[GHA] Add license header check (#2781)

* [GHA] Add license header check

# Motivation

We need to make sure all code files have the appropriate license headers in place. This is currently part of the soundness check and we need to replace this with a GH action.

# Modification

Adds a new job to the reusable workflow the check all files for license headers. Since some files are ignored every repo can specify a `.licenseignore` file.

# Result

Last part of the soundness script migrated.

* Review

* Remove default excludes

.github/workflows/pull_request.yml

@@ -9,4 +9,5 @@ jobs:
     name: Checks
     uses: ./.github/workflows/reusable_pull_request.yml
     with:
-      benchmarks_linux_package_path: "Benchmarks"
+      benchmarks_linux_package_path: "Benchmarks"
+      license_header_check_project_name: "SwiftNIO"

.github/workflows/reusable_pull_request.yml

@@ -31,6 +31,14 @@ on:
         type: string
         description: "List of unacceptable words. Defaults to a sensible list of words."
         default: "blacklist whitelist slave master sane sanity insane insanity kill killed killing hang hung hanged hanging" #ignore-unacceptable-language
+      license_header_check_enabled:
+        type: boolean
+        description: "Boolean to enable the license header check job. Defaults to true."
+        default: true
+      license_header_check_project_name:
+        type: string
+        description: "Name of the project called out in the license header."
+        required: true
 
 ## We are cancelling previously triggered workflow runs
 concurrency:
@@ -137,4 +145,17 @@ jobs:
     - name: Run unacceptable language check
       env:
         UNACCEPTABLE_WORD_LIST: ${{ inputs.unacceptable_language_check_word_list}}
-      run: curl -s https://raw.githubusercontent.com/apple/swift-nio/main/scripts/check-unacceptable-language.sh | bash
+      run: curl -s https://raw.githubusercontent.com/apple/swift-nio/main/scripts/check-unacceptable-language.sh | bash
+
+  license-header-check:
+    name: License headers check
+    if: ${{ inputs.license_header_check_enabled }}
+    runs-on: ubuntu-latest
+    timeout-minutes: 1
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+    - name: Run license header check
+      env:
+        PROJECT_NAME: ${{ inputs.license_header_check_project_name }}
+      run: curl -s https://raw.githubusercontent.com/apple/swift-nio/main/scripts/check-license-header.sh | bash

.licenseignore

@@ -0,0 +1,47 @@
+.gitignore
+**/.gitignore
+.licenseignore
+.gitattributes
+.mailfilter
+.mailmap
+.spi.yml
+.swift-format
+.github/*
+*.md
+*.txt
+*.yml
+*.yaml
+*.json
+Package.swift
+**/Package.swift
+Package@-*.swift
+**/Package@-*.swift
+Package.resolved
+**/Package.resolved
+Makefile
+*.modulemap
+**/*.modulemap
+**/*.docc/*
+*.xcprivacy
+**/*.xcprivacy
+*.symlink
+**/*.symlink
+Dockerfile
+**/Dockerfile
+Snippets/*
+Sources/CNIOAtomics/src/cpp_magic.h
+Sources/CNIOLLHTTP/LICENSE-MIT
+Sources/CNIOLLHTTP/c_nio_api.c
+Sources/CNIOLLHTTP/c_nio_http.c
+Sources/CNIOLLHTTP/c_nio_llhttp.c
+Sources/CNIOLLHTTP/include/c_nio_llhttp.h
+Sources/CNIOSHA1/c_nio_sha1.c
+Sources/CNIOSHA1/include/CNIOSHA1.h
+dev/alloc-limits-from-test-output
+dev/boxed-existentials.d
+dev/git.commit.template
+dev/lldb-smoker
+dev/make-single-file-spm
+dev/malloc-aggregation.d
+dev/update-alloc-limits-to-last-completed-ci-build
+scripts/nio-diagnose

Benchmarks/Package.swift

@@ -1,17 +1,4 @@
 // swift-tools-version: 5.7
-//===----------------------------------------------------------------------===//
-//
-// This source file is part of the SwiftCertificates open source project
-//
-// Copyright (c) 2023 Apple Inc. and the SwiftCertificates project authors
-// Licensed under Apache License v2.0
-//
-// See LICENSE.txt for license information
-// See CONTRIBUTORS.txt for the list of SwiftCertificates project authors
-//
-// SPDX-License-Identifier: Apache-2.0
-//
-//===----------------------------------------------------------------------===//
 
 import PackageDescription
 

scripts/check-license-header.sh

@@ -0,0 +1,74 @@
+#!/bin/bash
+##===----------------------------------------------------------------------===##
+##
+## This source file is part of the SwiftNIO open source project
+##
+## Copyright (c) 2024 Apple Inc. and the SwiftNIO project authors
+## Licensed under Apache License v2.0
+##
+## See LICENSE.txt for license information
+## See CONTRIBUTORS.txt for the list of SwiftNIO project authors
+##
+## SPDX-License-Identifier: Apache-2.0
+##
+##===----------------------------------------------------------------------===##
+set -euo pipefail
+
+log() { printf -- "** %s\n" "$*" >&2; }
+error() { printf -- "** ERROR: %s\n" "$*" >&2; }
+fatal() { error "$@"; exit 1; }
+
+test -n "${PROJECT_NAME:-}" || fatal "PROJECT_NAME unset"
+
+expected_file_header_template="@@===----------------------------------------------------------------------===@@
+@@
+@@ This source file is part of the ${PROJECT_NAME} open source project
+@@
+@@ Copyright (c) YEARS Apple Inc. and the ${PROJECT_NAME} project authors
+@@ Licensed under Apache License v2.0
+@@
+@@ See LICENSE.txt for license information
+@@ See CONTRIBUTORS.txt for the list of ${PROJECT_NAME} project authors
+@@
+@@ SPDX-License-Identifier: Apache-2.0
+@@
+@@===----------------------------------------------------------------------===@@"
+
+paths_with_missing_license=( )
+
+file_paths=$(git ls-files $(cat .licenseignore | xargs -I% printf ":(exclude)% "))
+
+while IFS= read -r file_path; do
+  file_basename=$(basename -- "${file_path}")
+  file_extension="${file_basename##*.}"
+
+  case "${file_extension}" in
+    swift) expected_file_header=$(sed -e 's|@@|//|g' <<<"${expected_file_header_template}") ;;
+    h) expected_file_header=$(sed -e 's|@@|//|g' <<<"${expected_file_header_template}") ;;
+    c) expected_file_header=$(sed -e 's|@@|//|g' <<<"${expected_file_header_template}") ;;
+    sh) expected_file_header=$(cat <(echo '#!/bin/bash') <(sed -e 's|@@|##|g' <<<"${expected_file_header_template}")) ;;
+    py) expected_file_header=$(cat <(echo '#!/usr/bin/env python3') <(sed -e 's|@@|##|g' <<<"${expected_file_header_template}")) ;;
+    rb) expected_file_header=$(cat <(echo '#!/usr/bin/env ruby') <(sed -e 's|@@|##|g' <<<"${expected_file_header_template}")) ;;
+    *) fatal "Unsupported file extension for file (exclude or update this script): ${file_path}" ;;
+  esac
+  expected_file_header_linecount=$(wc -l <<<"${expected_file_header}")
+
+  file_header=$(head -n "${expected_file_header_linecount}" "${file_path}")
+  normalized_file_header=$(
+    echo "${file_header}" \
+    | sed -e 's/20[12][0123456789]-20[12][0123456789]/YEARS/' -e 's/20[12][0123456789]/YEARS/' \
+  )
+
+  if ! diff -u \
+    --label "Expected header" <(echo "${expected_file_header}") \
+    --label "${file_path}" <(echo "${normalized_file_header}")
+  then
+    paths_with_missing_license+=("${file_path} ")
+  fi
+done <<< "$file_paths"
+
+if [ "${#paths_with_missing_license[@]}" -gt 0 ]; then
+  fatal "❌ Found missing license header in files: ${paths_with_missing_license[*]}."
+fi
+
+log "✅ Found no files with missing license header."