fix

ShaoChenHeng · Oct 18, 2022 · 019af02 · 019af02
1 parent 3cbd522
commit 019af02
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 13 deletions.
diff --git a/text/cleaners.py b/text/cleaners.py
@@ -129,10 +129,8 @@ def chinese_dialect_cleaners(text):
     from text.cantonese import cantonese_to_ipa
     from text.english import english_to_lazy_ipa2
     from text.ngu_dialect import ngu_dialect_to_ipa
-    text = re.sub(r'\[(MD|ZH)\](.*?)\[\1\]',
-                  lambda x: chinese_to_ipa2(x.group(2))+' ', text)
-    text = re.sub(r'\[TW\](.*?)\[TW\]',
-                  lambda x: chinese_to_ipa2(x.group(1), True)+' ', text)
+    text = re.sub(r'\[ZH\](.*?)\[ZH\]',
+                  lambda x: chinese_to_ipa2(x.group(1))+' ', text)
     text = re.sub(r'\[JA\](.*?)\[JA\]',
                   lambda x: japanese_to_ipa3(x.group(1)).replace('Q', 'ʔ')+' ', text)
     text = re.sub(r'\[SH\](.*?)\[SH\]', lambda x: shanghainese_to_ipa(x.group(1)).replace('1', '˥˧').replace('5',

diff --git a/text/mandarin.py b/text/mandarin.py
@@ -244,7 +244,7 @@ def number_to_chinese(text):
     return text
 
 
-def chinese_to_bopomofo(text, taiwanese=False):
+def chinese_to_bopomofo(text):
     text = text.replace('、', '，').replace('；', '，').replace('：', '，')
     words = jieba.lcut(text, cut_all=False)
     text = ''
@@ -257,10 +257,7 @@ def chinese_to_bopomofo(text, taiwanese=False):
             bopomofos[i] = re.sub(r'([\u3105-\u3129])$', r'\1ˉ', bopomofos[i])
         if text != '':
             text += ' '
-        if taiwanese:
-            text += '#'+'#'.join(bopomofos)
-        else:
-            text += ''.join(bopomofos)
+        text += ''.join(bopomofos)
     return text
 
 
@@ -321,9 +318,9 @@ def chinese_to_ipa(text):
     return text
 
 
-def chinese_to_ipa2(text, taiwanese=False):
+def chinese_to_ipa2(text):
     text = number_to_chinese(text)
-    text = chinese_to_bopomofo(text, taiwanese)
+    text = chinese_to_bopomofo(text)
     text = latin_to_bopomofo(text)
     text = bopomofo_to_ipa2(text)
     text = re.sub(r'i([aoe])', r'j\1', text)

diff --git a/text/ngu_dialect.py b/text/ngu_dialect.py
@@ -5,8 +5,9 @@
 dialects = {'SZ': 'suzhou', 'WX': 'wuxi', 'CZ': 'changzhou', 'HZ': 'hangzhou',
             'SX': 'shaoxing', 'NB': 'ningbo', 'JJ': 'jingjiang', 'YX': 'yixing',
             'JD': 'jiading', 'ZR': 'zhenru', 'PH': 'pinghu', 'TX': 'tongxiang',
-            'JS': 'jiashan', 'XS': 'xiashi', 'LP': 'linping', 'XS': 'xiaoshan',
-            'FY': 'fuyang', 'RA': 'ruao', 'CX': 'cixi', 'SM': 'sanmen', 'TT': 'tiantai'}
+            'JS': 'jiashan', 'HN': 'xiashi', 'LP': 'linping', 'XS': 'xiaoshan',
+            'FY': 'fuyang', 'RA': 'ruao', 'CX': 'cixi', 'SM': 'sanmen',
+            'TT': 'tiantai', 'WZ': 'wenzhou', 'SC': 'suichang', 'YB': 'youbu'}
 
 converters = {}