format code

examples/text_normalization/local/test_normalization.py

@@ -1,7 +1,22 @@
+# 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 argparse
+
 from text_processing import normalization
 
-parser = argparse.ArgumentParser(description="Normalize text in Chinese with some rules.")
+parser = argparse.ArgumentParser(
+    description="Normalize text in Chinese with some rules.")
 parser.add_argument("input", type=str, help="the input sentences")
 parser.add_argument("output", type=str, help="path to save the output file.")
 args = parser.parse_args()

examples/text_normalization/path.sh

@@ -1,5 +1,4 @@
 export MAIN_ROOT=${PWD}/../../
-
 export PATH=${MAIN_ROOT}:${MAIN_ROOT}/utils:${PATH}
 export LC_ALL=C
 

examples/text_normalization/run.sh

@@ -1,5 +1,4 @@
 #!/usr/bin/env bash
-
 source path.sh
 
 stage=-1

third_party/text_processing/__ini__.py

@@ -0,0 +1 @@
+ 

third_party/text_processing/normalization/char_convert.py

@@ -2,6 +2,7 @@
 `opencc <https://github.com/BYVoid/OpenCC>`_.
 """
 
+
 import opencc
 
 _t2s_converter = opencc.OpenCC("t2s.json")
@@ -11,4 +12,4 @@ def tranditional_to_simplified(text: str) -> str:
     return _t2s_converter.convert(text)
 
 def simplified_to_traditional(text: str) -> str:
-    return _s2t_converter.convert(text)
+    return _s2t_converter.convert(text)

third_party/text_processing/normalization/chronology.py

@@ -1,6 +1,7 @@
 import re
 from .num import verbalize_cardinal, verbalize_digit, num2str, DIGITS
 
+
 def _time_num2str(num_string: str) -> str:
     """A special case for verbalizing number in time."""
     result = num2str(num_string.lstrip('0'))
@@ -60,4 +61,4 @@ def replace_date2(match: re.Match) -> str:
         result += f"{verbalize_cardinal(month)}月"
     if day:
         result += f"{verbalize_cardinal(day)}日"
-    return result
+    return result

third_party/text_processing/normalization/constants.py

@@ -2,6 +2,7 @@ import string
 import re
 from pypinyin.constants import SUPPORT_UCS4
 
+
 # 全角半角转换
 # 英文字符全角 -> 半角映射表 (num: 52)
 F2H_ASCII_LETTERS = {

third_party/text_processing/normalization/num.py

@@ -2,6 +2,7 @@
 Rules to verbalize numbers into Chinese characters.
 https://zh.wikipedia.org/wiki/中文数字#現代中文
 """
+
 import re
 from typing import List
 from collections import OrderedDict

third_party/text_processing/normalization/phone.py

@@ -1,6 +1,7 @@
 import re
 from .num import verbalize_digit
 
+
 # 规范化固话/手机号码
 # 手机
 # http://www.jihaoba.com/news/show/13680
@@ -27,4 +28,4 @@ def phone2str(phone_string: str, mobile=True) -> str:
 
 
 def replace_phone(match: re.Match) -> str:
-    return phone2str(match.group(0))
+    return phone2str(match.group(0))

third_party/text_processing/normalization/quantifier.py

@@ -1,6 +1,7 @@
 import re
 from .num import num2str
 
+
 # 温度表达式，温度会影响负号的读法
 # -3°C 零下三度
 RE_TEMPERATURE = re.compile(
@@ -14,4 +15,4 @@ def replace_temperature(match: re.Match) -> str:
     temperature: str = num2str(temperature)
     unit: str = "摄氏度" if unit == "摄氏度" else "度"
     result = f"{sign}{temperature}{unit}"
-    return result
+    return result

third_party/text_processing/normalization/sentence_split.py

@@ -1,6 +1,7 @@
 import re
 from typing import List
 
+
 SENTENCE_SPLITOR = re.compile(r'([。！？][”’]?)')
 
 def split(text: str) -> List[str]: