Skip to content

Derek furst/fix duplicate ancestors #811

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yuanzhou merged 2 commits into from
Feb 11, 2025
Merged

Derek furst/fix duplicate ancestors #811

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
09decf0
fixed issue causing duplicate results in ancestors/descendants/childr…
DerekFurstPitt Feb 7, 2025
e010d85
included get_collection_datasets and get_upload_Datasets to duplicate…
DerekFurstPitt Feb 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 12 additions & 14 deletions src/schema/schema_neo4j_queries.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,9 +176,8 @@ def get_children(neo4j_driver, uuid, property_key = None):
query = (f"MATCH (e:Entity)-[:ACTIVITY_INPUT]->(:Activity)-[:ACTIVITY_OUTPUT]->(child:Entity) "
# The target entity can't be a Lab
f"WHERE e.uuid='{uuid}' AND e.entity_type <> 'Lab' "
# COLLECT() returns a list
# apoc.coll.toSet() reruns a set containing unique nodes
f"RETURN apoc.coll.toSet(COLLECT(apoc.create.vNode(labels(child), apoc.map.removeKeys(properties(child), {fields_to_omit})))) AS {record_field_name}")
f"WITH COLLECT(DISTINCT child) AS uniqueChildren "
f"RETURN [a IN uniqueChildren | apoc.create.vNode(labels(a), apoc.map.removeKeys(properties(a), {fields_to_omit}))] AS {record_field_name}")

logger.info("======get_children() query======")
logger.info(query)
Expand Down Expand Up @@ -228,9 +227,8 @@ def get_parents(neo4j_driver, uuid, property_key = None):
query = (f"MATCH (e:Entity)<-[:ACTIVITY_OUTPUT]-(:Activity)<-[:ACTIVITY_INPUT]-(parent:Entity) "
# Filter out the Lab entities
f"WHERE e.uuid='{uuid}' AND parent.entity_type <> 'Lab' "
# COLLECT() returns a list
# apoc.coll.toSet() reruns a set containing unique nodes
f"RETURN apoc.coll.toSet(COLLECT(apoc.create.vNode(labels(parent), apoc.map.removeKeys(properties(parent), {fields_to_omit})))) AS {record_field_name}")
f"WITH COLLECT(DISTINCT parent) AS uniqueParents "
f"RETURN [a IN uniqueParents | apoc.create.vNode(labels(a), apoc.map.removeKeys(properties(a), {fields_to_omit}))] AS {record_field_name}")

logger.info("======get_parents() query======")
logger.info(query)
Expand Down Expand Up @@ -392,9 +390,8 @@ def get_ancestors(neo4j_driver, uuid, property_key = None):
query = (f"MATCH (e:Entity)<-[:ACTIVITY_INPUT|ACTIVITY_OUTPUT*]-(ancestor:Entity) "
# Filter out the Lab entities
f"WHERE e.uuid='{uuid}' AND ancestor.entity_type <> 'Lab' "
# COLLECT() returns a list
# apoc.coll.toSet() reruns a set containing unique nodes
f"RETURN apoc.coll.toSet(COLLECT(apoc.create.vNode(labels(ancestor), apoc.map.removeKeys(properties(ancestor), {fields_to_omit})))) AS {record_field_name}")
f"WITH COLLECT(DISTINCT ancestor) AS uniqueAncestors "
f"RETURN [a IN uniqueAncestors | apoc.create.vNode(labels(a), apoc.map.removeKeys(properties(a), {fields_to_omit}))] AS {record_field_name}")

logger.info("======get_ancestors() query======")
logger.info(query)
Expand Down Expand Up @@ -443,9 +440,8 @@ def get_descendants(neo4j_driver, uuid, property_key = None):
query = (f"MATCH (e:Entity)-[:ACTIVITY_INPUT|ACTIVITY_OUTPUT*]->(descendant:Entity) "
# The target entity can't be a Lab
f"WHERE e.uuid='{uuid}' AND e.entity_type <> 'Lab' "
# COLLECT() returns a list
# apoc.coll.toSet() reruns a set containing unique nodes
f"RETURN apoc.coll.toSet(COLLECT(apoc.create.vNode(labels(descendant), apoc.map.removeKeys(properties(descendant), {fields_to_omit})))) AS {record_field_name}")
f"WITH COLLECT(DISTINCT descendant) AS uniqueDescendants "
f"RETURN [a IN uniqueDescendants | apoc.create.vNode(labels(a), apoc.map.removeKeys(properties(a), {fields_to_omit}))] AS {record_field_name}")

logger.info("======get_descendants() query======")
logger.info(query)
Expand Down Expand Up @@ -1188,7 +1184,8 @@ def get_collection_datasets(neo4j_driver, uuid):
fields_to_omit = SchemaConstants.OMITTED_FIELDS
query = (f"MATCH (e:Dataset)-[:IN_COLLECTION]->(c:Collection) "
f"WHERE c.uuid = '{uuid}' "
f"RETURN COLLECT(apoc.create.vNode(labels(e), apoc.map.removeKeys(properties(e), {fields_to_omit}))) AS {record_field_name}")
f"WITH COLLECT(DISTINCT e) AS uniqueDataset "
f"RETURN [a IN uniqueDataset | apoc.create.vNode(labels(a), apoc.map.removeKeys(properties(a), {fields_to_omit}))] AS {record_field_name}")

logger.info("======get_collection_datasets() query======")
logger.info(query)
Expand Down Expand Up @@ -1401,7 +1398,8 @@ def get_upload_datasets(neo4j_driver, uuid, property_key = None):
else:
query = (f"MATCH (e:Dataset)-[:IN_UPLOAD]->(s:Upload) "
f"WHERE s.uuid = '{uuid}' "
f"RETURN COLLECT(apoc.create.vNode(labels(e), apoc.map.removeKeys(properties(e), {fields_to_omit}))) AS {record_field_name}")
f"WITH COLLECT(DISTINCT e) AS uniqueUploads "
f"RETURN [a IN uniqueUploads | apoc.create.vNode(labels(a), apoc.map.removeKeys(properties(a), {fields_to_omit}))] AS {record_field_name}")

logger.info("======get_upload_datasets() query======")
logger.info(query)
Expand Down