extended examples and stardog load/query tests

_sources/activities/aggregation/bblock.json

@@ -0,0 +1,20 @@
+{
+  "name": "Aggregation Activity",
+  "abstract": "An aggregation activity integrates a stream of observations into a persistent archive.",
+  "status": "under-development",
+  "dateTimeAddition": "2023-05-19T00:00:00Z",
+  "itemClass": "schema",
+  "register": "ccm",
+  "version": "1.0",
+  "dateOfLastChange": "2023-05-19",
+  "sources": [
+  ],
+  "maturity": "development",
+  "scope": "unstable",
+  "dependsOn": [
+  ],
+  "tags": [
+    "prov"],
+  "group": "Activities",
+  "highlighted": true
+}

_sources/activities/aggregation/description.md

@@ -0,0 +1,7 @@
+## Aggregation Activity 
+
+This building block provides a JSON schema based on the PROV model for an activity that performs an aggregation over dimensions of a set of data observations.
+
+The aggregation function must be described using an appropriate AggregationFunction entity.
+
+

_sources/activities/aggregation/examples.yaml

@@ -0,0 +1,24 @@
+## Prefixes will be used for all RDF Turtle resources so that they can be omitted from the actual snippets
+# prefixes:
+#   dct: http://purl.org/dc/terms/
+
+## List of examples
+examples:
+  - title: Aggregation
+
+    ## Markdown content that will be shown for the example.
+    content:
+      Shows a aggregation activity with a positive result.
+
+    ## Base URI for semantic uplift
+    base-uri: http://example.com/activities/
+
+    ## The example can define its own prefixes, that will be merged with the global ones
+    prefixes:
+      myData: http://example.com/datasets/
+
+    ## List of code snippets for this example
+    snippets:
+      - language: json
+        # Reference to file
+        ref: examples/aggregation.json

_sources/activities/aggregation/examples/aggregation.json

@@ -0,0 +1,15 @@
+{
+  "provType": [ "Activity", "Aggregation" ],
+  "id": "aggregation_example",
+  "endedAtTime": "2029-01-01T22:05:19+02:00",
+  "wasAssociatedWith": "eg_agents:bc-3",
+  "generated": { "id": "myData:YearlySummary",
+    "wasDerivedFrom" : "myData:WeeklyRecords",
+    "wasGeneratedBy" : "aggregation_example"
+  },
+  "used": "myData:WeeklyRecords"
+}
+
+
+
+

_sources/activities/aggregation/schema.yaml

@@ -0,0 +1,18 @@
+description: Aggregation activity
+$defs:
+  Aggregation:
+    allOf:
+      - $ref: bblocks://ogc.ogc-utils.prov#/$defs/Activity
+      - properties:
+          provType:
+            type: array
+            contains:
+              type: string
+              const: Aggregation
+        required:
+          - provType
+          - generated
+          - used
+
+anyOf:
+  - $ref: "#/$defs/Aggregation"

_sources/activities/certification/bblock.json

@@ -4,7 +4,7 @@
   "status": "under-development",
   "dateTimeAddition": "2023-05-19T00:00:00Z",
   "itemClass": "schema",
-  "register": "ogc-building-block-examples",
+  "register": "ccm",
   "version": "1.0",
   "dateOfLastChange": "2023-05-19",
   "sources": [

_sources/activities/derivation/bblock.json

@@ -0,0 +1,20 @@
+{
+  "name": "Derivation Activity",
+  "abstract": "A derivation activity takes a data set and derives a new data set from it. It must reference an Entity which defines the derivation function, allowing identification of the derivation process.",
+  "status": "under-development",
+  "dateTimeAddition": "2023-05-19T00:00:00Z",
+  "itemClass": "schema",
+  "register": "ccm",
+  "version": "1.0",
+  "dateOfLastChange": "2023-05-19",
+  "sources": [
+  ],
+  "maturity": "development",
+  "scope": "unstable",
+  "dependsOn": [
+  ],
+  "tags": [
+    "prov"],
+  "group": "Activities",
+  "highlighted": true
+}

_sources/activities/derivation/description.md

@@ -0,0 +1,8 @@
+## Derivation Activity 
+
+This building block provides a JSON schema based on the PROV model for an activity derives new data using a function based on properties of that data. 
+
+
+
+
+

_sources/activities/derivation/examples.yaml

@@ -0,0 +1,24 @@
+## Prefixes will be used for all RDF Turtle resources so that they can be omitted from the actual snippets
+# prefixes:
+#   dct: http://purl.org/dc/terms/
+
+## List of examples
+examples:
+  - title: Derivation
+
+    ## Markdown content that will be shown for the example.
+    content:
+      Shows a derivation activity with a positive result.
+
+    ## Base URI for semantic uplift
+    base-uri: http://example.com/activities/
+
+    ## The example can define its own prefixes, that will be merged with the global ones
+    prefixes:
+      mydata: http://example.com/datasets/
+
+    ## List of code snippets for this example
+    snippets:
+      - language: json
+        # Reference to file
+        ref: examples/derivation.json

_sources/activities/derivation/examples/a-plus-b.ttl

@@ -0,0 +1,65 @@
+@prefix mydata: <http://example.com/data/> .
+@prefix prov:   <http://www.w3.org/ns/prov#> .
+@prefix xsd:    <http://www.w3.org/2001/XMLSchema#> .
+@prefix sdo:    <https://schema.org/> .
+@prefix rdfs:   <http://www.w3.org/2000/01/rdf-schema#> .
+@prefix ex:     <http://example.org/> .
+@prefix geo:    <http://www.opengis.net/ont/geosparql#> .
+@prefix sf:     <http://www.opengis.net/ont/sf#> .
+
+
+<http://example.com/activities/add1>
+    a                      prov:Activity ;
+    rdfs:label             "Adder-run1" ;
+    prov:endedAtTime       "2029-01-01T22:05:19+02:00"^^xsd:dateTime ;
+    prov:generated         mydata:c ;
+    prov:used              mydata:a, mydata:b ;
+    prov:wasAssociatedWith <http://example.com/agents/adder> .
+
+mydata:a
+    a          prov:Entity ;
+    rdfs:label "A" ;
+    sdo:value  1
+.
+
+mydata:b
+    a          prov:Entity ;
+    rdfs:label "B" ;
+    sdo:value  2
+.
+
+mydata:c
+    a               <http://example.com/data/results/c> ;
+    geo:hasGeometry [ geo:asWKT """POLYGON((150.5000 -34.0000, 150.5020 -34.0005, 150.5040 -34.0010, 150.5060 -34.0015,
+        150.5080 -34.0020, 150.5100 -34.0025, 150.5120 -34.0030, 150.5140 -34.0035,
+                         150.5160 -34.0040, 150.5180 -34.0045, 150.5200 -34.0050, 150.5220 -34.0045,
+                         150.5240 -34.0040, 150.5260 -34.0035, 150.5280 -34.0030, 150.5300 -34.0025,
+                         150.5280 -34.0020, 150.5260 -34.0015, 150.5240 -34.0010, 150.5220 -34.0005,
+                         150.5200 -34.0000, 150.5180 -34.0005, 150.5160 -34.0010, 150.5140 -34.0015,
+                         150.5120 -34.0020, 150.5100 -34.0025, 150.5080 -34.0030, 150.5060 -34.0025,
+                         150.5040 -34.0020, 150.5020 -34.0015, 150.5000 -34.0010, 150.5000 -34.0000))"""^^geo:wktLiteral ;
+                        geo:asGeoJSON """{
+        "type": "Polygon",
+        "coordinates": [[
+            [150.5000, -34.0000], [150.5020, -34.0005], [150.5040, -34.0010], [150.5060, -34.0015],
+            [150.5080, -34.0020], [150.5100, -34.0025], [150.5120, -34.0030], [150.5140, -34.0035],
+            [150.5160, -34.0040], [150.5180, -34.0045], [150.5200, -34.0050], [150.5220, -34.0045],
+            [150.5240, -34.0040], [150.5260, -34.0035], [150.5280, -34.0030], [150.5300, -34.0025],
+            [150.5280, -34.0020], [150.5260, -34.0015], [150.5240, -34.0010], [150.5220, -34.0005],
+            [150.5200, -34.0000], [150.5180, -34.0005], [150.5160, -34.0010], [150.5140, -34.0015],
+            [150.5120, -34.0020], [150.5100, -34.0025], [150.5080, -34.0030], [150.5060, -34.0025],
+            [150.5040, -34.0020], [150.5020, -34.0015], [150.5000, -34.0010], [150.5000, -34.0000]
+        ]]
+    }"""^^geo:geoJSONLiteral
+                    ];
+
+    rdfs:label "C" ;
+    sdo:value  3 ;
+    prov:wasDerivedFrom mydata:a, mydata:b ;
+    prov:wasGeneratedBy <http://example.com/activities/add1> .
+
+<http://example.com/agents/adder>
+    a               prov:Agent ;
+    rdfs:label      "Add" ;
+    sdo:description "Adds all input values"
+.

_sources/activities/derivation/examples/derivation.json

@@ -0,0 +1,15 @@
+{
+  "provType": [ "Activity", "Derivation" ],
+  "id": "derivation_example",
+  "endedAtTime": "2029-01-01T22:05:19+02:00",
+  "wasAssociatedWith": "eg_agents:bc-3",
+  "generated": { "id": "mydata:YearlySummary",
+    "wasDerivedFrom" : "mydata:WeeklyRecords",
+    "wasGeneratedBy" : "derivation_example"
+  },
+  "used": "mydata:WeeklyRecords"
+}
+
+
+
+

_sources/activities/derivation/schema.yaml

@@ -0,0 +1,18 @@
+description: Derivation activity
+$defs:
+  Derivation:
+    allOf:
+      - $ref: bblocks://ogc.ogc-utils.prov#/$defs/Activity
+      - properties:
+          provType:
+            type: array
+            contains:
+              type: string
+              const: Derivation
+        required:
+          - provType
+          - generated
+          - used
+
+anyOf:
+  - $ref: "#/$defs/Derivation"

bblocks-config.yaml

@@ -21,6 +21,7 @@ imports:
   - https://ogcincubator.github.io/bblock-prov-schema/build/register.json
   - https://ogcincubator.github.io/geodcat-ogcapi-records/build/register.json
 
+
 # SPARQL configuration (optional)
 #   Authentication can be set through the sparql_username and sparql_password GitHub Workflow inputs
 #   (see .github/workflow/process-bblocks.yml)

queries/clearGraph.sparql

@@ -0,0 +1 @@
+CLEAR GRAPH $graph

queries/cross-domain-alias.trig

@@ -0,0 +1,3 @@
+<tag:stardog:api:graph:aliases> {
+  <tag:cross-domain-model> <tag:stardog:api:graph:alias> <https://www.w3.org/ns/prov> .
+}

queries/getActivity.sparql

@@ -0,0 +1,9 @@
+prefix prov: <http://www.w3.org/ns/prov#>
+SELECT ?A ?p ?plabel ?o ?olabel
+WHERE {
+    $entity prov:wasGeneratedBy ?A .
+    ?A ?p ?o .
+    OPTIONAL { ?p rdfs:label ?plabel }
+    OPTIONAL { ?o rdfs:label ?olabel }
+
+}

queries/getEntity.sparql

@@ -0,0 +1,8 @@
+prefix prov: <http://www.w3.org/ns/prov#>
+SELECT $entity ?p ?plabel ?o ?olabel
+WHERE {
+    $entity  ?p ?o .
+    OPTIONAL { ?p rdfs:label ?plabel }
+    OPTIONAL { ?o rdfs:label ?olabel }
+
+}

queries/getSpatialEntities.sparql

@@ -0,0 +1,11 @@
+prefix prov: <http://www.w3.org/ns/prov#>
+prefix geo:    <http://www.opengis.net/ont/geosparql#>
+SELECT $entity ?label  ?geojson ?wkt
+WHERE {
+    $entity geo:hasGeometry ?g .
+    OPTIONAL { ?g geo:asGeoJSON ?geojson }
+    OPTIONAL { ?g geo:asWKT ?wkt }
+    OPTIONAL { $entity rdfs:label ?label }
+
+
+}

queries/loader.py

@@ -0,0 +1,79 @@
+import csv
+import os
+import requests
+from requests.auth import HTTPBasicAuth
+
+# Retrieve the server, database, username, and password from environment variables
+stardog_server = os.getenv('STARDOG_SERVER')
+stardog_database = os.getenv('STARDOG_DATABASE')
+username = os.getenv('STARDOG_USERNAME')
+password = os.getenv('STARDOG_PASSWORD')
+
+# Check if all required environment variables are set
+if not all([stardog_server, stardog_database, username, password]):
+    raise ValueError("One or more required environment variables are not set")
+
+
+# Define the default value for the "model" column
+DEFAULT_MODEL = None
+
+
+def load(filename, uri, context, model):
+    """
+    Load a data file into stardog, so that it appears as a named graph.
+    The named graph is included in an "alias" - allowing multiple queryable data collections to co-exist.
+
+    Todo: force entailment using the named "model" as a reasoning graph
+
+    Parameters:
+    - name: The filename of the graph.
+    - uri: The URI for the named graph.
+    - context: The alias (collection) graph to include the new data in.
+    - [ model: The reasoning model (T-box) . ]
+    """
+    # Set up the headers
+    with open(filename, 'r') as file:
+        data = file.read()
+
+        headers = {
+            'Content-Type': 'text/turtle',
+            'Accept': 'application/sparql-results+json'
+        }
+        # Construct the Stardog URL
+        stardog_url = f"{stardog_server}/{stardog_database}?graph={uri}"
+
+        # Send the POST request with Basic Authentication
+        response = requests.put(
+            stardog_url,
+            headers=headers,
+            data=data,
+            auth=HTTPBasicAuth(username, password)
+        )
+
+        # Check if the request was successful
+        if response.status_code in [200,201]:
+            # Print the response JSON (assuming it's in JSON format)
+            print(f"{filename} - > {uri} : {response.status_code}")
+        else:
+            print(f"Error: {filename} - > {uri} : {response.status_code}")
+            print(response.text)
+
+
+def process_csv(file_path):
+    with open(file_path, newline='') as csvfile:
+        reader = csv.DictReader(csvfile)
+        for row in reader:
+            name = row.get('filename')
+            uri = row.get('uri')
+            context = row.get('context')
+            model = row.get('model', DEFAULT_MODEL)  # Use default model if not present
+
+            # Call the load function with the values from the CSV row
+            load(name, uri, context, model)
+
+
+# Specify the path to your CSV file
+csv_file_path = 'manifest.csv'
+
+# Process the CSV file
+process_csv(csv_file_path)

queries/manifest.csv

@@ -0,0 +1,2 @@
+filename,uri,context,model
+../_sources/activities/derivation/examples/a-plus-b.ttl,tag:prov:a-plus-b,tag:prov-demo,tag:prov-demo-model