From 18e31f1805b4ac6e861a9f51e434d6a8ef5e5b38 Mon Sep 17 00:00:00 2001
From: Nikolay Martyanov <nikolay@zededa.com>
Date: Tue, 27 Aug 2024 01:42:36 +0200
Subject: [PATCH] github: Add GH Action to check SPDX license headers in new
 files.

- Created a workflow to automatically check for SPDX license headers in
  new files when a PR is opened or changes are pushed to `master` or version-stable branches.
- Added `tools/spdx-check.sh` script that scans new files with specific
  extensions and certain filenames for the `SPDX-License-Identifier`
  header.
- The script excludes files in `vendor/` directories from the check.
- The workflow will fail if any of the new files are missing the required SPDX license header.

Signed-off-by: Nikolay Martyanov <nikolay@zededa.com>
---
 .github/workflows/spdx.yml | 29 +++++++++++++++++++++
 tools/spdx-check.sh        | 52 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+)
 create mode 100644 .github/workflows/spdx.yml
 create mode 100755 tools/spdx-check.sh

diff --git a/.github/workflows/spdx.yml b/.github/workflows/spdx.yml
new file mode 100644
index 00000000000..1d3cc4db931
--- /dev/null
+++ b/.github/workflows/spdx.yml
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: Apache-2.0
+---
+name: Check SPDX License Headers
+
+on:
+  push:
+    branches:
+      - "master"
+      - "[0-9]+.[0-9]+"
+      - "[0-9]+.[0-9]+-stable"
+  pull_request:
+    branches:
+      - "master"
+      - "[0-9]+.[0-9]+"
+      - "[0-9]+.[0-9]+-stable"
+
+jobs:
+  spdx-check:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Run SPDX check
+        run: |
+          chmod +x ./tools/check_spdx.sh
+          ./tools/check_spdx.sh
\ No newline at end of file
diff --git a/tools/spdx-check.sh b/tools/spdx-check.sh
new file mode 100755
index 00000000000..a6bb8871f0b
--- /dev/null
+++ b/tools/spdx-check.sh
@@ -0,0 +1,52 @@
+#!/bin/bash
+
+# Copyright (c) 2024 Zededa, Inc.
+# SPDX-License-Identifier: Apache-2.0
+
+# List of files to check, excluding vendor directories
+files=$(git diff --name-only --diff-filter=A origin/master..HEAD | grep -v "vendor/")
+
+# SPDX License Identifier to check for
+license_identifier="SPDX-License-Identifier:"
+
+# Array of file extensions to check for SPDX header
+file_extensions=("sh" "c" "go" "py" "rs" "yaml" "yml")
+file_names=("Dockerfile" "Makefile")
+
+# Flag to check if all files contain the SPDX header
+all_files_contain_spdx=true
+
+# Loop through the files and check for the SPDX header
+for file in $files; do
+  # Get the file extension
+  file_extension="${file##*.}"
+
+  # Check if the file is a source file that should have a license header
+  for ext in "${file_extensions[@]}"; do
+    if [[ "$file_extension" == "$ext" ]]; then
+      # Check if the file contains the SPDX identifier
+      if ! grep -q "$license_identifier" "$file"; then
+        all_files_contain_spdx=false
+        echo "Missing SPDX-License-Identifier in $file"
+      fi
+      break
+    fi
+  done
+  for name in "${file_names[@]}"; do
+    if [[ "$file" == "$name" ]]; then
+      # Check if the file contains the SPDX identifier
+      if ! grep -q "$license_identifier" "$file"; then
+        all_files_contain_spdx=false
+        echo "Missing SPDX-License-Identifier in $file"
+      fi
+      break
+    fi
+  done
+done
+
+if [ "$all_files_contain_spdx" = true ]; then
+  echo "All files contain SPDX-License-Identifier."
+  exit 0
+else
+  exit 1
+fi