fix bug issue #132

jieba/posseg/char_state_tab.py

@@ -52545,7 +52545,7 @@ P={u'\u4e00': (('B', 'm'),
  u'\u8dd6': (('S', 'g'), ('M', 'n'), ('B', 'n'), ('E', 'nr')),
  u'\u8dd7': (('B', 'n'),),
  u'\u8dda': (('E', 'v'), ('S', 'x'), ('E', 'l'), ('E', 'nr'), ('E', 'vn')),
- u'\u8ddb': (('B', 'n'), ('B', 'v')),
+ u'\u8ddb': (('B', 'n'), ('B', 'v'), ('S','a') ),
  u'\u8ddd': (('B', 'n'),
              ('S', 'p'),
              ('E', 'n'),

jieba/posseg/viterbi.py

@@ -23,7 +23,9 @@ def viterbi(obs, states, start_p, trans_p, emit_p):
         obs_states = states.get(obs[t],all_states)
         obs_states = set(obs_states) &  set(prev_states_expect_next)
 
+        if len(obs_states)==0: obs_states = prev_states_expect_next
         if len(obs_states)==0: obs_states = all_states
+
         for y in obs_states:
             (prob,state ) = max([(V[t-1][y0] + trans_p[y0].get(y,MIN_FLOAT) + emit_p[y].get(obs[t],MIN_FLOAT) ,y0) for y0 in prev_states])
             V[t][y] =prob

test/test_bug.py

@@ -0,0 +1,9 @@
+#encoding=utf-8
+import sys
+sys.path.append("../")
+import jieba
+import jieba.posseg as pseg
+words=pseg.cut("又跛又啞")
+for w in words:
+	print w.word,w.flag
+

test/test_userdict.py

@@ -5,7 +5,7 @@ import jieba
 jieba.load_userdict("userdict.txt")
 import jieba.posseg as pseg
 
-test_sent = "李小福是创新办主任也是云计算方面的专家;"
+test_sent = "李小福是创新办主任也是云计算方面的专家; 什么是八一双鹿"
 test_sent += "例如我输入一个带“韩玉赏鉴”的标题，在自定义词库中也增加了此词为N类型"
 words = jieba.cut(test_sent)
 for w in words:

test/userdict.txt

@@ -3,4 +3,5 @@
 创新办 3 i
 easy_install 3 eng
 好用 300
-韩玉赏鉴 3 nz
+韩玉赏鉴 3 nz
+八一双鹿 3 nz