#!/usr/bin/env python
# -*- coding: utf-8 -*-
# License: FreeBSD License or The BSD 2-Clause License
# Copyright (c) 2012, Leo Jiang
# All rights reserved.
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
# Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
# Author: Leo Jiang <leo.jiang.dev@gmail.com>
# pylint: disable=I0011,C0301,W0621
"""
Loweracse Module
"""
import codecs
[docs]def lowercase_file(infile, outfile):
"""Read infile and write the lowercased sentences into outfile, support Unicode strings."""
with codecs.open(infile, 'r', encoding='utf-8') as fp_in:
with codecs.open(outfile, 'w', encoding='utf-8') as fp_out:
lowercase_fp(fp_in, fp_out)
[docs]def lowercase_fp(fin, fout):
"""Lowercase input file(fin) and output the result into output file(fout)."""
for line_in in fin:
line_out = line_in.lower()
fout.write(line_out)
if __name__ == '__main__':
import sys
with codecs.open(sys.argv[1], 'r', encoding='utf-8') as fp_in:
with codecs.open(sys.argv[2], 'w', encoding='utf-8') as fp_out:
lowercase_fp(fp_in, fp_out)