fix: issue with trig reference counting across graphs (#2085)

The TriG serializer was only considering BNode references inside a single
graph and not counting the BNodes subjects as references when considering if a
BNode should be serialized as unlabeled blank nodes (i.e. `[ ]`), and as a
result it was serializing BNodes as unlabeled if they were in fact referencing
BNodes in other graphs.

One caveat of this change is that some RDF Datasets may be serialized
less succinctly in that unlabeled blank nodes would not be used nodes where it is
technically possible to use them. This can be trivially fixed, but a trivial fix
increases the computational complexity of serialization significantly.

Other changes:
- Removed the roundtrip xfail that this change fixed.
- Added another roundtrip test which has various combinations of BNode
  references across graphs in a dataset, this test fails for JSON-LD
  however, so while this change removes one xfail it also now adds
  another.
- Set the default indent_size and style in `.editorconfig` as to avoid
  relying on undefined system defaults.

Author: aucampia

.editorconfig

@@ -6,6 +6,8 @@ root = true
 
 # Unix-style newlines with a newline ending every file
 [*]
+indent_size = 4
+indent_style = space
 end_of_line = lf
 insert_final_newline = true
 trim_trailing_whitespace = true

CHANGELOG.md

@@ -309,6 +309,27 @@ and will be removed for release.
 <!-- -->
 <!-- -->
 
+
+<!-- -->
+<!-- -->
+<!-- CHANGE BARRIER: START PR #2085 -->
+<!-- -->
+<!-- -->
+
+- Fixed serialization of BNodes in TriG.
+  The TriG serializer was only considering BNode references inside a single
+  graph and not counting the BNodes subjects as references when considering if a
+  BNode should be serialized as unlabeled blank nodes (i.e. `[ ]`), and as a
+  result it was serializing BNodes as unlabeled if they were in fact referencing
+  BNodes in other graphs.
+  [PR #2085](https://github.com/RDFLib/rdflib/pull/2085).
+
+<!-- -->
+<!-- -->
+<!-- CHANGE BARRIER: END PR #2085 -->
+<!-- -->
+<!-- -->
+
 <!-- -->
 <!-- -->
 <!-- CHANGE BARRIER: START -->

Taskfile.yml

@@ -282,6 +282,11 @@ tasks:
       - task: install:flake8
       - task: flake8
 
+  cmd:rdfpipe:
+    desc: Run rdfpipe
+    cmds:
+      - cmd: "{{._PYTHON | shellQuote}} -m rdflib.tools.rdfpipe {{.CLI_ARGS}}"
+
   _rimraf:
     # This task is a utility task for recursively removing directories, it is
     # similar to rm -rf but not identical and it should work wherever there is

rdflib/plugins/serializers/trig.py

@@ -3,7 +3,6 @@
 See <http://www.w3.org/TR/trig/> for syntax specification.
 """
 
-from collections import defaultdict
 from typing import IO, TYPE_CHECKING, Optional, Union
 
 from rdflib.graph import ConjunctiveGraph, Graph
@@ -37,17 +36,15 @@ def preprocess(self):
         for context in self.contexts:
             self.store = context
             self.getQName(context.identifier)
-            self._references = defaultdict(int)
             self._subjects = {}
 
             for triple in context:
                 self.preprocessTriple(triple)
 
-            self._contexts[context] = (
-                self.orderSubjects(),
-                self._subjects,
-                self._references,
-            )
+            for subject in self._subjects.keys():
+                self._references[subject] += 1
+
+            self._contexts[context] = (self.orderSubjects(), self._subjects)
 
     def reset(self):
         super(TrigSerializer, self).reset()
@@ -77,11 +74,10 @@ def serialize(
         self.startDocument()
 
         firstTime = True
-        for store, (ordered_subjects, subjects, ref) in self._contexts.items():
+        for store, (ordered_subjects, subjects) in self._contexts.items():
             if not ordered_subjects:
                 continue
 
-            self._references = ref
             self._serialized = {}
             self.store = store
             self._subjects = subjects

test/data/roundtrip/bnode_refs.trig

@@ -0,0 +1,71 @@
+@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
+@prefix dc: <http://purl.org/dc/terms/> .
+@prefix foaf: <http://xmlns.com/foaf/0.1/> .
+@prefix egdo: <http://example.org/> .
+
+{
+    egdo:bob dc:publisher "Bob" .
+    egdo:alice dc:publisher "Alice" .
+}
+
+
+egdo:alice {
+    _:alice foaf:name "Alice";
+        foaf:mbox <mailto:alice@work.example.org> .
+}
+
+egdo:bob {
+    _:bob foaf:name "Bob";
+        foaf:mbox <mailto:bob@oldcorp.example.org>;
+        foaf:knows _:alice .
+}
+
+
+egdo:blake {
+    [] foaf:name "Blake" ;
+        foaf:mbox <mailto:blake@oldcorp.example.org>;
+        foaf:knows [
+            foaf:name "Taylor";
+            foaf:mbox <mailto:taylor@work.example.org>
+        ] .
+}
+
+egdo:austin {
+    _:austin foaf:name "Austin" ;
+        foaf:mbox <mailto:austin@oldcorp.example.org>;
+        foaf:knows _:carson.
+
+
+    _:carson foaf:name "Carson" ;
+        foaf:mbox <mailto:carson@oldcorp.example.org>;
+        foaf:knows _:austin.
+}
+
+egdo:charlie {
+    _:charlie foaf:name "Charlie" ;
+        foaf:mbox <mailto:charlie@oldcorp.example.org>;
+        foaf:knows _:dylan;
+        foaf:knows _:greer.
+
+    _:dylan foaf:name "Dylan" ;
+        foaf:mbox <mailto:dylan@oldcorp.example.org>;
+        foaf:knows _:charlie;
+        foaf:knows _:greer.
+
+    _:greer foaf:name "Greer" ;
+        foaf:mbox <mailto:greer@oldcorp.example.org>;
+        foaf:knows _:charlie;
+        foaf:knows _:dylan.
+}
+
+egdo:jaime {
+    _:jaime foaf:name "Jaime";
+        foaf:mbox <mailto:jaime@work.example.org>;
+        foaf:knows _:keaton.
+}
+
+egdo:kennedy {
+    _:kennedy foaf:name "Kennedy";
+        foaf:mbox <mailto:kennedy@oldcorp.example.org>;
+        foaf:knows _:keaton .
+}

test/test_roundtrip.py

@@ -144,28 +144,6 @@
         reason="results in invalid xml element name: <ns1:name(s)/>",
         raises=SAXParseException,
     ),
-    ("trig", "rdf11trig_eg2.trig"): pytest.mark.xfail(
-        reason="""
-    Something is going wrong here with blank node serialization. In the second
-    graph below bob knows someone who does not exist, while in first he knows
-    someone that does exist and has the name Alice.
-
-    AssertionError: in both:
-        (rdflib.term.BNode('cbb5eb12b5dcf688537b0298cce144c6dd68cf047530d0b4a455a8f31f314244fd'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/mbox'), rdflib.term.URIRef('mailto:alice@work.example.org'))
-        (rdflib.term.BNode('cbb5eb12b5dcf688537b0298cce144c6dd68cf047530d0b4a455a8f31f314244fd'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/name'), rdflib.term.Literal('Alice'))
-        (rdflib.term.URIRef('http://example.org/alice'), rdflib.term.URIRef('http://purl.org/dc/terms/publisher'), rdflib.term.Literal('Alice'))
-        (rdflib.term.URIRef('http://example.org/bob'), rdflib.term.URIRef('http://purl.org/dc/terms/publisher'), rdflib.term.Literal('Bob'))
-    only in first:
-        (rdflib.term.BNode('cb0'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/knows'), rdflib.term.BNode('cbb5eb12b5dcf688537b0298cce144c6dd68cf047530d0b4a455a8f31f314244fd'))
-        (rdflib.term.BNode('cb0'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/mbox'), rdflib.term.URIRef('mailto:bob@oldcorp.example.org'))
-        (rdflib.term.BNode('cb0'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/name'), rdflib.term.Literal('Bob'))
-    only in second:
-        (rdflib.term.BNode('cb7be1d0397a49ddd4ae8aa96acc7b6135903c5f3fa5e47bf619c0e4b438aafcc1'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/knows'), rdflib.term.BNode('cb0'))
-        (rdflib.term.BNode('cb7be1d0397a49ddd4ae8aa96acc7b6135903c5f3fa5e47bf619c0e4b438aafcc1'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/mbox'), rdflib.term.URIRef('mailto:bob@oldcorp.example.org'))
-        (rdflib.term.BNode('cb7be1d0397a49ddd4ae8aa96acc7b6135903c5f3fa5e47bf619c0e4b438aafcc1'), rdflib.term.URIRef('http://xmlns.com/foaf/0.1/name'), rdflib.term.Literal('Bob'))
-        """,
-        raises=AssertionError,
-    ),
     ("json-ld", "diverse_quads.trig"): pytest.mark.xfail(
         reason="""
     jsonld serializer is dropping datatype:
@@ -204,6 +182,10 @@
         "n3",
         "data/suites/w3c/n3/N3Tests/cwm_syntax/neg-single-quote.n3",
     ): pytest.mark.xfail(raises=BadSyntax, reason="no support for single quotes"),
+    ("json-ld", "bnode_refs.trig"): pytest.mark.xfail(
+        reason="a whole bunch of triples with bnode as subject is not in the reconstituted graph",
+        raises=AssertionError,
+    ),
 }
 
 # This is for files which can only be represented properly in one format
@@ -253,7 +235,13 @@ def roundtrip(
     s = g1.serialize(format=testfmt)
 
     if logger.isEnabledFor(logging.DEBUG):
-        logger.debug("source = %s, serailized = \n%s", source, s)
+        logger.debug(
+            "infmt = %s, testfmt = %s, source = %s, serailized = \n%s",
+            infmt,
+            testfmt,
+            source,
+            s,
+        )
 
     g2 = graph_type()
     if same_public_id:
@@ -525,6 +513,7 @@ def test_n3_suite(
     (TEST_DATA_DIR / "variants" / "diverse_triples.nt", "ntriples"),
     (TEST_DATA_DIR / "variants" / "diverse_quads.nq", "nquads"),
     (TEST_DATA_DIR / "variants" / "diverse_quads.trig", "trig"),
+    (TEST_DATA_DIR / "roundtrip" / "bnode_refs.trig", "trig"),
     (TEST_DATA_DIR / "example-lots_of_graphs.n3", "n3"),
     (TEST_DATA_DIR / "issue156.n3", "n3"),
 ]