Merge pull request #1192 from Freakz2z/fix/rdf4j-repository-id

fix(triplet_store): honor RDF4J repository id
This commit is contained in:
Mohd Kaif
2026-08-24 12:21:50 +05:30
committed by GitHub
4 changed files with 75 additions and 9 deletions
+1 -1
View File
@@ -182,7 +182,7 @@ for row in result.bindings:
store = TripletStore(
backend="rdf4j",
endpoint="http://localhost:8080/rdf4j-server",
repository_id="semantica", # passed through **config
repository_id="semantica", # selects the remote repository
)
```
+2 -2
View File
@@ -35,7 +35,7 @@ This page is intentionally conservative: it distinguishes between an adapter exi
| FalkorDB | LPG | Yes | Yes | Partial | Partial | Redis-based; provenance depends on node/edge properties, and multi-graph isolation depends on the selected graph name. |
| Amazon Neptune | LPG | Yes | Yes | Partial | Partial | Use the property-graph endpoint; AWS auth, VPC, and endpoint configuration can affect local tests. Provenance depends on node/edge properties. |
| Apache AGE | LPG | Yes | Yes | Partial | Partial | Runs through PostgreSQL/AGE; Cypher compatibility and property handling can differ from standalone LPG engines. |
| RDF4J | RDF | Yes | Partial | Partial | Partial | Context separation relies on named graphs; triple-level provenance may require reification or graph-level metadata. `RDF4JStore(repository_id=...)` currently has no effect — the constructor always connects to the `"default"` repository regardless of the value passed; track a fix separately. |
| RDF4J | RDF | Yes | Partial | Partial | Partial | Context separation relies on named graphs; triple-level provenance may require reification or graph-level metadata. |
| Apache Jena | RDF | Yes | Partial | Partial | Partial | Named graphs are needed for context separation; backend configuration and transaction behavior matter. |
| Blazegraph | RDF | Yes | Partial | Partial | Partial | Use quads/named graphs for context; IRI stability and graph naming matter for provenance. |
| Anzo | RDF | Yes | Partial | Partial | Partial | Anzo deployments are environment-specific; validate `dataset_uri`/graphmart naming, named-graph support, and provenance mapping. |
@@ -107,7 +107,7 @@ from semantica.triplet_store import RDF4JStore
store = RDF4JStore(
endpoint='http://localhost:8080/rdf4j-server',
repository_id='semantica' # currently has no effect; connects to "default" (see Known limitations)
repository_id='semantica'
)
```
+7 -6
View File
@@ -28,7 +28,7 @@ License: MIT
import re
from typing import Any, Dict, List, Optional
from urllib.parse import urlparse
from urllib.parse import quote, urlparse
import requests
from rdflib import Graph, Literal
@@ -67,7 +67,8 @@ class RDF4JStore:
self.progress_tracker.enabled = True
self.endpoint = endpoint.rstrip("/")
self.repository_id = config.get("repository_id", "default")
self.repository_id = repository_id or config.get("repository_id", "default")
self._encoded_repository_id = quote(self.repository_id, safe="")
self.username = config.get("username")
self.password = config.get("password")
self.timeout = config.get("timeout", 30)
@@ -79,7 +80,7 @@ class RDF4JStore:
"""Connect to RDF4J server."""
try:
# Test connection
test_url = f"{self.endpoint}/repositories/{self.repository_id}"
test_url = f"{self.endpoint}/repositories/{self._encoded_repository_id}"
response = requests.get(
test_url,
timeout=self.timeout,
@@ -100,11 +101,11 @@ class RDF4JStore:
def _get_sparql_endpoint(self) -> str:
"""Get SPARQL query endpoint."""
return f"{self.endpoint}/repositories/{self.repository_id}"
return f"{self.endpoint}/repositories/{self._encoded_repository_id}"
def _get_update_endpoint(self) -> str:
"""Get SPARQL Update endpoint."""
return f"{self.endpoint}/repositories/{self.repository_id}/statements"
return f"{self.endpoint}/repositories/{self._encoded_repository_id}/statements"
def _is_construct_query(self, query: str) -> bool:
"""
@@ -163,7 +164,7 @@ class RDF4JStore:
"""
# RDF4J transaction support
transaction_url = (
f"{self.endpoint}/repositories/{self.repository_id}/transactions"
f"{self.endpoint}/repositories/{self._encoded_repository_id}/transactions"
)
try:
+65
View File
@@ -22,6 +22,71 @@ def _make_connected_store():
CONSTRUCT_QUERY = "CONSTRUCT { ?s ?p ?o } WHERE { ?s ?p ?o }"
class TestRDF4JStoreInitialization(unittest.TestCase):
def test_explicit_repository_id_selects_repository(self):
response = MagicMock(status_code=200)
with patch(
"semantica.triplet_store.rdf4j_store.requests.get",
return_value=response,
) as mock_get:
store = RDF4JStore(
endpoint="http://localhost:8080/rdf4j-server/",
repository_id="semantica",
)
self.assertEqual(store.repository_id, "semantica")
mock_get.assert_called_once_with(
"http://localhost:8080/rdf4j-server/repositories/semantica",
timeout=30,
auth=None,
)
def test_repository_id_is_encoded_as_a_single_url_path_segment(self):
response = MagicMock(status_code=200)
with patch(
"semantica.triplet_store.rdf4j_store.requests.get",
return_value=response,
) as mock_get:
store = RDF4JStore(
endpoint="http://localhost:8080/rdf4j-server",
repository_id="team/repo ?#",
)
self.assertEqual(store.repository_id, "team/repo ?#")
mock_get.assert_called_once_with(
"http://localhost:8080/rdf4j-server/repositories/team%2Frepo%20%3F%23",
timeout=30,
auth=None,
)
self.assertEqual(
store._get_sparql_endpoint(),
"http://localhost:8080/rdf4j-server/repositories/team%2Frepo%20%3F%23",
)
self.assertEqual(
store._get_update_endpoint(),
"http://localhost:8080/rdf4j-server/repositories/"
"team%2Frepo%20%3F%23/statements",
)
transaction_response = MagicMock()
transaction_response.headers = {"Location": "/transactions/tx-1"}
with patch(
"semantica.triplet_store.rdf4j_store.requests.post",
return_value=transaction_response,
) as mock_post:
self.assertEqual(store.begin_transaction(), "tx-1")
mock_post.assert_called_once_with(
"http://localhost:8080/rdf4j-server/repositories/"
"team%2Frepo%20%3F%23/transactions",
timeout=30,
auth=None,
)
class TestRDF4JStoreIsConstructQuery(unittest.TestCase):
def test_detects_uppercase(self):
self.assertTrue(_make_connected_store()._is_construct_query(