def test_function_filter_iterator():
expression = '?p = <http://purl.org/goodrelations/price> && isLiteral(?o) && !isNumeric(?o)'
iterator, card = hdtDoc.search_triples(triple['subject'], triple['predicate'], triple['object'])
scan = ProjectionIterator(ScanIterator(iterator, triple, card))
iterator = FilterIterator(scan, expression)
(results, saved, done) = engine.execute(iterator, math.inf)
assert len(results) == 1
def test_filter_iterator_interrupt():
expression = "?p = <http://schema.org/eligibleRegion>"
iterator, card = hdtDoc.search_triples(triple['subject'], triple['predicate'], triple['object'])
scan = ProjectionIterator(ScanIterator(iterator, triple, card))
iterator = FilterIterator(scan, expression)
(results, saved, done) = engine.execute(iterator, 10e-7)
assert len(results) <= 4
for b in results:
assert b['?p'] == 'http://schema.org/eligibleRegion'
assert b['?o'] in [
'http://db.uwaterloo.ca/~galuc/wsdbm/Country0',
'http://db.uwaterloo.ca/~galuc/wsdbm/Country1',
'http://db.uwaterloo.ca/~galuc/wsdbm/Country4',
'http://db.uwaterloo.ca/~galuc/wsdbm/Country9'
]
tmp = len(results)
reloaded = load(saved.SerializeToString(), DummyDataset(hdtDoc, 'watdiv100'))
(results, saved, done) = engine.execute(reloaded, 10e7)
assert len(results) + tmp == 4
for b in results:
assert b['?p'] == 'http://schema.org/eligibleRegion'
assert b['?o'] in [
'http://db.uwaterloo.ca/~galuc/wsdbm/Country0',
'http://db.uwaterloo.ca/~galuc/wsdbm/Country1',
'http://db.uwaterloo.ca/~galuc/wsdbm/Country4',
'http://db.uwaterloo.ca/~galuc/wsdbm/Country9'
]
assert done
def test_operation_filter_iterator():
expression = "10 = 5 * 2"
iterator, card = hdtDoc.search_triples(triple['subject'], triple['predicate'], triple['object'])
scan = ProjectionIterator(ScanIterator(iterator, triple, card))
iterator = FilterIterator(scan, expression)
(results, saved, done) = engine.execute(iterator, math.inf)
assert len(results) == 9
def test_projection_read_stopped():
iterator, card = hdtDoc.search_triples(triple['subject'], triple['predicate'], triple['object'])
scan = ScanIterator(iterator, triple, card)
proj = ProjectionIterator(scan, ['?common'])
(results, saved, done) = engine.execute(proj, 10e-4)
assert len(results) <= card
for res in results:
assert '?common' in res and '?s1' not in res
def build_join_plan(bgp, db_connector, projection=None):
"""Build a join plan between a BGP and a possible OPTIONAL clause"""
iterator, query_vars, cardinalities = build_left_plan(bgp, db_connector)
# if optional is not None:
# iterator, query_vars, c = build_left_plan(optional, db_connector, source=iterator, base_vars=query_vars, optional=True)
# cardinalities += c
values = projection if projection is not None else query_vars
return ProjectionIterator(iterator, values), cardinalities
def test_and_or_filter_iterator():
expression = "?p = <http://schema.org/eligibleRegion> && (?o = <http://db.uwaterloo.ca/~galuc/wsdbm/Country0> || ?o = <http://db.uwaterloo.ca/~galuc/wsdbm/Country9>)"
iterator, card = hdtDoc.search_triples(triple['subject'], triple['predicate'], triple['object'])
scan = ProjectionIterator(ScanIterator(iterator, triple, card))
iterator = FilterIterator(scan, expression)
(results, saved, done) = engine.execute(iterator, math.inf)
assert len(results) == 2
for b in results:
assert b['?p'] == 'http://schema.org/eligibleRegion'
assert b['?o'] in [
'http://db.uwaterloo.ca/~galuc/wsdbm/Country0',
'http://db.uwaterloo.ca/~galuc/wsdbm/Country9'
]
def parse_query_node(node, dataset, current_graphs, server_url, cardinalities):
"""
Recursively parse node in the query logical plan to build a preemptable physical query execution plan.
Args:
* node - Node of the logical plan to parse (in rdflib format)
* dataset - RDF dataset used to execute the query
* current_graphs - List of IRI of the current RDF graph queried
* server_url - URL of the SaGe server
* cardinalities - Map<triple,integer> used to track triple patterns cardinalities
"""
if node.name == 'SelectQuery':
# in case of a FROM clause, set the new default graphs used
graphs = current_graphs
if node.datasetClause is not None:
graphs = [format_graph_uri(format_term(graph_iri.default), server_url) for graph_iri in node.datasetClause]
return parse_query_node(node.p, dataset, graphs, server_url, cardinalities)
elif node.name == 'Project':
query_vars = list(map(lambda t: '?' + str(t), node._vars))
child = parse_query_node(node.p, dataset, current_graphs, server_url, cardinalities)
return ProjectionIterator(child, query_vars)
elif node.name == 'BGP':
# bgp_vars = node._vars
triples = list(localize_triple(node.triples, current_graphs))
iterator, query_vars, c = build_left_plan(triples, dataset, current_graphs)
# track cardinalities of every triple pattern
cardinalities += c
return iterator
elif node.name == 'Union':
left = parse_query_node(node.p1, dataset, current_graphs, server_url, cardinalities)
right = parse_query_node(node.p2, dataset, current_graphs, server_url, cardinalities)
return BagUnionIterator(left, right)
elif node.name == 'Filter':
expression = parse_filter_expr(node.expr)
iterator = parse_query_node(node.p, dataset, current_graphs, server_url, cardinalities)
return FilterIterator(iterator, expression)
elif node.name == 'Join':
# only allow for joining BGPs from different GRAPH clauses
triples = fetch_graph_triples(node.p1, current_graphs, server_url) + fetch_graph_triples(node.p2, current_graphs, server_url)
iterator, query_vars, c = build_left_plan(triples, dataset, current_graphs)
# track cardinalities of every triple pattern
cardinalities += c
return iterator
else:
raise UnsupportedSPARQL("Unsupported SPARQL feature: {}".format(node.name))
def build_join_plan(bgp, dataset, default_graph):
"""Build a join plan with a projection at the end"""
iterator, query_vars, cardinalities = build_left_plan(bgp, dataset, default_graph)
return ProjectionIterator(iterator, query_vars), cardinalities
def load_projection(saved_plan, dataset):
"""Load a ProjectionIterator from a protobuf serialization"""
sourceField = saved_plan.WhichOneof('source')
source = load(getattr(saved_plan, sourceField), dataset)
values = saved_plan.values if len(saved_plan.values) > 0 else None
return ProjectionIterator(source, values)