feat: extend SPARQL evaluator with comprehensive function and operator support (#945)

Add 30+ SPARQL 1.1 built-in functions and the MINUS algebra operator to the
custom SPARQL query backend.

String functions:
- SUBSTR (2-arg and 3-arg forms), STRBEFORE, STRAFTER
- REPLACE (regex with flags), ENCODE_FOR_URI

Numeric functions:
- FLOOR, CEIL, ROUND, ABS

Date/time accessors:
- YEAR, MONTH, DAY, HOURS, MINUTES, SECONDS
- NOW, TZ

Hash functions:
- MD5, SHA1, SHA256, SHA512

Term constructors:
- IRI/URI, BNODE, UUID, STRUUID

Other functions:
- LANGMATCHES, RAND
- EXISTS / NOT EXISTS (with async pre-evaluation to bridge the
  sync expression evaluator and async algebra evaluator)

Algebra:
- MINUS set-difference operator
- HAVING already works via rdflib's Filter mapping (verified)

Fix SPARQL ORDER handling

Includes 653 lines of new unit tests covering all added functionality
across expressions, solutions, and algebra layers.
This commit is contained in:
cybermaggedon 2026-05-21 10:50:11 +01:00 committed by GitHub
parent e57f4669e1
commit 2c3a699af3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 1021 additions and 29 deletions

View file

@ -84,6 +84,20 @@ def make_distinct(inner):
return node
def make_filter(inner, expr):
node = CompValue("Filter")
node.p = inner
node.expr = expr
return node
def make_minus(left, right):
node = CompValue("Minus")
node.p1 = left
node.p2 = right
return node
class TestQueryPattern:
"""Tests for _query_pattern — the leaf that calls TriplesClient."""
@ -282,6 +296,177 @@ class TestEvaluate:
assert len(solutions) == 1
@pytest.mark.asyncio
async def test_minus_removes_matching(self):
tc = AsyncMock()
alice = iri("http://example.com/alice")
bob = iri("http://example.com/bob")
knows = iri("http://example.com/knows")
hates = iri("http://example.com/hates")
charlie = iri("http://example.com/charlie")
left_triple = make_triple(alice, knows, bob)
right_triple1 = make_triple(alice, knows, bob)
right_triple2 = make_triple(alice, hates, charlie)
left_bgp = make_bgp(
(Variable("s"), URIRef("http://example.com/knows"), Variable("o"))
)
right_bgp = make_bgp(
(Variable("s"), URIRef("http://example.com/hates"), Variable("r"))
)
async def mock_query(**kwargs):
pred = kwargs.get("p")
if pred and pred.iri == "http://example.com/knows":
return [left_triple]
elif pred and pred.iri == "http://example.com/hates":
return [right_triple2]
return []
tc.query.side_effect = mock_query
tree = make_select(
make_project(
make_minus(left_bgp, right_bgp),
["s", "o"]
)
)
solutions = await evaluate(tree, tc, collection="default")
# alice knows bob, but alice also hates charlie
# shared var is "s" (alice), so alice's solution is removed
assert len(solutions) == 0
@pytest.mark.asyncio
async def test_minus_no_shared_vars_preserves_all(self):
tc = AsyncMock()
alice = iri("http://example.com/alice")
bob = iri("http://example.com/bob")
left_triple = make_triple(alice, iri("http://example.com/p"), bob)
left_bgp = make_bgp(
(Variable("s"), URIRef("http://example.com/p"), Variable("o"))
)
right_bgp = make_bgp(
(Variable("x"), URIRef("http://example.com/q"), Variable("y"))
)
async def mock_query(**kwargs):
pred = kwargs.get("p")
if pred and pred.iri == "http://example.com/p":
return [left_triple]
return []
tc.query.side_effect = mock_query
tree = make_select(
make_project(
make_minus(left_bgp, right_bgp),
["s", "o"]
)
)
solutions = await evaluate(tree, tc, collection="default")
assert len(solutions) == 1
@pytest.mark.asyncio
async def test_filter_exists_keeps_matching(self):
tc = AsyncMock()
alice = iri("http://example.com/alice")
bob = iri("http://example.com/bob")
charlie = iri("http://example.com/charlie")
left_triple1 = make_triple(alice, iri("http://example.com/knows"), bob)
left_triple2 = make_triple(alice, iri("http://example.com/knows"), charlie)
exists_triple = make_triple(bob, iri("http://example.com/likes"), alice)
left_bgp = make_bgp(
(Variable("s"), URIRef("http://example.com/knows"), Variable("o"))
)
exists_bgp = make_bgp(
(Variable("o"), URIRef("http://example.com/likes"), Variable("_any"))
)
async def mock_query(**kwargs):
pred = kwargs.get("p")
if pred and pred.iri == "http://example.com/knows":
return [left_triple1, left_triple2]
elif pred and pred.iri == "http://example.com/likes":
return [exists_triple]
return []
tc.query.side_effect = mock_query
exists_expr = CompValue("Builtin_EXISTS")
exists_expr.graph = exists_bgp
tree = make_select(
make_project(
make_filter(left_bgp, exists_expr),
["s", "o"]
)
)
solutions = await evaluate(tree, tc, collection="default")
# Only bob has a "likes" triple, so only the bob solution passes
result_objects = [s["o"].iri for s in solutions]
assert "http://example.com/bob" in result_objects
assert "http://example.com/charlie" not in result_objects
@pytest.mark.asyncio
async def test_filter_not_exists_removes_matching(self):
tc = AsyncMock()
alice = iri("http://example.com/alice")
bob = iri("http://example.com/bob")
charlie = iri("http://example.com/charlie")
left_triple1 = make_triple(alice, iri("http://example.com/knows"), bob)
left_triple2 = make_triple(alice, iri("http://example.com/knows"), charlie)
exists_triple = make_triple(bob, iri("http://example.com/likes"), alice)
left_bgp = make_bgp(
(Variable("s"), URIRef("http://example.com/knows"), Variable("o"))
)
exists_bgp = make_bgp(
(Variable("o"), URIRef("http://example.com/likes"), Variable("_any"))
)
async def mock_query(**kwargs):
pred = kwargs.get("p")
if pred and pred.iri == "http://example.com/knows":
return [left_triple1, left_triple2]
elif pred and pred.iri == "http://example.com/likes":
return [exists_triple]
return []
tc.query.side_effect = mock_query
not_exists_expr = CompValue("Builtin_NOTEXISTS")
not_exists_expr.graph = exists_bgp
tree = make_select(
make_project(
make_filter(left_bgp, not_exists_expr),
["s", "o"]
)
)
solutions = await evaluate(tree, tc, collection="default")
# bob has a "likes" triple so is removed; charlie stays
result_objects = [s["o"].iri for s in solutions]
assert "http://example.com/charlie" in result_objects
assert "http://example.com/bob" not in result_objects
@pytest.mark.asyncio
async def test_unsupported_node_returns_empty_solution(self):
tc = AsyncMock()