paramLongName": "workingPath", - "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 - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json deleted file mode 100644 index 5aace346d9..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json +++ /dev/null @@ -1,41 +0,0 @@ -[ - - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName": "dmp", - "paramLongName":"datasourceMapPath", - "paramDescription": "the path where the association datasource master has been stored", - "paramRequired": true - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - }, - { - "paramName": "wp", - "paramLongName": "workingPath", - "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 - }, - { - - "paramName": "rt", - "paramLongName": "resultType", - "paramDescription": "the result type", - "paramRequired": true - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/config-default.xml deleted file mode 100644 index fe82ae1940..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/config-default.xml +++ /dev/null @@ -1,54 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml deleted file mode 100644 index 0d4d1f046d..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml +++ /dev/null @@ -1,120 +0,0 @@ - - - - sourcePath - the source path - - - pathMap - the json path associated to each selection field - - - outputPath - the output path - - - baseURL - the community API base URL - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - yarn-cluster - cluster - bulkTagging-result - eu.dnetlib.dhp.bulktag.SparkBulkTagJob - dhp-enrichment-${projectVersion}.jar - - --num-executors=${sparkExecutorNumber} - --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} - - --sourcePath${sourcePath}/ - --outputPath${outputPath}/ - --pathMap${pathMap} - --baseURL${baseURL} - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json deleted file mode 100644 index f217e24582..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json +++ /dev/null @@ -1,32 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName": "p", - "paramLongName": "preparedInfoPath", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": false - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json deleted file mode 100644 index a00105f2ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json +++ /dev/null @@ -1,32 +0,0 @@ -[ - { - "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": "w", - "paramLongName": "whitelist", - "paramDescription": "the datasource having a type different from the allowed ones but that we want to add anyway", - "paramRequired": true - }, - { - "paramName": "at", - "paramLongName": "allowedtypes", - "paramDescription": "the allowed datasource types for country propagation", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json deleted file mode 100644 index 18163d1f96..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json +++ /dev/null @@ -1,38 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"out", - "paramLongName":"outputPath", - "paramDescription": "the output path", - "paramRequired": true - }, - { - "paramName":"w", - "paramLongName":"workingPath", - "paramDescription": "the working path", - "paramRequired": true - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - }, - { - "paramName": "p", - "paramLongName": "preparedInfoPath", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/workflow.xml deleted file mode 100644 index 271ccbf722..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/workflow.xml +++ /dev/null @@ -1,375 +0,0 @@ - - - - sourcePath - the source path - - - whitelist - the white list - - - allowedtypes - the allowed types - - - outputPath - the output path - - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - yarn - cluster - PrepareDatasourceCountryAssociation - eu.dnetlib.dhp.countrypropagation.PrepareDatasourceCountryAssociation - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath} - --whitelist${whitelist} - --allowedtypes${allowedtypes} - --outputPath${workingDir}/preparedInfo - - - - - - - - - - - - - - - yarn - cluster - prepareResultCountry-Publication - eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/publication - --outputPath${workingDir}/publication - --workingPath${workingDir}/workingP - --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --preparedInfoPath${workingDir}/preparedInfo - - - - - - - - yarn - cluster - prepareResultCountry-Dataset - eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/dataset - --outputPath${workingDir}/dataset - --workingPath${workingDir}/workingD - --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --preparedInfoPath${workingDir}/preparedInfo - - - - - - - - yarn - cluster - prepareResultCountry-ORP - eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/otherresearchproduct - --outputPath${workingDir}/otherresearchproduct - --workingPath${workingDir}/workingO - --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --preparedInfoPath${workingDir}/preparedInfo - - - - - - - - yarn - cluster - prepareResultCountry-Software - eu.dnetlib.dhp.countrypropagation.PrepareResultCountrySet - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/software - --outputPath${workingDir}/software - --workingPath${workingDir}/workingS - --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --preparedInfoPath${workingDir}/preparedInfo - - - - - - - - - - - - - - - - - yarn - cluster - countryPropagationForPublications - eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/publication - --preparedInfoPath${workingDir}/publication - --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${outputPath}/publication - - - - - - - - yarn - cluster - countryPropagationForDataset - eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/dataset - --preparedInfoPath${workingDir}/dataset - --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${outputPath}/dataset - - - - - - - - yarn - cluster - countryPropagationForORP - eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/otherresearchproduct - --preparedInfoPath${workingDir}/otherresearchproduct - --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${outputPath}/otherresearchproduct - - - - - - - - yarn - cluster - countryPropagationForSoftware - eu.dnetlib.dhp.countrypropagation.SparkCountryPropagationJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --sourcePath${sourcePath}/software - --preparedInfoPath${workingDir}/software - --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${outputPath}/software - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json deleted file mode 100644 index b599373318..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json +++ /dev/null @@ -1,50 +0,0 @@ -[ - { - "paramName":"gp", - "paramLongName":"graphPath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName":"lp", - "paramLongName":"leavesPath", - "paramDescription": "true if the new version of the graph must be saved", - "paramRequired": false - }, - { - "paramName":"cp", - "paramLongName":"childParentPath", - "paramDescription": "path where to store/find association from datasource and organization", - "paramRequired": true - }, - { - "paramName":"rp", - "paramLongName":"resultOrgPath", - "paramDescription": "path where to store/find already linked results and organizations", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": false - }, - { - "paramName": "rep", - "paramLongName": "relationPath", - "paramDescription": "the path where to store the selected subset of relations", - "paramRequired": false - }, - { - "paramName": "pop", - "paramLongName": "projectOrganizationPath", - "paramDescription": "the number of iterations to be computed", - "paramRequired": true - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json deleted file mode 100644 index 66a7f5b2f5..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json +++ /dev/null @@ -1,62 +0,0 @@ -[ - { - "paramName":"rep", - "paramLongName":"relationPath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName":"lp", - "paramLongName":"leavesPath", - "paramDescription": "true if the new version of the graph must be saved", - "paramRequired": false - }, - { - "paramName":"cp", - "paramLongName":"childParentPath", - "paramDescription": "path where to store/find association from datasource and organization", - "paramRequired": true - }, - { - "paramName":"rp", - "paramLongName":"resultOrgPath", - "paramDescription": "path where to store/find already linked results and organizations", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": false - }, - { - "paramName": "wd", - "paramLongName": "workingDir", - "paramDescription": "true if it is a test running", - "paramRequired": false - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName": "it", - "paramLongName": "iterations", - "paramDescription": "the number of iterations to be computed", - "paramRequired": false - }, - { - "paramName": "pop", - "paramLongName": "projectOrganizationPath", - "paramDescription": "the number of iterations to be computed", - "paramRequired": true - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml deleted file mode 100644 index d7335d8408..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml +++ /dev/null @@ -1,105 +0,0 @@ - - - - sourcePath - the source path - - - iterations - the number of hops to be done up on the hierarchy - - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - yarn - cluster - PrepareResultProjectOrganizationAssociation - eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --graphPath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --leavesPath${workingDir}/preparedInfo/leavesPath - --childParentPath${workingDir}/preparedInfo/childParentPath - --resultOrgPath${workingDir}/preparedInfo/resultOrgPath - --projectOrganizationPath${workingDir}/preparedInfo/projectOrganizationPath - --relationPath${workingDir}/preparedInfo/relation - - - - - - - - yarn - cluster - resultProjectToOrganizationFromSemRel - eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=3840 - - --relationPath${workingDir}/preparedInfo/relation - --outputPath${sourcePath}/relation - --leavesPath${workingDir}/preparedInfo/leavesPath - --childParentPath${workingDir}/preparedInfo/childParentPath - --resultOrgPath${workingDir}/preparedInfo/resultOrgPath - --projectOrganizationPath${workingDir}/preparedInfo/projectOrganizationPath - --hive_metastore_uris${hive_metastore_uris} - --workingDir${workingDir}/working - --iterations${iterations} - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json deleted file mode 100644 index 3cbaa23bb6..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json +++ /dev/null @@ -1,44 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"sg", - "paramLongName":"saveGraph", - "paramDescription": "true if the new version of the graph must be saved", - "paramRequired": false - }, - { - "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 - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - }, - { - "paramName":"pu", - "paramLongName":"possibleUpdatesPath", - "paramDescription": "the path the the association resultId orcid author list can be found", - "paramRequired": true - }, - { - "paramName":"test", - "paramLongName":"isTest", - "paramDescription": "true if it is executing a test", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json deleted file mode 100644 index 08648d61a1..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json +++ /dev/null @@ -1,38 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"as", - "paramLongName":"allowedsemrels", - "paramDescription": "the allowed sematinc relations for propagation", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "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 - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json deleted file mode 100644 index 1a67134a6b..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json +++ /dev/null @@ -1,20 +0,0 @@ -[ - { - "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 - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/config-default.xml deleted file mode 100644 index 8d2c341057..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml deleted file mode 100644 index 5f52c16585..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml +++ /dev/null @@ -1,371 +0,0 @@ - - - - sourcePath - the source path - - - allowedsemrels - the semantic relationships allowed for propagation - - - outputPath - the output path - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - - - - - - - - yarn - cluster - ORCIDPropagation-PreparePhase1-Publications - eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=3840 - --conf spark.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc - --allowedsemrels${allowedsemrels} - - - - - - - - yarn - cluster - ORCIDPropagation-PreparePhase1-Dataset - eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc - --allowedsemrels${allowedsemrels} - - - - - - - - yarn - cluster - ORCIDPropagation-PreparePhase1-ORP - eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc - --allowedsemrels${allowedsemrels} - - - - - - - - yarn - cluster - ORCIDPropagation-PreparePhase1-Software - eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc - --allowedsemrels${allowedsemrels} - - - - - - - - - - yarn - cluster - ORCIDPropagation-PreparePhase2 - eu.dnetlib.dhp.orcidtoresultfromsemrel.PrepareResultOrcidAssociationStep2 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${workingDir}/preparedInfo/targetOrcidAssoc - --outputPath${workingDir}/preparedInfo/mergedOrcidAssoc - - - - - - - - - - - - - - - yarn - cluster - ORCIDPropagation-Publication - eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 - - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc - --sourcePath${sourcePath}/publication - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${outputPath}/publication - - - - - - - - yarn - cluster - ORCIDPropagation-Dataset - eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc - --sourcePath${sourcePath}/dataset - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${outputPath}/dataset - - - - - - - - yarn - cluster - ORCIDPropagation-ORP - eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc - --sourcePath${sourcePath}/otherresearchproduct - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${outputPath}/otherresearchproduct - - - - - - - - yarn - cluster - ORCIDPropagation-Software - eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.speculation=false - --conf spark.hadoop.mapreduce.map.speculative=false - --conf spark.hadoop.mapreduce.reduce.speculative=false - - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc - --sourcePath${sourcePath}/software - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${outputPath}/software - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json deleted file mode 100644 index a70dbd6a08..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json +++ /dev/null @@ -1,33 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - - { - "paramName":"asr", - "paramLongName":"allowedsemrels", - "paramDescription": "the types of the allowed datasources. Split by ;", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName":"pu", - "paramLongName":"potentialUpdatePath", - "paramDescription": "the path of the potential updates ", - "paramRequired": true - }, - { - "paramName":"al", - "paramLongName":"alreadyLinkedPath", - "paramDescription": "the path of the already linked project result_set", - "paramRequired": true - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json deleted file mode 100644 index 7f44ba03cd..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json +++ /dev/null @@ -1,44 +0,0 @@ -[ - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName":"sg", - "paramLongName":"saveGraph", - "paramDescription": "true if the new version of the graph must be saved", - "paramRequired": false - }, - { - "paramName":"pu", - "paramLongName":"potentialUpdatePath", - "paramDescription": "the path of the potential updates ", - "paramRequired": true - }, - { - "paramName":"al", - "paramLongName":"alreadyLinkedPath", - "paramDescription": "the path of the already linked project result_set", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": false - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName": "test", - "paramLongName": "isTest", - "paramDescription": "true if it is a test running", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/config-default.xml deleted file mode 100644 index caf3c60500..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/config-default.xml +++ /dev/null @@ -1,63 +0,0 @@ - - - jobTracker - yarnRM - - - - nameNode - - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml deleted file mode 100644 index 9e91c06fb3..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml +++ /dev/null @@ -1,184 +0,0 @@ - - - - sourcePath - the source path - - - allowedsemrels - the allowed semantics - - - outputPath - the output path - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/publication - ${nameNode}/${outputPath}/publication - - - - - - - - ${nameNode}/${sourcePath}/dataset - ${nameNode}/${outputPath}/dataset - - - - - - - - ${nameNode}/${sourcePath}/otherresearchproduct - ${nameNode}/${outputPath}/otherresearchproduct - - - - - - - - ${nameNode}/${sourcePath}/software - ${nameNode}/${outputPath}/software - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - yarn - cluster - PrepareProjectResultsAssociation - eu.dnetlib.dhp.projecttoresult.PrepareProjectResultsAssociation - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --sourcePath${sourcePath}/relation - --allowedsemrels${allowedsemrels} - --hive_metastore_uris${hive_metastore_uris} - --potentialUpdatePath${workingDir}/preparedInfo/potentialUpdates - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - - - - - - - - yarn - cluster - ProjectToResultPropagation - eu.dnetlib.dhp.projecttoresult.SparkResultToProjectThroughSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --saveGraph${saveGraph} - --hive_metastore_uris${hive_metastore_uris} - --outputPath${outputPath}/relation - --potentialUpdatePath${workingDir}/preparedInfo/potentialUpdates - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json deleted file mode 100644 index 0db8085d19..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json +++ /dev/null @@ -1,28 +0,0 @@ -[ - { - "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 - }, - { - "paramName": "p", - "paramLongName": "preparedInfoPath", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": true - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json deleted file mode 100644 index 3601db7acc..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json +++ /dev/null @@ -1,33 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName": "bu", - "paramLongName": "baseURL", - "paramDescription": "the base URL to the community API to use", - "paramRequired": false - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml deleted file mode 100644 index dfa762ac67..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml +++ /dev/null @@ -1,147 +0,0 @@ - - - - sourcePath - the source path - - - outputPath - the output path - - - baseURL - the community API base URL - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - yarn - cluster - Prepare-Community-Result-Organization - eu.dnetlib.dhp.resulttocommunityfromorganization.PrepareResultCommunitySet - dhp-enrichment-${projectVersion}.jar - - --executor-cores=6 - --executor-memory=5G - --conf spark.executor.memoryOverhead=3g - --conf spark.sql.shuffle.partitions=3284 - --driver-memory=${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} - - --sourcePath${sourcePath}/relation - --outputPath${workingDir}/preparedInfo/resultCommunityList - --hive_metastore_uris${hive_metastore_uris} - --baseURL${baseURL} - - - - - - - - yarn - cluster - community2resultfromorganization - eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=6 - --executor-memory=5G - --conf spark.executor.memoryOverhead=3g - --conf spark.sql.shuffle.partitions=3284 - --driver-memory=${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} - - --preparedInfoPath${workingDir}/preparedInfo/resultCommunityList - --sourcePath${sourcePath}/ - --outputPath${outputPath}/ - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json deleted file mode 100644 index 0db8085d19..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json +++ /dev/null @@ -1,28 +0,0 @@ -[ - { - "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 - }, - { - "paramName": "p", - "paramLongName": "preparedInfoPath", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": true - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json deleted file mode 100644 index cbc01c2d5a..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json +++ /dev/null @@ -1,28 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName": "bu", - "paramLongName": "baseURL", - "paramDescription": "the path used to store temporary output files", - "paramRequired": false - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml deleted file mode 100644 index 21cc2d8874..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml +++ /dev/null @@ -1,144 +0,0 @@ - - - - sourcePath - the source path - - - - outputPath - the output path - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - yarn - cluster - Prepare-Community-Result-Organization - eu.dnetlib.dhp.resulttocommunityfromproject.PrepareResultCommunitySet - dhp-enrichment-${projectVersion}.jar - - --executor-cores=6 - --executor-memory=5G - --conf spark.executor.memoryOverhead=3g - --conf spark.sql.shuffle.partitions=3284 - --driver-memory=${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} - - --sourcePath${sourcePath}/relation - --outputPath${workingDir}/preparedInfo/resultCommunityList - --production${production} - - - - - - - - yarn - cluster - community2resultfromproject - eu.dnetlib.dhp.resulttocommunityfromproject.SparkResultToCommunityFromProject - dhp-enrichment-${projectVersion}.jar - - --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=${spark2MaxExecutors} - - --preparedInfoPath${workingDir}/preparedInfo/resultCommunityList - --sourcePath${sourcePath}/ - --outputPath${outputPath}/ - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json deleted file mode 100644 index a40ce375ee..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json +++ /dev/null @@ -1,52 +0,0 @@ -[ - - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"sg", - "paramLongName":"saveGraph", - "paramDescription": "true if the new version of the graph must be saved", - "paramRequired": false - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - }, - { - "paramName": "p", - "paramLongName": "preparedInfoPath", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": true - }, - { - "paramName":"test", - "paramLongName":"isTest", - "paramDescription": "true if it is executing a test", - "paramRequired": false - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json deleted file mode 100644 index 3ba3c8e9c7..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json +++ /dev/null @@ -1,20 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json deleted file mode 100644 index 271db10bb7..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json +++ /dev/null @@ -1,44 +0,0 @@ -[ - { - "paramName":"bu", - "paramLongName":"baseURL", - "paramDescription": "URL of the isLookUp Service", - "paramRequired": true - }, - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"as", - "paramLongName":"allowedsemrels", - "paramDescription": "the allowed semantic relations for propagation", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml deleted file mode 100644 index 916eb8b7ce..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml +++ /dev/null @@ -1,366 +0,0 @@ - - - - sourcePath - the source path - - - allowedsemrels - the semantic relationships allowed for propagation - - - baseURL - the baseurl for the comminity APIs - - - outputPath - the output path - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - - - - - - - - yarn - cluster - ResultToCommunitySemRel-PreparePhase1-Publications - eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc - --allowedsemrels${allowedsemrels} - --baseURL${baseURL} - - - - - - - - yarn - cluster - ResultToCommunitySemRel-PreparePhase1-Dataset - eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc - --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} - - - - - - - - yarn - cluster - ResultToCommunitySemRel-PreparePhase1-ORP - eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc - --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} - - - - - - - - yarn - cluster - ResultToCommunitySemRel-PreparePhase1-Software - eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc - --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} - - - - - - - - - - yarn - cluster - ResultToCommunityEmRelPropagation-PreparePhase2 - eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep2 - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${workingDir}/preparedInfo/targetCommunityAssoc - --outputPath${workingDir}/preparedInfo/mergedCommunityAssoc - - - - - - - - - - - - - - - yarn - cluster - Result2CommunitySemRelPropagation-Publication - eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc - --sourcePath${sourcePath}/publication - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${outputPath}/publication - --saveGraph${saveGraph} - - - - - - - - yarn - cluster - Result2CommunitySemRelPropagation-Dataset - eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc - --sourcePath${sourcePath}/dataset - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${outputPath}/dataset - --saveGraph${saveGraph} - - - - - - - - yarn - cluster - Result2CommunitySemRelPropagation-ORP - eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc - --sourcePath${sourcePath}/otherresearchproduct - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${outputPath}/otherresearchproduct - --saveGraph${saveGraph} - - - - - - - - yarn - cluster - Result2CommunitySemRelPropagation-Software - eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc - --sourcePath${sourcePath}/software - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${outputPath}/software - --saveGraph${saveGraph} - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json deleted file mode 100644 index 5fe92cff13..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json +++ /dev/null @@ -1,20 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": false - },{ - "paramName": "o", - "paramLongName": "outputPath", - "paramDescription": "institutional repositories that should not be considered for the propagation", - "paramRequired": false -} -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json deleted file mode 100644 index 3f4b1d151b..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json +++ /dev/null @@ -1,32 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - - { - "paramName":"wp", - "paramLongName":"workingPath", - "paramDescription": "the working path", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": false - },{ - "paramName": "bl", - "paramLongName": "blacklist", - "paramDescription": "institutional repositories that should not be considered for the propagation", - "paramRequired": false -} -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json deleted file mode 100644 index d2b076c827..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json +++ /dev/null @@ -1,56 +0,0 @@ -[ - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, - { - "paramName":"sg", - "paramLongName":"saveGraph", - "paramDescription": "true if the new version of the graph must be saved", - "paramRequired": false - }, - { - "paramName":"dop", - "paramLongName":"datasourceOrganizationPath", - "paramDescription": "path where to store/find association from datasource and organization", - "paramRequired": true - }, - { - "paramName":"alp", - "paramLongName":"alreadyLinkedPath", - "paramDescription": "path where to store/find already linked results and organizations", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "the path where prepared info have been stored", - "paramRequired": false - }, - { - "paramName": "test", - "paramLongName": "isTest", - "paramDescription": "true if it is a test running", - "paramRequired": false - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - }, - { - "paramName": "out", - "paramLongName": "outputPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/workflow.xml deleted file mode 100644 index edfff8817d..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/workflow.xml +++ /dev/null @@ -1,277 +0,0 @@ - - - - sourcePath - the source path - - - outputPath - sets the outputPath - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/publication - ${nameNode}/${outputPath}/publication - - - - - - - - ${nameNode}/${sourcePath}/dataset - ${nameNode}/${outputPath}/dataset - - - - - - - - ${nameNode}/${sourcePath}/otherresearchproduct - ${nameNode}/${outputPath}/otherresearchproduct - - - - - - - - ${nameNode}/${sourcePath}/software - ${nameNode}/${outputPath}/software - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - yarn - cluster - PrepareResultOrganizationAssociation - eu.dnetlib.dhp.resulttoorganizationfrominstrepo.PrepareResultInstRepoAssociation - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - --blacklist${blacklist} - - - - - - - - - - - - - - - yarn - cluster - resultToOrganizationFromInstRepoPropagationForPublications - eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath}/publication - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - - - - - - - - yarn - cluster - resultToOrganizationFromInstRepoPropagationForDataset - eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath}/dataset - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - - - - - - - - yarn - cluster - resultToOrganizationFromInstRepoPropagationForORP - eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath}/otherresearchproduct - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - - - - - - - - yarn - cluster - resultToOrganizationFromInstRepoPropagationForSoftware - eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganizationFromIstRepoJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --sourcePath${sourcePath}/software - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - --hive_metastore_uris${hive_metastore_uris} - --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties index 93e9e0ab1d..4cb759343c 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties @@ -1,12 +1,12 @@ sourcePath=/tmp/beta_provision/graph/09_graph_dedup_enriched -resumeFrom=AffiliationSemanticRelation +resumeFrom=CountryPropagation allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo allowedsemrelsresultproject=isSupplementedBy;isSupplementTo allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo -datasourceWhitelistForCountryPropagation=10|openaire____::3795d6478e30e2c9f787d427ff160944;10|opendoar____::16e6a3326dd7d868cbc926602a61e4d0;10|eurocrisdris::fe4903425d9040f680d8610d9079ea14 -allowedtypes=pubsrepository::institutional +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 -organizationtoresultcommunitymap={"20|corda__h2020::3fb05a9524c3f790391261347852f638":["mes","euromarine"], "20|corda__h2020::e8dbe14cca9bf6fce09d468872f813f8":["mes","euromarine"], "20|snsf________::9b253f265e3bef5cae6d881fdf61aceb":["mes","euromarine"],"20|ukri________::e054eea0a47665af8c3656b5785ccf76":["mes","euromarine"],"20|corda__h2020::edc18d67c9b11fb616ca9f6e1db1b151":["mes","euromarine"],"20|ukri________::d5736d9da90521ddcdc7828a05a85e9a":["mes","euromarine"],"20|corda__h2020::f5d418d3aa1cf817ddefcc3fdc039f27":["mes","euromarine"],"20|snsf________::8fa091f8f25a846779acb4ea97b50aef":["mes","euromarine"],"20|corda__h2020::81e020977211c2c40fae2e1a50bffd71":["mes","euromarine"],"20|corda_______::81e020977211c2c40fae2e1a50bffd71":["mes","euromarine"],"20|snsf________::31d0a100e54e3cdb3c6f52d91e638c78":["mes","euromarine"],"20|corda__h2020::ea379ef91b8cc86f9ac5edc4169292db":["mes","euromarine"],"20|corda__h2020::f75ee2ee48e5cb0ec8c8d30aaa8fef70":["mes","euromarine"],"20|ukri________::e16010089551a1a9182a94604fc0ea59":["mes","euromarine"],"20|corda__h2020::38531a2cce7c5c347ffc439b07c1f43b":["mes","euromarine"],"20|corda_______::38531a2cce7c5c347ffc439b07c1f43b":["mes","euromarine"],"20|grid________::b2cbbf5eadbbf87d534b022bad3191d7":["mes","euromarine"],"20|snsf________::74730ef1439d7f7636a8be58a6b471b8":["mes","euromarine"],"20|nsf_________::ad72e19043a5a467e35f9b444d11563e":["mes","euromarine"],"20|ukri________::0fc3e92500290902a2d38ec2445e74c3":["mes","euromarine"],"20|grid________::ad2c29905da0eb3c06b3fa80cacd89ea":["mes","euromarine"],"20|corda__h2020::30b53e4d63d3724f00acb9cbaca40860":["mes","euromarine"],"20|corda__h2020::f60f84bee14ad93f0db0e49af1d5c317":["mes","euromarine"], "20|corda__h2020::7bf251ac3765b5e89d82270a1763d09f":["mes","euromarine"], "20|corda__h2020::65531bd11be9935948c7f2f4db1c1832":["mes","euromarine"], "20|corda__h2020::e0e98f86bbc76638bbb72a8fe2302946":["mes","euromarine"], "20|snsf________::3eb43582ac27601459a8d8b3e195724b":["mes","euromarine"], "20|corda__h2020::af2481dab65d06c8ea0ae02b5517b9b6":["mes","euromarine"], "20|corda__h2020::c19d05cfde69a50d3ebc89bd0ee49929":["mes","euromarine"], "20|corda__h2020::af0bfd9fc09f80d9488f56d71a9832f0":["mes","euromarine"], "20|ukri________::f33c02afb0dc66c49d0ed97ca5dd5cb0":["beopen"], "20|grid________::a867f78acdc5041b34acfe4f9a349157":["beopen"], "20|grid________::7bb116a1a9f95ab812bf9d2dea2be1ff":["beopen"], "20|corda__h2020::6ab0e0739dbe625b99a2ae45842164ad":["beopen"], "20|corda__h2020::8ba50792bc5f4d51d79fca47d860c602":["beopen"], "20|corda_______::8ba50792bc5f4d51d79fca47d860c602":["beopen"], "20|corda__h2020::e70e9114979e963eef24666657b807c3":["beopen"], "20|corda_______::e70e9114979e963eef24666657b807c3":["beopen"], "20|corda_______::15911e01e9744d57205825d77c218737":["beopen"], "20|opendoar____::056a41e24e2a9a67215e87bbee6a80ab":["beopen"], "20|opendoar____::7f67f2e6c6fbb0628f8160fcd3d92ae3":["beopen"], "20|grid________::a8ecfd7c084e561168bcbe6bf0daf3e3":["beopen"], "20|corda_______::7bbe6cc5d8ec1864739a04b0d020c9e9":["beopen"], "20|corda_______::3ff558e30c2e434d688539548300b050":["beopen"], "20|corda__h2020::5ffee5b3b83b33a8cf0e046877bd3a39":["beopen"], "20|corda__h2020::5187217e2e806a6df3579c46f82401bc":["beopen"], "20|grid________::5fa7e2709bcd945e26bfa18689adeec1":["beopen"], "20|corda_______::d8696683c53027438031a96ad27c3c07":["beopen"], "20|corda__h2020::d8696683c53027438031a96ad27c3c07":["beopen"], "20|ukri________::23a79ebdfa59790864e4a485881568c1":["beopen"], "20|corda__h2020::b76cf8fe49590a966953c37e18608af9":["beopen"], "20|grid________::d2f0204126ee709244a488a4cd3b91c2":["beopen"], "20|corda__h2020::05aba9d2ed17533d15221e5655ac11e6":["beopen"], "20|grid________::802401579481dc32062bdee69f5e6a34":["beopen"], "20|corda__h2020::3f6d9d54cac975a517ba6b252c81582d":["beopen"], "20|openorgs____::d11f981828c485cd23d93f7f24f24db1":["eut"], "20|openorgs____::e66fe5dd092752e1dd6fd29fc699933a":["eut"], "20|openorgs____::526468206bca24c1c90da6a312295cf4":["eut"], "20|openorgs____::08e311e656e65ccb32e07c66b15b6ff7":["eut"], "20|openorgs____::55a1f889758964b77682904218fdb298":["eut"], "20|openorgs____::530092b6970d60a5329beb9f39e8d7d4":["eut"], "20|openorgs____::aadafa39392b3e200102596a3a4aad9d":["eut"], "20|openorgs____::c3fe999c74fad308132b8a5971367dce":["eut"], "20|openorgs____::1624ff7c01bb641b91f4518539a0c28a":["aurora"], "20|openorgs____::cdda7cfe17c89eb50628ec2eb1f8acd2":["aurora"], "20|openorgs____::818b75030e0e40612d69e049843ede7e":["aurora"], "20|openorgs____::0b0102bae51f4f4ef5ba57fbe1523b92":["aurora"], "20|openorgs____::ed47496b44722f0e9d7b98898189be0d":["aurora"], "20|openorgs____::eb0669daa9efeb898a3090d8aac7c953":["aurora"], "20|openorgs____::eb391317ed0dc684aa81ac16265de041":["aurora"], "20|openorgs____::f7cfcc98245e22c7d6e321cde930e746":["aurora"], "20|openorgs____::f33179d3306ba2599f7a898b056b604f":["aurora"], "20|pending_org_::75c41e6dd18466709ef359323d96fa05":["aurora"]} pathMap ={"author":"$['author'][*]['fullname']", \ "title":"$['title'][*]['value']",\ "orcid":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']" ,\ diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml index de054b962b..8e91707b6e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml @@ -29,10 +29,6 @@ outputPath the output path - - organizationtoresultcommunitymap - organization community map - pathMap the json path associated to each selection field @@ -315,7 +311,7 @@ allowedtypes - ${allowedtupes} + ${allowedtypes} diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml index 307997d4cd..6c51634484 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml @@ -26,12 +26,20 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml index 1fbaeb5d55..933bab7e06 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml @@ -25,12 +25,20 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml index dbb22b9948..05824d209b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml @@ -18,12 +18,20 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml index 93a2f98be3..f0db9c777f 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml @@ -22,13 +22,21 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - + + + + + + + + + yarn diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml index 8aec530cc9..6aeffb4574 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml @@ -21,12 +21,21 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + + yarn @@ -75,9 +84,9 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --preparedInfoPath${workingDir}/preparedInfo/resultCommunityList + --preparedInfoPath${workingDir}/communityorganization/preparedInfo/resultCommunityList --sourcePath${sourcePath}/ - --outputPath${workingDir}/resulttocommunityfromorganization/ + --outputPath${workingDir}/communityorganization/resulttocommunityfromorganization/ diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml index 90ed2e0b6f..dd845064b2 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml @@ -21,12 +21,19 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - + + + + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml index be88c45bdc..773c7fba76 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml @@ -18,13 +18,20 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - + + + + + + + + @@ -41,8 +48,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -70,8 +79,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -99,8 +110,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -128,8 +141,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -159,8 +174,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep2 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -191,8 +208,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -220,8 +239,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -249,8 +270,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -278,8 +301,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -295,10 +320,11 @@ --outputPath${workingDir}/communitysemrel/software - + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml index dadea2d280..e963453da9 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml @@ -21,12 +21,21 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + + @@ -79,7 +88,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/publication - --outputPath${workingDir}/affiliationinstrepo/publication/relation + --outputPath${workingDir}/affiliationInstRepo/publication/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -108,7 +117,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/dataset - --outputPath${workingDir}/affiliationinstrepo/dataset/relation + --outputPath${workingDir}/affiliationInstRepo/dataset/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -137,7 +146,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/otherresearchproduct - --outputPath${workingDir}/affiliationinstrepo/otherresearchproduct/relation + --outputPath${workingDir}/affiliationInstRepo/otherresearchproduct/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -166,7 +175,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/software - --outputPath${workingDir}/affiliationinstrepo/software/relation + --outputPath${workingDir}/affiliationInstRepo/software/relation --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} @@ -197,7 +206,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --outputPath${sourcePath}/relation - --sourcePath${workingDir}/affiliationinstrepo/ + --sourcePath${workingDir}/affiliationInstRepo/ diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92ba..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml deleted file mode 100644 index 7918df120b..0000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfromsemrel/oozie_app/workflow.xml +++ /dev/null @@ -1,97 +0,0 @@ - - - - sourcePath - the source path - - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - yarn - cluster - PrepareResultOrganizationAssociation - eu.dnetlib.dhp.resulttoorganizationfromsemrel.PrepareInfo - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --graphPath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --leavesPath${workingDir}/affiliationSemanticRelation/preparedInfo/leavesPath - --childParentPath${workingDir}/affiliationSemanticRelation/preparedInfo/childParentPath - --resultOrgPath${workingDir}/affiliationSemanticRelation/preparedInfo/resultOrgPath - --relationPath${workingDir}/affiliationSemanticRelation/preparedInfo/relation - - - - - - - - yarn - cluster - resultToOrganizationFromSemRel - eu.dnetlib.dhp.resulttoorganizationfromsemrel.SparkResultToOrganizationFromSemRel - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --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.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=3840 - - --relationPath${workingDir}/affiliationSemanticRelation/preparedInfo/relation - --outputPath${sourcePath} - --leavesPath${workingDir}/affiliationSemanticRelation/preparedInfo/leavesPath - --childParentPath${workingDir}/affiliationSemanticRelation/preparedInfo/childParentPath - --resultOrgPath${workingDir}/affiliationSemanticRelation/preparedInfo/resultOrgPath - --hive_metastore_uris${hive_metastore_uris} - --workingDir${workingDir}/affiliationSemanticRelation/working - --iterations${iterations} - - - - - - - - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh index 35220bd8c9..9877fe7de5 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh +++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh @@ -1,3 +1,3 @@ #!/bin/bash curl -LSs $1 | hdfs dfs -put - $2/$3 -curl -LSs http://api.crossref.org/works/10.1099/jgv.0.001453 > prova.txt \ No newline at end of file +#curl -LSs http://api.crossref.org/works/10.1099/jgv.0.001453 > prova.txt \ No newline at end of file From 5011c4d11a4c3884c99d784ed31a336ba89f8bfc Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Wed, 20 Dec 2023 15:57:26 +0100 Subject: [PATCH 08/17] refactoring after compiletion --- .../provision/IndexRecordTransformerTest.java | 2 +- .../dhp/oa/provision/XmlIndexingJobTest.java | 29 +++++++++---------- 2 files changed, 15 insertions(+), 16 deletions(-) diff --git a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java index e07ba1b4ea..e728830554 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java +++ b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java @@ -82,7 +82,7 @@ public class IndexRecordTransformerTest { void testPeerReviewed() throws IOException, TransformerException { final XmlRecordFactory xmlRecordFactory = new XmlRecordFactory(contextMapper, false, - XmlConverterJob.schemaLocation); + XmlConverterJob.schemaLocation); final Publication p = load("publication.json", Publication.class); diff --git a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlIndexingJobTest.java b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlIndexingJobTest.java index b62acbac34..a3a140cf64 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlIndexingJobTest.java +++ b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/XmlIndexingJobTest.java @@ -1,6 +1,8 @@ package eu.dnetlib.dhp.oa.provision; +import static org.junit.jupiter.api.Assertions.assertEquals; + import java.io.IOException; import java.io.StringReader; import java.net.URI; @@ -32,8 +34,6 @@ import eu.dnetlib.dhp.oa.provision.utils.ISLookupClient; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService; -import static org.junit.jupiter.api.Assertions.assertEquals; - @ExtendWith(MockitoExtension.class) public class XmlIndexingJobTest extends SolrTest { @@ -110,34 +110,33 @@ public class XmlIndexingJobTest extends SolrTest { QueryResponse rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "*:*")); assertEquals( - nRecord, rsp.getResults().getNumFound(), - "the number of indexed records should be equal to the number of input records"); - + nRecord, rsp.getResults().getNumFound(), + "the number of indexed records should be equal to the number of input records"); rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "isgreen:true")); assertEquals( - 0, rsp.getResults().getNumFound(), - "the number of indexed records having isgreen = true"); + 0, rsp.getResults().getNumFound(), + "the number of indexed records having isgreen = true"); rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "openaccesscolor:bronze")); assertEquals( - 0, rsp.getResults().getNumFound(), - "the number of indexed records having openaccesscolor = bronze"); + 0, rsp.getResults().getNumFound(), + "the number of indexed records having openaccesscolor = bronze"); rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "isindiamondjournal:true")); assertEquals( - 0, rsp.getResults().getNumFound(), - "the number of indexed records having isindiamondjournal = true"); + 0, rsp.getResults().getNumFound(), + "the number of indexed records having isindiamondjournal = true"); rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "publiclyfunded:true")); assertEquals( - 0, rsp.getResults().getNumFound(), - "the number of indexed records having publiclyfunded = true"); + 0, rsp.getResults().getNumFound(), + "the number of indexed records having publiclyfunded = true"); rsp = miniCluster.getSolrClient().query(new SolrQuery().add(CommonParams.Q, "peerreviewed:true")); assertEquals( - 0, rsp.getResults().getNumFound(), - "the number of indexed records having peerreviewed = true"); + 0, rsp.getResults().getNumFound(), + "the number of indexed records having peerreviewed = true"); } @Test From 3afd4aa57bb107e35f71108c64c45ada698cf8a7 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 11:27:30 +0100 Subject: [PATCH 09/17] adjustments for country propagation --- .../PrepareDatasourceCountryAssociation.java | 5 ++- .../PrepareResultCountrySet.java | 2 +- .../SparkCountryPropagationJob.java | 2 +- .../PrepareInfo.java | 2 +- .../input_countrypropagation_parameters.json | 32 ++++++++++++++++ .../input_prepareassoc_parameters.json | 32 ++++++++++++++++ ...input_prepareresultcountry_parameters.json | 38 +++++++++++++++++++ .../countrypropagation/oozie_app/workflow.xml | 35 ++++++++++------- 8 files changed, 130 insertions(+), 18 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java index 430c265924..a016509e57 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java @@ -45,7 +45,7 @@ public class PrepareDatasourceCountryAssociation { .toString( PrepareDatasourceCountryAssociation.class .getResourceAsStream( - "/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -90,7 +90,8 @@ public class PrepareDatasourceCountryAssociation { (FilterFunction) ds -> !ds.getDataInfo().getDeletedbyinference() && Optional.ofNullable(ds.getDatasourcetype()).isPresent() && Optional.ofNullable(ds.getDatasourcetype().getClassid()).isPresent() && - (allowedtypes.contains(ds.getJurisdiction().getClassid()) || + ((Optional.ofNullable(ds.getJurisdiction()).isPresent() && + allowedtypes.contains(ds.getJurisdiction().getClassid())) || whitelist.contains(ds.getId()))); // filtering of the relations taking the non deleted by inference and those with IsProvidedBy as relclass diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java index 184d24751b..884aa0e47e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java @@ -32,7 +32,7 @@ public class PrepareResultCountrySet { .toString( PrepareResultCountrySet.class .getResourceAsStream( - "/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java index 17247f8125..92930c18bd 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java @@ -35,7 +35,7 @@ public class SparkCountryPropagationJob { .toString( SparkCountryPropagationJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java index 8d3432f062..bdfdde13bd 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java @@ -60,7 +60,7 @@ public class PrepareInfo implements Serializable { .toString( SparkResultToOrganizationFromIstRepoJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json")); + "/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json new file mode 100644 index 0000000000..d3cde8b747 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json @@ -0,0 +1,32 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + }, + { + "paramName": "p", + "paramLongName": "preparedInfoPath", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + } +] diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json new file mode 100644 index 0000000000..a00105f2ba --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json @@ -0,0 +1,32 @@ +[ + { + "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": "w", + "paramLongName": "whitelist", + "paramDescription": "the datasource having a type different from the allowed ones but that we want to add anyway", + "paramRequired": true + }, + { + "paramName": "at", + "paramLongName": "allowedtypes", + "paramDescription": "the allowed datasource types for country propagation", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json new file mode 100644 index 0000000000..18163d1f96 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json @@ -0,0 +1,38 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"out", + "paramLongName":"outputPath", + "paramDescription": "the output path", + "paramRequired": true + }, + { + "paramName":"w", + "paramLongName":"workingPath", + "paramDescription": "the working path", + "paramRequired": true + }, + { + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + }, + { + "paramName": "p", + "paramLongName": "preparedInfoPath", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml index 933bab7e06..81d6dc3dc1 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml @@ -61,7 +61,7 @@ --sourcePath${sourcePath} --whitelist${whitelist} --allowedtypes${allowedtypes} - --workingPath${workingDir}/country + --outputPath${workingDir}/preparedInfo @@ -95,8 +95,10 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/publication - --workingPath${workingDir}/country + --outputPath${workingDir}/publication + --workingPath${workingDir}/workingP --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication + --preparedInfoPath${workingDir}/preparedInfo @@ -123,8 +125,10 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/dataset - --workingPath${workingDir}/country + --outputPath${workingDir}/dataset + --workingPath${workingDir}/workingD --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset + --preparedInfoPath${workingDir}/preparedInfo @@ -151,8 +155,10 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/otherresearchproduct - --workingPath${workingDir}/country + --outputPath${workingDir}/otherresearchproduct + --workingPath${workingDir}/workingO --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct + --preparedInfoPath${workingDir}/preparedInfo @@ -179,14 +185,16 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/software - --workingPath${workingDir}/country + --outputPath${workingDir}/software + --workingPath${workingDir}/workingS --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + --preparedInfoPath${workingDir}/preparedInfo - + @@ -216,9 +224,9 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/publication - --workingPath${workingDir}/country + --preparedInfoPath${workingDir}/publication --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - + --outputPath${workingDir}/country/publication @@ -245,9 +253,9 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/dataset - --workingPath${workingDir}/country + --preparedInfoPath${workingDir}/dataset --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - + --outputPath${workingDir}/country/dataset @@ -274,9 +282,9 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/otherresearchproduct - --workingPath${workingDir}/country + --preparedInfoPath${workingDir}/otherresearchproduct --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - + --outputPath${workingDir}/country/otherresearchproduct @@ -303,8 +311,9 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/software - --workingPath${workingDir}/country + --preparedInfoPath${workingDir}/software --resultTableNameeu.dnetlib.dhp.schema.oaf.Software + --outputPath${workingDir}/country/software From b06aea0adfe716fede41a6fd38e847dc90dd4692 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 11:35:37 +0100 Subject: [PATCH 10/17] adding the bulkTag parameter file in the folder for the oozie workflow for bulkTagging. Changes the path in the class --- .../dnetlib/dhp/bulktag/SparkBulkTagJob.java | 2 +- .../bulktag/input_bulkTag_parameters.json | 38 +++++++++++++++++++ 2 files changed, 39 insertions(+), 1 deletion(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java index 51307ccd1e..e20fcb081a 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java @@ -45,7 +45,7 @@ public class SparkBulkTagJob { .toString( SparkBulkTagJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json new file mode 100644 index 0000000000..ce1a8ecab6 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json @@ -0,0 +1,38 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName": "pm", + "paramLongName":"pathMap", + "paramDescription": "the json path associated to each selection field", + "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 + }, + { + "paramName": "tg", + "paramLongName": "taggingConf", + "paramDescription": "this parameter is intended for testing purposes only. It is a possible tagging configuration obtained via the XQUERY. Intended to be removed", + "paramRequired": false + }, + { + "paramName": "bu", + "paramLongName": "baseURL", + "paramDescription": "this parameter is to specify the api to be queried (beta or production)", + "paramRequired": false + } +] \ No newline at end of file From 89f269c7f4b63070358724213b5d39fac0678916 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 11:37:50 +0100 Subject: [PATCH 11/17] changed the path to the parameter file in the class for entitytoorganization propagation --- .../SparkEntityToOrganizationFromSemRel.java | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java index 87c0ec2b9d..4e30a6d6a8 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java @@ -39,7 +39,7 @@ public class SparkEntityToOrganizationFromSemRel implements Serializable { .toString( SparkResultToOrganizationFromIstRepoJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json")); + "/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); From 009730b3d1616fa3337cad380b9ff8e55641c9a5 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 11:42:09 +0100 Subject: [PATCH 12/17] added properties file in the forlder for the workflow of orcid propagation. Changes the path in the classes implementing the propagationchanged the path to the parameter file in the class for entitytoorganization propagation --- .../PrepareResultOrcidAssociationStep1.java | 2 +- .../PrepareResultOrcidAssociationStep2.java | 2 +- .../SparkOrcidToResultFromSemRelJob.java | 2 +- .../input_orcidtoresult_parameters.json | 44 +++++++++++++++++++ ...input_prepareorcidtoresult_parameters.json | 38 ++++++++++++++++ ...nput_prepareorcidtoresult_parameters2.json | 20 +++++++++ 6 files changed, 105 insertions(+), 3 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java index 95b870292d..bc72a2ae1b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java @@ -31,7 +31,7 @@ public class PrepareResultOrcidAssociationStep1 { .toString( PrepareResultOrcidAssociationStep1.class .getResourceAsStream( - "/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConf); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java index c60012a748..46894d0e1b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java @@ -29,7 +29,7 @@ public class PrepareResultOrcidAssociationStep2 { .toString( PrepareResultOrcidAssociationStep2.class .getResourceAsStream( - "/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json")); + "/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java index 5f9260e5dc..c5d6326581 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java @@ -36,7 +36,7 @@ public class SparkOrcidToResultFromSemRelJob { .toString( SparkOrcidToResultFromSemRelJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json new file mode 100644 index 0000000000..3cbaa23bb6 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json @@ -0,0 +1,44 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"sg", + "paramLongName":"saveGraph", + "paramDescription": "true if the new version of the graph must be saved", + "paramRequired": false + }, + { + "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 + }, + { + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + }, + { + "paramName":"pu", + "paramLongName":"possibleUpdatesPath", + "paramDescription": "the path the the association resultId orcid author list can be found", + "paramRequired": true + }, + { + "paramName":"test", + "paramLongName":"isTest", + "paramDescription": "true if it is executing a test", + "paramRequired": false + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json new file mode 100644 index 0000000000..08648d61a1 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json @@ -0,0 +1,38 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"as", + "paramLongName":"allowedsemrels", + "paramDescription": "the allowed sematinc relations for propagation", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "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 + }, + { + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json new file mode 100644 index 0000000000..1a67134a6b --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json @@ -0,0 +1,20 @@ +[ + { + "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 + } +] \ No newline at end of file From f2352e8a78017f26f297833546e1a0853c5a89b7 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 11:43:34 +0100 Subject: [PATCH 13/17] changed in the classes the path for the property files for the propagation of community from project --- .../resulttocommunityfromproject/PrepareResultCommunitySet.java | 2 +- .../SparkResultToCommunityFromProject.java | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java index 467e11a969..512dfa9bed 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java @@ -38,7 +38,7 @@ public class PrepareResultCommunitySet { .toString( PrepareResultCommunitySet.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java index 229ac7e32e..dde5340617 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java @@ -44,7 +44,7 @@ public class SparkResultToCommunityFromProject implements Serializable { .toString( SparkResultToCommunityFromProject.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); From 2f7b9ad815358857dd14656ae1e4b160e7721662 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 11:46:15 +0100 Subject: [PATCH 14/17] added properties file in the forlder for the workflow of project to result propagation. Changes the path in the classes implementing the propagation --- .../PrepareProjectResultsAssociation.java | 2 +- .../SparkResultToProjectThroughSemRelJob.java | 2 +- ...put_prepareprojecttoresult_parameters.json | 33 ++++++++++++++ .../input_projecttoresult_parameters.json | 44 +++++++++++++++++++ 4 files changed, 79 insertions(+), 2 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java index ac61e26f94..8f4e2ad9a5 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java @@ -28,7 +28,7 @@ public class PrepareProjectResultsAssociation { .toString( PrepareProjectResultsAssociation.class .getResourceAsStream( - "/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java index 1ec521af18..e7518673d8 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java @@ -33,7 +33,7 @@ public class SparkResultToProjectThroughSemRelJob { .toString( SparkResultToProjectThroughSemRelJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json new file mode 100644 index 0000000000..a70dbd6a08 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json @@ -0,0 +1,33 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + + { + "paramName":"asr", + "paramLongName":"allowedsemrels", + "paramDescription": "the types of the allowed datasources. Split by ;", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName":"pu", + "paramLongName":"potentialUpdatePath", + "paramDescription": "the path of the potential updates ", + "paramRequired": true + }, + { + "paramName":"al", + "paramLongName":"alreadyLinkedPath", + "paramDescription": "the path of the already linked project result_set", + "paramRequired": true + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json new file mode 100644 index 0000000000..7f44ba03cd --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json @@ -0,0 +1,44 @@ +[ + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName":"sg", + "paramLongName":"saveGraph", + "paramDescription": "true if the new version of the graph must be saved", + "paramRequired": false + }, + { + "paramName":"pu", + "paramLongName":"potentialUpdatePath", + "paramDescription": "the path of the potential updates ", + "paramRequired": true + }, + { + "paramName":"al", + "paramLongName":"alreadyLinkedPath", + "paramDescription": "the path of the already linked project result_set", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + }, + { + "paramName": "test", + "paramLongName": "isTest", + "paramDescription": "true if it is a test running", + "paramRequired": false + } +] \ No newline at end of file From 2f3b5a133d4ddfc4ed6a38366c927330d2c25b08 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 13:56:40 +0100 Subject: [PATCH 15/17] added properties file in the forlder for the workflow of result to community from organization propagation. Changes the path in the classes implementing the propagation --- .../PrepareResultCommunitySet.java | 2 +- ...kResultToCommunityFromOrganizationJob.java | 2 +- .../input_communitytoresult_parameters.json | 28 ++++++++++++++++ ...t_preparecommunitytoresult_parameters.json | 33 +++++++++++++++++++ 4 files changed, 63 insertions(+), 2 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java index 54fa601681..be31cd46cc 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java @@ -34,7 +34,7 @@ public class PrepareResultCommunitySet { .toString( PrepareResultCommunitySet.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java index adb7feef7e..cc87b80e5e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java @@ -36,7 +36,7 @@ public class SparkResultToCommunityFromOrganizationJob { .toString( SparkResultToCommunityFromOrganizationJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json new file mode 100644 index 0000000000..0db8085d19 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json @@ -0,0 +1,28 @@ +[ + { + "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 + }, + { + "paramName": "p", + "paramLongName": "preparedInfoPath", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": true + } + +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json new file mode 100644 index 0000000000..3601db7acc --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json @@ -0,0 +1,33 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + }, + { + "paramName": "bu", + "paramLongName": "baseURL", + "paramDescription": "the base URL to the community API to use", + "paramRequired": false + } + +] \ No newline at end of file From 9f966b59d446ba83d9dd002dddaf1d9585a3b037 Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 14:11:47 +0100 Subject: [PATCH 16/17] added properties file in the forlder for the workflow of result to community from semrel propagation. Changes the path in the classes implementing the propagation --- .../PrepareResultCommunitySetStep1.java | 2 +- .../PrepareResultCommunitySetStep2.java | 2 +- ...parkResultToCommunityThroughSemRelJob.java | 2 +- .../input_communitytoresult_parameters.json | 52 +++++++++++++++++++ ..._preparecommunitytoresult2_parameters.json | 20 +++++++ ...t_preparecommunitytoresult_parameters.json | 44 ++++++++++++++++ 6 files changed, 119 insertions(+), 3 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java index 40c074a6e5..aede9ef05b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java @@ -61,7 +61,7 @@ public class PrepareResultCommunitySetStep1 { .toString( PrepareResultCommunitySetStep1.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java index 0ddb19a1ac..a53d3dfe32 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java @@ -31,7 +31,7 @@ public class PrepareResultCommunitySetStep2 { .toString( PrepareResultCommunitySetStep2.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java index a107378499..4929c7582d 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java @@ -33,7 +33,7 @@ public class SparkResultToCommunityThroughSemRelJob { .toString( SparkResultToCommunityThroughSemRelJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json new file mode 100644 index 0000000000..a40ce375ee --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json @@ -0,0 +1,52 @@ +[ + + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"sg", + "paramLongName":"saveGraph", + "paramDescription": "true if the new version of the graph must be saved", + "paramRequired": false + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + }, + { + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + }, + { + "paramName": "p", + "paramLongName": "preparedInfoPath", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": true + }, + { + "paramName":"test", + "paramLongName":"isTest", + "paramDescription": "true if it is executing a test", + "paramRequired": false + } + +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json new file mode 100644 index 0000000000..3ba3c8e9c7 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json @@ -0,0 +1,20 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + } +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json new file mode 100644 index 0000000000..c6389ec8da --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json @@ -0,0 +1,44 @@ +[ + { + "paramName":"bu", + "paramLongName":"baseURL", + "paramDescription": "URL of the isLookUp Service", + "paramRequired": true + }, + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"as", + "paramLongName":"allowedsemrels", + "paramDescription": "the allowed semantic relations for propagation", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "true if the spark session is managed, false otherwise", + "paramRequired": false + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + }, + { + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + } +] \ No newline at end of file From cb14470ba6779bd6f5dea3e1b937512295c0854a Mon Sep 17 00:00:00 2001 From: "miriam.baglioni" Date: Fri, 22 Dec 2023 14:50:05 +0100 Subject: [PATCH 17/17] added properties file in the forlder for the workflow of result to organization from inst repo propagation. Changes the path in the classes implementing the propagation --- .../AppendNewRelations.java | 2 +- .../PrepareResultInstRepoAssociation.java | 2 +- ...arkResultToOrganizationFromIstRepoJob.java | 2 +- .../input_newrelation_parameters.json | 20 +++++++ .../input_prepareresultorg_parameters.json | 32 +++++++++++ ...sulaffiliationfrominstrepo_parameters.json | 56 +++++++++++++++++++ 6 files changed, 111 insertions(+), 3 deletions(-) create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json create mode 100644 dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java index 636c14b655..11e9421426 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java @@ -30,7 +30,7 @@ public class AppendNewRelations implements Serializable { .toString( AppendNewRelations.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_newrelation_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java index deec6fedc6..57488bd209 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java @@ -40,7 +40,7 @@ public class PrepareResultInstRepoAssociation { .toString( PrepareResultInstRepoAssociation.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java index bbad20e2d5..c8862b10c4 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java @@ -47,7 +47,7 @@ public class SparkResultToOrganizationFromIstRepoJob { .toString( SparkResultToOrganizationFromIstRepoJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json new file mode 100644 index 0000000000..5fe92cff13 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json @@ -0,0 +1,20 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + },{ + "paramName": "o", + "paramLongName": "outputPath", + "paramDescription": "institutional repositories that should not be considered for the propagation", + "paramRequired": false +} +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json new file mode 100644 index 0000000000..3f4b1d151b --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json @@ -0,0 +1,32 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + + { + "paramName":"wp", + "paramLongName":"workingPath", + "paramDescription": "the working path", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + },{ + "paramName": "bl", + "paramLongName": "blacklist", + "paramDescription": "institutional repositories that should not be considered for the propagation", + "paramRequired": false +} +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json new file mode 100644 index 0000000000..d2b076c827 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json @@ -0,0 +1,56 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hive_metastore_uris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName":"sg", + "paramLongName":"saveGraph", + "paramDescription": "true if the new version of the graph must be saved", + "paramRequired": false + }, + { + "paramName":"dop", + "paramLongName":"datasourceOrganizationPath", + "paramDescription": "path where to store/find association from datasource and organization", + "paramRequired": true + }, + { + "paramName":"alp", + "paramLongName":"alreadyLinkedPath", + "paramDescription": "path where to store/find already linked results and organizations", + "paramRequired": true + }, + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + }, + { + "paramName": "test", + "paramLongName": "isTest", + "paramDescription": "true if it is a test running", + "paramRequired": false + }, + { + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + }, + { + "paramName": "out", + "paramLongName": "outputPath", + "paramDescription": "the path used to store temporary output files", + "paramRequired": true + } +] \ No newline at end of file