From 18aa323ee972c8b0565273ada553892f0568f83e Mon Sep 17 00:00:00 2001 From: Claudio Atzori Date: Wed, 8 May 2024 11:36:46 +0200 Subject: [PATCH] cleanup unused classes, adjustments in the oozie wf definition --- .../dhp/oa/provision/RelationComparator.java | 44 ---------- .../dhp/oa/provision/RelationList.java | 25 ------ .../dhp/oa/provision/SortableRelation.java | 81 ------------------- .../model/ProvisionModelSupport.java | 10 +-- .../dhp/oa/provision/oozie_app/workflow.xml | 11 +-- 5 files changed, 7 insertions(+), 164 deletions(-) delete mode 100644 dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationComparator.java delete mode 100644 dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationList.java delete mode 100644 dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/SortableRelation.java diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationComparator.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationComparator.java deleted file mode 100644 index e13bc60eb..000000000 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationComparator.java +++ /dev/null @@ -1,44 +0,0 @@ - -package eu.dnetlib.dhp.oa.provision; - -import java.util.Comparator; -import java.util.Map; -import java.util.Optional; - -import com.google.common.collect.ComparisonChain; -import com.google.common.collect.Maps; - -import eu.dnetlib.dhp.schema.common.ModelConstants; -import eu.dnetlib.dhp.schema.oaf.Relation; - -public class RelationComparator implements Comparator { - - private static final Map weights = Maps.newHashMap(); - - static { - weights.put(ModelConstants.OUTCOME, 0); - weights.put(ModelConstants.SUPPLEMENT, 1); - weights.put(ModelConstants.REVIEW, 2); - weights.put(ModelConstants.CITATION, 3); - weights.put(ModelConstants.AFFILIATION, 4); - weights.put(ModelConstants.RELATIONSHIP, 5); - weights.put(ModelConstants.PUBLICATION_DATASET, 6); - weights.put(ModelConstants.SIMILARITY, 7); - - weights.put(ModelConstants.PROVISION, 8); - weights.put(ModelConstants.PARTICIPATION, 9); - weights.put(ModelConstants.DEDUP, 10); - } - - private Integer getWeight(Relation o) { - return Optional.ofNullable(weights.get(o.getSubRelType())).orElse(Integer.MAX_VALUE); - } - - @Override - public int compare(Relation o1, Relation o2) { - return ComparisonChain - .start() - .compare(getWeight(o1), getWeight(o2)) - .result(); - } -} diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationList.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationList.java deleted file mode 100644 index 6e5fd7dba..000000000 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/RelationList.java +++ /dev/null @@ -1,25 +0,0 @@ - -package eu.dnetlib.dhp.oa.provision; - -import java.io.Serializable; -import java.util.PriorityQueue; -import java.util.Queue; - -import eu.dnetlib.dhp.schema.oaf.Relation; - -public class RelationList implements Serializable { - - private Queue relations; - - public RelationList() { - this.relations = new PriorityQueue<>(new RelationComparator()); - } - - public Queue getRelations() { - return relations; - } - - public void setRelations(Queue relations) { - this.relations = relations; - } -} diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/SortableRelation.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/SortableRelation.java deleted file mode 100644 index 8740b47fc..000000000 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/SortableRelation.java +++ /dev/null @@ -1,81 +0,0 @@ - -package eu.dnetlib.dhp.oa.provision; - -import java.io.Serializable; -import java.util.Map; -import java.util.Optional; - -import com.fasterxml.jackson.annotation.JsonIgnore; -import com.google.common.collect.ComparisonChain; -import com.google.common.collect.Maps; - -import eu.dnetlib.dhp.schema.common.ModelConstants; -import eu.dnetlib.dhp.schema.oaf.Relation; - -public class SortableRelation extends Relation implements Comparable, Serializable { - - private static final Map weights = Maps.newHashMap(); - - static { - weights.put(ModelConstants.OUTCOME, 0); - weights.put(ModelConstants.SUPPLEMENT, 1); - weights.put(ModelConstants.REVIEW, 2); - weights.put(ModelConstants.CITATION, 3); - weights.put(ModelConstants.AFFILIATION, 4); - weights.put(ModelConstants.RELATIONSHIP, 5); - weights.put(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID, 6); - weights.put(ModelConstants.SIMILARITY, 7); - - weights.put(ModelConstants.PROVISION, 8); - weights.put(ModelConstants.PARTICIPATION, 9); - weights.put(ModelConstants.DEDUP, 10); - } - - private static final long serialVersionUID = 34753984579L; - - private String groupingKey; - - public static SortableRelation create(Relation r, String groupingKey) { - SortableRelation sr = new SortableRelation(); - sr.setGroupingKey(groupingKey); - sr.setSource(r.getSource()); - sr.setTarget(r.getTarget()); - sr.setRelType(r.getRelType()); - sr.setSubRelType(r.getSubRelType()); - sr.setRelClass(r.getRelClass()); - sr.setDataInfo(r.getDataInfo()); - sr.setCollectedfrom(r.getCollectedfrom()); - sr.setLastupdatetimestamp(r.getLastupdatetimestamp()); - sr.setProperties(r.getProperties()); - sr.setValidated(r.getValidated()); - sr.setValidationDate(r.getValidationDate()); - - return sr; - } - - @JsonIgnore - public Relation asRelation() { - return this; - } - - @Override - public int compareTo(SortableRelation o) { - return ComparisonChain - .start() - .compare(getGroupingKey(), o.getGroupingKey()) - .compare(getWeight(this), getWeight(o)) - .result(); - } - - private Integer getWeight(SortableRelation o) { - return Optional.ofNullable(weights.get(o.getSubRelType())).orElse(Integer.MAX_VALUE); - } - - public String getGroupingKey() { - return groupingKey; - } - - public void setGroupingKey(String groupingKey) { - this.groupingKey = groupingKey; - } -} diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/model/ProvisionModelSupport.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/model/ProvisionModelSupport.java index 0e6e95de5..10a99704c 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/model/ProvisionModelSupport.java +++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/model/ProvisionModelSupport.java @@ -1,8 +1,6 @@ package eu.dnetlib.dhp.oa.provision.model; -import static org.apache.commons.lang3.StringUtils.substringBefore; - import java.io.StringReader; import java.util.*; import java.util.stream.Collectors; @@ -16,12 +14,9 @@ import org.jetbrains.annotations.Nullable; import com.google.common.base.Splitter; import com.google.common.collect.Lists; import com.google.common.collect.Maps; -import com.google.common.collect.Sets; import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup; import eu.dnetlib.dhp.common.vocabulary.VocabularyTerm; -import eu.dnetlib.dhp.oa.provision.RelationList; -import eu.dnetlib.dhp.oa.provision.SortableRelation; import eu.dnetlib.dhp.oa.provision.utils.ContextDef; import eu.dnetlib.dhp.oa.provision.utils.ContextMapper; import eu.dnetlib.dhp.schema.common.ModelSupport; @@ -55,10 +50,7 @@ public class ProvisionModelSupport { .newArrayList( RelatedEntityWrapper.class, JoinedEntity.class, - RelatedEntity.class, - SortableRelationKey.class, - SortableRelation.class, - RelationList.class)); + RelatedEntity.class)); return modelClasses.toArray(new Class[] {}); } diff --git a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml index 434b4c9af..1fc28e7ca 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml @@ -125,7 +125,7 @@ ${wf:conf('resumeFrom') eq 'prepare_relations'} ${wf:conf('resumeFrom') eq 'fork_join_related_entities'} ${wf:conf('resumeFrom') eq 'fork_join_all_entities'} - ${wf:conf('resumeFrom') eq 'convert_to_xml'} + ${wf:conf('resumeFrom') eq 'create_payloads'} ${wf:conf('resumeFrom') eq 'drop_solr_collection'} ${wf:conf('resumeFrom') eq 'to_solr_index'} @@ -587,19 +587,20 @@ - + - + yarn cluster - convert_to_xml + create_payloads eu.dnetlib.dhp.oa.provision.XmlConverterJob dhp-graph-provision-${projectVersion}.jar --executor-cores=${sparkExecutorCores} --executor-memory=${sparkExecutorMemory} --driver-memory=${sparkDriverMemory} + --conf spark.executor.memoryOverhead=${sparkExecutorMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} @@ -607,7 +608,7 @@ --conf spark.sql.shuffle.partitions=3840 --conf spark.network.timeout=${sparkNetworkTimeout} - --inputPath${workingDir}/join_entities + --inputPath/user/claudio.atzori/data/beta_provision/join_entities --outputPath${workingDir}/xml_json --contextApiBaseUrl${contextApiBaseUrl} --isLookupUrl${isLookupUrl}