Merge pull request #143 from RDFLib/edmond/feature/bgs

Add reg:status to vocpub profile as an annotation prop. Add rdf:type to the vocabs API and add fix to ensure profile predicates and their values get annotation values added to response
RDFLib · Aug 9, 2023 · a56cb9a · a56cb9a
2 parents 070d8e1 + f8bc090
commit a56cb9a
Show file tree

Hide file tree

Showing 28 changed files with 1,015 additions and 190 deletions.
diff --git a/.github/workflows/on_pr_to_main.yaml b/.github/workflows/on_pr_to_main.yaml
@@ -63,6 +63,6 @@ jobs:
           cd ../catprez && poetry run pytest
           cd ../profiles && poetry run pytest
           cd ../services && poetry run pytest
-          cd ../curies && poetry run pytest
+          cd ../identifier && poetry run pytest
           cd ../object && poetry run pytest
           cd ../caching && poetry run pytest
diff --git a/.github/workflows/on_push_to_feature.yaml b/.github/workflows/on_push_to_feature.yaml
@@ -61,4 +61,5 @@ jobs:
           cd ../catprez && poetry run pytest
           cd ../profiles && poetry run pytest
           cd ../services && poetry run pytest
+          cd ../identifier && poetry run pytest
 #          cd ../local_sparql_store && poetry run pytest
diff --git a/README.md b/README.md
@@ -36,6 +36,14 @@ It expects "high quality" data to work well: Prez itself won't patch up bad or m
 
 Prez accesses data stored in an RDF database - a 'triplestore' - and uses the SPARQL Protocol to do so. Any SPARQL Protocol-compliant DB may be used.
 
+## Redirect Service
+
+As a Linked Data server, Prez provides a redirect service at `/identifier/redirect` that accepts a query parameter `iri`, looks up the `iri` in the database for a `foaf:homepage` predicate with a value, and if it exists, return a redirect response to the value.
+
+This functionality is useful for institutions who issue their own persistent identifiers under a domain name that they control. The mapping from the persistent identifier to the target web resource is stored in the backend SPARQL store.
+
+This is an alternative solution to persistent identifier services such as the [w3id.org](https://w3id.org/). In some cases, it can be used together with such persistent identifier services to avoid the need to provide the redirect mapping in webserver config (NGINX, Apache HTTP, etc.) and instead, define the config as RDF data.
+
 ## Development
 
 This section is for developing Prez locally. See the [Running](#running) options below for running Prez in production.
@@ -84,20 +92,20 @@ 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                                                                                                                                                                |
-| 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).  |
+| 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
 

diff --git a/prez/app.py b/prez/app.py
@@ -25,7 +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.routers.identifier import router as identifier_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 (
@@ -61,7 +61,7 @@
 app.include_router(catprez_router)
 app.include_router(vocprez_router)
 app.include_router(spaceprez_router)
-app.include_router(curie_router)
+app.include_router(identifier_router)
 
 
 @app.middleware("http")

diff --git a/prez/queries/identifier.py b/prez/queries/identifier.py
@@ -0,0 +1,18 @@
+from textwrap import dedent
+
+from jinja2 import Template
+
+
+def get_foaf_homepage_query(iri: str) -> str:
+    query = Template(
+        """
+        PREFIX foaf: <http://xmlns.com/foaf/0.1/>
+        
+        SELECT DISTINCT ?url
+        WHERE {
+            <{{ iri }}> foaf:homepage ?url . 
+        }
+    """
+    ).render(iri=iri)
+
+    return dedent(query)
diff --git a/prez/queries/vocprez.py b/prez/queries/vocprez.py
@@ -63,11 +63,15 @@ def get_concept_scheme_top_concepts_query(iri: str, page: int, per_page: int) ->
             ?concept prez:childrenCount ?narrowerChildrenCount .
             ?iri prez:childrenCount ?childrenCount .
             ?iri skos:hasTopConcept ?concept .
+            ?iri rdf:type ?type .
+            ?concept rdf:type ?conceptType .
         }
         WHERE {
             BIND(<{{ iri }}> as ?iri)
             ?iri skos:hasTopConcept ?concept .
             ?concept skos:prefLabel ?label .
+            ?iri rdf:type ?type .
+            ?concept rdf:type ?conceptType .
         
             {
                 SELECT (COUNT(?childConcept) AS ?childrenCount)
@@ -113,11 +117,15 @@ def get_concept_narrowers_query(iri: str, page: int, per_page: int) -> str:
             ?concept prez:childrenCount ?narrowerChildrenCount .
             ?iri prez:childrenCount ?childrenCount .
             ?iri skos:narrower ?concept .
+            ?iri rdf:type ?type .
+            ?concept rdf:type ?conceptType .
         }
         WHERE {
             BIND(<{{ iri }}> as ?iri)
             ?concept skos:broader ?iri .
             ?concept skos:prefLabel ?label .
+            ?iri rdf:type ?type .
+            ?concept rdf:type ?conceptType .
             
             {
                 SELECT (COUNT(?childConcept) AS ?childrenCount)

diff --git a/prez/reference_data/profiles/vocprez_default_profiles.ttl b/prez/reference_data/profiles/vocprez_default_profiles.ttl
@@ -69,7 +69,7 @@ prez:VocPrezProfile
     dcterms:identifier "vocpub"^^xsd:token ;
     dcterms:title "VocPub" ;
     altr-ext:hasLabelPredicate skos:prefLabel ;
-    altr-ext:otherAnnotationProps schema:color ;
+    altr-ext:otherAnnotationProps schema:color, reg:status ;
     altr-ext:constrainsClass
         skos:ConceptScheme ,
         skos:Concept ,

diff --git a/prez/renderers/renderer.py b/prez/renderers/renderer.py
@@ -72,6 +72,24 @@ async def return_rdf(graph, mediatype, profile_headers):
     return StreamingResponse(content=obj, media_type=mediatype, headers=profile_headers)
 
 
+async def get_annotations_graph(profile, graph, cache):
+    profile_annotation_props = get_annotation_predicates(profile)
+    queries_for_uncached, annotations_graph = await get_annotation_properties(
+        graph, **profile_annotation_props
+    )
+
+    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
+
+    return annotations_graph
+
+
 async def return_annotated_rdf(
     graph: Graph,
     profile_headers,
@@ -84,27 +102,19 @@ async def return_annotated_rdf(
     non_anot_mediatype = mediatype.replace("anot+", "")
 
     cache = tbox_cache
-    profile_annotation_props = get_annotation_predicates(profile)
-    queries_for_uncached, annotations_graph = await get_annotation_properties(
-        graph, **profile_annotation_props
-    )
 
-    if queries_for_uncached is None:
-        anots_from_triplestore = Graph()
-    else:
-        anots_from_triplestore = await queries_to_graph([queries_for_uncached])
+    previous_triples_count = len(graph)
 
-    if len(anots_from_triplestore) > 1:
-        annotations_graph += anots_from_triplestore
-        cache += anots_from_triplestore
+    # Expand the graph with annotations specified in the profile until no new statements are added.
+    while True:
+        graph += await get_annotations_graph(profile, graph, cache)
+        if len(graph) == previous_triples_count:
+            break
+        previous_triples_count = len(graph)
 
     generate_prez_links(graph, predicates_for_link_addition)
 
-    obj = io.BytesIO(
-        (graph + annotations_graph).serialize(
-            format=non_anot_mediatype, encoding="utf-8"
-        )
-    )
+    obj = io.BytesIO(graph.serialize(format=non_anot_mediatype, encoding="utf-8"))
     return StreamingResponse(
         content=obj, media_type=non_anot_mediatype, headers=profile_headers
     )

diff --git a/prez/routers/curie.py → prez/routers/identifier.py b/prez/routers/curie.py → prez/routers/identifier.py
@@ -1,13 +1,43 @@
-from fastapi import APIRouter, HTTPException, status
-from fastapi.responses import PlainTextResponse
+from fastapi import APIRouter, HTTPException, status, Request
+from fastapi.responses import PlainTextResponse, RedirectResponse
 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
+from prez.queries.identifier import get_foaf_homepage_query
+from prez.sparql.methods import sparql_query_non_async
 
 router = APIRouter(tags=["Identifier Resolution"])
 
 
+@router.get(
+    "/identifier/redirect",
+    summary="Get a redirect response to the resource landing page",
+    response_class=RedirectResponse,
+    responses={
+        status.HTTP_404_NOT_FOUND: {"content": {"application/json": {}}},
+    },
+)
+def get_identifier_redirect_route(iri: str, request: Request):
+    """
+    The `iri` query parameter is used to return a redirect response with the value from the `foaf:homepage` lookup.
+    If no value is found, a 404 HTTP response is returned.
+    """
+    query = get_foaf_homepage_query(iri)
+    _, result = sparql_query_non_async(query)
+    url = None
+    for row in result:
+        url = row["url"]["value"]
+
+    if url is None:
+        raise HTTPException(
+            status.HTTP_404_NOT_FOUND, f"No homepage found for IRI {iri}."
+        )
+
+    # Note: currently does not forward query parameters but we may want to implement this in the future.
+    return RedirectResponse(url, headers=request.headers)
+
+
 @router.get(
     "/identifier/curie/{iri:path}",
     summary="Get the IRI's CURIE identifier",

diff --git a/prez/routers/object.py b/prez/routers/object.py
@@ -2,7 +2,7 @@
 from starlette.responses import PlainTextResponse
 
 from prez.models import SpatialItem, VocabItem, CatalogItem
-from prez.routers.curie import get_iri_route
+from prez.routers.identifier import get_iri_route
 from prez.sparql.methods import sparql_query_non_async
 from prez.queries.object import object_inbound_query, object_outbound_query
 

diff --git a/prez/routers/vocprez.py b/prez/routers/vocprez.py
@@ -29,7 +29,7 @@
     get_concept_narrowers_query,
 )
 from prez.response import StreamingTurtleAnnotatedResponse
-from prez.routers.curie import get_iri_route
+from prez.routers.identifier import get_iri_route
 
 router = APIRouter(tags=["VocPrez"])
 

diff --git a/tests/data/spaceprez/input/redirect-foaf-homepage.ttl b/tests/data/spaceprez/input/redirect-foaf-homepage.ttl
@@ -0,0 +1,3 @@
+PREFIX foaf: <http://xmlns.com/foaf/0.1/>
+
+<http://data.bgs.ac.uk/id/dataHolding/13603129> foaf:homepage <http://metadata.bgs.ac.uk/geonetwork/srv/eng/catalog.search#/metadata/9df8df53-2a1d-37a8-e044-0003ba9b0d98> .