.copyright.hook 3.5 KB
Newer Older
D
dzhwinter 已提交
1 2 3 4 5 6 7 8 9 10 11
from __future__ import absolute_import
from __future__ import print_function
from __future__ import unicode_literals

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

COPYRIGHT = '''
D
dzhwinter 已提交
12
  Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserved.
D
dzhwinter 已提交
13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51

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)
D
dzhwinter 已提交
52 53
    BLANK = " "
    ans = LANG_COMMENT_MARK + BLANK + COPYRIGHT_HEADER + NEW_LINE_MARK
D
dzhwinter 已提交
54 55
    for lino, line in enumerate(lines):
        if lino == 0 or lino == 1 or lino == len(lines) - 1: continue
D
dzhwinter 已提交
56 57 58 59 60
        if len(line)  == 0:
            BLANK = ""
        else:
            BLANK = " "
        ans += LANG_COMMENT_MARK + BLANK + line + NEW_LINE_MARK
D
dzhwinter 已提交
61

D
dzhwinter 已提交
62
    return ans + "\n"
D
dzhwinter 已提交
63 64 65 66 67 68 69


def lang_type(filename):
    if filename.endswith(".py"):
        return "Python"
    elif filename.endswith(".h"):
        return "C"
D
dzhwinter 已提交
70 71
    elif filename.endswith(".c"):
        return "C"
D
dzhwinter 已提交
72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
    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:
D
dzhwinter 已提交
87
        print("Unsupported filetype %s", filename)
D
dzhwinter 已提交
88 89 90
        exit(0)


D
dzhwinter 已提交
91 92 93
PYTHON_ENCODE = re.compile("^[ \t\v]*#.*?coding[:=][ \t]*([-_.a-zA-Z0-9]+)")


D
dzhwinter 已提交
94 95 96 97 98 99 100 101
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:
D
dzhwinter 已提交
102
        fd = io.open(filename, encoding="utf-8")
D
dzhwinter 已提交
103
        first_line = fd.readline()
D
dzhwinter 已提交
104 105 106 107 108 109
        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()
D
dzhwinter 已提交
110 111 112 113 114 115 116 117 118 119 120 121
        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())