Initial commit

.github/workflows/release.yaml

@@ -0,0 +1,19 @@
+name: "Release"
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - "v*"
+  workflow_dispatch: {}
+
+jobs:
+  validate:
+    uses: RiverBench/ci-workflows/.github/workflows/dataset-validate.yaml@main
+    secrets: inherit
+
+  release:
+    uses: RiverBench/ci-workflows/.github/workflows/dataset-release.yaml@main
+    needs: validate
+    permissions: write-all
+    secrets: inherit

.github/workflows/validate.yaml

@@ -0,0 +1,11 @@
+name: "Validate"
+on:
+  pull_request:
+    branches:
+      - main
+  workflow_dispatch: {}
+
+jobs:
+  validate:
+    uses: RiverBench/ci-workflows/.github/workflows/dataset-validate.yaml@main
+    secrets: inherit

LICENSE

@@ -0,0 +1,5 @@
+PLACE HERE YOUR LICENSING INFORMATION
+
+LICENSE TEMPLATES: https://github.com/licenses/license-templates/tree/master/templates
+
+MORE TEMPLATES: https://github.com/spdx/license-list-data/tree/main/text

README.md

@@ -0,0 +1,5 @@
+# dataset-template
+
+Template for new datasets. See the [guide on creating new datasets](https://w3id.org/riverbench/documentation/creating-new-dataset) for information on how to use it.
+
+Do not edit this README. It will be overwritten automatically when you complete setting up the dataset's metadata.

metadata.ttl

@@ -0,0 +1,99 @@
+@prefix : <https://w3id.org/riverbench/temp#> .
+@prefix dcat: <http://www.w3.org/ns/dcat#> .
+@prefix dcterms: <http://purl.org/dc/terms/> .
+@prefix eurovoc: <http://eurovoc.europa.eu/> .
+@prefix foaf: <http://xmlns.com/foaf/0.1/> .
+@prefix rb: <https://w3id.org/riverbench/schema/metadata#> .
+@prefix rbdoc: <https://w3id.org/riverbench/schema/documentation#> .
+@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
+@prefix sh: <http://www.w3.org/ns/shacl#> .
+@prefix spdx: <http://spdx.org/rdf/terms#> .
+@prefix stax: <https://w3id.org/stax/ontology#> .
+@prefix void: <http://rdfs.org/ns/void#> .
+@prefix xsd: <http://www.w3.org/2001/XMLSchema#> .
+
+# This file contains the manually written metadata for the dataset.
+# The IRI of the dataset here is temporary. Real IRIs are assigned
+# automatically in CI.
+
+:dataset
+    a rb:Dataset, dcat:Dataset ;
+    dcterms:conformsTo <https://w3id.org/riverbench/schema/metadata> ;
+    dcterms:identifier "[YOUR DATASET ID (only a-z, 0-9, -)]" ;
+
+    dcterms:title "[HUMAN-READABLE NAME OF YOUR DATASET]"@en ;
+    dcterms:description """[ELABORATED DESCRIPTION OF THE DATASET]"""@en ;
+    dcterms:issued "[DATE OF INITIAL SUBMISSION TO RIVERBENCH, YYYY-MM-DD]"^^xsd:date ;
+
+    # License and attribution
+    # SPDX license list: https://spdx.org/licenses/
+    # Do not include ".html" at the end of the SPDX license URL
+    # Example of a valid URL: https://spdx.org/licenses/CC-BY-4.0
+    dcterms:license <SPDX-LICENSE-URL> ;
+    dcterms:rights "[ADDITIONAL LICENSING NOTES, IF NEEDED, OTHERWISE REMOVE THIS]"@en ;
+    # Feel free to add more creators or use any FOAF properties here
+    # All fields are optional, but at least one creator is required
+    dcterms:creator [
+        foaf:name "[YOUR NAME]" ;
+        foaf:nick "[YOUR NICK]" ;
+        foaf:homepage <LINK-TO-YOUR-PAGE> ;
+        rdfs:comment "[EXPLAIN, E.G., YOUR ROLE IN THE DATASET CREATION]"@en ;
+        # Use this property to order creators in the generated docs (from 1 to N)
+        rbdoc:hasDocWeight 1 ;
+    ] ;
+    # If applicable, add a link or multiples links to the original source of the dataset
+    dcterms:source <LINK-TO-SOURCE> ;
+
+    # Themes from EuroVoc
+    # E.g., eurovoc:4267, eurovoc:7219
+    # Use only concepts (those without numbers in their names), 
+    # not domain concepts or concept schemes.
+    # EuroVoc browser: https://op.europa.eu/en/web/eu-vocabularies/concept-scheme/-/resource?IRI=http://eurovoc.europa.eu/100141
+    dcat:theme eurovoc:ADD-AT-LEAST-ONE-THEME ;
+
+    # Technical metadata
+    # IRIs of the vocabularies and ontologies used in the dataset
+    void:vocabulary <ADD-VOCABULARY-IRIS> ;
+    # Set to number of stream elements in the dataset
+    rb:hasStreamElementCount -1 ;
+    # Stream type according to the RDF Stream Taxonomy (RDF-STaX)
+    # Each dataset must have two stream type usages: one for the grouped
+    # stream type and one for the flat stream type.
+    # Full list of stream types: https://w3id.org/stax/dev/taxonomy/
+    stax:hasStreamTypeUsage [
+        a stax:RdfStreamTypeUsage ;
+        rdfs:comment "[GROUPED STREAM TYPE EXPLANATION]"@en ;
+        stax:hasStreamType stax:GROUPED-STREAM-TYPE-IRI ;
+    ] , [
+        a stax:RdfStreamTypeUsage ;
+        rdfs:comment "[FLAT STREAM TYPE EXPLANATION]"@en ;
+        stax:hasStreamType stax:FLAT-STREAM-TYPE-IRI ;
+    ] ;
+    rb:hasStreamElementSplit [
+        # At least one of: rb:StatementCountStreamElementSplit,
+        #   rb:TimeStreamElementSplit, rb:TopicStreamElementSplit
+        a <SPLIT-TYPE> ;
+
+        # If your dataset is split by time, you must specify the temporal property.
+        # Example: https://github.com/RiverBench/dataset-assist-iot-weather-graphs/blob/main/metadata.ttl
+        # rb:hasTemporalProperty <PROPERTY-IRI> ;
+
+        rdfs:comment "[FURTHER EXPLANATION ON THE SPLIT]"@en ;
+
+        # If your dataset is an RDF subject graph stream, you must specify the
+        # subject node shape using SHACL.
+        # Example: https://github.com/RiverBench/dataset-linked-spending/blob/main/metadata.ttl
+        # SHACL documentation: https://www.w3.org/TR/shacl/#constraints-section
+        # rb:hasSubjectShape [  ] ;
+    ] ;
+    rb:conformsToRdf11 "" ; # true or false
+    rb:conformsToRdfStarDraft_20211217 "" ; # true or false
+    rb:usesGeneralizedRdfDatasets "" ; # true or false
+    rb:usesGeneralizedTriples "" ; # true or false
+    rb:usesRdfStar "" ; # true or false
+
+    # Add any additional metadata here
+    # Examples of useful properties:
+    # dcat:temporalResolution, dcat:spatialResolutionInMeters,
+    # dcterms:language
+.