fix setup.py in python2.7

Changelog

@@ -1,3 +1,6 @@
+2019-1-20: version 0.42.1
+1. 修复setup.py在python2.7版本无法工作的问题 (issue #809)
+
 2019-1-13: version 0.42
 1. 修复paddle模式空字符串coredump问题 @JesseyXujin
 2. 修复cut_all模式切分丢字问题 @fxsjy

jieba/__init__.py

@@ -1,6 +1,6 @@
 from __future__ import absolute_import, unicode_literals
 
-__version__ = '0.42'
+__version__ = '0.42.1'
 __license__ = 'MIT'
 
 import marshal
@@ -300,7 +300,7 @@ def cut(self, sentence, cut_all=False, HMM=True, use_paddle=False):
  sentence = strdecode(sentence)
  if use_paddle and is_paddle_installed:
  # if sentence is null, it will raise core exception in paddle.
- if sentence is None or sentence == "" or sentence == u"":
+ if sentence is None or len(sentence) == 0:
  return
  import jieba.lac_small.predict as predict
  results = predict.get_sent(sentence)

setup.py

@@ -43,7 +43,7 @@
 """
 
 setup(name='jieba',
- version='0.42',
+ version='0.42.1',
  description='Chinese Words Segmentation Utilities',
  long_description=LONGDOC,
  author='Sun, Junyi',
@@ -71,5 +71,5 @@
  keywords='NLP,tokenizing,Chinese word segementation',
  packages=['jieba'],
  package_dir={'jieba':'jieba'},
- package_data={'jieba':['*.*','finalseg/*','analyse/*','posseg/*', 'lac_small/*','lac_small/model_baseline/*']}
+ package_data={'jieba':['*.*','finalseg/*','analyse/*','posseg/*', 'lac_small/*.py','lac_small/*.dic', 'lac_small/model_baseline/*']}
 )