You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
56 lines
1.4 KiB
56 lines
1.4 KiB
# Copyright (c) 2021 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.
|
|
import codecs
|
|
import re
|
|
import unicodedata
|
|
|
|
import ujson
|
|
|
|
PAD = "<PAD>"
|
|
UNK = "<UNK>"
|
|
NUM = "<NUM>"
|
|
END = "</S>"
|
|
SPACE = "_SPACE"
|
|
|
|
|
|
def write_json(filename, dataset):
|
|
with codecs.open(filename, mode="w", encoding="utf-8") as f:
|
|
ujson.dump(dataset, f)
|
|
|
|
|
|
def word_convert(word, keep_number=True, lowercase=True):
|
|
if not keep_number:
|
|
if is_digit(word):
|
|
word = NUM
|
|
if lowercase:
|
|
word = word.lower()
|
|
return word
|
|
|
|
|
|
def is_digit(word):
|
|
try:
|
|
float(word)
|
|
return True
|
|
except ValueError:
|
|
pass
|
|
try:
|
|
unicodedata.numeric(word)
|
|
return True
|
|
except (TypeError, ValueError):
|
|
pass
|
|
result = re.compile(r'^[-+]?[0-9]+,[0-9]+$').match(word)
|
|
if result:
|
|
return True
|
|
return False
|