endings.py

# for python 3.5
import os, sys
import os.path
import shutil
import argparse
import argparse
import os
import sys
import glob
import tempfile

from stat import ST_ATIME, ST_MTIME

# Readme
# Source codes from here:
# https://jonlabelle.com/snippets/view/python/replace-lf-with-crlf-in-python

# #提交时转换为LF，检出时转换为CRLF
# git config --global core.autocrlf true
#
# #提交时转换为LF，检出时不转换
# git config --global core.autocrlf input
#
# #提交检出均不转换
# git config --global core.autocrlf false
#
#
# #拒绝提交包含混合换行符的文件
# git config --global core.safecrlf true
#
# # Git will always convert line endings to CRLF on checkout.
# # You should use this for files that must keep CRLF endings.
# text eol=crlf


EOL_UNIX = b'\n'
EOL_WINDOWS = b'\r\n'
EOL_MAC = b'\r'


def _read_file_data(filepath):
    """Read file data.
    :param filepath: The file path.
    :return: The file contents.
    """
    data = open(filepath, 'rb').read()
    return data


def _write_file_data(filepath, data):
    """Write file data.
    :param filepath: The file path.
    :param data: The data to write.
    """
    f = open(filepath, 'wb')
    f.write(data)
    f.close()


def _normalize_line_endings(lines, line_ending='u'):
    r"""Normalize line endings to unix (\n), windows (\r\n) or mac (\r).
    :param lines: The lines to normalize.
    :param line_ending: The line ending format.
    Acceptable values are 'unix' (default), 'windows' and 'mac'.
    :return: Line endings normalized.
    """
    lines = lines.replace(EOL_WINDOWS, EOL_UNIX).replace(EOL_MAC, EOL_UNIX)
    if line_ending == 'w':
        lines = lines.replace(EOL_UNIX, EOL_WINDOWS)
    elif line_ending == 'm':
        lines = lines.replace(EOL_UNIX, EOL_MAC)
    else:
        lines = lines.replace(EOL_UNIX, EOL_UNIX)
    return lines


def process_files(srcDir, extensions, line_ending):
    extsCount = len(extensions)
    cpyAll = False
    if extsCount == 1 and extensions[0] == '*':
        cpyAll = True
    for file in os.listdir(srcDir):
        srcFile = os.path.join(srcDir, file)
        if os.path.isfile(srcFile):
            sufix = os.path.splitext(srcFile)[1][1:]
            copyfile = False
            for index in range(extsCount):
                if sufix == extensions[index]:
                    copyfile = True
                    break
            if copyfile == True or(cpyAll == True):
                data = _read_file_data(srcFile)
                newdata = _normalize_line_endings(
                          #data.decode('utf-8')*/,
                    data,
                    line_ending=line_ending)
                if data != newdata and len(newdata) != 0:
                    print(srcFile)
                    _write_file_data(
                        srcFile,
                        #newdata.encode('utf-8'))
                        newdata)
        if os.path.isdir(srcFile):
            process_files(srcFile, exts, line_ending)


if __name__ == "__main__":
    # C:\Anaconda3\envs\py35\python.exe endings.py -i C:\Projects\arcgis-earth -ext cs,xaml - os u
    parser = argparse.ArgumentParser()
    parser.add_argument('-i', '--source_directory', type=str, help='the source directory')
    parser.add_argument('-ext', '--extensions', type=str, help='the extension you want to copy, use , to split it. If you want to keep all files, please use *')
    parser.add_argument('-os', '--operation_system', type=str, help='operation system. w: windows u: Unix m: Mac')
    args = parser.parse_args()
    params = vars(args)
    sourceDir = params['source_directory']
    exts_string= params['extensions']
    exts = exts_string.split(',')
    line_ending = params['operation_system']
    process_files(sourceDir, exts, line_ending)
    print ("ok!")