PaddleSpeech/.pre-commit-hooks/copyright-check.hook

# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed 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
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# 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.

import argparse
import io, re
import sys, os
import subprocess
import platform

COPYRIGHT = '''
Copyright (c) 2023 PaddlePaddle Authors. All Rights Reserved.

Licensed 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

    http://www.apache.org/licenses/LICENSE-2.0

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.
'''

LANG_COMMENT_MARK = None

NEW_LINE_MARK = None

COPYRIGHT_HEADER = None

if platform.system() == "Windows":
    NEW_LINE_MARK = "\r\n"
else:
    NEW_LINE_MARK = '\n'
    COPYRIGHT_HEADER = COPYRIGHT.split(NEW_LINE_MARK)[1]
    p = re.search('(\d{4})', COPYRIGHT_HEADER).group(0)
    process = subprocess.Popen(["date", "+%Y"], stdout=subprocess.PIPE)
    date, err = process.communicate()
    date = date.decode("utf-8").rstrip("\n")
    COPYRIGHT_HEADER = COPYRIGHT_HEADER.replace(p, date)


def generate_copyright(template, lang='C'):
    if lang == 'Python':
        LANG_COMMENT_MARK = '#'
    else:
        LANG_COMMENT_MARK = "//"

    lines = template.split(NEW_LINE_MARK)
    BLANK = " "
    ans = LANG_COMMENT_MARK + BLANK + COPYRIGHT_HEADER + NEW_LINE_MARK
    for lino, line in enumerate(lines):
        if lino == 0 or lino == 1 or lino == len(lines) - 1: continue
        if len(line)  == 0:
            BLANK = ""
        else:
            BLANK = " "
        ans += LANG_COMMENT_MARK + BLANK + line + NEW_LINE_MARK

    return ans + "\n"


def lang_type(filename):
    if filename.endswith(".py"):
        return "Python"
    elif filename.endswith(".h"):
        return "C"
    elif filename.endswith(".c"):
        return "C"
    elif filename.endswith(".hpp"):
        return "C"
    elif filename.endswith(".cc"):
        return "C"
    elif filename.endswith(".cpp"):
        return "C"
    elif filename.endswith(".cu"):
        return "C"
    elif filename.endswith(".cuh"):
        return "C"
    elif filename.endswith(".go"):
        return "C"
    elif filename.endswith(".proto"):
        return "C"
    else:
        print("Unsupported filetype %s", filename)
        exit(0)


PYTHON_ENCODE = re.compile("^[ \t\v]*#.*?coding[:=][ \t]*([-_.a-zA-Z0-9]+)")


def main(argv=None):
    parser = argparse.ArgumentParser(
        description='Checker for copyright declaration.')
    parser.add_argument('filenames', nargs='*', help='Filenames to check')
    args = parser.parse_args(argv)

    retv = 0
    for filename in args.filenames:
        fd = io.open(filename, encoding="utf-8")
        first_line = fd.readline()
        second_line = fd.readline()
        if "COPYRIGHT (C)" in first_line.upper(): continue
        if first_line.startswith("#!") or PYTHON_ENCODE.match(
                second_line) != None or PYTHON_ENCODE.match(first_line) != None:
            continue
        original_contents = io.open(filename, encoding="utf-8").read()
        new_contents = generate_copyright(
            COPYRIGHT, lang_type(filename)) + original_contents
        print('Auto Insert Copyright Header {}'.format(filename))
        retv = 1
        with io.open(filename, 'w') as output_file:
            output_file.write(new_contents)

    return retv


if __name__ == '__main__':
    exit(main())