Merge branch 'main' into main

.pre-commit-config.yaml

@@ -1,14 +1,14 @@
 ---
 ci:
   # https://pre-commit.ci/#configuration
-  autoupdate_schedule: weekly
+  autoupdate_schedule: quarterly
   autofix_prs: false
 
 # https://pre-commit.com/#adding-pre-commit-plugins-to-your-project
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
     # WARNING: Ruff version should be the same as in `pyproject.toml`
-    rev: v0.7.1
+    rev: v0.7.2
     hooks:
       - id: ruff
         args: ["--fix"]

devtools/requirements-poetry.in

@@ -1,3 +1,3 @@
 # Fixing this here as readthedocs can't use the compiled requirements-poetry.txt
 # due to conflicts.
-poetry==1.8.4
+poetry==1.8.5

docker/latest/Dockerfile

@@ -1,4 +1,4 @@
-FROM docker.io/library/python:3.13.0-slim@sha256:2ec5a4a5c3e919570f57675471f081d6299668d909feabd8d4803c6c61af666c
+FROM docker.io/library/python:3.13.1-slim@sha256:1127090f9fff0b8e7c3a1367855ef8a3299472d2c9ed122948a576c39addeaf1
 
 COPY docker/latest/requirements.txt /var/tmp/build/
 

docker/unstable/Dockerfile

@@ -1,4 +1,4 @@
-FROM docker.io/library/python:3.13.0-slim@sha256:751d8bece269ba9e672b3f2226050e7e6fb3f3da3408b5dcb5d415a054fcb061
+FROM docker.io/library/python:3.13.1-slim@sha256:1127090f9fff0b8e7c3a1367855ef8a3299472d2c9ed122948a576c39addeaf1
 
 # This file is generated from docker:unstable in Taskfile.yml
 COPY var/requirements.txt /var/tmp/build/

docs/developers.rst

@@ -231,20 +231,17 @@ our black.toml config file:
 
     poetry run black .
 
-Check style and conventions with `flake8 <https://flake8.pycqa.org/en/latest/>`_:
+Check style and conventions with `ruff <https://docs.astral.sh/ruff/linter/>`_:
 
 .. code-block:: bash
 
-    poetry run flake8 rdflib
+    poetry run ruff check
 
-We also provide a `flakeheaven <https://pypi.org/project/flakeheaven/>`_
-baseline that ignores existing flake8 errors and only reports on newly
-introduced flake8 errors:
+Any issues that are found can potentially be fixed automatically using:
 
 .. code-block:: bash
 
-    poetry run flakeheaven
-
+   poetry run ruff check --fix
 
 Check types with `mypy <http://mypy-lang.org/>`_:
 

pyproject.toml

@@ -63,7 +63,7 @@ pytest-cov = ">=4,<7"
 coverage = {version = "^7.0.1", extras = ["toml"]}
 types-setuptools = ">=68.0.0.3,<72.0.0.0"
 setuptools = ">=68,<72"
-wheel = ">=0.42,<0.45"
+wheel = ">=0.42,<0.46"
 
 [tool.poetry.group.docs.dependencies]
 sphinx = ">=7.1.2,<8"
@@ -73,7 +73,7 @@ sphinx-autodoc-typehints = ">=2.3.0,<2.4.0"
 typing-extensions = "^4.11.0"
 
 [tool.poetry.group.lint.dependencies]
-ruff = ">=0.7.1,<0.8.0"
+ruff = ">=0.7.2,<1"
 
 [tool.poetry.extras]
 berkeleydb = ["berkeleydb"]

rdflib/__init__.py

@@ -59,6 +59,7 @@
     "BNode",
     "IdentifiedNode",
     "Literal",
+    "Node",
     "Variable",
     "Namespace",
     "Dataset",
@@ -195,7 +196,7 @@
     XSD,
     Namespace,
 )
-from rdflib.term import BNode, IdentifiedNode, Literal, URIRef, Variable
+from rdflib.term import BNode, IdentifiedNode, Literal, Node, URIRef, Variable
 
 from rdflib import plugin, query, util  # isort:skip
 from rdflib.container import *  # isort:skip # noqa: F403

rdflib/graph.py

@@ -966,19 +966,19 @@ def triples_choices(
         self,
         triple: (
             tuple[
-                list[_SubjectType] | tuple[_SubjectType],
+                list[_SubjectType] | tuple[_SubjectType, ...],
                 _PredicateType,
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
-                list[_PredicateType] | tuple[_PredicateType],
+                list[_PredicateType] | tuple[_PredicateType, ...],
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
                 _PredicateType,
-                list[_ObjectType] | tuple[_ObjectType],
+                list[_ObjectType] | tuple[_ObjectType, ...],
             ]
         ),
         context: _ContextType | None = None,
@@ -2208,19 +2208,19 @@ def triples_choices(
         self,
         triple: (
             tuple[
-                list[_SubjectType] | tuple[_SubjectType],
+                list[_SubjectType] | tuple[_SubjectType, ...],
                 _PredicateType,
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
-                list[_PredicateType] | tuple[_PredicateType],
+                list[_PredicateType] | tuple[_PredicateType, ...],
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
                 _PredicateType,
-                list[_ObjectType] | tuple[_ObjectType],
+                list[_ObjectType] | tuple[_ObjectType, ...],
             ]
         ),
         context: _ContextType | None = None,
@@ -2962,19 +2962,19 @@ def triples_choices(
         self,
         triple: (
             tuple[
-                list[_SubjectType] | tuple[_SubjectType],
+                list[_SubjectType] | tuple[_SubjectType, ...],
                 _PredicateType,
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
-                list[_PredicateType] | tuple[_PredicateType],
+                list[_PredicateType] | tuple[_PredicateType, ...],
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
                 _PredicateType,
-                list[_ObjectType] | tuple[_ObjectType],
+                list[_ObjectType] | tuple[_ObjectType, ...],
             ]
         ),
         context: _ContextType | None = None,

rdflib/plugins/parsers/jsonld.py

@@ -34,6 +34,7 @@
 # we should consider streaming the input to deal with arbitrarily large graphs.
 from __future__ import annotations
 
+import secrets
 import warnings
 from collections.abc import Iterable
 from typing import TYPE_CHECKING, Any, Union
@@ -215,6 +216,7 @@ def __init__(
             if allow_lists_of_lists is not None
             else ALLOW_LISTS_OF_LISTS
         )
+        self.invalid_uri_to_bnode: dict[str, BNode] = {}
 
     def parse(self, data: Any, context: Context, dataset: Graph) -> Graph:
         topcontext = False
@@ -623,7 +625,12 @@ def _to_rdf_id(self, context: Context, id_val: str) -> IdentifiedNode | None:
             uri = context.resolve(id_val)
             if not self.generalized_rdf and ":" not in uri:
                 return None
-            return URIRef(uri)
+            node: IdentifiedNode = URIRef(uri)
+            if not str(node):
+                if id_val not in self.invalid_uri_to_bnode:
+                    self.invalid_uri_to_bnode[id_val] = BNode(secrets.token_urlsafe(20))
+                node = self.invalid_uri_to_bnode[id_val]
+            return node
 
     def _get_bnodeid(self, ref: str) -> str | None:
         if not ref.startswith("_:"):

rdflib/plugins/serializers/longturtle.py

@@ -20,7 +20,9 @@
 
 from typing import IO, Any, Optional
 
+from rdflib.compare import to_canonical_graph
 from rdflib.exceptions import Error
+from rdflib.graph import Graph
 from rdflib.namespace import RDF
 from rdflib.term import BNode, Literal, URIRef
 
@@ -42,7 +44,16 @@ class LongTurtleSerializer(RecursiveSerializer):
 
     def __init__(self, store):
         self._ns_rewrite = {}
-        super(LongTurtleSerializer, self).__init__(store)
+        store = to_canonical_graph(store)
+        content = store.serialize(format="application/n-triples")
+        lines = content.split("\n")
+        lines.sort()
+        graph = Graph()
+        graph.parse(
+            data="\n".join(lines), format="application/n-triples", skolemize=True
+        )
+        graph = graph.de_skolemize()
+        super(LongTurtleSerializer, self).__init__(graph)
         self.keywords = {RDF.type: "a"}
         self.reset()
         self.stream = None
@@ -186,7 +197,7 @@ def s_squared(self, subject):
             return False
         self.write("\n" + self.indent() + "[]")
         self.predicateList(subject, newline=False)
-        self.write(" ;\n.")
+        self.write("\n.")
         return True
 
     def path(self, node, position, newline=False):
@@ -303,6 +314,8 @@ def objectList(self, objects):
         if count > 1:
             if not isinstance(objects[0], BNode):
                 self.write("\n" + self.indent(1))
+            else:
+                self.write(" ")
             first_nl = True
         self.path(objects[0], OBJECT, newline=first_nl)
         for obj in objects[1:]:

rdflib/plugins/sparql/parser.py

@@ -1483,7 +1483,7 @@ def expandCollection(terms: ParseResults) -> list[list[Any]]:
 AskQuery = Comp(
     "AskQuery",
     Keyword("ASK")
-    + Param("datasetClause", ZeroOrMore(DatasetClause))
+    + ZeroOrMore(ParamList("datasetClause", DatasetClause))
     + WhereClause
     + SolutionModifier
     + ValuesClause,

rdflib/plugins/stores/sparqlstore.py

@@ -408,19 +408,19 @@ def triples_choices(
         self,
         _: (
             tuple[
-                list[_SubjectType] | tuple[_SubjectType],
+                list[_SubjectType] | tuple[_SubjectType, ...],
                 _PredicateType,
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
-                list[_PredicateType] | tuple[_PredicateType],
+                list[_PredicateType] | tuple[_PredicateType, ...],
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
                 _PredicateType,
-                list[_ObjectType] | tuple[_ObjectType],
+                list[_ObjectType] | tuple[_ObjectType, ...],
             ]
         ),
         context: _ContextType | None = None,

rdflib/store.py

@@ -271,19 +271,19 @@ def triples_choices(
         self,
         triple: (
             tuple[
-                list[_SubjectType] | tuple[_SubjectType],
+                list[_SubjectType] | tuple[_SubjectType, ...],
                 _PredicateType,
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
-                list[_PredicateType] | tuple[_PredicateType],
+                list[_PredicateType] | tuple[_PredicateType, ...],
                 _ObjectType | None,
             ]
             | tuple[
                 _SubjectType | None,
                 _PredicateType,
-                list[_ObjectType] | tuple[_ObjectType],
+                list[_ObjectType] | tuple[_ObjectType, ...],
             ]
         ),
         context: _ContextType | None = None,
@@ -301,9 +301,9 @@ def triples_choices(
         time from the default 'fallback' implementation, which will iterate
         over each term in the list and dispatch to triples
         """
-        subject: _SubjectType | list[_SubjectType] | tuple[_SubjectType] | None
-        predicate: _PredicateType | list[_PredicateType] | tuple[_PredicateType]
-        object_: _ObjectType | list[_ObjectType] | tuple[_ObjectType] | None
+        subject: _SubjectType | list[_SubjectType] | tuple[_SubjectType, ...] | None
+        predicate: _PredicateType | list[_PredicateType] | tuple[_PredicateType, ...]
+        object_: _ObjectType | list[_ObjectType] | tuple[_ObjectType, ...] | None
         subject, predicate, object_ = triple
         if isinstance(object_, (list, tuple)):
             # MyPy thinks these are unreachable due to the triple pattern signature.

test/data/longturtle/longturtle-target.ttl

@@ -0,0 +1,72 @@
+PREFIX geo: <http://www.opengis.net/ont/geosparql#>
+PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX schema: <https://schema.org/>
+PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
+
+<http://example.com/nicholas>
+    a schema:Person ;
+    schema:age 41 ;
+    schema:alternateName 
+        [
+            schema:name "Dr N.J. Car" ;
+        ] ,
+        "N.J. Car" ,
+        "Nick Car" ;
+    schema:name
+        [
+            a <https://linked.data.gov.au/def/cn/CompoundName> ;
+            schema:hasPart 
+                [
+                    a <https://linked.data.gov.au/def/cn/CompoundName> ;
+                    schema:hasPart 
+                        [
+                            a <https://linked.data.gov.au/def/cn/CompoundName> ;
+                            rdf:value "Car" ;
+                        ] ,
+                        [
+                            a <https://linked.data.gov.au/def/cn/CompoundName> ;
+                            rdf:value "Maxov" ;
+                        ] ;
+                ] ,
+                [
+                    a <https://linked.data.gov.au/def/cn/CompoundName> ;
+                    rdf:value "Nicholas" ;
+                ] ,
+                [
+                    a <https://linked.data.gov.au/def/cn/CompoundName> ;
+                    rdf:value "John" ;
+                ] ;
+        ] ;
+    schema:worksFor <https://kurrawong.ai> ;
+.
+
+<https://kurrawong.ai>
+    a schema:Organization ;
+    schema:location <https://kurrawong.ai/hq> ;
+.
+
+<https://kurrawong.ai/hq>
+    a schema:Place ;
+    schema:address
+        [
+            a schema:PostalAddress ;
+            schema:addressCountry
+                [
+                    schema:identifier "au" ;
+                    schema:name "Australia" ;
+                ] ;
+            schema:addressLocality "Shorncliffe" ;
+            schema:addressRegion "QLD" ;
+            schema:postalCode 4017 ;
+            schema:streetAddress (
+                72
+                "Yundah"
+                "Street"
+            ) ;
+        ] ;
+    schema:geo
+        [
+            schema:polygon "POLYGON((153.082403 -27.325801, 153.08241 -27.32582, 153.082943 -27.325612, 153.083010 -27.325742, 153.083543 -27.325521, 153.083456 -27.325365, 153.082403 -27.325801))"^^geo:wktLiteral ;
+        ] ;
+    schema:name "KurrawongAI HQ" ;
+.

test/jsonld/local-suite/manifest.jsonld

@@ -27,6 +27,17 @@
       "purpose": "Multiple @id aliases.  Issue #2164",
       "input": "toRdf-twoimports-in.jsonld",
       "expect": "toRdf-twoimports-out.nq"
+    },
+    {
+      "@id": "#toRdf-two-invalid-ids",
+      "@type": ["jld:PositiveEvaluationTest", "jld:ToRDFTest"],
+      "name": "Two invalid identifiers",
+      "purpose": "Multiple nodes with invalid @ids are not merged together.",
+      "option": {
+        "produceGeneralizedRdf": true
+      },
+      "input": "toRdf-twoinvalidids-in.jsonld",
+      "expect": "toRdf-twoinvalidids-out.nq"
     }
   ]
 }