mirror of
https://github.com/trustgraph-ai/trustgraph.git
synced 2026-05-17 03:15:14 +02:00
release/v2.4 -> master (#924)
* CLI auth migration, document embeddings core lifecycle (#913) Migrate get_kg_core and put_kg_core CLI tools to use Api/SocketClient with first-frame auth (fixes broken raw websocket path). Fix wire format field names (root/vector). Remove ~600 lines of dead raw websocket code from invoke_graph_rag.py. Add document embeddings core lifecycle to the knowledge service: list/get/put/delete/load operations across schema, translator, Cassandra table store, knowledge manager, gateway registry, REST API, socket client, and CLI (tg-get-de-core, tg-put-de-core). Fix delete_kg_core to also clean up document embeddings rows. * Remove spurious workspace parameter from SPARQL algebra evaluator (#915) Fix threading of workspace paramater: - The SPARQL algebra evaluator was threading a workspace parameter through every function and passing it to TriplesClient.query(), which doesn't accept it. Workspace isolation is handled by pub/sub topic routing — the TriplesClient is already scoped to a workspace-specific flow, same as GraphRAG. Passing workspace explicitly was both incorrect and unnecessary. Update tests: - tests/unit/test_query/test_sparql_algebra.py (new) — Tests _query_pattern, _eval_bgp, and evaluate() with various algebra nodes. Key tests assert workspace is never in tc.query() kwargs, plus correctness tests for BGP, JOIN, UNION, SLICE, DISTINCT, and edge cases. - tests/unit/test_retrieval/test_graph_rag.py — Added test_triples_query_never_passes_workspace (checks query()) and test_follow_edges_never_passes_workspace (checks query_stream()). * Make all Cassandra and Qdrant I/O async-safe with proper concurrency controls (#916) Cassandra triples services were using syncronous EntityCentricKnowledgeGraph methods from async contexts, and connection state was managed with threading.local which is wrong for asyncio coroutines sharing a single thread. Qdrant services had no async wrapping at all, blocking the event loop on every network call. Rows services had unprotected shared state mutations across concurrent coroutines. - Add async methods to EntityCentricKnowledgeGraph (async_insert, async_get_s/p/o/sp/po/os/spo/all, async_collection_exists, async_create_collection, async_delete_collection) using the existing cassandra_async.async_execute bridge - Rewrite triples write + query services: replace threading.local with asyncio.Lock + dict cache for per-workspace connections, use async ECKG methods for all data operations, keep asyncio.to_thread only for one-time blocking ECKG construction - Wrap all Qdrant calls in asyncio.to_thread across all 6 services (doc/graph/row embeddings write + query), add asyncio.Lock + set cache for collection existence checks - Add asyncio.Lock to rows write + query services to protect shared state (schemas, sessions, config caches) from concurrent mutation - Update all affected tests to match new async patterns * Fixed error only returning a page of results (#921) The root cause: async_execute only materialises the first result page (by design — it says so in its docstring). The streaming query set fetch_size=20 and expected to iterate all results, but only got the first 20 rows back. The fix uses asyncio.to_thread(lambda: list(tg.session.execute(...))) which lets the sync driver iterate all pages in a worker thread — exactly what the pre-async code did. * Optional test warning suppression (#923) * Fix test collection module errors & silence upstream Pytest warnings (#823) * chore: add virtual environment and .env directories to gitignore * test: filter upstream DeprecationWarning and UserWarning messages * fix(namespace): remove empty __init__.py files to fix PEP 420 implicit namespace routing for trustgraph sub-packages * Revert __init__.py deletions * Add .ini changes but commented out, will be useful at times --------- Co-authored-by: Salil M <d2kyt@protonmail.com>
This commit is contained in:
cybermaggedon
GitHub
parent
159b1e2824
commit
142dd0231c
42 changed files with 1910 additions and 1492 deletions
|
|
@ -89,12 +89,15 @@ class TestRowsGraphQLQueryLogic:
|
|||
@pytest.mark.asyncio
|
||||
async def test_schema_config_parsing(self):
|
||||
"""Test parsing of schema configuration"""
|
||||
import asyncio
|
||||
processor = MagicMock()
|
||||
processor.schemas = {}
|
||||
processor.schema_builders = {}
|
||||
processor.graphql_schemas = {}
|
||||
processor.config_key = "schema"
|
||||
processor.query_cassandra = MagicMock()
|
||||
processor._setup_lock = asyncio.Lock()
|
||||
processor._apply_schema_config = Processor._apply_schema_config.__get__(processor, Processor)
|
||||
processor.on_schema_config = Processor.on_schema_config.__get__(processor, Processor)
|
||||
|
||||
# Create test config
|
||||
|
|
@ -335,7 +338,7 @@ class TestUnifiedTableQueries:
|
|||
"""Test query execution with matching index"""
|
||||
processor = MagicMock()
|
||||
processor.session = MagicMock()
|
||||
processor.connect_cassandra = MagicMock()
|
||||
processor.connect_cassandra = AsyncMock()
|
||||
processor.sanitize_name = Processor.sanitize_name.__get__(processor, Processor)
|
||||
processor.get_index_names = Processor.get_index_names.__get__(processor, Processor)
|
||||
processor.find_matching_index = Processor.find_matching_index.__get__(processor, Processor)
|
||||
|
|
@ -396,7 +399,7 @@ class TestUnifiedTableQueries:
|
|||
"""Test query execution without matching index (scan mode)"""
|
||||
processor = MagicMock()
|
||||
processor.session = MagicMock()
|
||||
processor.connect_cassandra = MagicMock()
|
||||
processor.connect_cassandra = AsyncMock()
|
||||
processor.sanitize_name = Processor.sanitize_name.__get__(processor, Processor)
|
||||
processor.get_index_names = Processor.get_index_names.__get__(processor, Processor)
|
||||
processor.find_matching_index = Processor.find_matching_index.__get__(processor, Processor)
|
||||
|
|
|
|||
302
tests/unit/test_query/test_sparql_algebra.py
Normal file
302
tests/unit/test_query/test_sparql_algebra.py
Normal file
|
|
@ -0,0 +1,302 @@
|
|||
"""
|
||||
Tests for the SPARQL algebra evaluator.
|
||||
|
||||
Verifies that evaluate() and _query_pattern() call TriplesClient.query()
|
||||
with the correct arguments, and in particular that workspace is never
|
||||
passed — workspace isolation is handled by pub/sub topic routing.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import AsyncMock, MagicMock, call
|
||||
|
||||
from rdflib.term import Variable, URIRef, Literal
|
||||
from rdflib.plugins.sparql.parserutils import CompValue
|
||||
|
||||
from trustgraph.schema import Term, IRI, LITERAL
|
||||
from trustgraph.query.sparql.algebra import (
|
||||
evaluate, _query_pattern, _eval_bgp,
|
||||
)
|
||||
|
||||
|
||||
# --- Helpers ---
|
||||
|
||||
def iri(v):
|
||||
return Term(type=IRI, iri=v)
|
||||
|
||||
|
||||
def lit(v):
|
||||
return Term(type=LITERAL, value=v)
|
||||
|
||||
|
||||
def make_triple(s, p, o):
|
||||
t = MagicMock()
|
||||
t.s = s
|
||||
t.p = p
|
||||
t.o = o
|
||||
return t
|
||||
|
||||
|
||||
def make_bgp(*patterns):
|
||||
"""Build a CompValue BGP node from (s, p, o) tuples of rdflib terms."""
|
||||
node = CompValue("BGP")
|
||||
node.triples = list(patterns)
|
||||
return node
|
||||
|
||||
|
||||
def make_project(inner, variables):
|
||||
node = CompValue("Project")
|
||||
node.p = inner
|
||||
node.PV = [Variable(v) for v in variables]
|
||||
return node
|
||||
|
||||
|
||||
def make_select(inner):
|
||||
node = CompValue("SelectQuery")
|
||||
node.p = inner
|
||||
return node
|
||||
|
||||
|
||||
def make_join(left, right):
|
||||
node = CompValue("Join")
|
||||
node.p1 = left
|
||||
node.p2 = right
|
||||
return node
|
||||
|
||||
|
||||
def make_union(left, right):
|
||||
node = CompValue("Union")
|
||||
node.p1 = left
|
||||
node.p2 = right
|
||||
return node
|
||||
|
||||
|
||||
def make_slice(inner, start, length):
|
||||
node = CompValue("Slice")
|
||||
node.p = inner
|
||||
node.start = start
|
||||
node.length = length
|
||||
return node
|
||||
|
||||
|
||||
def make_distinct(inner):
|
||||
node = CompValue("Distinct")
|
||||
node.p = inner
|
||||
return node
|
||||
|
||||
|
||||
class TestQueryPattern:
|
||||
"""Tests for _query_pattern — the leaf that calls TriplesClient."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_passes_correct_args(self):
|
||||
tc = AsyncMock()
|
||||
tc.query.return_value = []
|
||||
|
||||
await _query_pattern(
|
||||
tc,
|
||||
s=iri("http://example.com/s"),
|
||||
p=iri("http://example.com/p"),
|
||||
o=None,
|
||||
collection="my-collection",
|
||||
limit=100,
|
||||
)
|
||||
|
||||
tc.query.assert_called_once_with(
|
||||
s=iri("http://example.com/s"),
|
||||
p=iri("http://example.com/p"),
|
||||
o=None,
|
||||
limit=100,
|
||||
collection="my-collection",
|
||||
)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_workspace_not_passed(self):
|
||||
tc = AsyncMock()
|
||||
tc.query.return_value = []
|
||||
|
||||
await _query_pattern(tc, None, None, None, "default", 10)
|
||||
|
||||
kwargs = tc.query.call_args.kwargs
|
||||
assert "workspace" not in kwargs
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_returns_query_results(self):
|
||||
tc = AsyncMock()
|
||||
triple = make_triple(iri("http://a"), iri("http://b"), lit("c"))
|
||||
tc.query.return_value = [triple]
|
||||
|
||||
results = await _query_pattern(tc, None, None, None, "default", 10)
|
||||
|
||||
assert len(results) == 1
|
||||
assert results[0].s.iri == "http://a"
|
||||
|
||||
|
||||
class TestEvalBgp:
|
||||
"""Tests for BGP evaluation — triple pattern queries."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_single_pattern_all_variables(self):
|
||||
tc = AsyncMock()
|
||||
triple = make_triple(iri("http://s"), iri("http://p"), lit("o"))
|
||||
tc.query.return_value = [triple]
|
||||
|
||||
bgp = make_bgp(
|
||||
(Variable("s"), Variable("p"), Variable("o")),
|
||||
)
|
||||
|
||||
solutions = await evaluate(bgp, tc, collection="default", limit=100)
|
||||
|
||||
assert len(solutions) == 1
|
||||
assert solutions[0]["s"].iri == "http://s"
|
||||
assert solutions[0]["p"].iri == "http://p"
|
||||
assert solutions[0]["o"].value == "o"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_single_pattern_bound_subject(self):
|
||||
tc = AsyncMock()
|
||||
tc.query.return_value = [
|
||||
make_triple(iri("http://s"), iri("http://p"), lit("val")),
|
||||
]
|
||||
|
||||
bgp = make_bgp(
|
||||
(URIRef("http://s"), Variable("p"), Variable("o")),
|
||||
)
|
||||
|
||||
solutions = await evaluate(bgp, tc, collection="default")
|
||||
|
||||
tc.query.assert_called_once()
|
||||
kwargs = tc.query.call_args.kwargs
|
||||
assert "workspace" not in kwargs
|
||||
assert kwargs["collection"] == "default"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_empty_bgp_returns_empty_solution(self):
|
||||
tc = AsyncMock()
|
||||
|
||||
bgp = make_bgp()
|
||||
|
||||
solutions = await evaluate(bgp, tc, collection="default")
|
||||
|
||||
assert solutions == [{}]
|
||||
tc.query.assert_not_called()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_no_results_returns_empty(self):
|
||||
tc = AsyncMock()
|
||||
tc.query.return_value = []
|
||||
|
||||
bgp = make_bgp(
|
||||
(Variable("s"), Variable("p"), Variable("o")),
|
||||
)
|
||||
|
||||
solutions = await evaluate(bgp, tc, collection="default")
|
||||
|
||||
assert solutions == []
|
||||
|
||||
|
||||
class TestEvaluate:
|
||||
"""Tests for the top-level evaluate() dispatcher."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_select_query_node(self):
|
||||
tc = AsyncMock()
|
||||
tc.query.return_value = [
|
||||
make_triple(iri("http://s"), iri("http://p"), lit("o")),
|
||||
]
|
||||
|
||||
bgp = make_bgp(
|
||||
(Variable("s"), Variable("p"), Variable("o")),
|
||||
)
|
||||
select = make_select(make_project(bgp, ["s", "p"]))
|
||||
|
||||
solutions = await evaluate(select, tc, collection="default")
|
||||
|
||||
assert len(solutions) == 1
|
||||
assert "s" in solutions[0]
|
||||
assert "p" in solutions[0]
|
||||
assert "o" not in solutions[0]
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_workspace_never_in_query_calls(self):
|
||||
"""Verify that no matter the algebra structure, workspace is never
|
||||
passed to TriplesClient.query()."""
|
||||
tc = AsyncMock()
|
||||
tc.query.return_value = [
|
||||
make_triple(iri("http://s"), iri("http://p"), lit("o")),
|
||||
]
|
||||
|
||||
bgp1 = make_bgp((Variable("s"), Variable("p"), Variable("o")))
|
||||
bgp2 = make_bgp((Variable("a"), Variable("b"), Variable("c")))
|
||||
tree = make_select(make_project(
|
||||
make_union(bgp1, bgp2), ["s", "p", "o"]
|
||||
))
|
||||
|
||||
await evaluate(tree, tc, collection="test-coll")
|
||||
|
||||
for c in tc.query.call_args_list:
|
||||
assert "workspace" not in c.kwargs
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_join(self):
|
||||
tc = AsyncMock()
|
||||
tc.query.side_effect = [
|
||||
[make_triple(iri("http://a"), iri("http://p"), lit("v"))],
|
||||
[make_triple(iri("http://a"), iri("http://q"), lit("w"))],
|
||||
]
|
||||
|
||||
bgp1 = make_bgp((Variable("s"), URIRef("http://p"), Variable("v1")))
|
||||
bgp2 = make_bgp((Variable("s"), URIRef("http://q"), Variable("v2")))
|
||||
tree = make_join(bgp1, bgp2)
|
||||
|
||||
solutions = await evaluate(tree, tc, collection="default")
|
||||
|
||||
assert len(solutions) == 1
|
||||
assert solutions[0]["s"].iri == "http://a"
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_slice(self):
|
||||
tc = AsyncMock()
|
||||
triples = [
|
||||
make_triple(iri(f"http://s{i}"), iri("http://p"), lit(f"o{i}"))
|
||||
for i in range(5)
|
||||
]
|
||||
tc.query.return_value = triples
|
||||
|
||||
bgp = make_bgp((Variable("s"), Variable("p"), Variable("o")))
|
||||
tree = make_slice(bgp, start=1, length=2)
|
||||
|
||||
solutions = await evaluate(tree, tc, collection="default")
|
||||
|
||||
assert len(solutions) == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_distinct(self):
|
||||
tc = AsyncMock()
|
||||
triple = make_triple(iri("http://s"), iri("http://p"), lit("o"))
|
||||
tc.query.return_value = [triple, triple]
|
||||
|
||||
bgp = make_bgp((Variable("s"), Variable("p"), Variable("o")))
|
||||
tree = make_distinct(bgp)
|
||||
|
||||
solutions = await evaluate(tree, tc, collection="default")
|
||||
|
||||
assert len(solutions) == 1
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_unsupported_node_returns_empty_solution(self):
|
||||
tc = AsyncMock()
|
||||
|
||||
node = CompValue("SomethingUnknown")
|
||||
|
||||
solutions = await evaluate(node, tc, collection="default")
|
||||
|
||||
assert solutions == [{}]
|
||||
tc.query.assert_not_called()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_non_compvalue_returns_empty_solution(self):
|
||||
tc = AsyncMock()
|
||||
|
||||
solutions = await evaluate("not a node", tc, collection="default")
|
||||
|
||||
assert solutions == [{}]
|
||||
|
|
@ -2,8 +2,10 @@
|
|||
Tests for Cassandra triples query service
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, patch
|
||||
from unittest.mock import MagicMock, patch, AsyncMock
|
||||
|
||||
from trustgraph.query.triples.cassandra.service import Processor, create_term
|
||||
from trustgraph.schema import Term, IRI, LITERAL
|
||||
|
|
@ -18,7 +20,7 @@ class TestCassandraQueryProcessor:
|
|||
return Processor(
|
||||
taskgroup=MagicMock(),
|
||||
id='test-cassandra-query',
|
||||
graph_host='localhost'
|
||||
cassandra_host='localhost'
|
||||
)
|
||||
|
||||
def test_create_term_with_http_uri(self, processor):
|
||||
|
|
@ -85,7 +87,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_result.o = 'test_object'
|
||||
mock_tg_instance.get_spo.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_spo = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(
|
||||
taskgroup=MagicMock(),
|
||||
|
|
@ -110,8 +112,8 @@ class TestCassandraQueryProcessor:
|
|||
keyspace='test_user'
|
||||
)
|
||||
|
||||
# Verify get_spo was called with correct parameters
|
||||
mock_tg_instance.get_spo.assert_called_once_with(
|
||||
# Verify async_get_spo was called with correct parameters
|
||||
mock_tg_instance.async_get_spo.assert_called_once_with(
|
||||
'test_collection', 'test_subject', 'test_predicate', 'test_object', g=None, limit=100
|
||||
)
|
||||
|
||||
|
|
@ -130,23 +132,25 @@ class TestCassandraQueryProcessor:
|
|||
assert processor.cassandra_host == ['cassandra'] # Updated default
|
||||
assert processor.cassandra_username is None
|
||||
assert processor.cassandra_password is None
|
||||
assert processor.table is None
|
||||
assert processor._connections == {}
|
||||
assert isinstance(processor._conn_lock, asyncio.Lock)
|
||||
|
||||
def test_processor_initialization_with_custom_params(self):
|
||||
"""Test processor initialization with custom parameters"""
|
||||
taskgroup_mock = MagicMock()
|
||||
|
||||
|
||||
processor = Processor(
|
||||
taskgroup=taskgroup_mock,
|
||||
cassandra_host='cassandra.example.com',
|
||||
cassandra_username='queryuser',
|
||||
cassandra_password='querypass'
|
||||
)
|
||||
|
||||
|
||||
assert processor.cassandra_host == ['cassandra.example.com']
|
||||
assert processor.cassandra_username == 'queryuser'
|
||||
assert processor.cassandra_password == 'querypass'
|
||||
assert processor.table is None
|
||||
assert processor._connections == {}
|
||||
assert isinstance(processor._conn_lock, asyncio.Lock)
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch('trustgraph.query.triples.cassandra.service.EntityCentricKnowledgeGraph')
|
||||
|
|
@ -164,7 +168,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.otype = None
|
||||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_tg_instance.get_sp.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_sp = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -178,7 +182,7 @@ class TestCassandraQueryProcessor:
|
|||
|
||||
result = await processor.query_triples('test_user', query)
|
||||
|
||||
mock_tg_instance.get_sp.assert_called_once_with('test_collection', 'test_subject', 'test_predicate', g=None, limit=50)
|
||||
mock_tg_instance.async_get_sp.assert_called_once_with('test_collection', 'test_subject', 'test_predicate', g=None, limit=50)
|
||||
assert len(result) == 1
|
||||
assert result[0].s.iri == 'test_subject'
|
||||
assert result[0].p.iri == 'test_predicate'
|
||||
|
|
@ -200,7 +204,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.otype = None
|
||||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_tg_instance.get_s.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_s = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -214,7 +218,7 @@ class TestCassandraQueryProcessor:
|
|||
|
||||
result = await processor.query_triples('test_user', query)
|
||||
|
||||
mock_tg_instance.get_s.assert_called_once_with('test_collection', 'test_subject', g=None, limit=25)
|
||||
mock_tg_instance.async_get_s.assert_called_once_with('test_collection', 'test_subject', g=None, limit=25)
|
||||
assert len(result) == 1
|
||||
assert result[0].s.iri == 'test_subject'
|
||||
assert result[0].p.iri == 'result_predicate'
|
||||
|
|
@ -236,7 +240,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.otype = None
|
||||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_tg_instance.get_p.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_p = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -250,7 +254,7 @@ class TestCassandraQueryProcessor:
|
|||
|
||||
result = await processor.query_triples('test_user', query)
|
||||
|
||||
mock_tg_instance.get_p.assert_called_once_with('test_collection', 'test_predicate', g=None, limit=10)
|
||||
mock_tg_instance.async_get_p.assert_called_once_with('test_collection', 'test_predicate', g=None, limit=10)
|
||||
assert len(result) == 1
|
||||
assert result[0].s.iri == 'result_subject'
|
||||
assert result[0].p.iri == 'test_predicate'
|
||||
|
|
@ -272,7 +276,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.otype = None
|
||||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_tg_instance.get_o.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_o = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -286,7 +290,7 @@ class TestCassandraQueryProcessor:
|
|||
|
||||
result = await processor.query_triples('test_user', query)
|
||||
|
||||
mock_tg_instance.get_o.assert_called_once_with('test_collection', 'test_object', g=None, limit=75)
|
||||
mock_tg_instance.async_get_o.assert_called_once_with('test_collection', 'test_object', g=None, limit=75)
|
||||
assert len(result) == 1
|
||||
assert result[0].s.iri == 'result_subject'
|
||||
assert result[0].p.iri == 'result_predicate'
|
||||
|
|
@ -305,11 +309,11 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.s = 'all_subject'
|
||||
mock_result.p = 'all_predicate'
|
||||
mock_result.o = 'all_object'
|
||||
mock_result.g = ''
|
||||
mock_result.d = ''
|
||||
mock_result.otype = None
|
||||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_tg_instance.get_all.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_all = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -323,7 +327,7 @@ class TestCassandraQueryProcessor:
|
|||
|
||||
result = await processor.query_triples('test_user', query)
|
||||
|
||||
mock_tg_instance.get_all.assert_called_once_with('test_collection', limit=1000)
|
||||
mock_tg_instance.async_get_all.assert_called_once_with('test_collection', limit=1000)
|
||||
assert len(result) == 1
|
||||
assert result[0].s.iri == 'all_subject'
|
||||
assert result[0].p.iri == 'all_predicate'
|
||||
|
|
@ -410,7 +414,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_result.o = 'test_object'
|
||||
mock_tg_instance.get_spo.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_spo = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(
|
||||
taskgroup=MagicMock(),
|
||||
|
|
@ -451,7 +455,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_result.o = 'test_object'
|
||||
mock_tg_instance.get_spo.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_spo = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -489,8 +493,8 @@ class TestCassandraQueryProcessor:
|
|||
mock_result.lang = None
|
||||
mock_result.p = 'p'
|
||||
mock_result.o = 'o'
|
||||
mock_tg_instance1.get_s.return_value = [mock_result]
|
||||
mock_tg_instance2.get_s.return_value = [mock_result]
|
||||
mock_tg_instance1.async_get_s = AsyncMock(return_value=[mock_result])
|
||||
mock_tg_instance2.async_get_s = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -504,7 +508,6 @@ class TestCassandraQueryProcessor:
|
|||
)
|
||||
|
||||
await processor.query_triples('user1', query1)
|
||||
assert processor.table == 'user1'
|
||||
|
||||
# Second query with different table
|
||||
query2 = TriplesQueryRequest(
|
||||
|
|
@ -516,10 +519,11 @@ class TestCassandraQueryProcessor:
|
|||
)
|
||||
|
||||
await processor.query_triples('user2', query2)
|
||||
assert processor.table == 'user2'
|
||||
|
||||
# Verify TrustGraph was created twice
|
||||
# Verify TrustGraph was created twice for different workspaces
|
||||
assert mock_kg_class.call_count == 2
|
||||
mock_kg_class.assert_any_call(hosts=['cassandra'], keyspace='user1')
|
||||
mock_kg_class.assert_any_call(hosts=['cassandra'], keyspace='user2')
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch('trustgraph.query.triples.cassandra.service.EntityCentricKnowledgeGraph')
|
||||
|
|
@ -529,7 +533,7 @@ class TestCassandraQueryProcessor:
|
|||
|
||||
mock_tg_instance = MagicMock()
|
||||
mock_kg_class.return_value = mock_tg_instance
|
||||
mock_tg_instance.get_spo.side_effect = Exception("Query failed")
|
||||
mock_tg_instance.async_get_spo = AsyncMock(side_effect=Exception("Query failed"))
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -566,7 +570,7 @@ class TestCassandraQueryProcessor:
|
|||
mock_result2.otype = None
|
||||
mock_result2.dtype = None
|
||||
mock_result2.lang = None
|
||||
mock_tg_instance.get_sp.return_value = [mock_result1, mock_result2]
|
||||
mock_tg_instance.async_get_sp = AsyncMock(return_value=[mock_result1, mock_result2])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -603,7 +607,7 @@ class TestCassandraQueryPerformanceOptimizations:
|
|||
mock_result.otype = None
|
||||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_tg_instance.get_po.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_po = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -618,8 +622,8 @@ class TestCassandraQueryPerformanceOptimizations:
|
|||
|
||||
result = await processor.query_triples('test_user', query)
|
||||
|
||||
# Verify get_po was called (should use optimized po_table)
|
||||
mock_tg_instance.get_po.assert_called_once_with(
|
||||
# Verify async_get_po was called (should use optimized po_table)
|
||||
mock_tg_instance.async_get_po.assert_called_once_with(
|
||||
'test_collection', 'test_predicate', 'test_object', g=None, limit=50
|
||||
)
|
||||
|
||||
|
|
@ -643,7 +647,7 @@ class TestCassandraQueryPerformanceOptimizations:
|
|||
mock_result.otype = None
|
||||
mock_result.dtype = None
|
||||
mock_result.lang = None
|
||||
mock_tg_instance.get_os.return_value = [mock_result]
|
||||
mock_tg_instance.async_get_os = AsyncMock(return_value=[mock_result])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -658,8 +662,8 @@ class TestCassandraQueryPerformanceOptimizations:
|
|||
|
||||
result = await processor.query_triples('test_user', query)
|
||||
|
||||
# Verify get_os was called (should use optimized subject_table with clustering)
|
||||
mock_tg_instance.get_os.assert_called_once_with(
|
||||
# Verify async_get_os was called (should use optimized subject_table with clustering)
|
||||
mock_tg_instance.async_get_os.assert_called_once_with(
|
||||
'test_collection', 'test_object', 'test_subject', g=None, limit=25
|
||||
)
|
||||
|
||||
|
|
@ -678,28 +682,28 @@ class TestCassandraQueryPerformanceOptimizations:
|
|||
mock_kg_class.return_value = mock_tg_instance
|
||||
|
||||
# Mock empty results for all queries
|
||||
mock_tg_instance.get_all.return_value = []
|
||||
mock_tg_instance.get_s.return_value = []
|
||||
mock_tg_instance.get_p.return_value = []
|
||||
mock_tg_instance.get_o.return_value = []
|
||||
mock_tg_instance.get_sp.return_value = []
|
||||
mock_tg_instance.get_po.return_value = []
|
||||
mock_tg_instance.get_os.return_value = []
|
||||
mock_tg_instance.get_spo.return_value = []
|
||||
mock_tg_instance.async_get_all = AsyncMock(return_value=[])
|
||||
mock_tg_instance.async_get_s = AsyncMock(return_value=[])
|
||||
mock_tg_instance.async_get_p = AsyncMock(return_value=[])
|
||||
mock_tg_instance.async_get_o = AsyncMock(return_value=[])
|
||||
mock_tg_instance.async_get_sp = AsyncMock(return_value=[])
|
||||
mock_tg_instance.async_get_po = AsyncMock(return_value=[])
|
||||
mock_tg_instance.async_get_os = AsyncMock(return_value=[])
|
||||
mock_tg_instance.async_get_spo = AsyncMock(return_value=[])
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
# Test each query pattern
|
||||
test_patterns = [
|
||||
# (s, p, o, expected_method)
|
||||
(None, None, None, 'get_all'), # All triples
|
||||
('s1', None, None, 'get_s'), # Subject only
|
||||
(None, 'p1', None, 'get_p'), # Predicate only
|
||||
(None, None, 'o1', 'get_o'), # Object only
|
||||
('s1', 'p1', None, 'get_sp'), # Subject + Predicate
|
||||
(None, 'p1', 'o1', 'get_po'), # Predicate + Object (CRITICAL OPTIMIZATION)
|
||||
('s1', None, 'o1', 'get_os'), # Object + Subject
|
||||
('s1', 'p1', 'o1', 'get_spo'), # All three
|
||||
(None, None, None, 'async_get_all'), # All triples
|
||||
('s1', None, None, 'async_get_s'), # Subject only
|
||||
(None, 'p1', None, 'async_get_p'), # Predicate only
|
||||
(None, None, 'o1', 'async_get_o'), # Object only
|
||||
('s1', 'p1', None, 'async_get_sp'), # Subject + Predicate
|
||||
(None, 'p1', 'o1', 'async_get_po'), # Predicate + Object (CRITICAL OPTIMIZATION)
|
||||
('s1', None, 'o1', 'async_get_os'), # Object + Subject
|
||||
('s1', 'p1', 'o1', 'async_get_spo'), # All three
|
||||
]
|
||||
|
||||
for s, p, o, expected_method in test_patterns:
|
||||
|
|
@ -759,7 +763,7 @@ class TestCassandraQueryPerformanceOptimizations:
|
|||
mock_result.lang = None
|
||||
mock_results.append(mock_result)
|
||||
|
||||
mock_tg_instance.get_po.return_value = mock_results
|
||||
mock_tg_instance.async_get_po = AsyncMock(return_value=mock_results)
|
||||
|
||||
processor = Processor(taskgroup=MagicMock())
|
||||
|
||||
|
|
@ -774,8 +778,8 @@ class TestCassandraQueryPerformanceOptimizations:
|
|||
|
||||
result = await processor.query_triples('large_dataset_user', query)
|
||||
|
||||
# Verify optimized get_po was used (no ALLOW FILTERING needed!)
|
||||
mock_tg_instance.get_po.assert_called_once_with(
|
||||
# Verify optimized async_get_po was used (no ALLOW FILTERING needed!)
|
||||
mock_tg_instance.async_get_po.assert_called_once_with(
|
||||
'massive_collection',
|
||||
'http://www.w3.org/1999/02/22-rdf-syntax-ns#type',
|
||||
'http://example.com/Person',
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue