Merge pull request #1489 from RDFLib/hextuples

Hextuples Serializer

.flake8

@@ -4,3 +4,5 @@ extend-ignore =
     # E501: line too long
     # Disabled so that black can control line length.
     E501,
+    # Ignored since this is soon not going to be considered an error, see https://www.flake8rules.com/rules/W503.html
+    W503,

docs/plugin_parsers.rst

@@ -13,24 +13,35 @@ The ``html`` parser will auto-detect RDFa, HTurtle or Microdata.
 
 It is also possible to pass a mime-type for the ``format`` parameter::
     
-  graph.parse(my_url, format='application/rdf+xml')
+	graph.parse(my_url, format='application/rdf+xml')
 
 If you are not sure what format your file will be, you can use :func:`rdflib.util.guess_format` which will guess based on the file extension. 
 
 ========= ====================================================================
 Name      Class                                                               
 ========= ====================================================================
+json-ld   :class:`~rdflib.plugins.parsers.jsonld.JsonLDParser`
+hext      :class:`~rdflib.plugins.parsers.hext.HextuplesParser`
 html      :class:`~rdflib.plugins.parsers.structureddata.StructuredDataParser`
-hturtle   :class:`~rdflib.plugins.parsers.hturtle.HTurtleParser`
-mdata     :class:`~rdflib.plugins.parsers.structureddata.MicrodataParser`
-microdata :class:`~rdflib.plugins.parsers.structureddata.MicrodataParser`
 n3        :class:`~rdflib.plugins.parsers.notation3.N3Parser`
 nquads    :class:`~rdflib.plugins.parsers.nquads.NQuadsParser`
 nt        :class:`~rdflib.plugins.parsers.ntriples.NTParser`
-rdfa      :class:`~rdflib.plugins.parsers.structureddata.RDFaParser`
-rdfa1.0   :class:`~rdflib.plugins.parsers.structureddata.RDFa10Parser`
-rdfa1.1   :class:`~rdflib.plugins.parsers.structureddata.RDFaParser`
 trix      :class:`~rdflib.plugins.parsers.trix.TriXParser`
 turtle    :class:`~rdflib.plugins.parsers.notation3.TurtleParser`
 xml       :class:`~rdflib.plugins.parsers.rdfxml.RDFXMLParser`
 ========= ====================================================================
+
+Multi-graph IDs
+---------------
+Note that for correct parsing of multi-graph data, e.g. Trig, HexT, etc., into a ``ConjunctiveGraph`` or a ``Dataset``,
+as opposed to a context-unaware ``Graph``, you will need to set the ``publicID`` of the ``ConjunctiveGraph`` a 
+``Dataset`` to the identifier of the ``default_context`` (default graph), for example::
+
+    d = Dataset()
+    d.parse(
+        data=""" ... """, 
+        format="trig", 
+        publicID=d.default_context.identifier
+    )
+
+(from the file tests/test_serializer_hext.py)

docs/plugin_serializers.rst

@@ -11,18 +11,35 @@ passing the name to a graph's :meth:`~rdflib.graph.Graph.serialize` method::
 
 It is also possible to pass a mime-type for the ``format`` parameter::
     
-  graph.serialize(my_url, format='application/rdf+xml')
+	graph.serialize(my_url, format='application/rdf+xml')
 
 ========== ===============================================================
 Name       Class                                                          
 ========== ===============================================================
+json-ld    :class:`~rdflib.plugins.serializers.jsonld.JsonLDSerializer`
 n3         :class:`~rdflib.plugins.serializers.n3.N3Serializer`
 nquads     :class:`~rdflib.plugins.serializers.nquads.NQuadsSerializer`
 nt         :class:`~rdflib.plugins.serializers.nt.NTSerializer`
+hext       :class:`~rdflib.plugins.serializers.hext.HextuplesSerializer`
 pretty-xml :class:`~rdflib.plugins.serializers.rdfxml.PrettyXMLSerializer`
 trig       :class:`~rdflib.plugins.serializers.trig.TrigSerializer`
 trix       :class:`~rdflib.plugins.serializers.trix.TriXSerializer`
 turtle     :class:`~rdflib.plugins.serializers.turtle.TurtleSerializer`
+longturtle :class:`~rdflib.plugins.serializers.turtle.LongTurtleSerializer`
 xml        :class:`~rdflib.plugins.serializers.rdfxml.XMLSerializer`
 ========== ===============================================================
 
+
+JSON-LD
+-------
+JSON-LD - 'json-ld' - has been incorprated in rdflib since v6.0.0.
+
+HexTuples
+---------
+The HexTuples Serializer - 'hext' - uses the HexTuples format defined at https://github.com/ontola/hextuples.
+
+For serialization of non-context-aware data sources, e.g. a single ``Graph``, the 'graph' field (6th variable in the 
+Hextuple) will be an empty string.
+
+For context-aware (multi-graph) serialization, the 'graph' field of the default graph will be an empty string and 
+the values for other graphs will be Blank Node IDs or IRIs.

rdflib/__init__.py

@@ -45,7 +45,7 @@
 __docformat__ = "restructuredtext en"
 
 # The format of the __version__ line is matched by a regex in setup.py
-__version__ = "6.03a"
+__version__ = "6.0.3"
 __date__ = "2021-10-10"
 
 __all__ = [

rdflib/compare.py

@@ -428,7 +428,6 @@ def _traces(
         candidates = self._get_candidates(coloring)
         best: List[List[Color]] = []
         best_score = None
-        best_experimental = None
         best_experimental_score = None
         last_coloring = None
         generator: Dict[Node, Set[Node]] = defaultdict(set)

rdflib/namespace/__init__.py

@@ -81,7 +81,6 @@
 
 __all__ = ["is_ncname", "split_uri", "Namespace", "ClosedNamespace", "NamespaceManager"]
 
-
 logger = logging.getLogger(__name__)
 
 
@@ -192,7 +191,7 @@ def __getitem__(cls, name, default=None):
         name = str(name)
         if str(name).startswith("__"):
             return super().__getitem__(name, default)
-        if (cls._warn or cls._fail) and not name in cls:
+        if (cls._warn or cls._fail) and name not in cls:
             if cls._fail:
                 raise AttributeError(f"term '{name}' not in namespace '{cls._NS}'")
             else:

rdflib/parser.py

@@ -341,8 +341,7 @@ def create_input_source(
             input_source = StringInputSource(data)
             auto_close = True
         else:
-            raise RuntimeError(
-                f"parse data can only str, or bytes. not: {type(data)}")
+            raise RuntimeError(f"parse data can only str, or bytes. not: {type(data)}")
 
     if input_source is None:
         raise Exception("could not create InputSource")