From fb64c79f7a906073279fa1ec7c2a53c329285d9c Mon Sep 17 00:00:00 2001
From: lfchener <lfchener@outlook.com>
Date: Thu, 10 Dec 2020 07:05:40 +0000
Subject: [PATCH] add normalize function in normalizer.py

---
 parakeet/frontend/normalizer/normalizer.py | 32 ++++++++++++++++++++++
 parakeet/frontend/phonectic.py             | 24 +++-------------
 2 files changed, 36 insertions(+), 20 deletions(-)

diff --git a/parakeet/frontend/normalizer/normalizer.py b/parakeet/frontend/normalizer/normalizer.py
index e69de29..96981f8 100644
--- a/parakeet/frontend/normalizer/normalizer.py
+++ b/parakeet/frontend/normalizer/normalizer.py
@@ -0,0 +1,32 @@
+# Copyright (c) 2020 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 re
+import unicodedata
+from builtins import str as unicode
+from parakeet.frontend.normalizer.numbers import normalize_numbers
+
+
+def normalize(sentence):
+    # preprocessing
+    text = unicode(text)
+    text = normalize_numbers(text)
+    text = ''.join(
+        char for char in unicodedata.normalize('NFD', text)
+        if unicodedata.category(char) != 'Mn')  # Strip accents
+    text = text.lower()
+    text = re.sub(r"[^ a-z'.,?!\-]", "", text)
+    text = text.replace("i.e.", "that is")
+    text = text.replace("e.g.", "for example")
+    return text
diff --git a/parakeet/frontend/phonectic.py b/parakeet/frontend/phonectic.py
index f814681..50cf432 100644
--- a/parakeet/frontend/phonectic.py
+++ b/parakeet/frontend/phonectic.py
@@ -16,13 +16,10 @@ from abc import ABC, abstractmethod
 from typing import Union
 from g2p_en import G2p
 from g2pM import G2pM
-import re
-import unicodedata
-from builtins import str as unicode
 from parakeet.frontend import Vocab
 from opencc import OpenCC
 from parakeet.frontend.punctuation import get_punctuations
-from parakeet.frontend.normalizer.numbers import normalize_numbers
+from parakeet.frontend.normalizer.normalizer import normalize
 
 __all__ = ["Phonetics", "English", "EnglishCharacter", "Chinese"]
 
@@ -77,29 +74,16 @@ class English(Phonetics):
 class EnglishCharacter(Phonetics):
     def __init__(self):
         self.backend = G2p()
-        self.phonemes = list(self.backend.graphemes)
+        self.graphemes = list(self.backend.graphemes)
         self.punctuations = get_punctuations("en")
-        self.vocab = Vocab(self.phonemes + self.punctuations)
-
-    def _prepocessing(self, text):
-        # preprocessing
-        text = unicode(text)
-        text = normalize_numbers(text)
-        text = ''.join(
-            char for char in unicodedata.normalize('NFD', text)
-            if unicodedata.category(char) != 'Mn')  # Strip accents
-        text = text.lower()
-        text = re.sub(r"[^ a-z'.,?!\-]", "", text)
-        text = text.replace("i.e.", "that is")
-        text = text.replace("e.g.", "for example")
-        return text
+        self.vocab = Vocab(self.graphemes + self.punctuations)
 
     def phoneticize(self, sentence):
         start = self.vocab.start_symbol
         end = self.vocab.end_symbol
 
         chars = ([] if start is None else [start]) \
-                 + _prepocessing(sentence) \
+                 + normalize(sentence) \
                  + ([] if end is None else [end])
         return chars