workflowhub integration

.github/actions/workflowhub/action.yml

@@ -0,0 +1,18 @@
+name: Update WorkflowHub data
+description: Generate validated Jekyll data from a configured WorkflowHub collection
+
+runs:
+  using: composite
+  steps:
+    - name: Set up Python
+      uses: actions/setup-python@v7
+      with:
+        python-version: "3.12"
+
+    - name: Install dependencies
+      shell: bash
+      run: python -m pip install "requests>=2.32,<3" "PyYAML>=6,<7"
+
+    - name: Generate WorkflowHub data
+      shell: bash
+      run: python "$GITHUB_ACTION_PATH/workflowhub_finder.py"

.github/actions/workflowhub/workflowhub_finder.py

@@ -0,0 +1,198 @@
+#!/usr/bin/env python3
+import os
+import tempfile
+from pathlib import Path
+
+import requests
+import yaml
+
+
+DEFAULT_BASE_URL = "https://workflowhub.eu"
+OUTPUT_PATH = Path("_data/data_workflows.yaml")
+REQUEST_TIMEOUT = 30.0
+REQUIRED_FIELDS = ("title", "url")
+
+
+class WorkflowHubClient:
+    def __init__(self, base_url, collection_id, timeout=REQUEST_TIMEOUT):
+        self.base_url = base_url.rstrip("/")
+        self.collection_id = collection_id
+        self.timeout = timeout
+
+    def _get_json(self, path):
+        response = requests.get(f"{self.base_url}/{path}", timeout=self.timeout)
+        response.raise_for_status()
+        return response.json()
+
+    def _workflow_ids(self):
+        items = self._get_json(
+            f"collections/{self.collection_id}/items.json"
+        )["data"]
+        return [
+            item["relationships"]["asset"]["data"]["id"] for item in items
+        ]
+
+    def _projects(self):
+        projects = self._get_json("projects.json")["data"]
+        return {
+            project["id"]: project["attributes"]["title"] for project in projects
+        }
+
+    @staticmethod
+    def _render_workflow(metadata, project_titles):
+        data = metadata["data"]
+        attributes = data["attributes"]
+        latest_version = attributes["latest_version"]
+        remote = next(
+            (
+                version.get("remote", "")
+                for version in attributes.get("versions", [])
+                if version.get("version") == latest_version
+            ),
+            "",
+        )
+        project_ids = (
+            data.get("relationships", {}).get("projects", {}).get("data", [])
+        )
+        projects = list(
+            dict.fromkeys(
+                project_titles[item["id"]]
+                for item in project_ids
+                if item["id"] in project_titles
+            )
+        )
+        workflow_class = attributes.get("workflow_class") or {}
+
+        return {
+            "title": attributes.get("title", "").replace("_", " "),
+            "class": workflow_class.get("key", ""),
+            "url": data.get("links", {}).get("self", ""),
+            "remote_link": remote,
+            "edam_top": [
+                annotation["label"]
+                for annotation in attributes.get("topic_annotations", [])
+            ] or "",
+            "edam_ops": [
+                annotation["label"]
+                for annotation in attributes.get("operation_annotations", [])
+            ] or "",
+            "license": attributes.get("license") or "",
+            "updated_at": (attributes.get("updated_at") or "").split("T")[0],
+            "doi": attributes.get("doi") or "",
+            "projects": projects or "",
+            "tools": attributes.get("tools") or "",
+        }
+
+    def workflows(self):
+        project_titles = self._projects()
+        workflows = [
+            self._render_workflow(
+                self._get_json(f"workflows/{workflow_id}.json"), project_titles
+            )
+            for workflow_id in sorted(set(self._workflow_ids()), key=str)
+        ]
+        return sorted(
+            workflows,
+            key=lambda workflow: (workflow["title"].casefold(), workflow["url"]),
+        )
+
+
+def load_workflows(path):
+    try:
+        data = yaml.safe_load(path.read_text(encoding="utf-8"))
+    except (OSError, yaml.YAMLError) as error:
+        raise ValueError(f"Could not read valid YAML from {path}: {error}") from error
+    if not isinstance(data, list):
+        raise ValueError(f"{path} must contain a top-level list")
+    return data
+
+
+def validate_workflows(workflows):
+    urls = set()
+    for index, workflow in enumerate(workflows, start=1):
+        if not isinstance(workflow, dict):
+            raise ValueError(f"Workflow {index} must be a mapping")
+        missing = [field for field in REQUIRED_FIELDS if not workflow.get(field)]
+        if missing:
+            raise ValueError(
+                f"Workflow {index} is missing required values: {', '.join(missing)}"
+            )
+        if workflow["url"] in urls:
+            raise ValueError(f"Duplicate workflow URL: {workflow['url']}")
+        urls.add(workflow["url"])
+
+
+def serialise_workflows(workflows):
+    return yaml.safe_dump(
+        workflows,
+        default_flow_style=False,
+        sort_keys=True,
+        allow_unicode=True,
+    )
+
+
+def update_workflow_file(workflows, output=OUTPUT_PATH):
+    baseline = load_workflows(output) if output.exists() else None
+    validate_workflows(workflows)
+    if baseline and not workflows:
+        raise ValueError("Refusing to replace a non-empty dataset with an empty result")
+    rendered = serialise_workflows(workflows)
+
+    if output.exists() and output.read_text(encoding="utf-8") == rendered:
+        return False
+
+    output.parent.mkdir(parents=True, exist_ok=True)
+    temporary_path = None
+    try:
+        with tempfile.NamedTemporaryFile(
+            mode="w",
+            encoding="utf-8",
+            dir=output.parent,
+            prefix=f".{output.name}.",
+            suffix=".tmp",
+            delete=False,
+        ) as temporary_file:
+            temporary_file.write(rendered)
+            temporary_path = Path(temporary_file.name)
+        os.replace(temporary_path, output)
+    finally:
+        if temporary_path and temporary_path.exists():
+            temporary_path.unlink()
+    return True
+
+
+def load_site_config(path):
+    try:
+        config = yaml.safe_load(path.read_text(encoding="utf-8")) or {}
+    except (OSError, yaml.YAMLError) as error:
+        raise ValueError(f"Could not read site configuration from {path}: {error}") from error
+
+    integration = config.get("workflowhub")
+    if not isinstance(integration, dict) or not integration.get("enabled", False):
+        return None
+    if integration.get("collection_id") in (None, ""):
+        raise ValueError("workflowhub.collection_id is required when enabled")
+    return {
+        "base_url": integration.get("base_url") or DEFAULT_BASE_URL,
+        "collection_id": int(integration["collection_id"]),
+    }
+
+
+def main():
+    settings = load_site_config(Path("_config.yml"))
+    if settings is None:
+        print("WorkflowHub integration is disabled; nothing to generate")
+        return
+
+    client = WorkflowHubClient(**settings)
+    workflows = client.workflows()
+    changed = update_workflow_file(workflows)
+    status = "Updated" if changed else "No changes to"
+    print(f"{status} {OUTPUT_PATH} ({len(workflows)} workflows)")
+
+
+if __name__ == "__main__":
+    try:
+        main()
+    except (ValueError, requests.RequestException) as error:
+        raise SystemExit(f"WorkflowHub update failed: {error}") from error

.github/workflows/workflowhub.yml

@@ -0,0 +1,48 @@
+name: Update WorkflowHub data
+
+on:
+  workflow_call:
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pull-requests: write
+
+concurrency:
+  group: update-workflowhub-data
+  cancel-in-progress: false
+
+jobs:
+  update:
+    runs-on: ubuntu-24.04
+    steps:
+      - name: Check out website
+        uses: actions/checkout@v7
+        with:
+          ref: ${{ github.event.repository.default_branch }}
+
+      - name: Check out WorkflowHub integration
+        uses: actions/checkout@v7
+        with:
+          repository: ${{ job.workflow_repository }}
+          ref: ${{ job.workflow_sha }}
+          path: .workflowhub-theme
+
+      - name: Update WorkflowHub data
+        uses: ./.workflowhub-theme/.github/actions/workflowhub
+
+      - name: Remove integration checkout
+        shell: bash
+        run: rm -rf -- .workflowhub-theme
+
+      - name: Create or update pull request
+        uses: peter-evans/create-pull-request@v8
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          commit-message: Update WorkflowHub workflow data
+          title: Update WorkflowHub workflow data
+          body: Automated refresh of validated WorkflowHub collection data.
+          branch: automation/update-workflowhub-data
+          base: ${{ github.event.repository.default_branch }}
+          add-paths: _data/data_workflows.yaml
+          delete-branch: true

.gitignore

@@ -9,4 +9,5 @@ _site/
 vendor/
 .vscode/
 Gemfile.lock
-.ruby-version
+.ruby-version
+**/__pycache__/

_config.yml

@@ -10,6 +10,10 @@ title: ELIXIR Toolkit Theme
 description: "Flexible Jekyll theme using bootstrap 5 as CSS framework."
 # Metadata description of the website
 
+workflowhub:
+  enabled: true
+  collection_id: 40
+
 dsw_deep_link_prefix: https://researchers.ds-wizard.org/knowledge-models/dsw:root:latest/preview?questionUuid=
 # prefix for DSW deep links to a certain question
 

_data/data_workflows.yaml

@@ -0,0 +1,31 @@
+- class: nextflow
+  doi: 10.48546/workflowhub.workflow.2318.1
+  edam_ops:
+  - Protein interaction prediction
+  - Protein quaternary structure prediction
+  - Protein structure analysis
+  - Protein structure prediction
+  edam_top:
+  - Protein folds and structural domains
+  - Protein structure analysis
+  - Structure prediction
+  license: MIT
+  projects:
+  - Lucet Laboratory (WEHI)
+  remote_link: ''
+  title: nf-boltz-2
+  tools: ''
+  updated_at: '2026-09-28'
+  url: /workflows/2318?version=1
+- class: nextflow
+  doi: ''
+  edam_ops: ''
+  edam_top: ''
+  license: MIT
+  projects:
+  - nf-core
+  remote_link: https://github.com/nf-core/proteinfold.git
+  title: nf-core/proteinfold
+  tools: ''
+  updated_at: '2026-05-13'
+  url: /workflows/1011?version=3

_data/sidebars/main.yml

@@ -33,6 +33,8 @@ subitems:
         url: /resource_table
       - title: Supported by
         url: /supported_by
+      - title: WorkflowHub workflows table
+        url: /workflowhub_integration
   - title: Versions and upgrades
     icon: icon-refresh-cw
     subitems:
@@ -70,6 +72,8 @@ subitems:
             url: /general_page_7
       - title: All training
         url: /all_trainings
+      - title: Workflows
+        url: /workflows
       - title: List of page IDs
         url: /list_page_ids
   - title: Page Not Found