Add new vocabs API

README.md

@@ -84,19 +84,20 @@ via python-dotenv, or directly in the environment in which Prez is run. The envi
 instantiate a Pydantic `Settings` object which is used throughout Prez to configure its behaviour. To see how prez
 interprets/uses these environment variables see the `prez/config.py` file.
 
-| Environment Variable | Description                                                                                                                       |
-|-------------------|-----------------------------------------------------------------------------------------------------------------------------------|
-| SPARQL_ENDPOINT   | Read-only SPARQL endpoint for SpacePrez                                                                                           |
-| SPARQL_USERNAME   | A username for Basic Auth against the SPARQL endpoint, if required by the SPARQL endpoint.                                        |
-| SPARQL_PASSWORD   | A password for Basic Auth against the SPARQL endpoint, if required by the SPARQL endpoint.                                        |
-| PROTOCOL          | The protocol used to deliver Prez. Usually 'http'.                                                                                |
-| HOST              | The host on which to server prez, typically 'localhost'.                                                                          |
-| PORT              | The port Prez is made accessible on. Default is 8000, could be 80 or anything else that your system has permission to use         |
-| SYSTEM_URI        | Documentation property. An IRI for the Prez system as a whole. This value appears in the landing page RDF delivered by Prez ('/') |
-| LOG_LEVEL         | One of CRITICAL, ERROR, WARNING, INFO, DEBUG. Defaults to INFO.                                                                   |
-| LOG_OUTPUT        | "file", "stdout", or "both" ("file" and "stdout"). Defaults to stdout.                                                            |
-| PREZ_TITLE        | The title to use for Prez instance                                                                                                |
-| PREZ_DESC         | A description to use for the Prez instance                                                                                        |
+| Environment Variable      | Description                                                                                                                                                                                               |
+|---------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| SPARQL_ENDPOINT           | Read-only SPARQL endpoint for SpacePrez                                                                                                                                                                   |
+| SPARQL_USERNAME           | A username for Basic Auth against the SPARQL endpoint, if required by the SPARQL endpoint.                                                                                                                |
+| SPARQL_PASSWORD           | A password for Basic Auth against the SPARQL endpoint, if required by the SPARQL endpoint.                                                                                                                |
+| PROTOCOL                  | The protocol used to deliver Prez. Usually 'http'.                                                                                                                                                        |
+| HOST                      | The host on which to server prez, typically 'localhost'.                                                                                                                                                  |
+| PORT                      | The port Prez is made accessible on. Default is 8000, could be 80 or anything else that your system has permission to use                                                                                 |
+| SYSTEM_URI                | Documentation property. An IRI for the Prez system as a whole. This value appears in the landing page RDF delivered by Prez ('/')                                                                         |
+| LOG_LEVEL                 | One of CRITICAL, ERROR, WARNING, INFO, DEBUG. Defaults to INFO.                                                                                                                                           |
+| LOG_OUTPUT                | "file", "stdout", or "both" ("file" and "stdout"). Defaults to stdout.                                                                                                                                    |
+| PREZ_TITLE                | The title to use for Prez instance                                                                                                                                                                        |
+| PREZ_DESC                 | A description to use for the Prez instance                                                                                                                                                                |
+| DISABLE_PREFIX_GENERATION | Default value is `false`. Very large datasets may want to disable this setting and provide a predefined set of prefixes for namespaces as described in [Link Generation](README-Dev.md#link-generation).  |
 
 ### Running in a Container
 

prez/app.py

@@ -25,6 +25,7 @@
 from prez.routers.spaceprez import router as spaceprez_router
 from prez.routers.sparql import router as sparql_router
 from prez.routers.vocprez import router as vocprez_router
+from prez.routers.curie import router as curie_router
 from prez.services.app_service import healthcheck_sparql_endpoints, count_objects
 from prez.services.app_service import populate_api_info, add_prefixes_to_prefix_graph
 from prez.services.exception_catchers import (
@@ -60,6 +61,7 @@
 app.include_router(catprez_router)
 app.include_router(vocprez_router)
 app.include_router(spaceprez_router)
+app.include_router(curie_router)
 
 
 @app.middleware("http")

prez/bnode.py

@@ -0,0 +1,23 @@
+from rdflib import Graph, URIRef, BNode
+
+
+def get_bnode_depth(
+    graph: Graph, node: URIRef | BNode = None, depth: int = 0, seen: list[BNode] = None
+) -> int:
+    """Get the max blank node depth of the node in the graph.
+
+    This is a recursive function.
+
+    >>> graph = Graph().parse(...)
+    >>> depth = get_bnode_depth(graph, URIRef("node-name"))
+    """
+    if seen is None:
+        seen = []
+
+    if isinstance(node, BNode) or depth == 0:
+        for o in graph.objects(node, None):
+            if isinstance(o, BNode) and o not in seen:
+                seen.append(o)
+                depth = get_bnode_depth(graph, o, depth + 1, seen)
+
+    return depth

prez/config.py

@@ -74,6 +74,7 @@ class Settings(BaseSettings):
         "Knowledge Graph data which can be subset according to information profiles."
     )
     prez_version: Optional[str]
+    disable_prefix_generation: bool = False
 
     @root_validator()
     def check_endpoint_enabled(cls, values):

prez/models/profiles_item.py

@@ -39,5 +39,8 @@ def populate(cls, values):
         if len(r.bindings) > 0:
             values["classes"] = frozenset([prof.get("class") for prof in r.bindings])
 
-        values["label"] = profiles_graph_cache.value(URIRef(values["uri"]), URIRef("http://www.w3.org/ns/dx/conneg/altr-ext#hasLabelPredicate"))
+        values["label"] = profiles_graph_cache.value(
+            URIRef(values["uri"]),
+            URIRef("http://www.w3.org/ns/dx/conneg/altr-ext#hasLabelPredicate"),
+        )
         return values

prez/models/vocprez_item.py

@@ -10,7 +10,7 @@
 
 class VocabItem(BaseModel):
     uri: Optional[URIRef] = None
-    classes: Optional[Set[URIRef]]
+    classes: Optional[frozenset[URIRef]]
     curie_id: Optional[str] = None
     general_class: Optional[URIRef] = None
     scheme_curie: Optional[str] = None

prez/renderers/renderer.py

@@ -1,6 +1,6 @@
 import io
 import logging
-from typing import Optional, Dict
+from typing import Optional
 
 from connegp import RDF_MEDIATYPES, RDF_SERIALIZER_TYPES_MAP
 from fastapi.responses import StreamingResponse
@@ -28,7 +28,7 @@ async def return_from_queries(
     mediatype,
     profile,
     profile_headers,
-    predicates_for_link_addition: Dict = {},
+    predicates_for_link_addition: dict = None,
 ):
     """
     Executes SPARQL queries, loads these to RDFLib Graphs, and calls the "return_from_graph" function to return the
@@ -45,7 +45,7 @@ async def return_from_graph(
     mediatype,
     profile,
     profile_headers,
-    predicates_for_link_addition: dict = {},
+    predicates_for_link_addition: dict = None,
 ):
     profile_headers["Content-Disposition"] = "inline"
     if str(mediatype) in RDF_MEDIATYPES:
@@ -88,7 +88,12 @@ async def return_annotated_rdf(
     queries_for_uncached, annotations_graph = await get_annotation_properties(
         graph, **profile_annotation_props
     )
-    anots_from_triplestore = await queries_to_graph([queries_for_uncached])
+
+    if queries_for_uncached is None:
+        anots_from_triplestore = Graph()
+    else:
+        anots_from_triplestore = await queries_to_graph([queries_for_uncached])
+
     if len(anots_from_triplestore) > 1:
         annotations_graph += anots_from_triplestore
         cache += anots_from_triplestore

prez/response.py

@@ -0,0 +1,12 @@
+from fastapi.responses import StreamingResponse
+
+
+class StreamingTurtleResponse(StreamingResponse):
+    media_type = "text/turtle"
+
+    def render(self, content: str) -> bytes:
+        return content.encode("utf-8")
+
+
+class StreamingTurtleAnnotatedResponse(StreamingTurtleResponse):
+    media_type = "text/anot+turtle"

prez/routers/curie.py

@@ -0,0 +1,54 @@
+from fastapi import APIRouter, HTTPException, status
+from fastapi.responses import PlainTextResponse
+from rdflib import URIRef
+from rdflib.term import _is_valid_uri
+
+from prez.services.curie_functions import get_uri_for_curie_id, get_curie_id_for_uri
+
+router = APIRouter(tags=["Identifier Resolution"])
+
+
+@router.get(
+    "/identifier/curie/{iri:path}",
+    summary="Get the IRI's CURIE identifier",
+    response_class=PlainTextResponse,
+    responses={
+        status.HTTP_400_BAD_REQUEST: {"content": {"application/json": {}}},
+        status.HTTP_500_INTERNAL_SERVER_ERROR: {"content": {"application/json": {}}},
+    },
+)
+def get_curie_route(iri: str):
+    if not _is_valid_uri(iri):
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, f"Invalid characters in {iri}")
+    try:
+        return get_curie_id_for_uri(URIRef(iri))
+    except ValueError as err:
+        raise HTTPException(
+            status.HTTP_400_BAD_REQUEST, f"Error processing IRI {iri}"
+        ) from err
+    except Exception as err:
+        raise HTTPException(
+            status.HTTP_500_INTERNAL_SERVER_ERROR,
+            f"Unhandled server error for IRI {iri}",
+        ) from err
+
+
+@router.get(
+    "/identifier/iri/{curie}",
+    summary="Get the CURIE identifier's fully qualified IRI",
+    response_class=PlainTextResponse,
+    responses={
+        status.HTTP_400_BAD_REQUEST: {"content": {"application/json": {}}},
+        status.HTTP_500_INTERNAL_SERVER_ERROR: {"content": {"application/json": {}}},
+    },
+)
+def get_iri_route(curie: str):
+    try:
+        return get_uri_for_curie_id(curie)
+    except ValueError as err:
+        raise HTTPException(status.HTTP_400_BAD_REQUEST, str(err)) from err
+    except Exception as err:
+        raise HTTPException(
+            status.HTTP_500_INTERNAL_SERVER_ERROR,
+            f"Unhandled server error for curie {curie}",
+        ) from err