Feature support in the schema

* Type annotations
* Feature type
* Moved from_string from Schema to its own file/function
* Root predicate has a valid (not-None) range
* ROOT_... export in schema.types
* Empty as the default Schema constructor
* Schema loads some additional default symbols
* _Type instances compare along class hierarchy

1 files changed, 19 insertions, 92 deletions

diff --git a/bsfs/schema/schema.py b/bsfs/schema/schema.py
index c5d4571..1c4c807 100644
--- a/bsfs/schema/schema.py
+++ b/bsfs/schema/schema.py
@@ -51,11 +51,13 @@ class Schema():
 
     def __init__(
             self,
-            predicates: typing.Iterable[types.Predicate],
+            predicates: typing.Optional[typing.Iterable[types.Predicate]] = None,
             nodes: typing.Optional[typing.Iterable[types.Node]] = None,
             literals: typing.Optional[typing.Iterable[types.Literal]] = None,
             ):
         # materialize arguments
+        if predicates is None:
+            predicates = set()
         if nodes is None:
             nodes = set()
         if literals is None:
@@ -63,24 +65,36 @@ class Schema():
         nodes = set(nodes)
         literals = set(literals)
         predicates = set(predicates)
+
+        # add root types to the schema
+        nodes.add(types.ROOT_NODE)
+        literals.add(types.ROOT_LITERAL)
+        predicates.add(types.ROOT_PREDICATE)
+        # add minimally necessary types to the schema
+        literals.add(types.ROOT_NUMBER)
+        predicates.add(types.ROOT_FEATURE)
+
         # include parents in predicates set
         # TODO: review type annotations and ignores for python >= 3.11 (parents is _Type but should be typing.Self)
         predicates |= {par for pred in predicates for par in pred.parents()} # type: ignore [misc]
         # include predicate domain in nodes set
         nodes |= {pred.domain for pred in predicates}
         # include predicate range in nodes and literals sets
-        prange = {pred.range for pred in predicates if pred.range is not None}
+        prange = {pred.range for pred in predicates}
         nodes |= {vert for vert in prange if isinstance(vert, types.Node)}
         literals |= {vert for vert in prange if isinstance(vert, types.Literal)}
+        # NOTE: ROOT_PREDICATE has a _Vertex as range which is neither in nodes nor literals
+        # FIXME: with the ROOT_VERTEX missing, the schema is not complete anymore!
+
         # include parents in nodes and literals sets
-        # NOTE: Must be done after predicate domain/range was handled
-        # so that their parents are included as well.
+        # NOTE: Must come after predicate domain/range was handled to have their parents as well.
         nodes |= {par for node in nodes for par in node.parents()} # type: ignore [misc]
         literals |= {par for lit in literals for par in lit.parents()} # type: ignore [misc]
         # assign members
         self._nodes = {node.uri: node for node in nodes}
         self._literals = {lit.uri: lit for lit in literals}
         self._predicates = {pred.uri: pred for pred in predicates}
+
         # verify unique uris
         if len(nodes) != len(self._nodes):
             raise errors.ConsistencyError('inconsistent nodes')
@@ -214,6 +228,7 @@ class Schema():
         >>> Schema.Union([a, b, c])
 
         """
+        # FIXME: copy type annotations?
         if len(args) == 0:
             raise TypeError('Schema.Union requires at least one argument (Schema or Iterable)')
         if isinstance(args[0], cls): # args is sequence of Schema instances
@@ -295,92 +310,4 @@ class Schema():
         """Return the Literal matching the *uri*."""
         return self._literals[uri]
 
-
-    ## constructors ##
-
-
-    @classmethod
-    def Empty(cls) -> 'Schema': # pylint: disable=invalid-name # capitalized classmethod
-        """Return a minimal Schema."""
-        node = types.Node(ns.bsfs.Node, None)
-        literal = types.Literal(ns.bsfs.Literal, None)
-        predicate = types.Predicate(
-            uri=ns.bsfs.Predicate,
-            parent=None,
-            domain=node,
-            range=None,
-            unique=False,
-            )
-        return cls((predicate, ), (node, ), (literal, ))
-
-
-    @classmethod
-    def from_string(cls, schema: str) -> 'Schema': # pylint: disable=invalid-name # capitalized classmethod
-        """Load and return a Schema from a string."""
-        # parse string into rdf graph
-        graph = rdflib.Graph()
-        graph.parse(data=schema, format='turtle')
-
-        def _fetch_hierarchically(factory, curr):
-            # emit current node
-            yield curr
-            # walk through childs
-            for child in graph.subjects(rdflib.URIRef(ns.rdfs.subClassOf), rdflib.URIRef(curr.uri)):
-                # convert to URI
-                child = URI(child)
-                # check circular dependency
-                if child == curr.uri or child in {node.uri for node in curr.parents()}:
-                    raise errors.ConsistencyError('circular dependency')
-                # recurse and emit (sub*)childs
-                yield from _fetch_hierarchically(factory, factory(child, curr))
-
-        # fetch nodes
-        nodes = set(_fetch_hierarchically(types.Node, types.Node(ns.bsfs.Node, None)))
-        nodes_lut = {node.uri: node for node in nodes}
-        if len(nodes_lut) != len(nodes):
-            raise errors.ConsistencyError('inconsistent nodes')
-
-        # fetch literals
-        literals = set(_fetch_hierarchically(types.Literal, types.Literal(ns.bsfs.Literal, None)))
-        literals_lut = {lit.uri: lit for lit in literals}
-        if len(literals_lut) != len(literals):
-            raise errors.ConsistencyError('inconsistent literals')
-
-        # fetch predicates
-        def build_predicate(uri, parent):
-            uri = rdflib.URIRef(uri)
-            # get domain
-            domains = set(graph.objects(uri, rdflib.RDFS.domain))
-            if len(domains) != 1:
-                raise errors.ConsistencyError(f'inconsistent domain: {domains}')
-            dom = nodes_lut.get(next(iter(domains)))
-            if dom is None:
-                raise errors.ConsistencyError('missing domain')
-            # get range
-            ranges = set(graph.objects(uri, rdflib.RDFS.range))
-            if len(ranges) != 1:
-                raise errors.ConsistencyError(f'inconsistent range: {ranges}')
-            rng = next(iter(ranges))
-            rng = nodes_lut.get(rng, literals_lut.get(rng))
-            if rng is None:
-                raise errors.ConsistencyError('missing range')
-            # get unique flag
-            uniques = set(graph.objects(uri, rdflib.URIRef(ns.bsfs.unique)))
-            if len(uniques) != 1:
-                raise errors.ConsistencyError(f'inconsistent unique flags: {uniques}')
-            unique = bool(next(iter(uniques)))
-            # build Predicate
-            return types.Predicate(URI(uri), parent, dom, rng, unique)
-
-        root_predicate = types.Predicate(
-            uri=ns.bsfs.Predicate,
-            parent=None,
-            domain=nodes_lut[ns.bsfs.Node],
-            range=None, # FIXME: Unclear how to handle this! Can be either a Literal or a Node
-            unique=False,
-            )
-        predicates = _fetch_hierarchically(build_predicate, root_predicate)
-        # return Schema
-        return cls(predicates, nodes, literals)
-
 ## EOF ##