bug fix, issue: #511, #512

jieba/__init__.py

@@ -40,7 +40,7 @@ re_eng = re.compile('[a-zA-Z0-9]', re.U)
 
 # \u4E00-\u9FD5a-zA-Z0-9+#&\._ : All non-space characters. Will be handled with re_han
 # \r\n|\s : whitespace characters. Will not be handled.
-re_han_default = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._]+)", re.U)
+re_han_default = re.compile("([\u4E00-\u9FD5a-zA-Z0-9+#&\._%]+)", re.U)
 re_skip_default = re.compile("(\r\n|\s)", re.U)
 re_han_cut_all = re.compile("([\u4E00-\u9FD5]+)", re.U)
 re_skip_cut_all = re.compile("[^a-zA-Z0-9+#\n]", re.U)
@@ -409,6 +409,8 @@ class Tokenizer(object):
             wfrag = word[:ch + 1]
             if wfrag not in self.FREQ:
                 self.FREQ[wfrag] = 0
+        if freq == 0:
+            finalseg.add_force_split(word)
 
     def del_word(self, word):
         """

jieba/finalseg/__init__.py

@@ -19,7 +19,7 @@ PrevStatus = {
     'E': 'BM'
 }
 
-
+Force_Split_Words = set([])
 def load_model():
     start_p = pickle.load(get_module_res("finalseg", PROB_START_P))
     trans_p = pickle.load(get_module_res("finalseg", PROB_TRANS_P))
@@ -75,16 +75,24 @@ def __cut(sentence):
         yield sentence[nexti:]
 
 re_han = re.compile("([\u4E00-\u9FD5]+)")
-re_skip = re.compile("(\d+\.\d+|[a-zA-Z0-9]+)")
+re_skip = re.compile("([a-zA-Z0-9]+(?:\.\d+)?%?)")
 
 
+def add_force_split(word):
+    global Force_Split_Words
+    Force_Split_Words.add(word)
+
 def cut(sentence):
     sentence = strdecode(sentence)
     blocks = re_han.split(sentence)
     for blk in blocks:
         if re_han.match(blk):
             for word in __cut(blk):
+                if word not in Force_Split_Words:
                     yield word
+                else:
+                    for c in word:
+                        yield c
         else:
             tmp = re_skip.split(blk)
             for x in tmp:

test/test.py

@@ -98,3 +98,5 @@ if __name__ == "__main__":
     cuttest('张三风同学走上了不归路')
     cuttest('阿Q腰间挂着BB机手里拿着大哥大，说：我一般吃饭不AA制的。')
     cuttest('在1号店能买到小S和大S八卦的书，还有3D电视。')
+    jieba.del_word('很赞')
+    cuttest('看上去iphone8手机样式很赞,售价699美元,销量涨了5%么？')