.github: add check-license-header workflow

this workflow checks the first 10 lines for
"LicenseRef-ScyllaDB-Source-Available-1.0" in newly introduced files
when a new pull request is created against "master" or "next".

if "LicenseRef-ScyllaDB-Source-Available-1.0" is not found, the
workflow fails. for the sake of simplicity, instead of parsing the
header for SPDX License ID, we just check to see if the
"LicenseRef-ScyllaDB-Source-Available-1.0" is included.

Signed-off-by: Kefu Chai <[email protected]>

.github/scripts/check-license.py

@@ -0,0 +1,74 @@
+#!/usr/bin/env python3
+
+import argparse
+import sys
+from pathlib import Path
+from typing import Set
+
+
+def parse_args() -> argparse.Namespace:
+    """Parses command-line arguments."""
+    parser = argparse.ArgumentParser(description='Check license headers in files')
+    parser.add_argument('--files', required=True, nargs="+", type=Path,
+                        help='List of files to check')
+    parser.add_argument('--license', required=True,
+                        help='License to check for')
+    parser.add_argument('--check-lines', type=int, default=10,
+                        help='Number of lines to check (default: %(default)s)')
+    parser.add_argument('--extensions', required=True, nargs="+",
+                        help='List of file extensions to check')
+    parser.add_argument('--verbose', action='store_true',
+                        help='Print verbose output (default: %(default)s)')
+    return parser.parse_args()
+
+
+def should_check_file(file_path: Path, allowed_extensions: Set[str]) -> bool:
+    return file_path.suffix in allowed_extensions
+
+
+def check_license_header(file_path: Path, license_header: str, check_lines: int) -> bool:
+    try:
+        with open(file_path, 'r', encoding='utf-8') as f:
+            for _ in range(check_lines):
+                line = f.readline()
+                if license_header in line:
+                    return True
+        return False
+    except (UnicodeDecodeError, StopIteration):
+        # Handle files that can't be read as text or have fewer lines
+        return False
+
+
+def main() -> int:
+    args = parse_args()
+
+    if not args.files:
+        print("No files to check")
+        return 0
+
+    num_errors = 0
+
+    for file_path in args.files:
+        # Skip non-existent files
+        if not file_path.exists():
+            continue
+
+        # Skip files with non-matching extensions
+        if not should_check_file(file_path, args.extensions):
+            print(f"ℹ️ Skipping file with unchecked extension: {file_path}")
+            continue
+
+        # Check license header
+        if check_license_header(file_path, args.license, args.check_lines):
+            if args.verbose:
+                print(f"✅ License header found in: {file_path}")
+        else:
+            print(f"❌ Missing license header in: {file_path}")
+            num_errors += 1
+
+    if num_errors > 0:
+        sys.exit(1)
+
+
+if __name__ == '__main__':
+    main()

.github/workflows/check-license-header.yaml

@@ -0,0 +1,51 @@
+name: License Header Check
+
+on:
+  pull_request:
+    types: [opened, synchronize, reopened]
+    branches:
+      - master
+      - next
+
+env:
+  HEADER_CHECK_LINES: 10
+  LICENSE: "LicenseRef-ScyllaDB-Source-Available-1.0"
+  CHECKED_EXTENSIONS: ".cc .hh .py"
+
+jobs:
+  check-license-headers:
+    name: Check License Headers
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Get changed files
+        id: changed-files
+        run: |
+          # Get list of added files comparing with base branch
+          echo "files=$(git diff --name-only --diff-filter=A ${{ github.event.pull_request.base.sha }} ${{ github.sha }} | tr '\n' ' ')" >> $GITHUB_OUTPUT
+
+      - name: Check license headers
+        run: |
+          .github/scripts/check-license.py \
+            --files ${{ steps.changed-files.outputs.files }} \
+            --license "${{ env.LICENSE }}" \
+            --check-lines "${{ env.HEADER_CHECK_LINES }}" \
+            --extensions ${{ env.CHECKED_EXTENSIONS }}
+
+      - name: Comment on PR if check fails
+        if: failure()
+        uses: actions/github-script@v7
+        with:
+          script: |
+            const licenseHeader = '${{ env.LICENSE_HEADER }}';
+            github.rest.issues.createComment({
+              issue_number: context.issue.number,
+              owner: context.repo.owner,
+              repo: context.repo.name,
+              body: `❌ License header check failed. Please ensure all new files include the header within the first ${{ env.HEADER_CHECK_LINES }} lines:\n\`\`\`\n${licenseHeader}\n\`\`\`\nSee action logs for details.`
+            })