Skip to content

Data source improvement #1

Data source improvement

Data source improvement #1

name: Validate Changed Attack Data Files
on:
pull_request:
branches: [ master, main ]
types: [opened, synchronize, reopened]
paths:
- 'datasets/**/*.yml'
- 'datasets/**/*.yaml'
jobs:
validate-changed-files:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
lfs: true
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.9'
cache: 'pip'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install -r bin/requirements.txt
- name: Get changed YAML files
id: changed-files
uses: tj-actions/changed-files@v41
with:
files: |
datasets/**/*.yml
datasets/**/*.yaml
separator: ","
- name: Validate changed YAML files
if: steps.changed-files.outputs.any_changed == 'true'
run: |
echo "Changed YAML files:"
echo "${{ steps.changed-files.outputs.all_changed_files }}"
# Create a temporary script to validate only changed files
cat > validate_changed.py << 'EOF'
#!/usr/bin/env python3
import sys
import os
sys.path.insert(0, os.path.join(os.path.dirname(__file__), 'bin'))
from validate import load_yaml_schema, validate_yaml_file
from pathlib import Path
# Get changed files from environment
changed_files = os.environ.get('CHANGED_FILES', '').split(',')
changed_files = [f.strip() for f in changed_files if f.strip()]
if not changed_files:
print("No changed YAML files to validate")
sys.exit(0)
# Load schema
schema = load_yaml_schema()
total_files = len(changed_files)
valid_files = 0
invalid_files = 0
failed_validations = []
print(f"Validating {total_files} changed YAML file(s)...")
print("-" * 60)
for file_path in changed_files:
yaml_file = Path(file_path)
if not yaml_file.exists():
print(f"⚠️ File not found (may have been deleted): {yaml_file}")
continue
print(f"\nValidating: {yaml_file}")
errors = validate_yaml_file(yaml_file, schema)
if errors:
invalid_files += 1
print(f"❌ INVALID - {len(errors)} error(s):")
for error in errors:
print(f" • {error}")
failed_validations.append((yaml_file, errors))
else:
valid_files += 1
print("✅ VALID")
# Print summary
print("\n" + "=" * 60)
print("VALIDATION SUMMARY")
print("=" * 60)
print(f"Total files processed: {valid_files + invalid_files}")
print(f"Valid files: {valid_files}")
print(f"Invalid files: {invalid_files}")
if invalid_files > 0:
print(f"\n❌ {invalid_files} file(s) failed validation!")
sys.exit(1)
else:
print("\n✅ All changed files passed validation!")
EOF
# Run validation on changed files
CHANGED_FILES="${{ steps.changed-files.outputs.all_changed_files }}" python validate_changed.py
env:
PYTHONPATH: ${{ github.workspace }}/bin
- name: No YAML files changed
if: steps.changed-files.outputs.any_changed == 'false'
run: |
echo "No YAML files were changed in this PR. Skipping validation."
- name: Comment PR on validation failure
if: failure() && steps.changed-files.outputs.any_changed == 'true'
uses: actions/github-script@v7
with:
script: |
const { owner, repo, number } = context.issue;
await github.rest.issues.createComment({
owner,
repo,
issue_number: number,
body: `❌ **Changed Files Validation Failed**
The following changed YAML files in this PR do not pass validation:
\`\`\`
${{ steps.changed-files.outputs.all_changed_files }}
\`\`\`
Please check the workflow logs for detailed error messages and fix the issues before merging.
[View workflow run](${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }})`
});
- name: Comment PR on validation success
if: success() && steps.changed-files.outputs.any_changed == 'true'
uses: actions/github-script@v7
with:
script: |
const { owner, repo, number } = context.issue;
await github.rest.issues.createComment({
owner,
repo,
issue_number: number,
body: `✅ **Changed Files Validation Passed**
All changed YAML files in this PR have been successfully validated:
\`\`\`
${{ steps.changed-files.outputs.all_changed_files }}
\`\`\`
Ready for review and merge! 🚀`
});