fix

41525255 · Oct 11, 2022 · 3cbd522 · 3cbd522
1 parent 1d8096e
commit 3cbd522
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 7 deletions.
diff --git a/text/cleaners.py b/text/cleaners.py
@@ -129,20 +129,20 @@ 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'\[MD\](.*?)\[MD\]',
-                  lambda x: chinese_to_ipa2(x.group(1))+' ', text)
+    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'\[JA\](.*?)\[JA\]',
-                  lambda x: japanese_to_ipa3(x.group(1)).replace('Q','ʔ')+' ', text)
+                  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',
                   '˧˧˦').replace('6', '˩˩˧').replace('7', '˥').replace('8', '˩˨').replace('ᴀ', 'ɐ').replace('ᴇ', 'e')+' ', text)
     text = re.sub(r'\[GD\](.*?)\[GD\]',
                   lambda x: cantonese_to_ipa(x.group(1))+' ', text)
     text = re.sub(r'\[EN\](.*?)\[EN\]',
                   lambda x: english_to_lazy_ipa2(x.group(1))+' ', text)
-    text = re.sub(r'\[([A-Z]{2})\](.*?)\[\1\]',
-                  lambda x: ngu_dialect_to_ipa(x.group(2), x.group(1))+' ', text)
+    text = re.sub(r'\[([A-Z]{2})\](.*?)\[\1\]', lambda x: ngu_dialect_to_ipa(x.group(2), x.group(
+        1)).replace('ʣ', 'dz').replace('ʥ', 'dʑ').replace('ʦ', 'ts').replace('ʨ', 'tɕ')+' ', text)
     text = re.sub(r'\s+$', '', text)
     text = re.sub(r'([^\.,!\?\-…~])$', r'\1.', text)
     return text
diff --git a/text/mandarin.py b/text/mandarin.py
@@ -328,6 +328,6 @@ def chinese_to_ipa2(text, taiwanese=False):
     text = bopomofo_to_ipa2(text)
     text = re.sub(r'i([aoe])', r'j\1', text)
     text = re.sub(r'u([aoəe])', r'w\1', text)
-    text = re.sub(r'([ʂɹ]`ʰ?)([˩˨˧˦˥ ]+|$)', r'\1ʅ\2', text)
+    text = re.sub(r'([ʂɹ]ʰ?)([˩˨˧˦˥ ]+|$)', r'\1ʅ\2', text)
     text = re.sub(r'(sʰ?)([˩˨˧˦˥ ]+|$)', r'\1ɿ\2', text)
     return text
diff --git a/text/ngu_dialect.py b/text/ngu_dialect.py
@@ -11,7 +11,10 @@
 converters = {}
 
 for dialect in dialects.values():
-    converters[dialect] = opencc.OpenCC(dialect)
+    try:
+        converters[dialect] = opencc.OpenCC(dialect)
+    except:
+        pass
 
 
 def ngu_dialect_to_ipa(text, dialect):