WIP: RDF, SPARQL, SKOSMOS

config/settings/base.py

@@ -92,6 +92,7 @@
     "treebeard",
     "corsheaders",
     "rules.apps.AutodiscoverRulesConfig",
+    "rdflib_django",
 ]
 
 LOCAL_APPS = [
@@ -101,6 +102,7 @@
     "metadata_catalogue.datasets.csw",
     "metadata_catalogue.datasets.geoapi",
     "metadata_catalogue.maps",
+    "metadata_catalogue.dictionaries",
 ]
 # https://docs.djangoproject.com/en/dev/ref/settings/#installed-apps
 INSTALLED_APPS = DJANGO_APPS + THIRD_PARTY_APPS + LOCAL_APPS

config/settings/local.py

@@ -60,3 +60,19 @@
 
 
 INSTALLED_APPS += ["models2puml"]
+
+DICTIONARIES_EXAMPLE_QUERIES = {
+    "Bio2RDF query": {
+        "endpoint": "https://bio2rdf.org/sparql",
+        "query": """SELECT DISTINCT * WHERE {
+    ?s a ?o .
+} LIMIT 10""",
+    },
+    "Custom function": {
+        "query": """PREFIX myfunctions: <https://w3id.org/um/sparql-functions/>
+SELECT ?concat ?concatLength WHERE {
+    BIND("First" AS ?first)
+    BIND(myfunctions:custom_concat(?first, "last") AS ?concat)
+}""",
+    },
+}

config/urls.py

@@ -23,6 +23,7 @@
     path("geoapi/", include("metadata_catalogue.datasets.geoapi.urls", namespace="geoapi")),
     path("datasets/", include("metadata_catalogue.datasets.urls")),
     path("api/", api.urls),
+    path("", include("metadata_catalogue.dictionaries.urls")),
 ]
 
 

docker-compose.yml

@@ -178,3 +178,10 @@ services:
       context: ./varnish
     ports:
       - 8000:80
+
+  skosmos:
+    image: ghcr.io/nicokant/skosmos:master
+    ports:
+      - 8050:80
+    volumes:
+      - ./skosmos.ttl:/var/www/html/config.ttl

metadata_catalogue/dictionaries/conf.py

@@ -0,0 +1,76 @@
+from appconf import AppConf
+from django.conf import settings
+
+from .rdf_functions import custom_concat
+
+
+class DictionariesConf(AppConf):
+    DEFAULT_TITLE: str = "SPARQL endpoint for RDFLib graph"
+    DEFAULT_DESCRIPTION: str = (
+        "A SPARQL endpoint to serve machine learning models, or any other logic implemented in Python."
+    )
+    DEFAULT_VERSION: str = "0.1.0"
+    DEFAULT_FAVICON: str = "https://rdflib.readthedocs.io/en/stable/_static/RDFlib.png"
+    DEFAULT_EXAMPLE = """\
+    PREFIX myfunctions: <https://w3id.org/um/sparql-functions/>
+
+    SELECT ?concat ?concatLength WHERE {
+        BIND("First" AS ?first)
+        BIND(myfunctions:custom_concat(?first, "last") AS ?concat)
+    }
+    """.rstrip()
+
+    SERVICE_DESCRIPTION_TTL_FMT = """\
+    @prefix sd: <http://www.w3.org/ns/sparql-service-description#> .
+    @prefix ent: <http://www.w3.org/ns/entailment/> .
+    @prefix prof: <http://www.w3.org/ns/owl-profile/> .
+    @prefix void: <http://rdfs.org/ns/void#> .
+    @prefix dc: <http://purl.org/dc/elements/1.1/> .
+    @prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
+
+    <{public_url}> a sd:Service ;
+        rdfs:label "{title}" ;
+        dc:description "{description}" ;
+        sd:endpoint <{public_url}> ;
+        sd:supportedLanguage sd:SPARQL11Query ;
+        sd:resultFormat <http://www.w3.org/ns/formats/SPARQL_Results_JSON>, <http://www.w3.org/ns/formats/SPARQL_Results_CSV> ;
+        sd:feature sd:DereferencesURIs ;
+        sd:defaultEntailmentRegime ent:RDFS ;
+        sd:defaultDataset [
+            a sd:Dataset ;
+            sd:defaultGraph [
+                a sd:Graph ;
+            ]
+        ] .
+    """.rstrip()
+
+    #: This is default for federated queries
+    DEFAULT_CONTENT_TYPE = "application/xml"
+
+    #: A mapping from content types to the keys used for serializing
+    #: in :meth:`rdflib.Graph.serialize` and other serialization functions
+    CONTENT_TYPE_TO_RDFLIB_FORMAT = {
+        # https://www.w3.org/TR/sparql11-results-json/
+        "application/sparql-results+json": "json",
+        "application/json": "json",
+        "text/json": "json",
+        # https://www.w3.org/TR/rdf-sparql-XMLres/
+        "application/sparql-results+xml": "xml",
+        "application/xml": "xml",  # for compatibility
+        "application/rdf+xml": "xml",  # for compatibility
+        "text/xml": "xml",  # not standard
+        # https://www.w3.org/TR/sparql11-results-csv-tsv/
+        "application/sparql-results+csv": "csv",
+        "text/csv": "csv",  # for compatibility
+        # Extras
+        "text/turtle": "ttl",
+    }
+
+    CUSTOM_EVAL = None
+    FUNCTIONS = {
+        "https://w3id.org/um/sparql-functions/custom_concat": custom_concat,
+    }
+    EXAMPLE_QUERIES = None
+    ENABLE_UPDATE = False
+    PROCESSOR = "sparql"
+    RDFLIB_APIKEY = None

metadata_catalogue/dictionaries/rdf_functions.py

@@ -0,0 +1,33 @@
+import rdflib
+from rdflib import Literal
+from rdflib.plugins.sparql.evalutils import _eval
+
+
+def custom_concat(query_results, ctx, part, eval_part):
+    """
+    Concat 2 string and return the length as additional Length variable
+    \f
+    :param query_results:   An array with the query results objects
+    :param ctx:             <class 'rdflib.plugins.sparql.sparql.QueryContext'>
+    :param part:            Part of the query processed (e.g. Extend or BGP) <class 'rdflib.plugins.sparql.parserutils.CompValue'>
+    :param eval_part:       Part currently evaluated
+    :return:                the same query_results provided in input param, with additional results
+    """
+    argument1 = str(_eval(part.expr.expr[0], eval_part.forget(ctx, _except=part.expr._vars)))
+    argument2 = str(_eval(part.expr.expr[1], eval_part.forget(ctx, _except=part.expr._vars)))
+    evaluation = []
+    scores = []
+    concat_string = argument1 + argument2
+    reverse_string = argument2 + argument1
+    # Append the concatenated string to the results
+    evaluation.append(concat_string)
+    evaluation.append(reverse_string)
+    # Append the scores for each row of results
+    scores.append(len(concat_string))
+    scores.append(len(reverse_string))
+    # Append our results to the query_results
+    for i, result in enumerate(evaluation):
+        query_results.append(
+            eval_part.merge({part.var: Literal(result), rdflib.term.Variable(part.var + "Length"): Literal(scores[i])})
+        )
+    return query_results, ctx, part, eval_part

metadata_catalogue/dictionaries/templates/dictionaries/yasgui.html

@@ -0,0 +1,69 @@
+<!DOCTYPE html>
+<html lang="en">
+  <head>
+    <meta charset="utf-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1" />
+    <title>{{ title }}</title>
+    <meta name="description" content="{{ description }}" />
+    <link href="https://unpkg.com/@triply/yasgui@4/build/yasgui.min.css"
+          rel="stylesheet"
+          type="text/css" />
+    <script src="https://unpkg.com/@triply/yasgui@4/build/yasgui.min.js"></script>
+  </head>
+  <body>
+    <div id="yasgui"></div>
+    {% if example_queries %}{{ example_queries|json_script:"example-queries" }}{% endif %}
+    <script>
+      let queries_obj = []
+      try {
+        queries_obj = JSON.parse(document.getElementById('example-queries').textContent) || []
+      } catch (e) {
+        console.log(e)
+      }
+
+      const url = window.location.href;
+      // Make sure the endpoints list is unique
+      const endpointsList = [...new Set([url, ...Object.keys(queries_obj).map((label) => {
+        if (queries_obj[label]["endpoint"]) return queries_obj[label]["endpoint"]
+      })])]
+      const yasguiEndpoints = endpointsList.map((endpoint) => {
+        return {
+          endpoint: endpoint
+        }
+      })
+
+      const yasgui = new Yasgui(document.getElementById("yasgui"), {
+        requestConfig: {
+          endpoint: url,
+          copyEndpointOnNewTab: true,
+        },
+        endpointCatalogueOptions: {
+          getData: function() {
+            return yasguiEndpoints
+          },
+          keys: [],
+        },
+      });
+
+      // Add tab to yasgui for each query
+      Object.keys(queries_obj).map((label) => {
+        const tabsLabel = Object.keys(yasgui._tabs).map(tab => yasgui._tabs[tab].persistentJson.name)
+        if (!tabsLabel.includes(label)) {
+          yasgui.addTab(
+            false, // set as active tab not really working
+            {
+              ...Yasgui.Tab.getDefaults(),
+              name: label,
+              requestConfig: {
+                endpoint: queries_obj[label]['endpoint']
+              },
+              yasqe: {
+                value: queries_obj[label]['query']
+              }
+            }
+          );
+        }
+      })
+    </script>
+  </body>
+</html>

metadata_catalogue/dictionaries/tests/test_utils.py

@@ -0,0 +1,21 @@
+import pytest
+
+from ..utils import parse_accept_header
+
+accept_cases = [
+    ("text/xml", "text/xml"),
+    ("text/rdf+xml, text/xml, */*", "text/rdf+xml"),
+    ("text/html, application/xhtml+xml, application/xml;q=0.9, */*;q=0.8", "text/html"),
+    ("text/html, application/xhtml+xml, application/xml;q=0.9, */*;q=", "text/html"),
+    ("text/html;q=0.3, application/xhtml+xml, application/xml;q=0.9, */*;q=0.8", "application/xhtml+xml"),
+    (
+        'text/turtle;q=0.9;profile="urn:example:profile-1", text/turtle;q=0.7;profile="urn:example:profile-2"',
+        "text/turtle",
+    ),
+]
+
+
+@pytest.mark.parametrize("accept,expected", accept_cases)
+def test_accept_preference(accept, expected):
+    pref = parse_accept_header(accept)
+    assert pref[0] == expected