clean.py

#   Copyright (c) 2019 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.
"""
Tokenizer class.
"""

from __future__ import absolute_import, division, print_function, unicode_literals

import collections
import json
import logging
import os
import sys
import unicodedata


def clean_string(string):
    replace_mp = {
        " - ": "-",
        " ' ": "'",
        " n't": "n't",
        " 'm": "'m",
        " do not": " don't",
        " 's": "'s",
        " 've": "'ve",
        " 're": "'re"
    }
    for k, v in replace_mp.items():
        string = string.replace(k, v)
    return string


def decode(string):
    string = clean_string(string.decode("utf8"))
    return string.encode("utf8")


for line in sys.stdin:
    print(decode(line.strip()))