Refactors

PyMultiDictionary/_goslate.py

@@ -136,7 +136,6 @@ class Goslate(object):
         >>> print(gs_roman.translate('hello', 'zh'))
         Nín hǎo
     """
-
     _MAX_LENGTH_PER_QUERY = 1800
 
     def __init__(self, writing=WRITING_NATIVE, opener=None, retry_times=4, executor=_g_executor,
@@ -295,7 +294,7 @@ def get_languages(self):
         self._languages = languages
         return self._languages
 
-    _SEPERATORS = [quote_plus(i.encode('utf-8')) for i in
+    _SEPERATORS = [quote_plus(i.encode()) for i in
                    u'.!?,;。，？！:："“”’‘#$%&()（）*×+/<=>@＃￥[\]…［］^`{|}｛｝～~\n\r\t ']
 
     def _translate_single_text(self, text, target_language, source_lauguage):
@@ -332,7 +331,7 @@ def translate(self, text, target_language, source_language='auto'):
 
          - Input all source strings at once. Goslate will batch and fetch concurrently for maximize speed.
          - `futures <https://pypi.python.org/pypi/futures>`_ is required for best performance.
-         - It returns generator on batch input in order to better fit pipeline architecture
+         - It returns generator on batch input to better fit pipeline architecture
 
         :param text: The source text(s) to be translated. Batch translation is supported via sequence input
         :type text: UTF-8 str; unicode; string sequence (list, tuple, iterator, generator)
@@ -394,17 +393,17 @@ def translate(self, text, target_language, source_language='auto'):
 
         if not _is_sequence(text):
             if isinstance(text, str):
-                text = text.encode('utf-8')
+                text = text.encode()
             return _unwrapper_single_element(self._translate_single_text(text, target_language, source_language))
 
         JOINT = u'\u26ff'
-        UTF8_JOINT = (u'\n%s\n' % JOINT).encode('utf-8')
+        UTF8_JOINT = (u'\n%s\n' % JOINT).encode()
 
         def join_texts(texts):
             def convert_to_utf8(texts):
                 for i in texts:
                     if isinstance(i, str):
-                        i = i.encode('utf-8')
+                        i = i.encode()
                     yield i.strip()
 
             texts = convert_to_utf8(texts)
@@ -443,7 +442,7 @@ def detect(self, text):
 
          - Input all source strings at once. Goslate will detect concurrently for maximize speed.
          - `futures <https://pypi.python.org/pypi/futures>`_ is required for best performance.
-         - It returns generator on batch input in order to better fit pipeline architecture.
+         - It returns generator on batch input to better fit pipeline architecture.
 
         :param text: The source text(s) whose language you want to identify.
                      Batch detection is supported via sequence input

PyMultiDictionary/_tokenizer.py

@@ -121,7 +121,6 @@ class RegexpTokenizer(TokenizerI):
     :param flags: The regexp flags used to compile this
         tokenizer's pattern.  By default, the following flags are
         used: `re.UNICODE | re.MULTILINE | re.DOTALL`.
-
     """
 
     def __init__(

PyMultiDictionary/_utils.py

@@ -63,10 +63,14 @@
            ('no', 'Norvegese'), ('pl', 'Polacco'), ('pt', 'Portoghese'), ('ro', 'Rumeno'), ('ru', 'Russo'),
            ('sv', 'Svedese'), ('ta', 'Tamil'), ('tr', 'Turco'), ('uk', 'Ucraino'), ('vi', 'Vietnamita'),
            ('zh', 'Cinese')],
-    'ja': [('af', 'アフリカーンス語'), ('ar', 'アラビア語'), ('bn', 'ベンガル語'), ('de', 'ドイツ語'), ('el', 'ギリシャ語'), ('en', '英語'),
-           ('es', 'スペイン語'), ('fr', 'フランス語'), ('hi', 'ヒンディー語'), ('it', 'イタリア語'), ('ja', '日本語'), ('jv', 'ジャワ語'),
-           ('ko', '韓国語'), ('mr', 'マラーティー語'), ('ms', 'マレー語'), ('no', 'ノルウェー語'), ('pl', 'ポーランド語'), ('pt', 'ポルトガル語'),
-           ('ro', 'ルーマニア語'), ('ru', 'ロシア語'), ('sv', 'スウェーデン語'), ('ta', 'タミル語'), ('tr', 'トルコ語'), ('uk', 'ウクライナ語'),
+    'ja': [('af', 'アフリカーンス語'), ('ar', 'アラビア語'), ('bn', 'ベンガル語'), ('de', 'ドイツ語'),
+           ('el', 'ギリシャ語'), ('en', '英語'),
+           ('es', 'スペイン語'), ('fr', 'フランス語'), ('hi', 'ヒンディー語'), ('it', 'イタリア語'), ('ja', '日本語'),
+           ('jv', 'ジャワ語'),
+           ('ko', '韓国語'), ('mr', 'マラーティー語'), ('ms', 'マレー語'), ('no', 'ノルウェー語'),
+           ('pl', 'ポーランド語'), ('pt', 'ポルトガル語'),
+           ('ro', 'ルーマニア語'), ('ru', 'ロシア語'), ('sv', 'スウェーデン語'), ('ta', 'タミル語'), ('tr', 'トルコ語'),
+           ('uk', 'ウクライナ語'),
            ('vi', 'ベトナム語'), ('zh', '中国語')],
     'jv': [('af', 'Basa afrikaans'), ('ar', 'Basa arab'), ('bn', 'Basa bengali'), ('de', 'Basa jerman'),
            ('el', 'Basa yunani'), ('en', 'Basa inggris'), ('es', 'Basa spanyol'), ('fr', 'Basa prancis'),
@@ -130,10 +134,14 @@
            ('no', 'Норвезька'), ('pl', 'Польська'), ('pt', 'Португальська'), ('ro', 'Румунська'), ('ru', 'Російська'),
            ('sv', 'Шведська'), ('ta', 'Тамільська'), ('tr', 'Турецька'), ('uk', 'Українська'), ('vi', 'В’єтнамська'),
            ('zh', 'Китайська')],
-    'zh': [('af', '布尔语(南非荷兰语)'), ('ar', '阿拉伯语'), ('bn', '孟加拉语'), ('de', '德语'), ('el', '希腊语'), ('en', '英语'),
-           ('es', '西班牙语'), ('fr', '法语'), ('hi', '印地语'), ('it', '意大利语'), ('ja', '日语'), ('jv', '印尼爪哇语'), ('ko', '韩语'),
-           ('mr', '马拉地语'), ('ms', '马来语'), ('no', '挪威语'), ('pl', '波兰语'), ('pt', '葡萄牙语'), ('ro', '罗马尼亚语'), ('ru', '俄语'),
-           ('sv', '瑞典语'), ('ta', '泰米尔语'), ('tr', '土耳其语'), ('uk', '乌克兰语'), ('vi', '越南语'), ('zh', '中文')]
+    'zh': [('af', '布尔语(南非荷兰语)'), ('ar', '阿拉伯语'), ('bn', '孟加拉语'), ('de', '德语'), ('el', '希腊语'),
+           ('en', '英语'),
+           ('es', '西班牙语'), ('fr', '法语'), ('hi', '印地语'), ('it', '意大利语'), ('ja', '日语'),
+           ('jv', '印尼爪哇语'), ('ko', '韩语'),
+           ('mr', '马拉地语'), ('ms', '马来语'), ('no', '挪威语'), ('pl', '波兰语'), ('pt', '葡萄牙语'),
+           ('ro', '罗马尼亚语'), ('ru', '俄语'),
+           ('sv', '瑞典语'), ('ta', '泰米尔语'), ('tr', '土耳其语'), ('uk', '乌克兰语'), ('vi', '越南语'),
+           ('zh', '中文')]
 
 }
 

PyMultiDictionary/version.py

@@ -17,7 +17,7 @@ class Version(tuple):
     __slots__ = ()
     fields = 'major', 'minor', 'patch'
 
-    def __new__(cls, major, minor, patch) -> 'Version':
+    def __new__(cls, major, minor, patch) -> tuple:
         return tuple.__new__(cls, (major, minor, patch))
 
     def __repr__(self) -> str: