jsonld: Do not merge nodes with different invalid URIs (#3011)

When parsing JSON-LD with invalid URIs in the `@id`, the
`generalized_rdf: True` option allows parsing these nodes as blank nodes
instead of outright rejecting the document.

However, all nodes with invalid URIs were mapped to the same blank node,
resulting in incorrect data. For example, without this patch, the new test
fails with:

```
AssertionError: Expected:
@Prefix schema: <https://schema.org/> .

<https://example.org/root-object> schema:author [ schema:familyName "Doe" ;
            schema:givenName "Jane" ;
            schema:name "Jane Doe" ],
        [ schema:familyName "Doe" ;
            schema:givenName "John" ;
            schema:name "John Doe" ] .

Got:
@Prefix schema: <https://schema.org/> .

<https://example.org/root-object> schema:author <> .

<> schema:familyName "Doe" ;
    schema:givenName "Jane",
        "John" ;
    schema:name "Jane Doe",
        "John Doe" .
```

Author: progval

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 typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
 
@@ -221,6 +222,7 @@ 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
@@ -629,7 +631,12 @@ def _to_rdf_id(self, context: Context, id_val: str) -> Optional[IdentifiedNode]:
             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) -> Optional[str]:
         if not ref.startswith("_:"):

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"
     }
   ]
 }

test/jsonld/local-suite/toRdf-twoinvalidids-in.jsonld

@@ -0,0 +1,20 @@
+{
+    "@id": "https://example.org/root-object",
+    "https://schema.org/author": [
+        {
+            "@id": "https://example.org/ invalid url 1",
+            "https://schema.org/name": "Jane Doe"
+        },
+        {
+            "@id": "https://example.org/ invalid url 1",
+            "https://schema.org/givenName": "Jane",
+            "https://schema.org/familyName": "Doe"
+        },
+        {
+            "@id": "https://example.org/ invalid url 2",
+            "https://schema.org/name": "John Doe",
+            "https://schema.org/givenName": "John",
+            "https://schema.org/familyName": "Doe"
+        }
+    ]
+}

test/jsonld/local-suite/toRdf-twoinvalidids-out.nq

@@ -0,0 +1,10 @@
+
+<https://example.org/root-object> <https://schema.org/author> _:b1.
+<https://example.org/root-object> <https://schema.org/author> _:b2.
+
+_:b1 <https://schema.org/name> "Jane Doe".
+_:b1 <https://schema.org/givenName> "Jane".
+_:b1 <https://schema.org/familyName> "Doe".
+_:b2 <https://schema.org/name> "John Doe".
+_:b2 <https://schema.org/givenName> "John".
+_:b2 <https://schema.org/familyName> "Doe".