Merge pull request #11 from esl-epfl/pr-yaml

Add schema definition

.github/workflows/docker-publish-algo-checks.yml

@@ -0,0 +1,97 @@
+name: Publish algorithm checker container
+
+# This workflow uses actions that are not certified by GitHub.
+# They are provided by a third-party and are governed by
+# separate terms of service, privacy policy, and support
+# documentation.
+
+on:
+  push:
+    branches: [ "main" ]
+    paths: "config/algo-checks.Dockerfile"
+  pull_request:
+    branches: [ "main" ]
+    paths: "config/algo-checks.Dockerfile"
+
+env:
+  # Use docker.io for Docker Hub if empty
+  REGISTRY: ghcr.io
+  # github.repository as <account>/<repo>
+  IMAGE_NAME: ${{ github.repository }}-algo-checks
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+      # This is used to complete the identity challenge
+      # with sigstore/fulcio when running outside of PRs.
+      id-token: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      # Install the cosign tool except on PR
+      # https://github.com/sigstore/cosign-installer
+      - name: Install cosign
+        if: github.event_name != 'pull_request'
+        uses: sigstore/cosign-installer@59acb6260d9c0ba8f4a2f9d9b48431a222b68e20 #v3.5.0
+        with:
+          cosign-release: 'v2.2.4'
+
+      # Set up BuildKit Docker container builder to be able to build
+      # multi-platform images and export cache
+      # https://github.com/docker/setup-buildx-action
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@f95db51fddba0c2d1ec667646a06c2ce06100226 # v3.0.0
+
+      # Login against a Docker registry except on PR
+      # https://github.com/docker/login-action
+      - name: Log into registry ${{ env.REGISTRY }}
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@343f7c4344506bcbf9b4de18042ae17996df046d # v3.0.0
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Extract metadata (tags, labels) for Docker
+      # https://github.com/docker/metadata-action
+      - name: Extract Docker metadata
+        id: meta
+        uses: docker/metadata-action@96383f45573cb7f253c731d3b3ab81c87ef81934 # v5.0.0
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      # Build and push Docker image with Buildx (don't push on PR)
+      # https://github.com/docker/build-push-action
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@0565240e2d4ab88bba5387d719585280857ece09 # v5.0.0
+        with:
+          context: ./evaluation
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          file: config/algo-checks.Dockerfile
+
+      # Sign the resulting Docker image digest except on PRs.
+      # This will only write to the public Rekor transparency log when the Docker
+      # repository is public to avoid leaking data.  If you would like to publish
+      # transparency data even for private images, pass --force to cosign below.
+      # https://github.com/sigstore/cosign
+      - name: Sign the published Docker image
+        if: ${{ github.event_name != 'pull_request' }}
+        env:
+          # https://docs.github.com/en/actions/security-guides/security-hardening-for-github-actions#using-an-intermediate-environment-variable
+          TAGS: ${{ steps.meta.outputs.tags }}
+          DIGEST: ${{ steps.build-and-push.outputs.digest }}
+        # This step uses the identity token to provision an ephemeral certificate
+        # against the sigstore community Fulcio instance.
+        run: echo "${TAGS}" | xargs -I {} cosign sign --yes {}@${DIGEST}
+

.github/workflows/pr-check.yml

@@ -1,31 +1,55 @@
-name: PR checks for algorithm submission
+name: PR checks fon algorithm submission
 
 on:
   pull_request:
     paths:
       - 'algorithms/*.yaml'
-
-env:
-  IMAGE_NAME: ${{ github.repository }}-evaluator
+  push:
+    paths:
+      - 'algorithms/*.yaml'
 
 jobs:
 
   check_yaml:
+    runs-on: ubuntu-latest
     container:
-      image: ghcr.io/${{ env.IMAGE_NAME }}
+      image: ghcr.io/${{ github.repository }}-algo-checks:latest
       credentials:
         username: ${{ github.actor }}
         password: ${{ secrets.github_token }}
     steps:
 
-      - name: Convert yaml
-        run: yq -o json FILE.yaml > FILE.json
-
-      - name: Validate jsonschema
-        run: jsonschema-cli -i FILE.json SCHEMA.json
+      - name: find algorithm files
+        run: |
+          {
+            echo 'FILELIST<<EOF'
+            find ./algorithms -name '*.yaml' -print
+            echo EOF
+          }  >> "$GITHUB_ENV"
+
+      - name: Convert and validate using jsonschema
+        run: |
+          for algo in ${FILELIST}; do
+            yq -o json $algo > algo.json \
+            && jsonschema-cli -i algo.json "config/schema.json"
+          done
+          rm algo.json
 
   check_image:
+    runs-on: ubuntu-latest
     steps:
+
+      - name: find algorithm files
+        run: |
+          {
+            echo 'FILELIST<<EOF'
+            find ./algorithms -name '*.yaml' -print
+            echo EOF
+          }  >> "$GITHUB_ENV"
+
       - name: Pull image
-        run: docker pull $(sed 's/^image: \(.*\)$' FILE.yaml)
+        run: |
+          for algo in ${FILELIST}; do 
+            docker pull $(sed 's/^image: \+\(.*\)$/\1/' $algo)
+          done
 

algorithms/algorithm.yaml

@@ -1,40 +1,41 @@
 ---
 # Description of a seizure detection algorithm
 title: My Research Software
-repository-code: "https://github.com/citation-file-format/my-research-software"
+image: "ghcr.io/username/image-name:tag"
 authors:
   - family-names: Druskat
     given-names: Stephan
     orcid: "https://orcid.org/1234-5678-9101-1121"
   - name: "The Research Software project"
 version: 0.11.2
 date-released: "2024-10-24"
-description: This algorithm performs random detection of epileptic seizures. On each epoch of 1 second it assigns a 30% probability of being a seizure.
+abstract: This algorithm performs random detection of epileptic seizures. On each epoch of 1 second it assigns a 30% probability of being a seizure.
 license: Apache-2.0
+repository: https://github.com/
 message: If you use this software, please cite it using these metadata.
 
 # List all datasets that were used to train this algorithm
 Dataset:
     - title: Physionet CHB-MIT Scalp EEG Database
-      license: ODC-By v1.0
+      license: CC-BY-1.0
       identifiers:
         - description: Zenodo BIDS standardized version of CHB-MIT Scalp EEG database
           type: doi
           value: "10.5281/zenodo.123456"
     - title: TUH EEG Seizure Corpus
-      license: Private
+      license: https://isip.piconepress.com/projects/nedc/forms/tuh_eeg.pdf
       identifiers:
         - description: Temple University Seizure Corpus
           type: url
           value: "https://isip.piconepress.com/projects/nedc/html/tuh_eeg/#c_tusz"
     - title: Siena Scalp EEG
-      license: ODC-By v1.0
+      license: CC-BY-1.0
       identifiers:
         - description: Zenodo BIDS standardized version of Siena Scalp EEG database
           type: doi
           value: "10.5281/zenodo.10640762"
     - title: SeizeIT1
-      license: Custom KU Leuven
+      license: https://www.kuleuven.be/rdm/en/rdr/custom-kuleuven
       identifiers:
         - description: KU Lueven SeizeIT1 dataset
           type: doi

config/algo-checks.Dockerfile

@@ -1,3 +1,4 @@
+# Dockerfile
 # Provides dependencies to verify algorithm definition files 
 # and validate them against schema