feat: ddd SPDX IDs to repository files

.editorconfig

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
 # http://editorconfig.org/
 root = yes
 

.gitattributes

@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
 * text eol=lf
 *.jpg binary
 *.odt binary

Bylaws.md

@@ -1,3 +1,5 @@
+<!-- SPDX-License-Identifier: GPL-3.0-or-later -->
+
 # Apertium Bylaws
 
 ## Mission

README.md

@@ -5,3 +5,35 @@ This is a placeholder for whatever we make the introductory and formal entry-poi
 * [Issues suitable for newcomers](https://github.com/issues?q=is%3Aopen+is%3Aissue+org%3Aapertium+archived%3Afalse+label%3A%22good+first+issue%22) ([un-authed link](https://github.com/search?q=org%3Aapertium+label%3A%22good+first+issue%22&state=open&type=Issues))
 * [Open issues across Apertium](https://github.com/issues?q=is%3Aopen+is%3Aissue+org%3Aapertium+archived%3Afalse) ([un-authed link](https://github.com/search?q=org%3Aapertium&state=open&type=Issues))
 * [Open pull requests](https://github.com/issues?q=is%3Aopen+is%3Apr+org%3Aapertium+archived%3Afalse) ([un-authed link](https://github.com/search?q=org%3Aapertium+type%3apr&state=open&type=Issues))
+
+## Helper Script for Adding SPDX IDs
+
+We have created a helper script named `add_spdx_ids.py` to automatically add SPDX IDs to files based on their file type and existing license information. This script helps ensure that all files in the repository have the appropriate SPDX IDs.
+
+### Usage Instructions
+
+To use the `add_spdx_ids.py` script, follow these steps:
+
+1. Ensure you have Python installed on your system.
+2. Download the `add_spdx_ids.py` script from the repository.
+3. Open a terminal or command prompt.
+4. Navigate to the directory where the script is located.
+5. Run the script with the file path as an argument:
+
+   ```sh
+   python add_spdx_ids.py <file_path>
+   ```
+
+   Replace `<file_path>` with the path to the file you want to add the SPDX ID to.
+
+### Example
+
+```sh
+python add_spdx_ids.py README.md
+```
+
+This command will add the appropriate SPDX ID to the `README.md` file.
+
+### Dependencies
+
+The `add_spdx_ids.py` script requires Python 3.x to run. Ensure you have Python 3.x installed on your system before running the script.

app_spdx_ids.py

@@ -0,0 +1,81 @@
+import sys
+import os
+import logging
+
+# Set up logging
+logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')
+
+# Define comment styles for different file types
+xml_comment = '<!-- %s -->\n'
+hfst_comment = '! %s\n'
+cpp_comment = '// %s\n'
+other_comment = '# %s\n'
+
+# Define SPDX license identifiers
+license_identifiers = {
+    'GPL-3.0-or-later': 'SPDX-License-Identifier: GPL-3.0-or-later',
+    'GPL-2.0-or-later': 'SPDX-License-Identifier: GPL-2.0-or-later',
+    'GPL-3.0-only': 'SPDX-License-Identifier: GPL-3.0-only',
+    'CC0-1.0': 'SPDX-License-Identifier: CC0-1.0'
+}
+
+def get_license_identifier(file_path):
+    # Check for existing license in the file
+    with open(file_path, 'r') as f:
+        lines = f.readlines()
+        for line in lines:
+            for license_id in license_identifiers.values():
+                if license_id in line:
+                    return license_id
+
+    # Check for existing license in the repository COPYING file
+    repo_root = os.path.dirname(os.path.abspath(file_path))
+    copying_file = os.path.join(repo_root, 'COPYING')
+    if os.path.exists(copying_file):
+        with open(copying_file, 'r') as f:
+            content = f.read()
+            for license_id in license_identifiers.values():
+                if license_id in content:
+                    return license_id
+
+    # Default to GPL-3.0-or-later if no existing license is found
+    return license_identifiers['GPL-3.0-or-later']
+
+def add_spdx_id(file_path):
+    ext = os.path.splitext(file_path)[-1]
+    license_id = get_license_identifier(file_path)
+    lines = []
+
+    with open(file_path, 'r') as f:
+        lines = f.readlines()
+
+    if ext in ['.xml', '.svg']:
+        if '<?xml' not in lines[0].lower():
+            lines.insert(0, '<?xml version="1.0" encoding="UTF-8"?>\n')
+        lines.insert(1, xml_comment % license_id)
+    elif ext in ['.hfst']:
+        lines.insert(0, hfst_comment % license_id)
+    elif ext in ['.cpp', '.c', '.h']:
+        lines.insert(0, cpp_comment % license_id)
+    else:
+        n = 0
+        if lines[0].startswith('#!/'):
+            n = 1
+        lines.insert(n, other_comment % license_id)
+
+    with open(file_path, 'w') as f:
+        f.write(''.join(lines))
+
+    logging.info(f'Added SPDX ID to {file_path}')
+
+if __name__ == '__main__':
+    if len(sys.argv) < 2:
+        logging.error('Usage: python add_spdx_ids.py <file_path>')
+        sys.exit(1)
+
+    file_path = sys.argv[1]
+    if not os.path.exists(file_path):
+        logging.error(f'File not found: {file_path}')
+        sys.exit(1)
+
+    add_spdx_id(file_path)

brochure/README.md

@@ -1,3 +1,5 @@
+<!-- SPDX-License-Identifier: GPL-3.0-or-later -->
+
 # Apertium brochure
 
 The Apertium 2-sided A4 brochure (for conferences and other events) needs to be updated periodically.

posters/eamt-2016/README.md

@@ -1 +1,2 @@
+<!-- SPDX-License-Identifier: GPL-3.0-or-later -->
 # EAMT 2016 Apertium poster, recovered from Overleaf.

posters/lt4all/Makefile

@@ -1,2 +1,4 @@
-apertium-at-lt4all.pdf: apertium-at-lt4all.tex Images/pairs.pdf
-	xelatex apertium-at-lt4all.tex
+<!-- SPDX-License-Identifier: GPL-3.0-or-later -->
+# Apertium poster for LT4All
+4-6 December 2019, UNESCO, Paris.
+In progress.