nltkor 1.2.18__cp39-cp39-macosx_10_9_universal2.whl → 1.2.19__cp39-cp39-macosx_10_9_universal2.whl

nltkor/__init__.py

@@ -13,4 +13,4 @@ from nltkor import trans
 from nltkor import Kor_char
 from nltkor import etc
 
-__version__ = '1.2.18'
+__version__ = '1.2.19'

nltkor/search/__init__.py

@@ -8,4 +8,4 @@ from .classical import (
 )
 from .faiss_search import FaissSearch
 from .kobert_tokenizer import KoBERTTokenizer
-from .search_dict import SearchDic
+from .trie_search import TRIESearch

nltkor/search/test.py

@@ -0,0 +1,25 @@
+from trie_search import TRIESearch
+
+root = {}
+dict_file = '/Users/chanhyeok/Downloads/lexicon.txt'
+sc = TRIESearch(root)
+with open(dict_file, 'r') as f:
+    for line in f:
+        if ';;' in line[:2]: continue
+        k, v = line.strip().split('\t')
+        sc.build_trie_search(k, v)
+    # print(root)
+word = '고용 노동부'
+values, value_data = sc.trie_search(word, True)
+print(values, value_data)
+
+word = '2시뉴스외전'
+values, value_data = sc.trie_search( word, True)
+print(values, value_data)
+word = '2시 뉴스외전'
+values, value_data = sc.trie_search( word, True)
+print(values, value_data)
+
+word = 'gbc'
+values, value_data = sc.trie_search( word, True)
+print(values, value_data)

nltkor/search/{search_dict.py → trie_search.py}

@@ -4,11 +4,11 @@ import numpy as np
 import json
 import argparse
 
-class SearchDic :
+class TRIESearch :
     def __init__ (self,root) :
         self.root = root
 
-    def build_search_dict(self, word, data) -> dict:
+    def build_trie_search(self, word, data) -> dict:
         current_dict = self.root
         _end_word_ = '$$'
         for letter in word:
@@ -19,7 +19,7 @@ class SearchDic :
 
 
 
-    def search_dict(self, word, space_flag=False):
+    def trie_search(self, word, space_flag=False):
         '''
         TRIE 탐색
         space_flag: if True then including space, otherwise do not including space
@@ -69,27 +69,27 @@ class SearchDic :
             return pickle.load(f)
 if __name__ == "__main__":
     root = {}
-    dict_file = '텍스트파일경로'
-    sc = SearchDic(root)
+    dict_file = '텍스트파일 경로'
+    sc = TRIESearch(root)
     with open(dict_file, 'r') as f:
         for line in f:
             if ';;' in line[:2]: continue
             k, v = line.strip().split('\t')
-            sc.build_search_dict(k, v)
+            sc.build_trie_search(k, v)
     # print(root)
     word = '고용 노동부'
-    values, value_data = sc.search_dict(word, True)
+    values, value_data = sc.trie_search(word, True)
     print(values, value_data)
 
     word = '2시뉴스외전'
-    values, value_data = sc.search_dict( word, True)
+    values, value_data = sc.trie_search( word, True)
     print(values, value_data)
     word = '2시 뉴스외전'
-    values, value_data = sc.search_dict( word, True)
+    values, value_data = sc.trie_search( word, True)
     print(values, value_data)
 
     word = 'gbc'
-    values, value_data = sc.search_dict( word, True)
+    values, value_data = sc.trie_search( word, True)
     print(values, value_data)