deepcut & dict_word_tokenize

pythainlp/corpus/words_th.txt

@@ -61186,7 +61186,6 @@
 แอกน้อย
 แอด ๆ
 แอบ ๆ
-๒,๕๔๐ รายการ
 โอ้กอ้าก
 โอฆ
 โอฆชล

pythainlp/tokenize/__init__.py

@@ -71,7 +71,7 @@ def dict_word_tokenize(
     :meth:`dict_word_tokenize` tokenizes word based on the dictionary you provide. The format has to be in trie data structure.
     :param str text: text to be tokenized
     :param dict custom_dict: a dictionary trie
-    :param str engine: choose between different options of engine to token (newmm, longest)
+    :param str engine: choose between different options of engine to token (newmm, mm, longest and deepcut)
     :return: list of words
     **Example**::
         >>> from pythainlp.tokenize import dict_word_tokenize, dict_trie
@@ -90,9 +90,11 @@ def dict_word_tokenize(
         from .longest import segment
     elif engine == "mm" or engine == "multi_cut":
         from .multi_cut import segment
+    elif engine == "deepcut":
+        from .deepcut import segment
+        return segment(text,list(custom_dict))
     else:  # default, use "newmm" engine
         from .newmm import segment
-
     return segment(text, custom_dict)
 
 

pythainlp/tokenize/deepcut.py

@@ -8,5 +8,7 @@
 import deepcut
 
 
-def segment(text: str) -> List[str]:
+def segment(text: str,dict_source:List[str]=None) -> List[str]:
+    if dict_source!=None:
+        return deepcut.tokenize(text, custom_dict=dict_source)
     return deepcut.tokenize(text)