#!/usr/bin/env python
# BSD 3-Clause License
#
# Copyright (c) 2017 xxxx
# All rights reserved.
# Copyright 2021 Huawei Technologies Co., Ltd
#
# 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.
#
# * Neither the name of the copyright holder nor the names of its
#   contributors may be used to endorse or promote products derived from
#   this software without specific prior written permission.
#
# 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.
# ============================================================================
#!/usr/bin/env python
# Apache 2.0

import sys
import argparse

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--exclude', '-v', dest='exclude',
                        action='store_true', help='exclude filter words')
    parser.add_argument('filt', type=str, help='filter list')
    parser.add_argument('infile', type=str, help='input file')
    args = parser.parse_args()

    vocab = set()
    with open(args.filt) as vocabfile:
        for line in vocabfile:
            vocab.add(line.strip())

    with open(args.infile) as textfile:
        for line in textfile:
            if args.exclude:
                print(" ".join(
                    map(lambda word: word if not word in vocab else '', line.strip().split())))
            # else:
            #     print(" ".join(map(lambda word: word if word in vocab else '<UNK>', unicode(line, 'utf_8').strip().split())).encode('utf_8'))