Merge branch 'main' into sparql-connector-default-graph

nicholascar · web-flow · commit dfa071c9943a · 2024-07-25T11:59:27.000+10:00
diff --git a/.github/dependabot.yml b/.github/dependabot.yml
@@ -5,7 +5,9 @@ updates:
     schedule:
       interval: weekly
     open-pull-requests-limit: 10
-    versioning-strategy: widen
+    # todo: change this to widen when Dependabot adds widen back to Pip ecosystem
+    # see https://github.com/dependabot/dependabot-core/pull/10194
+    versioning-strategy: auto
     ignore:
       - dependency-name: sphinx
         versions:
@@ -28,7 +30,7 @@ updates:
     directory: docker/latest/
     schedule:
       interval: weekly
-    versioning-strategy: widen
+    versioning-strategy: auto
   - package-ecosystem: docker
     directory: docker/unstable/
     schedule:
@@ -37,4 +39,4 @@ updates:
     directory: devtools/
     schedule:
       interval: weekly
-    versioning-strategy: widen
+    versioning-strategy: auto
diff --git a/docker/latest/Dockerfile b/docker/latest/Dockerfile
@@ -1,4 +1,4 @@
-FROM docker.io/library/python:3.12.4-slim@sha256:f11725aba18c19664a408902103365eaf8013823ffc56270f921d1dc78a198cb
+FROM docker.io/library/python:3.12.4-slim@sha256:52f92c54e879539342692d20a4bea99516d4a2eb3cd16dfbb4e4b964aa8becaa
 
 COPY docker/latest/requirements.txt /var/tmp/build/
 
diff --git a/docker/unstable/Dockerfile b/docker/unstable/Dockerfile
@@ -1,4 +1,4 @@
-FROM docker.io/library/python:3.12.2-slim@sha256:36d57d7f9948fefe7b6092cfe8567da368033e71ba281b11bb9eeffce3d45bc6
+FROM docker.io/library/python:3.12.4-slim@sha256:52f92c54e879539342692d20a4bea99516d4a2eb3cd16dfbb4e4b964aa8becaa
 
 # This file is generated from docker:unstable in Taskfile.yml
 COPY var/requirements.txt /var/tmp/build/
diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -44,7 +44,7 @@ pyparsing = ">=2.1.0,<4"
 berkeleydb = {version = "^18.1.0", optional = true}
 networkx = {version = ">=2,<4", optional = true}
 html5lib = {version = "^1.0", optional = true}
-lxml = {version = "^4.3.0", optional = true}
+lxml = {version = ">=4.3,<6.0", optional = true}
 
 [tool.poetry.group.dev.dependencies]
 black = "24.4.2"
@@ -60,10 +60,10 @@ setuptools = ">=68,<72"
 wheel = ">=0.42,<0.44"
 
 [tool.poetry.group.docs.dependencies]
-sphinx = "^7.1.1"
+sphinx = ">=7.1.2,<8"
 myst-parser = ">=2,<4"
 sphinxcontrib-apidoc = ">=0.3,<0.6"
-sphinx-autodoc-typehints = "^1.17.1"
+sphinx-autodoc-typehints = ">=1.25.3,<=2.0.1"
 typing-extensions = "^4.5.0"
 
 [tool.poetry.group.lint.dependencies]
diff --git a/rdflib/extras/infixowl.py b/rdflib/extras/infixowl.py
@@ -1329,7 +1329,10 @@ def subSumpteeIds(self):  # noqa: N802
     #        predicate=RDFS.subClassOf,object=self.identifier):
     #         yield Class(s,skipOWLClassMembership=True)
 
-    def __repr__(self, full=False, normalization=True):
+    def __repr__(self):
+        return self.manchesterClass(full=False, normalization=True)
+
+    def manchesterClass(self, full=False, normalization=True):  # noqa: N802
         """
         Returns the Manchester Syntax equivalent for this class
         """
diff --git a/rdflib/graph.py b/rdflib/graph.py
@@ -433,6 +433,11 @@ class Graph(Node):
     For more on named graphs, see: http://www.w3.org/2004/03/trix/
     """
 
+    context_aware: bool
+    formula_aware: bool
+    default_union: bool
+    base: Optional[str]
+
     def __init__(
         self,
         store: Union[Store, str] = "default",
@@ -1393,9 +1398,9 @@ def parse(
            :doc:`Security Considerations </security_considerations>`
            documentation.
 
-        :param source: An `InputSource`, file-like object, `Path` like object,
-            or string. In the case of a string the string is the location of the
-            source.
+        :param source: An `xml.sax.xmlreader.InputSource`, file-like object,
+            `pathlib.Path` like object, or string. In the case of a string the string
+            is the location of the source.
         :param location: A string indicating the relative or absolute URL of the
             source. `Graph`'s absolutize method is used if a relative location
             is specified.
@@ -1910,6 +1915,8 @@ class ConjunctiveGraph(Graph):
     All queries are carried out against the union of all graphs.
     """
 
+    default_context: _ContextType
+
     def __init__(
         self,
         store: Union[Store, str] = "default",
@@ -2227,8 +2234,9 @@ def parse(
 
         See :meth:`rdflib.graph.Graph.parse` for documentation on arguments.
 
-        If the source is in a format that does not support named graphs it's triples
-        will be added to the default graph (i.e. `Dataset.default_context`).
+        If the source is in a format that does not support named graphs its triples
+        will be added to the default graph
+        (i.e. :attr:`ConjunctiveGraph.default_context`).
 
         :Returns:
 
@@ -2254,7 +2262,7 @@ def parse(
         the ``publicID`` parameter will also not be used as the name for the
         graph that the data is loaded into, and instead the triples from sources
         that do not support named graphs will be loaded into the default graph
-        (i.e. `ConjunctionGraph.default_context`).
+        (i.e. :attr:`ConjunctiveGraph.default_context`).
         """
 
         source = create_input_source(
@@ -2488,8 +2496,9 @@ def parse(
 
         The source is specified using one of source, location, file or data.
 
-        If the source is in a format that does not support named graphs it's triples
-        will be added to the default graph (i.e. `Dataset.default_context`).
+        If the source is in a format that does not support named graphs its triples
+        will be added to the default graph
+        (i.e. :attr:`.Dataset.default_context`).
 
         .. caution::
 
@@ -2510,7 +2519,7 @@ def parse(
         the ``publicID`` parameter will also not be used as the name for the
         graph that the data is loaded into, and instead the triples from sources
         that do not support named graphs will be loaded into the default graph
-        (i.e. `ConjunctionGraph.default_context`).
+        (i.e. :attr:`.Dataset.default_context`).
         """
 
         c = ConjunctiveGraph.parse(
diff --git a/rdflib/namespace/_WGS.py b/rdflib/namespace/_WGS.py
@@ -7,7 +7,7 @@ class WGS(DefinedNamespace):
     Basic Geo (WGS84 lat/long) Vocabulary
 
     The HTML Specification for the vocabulary can be found
-    `here <https://www.w3.org/2003/01/geo/>`.
+    here <https://www.w3.org/2003/01/geo/>.
     """
 
     _NS = Namespace("https://www.w3.org/2003/01/geo/wgs84_pos#")
diff --git a/rdflib/namespace/__init__.py b/rdflib/namespace/__init__.py
@@ -233,6 +233,13 @@ def __repr__(self) -> str:
     "_underscore_num",
 }
 
+# Some libraries probe classes for certain attributes or items.
+# This is a list of those attributes and items that should be ignored.
+_IGNORED_ATTR_LOOKUP: Set[str] = {
+    "_pytestfixturefunction",  # pytest tries to look this up on Defined namespaces
+    "_partialmethod",  # sphinx tries to look this up during autodoc generation
+}
+
 
 class DefinedNamespaceMeta(type):
     """Utility metaclass for generating URIRefs with a common prefix."""
@@ -246,10 +253,13 @@ class DefinedNamespaceMeta(type):
     @lru_cache(maxsize=None)
     def __getitem__(cls, name: str, default=None) -> URIRef:
         name = str(name)
+
         if name in _DFNS_RESERVED_ATTRS:
             raise AttributeError(
                 f"DefinedNamespace like object has no attribute {name!r}"
             )
+        elif name in _IGNORED_ATTR_LOOKUP:
+            raise KeyError()
         if str(name).startswith("__"):
             # NOTE on type ignore: This seems to be a real bug, super() does not
             # implement this method, it will fail if it is ever reached.
@@ -265,6 +275,8 @@ def __getitem__(cls, name: str, default=None) -> URIRef:
         return cls._NS[name]
 
     def __getattr__(cls, name: str):
+        if name in _IGNORED_ATTR_LOOKUP:
+            raise AttributeError()
         return cls.__getitem__(name)
 
     def __repr__(cls) -> str:
diff --git a/rdflib/plugins/parsers/hext.py b/rdflib/plugins/parsers/hext.py
@@ -72,7 +72,11 @@ def _parse_hextuple(
 
         # 6 - context
         if tup[5] is not None:
-            c = URIRef(tup[5])
+            c = (
+                BNode(tup[5].replace("_:", ""))
+                if tup[5].startswith("_:")
+                else URIRef(tup[5])
+            )
             # type error: Argument 1 to "add" of "ConjunctiveGraph" has incompatible type "Tuple[Union[URIRef, BNode], URIRef, Union[URIRef, BNode, Literal], URIRef]"; expected "Union[Tuple[Node, Node, Node], Tuple[Node, Node, Node, Optional[Graph]]]"
             cg.add((s, p, o, c))  # type: ignore[arg-type]
         else:
diff --git a/rdflib/plugins/serializers/hext.py b/rdflib/plugins/serializers/hext.py
@@ -9,7 +9,7 @@
 import warnings
 from typing import IO, Optional, Type, Union
 
-from rdflib.graph import ConjunctiveGraph, Graph
+from rdflib.graph import DATASET_DEFAULT_GRAPH_ID, ConjunctiveGraph, Graph
 from rdflib.namespace import RDF, XSD
 from rdflib.serializer import Serializer
 from rdflib.term import BNode, Literal, Node, URIRef
@@ -136,10 +136,14 @@ def _iri_or_bn(self, i_):
     def _context(self, context):
         if self.graph_type == Graph:
             return ""
-        if context.identifier == "urn:x-rdflib:default":
+        if context.identifier == DATASET_DEFAULT_GRAPH_ID:
             return ""
         elif context is not None and self.default_context is not None:
             # type error: "Node" has no attribute "identifier"
             if context.identifier == self.default_context.identifier:  # type: ignore[attr-defined]
                 return ""
-        return context.identifier
+        return (
+            context.identifier
+            if isinstance(context.identifier, URIRef)
+            else context.identifier.n3()
+        )
diff --git a/test/test_extras/test_infixowl/test_class.py b/test/test_extras/test_infixowl/test_class.py
@@ -153,7 +153,7 @@ def test_class_getparents(graph):
 
     assert list(sibling.subSumpteeIds()) == []
 
-    assert str(brother.__repr__(full=True)) == "Class: ex:Brother "
+    assert str(brother.manchesterClass(full=True)) == "Class: ex:Brother "
 
     assert graph.serialize(format="ttl") == (
         "@prefix ex: <http://example.org/vocab/> .\n"
@@ -251,7 +251,7 @@ def test_class_serialize(graph):
 
     assert str(owlc.__invert__()) == "Some Class DisjointWith ( NOT ex:Sister )\n"
 
-    assert owlc.__repr__(full=True) == (
+    assert owlc.manchesterClass(full=True) == (
         "Class: ex:test \n"
         "    ## A Defined Class (Man) ##\n"
         "    This is a Man\n"
diff --git a/test/test_parsers/test_parser_hext.py b/test/test_parsers/test_parser_hext.py
@@ -1,13 +1,39 @@
 from pathlib import Path
 
-from rdflib import ConjunctiveGraph, Dataset, Literal
+from rdflib import BNode, ConjunctiveGraph, Dataset, Literal, URIRef
+from rdflib.compare import isomorphic
+from rdflib.graph import DATASET_DEFAULT_GRAPH_ID
 from rdflib.namespace import XSD
 
 
+def test_named_and_anonymous_graph_roundtrip():
+    s = """
+        ["http://example.com/s01", "http://example.com/a", "http://example.com/Type1", "globalId", "", "https://example.com/graph/1"]
+        ["http://example.com/s01", "http://example.com/label", "This is a Label", "http://www.w3.org/1999/02/22-rdf-syntax-ns#langString", "en", "_:graph-2"]
+        ["http://example.com/s01", "http://example.com/comment", "This is a comment", "http://www.w3.org/2001/XMLSchema#string", "", ""]
+    """
+    d = Dataset()
+    d.parse(data=s, format="hext")
+
+    new_s = d.serialize(format="hext")
+    new_d = Dataset()
+    new_d.parse(data=new_s, format="hext")
+
+    named_graph = URIRef("https://example.com/graph/1")
+    assert isomorphic(d.graph(named_graph), new_d.graph(named_graph))
+
+    anonymous_graph = BNode("graph-2")
+    assert isomorphic(d.graph(anonymous_graph), new_d.graph(anonymous_graph))
+
+    assert isomorphic(
+        d.graph(DATASET_DEFAULT_GRAPH_ID), new_d.graph(DATASET_DEFAULT_GRAPH_ID)
+    )
+
+
 def test_small_string():
     s = """
-        ["http://example.com/s01", "http://example.com/a", "http://example.com/Type1", "globalId", "", ""]
-        ["http://example.com/s01", "http://example.com/label", "This is a Label", "http://www.w3.org/1999/02/22-rdf-syntax-ns#langString", "en", ""]
+        ["http://example.com/s01", "http://example.com/a", "http://example.com/Type1", "globalId", "", "https://example.com/graph/1"]
+        ["http://example.com/s01", "http://example.com/label", "This is a Label", "http://www.w3.org/1999/02/22-rdf-syntax-ns#langString", "en", "_:graph-2"]
         ["http://example.com/s01", "http://example.com/comment", "This is a comment", "http://www.w3.org/2001/XMLSchema#string", "", ""]
         ["http://example.com/s01", "http://example.com/creationDate", "2021-12-01", "http://www.w3.org/2001/XMLSchema#date", "", ""]
         ["http://example.com/s01", "http://example.com/creationTime", "2021-12-01T12:13:00", "http://www.w3.org/2001/XMLSchema#dateTime", "", ""]
@@ -17,14 +43,24 @@ def test_small_string():
         ["http://example.com/s01", "http://example.com/op1", "http://example.com/o2", "globalId", "", ""]
         ["http://example.com/s01", "http://example.com/op2", "http://example.com/o3", "globalId", "", ""]
         """
-    d = Dataset().parse(data=s, format="hext")
+    d = Dataset()
+    d.parse(data=s, format="hext")
+
+    expected_graph_names = (
+        URIRef(DATASET_DEFAULT_GRAPH_ID),
+        URIRef("https://example.com/graph/1"),
+        BNode("graph-2"),
+    )
+    for graph in d.contexts():
+        assert graph.identifier in expected_graph_names
+
     assert len(d) == 10
 
 
 def test_small_string_cg():
     s = """
-        ["http://example.com/s01", "http://example.com/a", "http://example.com/Type1", "globalId", "", ""]
-        ["http://example.com/s01", "http://example.com/label", "This is a Label", "http://www.w3.org/1999/02/22-rdf-syntax-ns#langString", "en", ""]
+        ["http://example.com/s01", "http://example.com/a", "http://example.com/Type1", "globalId", "", "https://example.com/graph/1"]
+        ["http://example.com/s01", "http://example.com/label", "This is a Label", "http://www.w3.org/1999/02/22-rdf-syntax-ns#langString", "en", "_:graph-2"]
         ["http://example.com/s01", "http://example.com/comment", "This is a comment", "http://www.w3.org/2001/XMLSchema#string", "", ""]
         ["http://example.com/s01", "http://example.com/creationDate", "2021-12-01", "http://www.w3.org/2001/XMLSchema#date", "", ""]
         ["http://example.com/s01", "http://example.com/creationTime", "2021-12-01T12:13:00", "http://www.w3.org/2001/XMLSchema#dateTime", "", ""]
@@ -34,7 +70,17 @@ def test_small_string_cg():
         ["http://example.com/s01", "http://example.com/op1", "http://example.com/o2", "globalId", "", ""]
         ["http://example.com/s01", "http://example.com/op2", "http://example.com/o3", "globalId", "", ""]
         """
-    d = ConjunctiveGraph().parse(data=s, format="hext")
+    d = ConjunctiveGraph(identifier=DATASET_DEFAULT_GRAPH_ID)
+    d.parse(data=s, format="hext")
+
+    expected_graph_names = (
+        URIRef(DATASET_DEFAULT_GRAPH_ID),
+        URIRef("https://example.com/graph/1"),
+        BNode("graph-2"),
+    )
+    for graph in d.contexts():
+        assert graph.identifier in expected_graph_names
+
     assert len(d) == 10
 
 
diff --git a/test/test_serializers/test_serializer.py b/test/test_serializers/test_serializer.py
@@ -717,4 +717,5 @@ def test_serialize_to_fileuri_with_authortiy(
             format=format.info.serializer,
         )
         assert False  # this should never happen as serialize should always fail
-    assert catcher.value is not None
+    # type error, mypy thinks this line is unreachable, but it works fine
+    assert catcher.value is not None  # type: ignore[unreachable, unused-ignore]
diff --git a/test/test_sparql/test_result.py b/test/test_sparql/test_result.py
@@ -441,4 +441,5 @@ def test_serialize_to_fileuri_with_authortiy(
             encoding=encoding,
         )
         assert False  # this should never happen as serialize should always fail
-    assert catcher.value is not None
+    # type error, mypy thinks this line is unreachable, but it works fine
+    assert catcher.value is not None  # type: ignore[unreachable, unused-ignore]
diff --git a/test/utils/test/test_outcome.py b/test/utils/test/test_outcome.py
@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 from contextlib import ExitStack
-from typing import Any, Callable, NoReturn, Optional, Type, Union
+from typing import Any, Callable, NoReturn, Optional, Type, Union, cast
 
 import pytest
 
@@ -16,7 +16,8 @@ def _raise(
     if isinstance(what, type) and issubclass(what, Exception):
         raise what(*args, **kwargs)
     elif callable(what):
-        raise what(*args, **kwargs)
+        what_fn: Callable[..., Exception] = cast(Callable[..., Exception], what)
+        raise what_fn(*args, **kwargs)
 
 
 @pytest.mark.parametrize(

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-FROM docker.io/library/python:3.12.4-slim@sha256:f11725aba18c19664a408902103365eaf8013823ffc56270f921d1dc78a198cb`
	`1`	`+FROM docker.io/library/python:3.12.4-slim@sha256:52f92c54e879539342692d20a4bea99516d4a2eb3cd16dfbb4e4b964aa8becaa`
`2`	`2`
`3`	`3`	`COPY docker/latest/requirements.txt /var/tmp/build/`
`4`	`4`
Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,4 @@`
`1`		`-FROM docker.io/library/python:3.12.2-slim@sha256:36d57d7f9948fefe7b6092cfe8567da368033e71ba281b11bb9eeffce3d45bc6`
	`1`	`+FROM docker.io/library/python:3.12.4-slim@sha256:52f92c54e879539342692d20a4bea99516d4a2eb3cd16dfbb4e4b964aa8becaa`
`2`	`2`
`3`	`3`	`# This file is generated from docker:unstable in Taskfile.yml`
`4`	`4`	`COPY var/requirements.txt /var/tmp/build/`