From b7504527828eb3e2377b932fe6dd5bcf1aa50a58 Mon Sep 17 00:00:00 2001
From: Edresson <edresson1@gmail.com>
Date: Mon, 27 Jul 2020 17:20:51 -0300
Subject: [PATCH] add Portuguese Cleaner

---
 mozilla_voice_tts/tts/utils/text/cleaners.py | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/mozilla_voice_tts/tts/utils/text/cleaners.py b/mozilla_voice_tts/tts/utils/text/cleaners.py
index 6d1ace08..227118e6 100644
--- a/mozilla_voice_tts/tts/utils/text/cleaners.py
+++ b/mozilla_voice_tts/tts/utils/text/cleaners.py
@@ -67,15 +67,16 @@ def remove_aux_symbols(text):
     text = re.sub(r'[\<\>\(\)\[\]\"]+', '', text)
     return text
 
-
-def replace_symbols(text):
+def replace_symbols(text, lang='en'):
     text = text.replace(';', ',')
     text = text.replace('-', ' ')
-    text = text.replace(':', ',')
-    text = text.replace('&', 'and')
+    text = text.replace(':', ' ')
+    if lang == 'en':
+        text = text.replace('&', 'and')
+    elif lang == 'pt':
+        text = text.replace('&', ' e ')
     return text
 
-
 def basic_cleaners(text):
     '''Basic pipeline that lowercases and collapses whitespace without transliteration.'''
     text = lowercase(text)
@@ -118,6 +119,14 @@ def english_cleaners(text):
     text = collapse_whitespace(text)
     return text
 
+def portuguese_cleaners(text):
+    '''Basic pipeline for Portuguese text. There is no need to expand abbreviation and 
+        numbers, phonemizer already does that'''
+    text = lowercase(text)
+    text = replace_symbols(text, lang='pt')
+    text = remove_aux_symbols(text)
+    text = collapse_whitespace(text)
+    return text
 
 def phoneme_cleaners(text):
     '''Pipeline for phonemes mode, including number and abbreviation expansion.'''