Should SPARQL loading not also support formats with named graphs?

[aucampia]

Currently SPARQL queries seem to only be able to load sources that are in formats that don't support named graphs:

rdflib/rdflib/plugins/sparql/sparql.py

Lines 314 to 333 in ad56044

	def load(self, source: URIRef, default: bool = False, **kwargs: Any) -> None:
	def _load(graph, source):
	try:
	return graph.parse(source, format="turtle", **kwargs)
	except Exception:
	pass
	try:
	return graph.parse(source, format="xml", **kwargs)
	except Exception:
	pass
	try:
	return graph.parse(source, format="n3", **kwargs)
	except Exception:
	pass
	try:
	return graph.parse(source, format="nt", **kwargs)
	except Exception:
	raise Exception(
	"Could not load %s as either RDF/XML, N3 or NTriples" % source
	)

I'm not sure if this is right.

[edmondchuc]

i'm guessing this load function is only applicable to SPARQL CONSTRUCT queries?

According to the spec https://www.w3.org/TR/sparql11-query/#construct

The CONSTRUCT query form returns a single RDF graph specified by a graph template.