From e41993a6bd7b10389991dd222ff260e969033d13 Mon Sep 17 00:00:00 2001 From: Freakz2z Date: Sun, 23 Aug 2026 23:02:15 +0800 Subject: [PATCH 1/2] fix(triplet_store): honor RDF4J repository id --- docs/storage-backends.md | 4 ++-- semantica/triplet_store/rdf4j_store.py | 2 +- tests/triplet_store/test_rdf4j_store.py | 21 +++++++++++++++++++++ 3 files changed, 24 insertions(+), 3 deletions(-) diff --git a/docs/storage-backends.md b/docs/storage-backends.md index bb05e115..dc211ef0 100644 --- a/docs/storage-backends.md +++ b/docs/storage-backends.md @@ -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' ) ``` diff --git a/semantica/triplet_store/rdf4j_store.py b/semantica/triplet_store/rdf4j_store.py index 8dad6997..c03b64a8 100644 --- a/semantica/triplet_store/rdf4j_store.py +++ b/semantica/triplet_store/rdf4j_store.py @@ -67,7 +67,7 @@ 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.username = config.get("username") self.password = config.get("password") self.timeout = config.get("timeout", 30) diff --git a/tests/triplet_store/test_rdf4j_store.py b/tests/triplet_store/test_rdf4j_store.py index 4ef4f16b..3f630b93 100644 --- a/tests/triplet_store/test_rdf4j_store.py +++ b/tests/triplet_store/test_rdf4j_store.py @@ -22,6 +22,27 @@ 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, + ) + + class TestRDF4JStoreIsConstructQuery(unittest.TestCase): def test_detects_uppercase(self): self.assertTrue(_make_connected_store()._is_construct_query( From 4c997b501799f2c71e7040187a5c87e972e1fd4e Mon Sep 17 00:00:00 2001 From: Freakz2z Date: Mon, 24 Aug 2026 09:01:22 +0800 Subject: [PATCH 2/2] fix(triplet_store): encode RDF4J repository paths --- docs/reference/triplet_store.md | 2 +- semantica/triplet_store/rdf4j_store.py | 11 ++++--- tests/triplet_store/test_rdf4j_store.py | 44 +++++++++++++++++++++++++ 3 files changed, 51 insertions(+), 6 deletions(-) diff --git a/docs/reference/triplet_store.md b/docs/reference/triplet_store.md index ad7a0645..ee5c24e6 100644 --- a/docs/reference/triplet_store.md +++ b/docs/reference/triplet_store.md @@ -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 ) ``` diff --git a/semantica/triplet_store/rdf4j_store.py b/semantica/triplet_store/rdf4j_store.py index c03b64a8..d788ab7b 100644 --- a/semantica/triplet_store/rdf4j_store.py +++ b/semantica/triplet_store/rdf4j_store.py @@ -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 @@ -68,6 +68,7 @@ class RDF4JStore: self.endpoint = endpoint.rstrip("/") 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: diff --git a/tests/triplet_store/test_rdf4j_store.py b/tests/triplet_store/test_rdf4j_store.py index 3f630b93..03a9b90b 100644 --- a/tests/triplet_store/test_rdf4j_store.py +++ b/tests/triplet_store/test_rdf4j_store.py @@ -23,6 +23,7 @@ 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) @@ -42,6 +43,49 @@ class TestRDF4JStoreInitialization(unittest.TestCase): 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):