fix(export): @vocab mints into the shipped ns# namespace (#1236)

fix(export): keep caller data out of the shipped ns# namespace

Every JSON-LD context set @vocab to https://semantica.dev/vocab/,
which 404s, so every bare term in caller data (extracted entity/
relationship types, arbitrary metadata keys) minted under a namespace
the package never ships. The obvious fix, pointing @vocab at
SEMANTICA_NS instead, turned out to be worse than the dead link: since
that namespace is real and populated, every bare term a caller happens
to use now expands into something that looks like official Semantica
vocabulary. An extracted type "ORG" became ns#ORG, a class the
vocabulary never defines. A metadata key "source" attached a plain
string value to sem:source, an owl:ObjectProperty that already exists
in semantica-ns.ttl with a resource-valued range, silently corrupting
its semantics.

@vocab is now removed from all five contexts (four in
json_exporter.py, one in rdf_exporter.py) rather than repointed.
Every document already used explicit semantica: prefixes for its own
terms, so nothing else in the output changes; an unscoped bare term
now simply fails to expand, which is standard JSON-LD behavior for a
context that doesn't know it, instead of being silently claimed by
our namespace.

Two call sites needed to stop handing caller data to @type/bare terms
in the first place:

- Entity nodes are always typed semantica:Entity now, with the
  caller's label carried as a semantica:type string instead of
  minted into @type. This matches how relationship nodes already
  carried their type. sem:type's domain in semantica-ns.ttl opens up
  to cover entities as well as relationships, following the
  sem:confidence precedent, since the property is now legitimately
  emitted for both.
- semantica:metadata gets an explicit @json term definition, so a
  caller's metadata dict travels as one rdf:JSON literal instead of
  having its keys expand as separate predicates. A metadata key can
  no longer collide with a real ontology term no matter what the
  caller names it.

Both JSONExporter and RDFExporter.serialize_to_jsonld got the same
treatment, since they build separate JSON-LD structures for the same
underlying data.

The regression tests assert the negative space this bug lived in: no
context declares @vocab, no caller type label appears as an rdf:type
under ns#, and no caller metadata key appears as a predicate under
ns# at all, only as content inside the single JSON literal.

Closes #1146
This commit is contained in:
Kevin Zhang
2026-08-28 19:53:35 +05:00
committed by GitHub
parent 5376f046ca
commit da642f12fa
5 changed files with 173 additions and 21 deletions
+30 -11
View File
@@ -306,10 +306,10 @@ class JSONExporter:
self.logger.debug(f"Exporting {len(entities)} entity(ies) to JSON")
# Build JSON data with JSON-LD context
# Build JSON data with JSON-LD context. No @vocab: it would expand
# every bare key in the caller's entity dicts into ns# (#1146).
json_data = {
"@context": {
"@vocab": "https://semantica.dev/vocab/",
"semantica": SEMANTICA_NS,
"entities": {"@id": "semantica:entities", "@container": "@list"},
},
@@ -339,7 +339,6 @@ class JSONExporter:
"""
json_data = {
"@context": {
"@vocab": "https://semantica.dev/vocab/",
"semantica": SEMANTICA_NS,
"relationships": {
"@id": "semantica:relationships",
@@ -434,11 +433,14 @@ class JSONExporter:
Returns:
Dictionary in JSON-LD format with @context, @graph/@value, and metadata
"""
# Initialize JSON-LD structure with context
# Initialize JSON-LD structure with context. No @vocab: for a generic
# payload it turned whatever bare keys the caller happened to use into
# ns# terms (#1146). Undeclared terms now simply expand to nothing,
# which is standard JSON-LD behaviour for a context that does not
# know them; the raw payload is still in the document.
jsonld = {
"@context": {
"@vocab": "https://semantica.dev/vocab/",
"semantica": "https://semantica.dev/ns#",
"semantica": SEMANTICA_NS,
}
}
@@ -598,13 +600,21 @@ class JSONExporter:
Returns:
Dictionary in JSON-LD format with @context, @id, @type, and graph data
"""
# Initialize JSON-LD structure with RDF context
# Initialize JSON-LD structure with RDF context. No @vocab: it applied
# to every bare term in caller data, so an extracted type like "ORG"
# became ns#ORG and a metadata key like "source" collided with the
# real sem:source object property (#1146). Only explicit semantica:
# terms resolve now, and the caller's metadata dict is typed @json so
# it survives as one rdf:JSON literal instead of expanding its keys.
jsonld = {
"@context": {
"@vocab": "https://semantica.dev/vocab/",
"semantica": "https://semantica.dev/ns#",
"semantica": SEMANTICA_NS,
"rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
"rdfs": "http://www.w3.org/2000/01/rdf-schema#",
"semantica:metadata": {
"@id": "semantica:metadata",
"@type": "@json",
},
},
# Minted from the graph's own content rather than the wall clock
# (#1147): re-exporting an unchanged graph must produce the same
@@ -664,14 +674,23 @@ class JSONExporter:
entity_text = entity.get("text") or entity.get("label", "unknown")
entity_id = entity.get("id") or mint_entity_iri(entity_text)
# The caller's type label is data, not a class we define: minting it
# into @type expanded it through @vocab into ns#ORG and friends, terms
# that look official but do not exist (#1146). The node is always a
# semantica:Entity and the label travels as semantica:type, exactly
# how _relationship_to_jsonld has always carried the relationship type.
jsonld = {
"@id": entity_id,
"@type": entity.get("type") or "semantica:Entity",
"@type": "semantica:Entity",
"semantica:text": entity.get("text") or entity.get("label", ""),
"semantica:confidence": entity.get("confidence", 1.0),
}
entity_type = entity.get("type")
if entity_type:
jsonld["semantica:type"] = entity_type
# Add metadata if present
# Add metadata if present. The @json term definition on
# semantica:metadata keeps the whole dict one rdf:JSON literal.
if "metadata" in entity:
jsonld["semantica:metadata"] = entity["metadata"]
+16 -4
View File
@@ -1226,11 +1226,14 @@ class RDFSerializer:
metadata_terms = _resolve_metadata_terms(options.pop("metadata_terms", None))
graph_uri: Optional[str] = options.pop("graph_uri", None)
# Initialize JSON-LD structure with context
# Initialize JSON-LD structure with context. No @vocab: it applied to
# every bare term in caller data, so an extracted type like "ORG"
# became ns#ORG and a metadata key like "source" collided with the
# real sem:source object property (#1146). Only explicit semantica:
# terms resolve now.
jsonld = {
"@context": {
"@vocab": "https://semantica.dev/vocab/",
"semantica": "https://semantica.dev/ns#",
"semantica": SEMANTICA_NS,
"rdf": "http://www.w3.org/1999/02/22-rdf-syntax-ns#",
"rdfs": "http://www.w3.org/2000/01/rdf-schema#",
},
@@ -1252,11 +1255,20 @@ class RDFSerializer:
# and was dropped in full by a JSON-LD parser, silently.
entity_id = entity.get("id") or mint_entity_iri(entity.get("text", ""))
# The caller's type label is data, not a class we define: minting
# it into @type expanded it through @vocab into ns#ORG and
# friends, terms that look official but do not exist (#1146).
# The node is always a semantica:Entity and the label travels as
# semantica:type, matching the relationship node below and
# JSONExporter._entity_to_jsonld.
node = {
"@id": entity_id,
"@type": entity.get("type", "semantica:Entity"),
"@type": "semantica:Entity",
"semantica:text": entity.get("text") or entity.get("label", ""),
}
entity_type = entity.get("type")
if entity_type:
node["semantica:type"] = entity_type
confidence = normalize_confidence(entity.get("confidence", 1.0))
if confidence is None:
self.logger.warning(
@@ -70,7 +70,8 @@ sem:metadata a owl:AnnotationProperty ;
rdfs:label "metadata" ;
rdfs:comment """Free-form metadata carried through from extraction. An
annotation property because its value is an arbitrary structure rather than a
modelled one.""" ;
modelled one; in the JSON-LD export the whole mapping is written as one
rdf:JSON literal so caller keys never expand into this namespace (#1146).""" ;
rdfs:isDefinedBy <https://semantica.dev/ns> .
# ── Relationship terms (JSON-LD export) ──────────────────────────────────────
@@ -96,10 +97,10 @@ sem:target a owl:ObjectProperty ;
sem:type a owl:DatatypeProperty ;
rdfs:label "type" ;
rdfs:comment """The relationship type as a label, as emitted in the JSON-LD
export. Distinct from rdf:type, which relates a node to a class rather than to
a string.""" ;
rdfs:domain sem:Relationship ;
rdfs:comment """The entity or relationship type as a label, as emitted in
the JSON-LD export. Distinct from rdf:type, which relates a node to a class
rather than to a string. Emitted for both entities and relationships, so the
domain is left open rather than tied to sem:Relationship.""" ;
rdfs:range xsd:string ;
rdfs:isDefinedBy <https://semantica.dev/ns> .
+1 -1
View File
@@ -67,7 +67,7 @@ def test_merging_repeated_exports_yields_one_graph_node(tmp_path):
assert len(kg_nodes) == 1
entity_nodes = set(
merged.subjects(RDF.type, URIRef("https://semantica.dev/vocab/ORG"))
merged.subjects(RDF.type, URIRef("https://semantica.dev/ns#Entity"))
)
assert len(entity_nodes) == 1
+120
View File
@@ -0,0 +1,120 @@
"""Caller data must never expand into the Semantica namespace (#1146).
``@vocab`` used to sit in every JSON-LD context pointing at ``ns#``, so every
bare term in caller data expanded into it: an extracted type like ``"ORG"``
became ``ns#ORG`` (a term the vocabulary does not define), and a metadata key
like ``"source"`` collided with the real ``sem:source`` object property,
attaching a plain string to a property whose range is a resource. The fix
removes ``@vocab`` outright: only explicit ``semantica:``-prefixed terms
resolve, caller type labels travel as ``semantica:type`` strings, and caller
metadata survives as one ``rdf:JSON`` literal.
"""
import json
from rdflib import RDF, Graph, Literal, URIRef
from semantica.export.json_exporter import JSONExporter
from semantica.export.rdf_exporter import RDFExporter, SEMANTICA_NS
NS = SEMANTICA_NS
E1 = "https://example.org/e1"
KG = {
"entities": [
{
"id": E1,
"text": "Acme",
"type": "ORG",
"metadata": {"source": "crm_export_2024"},
}
],
"relationships": [
{
"source_id": E1,
"target_id": "https://example.org/e2",
"type": "employs",
}
],
}
def _jsonld_file(exporter, kind, tmp_path, name):
path = tmp_path / name
if kind == "knowledge_graph":
exporter.export_knowledge_graph(KG, path, format="json-ld")
elif kind == "entities":
exporter.export_entities(KG["entities"], path, format="json-ld")
elif kind == "relationships":
exporter.export_relationships(KG["relationships"], path, format="json-ld")
elif kind == "generic":
exporter.export({"note": "plain payload, no @id"}, path, format="json-ld")
else:
raise AssertionError(kind)
return json.loads(path.read_text())
def test_no_jsonld_context_declares_a_vocab(tmp_path):
exporter = JSONExporter()
for kind in ("knowledge_graph", "entities", "relationships", "generic"):
context = _jsonld_file(exporter, kind, tmp_path, f"{kind}.jsonld")[
"@context"
]
assert "@vocab" not in context, f"{kind}: @vocab expands caller data"
context = json.loads(RDFExporter().export_to_rdf(KG, format="jsonld"))[
"@context"
]
assert "@vocab" not in context
def test_extracted_type_labels_stay_out_of_the_namespace(tmp_path):
path = tmp_path / "kg.jsonld"
JSONExporter().export_knowledge_graph(KG, path, format="json-ld")
graph = Graph()
graph.parse(str(path), format="json-ld")
assert (None, RDF.type, URIRef(NS + "ORG")) not in graph, (
"the caller's type label was minted as a class in ns#"
)
assert (URIRef(E1), RDF.type, URIRef(NS + "Entity")) in graph
assert (URIRef(E1), URIRef(NS + "type"), Literal("ORG")) in graph, (
"the label itself must survive, as a string"
)
def test_metadata_keys_stay_out_of_the_namespace(tmp_path):
path = tmp_path / "kg.jsonld"
JSONExporter().export_knowledge_graph(KG, path, format="json-ld")
graph = Graph()
graph.parse(str(path), format="json-ld")
assert (None, URIRef(NS + "source"), Literal("crm_export_2024")) not in (
graph
), "caller metadata value attached to the real sem:source object property"
for _, _, o in graph.triples((None, URIRef(NS + "source"), None)):
assert not isinstance(o, Literal), (
"sem:source has a resource range but received a plain literal"
)
literals = [
o
for o in graph.objects(None, URIRef(NS + "metadata"))
if isinstance(o, Literal)
]
assert literals, "the metadata dict was dropped instead of preserved"
assert literals[0].datatype == RDF.JSON
assert json.loads(str(literals[0])) == {"source": "crm_export_2024"}
def test_rdf_exporter_jsonld_keeps_type_labels_out_of_the_namespace():
graph = Graph()
graph.parse(
data=RDFExporter().export_to_rdf(KG, format="jsonld"), format="json-ld"
)
assert (None, RDF.type, URIRef(NS + "ORG")) not in graph
assert (URIRef(E1), RDF.type, URIRef(NS + "Entity")) in graph
assert (URIRef(E1), URIRef(NS + "type"), Literal("ORG")) in graph