Issue 1003

rdflib/graph.py

@@ -293,8 +293,9 @@ class Graph(Node):
     For more on named graphs, see: http://www.w3.org/2004/03/trix/
     """
 
-    def __init__(self, store="default", identifier=None, namespace_manager=None):
+    def __init__(self, store="default", identifier=None, namespace_manager=None, base=None):
         super(Graph, self).__init__()
+        self.base = base
         self.__identifier = identifier or BNode()
 
         if not isinstance(self.__identifier, Node):
@@ -952,6 +953,11 @@ def serialize(
         Format support can be extended with plugins,
         but "xml", "n3", "turtle", "nt", "pretty-xml", "trix", "trig" and "nquads" are built in.
         """
+
+        # if base is not given as attribute use the base set for the graph
+        if base is None:
+            base = self.base
+
         serializer = plugin.get(format, Serializer)(self)
         if destination is None:
             stream = BytesIO()
@@ -1336,14 +1342,16 @@ class ConjunctiveGraph(Graph):
     All queries are carried out against the union of all graphs.
     """
 
-    def __init__(self, store="default", identifier=None):
+    def __init__(self, store="default", identifier=None, default_graph_base=None):
         super(ConjunctiveGraph, self).__init__(store, identifier=identifier)
         assert self.store.context_aware, (
             "ConjunctiveGraph must be backed by" " a context aware store."
         )
         self.context_aware = True
         self.default_union = True  # Conjunctive!
-        self.default_context = Graph(store=self.store, identifier=identifier or BNode())
+        self.default_context = Graph(
+            store=self.store, identifier=identifier or BNode(), base=default_graph_base
+        )
 
     def __str__(self):
         pattern = (
@@ -1483,12 +1491,12 @@ def contexts(self, triple=None):
             else:
                 yield self.get_context(context)
 
-    def get_context(self, identifier, quoted=False):
+    def get_context(self, identifier, quoted=False, base=None):
         """Return a context graph for the given identifier
 
         identifier must be a URIRef or BNode.
         """
-        return Graph(store=self.store, identifier=identifier, namespace_manager=self)
+        return Graph(store=self.store, identifier=identifier, namespace_manager=self, base=base)
 
     def remove_context(self, context):
         """Removes the given context from the graph"""
@@ -1651,13 +1659,13 @@ class Dataset(ConjunctiveGraph):
     .. versionadded:: 4.0
     """
 
-    def __init__(self, store="default", default_union=False):
+    def __init__(self, store="default", default_union=False, default_graph_base=None):
         super(Dataset, self).__init__(store=store, identifier=None)
 
         if not self.store.graph_aware:
             raise Exception("DataSet must be backed by a graph-aware store!")
         self.default_context = Graph(
-            store=self.store, identifier=DATASET_DEFAULT_GRAPH_ID
+            store=self.store, identifier=DATASET_DEFAULT_GRAPH_ID, base=default_graph_base
         )
 
         self.default_union = default_union
@@ -1668,7 +1676,7 @@ def __str__(self):
         )
         return pattern % self.store.__class__.__name__
 
-    def graph(self, identifier=None):
+    def graph(self, identifier=None, base=None):
         if identifier is None:
             from rdflib.term import rdflib_skolem_genid
 
@@ -1678,6 +1686,7 @@ def graph(self, identifier=None):
             identifier = BNode().skolemize()
 
         g = self._graph(identifier)
+        g.base = base
 
         self.store.add_graph(g)
         return g

rdflib/plugins/serializers/rdfxml.py

@@ -46,7 +46,11 @@ def __bindings(self):
             yield prefix, namespace
 
     def serialize(self, stream, base=None, encoding=None, **args):
-        self.base = base
+        # if base is given here, use that, if not and a base is set for the graph use that
+        if base is not None:
+            self.base = base
+        elif self.store.base is not None:
+            self.base = self.store.base
         self.__stream = stream
         self.__serialized = {}
         encoding = self.encoding
@@ -62,6 +66,8 @@ def serialize(self, stream, base=None, encoding=None, **args):
         # If provided, write xml:base attribute for the RDF
         if "xml_base" in args:
             write('   xml:base="%s"\n' % args['xml_base'])
+        elif self.base:
+            write('   xml:base="%s"\n' % self.base)
         # TODO:
         # assert(
         #    namespaces["http://www.w3.org/1999/02/22-rdf-syntax-ns#"]=='rdf')
@@ -163,7 +169,11 @@ def __init__(self, store, max_depth=3):
     def serialize(self, stream, base=None, encoding=None, **args):
         self.__serialized = {}
         store = self.store
-        self.base = base
+        # if base is given here, use that, if not and a base is set for the graph use that
+        if base is not None:
+            self.base = base
+        elif store.base is not None:
+            self.base = store.base
         self.max_depth = args.get("max_depth", 3)
         assert self.max_depth > 0, "max_depth must be greater than 0"
 
@@ -184,6 +194,8 @@ def serialize(self, stream, base=None, encoding=None, **args):
 
         if "xml_base" in args:
             writer.attribute(XMLBASE, args["xml_base"])
+        elif self.base:
+            writer.attribute(XMLBASE, self.base)
 
         writer.namespaces(namespaces.items())
 

rdflib/plugins/serializers/trig.py

@@ -39,7 +39,7 @@ def preprocess(self):
             for triple in context:
                 self.preprocessTriple(triple)
 
-            self._contexts[context]=(self.orderSubjects(), self._subjects, self._references)
+            self._contexts[context] = (self.orderSubjects(), self._subjects, self._references)
 
     def reset(self):
         super(TrigSerializer, self).reset()
@@ -49,7 +49,11 @@ def serialize(self, stream, base=None, encoding=None,
                   spacious=None, **args):
         self.reset()
         self.stream = stream
-        self.base = base
+        # if base is given here, use that, if not and a base is set for the graph use that
+        if base is not None:
+            self.base = base
+        elif self.store.base is not None:
+            self.base = self.store.base
 
         if spacious is not None:
             self._spacious = spacious

rdflib/plugins/serializers/trix.py

@@ -29,6 +29,11 @@ def serialize(self, stream, base=None, encoding=None, **args):
         self.writer = XMLWriter(stream, nm, encoding, extra_ns={"": TRIXNS})
 
         self.writer.push(TRIXNS[u"TriX"])
+        # if base is given here, use that, if not and a base is set for the graph use that
+        if base is None and self.store.base is not None:
+            base = self.store.base
+        if base is not None:
+            self.writer.attribute("http://www.w3.org/XML/1998/namespacebase", base)
         self.writer.namespaces()
 
         if isinstance(self.store, ConjunctiveGraph):
@@ -44,6 +49,8 @@ def serialize(self, stream, base=None, encoding=None, **args):
 
     def _writeGraph(self, graph):
         self.writer.push(TRIXNS[u"graph"])
+        if graph.base:
+            self.writer.attribute("http://www.w3.org/XML/1998/namespacebase", graph.base)
         if isinstance(graph.identifier, URIRef):
             self.writer.element(
                 TRIXNS[u"uri"], content=text_type(graph.identifier))

rdflib/plugins/serializers/turtle.py

@@ -224,7 +224,11 @@ def serialize(self, stream, base=None, encoding=None,
                   spacious=None, **args):
         self.reset()
         self.stream = stream
-        self.base = base
+        # if base is given here, use that, if not and a base is set for the graph use that
+        if base is not None:
+            self.base = base
+        elif self.store.base is not None:
+            self.base = self.store.base
 
         if spacious is not None:
             self._spacious = spacious
@@ -246,6 +250,8 @@ def serialize(self, stream, base=None, encoding=None,
         self.endDocument()
         stream.write(b("\n"))
 
+        self.base = None
+
     def preprocessTriple(self, triple):
         super(TurtleSerializer, self).preprocessTriple(triple)
         for i, node in enumerate(triple):
@@ -291,6 +297,9 @@ def getQName(self, uri, gen_prefix=True):
     def startDocument(self):
         self._started = True
         ns_list = sorted(self.namespaces.items())
+
+        if self.base:
+            self.write(self.indent() + '@base <%s> .\n' % self.base)
         for prefix, uri in ns_list:
             self.write(self.indent() + '@prefix %s: <%s> .\n' % (prefix, uri))
         if ns_list and self._spacious:

test/test_issue1003.py

@@ -0,0 +1,117 @@
+from rdflib import Graph, Dataset, Literal, Namespace, RDF, URIRef
+from rdflib.namespace import SKOS, DCTERMS
+
+"""
+Testing scenarios:
+    1. no base set
+    2. base set at graph creation
+    3. base set at serialization
+    4. base set at both graph creation & serialization, serialization overrides
+    5. multiple serialization side effect checking
+    6. checking results for RDF/XML
+    7. checking results for N3
+    8. checking results for TriX & TriG
+"""
+
+# variables
+base_one = Namespace("http://one.org/")
+base_two = Namespace("http://two.org/")
+title = Literal("Title", lang="en")
+description = Literal("Test Description", lang="en")
+creator = URIRef("https://creator.com")
+cs = URIRef("")
+
+# starting graph
+g = Graph()
+g.add((cs, RDF.type, SKOS.ConceptScheme))
+g.add((cs, DCTERMS.creator, creator))
+g.add((cs, DCTERMS.source, URIRef("nick")))
+g.bind("dct", DCTERMS)
+g.bind("skos", SKOS)
+
+
+# 1. no base set for graph, no base set for serialization
+g1 = Graph()
+g1 += g
+# @base should not be in output
+assert "@base" not in g.serialize(format='turtle').decode("utf-8")
+
+
+# 2. base one set for graph, no base set for serialization
+g2 = Graph(base=base_one)
+g2 += g
+# @base should be in output, from Graph (one)
+assert "@base <http://one.org/> ." in g2.serialize(format='turtle').decode("utf-8")
+
+
+# 3. no base set for graph, base two set for serialization
+g3 = Graph()
+g3 += g
+# @base should be in output, from serialization (two)
+assert "@base <http://two.org/> ." in g3.serialize(format='turtle', base=base_two).decode("utf-8")
+
+
+# 4. base one set for graph, base two set for serialization, Graph one overrides
+g4 = Graph(base=base_one)
+g4 += g
+# @base should be in output, from graph (one)
+assert "@base <http://two.org/> ." in g4.serialize(format='turtle', base=base_two).decode("utf-8")
+# just checking that the serialization setting (two) hasn't snuck through
+assert "@base <http://one.org/> ." not in g4.serialize(format='turtle', base=base_two).decode("utf-8")
+
+
+# 5. multiple serialization side effect checking
+g5 = Graph()
+g5 += g
+# @base should be in output, from serialization (two)
+assert "@base <http://two.org/> ." in g5.serialize(format='turtle', base=base_two).decode("utf-8")
+
+# checking for side affects - no base now set for this serialization
+# @base should not be in output
+assert "@base" not in g5.serialize(format='turtle').decode("utf-8")
+
+
+# 6. checking results for RDF/XML
+g6 = Graph()
+g6 += g
+g6.bind("dct", DCTERMS)
+g6.bind("skos", SKOS)
+assert "@xml:base" not in g6.serialize(format='xml').decode("utf-8")
+assert 'xml:base="http://one.org/"' in g6.serialize(format='xml', base=base_one).decode("utf-8")
+g6.base = base_two
+assert 'xml:base="http://two.org/"' in g6.serialize(format='xml').decode("utf-8")
+assert 'xml:base="http://one.org/"' in g6.serialize(format='xml', base=base_one).decode("utf-8")
+
+# 7. checking results for N3
+g7 = Graph()
+g7 += g
+g7.bind("dct", DCTERMS)
+g7.bind("skos", SKOS)
+assert "@xml:base" not in g7.serialize(format='xml').decode("utf-8")
+assert "@base <http://one.org/> ." in g7.serialize(format='n3', base=base_one).decode("utf-8")
+g7.base = base_two
+assert "@base <http://two.org/> ." in g7.serialize(format='n3').decode("utf-8")
+assert "@base <http://one.org/> ." in g7.serialize(format='n3', base=base_one).decode("utf-8")
+
+# 8. checking results for TriX & TriG
+# TriX can specify a base per graph but setting a base for the whole
+base_three = Namespace("http://three.org/")
+ds1 = Dataset()
+ds1.bind("dct", DCTERMS)
+ds1.bind("skos", SKOS)
+g8 = ds1.graph(URIRef('http://g8.com/'), base=base_one)
+g9 = ds1.graph(URIRef('http://g9.com/'))
+g8 += g
+g9 += g
+g9.base = base_two
+ds1.base = base_three
+
+trix = ds1.serialize(format='trix', base=Namespace("http://two.org/")).decode("utf-8")
+assert '<graph xml:base="http://one.org/">' in trix
+assert '<graph xml:base="http://two.org/">' in trix
+assert '<TriX xml:base="http://two.org/"' in trix
+
+trig = ds1.serialize(format='trig', base=Namespace("http://two.org/")).decode("utf-8")
+assert '@base <http://one.org/> .' not in trig
+assert '@base <http://three.org/> .' not in trig
+assert '@base <http://two.org/> .' in trig