pyjelly 0.2.3__py3-none-any.whl → 0.4.0__py3-none-any.whl

pyjelly/integrations/rdflib/parse.py

@@ -1,14 +1,15 @@
 from __future__ import annotations
 
 from collections.abc import Generator, Iterable
-from typing import IO, Any
-from typing_extensions import Never, override
+from itertools import chain
+from typing import IO, Any, Callable, Union
+from typing_extensions import Never, Self, override
 
 import rdflib
+from rdflib import Node
 from rdflib.graph import DATASET_DEFAULT_GRAPH_ID, Dataset, Graph
 from rdflib.parser import InputSource
 from rdflib.parser import Parser as RDFLibParser
-from rdflib.store import Store
 
 from pyjelly import jelly
 from pyjelly.errors import JellyConformanceError
@@ -16,8 +17,113 @@ from pyjelly.options import StreamTypes
 from pyjelly.parse.decode import Adapter, Decoder, ParserOptions
 from pyjelly.parse.ioutils import get_options_and_frames
 
+GraphName = Union[rdflib.URIRef, rdflib.BNode, str]
+
+
+class Triple(tuple[Node, Node, Node]):
+    """
+    Describe RDFLib triple.
+
+    Args:
+        tuple (Node, Node, Node): s/p/o tuple of RDFLib Nodes.
+
+    Returns:
+        Triple: triple as tuple.
+
+    """
+
+    __slots__ = ()
+
+    def __new__(cls, s: Node, p: Node, o: Node) -> Self:
+        return tuple.__new__(cls, (s, p, o))
+
+    @property
+    def s(self) -> Node:
+        return self[0]
+
+    @property
+    def p(self) -> Node:
+        return self[1]
+
+    @property
+    def o(self) -> Node:
+        return self[2]
+
+
+class Quad(tuple[Node, Node, Node, GraphName]):
+    """
+    Describe RDFLib quad.
+
+    Args:
+        tuple (Node, Node, Node, GraphName):
+            s/p/o/g as a tuple of RDFLib nodes and a GraphName,
+
+    Returns:
+        Quad: quad as tuple.
+
+    """
+
+    __slots__ = ()
+
+    def __new__(cls, s: Node, p: Node, o: Node, g: GraphName) -> Self:
+        return tuple.__new__(cls, (s, p, o, g))
+
+    @property
+    def s(self) -> Node:
+        return self[0]
+
+    @property
+    def p(self) -> Node:
+        return self[1]
+
+    @property
+    def o(self) -> Node:
+        return self[2]
+
+    @property
+    def g(self) -> GraphName:
+        return self[3]
+
+
+Statement = Union[Triple, Quad]
+
+
+class Prefix(tuple[str, rdflib.URIRef]):
+    """
+    Describe RDF Prefix(i.e, namespace declaration).
+
+    Args:
+        tuple (str, rdflib.URIRef): expects prefix as a string,
+            and full namespace URI as Rdflib.URIRef.
+
+    Returns:
+        Prefix: prefix as tuple(prefix, iri).
+
+    """
+
+    __slots__ = ()
+
+    def __new__(cls, prefix: str, iri: rdflib.URIRef) -> Self:
+        return tuple.__new__(cls, (prefix, iri))
+
+    @property
+    def prefix(self) -> str:
+        return self[0]
+
+    @property
+    def iri(self) -> rdflib.URIRef:
+        return self[1]
+
 
 class RDFLibAdapter(Adapter):
+    """
+    RDFLib adapter class, is extended by triples and quads implementations.
+
+    Args:
+        Adapter (): abstract adapter class
+
+    """
+
     @override
     def iri(self, iri: str) -> rdflib.URIRef:
         return rdflib.URIRef(iri)
@@ -39,8 +145,28 @@ class RDFLibAdapter(Adapter):
     ) -> rdflib.Literal:
         return rdflib.Literal(lex, lang=language, datatype=datatype)
 
+    @override
+    def namespace_declaration(self, name: str, iri: str) -> Prefix:
+        return Prefix(name, self.iri(iri))
+
 
 def _adapter_missing(feature: str, *, stream_types: StreamTypes) -> Never:
+    """
+    Raise error if functionality is missing in adapter.
+
+    Args:
+        feature (str): function which is not implemented
+        stream_types (StreamTypes): what combination of physical/logical types
+            triggered the error
+
+    Raises:
+        NotImplementedError: raises error with message with missing functionality
+            and types encountered
+
+    Returns:
+        Never: only raises errors
+
+    """
     physical_type_name = jelly.PhysicalStreamType.Name(stream_types.physical_type)
     logical_type_name = jelly.LogicalStreamType.Name(stream_types.logical_type)
     msg = (
@@ -51,242 +177,314 @@ def _adapter_missing(feature: str, *, stream_types: StreamTypes) -> Never:
 
 
 class RDFLibTriplesAdapter(RDFLibAdapter):
-    graph: Graph
-
-    def __init__(self, options: ParserOptions, store: Store | str = "default") -> None:
-        super().__init__(options=options)
-        self.graph = Graph(store=store)
+    """
+    Triples adapter RDFLib implementation.
 
-    @override
-    def triple(self, terms: Iterable[Any]) -> Any:
-        self.graph.add(terms)  # type: ignore[arg-type]
+    Notes: returns triple/namespace declaration as soon as receives them.
+    """
 
-    @override
-    def namespace_declaration(self, name: str, iri: str) -> None:
-        self.graph.bind(name, self.iri(iri))
-
-    def frame(self) -> Graph | None:
-        if self.options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_GRAPHS:
-            this_graph = self.graph
-            self.graph = Graph(store=self.graph.store)
-            return this_graph
-        if self.options.stream_types.logical_type in (
-            jelly.LOGICAL_STREAM_TYPE_UNSPECIFIED,
-            jelly.LOGICAL_STREAM_TYPE_FLAT_TRIPLES,
-        ):
-            return None
-        return _adapter_missing(
-            "interpreting frames",
-            stream_types=self.options.stream_types,
-        )
-
-
-class RDFLibQuadsBaseAdapter(RDFLibAdapter):
     def __init__(
         self,
         options: ParserOptions,
-        store: Store | str,
     ) -> None:
         super().__init__(options=options)
-        self.store = store
-        self.dataset = self.new_dataset()
-
-    def new_dataset(self) -> Dataset:
-        return Dataset(store=self.store, default_union=True)
 
     @override
-    def frame(self) -> Dataset | None:
-        if self.options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_DATASETS:
-            this_dataset = self.dataset
-            self.dataset = self.new_dataset()
-            return this_dataset
-        if self.options.stream_types.logical_type in (
-            jelly.LOGICAL_STREAM_TYPE_UNSPECIFIED,
-            jelly.LOGICAL_STREAM_TYPE_FLAT_QUADS,
-        ):
-            return None
-        return _adapter_missing(
-            "interpreting frames", stream_types=self.options.stream_types
-        )
+    def triple(self, terms: Iterable[Any]) -> Triple:
+        return Triple(*terms)
+
+
+class RDFLibQuadsBaseAdapter(RDFLibAdapter):
+    def __init__(self, options: ParserOptions) -> None:
+        super().__init__(options=options)
 
 
 class RDFLibQuadsAdapter(RDFLibQuadsBaseAdapter):
-    @override
-    def namespace_declaration(self, name: str, iri: str) -> None:
-        self.dataset.bind(name, self.iri(iri))
+    """
+    Extended RDFLib adapter for the QUADS physical type.
+
+    Args:
+        RDFLibQuadsBaseAdapter (RDFLibAdapter): base quads adapter
+            (shared with graphs physical type)
+
+    """
 
     @override
-    def quad(self, terms: Iterable[Any]) -> Any:
-        self.dataset.add(terms)  # type: ignore[arg-type]
+    def quad(self, terms: Iterable[Any]) -> Quad:
+        return Quad(*terms)
 
 
 class RDFLibGraphsAdapter(RDFLibQuadsBaseAdapter):
-    _graph: Graph | None = None
+    """
+    Extension of RDFLibQuadsBaseAdapter for the GRAPHS physical type.
+
+    Notes: introduces graph start/end, checks if graph exists.
+
+    Args:
+        RDFLibQuadsBaseAdapter (RDFLibAdapter): base adapter for quads management.
+
+    Raises:
+        JellyConformanceError: if no graph_start was encountered
+
+    """
+
+    _graph_id: str | None
 
     def __init__(
         self,
         options: ParserOptions,
-        store: Store | str,
     ) -> None:
-        super().__init__(options=options, store=store)
-        self._graph = None
+        super().__init__(options=options)
+        self._graph_id = None
 
     @property
-    def graph(self) -> Graph:
-        if self._graph is None:
+    def graph(self) -> None:
+        if self._graph_id is None:
             msg = "new graph was not started"
             raise JellyConformanceError(msg)
-        return self._graph
 
     @override
     def graph_start(self, graph_id: str) -> None:
-        self._graph = Graph(store=self.dataset.store, identifier=graph_id)
+        self._graph_id = graph_id
 
     @override
-    def namespace_declaration(self, name: str, iri: str) -> None:
-        self.graph.bind(name, self.iri(iri))
-
-    @override
-    def triple(self, terms: Iterable[Any]) -> None:
-        self.graph.add(terms)  # type: ignore[arg-type]
+    def triple(self, terms: Iterable[Any]) -> Quad:
+        return Quad(*chain(terms, [self._graph_id]))
 
     @override
     def graph_end(self) -> None:
-        self.dataset.store.add_graph(self.graph)
-        self._graph = None
+        self._graph_id = None
 
-    def frame(self) -> Dataset | None:
-        if self.options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_DATASETS:
-            this_dataset = self.dataset
-            self._graph = None
-            self.dataset = self.new_dataset()
-            return this_dataset
-        return super().frame()
 
-
-def parse_flat_triples_stream(
+def parse_triples_stream(
     frames: Iterable[jelly.RdfStreamFrame],
     options: ParserOptions,
-    store: Store | str = "default",
-    identifier: str | None = None,
-) -> Dataset | Graph:
-    assert options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_FLAT_TRIPLES
-    adapter = RDFLibTriplesAdapter(options, store=store)
-    if identifier is not None:
-        adapter.graph = Graph(identifier=identifier, store=store)
+) -> Generator[Iterable[Triple | Prefix]]:
+    """
+    Parse flat triple stream.
+
+    Args:
+        frames (Iterable[jelly.RdfStreamFrame]): iterator over stream frames
+        options (ParserOptions): stream options
+
+    Yields:
+        Generator[Iterable[Triple | Prefix]]:
+            Generator of iterables of Triple or Prefix objects,
+            one iterable per frame.
+
+    """
+    adapter = RDFLibTriplesAdapter(options)
     decoder = Decoder(adapter=adapter)
     for frame in frames:
-        decoder.decode_frame(frame=frame)
-    return adapter.graph
+        yield decoder.iter_rows(frame)
+    return
 
 
-def parse_flat_quads_stream(
+def parse_quads_stream(
     frames: Iterable[jelly.RdfStreamFrame],
     options: ParserOptions,
-    store: Store | str = "default",
-    identifier: str | None = None,
-) -> Dataset:
-    assert options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_FLAT_QUADS
+) -> Generator[Iterable[Quad | Prefix]]:
+    """
+    Parse flat quads stream.
+
+    Args:
+        frames (Iterable[jelly.RdfStreamFrame]): iterator over stream frames
+        options (ParserOptions): stream options
+
+    Yields:
+        Generator[Iterable[Quad | Prefix]]:
+            Generator of iterables of Quad or Prefix objects,
+            one iterable per frame.
+
+    """
     adapter_class: type[RDFLibQuadsBaseAdapter]
     if options.stream_types.physical_type == jelly.PHYSICAL_STREAM_TYPE_QUADS:
         adapter_class = RDFLibQuadsAdapter
-    else:  # jelly.PHYSICAL_STREAM_TYPE_GRAPHS
+    else:
         adapter_class = RDFLibGraphsAdapter
-    adapter = adapter_class(options=options, store=store)
-    adapter.dataset.default_context = Graph(identifier=identifier, store=store)
-    decoder = Decoder(adapter=adapter)
-    for frame in frames:
-        decoder.decode_frame(frame=frame)
-    return adapter.dataset
-
-
-def parse_graph_stream(
-    frames: Iterable[jelly.RdfStreamFrame],
-    options: ParserOptions,
-    store: Store | str = "default",
-) -> Generator[Graph]:
-    assert options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_GRAPHS
-    adapter = RDFLibTriplesAdapter(options, store=store)
+    adapter = adapter_class(options=options)
     decoder = Decoder(adapter=adapter)
     for frame in frames:
-        yield decoder.decode_frame(frame=frame)
+        yield decoder.iter_rows(frame)
+    return
 
 
-def graphs_from_jelly(
+def parse_jelly_grouped(
     inp: IO[bytes],
-    store: Store | str = "default",
-) -> Generator[Any] | Generator[Dataset] | Generator[Graph]:
+    graph_factory: Callable[[], Graph] = lambda: Graph(),
+    dataset_factory: Callable[[], Dataset] = lambda: Dataset(),
+) -> Generator[Graph] | Generator[Dataset]:
+    """
+    Take jelly file and return generators based on the detected logical type.
+
+    Yields one graph/dataset per frame.
+
+    Args:
+        inp (IO[bytes]): input jelly buffered binary stream
+        graph_factory (Callable): lambda to construct a Graph.
+            By default creates an empty in-memory Graph,
+            but you can pass something else here.
+        dataset_factory (Callable): lambda to construct a Dataset.
+            By default creates an empty in-memory Dataset,
+            but you can pass something else here.
+
+    Raises:
+        NotImplementedError: is raised if a logical type is not implemented
+
+    Yields:
+        Generator[Graph] | Generator[Dataset]:
+            returns generators for graphs/datasets based on the type of input
+
+    """
     options, frames = get_options_and_frames(inp)
-
-    if options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_FLAT_TRIPLES:
-        yield parse_flat_triples_stream(frames=frames, options=options, store=store)
-        return
-
-    if options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_FLAT_QUADS:
-        yield parse_flat_quads_stream(frames=frames, options=options, store=store)
+    if options.stream_types.physical_type == jelly.PHYSICAL_STREAM_TYPE_TRIPLES:
+        for graph in parse_triples_stream(
+            frames=frames,
+            options=options,
+        ):
+            sink = graph_factory()
+            for graph_item in graph:
+                if isinstance(graph_item, Prefix):
+                    sink.bind(graph_item.prefix, graph_item.iri)
+                else:
+                    sink.add(graph_item)
+            yield sink
         return
-
-    if options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_GRAPHS:
-        yield from parse_graph_stream(frames=frames, options=options, store=store)
+    elif options.stream_types.physical_type in (
+        jelly.PHYSICAL_STREAM_TYPE_QUADS,
+        jelly.PHYSICAL_STREAM_TYPE_GRAPHS,
+    ):
+        for dataset in parse_quads_stream(
+            frames=frames,
+            options=options,
+        ):
+            sink = dataset_factory()
+            for item in dataset:
+                if isinstance(item, Prefix):
+                    sink.bind(item.prefix, item.iri)
+                else:
+                    s, p, o, graph_name = item
+                    context = sink.get_context(graph_name)
+                    sink.add((s, p, o, context))
+            yield sink
         return
 
-    logical_type_name = jelly.LogicalStreamType.Name(options.stream_types.logical_type)
-    msg = f"the stream type {logical_type_name} is not supported "
+    physical_type_name = jelly.PhysicalStreamType.Name(
+        options.stream_types.physical_type
+    )
+    msg = f"the stream type {physical_type_name} is not supported "
     raise NotImplementedError(msg)
 
 
-def graph_from_jelly(
+def parse_jelly_to_graph(
     inp: IO[bytes],
-    store: Store | str = "default",
-    identifier: str | None = None,
-) -> Any | Dataset | Graph:
+    graph_factory: Callable[[], Graph] = lambda: Graph(),
+    dataset_factory: Callable[[], Dataset] = lambda: Dataset(),
+) -> Graph | Dataset:
+    """
+    Add statements from Generator to provided Graph/Dataset.
+
+    Args:
+        inp (IO[bytes]): input jelly stream.
+        graph_factory (Callable[[], Graph]): factory to create Graph.
+            By default creates an empty in-memory Graph,
+            but you can pass something else here.
+        dataset_factory (Callable[[], Dataset]): factory to create Dataset.
+            By default creates an empty in-memory Dataset,
+            but you can pass something else here.
+
+    Returns:
+        Dataset | Graph: Dataset or Graph with statements.
+
+    """
     options, frames = get_options_and_frames(inp)
 
-    if options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_DATASETS:
-        msg = (
-            "the stream contains multiple datasets and cannot be parsed into "
-            "a single dataset"
-        )
-        raise NotImplementedError(msg)
-
-    if options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_FLAT_TRIPLES:
-        return parse_flat_triples_stream(
-            frames=frames,
-            options=options,
-            store=store,
-            identifier=identifier,
-        )
-
-    if options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_FLAT_QUADS:
-        return parse_flat_quads_stream(
+    if options.stream_types.physical_type == jelly.PHYSICAL_STREAM_TYPE_TRIPLES:
+        sink = graph_factory()
+    if options.stream_types.physical_type in (
+        jelly.PHYSICAL_STREAM_TYPE_QUADS,
+        jelly.PHYSICAL_STREAM_TYPE_GRAPHS,
+    ):
+        quad_sink = dataset_factory()
+        sink = quad_sink
+
+    for item in parse_jelly_flat(inp=inp, frames=frames, options=options):
+        if isinstance(item, Prefix):
+            sink.bind(item.prefix, item.iri)
+        if isinstance(item, Triple):
+            sink.add(item)
+        if isinstance(item, Quad):
+            s, p, o, graph_name = item
+            context = quad_sink.get_context(graph_name)
+            quad_sink.add((s, p, o, context))
+    return sink
+
+
+def parse_jelly_flat(
+    inp: IO[bytes],
+    frames: Iterable[jelly.RdfStreamFrame] | None = None,
+    options: ParserOptions | None = None,
+) -> Generator[Statement | Prefix]:
+    """
+    Parse jelly file with FLAT physical type into a Generator of stream events.
+
+    Args:
+        inp (IO[bytes]): input jelly buffered binary stream.
+        frames (Iterable[jelly.RdfStreamFrame | None):
+            jelly frames if read before.
+        options (ParserOptions | None): stream options
+            if read before.
+
+    Raises:
+        NotImplementedError: if physical type is not supported
+
+    Yields:
+        Generator[Statement | Prefix]: Generator of stream events
+
+    """
+    if not frames or not options:
+        options, frames = get_options_and_frames(inp)
+
+    if options.stream_types.physical_type == jelly.PHYSICAL_STREAM_TYPE_TRIPLES:
+        for triples in parse_triples_stream(frames=frames, options=options):
+            yield from triples
+        return
+    if options.stream_types.physical_type in (
+        jelly.PHYSICAL_STREAM_TYPE_QUADS,
+        jelly.PHYSICAL_STREAM_TYPE_GRAPHS,
+    ):
+        for quads in parse_quads_stream(
             frames=frames,
             options=options,
-            store=store,
-            identifier=identifier,
-        )
-
-    if options.stream_types.logical_type == jelly.LOGICAL_STREAM_TYPE_GRAPHS:
-        ds = Dataset(store=store, default_union=True)
-        ds.default_context = Graph(identifier=identifier, store=store)
-
-        for graph in parse_graph_stream(frames=frames, options=options, store=store):
-            ds.add_graph(graph)
-
-        return ds
-
-    logical_type_name = jelly.LogicalStreamType.Name(options.stream_types.logical_type)
-    msg = f"the stream type {logical_type_name} is not supported "
+        ):
+            yield from quads
+        return
+    physical_type_name = jelly.PhysicalStreamType.Name(
+        options.stream_types.physical_type
+    )
+    msg = f"the stream type {physical_type_name} is not supported "
     raise NotImplementedError(msg)
 
 
 class RDFLibJellyParser(RDFLibParser):
     def parse(self, source: InputSource, sink: Graph) -> None:
+        """
+        Parse jelly file into provided RDFLib Graph.
+
+        Args:
+            source (InputSource): jelly file as buffered binary stream InputSource obj
+            sink (Graph): RDFLib Graph
+
+        Raises:
+            TypeError: raises error if invalid input
+
+        """
         inp = source.getByteStream()  # type: ignore[no-untyped-call]
         if inp is None:
             msg = "expected source to be a stream of bytes"
             raise TypeError(msg)
-        graph_from_jelly(
+        parse_jelly_to_graph(
             inp,
-            identifier=sink.identifier,
-            store=sink.store,
+            graph_factory=lambda: Graph(store=sink.store, identifier=sink.identifier),
+            dataset_factory=lambda: Dataset(store=sink.store),
         )