[PR #5098/aab22e7f backport][stable-5] Add remaining copyright statements, add licenses sanity test (#5099)

* Add remaining copyright statements, add licenses sanity test (#5098)

* Add sanity test (currently fails).

* doc_fragments can also be non-GPLv3+.

* Replace 'Author:' by 'Copyright:' in some specific cases.

* Avoid matching string for license checkers.

* Reformulate not to throw license detection off.

* Add PSF copyright notice for plugins/module_utils/_mount.py.

* Add generic copyright notices.

* Update changelog fragment.

(cherry picked from commit aab22e7f32)

* Update copyright statements. (#5106)

(cherry picked from commit c8925058aa)

Co-authored-by: Felix Fontein <felix@fontein.de>

changelogs/fragments/licenses.yml

@@ -1,3 +1,3 @@
 minor_changes:
-  - "All software licenses are now in the ``LICENSES/`` directory of the collection root (https://github.com/ansible-collections/community.general/pull/5065, https://github.com/ansible-collections/community.general/pull/5079, https://github.com/ansible-collections/community.general/pull/5080, https://github.com/ansible-collections/community.general/pull/5083, https://github.com/ansible-collections/community.general/pull/5087, https://github.com/ansible-collections/community.general/pull/5095)."
+  - "All software licenses are now in the ``LICENSES/`` directory of the collection root (https://github.com/ansible-collections/community.general/pull/5065, https://github.com/ansible-collections/community.general/pull/5079, https://github.com/ansible-collections/community.general/pull/5080, https://github.com/ansible-collections/community.general/pull/5083, https://github.com/ansible-collections/community.general/pull/5087, https://github.com/ansible-collections/community.general/pull/5095, https://github.com/ansible-collections/community.general/pull/5098, https://github.com/ansible-collections/community.general/pull/5106)."
   - "Added MIT license as ``LICENSES/MIT.txt`` for tests/unit/plugins/modules/packaging/language/test_gem.py (https://github.com/ansible-collections/community.general/pull/5065)."

plugins/module_utils/_mount.py

@@ -2,6 +2,8 @@
 # This code is part of Ansible, but is an independent component.
 # This particular file snippet, and this file snippet only, is based on
 # Lib/posixpath.py of cpython
+#
+# Copyright (c) 2001-2022 Python Software Foundation.  All rights reserved.
 # It is licensed under the PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
 # (See LICENSES/PSF-2.0.txt in this collection)
 # SPDX-License-Identifier: PSF-2.0

plugins/modules/monitoring/datadog/datadog_event.py

@@ -6,6 +6,7 @@
 #
 # This module is proudly sponsored by iGeolise (www.igeolise.com) and
 # Tiny Lab Productions (www.tinylabproductions.com).
+# Copyright (c) Ansible project
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later
 

plugins/modules/monitoring/icinga2_host.py

@@ -3,6 +3,7 @@
 
 # This module is proudly sponsored by CGI (www.cgi.com) and
 # KPN (www.kpn.com).
+# Copyright (c) Ansible project
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later
 

plugins/modules/net_tools/snmp_facts.py

@@ -2,6 +2,7 @@
 # -*- coding: utf-8 -*-
 
 # This file is part of Networklore's snmp library for Ansible
+# Copyright (c) Ansible project
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later
 

tests/integration/targets/jboss/tasks/jboss.yml

@@ -4,8 +4,8 @@
 # Integration tests for jboss module.
 # SPDX-License-Identifier: GPL-3.0-or-later
 
-# helloworld.war (got from https://github.com/aeimer/java-example-helloworld-war/) license:
+# helloworld.war (got from https://github.com/aeimer/java-example-helloworld-war/) is licensed
-# MIT License
+# under the MIT license:
 #
 # Copyright (c) 2017 Alex Eimer
 #

tests/integration/targets/kernel_blacklist/tasks/main.yml

@@ -49,7 +49,7 @@
     expected_content: |
       # Copyright (c) Ansible Project
       # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
-      # SPDX-License-Identifier: GPL-3.0-or-later
+      # SPDX-{{ '' }}License-Identifier: GPL-3.0-or-later
 
       blacklist aaaa
       blacklist bbbb
@@ -76,7 +76,7 @@
     content: |
       # Copyright (c) Ansible Project
       # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
-      # SPDX-License-Identifier: GPL-3.0-or-later
+      # SPDX-{{ '' }}License-Identifier: GPL-3.0-or-later
 
       blacklist aaaa
       blacklist bbbb
@@ -104,7 +104,7 @@
     content: |
       # Copyright (c) Ansible Project
       # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
-      # SPDX-License-Identifier: GPL-3.0-or-later
+      # SPDX-{{ '' }}License-Identifier: GPL-3.0-or-later
 
       blacklist aaaa
       blacklist cccc

tests/sanity/extra/licenses.json

@@ -0,0 +1,4 @@
+{
+    "include_symlinks": false,
+    "output": "path-message"
+}

tests/sanity/extra/licenses.py

@@ -0,0 +1,113 @@
+#!/usr/bin/env python
+# Copyright (c) 2022, Felix Fontein <felix@fontein.de>
+# GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
+# SPDX-License-Identifier: GPL-3.0-or-later
+"""Prevent files without a correct license identifier from being added to the source tree."""
+from __future__ import (absolute_import, division, print_function)
+__metaclass__ = type
+
+import os
+import glob
+import sys
+
+
+def format_license_list(licenses):
+    if not licenses:
+        return '(empty)'
+    return ', '.join(['"%s"' % license for license in licenses])
+
+
+def find_licenses(filename, relax=False):
+    spdx_license_identifiers = []
+    other_license_identifiers = []
+    has_copyright = False
+    try:
+        with open(filename, 'r', encoding='utf-8') as f:
+            for line in f:
+                line = line.rstrip()
+                if 'Copyright ' in line:
+                    has_copyright = True
+                if 'Copyright: ' in line:
+                    print('%s: found copyright line with "Copyright:". Please remove the colon.' % (filename, ))
+                if 'SPDX-FileCopyrightText: ' in line:
+                    has_copyright = True
+                idx = line.find('SPDX-License-Identifier: ')
+                if idx >= 0:
+                    spdx_license_identifiers.append(line[idx + len('SPDX-License-Identifier: '):])
+                if 'GNU General Public License' in line:
+                    if 'v3.0+' in line:
+                        other_license_identifiers.append('GPL-3.0-or-later')
+                    if 'version 3 or later' in line:
+                        other_license_identifiers.append('GPL-3.0-or-later')
+                if 'Simplified BSD License' in line:
+                    other_license_identifiers.append('BSD-2-Clause')
+                if 'Apache License 2.0' in line:
+                    other_license_identifiers.append('Apache-2.0')
+                if 'PSF License' in line or 'Python-2.0' in line:
+                    other_license_identifiers.append('PSF-2.0')
+                if 'MIT License' in line:
+                    other_license_identifiers.append('MIT')
+    except Exception as exc:
+        print('%s: error while processing file: %s' % (filename, exc))
+    if len(set(spdx_license_identifiers)) < len(spdx_license_identifiers):
+        print('%s: found identical SPDX-License-Identifier values' % (filename, ))
+    if other_license_identifiers and set(other_license_identifiers) != set(spdx_license_identifiers):
+        print('%s: SPDX-License-Identifier yielded the license list %s, while manual guessing yielded the license list %s' % (
+            filename, format_license_list(spdx_license_identifiers), format_license_list(other_license_identifiers)))
+    if not has_copyright and not relax:
+        print('%s: found no copyright notice' % (filename, ))
+    return sorted(spdx_license_identifiers)
+
+
+def main():
+    """Main entry point."""
+    paths = sys.argv[1:] or sys.stdin.read().splitlines()
+
+    # The following paths are allowed to have no license identifier
+    no_comments_allowed = [
+        'changelogs/fragments/*.yml',
+        'changelogs/fragments/*.yaml',
+        'tests/sanity/extra/*.json',
+        'tests/sanity/ignore-2.*.txt',
+        'COPYING',
+    ]
+
+    # These files are completely ignored
+    ignore_paths = [
+        'CHANGELOG.rst',
+        'changelogs/changelog.yaml',
+        'tests/sanity/extra/licenses.py',  # The strings in find_licenses() confuse this code :-)
+        '.ansible-test-timeout.json',
+        'LICENSES/*.txt',
+    ]
+
+    no_comments_allowed = [fn for pattern in no_comments_allowed for fn in glob.glob(pattern)]
+    ignore_paths = [fn for pattern in ignore_paths for fn in glob.glob(pattern)]
+
+    valid_licenses = [license_file[len('LICENSES/'):-len('.txt')] for license_file in glob.glob('LICENSES/*.txt')]
+
+    for path in paths:
+        if path.startswith('./'):
+            path = path[2:]
+        if path in ignore_paths or path.startswith('tests/output/'):
+            continue
+        if os.stat(path).st_size == 0:
+            continue
+        if not path.endswith('.license') and os.path.exists(path + '.license'):
+            path = path + '.license'
+        valid_licenses_for_path = valid_licenses
+        if path.startswith('plugins/') and not path.startswith(('plugins/modules/', 'plugins/module_utils/', 'plugins/doc_fragments/')):
+            valid_licenses_for_path = [license for license in valid_licenses if license == 'GPL-3.0-or-later']
+        licenses = find_licenses(path, relax=path in no_comments_allowed)
+        if not licenses:
+            if path not in no_comments_allowed:
+                print('%s: must have at least one license' % (path, ))
+        else:
+            for license in licenses:
+                if license not in valid_licenses_for_path:
+                    print('%s: found not allowed license "%s", must be one of %s' % (
+                        path, license, format_license_list(valid_licenses_for_path)))
+
+
+if __name__ == '__main__':
+    main()

tests/unit/plugins/modules/packaging/language/test_cpanm.py

@@ -2,6 +2,9 @@
 # Largely adapted from test_redhat_subscription by
 # Jiri Hnidek (jhnidek@redhat.com)
 #
+# Copyright (c) Alexei Znamensky (russoz@gmail.com)
+# Copyright (c) Jiri Hnidek (jhnidek@redhat.com)
+#
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later
 

tests/unit/plugins/modules/packaging/os/test_redhat_subscription.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-# Author: Jiri Hnidek (jhnidek@redhat.com)
+# Copyright (c) Jiri Hnidek (jhnidek@redhat.com)
 #
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later

tests/unit/plugins/modules/system/test_gconftool2_info.py

@@ -1,5 +1,5 @@
 # -*- coding: utf-8 -*-
-# Author: Alexei Znamensky (russoz@gmail.com)
+# Copyright (c) Alexei Znamensky (russoz@gmail.com)
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later
 

tests/unit/plugins/modules/system/test_xfconf.py

@@ -3,6 +3,9 @@
 # Largely adapted from test_redhat_subscription by
 # Jiri Hnidek (jhnidek@redhat.com)
 #
+# Copyright (c) Alexei Znamensky (russoz@gmail.com)
+# Copyright (c) Jiri Hnidek (jhnidek@redhat.com)
+#
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later
 

tests/unit/plugins/modules/system/test_xfconf_info.py

@@ -1,4 +1,4 @@
-# Author: Alexei Znamensky (russoz@gmail.com)
+# Copyright (c) Alexei Znamensky (russoz@gmail.com)
 # GNU General Public License v3.0+ (see LICENSES/GPL-3.0-or-later.txt or https://www.gnu.org/licenses/gpl-3.0.txt)
 # SPDX-License-Identifier: GPL-3.0-or-later