hooks/install/sbom_info_lib/licenses.py

# Copyright 2022 Google LLC
#
# This program is free software; you can redistribute it and/or
# modify it under the terms of the GNU General Public License
# version 2 as published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#

# This script is used to parse licenses of a package.

import re
import os

# Parse LICENSE is a ebuild.
def parse_gentoo_license(line):
    license_set = set()
    use_or = False
    res = ""
    for e in line.strip().split(" "):
        if e == "||":
            use_or = True
        elif e == "(":
            if res:
                res += "AND ("
            else:
                res += "("
        elif e == ")":
            res = f"{res[:-1]}) "
            use_or = False
        else:
            license_set.add(e)
            if not res or res.endswith("("):
                res += f"{e} "
            elif use_or:
                res += f"OR {e} "
            else:
                res += f"AND {e} "
    return res.strip(), license_set


# If a license is in license.yaml but not LICENSE,
# add it to the result.
def parse_license_yaml(yaml, res, license_set):
    lines = yaml.strip().split("\n")
    idx = lines.index("  - license_names") + 1
    match = re.findall("\{(.*?)\}", lines[idx], re.DOTALL)
    if not match:
        return res
    found = []
    for m in match:
        for part in m.split(","):
            found.append(part.split(":")[0])
    for license in found:
        license = license.strip()
        if license and not license in license_set:
            license_set.add(license)
            res += f" AND {license}"
    return res


def get_licenses(build_info_dir):
    if not os.path.exists(os.path.join(build_info_dir, "LICENSE")):
        return ""
    with open(os.path.join(build_info_dir, "LICENSE"), "r") as f:
        res, license_set = parse_gentoo_license(f.read())
        with open(os.path.join(build_info_dir, "license.yaml"), "r") as y:
            return parse_license_yaml(y.read(), res, license_set)