Feature/neo4j user collection isolation (#509)

* Tech spec

* User/collection separation

* Update tests
This commit is contained in:
cybermaggedon 2025-09-10 22:11:21 +01:00 committed by GitHub
parent 0b59f0c828
commit c694b12e9c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 2008 additions and 81 deletions

View file

@ -55,6 +55,10 @@ class Processor(TriplesQueryService):
try:
# Extract user and collection, use defaults if not provided
user = query.user if query.user else "default"
collection = query.collection if query.collection else "default"
triples = []
if query.s is not None:
@ -64,9 +68,12 @@ class Processor(TriplesQueryService):
# SPO
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel {uri: $rel}]->(dest:Literal {value: $value}) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {uri: $rel, user: $user, collection: $collection}]->"
"(dest:Literal {value: $value, user: $user, collection: $collection}) "
"RETURN $src as src",
src=query.s.value, rel=query.p.value, value=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -74,9 +81,12 @@ class Processor(TriplesQueryService):
triples.append((query.s.value, query.p.value, query.o.value))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel {uri: $rel}]->(dest:Node {uri: $uri}) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {uri: $rel, user: $user, collection: $collection}]->"
"(dest:Node {uri: $uri, user: $user, collection: $collection}) "
"RETURN $src as src",
src=query.s.value, rel=query.p.value, uri=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -88,9 +98,12 @@ class Processor(TriplesQueryService):
# SP
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel {uri: $rel}]->(dest:Literal) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {uri: $rel, user: $user, collection: $collection}]->"
"(dest:Literal {user: $user, collection: $collection}) "
"RETURN dest.value as dest",
src=query.s.value, rel=query.p.value,
user=user, collection=collection,
database_=self.db,
)
@ -99,9 +112,12 @@ class Processor(TriplesQueryService):
triples.append((query.s.value, query.p.value, data["dest"]))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel {uri: $rel}]->(dest:Node) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {uri: $rel, user: $user, collection: $collection}]->"
"(dest:Node {user: $user, collection: $collection}) "
"RETURN dest.uri as dest",
src=query.s.value, rel=query.p.value,
user=user, collection=collection,
database_=self.db,
)
@ -116,9 +132,12 @@ class Processor(TriplesQueryService):
# SO
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel]->(dest:Literal {value: $value}) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Literal {value: $value, user: $user, collection: $collection}) "
"RETURN rel.uri as rel",
src=query.s.value, value=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -127,9 +146,12 @@ class Processor(TriplesQueryService):
triples.append((query.s.value, data["rel"], query.o.value))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel]->(dest:Node {uri: $uri}) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Node {uri: $uri, user: $user, collection: $collection}) "
"RETURN rel.uri as rel",
src=query.s.value, uri=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -142,9 +164,12 @@ class Processor(TriplesQueryService):
# S
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel]->(dest:Literal) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Literal {user: $user, collection: $collection}) "
"RETURN rel.uri as rel, dest.value as dest",
src=query.s.value,
user=user, collection=collection,
database_=self.db,
)
@ -153,9 +178,12 @@ class Processor(TriplesQueryService):
triples.append((query.s.value, data["rel"], data["dest"]))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node {uri: $src})-[rel:Rel]->(dest:Node) "
"MATCH (src:Node {uri: $src, user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Node {user: $user, collection: $collection}) "
"RETURN rel.uri as rel, dest.uri as dest",
src=query.s.value,
user=user, collection=collection,
database_=self.db,
)
@ -173,9 +201,12 @@ class Processor(TriplesQueryService):
# PO
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel {uri: $uri}]->(dest:Literal {value: $value}) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {uri: $uri, user: $user, collection: $collection}]->"
"(dest:Literal {value: $value, user: $user, collection: $collection}) "
"RETURN src.uri as src",
uri=query.p.value, value=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -184,9 +215,12 @@ class Processor(TriplesQueryService):
triples.append((data["src"], query.p.value, query.o.value))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel {uri: $uri}]->(dest:Node {uri: $dest}) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {uri: $uri, user: $user, collection: $collection}]->"
"(dest:Node {uri: $dest, user: $user, collection: $collection}) "
"RETURN src.uri as src",
uri=query.p.value, dest=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -199,9 +233,12 @@ class Processor(TriplesQueryService):
# P
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel {uri: $uri}]->(dest:Literal) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {uri: $uri, user: $user, collection: $collection}]->"
"(dest:Literal {user: $user, collection: $collection}) "
"RETURN src.uri as src, dest.value as dest",
uri=query.p.value,
user=user, collection=collection,
database_=self.db,
)
@ -210,9 +247,12 @@ class Processor(TriplesQueryService):
triples.append((data["src"], query.p.value, data["dest"]))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel {uri: $uri}]->(dest:Node) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {uri: $uri, user: $user, collection: $collection}]->"
"(dest:Node {user: $user, collection: $collection}) "
"RETURN src.uri as src, dest.uri as dest",
uri=query.p.value,
user=user, collection=collection,
database_=self.db,
)
@ -227,9 +267,12 @@ class Processor(TriplesQueryService):
# O
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel]->(dest:Literal {value: $value}) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Literal {value: $value, user: $user, collection: $collection}) "
"RETURN src.uri as src, rel.uri as rel",
value=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -238,9 +281,12 @@ class Processor(TriplesQueryService):
triples.append((data["src"], data["rel"], query.o.value))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel]->(dest:Node {uri: $uri}) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Node {uri: $uri, user: $user, collection: $collection}) "
"RETURN src.uri as src, rel.uri as rel",
uri=query.o.value,
user=user, collection=collection,
database_=self.db,
)
@ -253,8 +299,11 @@ class Processor(TriplesQueryService):
# *
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel]->(dest:Literal) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Literal {user: $user, collection: $collection}) "
"RETURN src.uri as src, rel.uri as rel, dest.value as dest",
user=user, collection=collection,
database_=self.db,
)
@ -263,8 +312,11 @@ class Processor(TriplesQueryService):
triples.append((data["src"], data["rel"], data["dest"]))
records, summary, keys = self.io.execute_query(
"MATCH (src:Node)-[rel:Rel]->(dest:Node) "
"MATCH (src:Node {user: $user, collection: $collection})-"
"[rel:Rel {user: $user, collection: $collection}]->"
"(dest:Node {user: $user, collection: $collection}) "
"RETURN src.uri as src, rel.uri as rel, dest.uri as dest",
user=user, collection=collection,
database_=self.db,
)

View file

@ -61,6 +61,7 @@ class Processor(TriplesStoreService):
logger.info("Create indexes...")
# Legacy indexes for backwards compatibility
try:
session.run(
"CREATE INDEX Node_uri FOR (n:Node) ON (n.uri)",
@ -88,15 +89,50 @@ class Processor(TriplesStoreService):
# Maybe index already exists
logger.warning("Index create failure ignored")
# New compound indexes for user/collection filtering
try:
session.run(
"CREATE INDEX node_user_collection_uri FOR (n:Node) ON (n.user, n.collection, n.uri)",
)
except Exception as e:
logger.warning(f"Compound index create failure: {e}")
logger.warning("Index create failure ignored")
try:
session.run(
"CREATE INDEX literal_user_collection_value FOR (n:Literal) ON (n.user, n.collection, n.value)",
)
except Exception as e:
logger.warning(f"Compound index create failure: {e}")
logger.warning("Index create failure ignored")
# Note: Neo4j doesn't support compound indexes on relationships in all versions
# Try to create individual indexes on relationship properties
try:
session.run(
"CREATE INDEX rel_user FOR ()-[r:Rel]-() ON (r.user)",
)
except Exception as e:
logger.warning(f"Relationship index create failure: {e}")
logger.warning("Index create failure ignored")
try:
session.run(
"CREATE INDEX rel_collection FOR ()-[r:Rel]-() ON (r.collection)",
)
except Exception as e:
logger.warning(f"Relationship index create failure: {e}")
logger.warning("Index create failure ignored")
logger.info("Index creation done")
def create_node(self, uri):
def create_node(self, uri, user, collection):
logger.debug(f"Create node {uri}")
logger.debug(f"Create node {uri} for user={user}, collection={collection}")
summary = self.io.execute_query(
"MERGE (n:Node {uri: $uri})",
uri=uri,
"MERGE (n:Node {uri: $uri, user: $user, collection: $collection})",
uri=uri, user=user, collection=collection,
database_=self.db,
).summary
@ -105,13 +141,13 @@ class Processor(TriplesStoreService):
time=summary.result_available_after
))
def create_literal(self, value):
def create_literal(self, value, user, collection):
logger.debug(f"Create literal {value}")
logger.debug(f"Create literal {value} for user={user}, collection={collection}")
summary = self.io.execute_query(
"MERGE (n:Literal {value: $value})",
value=value,
"MERGE (n:Literal {value: $value, user: $user, collection: $collection})",
value=value, user=user, collection=collection,
database_=self.db,
).summary
@ -120,15 +156,15 @@ class Processor(TriplesStoreService):
time=summary.result_available_after
))
def relate_node(self, src, uri, dest):
def relate_node(self, src, uri, dest, user, collection):
logger.debug(f"Create node rel {src} {uri} {dest}")
logger.debug(f"Create node rel {src} {uri} {dest} for user={user}, collection={collection}")
summary = self.io.execute_query(
"MATCH (src:Node {uri: $src}) "
"MATCH (dest:Node {uri: $dest}) "
"MERGE (src)-[:Rel {uri: $uri}]->(dest)",
src=src, dest=dest, uri=uri,
"MATCH (src:Node {uri: $src, user: $user, collection: $collection}) "
"MATCH (dest:Node {uri: $dest, user: $user, collection: $collection}) "
"MERGE (src)-[:Rel {uri: $uri, user: $user, collection: $collection}]->(dest)",
src=src, dest=dest, uri=uri, user=user, collection=collection,
database_=self.db,
).summary
@ -137,15 +173,15 @@ class Processor(TriplesStoreService):
time=summary.result_available_after
))
def relate_literal(self, src, uri, dest):
def relate_literal(self, src, uri, dest, user, collection):
logger.debug(f"Create literal rel {src} {uri} {dest}")
logger.debug(f"Create literal rel {src} {uri} {dest} for user={user}, collection={collection}")
summary = self.io.execute_query(
"MATCH (src:Node {uri: $src}) "
"MATCH (dest:Literal {value: $dest}) "
"MERGE (src)-[:Rel {uri: $uri}]->(dest)",
src=src, dest=dest, uri=uri,
"MATCH (src:Node {uri: $src, user: $user, collection: $collection}) "
"MATCH (dest:Literal {value: $dest, user: $user, collection: $collection}) "
"MERGE (src)-[:Rel {uri: $uri, user: $user, collection: $collection}]->(dest)",
src=src, dest=dest, uri=uri, user=user, collection=collection,
database_=self.db,
).summary
@ -156,16 +192,20 @@ class Processor(TriplesStoreService):
async def store_triples(self, message):
# Extract user and collection from metadata
user = message.metadata.user if message.metadata.user else "default"
collection = message.metadata.collection if message.metadata.collection else "default"
for t in message.triples:
self.create_node(t.s.value)
self.create_node(t.s.value, user, collection)
if t.o.is_uri:
self.create_node(t.o.value)
self.relate_node(t.s.value, t.p.value, t.o.value)
self.create_node(t.o.value, user, collection)
self.relate_node(t.s.value, t.p.value, t.o.value, user, collection)
else:
self.create_literal(t.o.value)
self.relate_literal(t.s.value, t.p.value, t.o.value)
self.create_literal(t.o.value, user, collection)
self.relate_literal(t.s.value, t.p.value, t.o.value, user, collection)
@staticmethod
def add_args(parser):