修复由于python数组长度在循环判断中不改变导致的部分标点符号分词失败问题

thunlp · Feb 14, 2017 · 6a7ee99 · 6a7ee99
1 parent 64d5917
commit 6a7ee99
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/thulac/manage/Punctuation.py b/thulac/manage/Punctuation.py
@@ -10,6 +10,8 @@ def adjustSeg(self, sentence):
  return
  tmpVec = []
  for i in range(len(sentence)):
+ if(i>=len(sentence)):
+ break
  tmp = sentence[i]
  if(self.__pDat.getInfo(tmp) >= 0):
  continue
@@ -36,6 +38,8 @@ def adjustTag(self, sentence):
  tmpVec = []
  findMulti = False
  for i in range(len(sentence)):
+ if (i >= len(sentence)):
+ break
  tmp = sentence[i][0]
  if(self.__pDat.getInfo(tmp) >= 0):
  continue