Adding initial version of Cirro validation to CI/CD (#276)

* Adding initial version of Cirro validation to CI/CD

* Adding Cirro validation to CONTRIBUTING.md

* Adding permissions to linting.yml

Author: tefirman

.github/CONTRIBUTING.md

@@ -175,6 +175,8 @@ Pipelines may include optional platform-specific configuration directories for e
 
 Platform configurations are entirely optional and should not be required to run the pipeline with standard WDL executors (Cromwell, miniWDL, Sprocket).
 
+**Cirro Configuration Validation**: Pipelines with `.cirro/` directories are automatically validated in CI. The validation checks that all required files are present (`preprocess.py`, `process-form.json`, `process-input.json`, `process-output.json`, `process-compute.config`), JSON files are valid, and `preprocess.py` has no syntax errors. You can run this locally with `make lint_cirro`.
+
 ## Testing Requirements
 
 ### Local Tests
@@ -256,6 +258,7 @@ All contributions must pass our automated testing pipeline which executes on a P
 - **Container verification**: All Docker images must be accessible and functional
 - **Syntax validation**: WDL syntax and structure validation
 - **Integration testing**: Cross-module compatibility testing
+- **Cirro validation**: Validates `.cirro/` configurations for pipelines that include them
 
 ## Documentation Website
 

.github/scripts/validate_cirro.py

@@ -0,0 +1,173 @@
+#!/usr/bin/env python3
+"""
+Validate .cirro configurations in WILDS pipelines.
+
+Checks that .cirro directories contain the required files,
+JSON files are valid, and preprocess.py has no syntax errors.
+"""
+
+import json
+import sys
+from pathlib import Path
+
+REQUIRED_FILES = [
+    "preprocess.py",
+    "process-form.json",
+    "process-input.json",
+    "process-output.json",
+    "process-compute.config",
+]
+
+def validate_json_file(filepath):
+    """Validate that a file contains valid JSON. Returns list of error strings."""
+    errors = []
+    try:
+        with open(filepath) as f:
+            data = json.load(f)
+    except json.JSONDecodeError as e:
+        errors.append(f"  Invalid JSON in {filepath.name}: {e}")
+        return errors, None
+    return errors, data
+
+
+def validate_form(filepath):
+    """Validate process-form.json has expected structure."""
+    errors, data = validate_json_file(filepath)
+    if data is None:
+        return errors
+
+    if not isinstance(data, dict):
+        errors.append(f"  {filepath.name}: expected a JSON object at top level")
+        return errors
+
+    if "form" not in data:
+        errors.append(f"  {filepath.name}: missing top-level 'form' key")
+        return errors
+
+    form = data["form"]
+    if not isinstance(form, dict):
+        errors.append(f"  {filepath.name}: 'form' should be an object")
+        return errors
+
+    if "properties" not in form:
+        errors.append(f"  {filepath.name}: 'form' missing 'properties' key")
+
+    if "required" in form and not isinstance(form["required"], list):
+        errors.append(f"  {filepath.name}: 'required' should be a list")
+
+    return errors
+
+
+def validate_input(filepath):
+    """Validate process-input.json has JSON path mappings."""
+    errors, data = validate_json_file(filepath)
+    if data is None:
+        return errors
+
+    if not isinstance(data, dict):
+        errors.append(f"  {filepath.name}: expected a JSON object")
+        return errors
+
+    for key, value in data.items():
+        if not isinstance(value, str):
+            errors.append(f"  {filepath.name}: value for '{key}' should be a string, got {type(value).__name__}")
+        elif not value.startswith("$."):
+            errors.append(f"  {filepath.name}: value for '{key}' should be a JSON path (start with '$.')")
+
+    return errors
+
+
+def validate_output(filepath):
+    """Validate process-output.json is valid JSON."""
+    errors, _ = validate_json_file(filepath)
+    return errors
+
+
+def validate_preprocess(filepath):
+    """Validate preprocess.py has no syntax errors."""
+    errors = []
+    try:
+        source = filepath.read_text()
+        compile(source, str(filepath), "exec")
+    except SyntaxError as e:
+        errors.append(f"  {filepath.name}: Python syntax error: {e}")
+    return errors
+
+
+def validate_cirro_dir(cirro_dir):
+    """Validate a single .cirro directory. Returns list of error strings."""
+    errors = []
+
+    # Check required files
+    for filename in REQUIRED_FILES:
+        if not (cirro_dir / filename).exists():
+            errors.append(f"  Missing required file: {filename}")
+
+    # Validate individual files
+    form_path = cirro_dir / "process-form.json"
+    if form_path.exists():
+        errors.extend(validate_form(form_path))
+
+    input_path = cirro_dir / "process-input.json"
+    if input_path.exists():
+        errors.extend(validate_input(input_path))
+
+    output_path = cirro_dir / "process-output.json"
+    if output_path.exists():
+        errors.extend(validate_output(output_path))
+
+    preprocess_path = cirro_dir / "preprocess.py"
+    if preprocess_path.exists():
+        errors.extend(validate_preprocess(preprocess_path))
+
+    return errors
+
+
+def main():
+    pipelines_dir = Path("pipelines")
+    if not pipelines_dir.exists():
+        print("No pipelines directory found")
+        return 0
+
+    found_any = False
+    all_errors = {}
+
+    for pipeline_dir in sorted(pipelines_dir.iterdir()):
+        if not pipeline_dir.is_dir():
+            continue
+
+        cirro_dir = pipeline_dir / ".cirro"
+        if not cirro_dir.is_dir():
+            print(f"Skipping {pipeline_dir.name} (no .cirro directory)")
+            continue
+
+        found_any = True
+        print(f"Validating {pipeline_dir.name}/.cirro/ ...")
+        errors = validate_cirro_dir(cirro_dir)
+
+        if errors:
+            all_errors[pipeline_dir.name] = errors
+            print(f"  FAIL ({len(errors)} issue(s))")
+        else:
+            print(f"  OK")
+
+    if not found_any:
+        print("No .cirro directories found in any pipeline")
+        return 0
+
+    if all_errors:
+        print(f"\n{'='*50}")
+        print(f"Cirro validation failed for {len(all_errors)} pipeline(s):\n")
+        for pipeline, errors in all_errors.items():
+            print(f"{pipeline}:")
+            for error in errors:
+                print(error)
+            print()
+        return 1
+
+    print(f"\nAll Cirro configurations valid!")
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

.github/workflows/linting.yml

@@ -8,6 +8,9 @@ on:
   pull_request:
     types: [opened, reopened, synchronize]
 
+permissions:
+  contents: read
+
 jobs:
   miniwdl_check:
     runs-on: ubuntu-latest
@@ -80,3 +83,18 @@ jobs:
       uses: stjude-rust-labs/sprocket-action@v0.10.0
       with:
         action: lint
+
+  cirro_validation:
+    runs-on: ubuntu-latest
+    steps:
+    -
+      name: Checkout
+      uses: actions/checkout@v4
+    -
+      name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.13
+    -
+      name: Validate Cirro Configurations
+      run: python .github/scripts/validate_cirro.py

Makefile

@@ -146,7 +146,11 @@ lint_womtool: check_java check_womtool check_name ## Run WOMtool validate on mod
 	done
 
 
-lint: lint_sprocket lint_miniwdl lint_womtool ## Run all linting checks
+lint_cirro: ## Validate .cirro configurations in pipelines
+	@echo "Validating Cirro configurations..."
+	@python3 .github/scripts/validate_cirro.py
+
+lint: lint_sprocket lint_miniwdl lint_womtool lint_cirro ## Run all linting checks
 
 ##@ Run