licenses.py

#!/usr/bin/env python3
# Copyright The Threadbare Authors
# SPDX-License-Identifier: MPL-2.0
import json
import subprocess
import csv
import sys
import re

NO_CREDIT_LICENSES = {
    "LicenseRef-AlkaKrab",
    "LicenseRef-AllRightsReserved",
    "LicenseRef-CathranMusic",
    "CC0-1.0",
}

CREDIT_LICENSES = {
    "CC-BY-4.0",
    "CC-BY-SA-4.0",
    "MIT",
    "MPL-2.0",
    "OFL-1.1",
}

STRIP_PREFIXES = {
    # stop reuse lint from reading this file!
    "SPDX-" + "FileCopyrightText:",
    "Copy" + "right",
}

def main() -> None:
    result = subprocess.run(("reuse", "lint", "-j"), capture_output=True)
    lint = json.loads(result.stdout)
    credits_by_license = {}

    for file in lint["files"]:
        if file["path"] == "docs/LICENSING.md":
            # This file confuses `reuse` because it contains examples of the
            # license header embedded within it.
            continue

        if len(file["spdx_expressions"]) != 1:
            raise ValueError(file)
        spdx = file["spdx_expressions"][0]
        license = spdx["value"]
        if license in NO_CREDIT_LICENSES:
            continue
        if license not in CREDIT_LICENSES:
            raise ValueError(file)

        for copyright in file["copyrights"]:
            value = copyright["value"].strip()
            for prefix in STRIP_PREFIXES:
                value = value.removeprefix(prefix).strip()

            credits_by_license.setdefault(license, set()).add(value)

    w = csv.writer(sys.stdout)
    w.writerow(["License", "Credit"])
    for license, credits in credits_by_license.items():
        for credit in credits:
            w.writerow([license, credit])


if __name__ == "__main__":
    main()