Warn the user that only zh supports coarse tokenization

dumbcoder42 · May 4, 2022 · 94b88c0 · 94b88c0
1 parent 2d5aba2
commit 94b88c0
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 1 deletion.
diff --git a/plugins/hanlp_restful/hanlp_restful/__init__.py b/plugins/hanlp_restful/hanlp_restful/__init__.py
@@ -294,6 +294,9 @@ def tokenize(self, text: Union[str, List[str]], coarse: Optional[bool] = None, l
              ['2021', '年', 'HanLPv2.1', '为', '生产', '环境', '带来', '次世代', '最', '先进的',
               '多', '语种', 'NLP', '技术', '。']]
         """
+        language = language or self._language
+        if coarse and language and language != 'zh':
+            raise NotImplementedError(f'Coarse tokenization not supported for {language}. Please set language="zh".')
         doc = self.parse(text=text, tasks='tok/coarse' if coarse is True else 'tok', language=language)
         return next(iter(doc.values()))
 

diff --git a/plugins/hanlp_restful/setup.py b/plugins/hanlp_restful/setup.py
@@ -10,7 +10,7 @@
 
 setup(
     name='hanlp_restful',
-    version='0.0.15',
+    version='0.0.16',
     description='HanLP: Han Language Processing',
     long_description=long_description,
     long_description_content_type="text/markdown",