2018-04-09 10:32:02 +03:00
#!/usr/bin/env python
2019-09-17 14:16:32 +03:00
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
2018-04-09 10:32:02 +03:00
#
2019-09-17 14:16:32 +03:00
# http://www.apache.org/licenses/LICENSE-2.0
2018-04-09 10:32:02 +03:00
#
2019-09-17 14:16:32 +03:00
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
2018-04-09 10:32:02 +03:00
import os
import re
import string
2019-08-29 05:31:56 +03:00
import slugify
2018-04-09 10:32:02 +03:00
# order is important
_licenses = {'MIT': ['Permission is hereby granted free of charge', 'The above copyright notice and this permission notice shall'],
'BSD-3': ['Redistributions of source code must retain the above copyright', 'Redistributions in binary form must reproduce the above copyright', 'specific prior written permission'],
'BSD-2': ['Redistributions of source code must retain the above copyright', 'Redistributions in binary form must reproduce the above copyright'],
'AL': ['http://www.apache.org/licenses/LICENSE-2.0']}
def get_notices():
license_file = open("../LICENSE", "r")
2019-04-30 12:13:33 +03:00
regex = r"\((.+?)\) (.+?) \((http.+?)\)"
2018-04-09 10:32:02 +03:00
return list(filter(None, [re.findall(regex, line) for line in license_file]))
def parse_license_file(project_name):
name = re.match("^[a-z0-9\-]+", project_name.lower())
name = slugify.slugify(name.group(0))
path = "../licenses/LICENSE-{}.txt".format(name)
if os.path.exists(path):
data = " ".join(line.strip() for line in open(path)).lower()
data = data.translate(None, string.punctuation)
for k in _licenses:
matches = 0
for v in _licenses[k]:
if v.lower() in data:
matches += 1
if matches == len(_licenses[k]):
return k
return False
if __name__ == "__main__":
print("{:<30}|{:<50}||{:<20}||{:<10}"
.format("PROJECT", "URL", "LICENSE TYPE DEFINED", "DETECTED"))
notices = get_notices()
for notice in notices:
notice = notice[0]
license = parse_license_file(notice[1])
print("{:<30}|{:<50}||{:<20}||{:<10}"
.format(notice[1], notice[2][:50], notice[0], license))
file_count = len([name for name in os.listdir("../licenses")])
print("Defined licenses: {} Files found: {}".format(len(notices), file_count))